diff options
978 files changed, 27472 insertions, 9512 deletions
@@ -87,6 +87,7 @@ Baolin Wang <[email protected]> <[email protected]> Baolin Wang <[email protected]> <[email protected]> Bart Van Assche <[email protected]> <[email protected]> Bart Van Assche <[email protected]> <[email protected]> +Bartosz Golaszewski <[email protected]> <[email protected]> Ben Dooks <[email protected]> <[email protected]> Ben Dooks <[email protected]> <[email protected]> Ben Gardner <[email protected]> @@ -450,9 +451,10 @@ Oleksandr Natalenko <[email protected]> <[email protected]> Oleksij Rempel <[email protected]> <[email protected]> Oleksij Rempel <[email protected]> <[email protected]> Oleksij Rempel <[email protected]> <[email protected]> -Oleksij Rempel <[email protected]> <[email protected]> -Oleksij Rempel <[email protected]> <[email protected]> +Oleksij Rempel <[email protected]> +Oleksij Rempel <[email protected]> <[email protected]> Oliver Upton <[email protected]> <[email protected]> +Ondřej Jirman <[email protected]> <[email protected]> Oza Pawandeep <[email protected]> <[email protected]> Pali Rohár <[email protected]> <[email protected]> Paolo 'Blaisorblade' Giarrusso <[email protected]> diff --git a/Documentation/ABI/testing/sysfs-class-firmware b/Documentation/ABI/testing/sysfs-class-firmware index 978d3d500400..fba87a55f3ca 100644 --- a/Documentation/ABI/testing/sysfs-class-firmware +++ b/Documentation/ABI/testing/sysfs-class-firmware @@ -1,7 +1,7 @@ What: /sys/class/firmware/.../data Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: The data sysfs file is used for firmware-fallback and for firmware uploads. Cat a firmware image to this sysfs file after you echo 1 to the loading sysfs file. When the firmware @@ -13,7 +13,7 @@ Description: The data sysfs file is used for firmware-fallback and for What: /sys/class/firmware/.../cancel Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: Write-only. For firmware uploads, write a "1" to this file to request that the transfer of firmware data to the lower-level device be canceled. This request will be rejected (EBUSY) if @@ -23,7 +23,7 @@ Description: Write-only. For firmware uploads, write a "1" to this file to What: /sys/class/firmware/.../error Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: Read-only. Returns a string describing a failed firmware upload. This string will be in the form of <STATUS>:<ERROR>, where <STATUS> will be one of the status strings described @@ -37,7 +37,7 @@ Description: Read-only. Returns a string describing a failed firmware What: /sys/class/firmware/.../loading Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: The loading sysfs file is used for both firmware-fallback and for firmware uploads. Echo 1 onto the loading file to indicate you are writing a firmware file to the data sysfs node. Echo @@ -49,7 +49,7 @@ Description: The loading sysfs file is used for both firmware-fallback and What: /sys/class/firmware/.../remaining_size Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: Read-only. For firmware upload, this file contains the size of the firmware data that remains to be transferred to the lower-level device driver. The size value is initialized to @@ -62,7 +62,7 @@ Description: Read-only. For firmware upload, this file contains the size What: /sys/class/firmware/.../status Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: Read-only. Returns a string describing the current status of a firmware upload. The string will be one of the following: idle, "receiving", "preparing", "transferring", "programming". @@ -70,7 +70,7 @@ Description: Read-only. Returns a string describing the current status of What: /sys/class/firmware/.../timeout Date: July 2022 KernelVersion: 5.19 -Contact: Russ Weight <[email protected]> +Contact: Russ Weight <[email protected]> Description: This file supports the timeout mechanism for firmware fallback. This file has no affect on firmware uploads. For more information on timeouts please see the documentation diff --git a/Documentation/bpf/standardization/instruction-set.rst b/Documentation/bpf/standardization/instruction-set.rst index c5d53a6e8c79..245b6defc298 100644 --- a/Documentation/bpf/standardization/instruction-set.rst +++ b/Documentation/bpf/standardization/instruction-set.rst @@ -283,6 +283,14 @@ For signed operations (``BPF_SDIV`` and ``BPF_SMOD``), for ``BPF_ALU``, is first :term:`sign extended<Sign Extend>` from 32 to 64 bits, and then interpreted as a 64-bit signed value. +Note that there are varying definitions of the signed modulo operation +when the dividend or divisor are negative, where implementations often +vary by language such that Python, Ruby, etc. differ from C, Go, Java, +etc. This specification requires that signed modulo use truncated division +(where -13 % 3 == -1) as implemented in C, Go, etc.: + + a % n = a - n * trunc(a / n) + The ``BPF_MOVSX`` instruction does a move operation with sign extension. ``BPF_ALU | BPF_MOVSX`` :term:`sign extends<Sign Extend>` 8-bit and 16-bit operands into 32 bit operands, and zeroes the remaining upper 32 bits. diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst index 5d7b01aed1fe..0046af06531a 100644 --- a/Documentation/core-api/workqueue.rst +++ b/Documentation/core-api/workqueue.rst @@ -244,7 +244,7 @@ unbound worker-pools and only one work item could be active at any given time thus achieving the same ordering property as ST wq. In the current implementation the above configuration only guarantees -ST behavior within a given NUMA node. Instead ``alloc_ordered_queue()`` should +ST behavior within a given NUMA node. Instead ``alloc_ordered_workqueue()`` should be used to achieve system-wide ST behavior. @@ -390,7 +390,7 @@ The default affinity scope can be changed with the module parameter scope can be changed using ``apply_workqueue_attrs()``. If ``WQ_SYSFS`` is set, the workqueue will have the following affinity scope -related interface files under its ``/sys/devices/virtual/WQ_NAME/`` +related interface files under its ``/sys/devices/virtual/workqueue/WQ_NAME/`` directory. ``affinity_scope`` diff --git a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml index 23ada8f87526..769ce23aaac2 100644 --- a/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml +++ b/Documentation/devicetree/bindings/dma/xilinx/xlnx,zynqmp-dma-1.0.yaml @@ -13,6 +13,8 @@ description: | maintainers: - Michael Tretter <[email protected]> + - Harini Katakam <[email protected]> + - Radhey Shyam Pandey <[email protected]> allOf: - $ref: ../dma-controller.yaml# @@ -65,6 +67,7 @@ required: - interrupts - clocks - clock-names + - xlnx,bus-width additionalProperties: false diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7292.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7292.yaml index 7cc4ddc4e9b7..2aa1f4b063eb 100644 --- a/Documentation/devicetree/bindings/iio/adc/adi,ad7292.yaml +++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7292.yaml @@ -61,7 +61,7 @@ patternProperties: required: - reg - additionalProperties: true + additionalProperties: false allOf: - $ref: /schemas/spi/spi-peripheral-props.yaml# diff --git a/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml b/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml index 8376d64a641a..bed42d5d0d94 100644 --- a/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml +++ b/Documentation/devicetree/bindings/iio/light/rohm,bu27010.yaml @@ -45,5 +45,6 @@ examples: light-sensor@38 { compatible = "rohm,bu27010"; reg = <0x38>; + vdd-supply = <&vdd>; }; }; diff --git a/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml b/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml index 80141eb7fc6b..10f34aa8ba8a 100644 --- a/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml +++ b/Documentation/devicetree/bindings/mmc/sdhci-msm.yaml @@ -69,7 +69,7 @@ properties: maxItems: 4 clocks: - minItems: 3 + minItems: 2 items: - description: Main peripheral bus clock, PCLK/HCLK - AHB Bus clock - description: SDC MMC clock, MCLK diff --git a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml index 4bfac9186886..7fe0352dff0f 100644 --- a/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml +++ b/Documentation/devicetree/bindings/net/allwinner,sun8i-a83t-emac.yaml @@ -158,6 +158,8 @@ allOf: patternProperties: "^ethernet-phy@[0-9a-f]$": type: object + $ref: ethernet-phy.yaml# + unevaluatedProperties: false description: Integrated PHY node diff --git a/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml b/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml index aa3162c74833..75d8138298fb 100644 --- a/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml +++ b/Documentation/devicetree/bindings/net/brcm,asp-v2.0.yaml @@ -53,7 +53,7 @@ properties: const: 0 patternProperties: - "^port@[0-9]+$": + "^port@[0-9a-f]+$": type: object $ref: ethernet-controller.yaml# diff --git a/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml b/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml index b06c416893ff..f21bdd0f408d 100644 --- a/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml +++ b/Documentation/devicetree/bindings/net/dsa/brcm,sf2.yaml @@ -78,6 +78,7 @@ properties: ports: type: object + additionalProperties: true patternProperties: '^port@[0-9a-f]$': diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.yaml b/Documentation/devicetree/bindings/net/dsa/dsa.yaml index ec74a660beda..6107189d276a 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.yaml +++ b/Documentation/devicetree/bindings/net/dsa/dsa.yaml @@ -40,17 +40,8 @@ $defs: patternProperties: "^(ethernet-)?ports$": - type: object - additionalProperties: false - - properties: - '#address-cells': - const: 1 - '#size-cells': - const: 0 - patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-9a-f]+$": description: Ethernet switch ports $ref: dsa-port.yaml# unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml index e532c6b795f4..1c2444121e60 100644 --- a/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml +++ b/Documentation/devicetree/bindings/net/dsa/mediatek,mt7530.yaml @@ -60,7 +60,7 @@ description: | Check out example 6. - - Port 5 can be wired to an external phy. Port 5 becomes a DSA slave. + - Port 5 can be wired to an external phy. Port 5 becomes a DSA user port. For the multi-chip module MT7530, the external phy must be wired TX to TX to gmac1 of the SoC for this to work. Ubiquiti EdgeRouter X SFP is wired @@ -154,10 +154,12 @@ properties: patternProperties: "^(ethernet-)?ports$": type: object + additionalProperties: true patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-6]$": type: object + additionalProperties: true properties: reg: @@ -184,7 +186,7 @@ $defs: patternProperties: "^(ethernet-)?ports$": patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-6]$": if: required: [ ethernet ] then: @@ -210,7 +212,7 @@ $defs: patternProperties: "^(ethernet-)?ports$": patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-6]$": if: required: [ ethernet ] then: diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index 41014f5c01c4..b3029c64d0d5 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -38,6 +38,8 @@ properties: Should be a gpio specifier for a reset line. maxItems: 1 + wakeup-source: true + microchip,synclko-125: $ref: /schemas/types.yaml#/definitions/flag description: diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml index 8d7e878b84dc..9973d64f15a7 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,lan937x.yaml @@ -37,8 +37,9 @@ properties: patternProperties: "^(ethernet-)?ports$": + additionalProperties: true patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-7]$": allOf: - if: properties: diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index 4d5f5cc6d031..9432565f4f5d 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -43,6 +43,7 @@ properties: # PHY 1. mdios: type: object + additionalProperties: false properties: '#address-cells': @@ -74,8 +75,9 @@ properties: patternProperties: "^(ethernet-)?ports$": + additionalProperties: true patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-9]$": allOf: - if: properties: diff --git a/Documentation/devicetree/bindings/net/dsa/qca8k.yaml b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml index df64eebebe18..167398ab253a 100644 --- a/Documentation/devicetree/bindings/net/dsa/qca8k.yaml +++ b/Documentation/devicetree/bindings/net/dsa/qca8k.yaml @@ -73,6 +73,7 @@ $ref: dsa.yaml# patternProperties: "^(ethernet-)?ports$": type: object + additionalProperties: true patternProperties: "^(ethernet-)?port@[0-6]$": type: object diff --git a/Documentation/devicetree/bindings/net/dsa/realtek.yaml b/Documentation/devicetree/bindings/net/dsa/realtek.yaml index cfd69c2604ea..cce692f57b08 100644 --- a/Documentation/devicetree/bindings/net/dsa/realtek.yaml +++ b/Documentation/devicetree/bindings/net/dsa/realtek.yaml @@ -68,6 +68,8 @@ properties: interrupt-controller: type: object + additionalProperties: false + description: | This defines an interrupt controller with an IRQ line (typically a GPIO) that will demultiplex and handle the interrupt from the single diff --git a/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml b/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml index 833d2f68daa1..ea285ef3e64f 100644 --- a/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml +++ b/Documentation/devicetree/bindings/net/dsa/renesas,rzn1-a5psw.yaml @@ -61,17 +61,11 @@ properties: ethernet-ports: type: object - properties: - '#address-cells': - const: 1 - '#size-cells': - const: 0 - + additionalProperties: true patternProperties: "^(ethernet-)?port@[0-4]$": type: object - description: Ethernet switch ports - + additionalProperties: true properties: pcs-handle: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/engleder,tsnep.yaml b/Documentation/devicetree/bindings/net/engleder,tsnep.yaml index 82a5d7927ca4..34fd24ff6a71 100644 --- a/Documentation/devicetree/bindings/net/engleder,tsnep.yaml +++ b/Documentation/devicetree/bindings/net/engleder,tsnep.yaml @@ -63,6 +63,7 @@ properties: mdio: type: object $ref: mdio.yaml# + unevaluatedProperties: false description: optional node for embedded MDIO controller required: diff --git a/Documentation/devicetree/bindings/net/ethernet-switch.yaml b/Documentation/devicetree/bindings/net/ethernet-switch.yaml index f1b9075dc7fb..72ac67ca3415 100644 --- a/Documentation/devicetree/bindings/net/ethernet-switch.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-switch.yaml @@ -36,7 +36,7 @@ patternProperties: const: 0 patternProperties: - "^(ethernet-)?port@[0-9]+$": + "^(ethernet-)?port@[0-9a-f]+$": type: object description: Ethernet switch ports @@ -53,14 +53,16 @@ oneOf: additionalProperties: true $defs: - base: + ethernet-ports: description: An ethernet switch without any extra port properties $ref: '#' patternProperties: - "^(ethernet-)?port@[0-9]+$": - description: Ethernet switch ports - $ref: ethernet-switch-port.yaml# - unevaluatedProperties: false + "^(ethernet-)?ports$": + patternProperties: + "^(ethernet-)?port@[0-9a-f]+$": + description: Ethernet switch ports + $ref: ethernet-switch-port.yaml# + unevaluatedProperties: false ... diff --git a/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml b/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml index 8ee2c7d7ff42..86a9c3fc76c8 100644 --- a/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml +++ b/Documentation/devicetree/bindings/net/mscc,vsc7514-switch.yaml @@ -24,7 +24,7 @@ allOf: compatible: const: mscc,vsc7514-switch then: - $ref: ethernet-switch.yaml# + $ref: ethernet-switch.yaml#/$defs/ethernet-ports required: - interrupts - interrupt-names @@ -33,28 +33,18 @@ allOf: minItems: 21 reg-names: minItems: 21 - ethernet-ports: - patternProperties: - "^port@[0-9a-f]+$": - $ref: ethernet-switch-port.yaml# - unevaluatedProperties: false - if: properties: compatible: const: mscc,vsc7512-switch then: - $ref: /schemas/net/dsa/dsa.yaml# + $ref: /schemas/net/dsa/dsa.yaml#/$defs/ethernet-ports properties: reg: maxItems: 20 reg-names: maxItems: 20 - ethernet-ports: - patternProperties: - "^port@[0-9a-f]+$": - $ref: /schemas/net/dsa/dsa-port.yaml# - unevaluatedProperties: false properties: compatible: @@ -185,7 +175,7 @@ examples: }; # VSC7512 (DSA) - | - ethernet-switch@1{ + ethernet-switch@1 { compatible = "mscc,vsc7512-switch"; reg = <0x71010000 0x10000>, <0x71030000 0x10000>, @@ -212,22 +202,22 @@ examples: "port7", "port8", "port9", "port10", "qsys", "ana", "s0", "s1", "s2"; - ethernet-ports { - #address-cells = <1>; - #size-cells = <0>; - - port@0 { - reg = <0>; - ethernet = <&mac_sw>; - phy-handle = <&phy0>; - phy-mode = "internal"; - }; - port@1 { - reg = <1>; - phy-handle = <&phy1>; - phy-mode = "internal"; - }; + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + ethernet = <&mac_sw>; + phy-handle = <&phy0>; + phy-mode = "internal"; + }; + port@1 { + reg = <1>; + phy-handle = <&phy1>; + phy-mode = "internal"; }; }; + }; ... diff --git a/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml b/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml index ab8867e6939b..85bfa45f5122 100644 --- a/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml +++ b/Documentation/devicetree/bindings/net/nxp,tja11xx.yaml @@ -20,6 +20,7 @@ allOf: patternProperties: "^ethernet-phy@[0-9a-f]+$": type: object + additionalProperties: false description: | Some packages have multiple PHYs. Secondary PHY should be defines as subnode of the first (parent) PHY. diff --git a/Documentation/devicetree/bindings/net/renesas,ether.yaml b/Documentation/devicetree/bindings/net/renesas,ether.yaml index 06b38c9bc6ec..29355ab98569 100644 --- a/Documentation/devicetree/bindings/net/renesas,ether.yaml +++ b/Documentation/devicetree/bindings/net/renesas,ether.yaml @@ -81,9 +81,8 @@ properties: active-high patternProperties: - "^ethernet-phy@[0-9a-f]$": + "@[0-9a-f]$": type: object - $ref: ethernet-phy.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml index 3f41294f5997..5d074f27d462 100644 --- a/Documentation/devicetree/bindings/net/renesas,etheravb.yaml +++ b/Documentation/devicetree/bindings/net/renesas,etheravb.yaml @@ -109,9 +109,8 @@ properties: enum: [0, 2000] patternProperties: - "^ethernet-phy@[0-9a-f]$": + "@[0-9a-f]$": type: object - $ref: ethernet-phy.yaml# required: - compatible diff --git a/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml b/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml index b04ac4966608..f07ae3173b03 100644 --- a/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml +++ b/Documentation/devicetree/bindings/net/ti,cpsw-switch.yaml @@ -86,7 +86,7 @@ properties: const: 0 patternProperties: - "^port@[0-9]+$": + "^port@[12]$": type: object description: CPSW external ports diff --git a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml index 5073007267ad..634cec5d57ea 100644 --- a/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml +++ b/Documentation/devicetree/bindings/phy/qcom,ipq8074-qmp-pcie-phy.yaml @@ -70,7 +70,7 @@ examples: phy@84000 { compatible = "qcom,ipq6018-qmp-pcie-phy"; - reg = <0x0 0x00084000 0x0 0x1000>; + reg = <0x00084000 0x1000>; clocks = <&gcc GCC_PCIE0_AUX_CLK>, <&gcc GCC_PCIE0_AHB_CLK>, diff --git a/Documentation/devicetree/bindings/sound/cirrus,cs42l43.yaml b/Documentation/devicetree/bindings/sound/cirrus,cs42l43.yaml index 7a6de938b11d..4118aa54bbd5 100644 --- a/Documentation/devicetree/bindings/sound/cirrus,cs42l43.yaml +++ b/Documentation/devicetree/bindings/sound/cirrus,cs42l43.yaml @@ -82,7 +82,7 @@ properties: description: Current at which the headset micbias sense clamp will engage, 0 to disable. - enum: [ 0, 14, 23, 41, 50, 60, 68, 86, 95 ] + enum: [ 0, 14, 24, 43, 52, 61, 71, 90, 99 ] default: 0 cirrus,bias-ramp-ms: diff --git a/Documentation/filesystems/overlayfs.rst b/Documentation/filesystems/overlayfs.rst index cdefbe73d85c..5b93268e400f 100644 --- a/Documentation/filesystems/overlayfs.rst +++ b/Documentation/filesystems/overlayfs.rst @@ -339,6 +339,18 @@ The specified lower directories will be stacked beginning from the rightmost one and going left. In the above example lower1 will be the top, lower2 the middle and lower3 the bottom layer. +Note: directory names containing colons can be provided as lower layer by +escaping the colons with a single backslash. For example: + + mount -t overlay overlay -olowerdir=/a\:lower\:\:dir /merged + +Since kernel version v6.5, directory names containing colons can also +be provided as lower layer using the fsconfig syscall from new mount api: + + fsconfig(fs_fd, FSCONFIG_SET_STRING, "lowerdir", "/a:lower::dir", 0); + +In the latter case, colons in lower layer directory names will be escaped +as an octal characters (\072) when displayed in /proc/self/mountinfo. Metadata only copy up --------------------- diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index f9366aaddd21..9d13bbb7ae47 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -13,6 +13,11 @@ $defs: type: [ string, integer ] pattern: ^[0-9A-Za-z_]+( - 1)?$ minimum: 0 + len-or-limit: + # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc. + type: [ string, integer ] + pattern: ^[su](8|16|32|64)-(min|max)$ + minimum: 0 # Schema for specs title: Protocol @@ -144,7 +149,8 @@ properties: name: type: string type: &attr-type - enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64, + enum: [ unused, pad, flag, binary, + uint, sint, u8, u16, u32, u64, s32, s64, string, nest, array-nest, nest-type-value ] doc: description: Documentation of the attribute. @@ -183,13 +189,19 @@ properties: type: string min: description: Min value for an integer attribute. - type: integer + $ref: '#/$defs/len-or-limit' + max: + description: Max value for an integer attribute. + $ref: '#/$defs/len-or-limit' min-len: description: Min length for a binary attribute. $ref: '#/$defs/len-or-define' max-len: description: Max length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + exact-len: + description: Exact length for a string or a binary attribute. + $ref: '#/$defs/len-or-define' sub-type: *attr-type display-hint: &display-hint description: | @@ -283,6 +295,11 @@ properties: type: array items: enum: [ strict, dump, dump-strict ] + config-cond: + description: | + Name of the kernel config option gating the presence of + the operation, without the 'CONFIG_' prefix. + type: string do: &subop-type description: Main command handler. type: object diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml index a6a490333a1a..0daf40402a29 100644 --- a/Documentation/netlink/genetlink-legacy.yaml +++ b/Documentation/netlink/genetlink-legacy.yaml @@ -13,6 +13,11 @@ $defs: type: [ string, integer ] pattern: ^[0-9A-Za-z_]+( - 1)?$ minimum: 0 + len-or-limit: + # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc. + type: [ string, integer ] + pattern: ^[su](8|16|32|64)-(min|max)$ + minimum: 0 # Schema for specs title: Protocol @@ -187,7 +192,8 @@ properties: type: string type: &attr-type description: The netlink attribute type - enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64, + enum: [ unused, pad, flag, binary, bitfield32, + uint, sint, u8, u16, u32, u64, s32, s64, string, nest, array-nest, nest-type-value ] doc: description: Documentation of the attribute. @@ -226,13 +232,19 @@ properties: type: string min: description: Min value for an integer attribute. - type: integer + $ref: '#/$defs/len-or-limit' + max: + description: Max value for an integer attribute. + $ref: '#/$defs/len-or-limit' min-len: description: Min length for a binary attribute. $ref: '#/$defs/len-or-define' max-len: description: Max length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + exact-len: + description: Exact length for a string or a binary attribute. + $ref: '#/$defs/len-or-define' sub-type: *attr-type display-hint: *display-hint # Start genetlink-c @@ -328,12 +340,17 @@ properties: description: Command flags. type: array items: - enum: [ admin-perm ] + enum: [ admin-perm, uns-admin-perm ] dont-validate: description: Kernel attribute validation flags. type: array items: enum: [ strict, dump, dump-strict ] + config-cond: + description: | + Name of the kernel config option gating the presence of + the operation, without the 'CONFIG_' prefix. + type: string # Start genetlink-legacy fixed-header: *fixed-header # End genetlink-legacy diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index 2b788e607a14..3283bf458ff1 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -13,6 +13,11 @@ $defs: type: [ string, integer ] pattern: ^[0-9A-Za-z_]+( - 1)?$ minimum: 0 + len-or-limit: + # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc. + type: [ string, integer ] + pattern: ^[su](8|16|32|64)-(min|max)$ + minimum: 0 # Schema for specs title: Protocol @@ -117,7 +122,8 @@ properties: name: type: string type: &attr-type - enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64, + enum: [ unused, pad, flag, binary, + uint, sint, u8, u16, u32, u64, s32, s64, string, nest, array-nest, nest-type-value ] doc: description: Documentation of the attribute. @@ -156,13 +162,19 @@ properties: type: string min: description: Min value for an integer attribute. - type: integer + $ref: '#/$defs/len-or-limit' + max: + description: Max value for an integer attribute. + $ref: '#/$defs/len-or-limit' min-len: description: Min length for a binary attribute. $ref: '#/$defs/len-or-define' max-len: description: Max length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + exact-len: + description: Exact length for a string or a binary attribute. + $ref: '#/$defs/len-or-define' sub-type: *attr-type display-hint: &display-hint description: | @@ -252,6 +264,11 @@ properties: type: array items: enum: [ strict, dump, dump-strict ] + config-cond: + description: | + Name of the kernel config option gating the presence of + the operation, without the 'CONFIG_' prefix. + type: string do: &subop-type description: Main command handler. type: object diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index d976851b80f8..48db31f1d059 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -240,6 +240,9 @@ properties: max-len: description: Max length for a string or a binary attribute. $ref: '#/$defs/len-or-define' + exact-len: + description: Exact length for a string or a binary attribute. + $ref: '#/$defs/len-or-define' sub-type: *attr-type display-hint: *display-hint # Start genetlink-c diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 86a12c5bcff1..c6ba4889575a 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -15,6 +15,161 @@ definitions: name: ingress - name: egress + - + type: enum + name: port-type + entries: + - + name: notset + - + name: auto + - + name: eth + - + name: ib + - + type: enum + name: port-flavour + entries: + - + name: physical + - + name: cpu + - + name: dsa + - + name: pci_pf + - + name: pci_vf + - + name: virtual + - + name: unused + - + name: pci_sf + - + type: enum + name: port-fn-state + entries: + - + name: inactive + - + name: active + - + type: enum + name: port-fn-opstate + entries: + - + name: detached + - + name: attached + - + type: enum + name: port-fn-attr-cap + entries: + - + name: roce-bit + - + name: migratable-bit + - + type: enum + name: sb-threshold-type + entries: + - + name: static + - + name: dynamic + - + type: enum + name: eswitch-mode + entries: + - + name: legacy + - + name: switchdev + - + type: enum + name: eswitch-inline-mode + entries: + - + name: none + - + name: link + - + name: network + - + name: transport + - + type: enum + name: eswitch-encap-mode + entries: + - + name: none + - + name: basic + - + type: enum + name: dpipe-match-type + entries: + - + name: field-exact + - + type: enum + name: dpipe-action-type + entries: + - + name: field-modify + - + type: enum + name: dpipe-field-mapping-type + entries: + - + name: none + - + name: ifindex + - + type: enum + name: resource-unit + entries: + - + name: entry + - + type: enum + name: reload-action + entries: + - + name: driver-reinit + value: 1 + - + name: fw-activate + - + type: enum + name: param-cmode + entries: + - + name: runtime + - + name: driverinit + - + name: permanent + - + type: enum + name: flash-overwrite + entries: + - + name: settings-bit + - + name: identifiers-bit + - + type: enum + name: trap-action + entries: + - + name: drop + - + name: trap + - + name: mirror attribute-sets: - @@ -31,6 +186,17 @@ attribute-sets: - name: port-index type: u32 + - + name: port-type + type: u16 + enum: port-type + + # TODO: fill in the attributes in between + + - + name: port-split-count + type: u32 + value: 9 # TODO: fill in the attributes in between @@ -45,18 +211,224 @@ attribute-sets: name: sb-pool-index type: u16 value: 17 - - name: sb-pool-type type: u8 enum: sb-pool-type + - + name: sb-pool-size + type: u32 + - + name: sb-pool-threshold-type + type: u8 + enum: sb-threshold-type + - + name: sb-threshold + type: u32 + - + name: sb-tc-index + type: u16 + value: 22 # TODO: fill in the attributes in between - - name: sb-tc-index + name: eswitch-mode type: u16 - value: 22 + value: 25 + enum: eswitch-mode + + - + name: eswitch-inline-mode + type: u16 + enum: eswitch-inline-mode + - + name: dpipe-tables + type: nest + nested-attributes: dl-dpipe-tables + - + name: dpipe-table + type: nest + multi-attr: true + nested-attributes: dl-dpipe-table + - + name: dpipe-table-name + type: string + - + name: dpipe-table-size + type: u64 + - + name: dpipe-table-matches + type: nest + nested-attributes: dl-dpipe-table-matches + - + name: dpipe-table-actions + type: nest + nested-attributes: dl-dpipe-table-actions + - + name: dpipe-table-counters-enabled + type: u8 + - + name: dpipe-entries + type: nest + nested-attributes: dl-dpipe-entries + - + name: dpipe-entry + type: nest + multi-attr: true + nested-attributes: dl-dpipe-entry + - + name: dpipe-entry-index + type: u64 + - + name: dpipe-entry-match-values + type: nest + nested-attributes: dl-dpipe-entry-match-values + - + name: dpipe-entry-action-values + type: nest + nested-attributes: dl-dpipe-entry-action-values + - + name: dpipe-entry-counter + type: u64 + - + name: dpipe-match + type: nest + multi-attr: true + nested-attributes: dl-dpipe-match + - + name: dpipe-match-value + type: nest + multi-attr: true + nested-attributes: dl-dpipe-match-value + - + name: dpipe-match-type + type: u32 + enum: dpipe-match-type + - + name: dpipe-action + type: nest + multi-attr: true + nested-attributes: dl-dpipe-action + - + name: dpipe-action-value + type: nest + multi-attr: true + nested-attributes: dl-dpipe-action-value + - + name: dpipe-action-type + type: u32 + enum: dpipe-action-type + - + name: dpipe-value + type: binary + - + name: dpipe-value-mask + type: binary + - + name: dpipe-value-mapping + type: u32 + - + name: dpipe-headers + type: nest + nested-attributes: dl-dpipe-headers + - + name: dpipe-header + type: nest + multi-attr: true + nested-attributes: dl-dpipe-header + - + name: dpipe-header-name + type: string + - + name: dpipe-header-id + type: u32 + - + name: dpipe-header-fields + type: nest + nested-attributes: dl-dpipe-header-fields + - + name: dpipe-header-global + type: u8 + - + name: dpipe-header-index + type: u32 + - + name: dpipe-field + type: nest + multi-attr: true + nested-attributes: dl-dpipe-field + - + name: dpipe-field-name + type: string + - + name: dpipe-field-id + type: u32 + - + name: dpipe-field-bitwidth + type: u32 + - + name: dpipe-field-mapping-type + type: u32 + enum: dpipe-field-mapping-type + - + name: pad + type: pad + - + name: eswitch-encap-mode + type: u8 + value: 62 + enum: eswitch-encap-mode + - + name: resource-list + type: nest + nested-attributes: dl-resource-list + - + name: resource + type: nest + multi-attr: true + nested-attributes: dl-resource + - + name: resource-name + type: string + - + name: resource-id + type: u64 + - + name: resource-size + type: u64 + - + name: resource-size-new + type: u64 + - + name: resource-size-valid + type: u8 + - + name: resource-size-min + type: u64 + - + name: resource-size-max + type: u64 + - + name: resource-size-gran + type: u64 + - + name: resource-unit + type: u8 + enum: resource-unit + - + name: resource-occ + type: u64 + - + name: dpipe-table-resource-id + type: u64 + - + name: dpipe-table-resource-units + type: u64 + - + name: port-flavour + type: u16 + enum: port-flavour # TODO: fill in the attributes in between @@ -68,16 +440,40 @@ attribute-sets: # TODO: fill in the attributes in between - + name: param-type + type: u8 + value: 83 + + # TODO: fill in the attributes in between + + - + name: param-value-cmode + type: u8 + enum: param-cmode + value: 87 + - name: region-name type: string - value: 88 # TODO: fill in the attributes in between - + name: region-snapshot-id + type: u32 + value: 92 + + # TODO: fill in the attributes in between + + - + name: region-chunk-addr + type: u64 + value: 96 + - + name: region-chunk-len + type: u64 + - name: info-driver-name type: string - value: 98 - name: info-serial-number type: string @@ -106,6 +502,29 @@ attribute-sets: # TODO: fill in the attributes in between - + name: fmsg + type: nest + nested-attributes: dl-fmsg + value: 106 + - + name: fmsg-obj-nest-start + type: flag + - + name: fmsg-pair-nest-start + type: flag + - + name: fmsg-arr-nest-start + type: flag + - + name: fmsg-nest-end + type: flag + - + name: fmsg-obj-name + type: string + + # TODO: fill in the attributes in between + + - name: health-reporter-name type: string value: 115 @@ -113,9 +532,36 @@ attribute-sets: # TODO: fill in the attributes in between - + name: health-reporter-graceful-period + type: u64 + value: 120 + - + name: health-reporter-auto-recover + type: u8 + - + name: flash-update-file-name + type: string + - + name: flash-update-component + type: string + + # TODO: fill in the attributes in between + + - + name: port-pci-pf-number + type: u16 + value: 127 + + # TODO: fill in the attributes in between + + - name: trap-name type: string value: 130 + - + name: trap-action + type: u8 + enum: trap-action # TODO: fill in the attributes in between @@ -131,23 +577,68 @@ attribute-sets: # TODO: fill in the attributes in between - - name: trap-policer-id + name: netns-fd + type: u32 + value: 138 + - + name: netns-pid + type: u32 + - + name: netns-id type: u32 - value: 142 # TODO: fill in the attributes in between - - name: reload-action + name: health-reporter-auto-dump type: u8 - value: 153 + value: 141 + - + name: trap-policer-id + type: u32 + - + name: trap-policer-rate + type: u64 + - + name: trap-policer-burst + type: u64 + - + name: port-function + type: nest + nested-attributes: dl-port-function + + # TODO: fill in the attributes in between + + - + name: port-controller-number + type: u32 + value: 150 # TODO: fill in the attributes in between - + name: flash-update-overwrite-mask + type: bitfield32 + enum: flash-overwrite + enum-as-flags: True + value: 152 + - + name: reload-action + type: u8 + enum: reload-action + - + name: reload-actions-performed + type: bitfield32 + enum: reload-action + enum-as-flags: True + - + name: reload-limits + type: bitfield32 + enum: reload-action + enum-as-flags: True + - name: dev-stats type: nest - value: 156 nested-attributes: dl-dev-stats - name: reload-stats @@ -182,9 +673,25 @@ attribute-sets: # TODO: fill in the attributes in between - + name: port-pci-sf-number + type: u32 + value: 164 + + # TODO: fill in the attributes in between + + - + name: rate-tx-share + type: u64 + value: 166 + - + name: rate-tx-max + type: u64 + - name: rate-node-name type: string - value: 168 + - + name: rate-parent-node-name + type: string # TODO: fill in the attributes in between @@ -193,6 +700,30 @@ attribute-sets: type: u32 value: 171 + # TODO: fill in the attributes in between + + - + name: linecard-type + type: string + value: 173 + + # TODO: fill in the attributes in between + + - + name: selftests + type: nest + value: 176 + nested-attributes: dl-selftest-id + - + name: rate-tx-priority + type: u32 + - + name: rate-tx-weight + type: u32 + - + name: region-direct + type: flag + - name: dl-dev-stats subset-of: devlink @@ -237,6 +768,261 @@ attribute-sets: name: info-version-name - name: info-version-value + - + name: dl-port-function + name-prefix: devlink-port-fn-attr- + attr-max-name: devlink-port-function-attr-max + attributes: + - + name-prefix: devlink-port-function-attr- + name: hw-addr + type: binary + value: 1 + - + name: state + type: u8 + enum: port-fn-state + - + name: opstate + type: u8 + enum: port-fn-opstate + - + name: caps + type: bitfield32 + enum: port-fn-attr-cap + enum-as-flags: True + + - + name: dl-dpipe-tables + subset-of: devlink + attributes: + - + name: dpipe-table + + - + name: dl-dpipe-table + subset-of: devlink + attributes: + - + name: dpipe-table-name + - + name: dpipe-table-size + - + name: dpipe-table-name + - + name: dpipe-table-size + - + name: dpipe-table-matches + - + name: dpipe-table-actions + - + name: dpipe-table-counters-enabled + - + name: dpipe-table-resource-id + - + name: dpipe-table-resource-units + + - + name: dl-dpipe-table-matches + subset-of: devlink + attributes: + - + name: dpipe-match + + - + name: dl-dpipe-table-actions + subset-of: devlink + attributes: + - + name: dpipe-action + + - + name: dl-dpipe-entries + subset-of: devlink + attributes: + - + name: dpipe-entry + + - + name: dl-dpipe-entry + subset-of: devlink + attributes: + - + name: dpipe-entry-index + - + name: dpipe-entry-match-values + - + name: dpipe-entry-action-values + - + name: dpipe-entry-counter + + - + name: dl-dpipe-entry-match-values + subset-of: devlink + attributes: + - + name: dpipe-match-value + + - + name: dl-dpipe-entry-action-values + subset-of: devlink + attributes: + - + name: dpipe-action-value + + - + name: dl-dpipe-match + subset-of: devlink + attributes: + - + name: dpipe-match-type + - + name: dpipe-header-id + - + name: dpipe-header-global + - + name: dpipe-header-index + - + name: dpipe-field-id + + - + name: dl-dpipe-match-value + subset-of: devlink + attributes: + - + name: dpipe-match + - + name: dpipe-value + - + name: dpipe-value-mask + - + name: dpipe-value-mapping + + - + name: dl-dpipe-action + subset-of: devlink + attributes: + - + name: dpipe-action-type + - + name: dpipe-header-id + - + name: dpipe-header-global + - + name: dpipe-header-index + - + name: dpipe-field-id + + - + name: dl-dpipe-action-value + subset-of: devlink + attributes: + - + name: dpipe-action + - + name: dpipe-value + - + name: dpipe-value-mask + - + name: dpipe-value-mapping + + - + name: dl-dpipe-headers + subset-of: devlink + attributes: + - + name: dpipe-header + + - + name: dl-dpipe-header + subset-of: devlink + attributes: + - + name: dpipe-header-name + - + name: dpipe-header-id + - + name: dpipe-header-global + - + name: dpipe-header-fields + + - + name: dl-dpipe-header-fields + subset-of: devlink + attributes: + - + name: dpipe-field + + - + name: dl-dpipe-field + subset-of: devlink + attributes: + - + name: dpipe-field-name + - + name: dpipe-field-id + - + name: dpipe-field-bitwidth + - + name: dpipe-field-mapping-type + + - + name: dl-resource + subset-of: devlink + attributes: + # - + # name: resource-list + # This is currently unsupported due to circular dependency + - + name: resource-name + - + name: resource-id + - + name: resource-size + - + name: resource-size-new + - + name: resource-size-valid + - + name: resource-size-min + - + name: resource-size-max + - + name: resource-size-gran + - + name: resource-unit + - + name: resource-occ + + - + name: dl-resource-list + subset-of: devlink + attributes: + - + name: resource + + - + name: dl-fmsg + subset-of: devlink + attributes: + - + name: fmsg-obj-nest-start + - + name: fmsg-pair-nest-start + - + name: fmsg-arr-nest-start + - + name: fmsg-nest-end + - + name: fmsg-obj-name + + - + name: dl-selftest-id + name-prefix: devlink-attr-selftest-id- + attributes: + - + name: flash + type: flag operations: enum-model: directional @@ -245,10 +1031,7 @@ operations: name: get doc: Get devlink instances. attribute-set: devlink - dont-validate: - - strict - - dump - + dont-validate: [ strict, dump ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -263,7 +1046,6 @@ operations: - bus-name - dev-name - reload-failed - - reload-action - dev-stats dump: reply: *get-reply @@ -272,9 +1054,7 @@ operations: name: port-get doc: Get devlink port instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit-port post: devlink-nl-post-doit @@ -293,16 +1073,90 @@ operations: reply: value: 3 # due to a bug, port dump returns DEVLINK_CMD_NEW attributes: *port-id-attrs + - + name: port-set + doc: Set devlink port instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - port-index + - port-type + - port-function - # TODO: fill in the operations in between + - + name: port-new + doc: Create devlink port instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - port-index + - port-flavour + - port-pci-pf-number + - port-pci-sf-number + - port-controller-number + reply: + value: 7 + attributes: *port-id-attrs + + - + name: port-del + doc: Delete devlink port instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: *port-id-attrs + + - + name: port-split + doc: Split devlink port instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - port-index + - port-split-count + + - + name: port-unsplit + doc: Unplit devlink port instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: *port-id-attrs - name: sb-get doc: Get shared buffer instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -313,22 +1167,18 @@ operations: - dev-name - sb-index reply: &sb-get-reply - value: 11 + value: 13 attributes: *sb-id-attrs dump: request: attributes: *dev-id-attrs reply: *sb-get-reply - # TODO: fill in the operations in between - - name: sb-pool-get doc: Get shared buffer pool instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -340,22 +1190,36 @@ operations: - sb-index - sb-pool-index reply: &sb-pool-get-reply - value: 15 + value: 17 attributes: *sb-pool-id-attrs dump: request: attributes: *dev-id-attrs reply: *sb-pool-get-reply - # TODO: fill in the operations in between + - + name: sb-pool-set + doc: Set shared buffer pool instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - sb-index + - sb-pool-index + - sb-pool-threshold-type + - sb-pool-size - name: sb-port-pool-get doc: Get shared buffer port-pool combinations and threshold. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit-port post: devlink-nl-post-doit @@ -368,22 +1232,36 @@ operations: - sb-index - sb-pool-index reply: &sb-port-pool-get-reply - value: 19 + value: 21 attributes: *sb-port-pool-id-attrs dump: request: attributes: *dev-id-attrs reply: *sb-port-pool-get-reply - # TODO: fill in the operations in between + - + name: sb-port-pool-set + doc: Set shared buffer port-pool combinations and threshold. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - port-index + - sb-index + - sb-pool-index + - sb-threshold - name: sb-tc-pool-bind-get doc: Get shared buffer port-TC to pool bindings and threshold. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit-port post: devlink-nl-post-doit @@ -397,48 +1275,271 @@ operations: - sb-pool-type - sb-tc-index reply: &sb-tc-pool-bind-get-reply - value: 23 + value: 25 attributes: *sb-tc-pool-bind-id-attrs dump: request: attributes: *dev-id-attrs reply: *sb-tc-pool-bind-get-reply - # TODO: fill in the operations in between + - + name: sb-tc-pool-bind-set + doc: Set shared buffer port-TC to pool bindings and threshold. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - port-index + - sb-index + - sb-pool-index + - sb-pool-type + - sb-tc-index + - sb-threshold + + - + name: sb-occ-snapshot + doc: Take occupancy snapshot of shared buffer. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + value: 27 + attributes: + - bus-name + - dev-name + - sb-index + + - + name: sb-occ-max-clear + doc: Clear occupancy watermarks of shared buffer. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - sb-index + + - + name: eswitch-get + doc: Get eswitch attributes. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: *dev-id-attrs + reply: + value: 29 + attributes: &eswitch-attrs + - bus-name + - dev-name + - eswitch-mode + - eswitch-inline-mode + - eswitch-encap-mode + + - + name: eswitch-set + doc: Set eswitch attributes. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: *eswitch-attrs + + - + name: dpipe-table-get + doc: Get dpipe table attributes. + attribute-set: devlink + dont-validate: [ strict ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - dpipe-table-name + reply: + value: 31 + attributes: + - bus-name + - dev-name + - dpipe-tables + + - + name: dpipe-entries-get + doc: Get dpipe entries attributes. + attribute-set: devlink + dont-validate: [ strict ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - dpipe-table-name + reply: + attributes: + - bus-name + - dev-name + - dpipe-entries + + - + name: dpipe-headers-get + doc: Get dpipe headers attributes. + attribute-set: devlink + dont-validate: [ strict ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + reply: + attributes: + - bus-name + - dev-name + - dpipe-headers + + - + name: dpipe-table-counters-set + doc: Set dpipe counter attributes. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - dpipe-table-name + - dpipe-table-counters-enabled + + - + name: resource-set + doc: Set resource attributes. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - resource-id + - resource-size + + - + name: resource-dump + doc: Get resource attributes. + attribute-set: devlink + dont-validate: [ strict ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + reply: + value: 36 + attributes: + - bus-name + - dev-name + - resource-list + + - + name: reload + doc: Reload devlink. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - reload-action + - reload-limits + - netns-pid + - netns-fd + - netns-id + reply: + attributes: + - bus-name + - dev-name + - reload-actions-performed - name: param-get doc: Get param instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit request: - value: 38 attributes: ¶m-id-attrs - bus-name - dev-name - param-name reply: ¶m-get-reply - value: 38 attributes: *param-id-attrs dump: request: attributes: *dev-id-attrs reply: *param-get-reply - # TODO: fill in the operations in between + - + name: param-set + doc: Set param instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - param-name + - param-type + # param-value-data is missing here as the type is variable + - param-value-cmode - name: region-get doc: Get region instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit-port-optional post: devlink-nl-post-doit @@ -457,16 +1558,97 @@ operations: attributes: *dev-id-attrs reply: *region-get-reply - # TODO: fill in the operations in between + - + name: region-new + doc: Create region snapshot. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + value: 44 + attributes: ®ion-snapshot-id-attrs + - bus-name + - dev-name + - port-index + - region-name + - region-snapshot-id + reply: + value: 44 + attributes: *region-snapshot-id-attrs + + - + name: region-del + doc: Delete region snapshot. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + attributes: *region-snapshot-id-attrs + + - + name: region-read + doc: Read region data. + attribute-set: devlink + dont-validate: [ dump-strict ] + flags: [ admin-perm ] + dump: + request: + attributes: + - bus-name + - dev-name + - port-index + - region-name + - region-snapshot-id + - region-direct + - region-chunk-addr + - region-chunk-len + reply: + value: 46 + attributes: + - bus-name + - dev-name + - port-index + - region-name + + - + name: port-param-get + doc: Get port param instances. + attribute-set: devlink + dont-validate: [ strict, dump-strict ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: *port-id-attrs + reply: + attributes: *port-id-attrs + dump: + reply: + attributes: *port-id-attrs + + - + name: port-param-set + doc: Set port param instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port + post: devlink-nl-post-doit + request: + attributes: *port-id-attrs - name: info-get doc: Get device information, like driver name, hardware and firmware versions etc. attribute-set: devlink - dont-validate: - - strict - - dump - + dont-validate: [ strict, dump ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -490,9 +1672,7 @@ operations: name: health-reporter-get doc: Get health reporter instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit-port-optional post: devlink-nl-post-doit @@ -509,15 +1689,97 @@ operations: attributes: *port-id-attrs reply: *health-reporter-get-reply - # TODO: fill in the operations in between + - + name: health-reporter-set + doc: Set health reporter instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - port-index + - health-reporter-name + - health-reporter-graceful-period + - health-reporter-auto-recover + - health-reporter-auto-dump + + - + name: health-reporter-recover + doc: Recover health reporter instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + attributes: *health-reporter-id-attrs + + - + name: health-reporter-diagnose + doc: Diagnose health reporter instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + attributes: *health-reporter-id-attrs + + - + name: health-reporter-dump-get + doc: Dump health reporter instances. + attribute-set: devlink + dont-validate: [ dump-strict ] + flags: [ admin-perm ] + dump: + request: + attributes: *health-reporter-id-attrs + reply: + value: 56 + attributes: + - fmsg + + - + name: health-reporter-dump-clear + doc: Clear dump of health reporter instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + attributes: *health-reporter-id-attrs + + - + name: flash-update + doc: Flash update devlink instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - flash-update-file-name + - flash-update-component + - flash-update-overwrite-mask - name: trap-get doc: Get trap instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -528,22 +1790,34 @@ operations: - dev-name - trap-name reply: &trap-get-reply - value: 61 + value: 63 attributes: *trap-id-attrs dump: request: attributes: *dev-id-attrs reply: *trap-get-reply - # TODO: fill in the operations in between + - + name: trap-set + doc: Set trap instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - trap-name + - trap-action - name: trap-group-get doc: Get trap group instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -554,22 +1828,35 @@ operations: - dev-name - trap-group-name reply: &trap-group-get-reply - value: 65 + value: 67 attributes: *trap-group-id-attrs dump: request: attributes: *dev-id-attrs reply: *trap-group-get-reply - # TODO: fill in the operations in between + - + name: trap-group-set + doc: Set trap group instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - trap-group-name + - trap-action + - trap-policer-id - name: trap-policer-get doc: Get trap policer instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -580,22 +1867,48 @@ operations: - dev-name - trap-policer-id reply: &trap-policer-get-reply - value: 69 + value: 71 attributes: *trap-policer-id-attrs dump: request: attributes: *dev-id-attrs reply: *trap-policer-get-reply - # TODO: fill in the operations in between + - + name: trap-policer-set + doc: Get trap policer instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - trap-policer-id + - trap-policer-rate + - trap-policer-burst + + - + name: health-reporter-test + doc: Test health reporter instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit-port-optional + post: devlink-nl-post-doit + request: + value: 73 + attributes: *health-reporter-id-attrs - name: rate-get doc: Get rate instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -607,22 +1920,73 @@ operations: - port-index - rate-node-name reply: &rate-get-reply - value: 74 + value: 76 attributes: *rate-id-attrs dump: request: attributes: *dev-id-attrs reply: *rate-get-reply - # TODO: fill in the operations in between + - + name: rate-set + doc: Set rate instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - rate-node-name + - rate-tx-share + - rate-tx-max + - rate-tx-priority + - rate-tx-weight + - rate-parent-node-name + + - + name: rate-new + doc: Create rate instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - rate-node-name + - rate-tx-share + - rate-tx-max + - rate-tx-priority + - rate-tx-weight + - rate-parent-node-name + + - + name: rate-del + doc: Delete rate instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - rate-node-name - name: linecard-get doc: Get line card instances. attribute-set: devlink - dont-validate: - - strict - + dont-validate: [ strict ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -633,23 +1997,34 @@ operations: - dev-name - linecard-index reply: &linecard-get-reply - value: 78 + value: 80 attributes: *linecard-id-attrs dump: request: attributes: *dev-id-attrs reply: *linecard-get-reply - # TODO: fill in the operations in between + - + name: linecard-set + doc: Set line card instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - linecard-index + - linecard-type - name: selftests-get doc: Get device selftest instances. attribute-set: devlink - dont-validate: - - strict - - dump - + dont-validate: [ strict, dump ] do: pre: devlink-nl-pre-doit post: devlink-nl-post-doit @@ -661,3 +2036,18 @@ operations: attributes: *dev-id-attrs dump: reply: *selftests-get-reply + + - + name: selftests-run + doc: Run device selftest instances. + attribute-set: devlink + dont-validate: [ strict ] + flags: [ admin-perm ] + do: + pre: devlink-nl-pre-doit + post: devlink-nl-post-doit + request: + attributes: + - bus-name + - dev-name + - selftests diff --git a/Documentation/netlink/specs/mptcp.yaml b/Documentation/netlink/specs/mptcp.yaml new file mode 100644 index 000000000000..ec5c454a87ea --- /dev/null +++ b/Documentation/netlink/specs/mptcp.yaml @@ -0,0 +1,391 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: mptcp_pm +protocol: genetlink-legacy +doc: Multipath TCP. + +c-family-name: mptcp-pm-name +c-version-name: mptcp-pm-ver +max-by-define: true +kernel-policy: per-op + +definitions: + - + type: enum + name: event-type + enum-name: mptcp-event-type + name-prefix: mptcp-event- + entries: + - + name: unspec + doc: unused event + - + name: created + doc: + token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + A new MPTCP connection has been created. It is the good time to + allocate memory and send ADD_ADDR if needed. Depending on the + traffic-patterns it can take a long time until the + MPTCP_EVENT_ESTABLISHED is sent. + - + name: established + doc: + token, family, saddr4 | saddr6, daddr4 | daddr6, sport, dport + A MPTCP connection is established (can start new subflows). + - + name: closed + doc: + token + A MPTCP connection has stopped. + - + name: announced + value: 6 + doc: + token, rem_id, family, daddr4 | daddr6 [, dport] + A new address has been announced by the peer. + - + name: removed + doc: + token, rem_id + An address has been lost by the peer. + - + name: sub-established + value: 10 + doc: + token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, backup, if_idx [, error] + A new subflow has been established. 'error' should not be set. + - + name: sub-closed + doc: + token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, backup, if_idx [, error] + A subflow has been closed. An error (copy of sk_err) could be set if an + error has been detected for this subflow. + - + name: sub-priority + value: 13 + doc: + token, family, loc_id, rem_id, saddr4 | saddr6, daddr4 | daddr6, sport, + dport, backup, if_idx [, error] + The priority of a subflow has changed. 'error' should not be set. + - + name: listener-created + value: 15 + doc: + family, sport, saddr4 | saddr6 + A new PM listener is created. + - + name: listener-closed + doc: + family, sport, saddr4 | saddr6 + A PM listener is closed. + +attribute-sets: + - + name: address + name-prefix: mptcp-pm-addr-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: family + type: u16 + - + name: id + type: u8 + - + name: addr4 + type: u32 + byte-order: big-endian + - + name: addr6 + type: binary + checks: + exact-len: 16 + - + name: port + type: u16 + byte-order: big-endian + - + name: flags + type: u32 + - + name: if-idx + type: s32 + - + name: subflow-attribute + name-prefix: mptcp-subflow-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: token-rem + type: u32 + - + name: token-loc + type: u32 + - + name: relwrite-seq + type: u32 + - + name: map-seq + type: u64 + - + name: map-sfseq + type: u32 + - + name: ssn-offset + type: u32 + - + name: map-datalen + type: u16 + - + name: flags + type: u32 + - + name: id-rem + type: u8 + - + name: id-loc + type: u8 + - + name: pad + type: pad + - + name: endpoint + name-prefix: mptcp-pm-endpoint- + attributes: + - + name: addr + type: nest + nested-attributes: address + - + name: attr + name-prefix: mptcp-pm-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: addr + type: nest + nested-attributes: address + - + name: rcv-add-addrs + type: u32 + - + name: subflows + type: u32 + - + name: token + type: u32 + - + name: loc-id + type: u8 + - + name: addr-remote + type: nest + nested-attributes: address + - + name: event-attr + enum-name: mptcp-event-attr + name-prefix: mptcp-attr- + attributes: + - + name: unspec + type: unused + value: 0 + - + name: token + type: u32 + - + name: family + type: u16 + - + name: loc-id + type: u8 + - + name: rem-id + type: u8 + - + name: saddr4 + type: u32 + byte-order: big-endian + - + name: saddr6 + type: binary + checks: + min-len: 16 + - + name: daddr4 + type: u32 + byte-order: big-endian + - + name: daddr6 + type: binary + checks: + min-len: 16 + - + name: sport + type: u16 + byte-order: big-endian + - + name: dport + type: u16 + byte-order: big-endian + - + name: backup + type: u8 + - + name: error + type: u8 + - + name: flags + type: u16 + - + name: timeout + type: u32 + - + name: if_idx + type: u32 + - + name: reset-reason + type: u32 + - + name: reset-flags + type: u32 + - + name: server-side + type: u8 + +operations: + list: + - + name: unspec + doc: unused + value: 0 + - + name: add-addr + doc: Add endpoint + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &add-addr-attrs + request: + attributes: + - addr + - + name: del-addr + doc: Delete endpoint + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: *add-addr-attrs + - + name: get-addr + doc: Get endpoint information + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &get-addr-attrs + request: + attributes: + - addr + reply: + attributes: + - addr + dump: + reply: + attributes: + - addr + - + name: flush-addrs + doc: flush addresses + attribute-set: endpoint + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: *add-addr-attrs + - + name: set-limits + doc: Set protocol limits + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &mptcp-limits + request: + attributes: + - rcv-add-addrs + - subflows + - + name: get-limits + doc: Get protocol limits + attribute-set: attr + dont-validate: [ strict ] + do: &mptcp-get-limits + request: + attributes: + - rcv-add-addrs + - subflows + reply: + attributes: + - rcv-add-addrs + - subflows + - + name: set-flags + doc: Change endpoint flags + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &mptcp-set-flags + request: + attributes: + - addr + - token + - addr-remote + - + name: announce + doc: announce new sf + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &announce-add + request: + attributes: + - addr + - token + - + name: remove + doc: announce removal + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: + request: + attributes: + - token + - loc-id + - + name: subflow-create + doc: todo + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: &sf-create + request: + attributes: + - addr + - token + - addr-remote + - + name: subflow-destroy + doc: todo + attribute-set: attr + dont-validate: [ strict ] + flags: [ uns-admin-perm ] + do: *sf-create diff --git a/Documentation/networking/devlink/i40e.rst b/Documentation/networking/devlink/i40e.rst new file mode 100644 index 000000000000..d3cb5bb5197e --- /dev/null +++ b/Documentation/networking/devlink/i40e.rst @@ -0,0 +1,59 @@ +.. SPDX-License-Identifier: GPL-2.0 + +==================== +i40e devlink support +==================== + +This document describes the devlink features implemented by the ``i40e`` +device driver. + +Info versions +============= + +The ``i40e`` driver reports the following versions + +.. list-table:: devlink info versions implemented + :widths: 5 5 5 90 + + * - Name + - Type + - Example + - Description + * - ``board.id`` + - fixed + - K15190-000 + - The Product Board Assembly (PBA) identifier of the board. + * - ``fw.mgmt`` + - running + - 9.130 + - 2-digit version number of the management firmware that controls the + PHY, link, etc. + * - ``fw.mgmt.api`` + - running + - 1.15 + - 2-digit version number of the API exported over the AdminQ by the + management firmware. Used by the driver to identify what commands + are supported. + * - ``fw.mgmt.build`` + - running + - 73618 + - Build number of the source for the management firmware. + * - ``fw.undi`` + - running + - 1.3429.0 + - Version of the Option ROM containing the UEFI driver. The version is + reported in ``major.minor.patch`` format. The major version is + incremented whenever a major breaking change occurs, or when the + minor version would overflow. The minor version is incremented for + non-breaking changes and reset to 1 when the major version is + incremented. The patch version is normally 0 but is incremented when + a fix is delivered as a patch against an older base Option ROM. + * - ``fw.psid.api`` + - running + - 9.30 + - Version defining the format of the flash contents. + * - ``fw.bundle_id`` + - running + - 0x8000e5f3 + - Unique identifier of the firmware image file that was loaded onto + the device. Also referred to as the EETRACK identifier of the NVM. diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index b49749e2b9a6..e14d7a701b72 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -18,6 +18,34 @@ netlink commands. Drivers are encouraged to use the devlink instance lock for their own needs. +Drivers need to be cautious when taking devlink instance lock and +taking RTNL lock at the same time. Devlink instance lock needs to be taken +first, only after that RTNL lock could be taken. + +Nested instances +---------------- + +Some objects, like linecards or port functions, could have another +devlink instances created underneath. In that case, drivers should make +sure to respect following rules: + + - Lock ordering should be maintained. If driver needs to take instance + lock of both nested and parent instances at the same time, devlink + instance lock of the parent instance should be taken first, only then + instance lock of the nested instance could be taken. + - Driver should use object-specific helpers to setup the + nested relationship: + + - ``devl_nested_devlink_set()`` - called to setup devlink -> nested + devlink relationship (could be user for multiple nested instances. + - ``devl_port_fn_devlink_set()`` - called to setup port function -> + nested devlink relationship. + - ``devlink_linecard_nested_dl_set()`` - called to setup linecard -> + nested devlink relationship. + +The nested devlink info is exposed to the userspace over object-specific +attributes of devlink netlink. + Interface documentation ----------------------- @@ -52,6 +80,7 @@ parameters, info versions, and other features it supports. bnxt etas_es58x hns3 + i40e ionic ice mlx4 diff --git a/Documentation/networking/dsa/b53.rst b/Documentation/networking/dsa/b53.rst index b41637cdb82b..1cb3ff648f88 100644 --- a/Documentation/networking/dsa/b53.rst +++ b/Documentation/networking/dsa/b53.rst @@ -52,7 +52,7 @@ VLAN programming would basically change the CPU port's default PVID and make it untagged, undesirable. In difference to the configuration described in :ref:`dsa-vlan-configuration` -the default VLAN 1 has to be removed from the slave interface configuration in +the default VLAN 1 has to be removed from the user interface configuration in single port and gateway configuration, while there is no need to add an extra VLAN configuration in the bridge showcase. @@ -68,13 +68,13 @@ By default packages are tagged with vid 1: ip link add link eth0 name eth0.2 type vlan id 2 ip link add link eth0 name eth0.3 type vlan id 3 - # The master interface needs to be brought up before the slave ports. + # The conduit interface needs to be brought up before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up ip link set eth0.3 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -113,11 +113,11 @@ bridge # tag traffic on CPU port ip link add link eth0 name eth0.1 type vlan id 1 - # The master interface needs to be brought up before the slave ports. + # The conduit interface needs to be brought up before the user ports. ip link set eth0 up ip link set eth0.1 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -149,12 +149,12 @@ gateway ip link add link eth0 name eth0.1 type vlan id 1 ip link add link eth0 name eth0.2 type vlan id 2 - # The master interface needs to be brought up before the slave ports. + # The conduit interface needs to be brought up before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up diff --git a/Documentation/networking/dsa/bcm_sf2.rst b/Documentation/networking/dsa/bcm_sf2.rst index dee234039e1e..d2571435696f 100644 --- a/Documentation/networking/dsa/bcm_sf2.rst +++ b/Documentation/networking/dsa/bcm_sf2.rst @@ -67,7 +67,7 @@ MDIO indirect accesses ---------------------- Due to a limitation in how Broadcom switches have been designed, external -Broadcom switches connected to a SF2 require the use of the DSA slave MDIO bus +Broadcom switches connected to a SF2 require the use of the DSA user MDIO bus in order to properly configure them. By default, the SF2 pseudo-PHY address, and an external switch pseudo-PHY address will both be snooping for incoming MDIO transactions, since they are at the same address (30), resulting in some kind of diff --git a/Documentation/networking/dsa/configuration.rst b/Documentation/networking/dsa/configuration.rst index d2934c40f0f1..6cc4ded3cc23 100644 --- a/Documentation/networking/dsa/configuration.rst +++ b/Documentation/networking/dsa/configuration.rst @@ -31,38 +31,38 @@ at https://www.kernel.org/pub/linux/utils/net/iproute2/ Through DSA every port of a switch is handled like a normal linux Ethernet interface. The CPU port is the switch port connected to an Ethernet MAC chip. -The corresponding linux Ethernet interface is called the master interface. -All other corresponding linux interfaces are called slave interfaces. +The corresponding linux Ethernet interface is called the conduit interface. +All other corresponding linux interfaces are called user interfaces. -The slave interfaces depend on the master interface being up in order for them -to send or receive traffic. Prior to kernel v5.12, the state of the master +The user interfaces depend on the conduit interface being up in order for them +to send or receive traffic. Prior to kernel v5.12, the state of the conduit interface had to be managed explicitly by the user. Starting with kernel v5.12, the behavior is as follows: -- when a DSA slave interface is brought up, the master interface is +- when a DSA user interface is brought up, the conduit interface is automatically brought up. -- when the master interface is brought down, all DSA slave interfaces are +- when the conduit interface is brought down, all DSA user interfaces are automatically brought down. In this documentation the following Ethernet interfaces are used: *eth0* - the master interface + the conduit interface *eth1* - another master interface + another conduit interface *lan1* - a slave interface + a user interface *lan2* - another slave interface + another user interface *lan3* - a third slave interface + a third user interface *wan* - A slave interface dedicated for upstream traffic + A user interface dedicated for upstream traffic Further Ethernet interfaces can be configured similar. The configured IPs and networks are: @@ -96,11 +96,11 @@ without using a VLAN based configuration. ip addr add 192.0.2.5/30 dev lan2 ip addr add 192.0.2.9/30 dev lan3 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -108,11 +108,11 @@ without using a VLAN based configuration. *bridge* .. code-block:: sh - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -134,11 +134,11 @@ without using a VLAN based configuration. *gateway* .. code-block:: sh - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -178,14 +178,14 @@ configuration. ip link add link eth0 name eth0.2 type vlan id 2 ip link add link eth0 name eth0.3 type vlan id 3 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up ip link set eth0.3 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -221,12 +221,12 @@ configuration. # tag traffic on CPU port ip link add link eth0 name eth0.1 type vlan id 1 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up ip link set eth0.1 up - # bring up the slave interfaces + # bring up the user interfaces ip link set lan1 up ip link set lan2 up ip link set lan3 up @@ -261,13 +261,13 @@ configuration. ip link add link eth0 name eth0.1 type vlan id 1 ip link add link eth0 name eth0.2 type vlan id 2 - # For kernels earlier than v5.12, the master interface needs to be - # brought up manually before the slave ports. + # For kernels earlier than v5.12, the conduit interface needs to be + # brought up manually before the user ports. ip link set eth0 up ip link set eth0.1 up ip link set eth0.2 up - # bring up the slave interfaces + # bring up the user interfaces ip link set wan up ip link set lan1 up ip link set lan2 up @@ -380,22 +380,22 @@ affinities according to the available CPU ports. Secondly, it is possible to perform load balancing between CPU ports on a per packet basis, rather than statically assigning user ports to CPU ports. -This can be achieved by placing the DSA masters under a LAG interface (bonding +This can be achieved by placing the DSA conduits under a LAG interface (bonding or team). DSA monitors this operation and creates a mirror of this software LAG -on the CPU ports facing the physical DSA masters that constitute the LAG slave +on the CPU ports facing the physical DSA conduits that constitute the LAG slave devices. To make use of multiple CPU ports, the firmware (device tree) description of -the switch must mark all the links between CPU ports and their DSA masters +the switch must mark all the links between CPU ports and their DSA conduits using the ``ethernet`` reference/phandle. At startup, only a single CPU port -and DSA master will be used - the numerically first port from the firmware +and DSA conduit will be used - the numerically first port from the firmware description which has an ``ethernet`` property. It is up to the user to -configure the system for the switch to use other masters. +configure the system for the switch to use other conduits. DSA uses the ``rtnl_link_ops`` mechanism (with a "dsa" ``kind``) to allow -changing the DSA master of a user port. The ``IFLA_DSA_MASTER`` u32 netlink -attribute contains the ifindex of the master device that handles each slave -device. The DSA master must be a valid candidate based on firmware node +changing the DSA conduit of a user port. The ``IFLA_DSA_CONDUIT`` u32 netlink +attribute contains the ifindex of the conduit device that handles each user +device. The DSA conduit must be a valid candidate based on firmware node information, or a LAG interface which contains only slaves which are valid candidates. @@ -403,7 +403,7 @@ Using iproute2, the following manipulations are possible: .. code-block:: sh - # See the DSA master in current use + # See the DSA conduit in current use ip -d link show dev swp0 (...) dsa master eth0 @@ -414,7 +414,7 @@ Using iproute2, the following manipulations are possible: ip link set swp2 type dsa master eth1 ip link set swp3 type dsa master eth0 - # CPU ports in LAG, using explicit assignment of the DSA master + # CPU ports in LAG, using explicit assignment of the DSA conduit ip link add bond0 type bond mode balance-xor && ip link set bond0 up ip link set eth1 down && ip link set eth1 master bond0 ip link set swp0 type dsa master bond0 @@ -426,7 +426,7 @@ Using iproute2, the following manipulations are possible: (...) dsa master bond0 - # CPU ports in LAG, relying on implicit migration of the DSA master + # CPU ports in LAG, relying on implicit migration of the DSA conduit ip link add bond0 type bond mode balance-xor && ip link set bond0 up ip link set eth0 down && ip link set eth0 master bond0 ip link set eth1 down && ip link set eth1 master bond0 @@ -435,24 +435,24 @@ Using iproute2, the following manipulations are possible: dsa master bond0 Notice that in the case of CPU ports under a LAG, the use of the -``IFLA_DSA_MASTER`` netlink attribute is not strictly needed, but rather, DSA -reacts to the ``IFLA_MASTER`` attribute change of its present master (``eth0``) +``IFLA_DSA_CONDUIT`` netlink attribute is not strictly needed, but rather, DSA +reacts to the ``IFLA_MASTER`` attribute change of its present conduit (``eth0``) and migrates all user ports to the new upper of ``eth0``, ``bond0``. Similarly, when ``bond0`` is destroyed using ``RTM_DELLINK``, DSA migrates the user ports -that were assigned to this interface to the first physical DSA master which is +that were assigned to this interface to the first physical DSA conduit which is eligible, based on the firmware description (it effectively reverts to the startup configuration). In a setup with more than 2 physical CPU ports, it is therefore possible to mix -static user to CPU port assignment with LAG between DSA masters. It is not -possible to statically assign a user port towards a DSA master that has any -upper interfaces (this includes LAG devices - the master must always be the LAG +static user to CPU port assignment with LAG between DSA conduits. It is not +possible to statically assign a user port towards a DSA conduit that has any +upper interfaces (this includes LAG devices - the conduit must always be the LAG in this case). -Live changing of the DSA master (and thus CPU port) affinity of a user port is +Live changing of the DSA conduit (and thus CPU port) affinity of a user port is permitted, in order to allow dynamic redistribution in response to traffic. -Physical DSA masters are allowed to join and leave at any time a LAG interface -used as a DSA master; however, DSA will reject a LAG interface as a valid -candidate for being a DSA master unless it has at least one physical DSA master +Physical DSA conduits are allowed to join and leave at any time a LAG interface +used as a DSA conduit; however, DSA will reject a LAG interface as a valid +candidate for being a DSA conduit unless it has at least one physical DSA conduit as a slave device. diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index a94ddf83348a..7b2e69cd7ef0 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -25,7 +25,7 @@ presence of a management port connected to an Ethernet controller capable of receiving Ethernet frames from the switch. This is a very common setup for all kinds of Ethernet switches found in Small Home and Office products: routers, gateways, or even top-of-rack switches. This host Ethernet controller will -be later referred to as "master" and "cpu" in DSA terminology and code. +be later referred to as "conduit" and "cpu" in DSA terminology and code. The D in DSA stands for Distributed, because the subsystem has been designed with the ability to configure and manage cascaded switches on top of each other @@ -35,7 +35,7 @@ of multiple switches connected to each other is called a "switch tree". For each front-panel port, DSA creates specialized network devices which are used as controlling and data-flowing endpoints for use by the Linux networking -stack. These specialized network interfaces are referred to as "slave" network +stack. These specialized network interfaces are referred to as "user" network interfaces in DSA terminology and code. The ideal case for using DSA is when an Ethernet switch supports a "switch tag" @@ -56,12 +56,16 @@ Note that DSA does not currently create network interfaces for the "cpu" and - the "cpu" port is the Ethernet switch facing side of the management controller, and as such, would create a duplication of feature, since you - would get two interfaces for the same conduit: master netdev, and "cpu" netdev + would get two interfaces for the same conduit: conduit netdev, and "cpu" netdev - the "dsa" port(s) are just conduits between two or more switches, and as such cannot really be used as proper network interfaces either, only the downstream, or the top-most upstream interface makes sense with that model +NB: for the past 15 years, the DSA subsystem had been making use of the terms +"master" (rather than "conduit") and "slave" (rather than "user"). These terms +have been removed from the DSA codebase and phased out of the uAPI. + Switch tagging protocols ------------------------ @@ -80,14 +84,14 @@ methods of the ``struct dsa_device_ops`` structure, which are detailed below. Tagging protocols generally fall in one of three categories: 1. The switch-specific frame header is located before the Ethernet header, - shifting to the right (from the perspective of the DSA master's frame + shifting to the right (from the perspective of the DSA conduit's frame parser) the MAC DA, MAC SA, EtherType and the entire L2 payload. 2. The switch-specific frame header is located before the EtherType, keeping - the MAC DA and MAC SA in place from the DSA master's perspective, but + the MAC DA and MAC SA in place from the DSA conduit's perspective, but shifting the 'real' EtherType and L2 payload to the right. 3. The switch-specific frame header is located at the tail of the packet, keeping all frame headers in place and not altering the view of the packet - that the DSA master's frame parser has. + that the DSA conduit's frame parser has. A tagging protocol may tag all packets with switch tags of the same length, or the tag length might vary (for example packets with PTP timestamps might @@ -95,7 +99,7 @@ require an extended switch tag, or there might be one tag length on TX and a different one on RX). Either way, the tagging protocol driver must populate the ``struct dsa_device_ops::needed_headroom`` and/or ``struct dsa_device_ops::needed_tailroom`` with the length in octets of the longest switch frame header/trailer. The DSA -framework will automatically adjust the MTU of the master interface to +framework will automatically adjust the MTU of the conduit interface to accommodate for this extra size in order for DSA user ports to support the standard MTU (L2 payload length) of 1500 octets. The ``needed_headroom`` and ``needed_tailroom`` properties are also used to request from the network stack, @@ -140,18 +144,18 @@ adding or removing the ``ETH_P_EDSA`` EtherType and some padding octets). It is possible to construct cascaded setups of DSA switches even if their tagging protocols are not compatible with one another. In this case, there are no DSA links in this fabric, and each switch constitutes a disjoint DSA switch -tree. The DSA links are viewed as simply a pair of a DSA master (the out-facing +tree. The DSA links are viewed as simply a pair of a DSA conduit (the out-facing port of the upstream DSA switch) and a CPU port (the in-facing port of the downstream DSA switch). The tagging protocol of the attached DSA switch tree can be viewed through the -``dsa/tagging`` sysfs attribute of the DSA master:: +``dsa/tagging`` sysfs attribute of the DSA conduit:: cat /sys/class/net/eth0/dsa/tagging If the hardware and driver are capable, the tagging protocol of the DSA switch tree can be changed at runtime. This is done by writing the new tagging -protocol name to the same sysfs device attribute as above (the DSA master and +protocol name to the same sysfs device attribute as above (the DSA conduit and all attached switch ports must be down while doing this). It is desirable that all tagging protocols are testable with the ``dsa_loop`` @@ -159,7 +163,7 @@ mockup driver, which can be attached to any network interface. The goal is that any network interface should be capable of transmitting the same packet in the same way, and the tagger should decode the same received packet in the same way regardless of the driver used for the switch control path, and the driver used -for the DSA master. +for the DSA conduit. The transmission of a packet goes through the tagger's ``xmit`` function. The passed ``struct sk_buff *skb`` has ``skb->data`` pointing at @@ -183,44 +187,44 @@ virtual DSA user network interface corresponding to the physical front-facing switch port that the packet was received on. Since tagging protocols in category 1 and 2 break software (and most often also -hardware) packet dissection on the DSA master, features such as RPS (Receive -Packet Steering) on the DSA master would be broken. The DSA framework deals +hardware) packet dissection on the DSA conduit, features such as RPS (Receive +Packet Steering) on the DSA conduit would be broken. The DSA framework deals with this by hooking into the flow dissector and shifting the offset at which -the IP header is to be found in the tagged frame as seen by the DSA master. +the IP header is to be found in the tagged frame as seen by the DSA conduit. This behavior is automatic based on the ``overhead`` value of the tagging protocol. If not all packets are of equal size, the tagger can implement the ``flow_dissect`` method of the ``struct dsa_device_ops`` and override this default behavior by specifying the correct offset incurred by each individual RX packet. Tail taggers do not cause issues to the flow dissector. -Checksum offload should work with category 1 and 2 taggers when the DSA master +Checksum offload should work with category 1 and 2 taggers when the DSA conduit driver declares NETIF_F_HW_CSUM in vlan_features and looks at csum_start and csum_offset. For those cases, DSA will shift the checksum start and offset by -the tag size. If the DSA master driver still uses the legacy NETIF_F_IP_CSUM +the tag size. If the DSA conduit driver still uses the legacy NETIF_F_IP_CSUM or NETIF_F_IPV6_CSUM in vlan_features, the offload might only work if the offload hardware already expects that specific tag (perhaps due to matching -vendors). DSA slaves inherit those flags from the master port, and it is up to +vendors). DSA user ports inherit those flags from the conduit, and it is up to the driver to correctly fall back to software checksum when the IP header is not where the hardware expects. If that check is ineffective, the packets might go to the network without a proper checksum (the checksum field will have the pseudo IP header sum). For category 3, when the offload hardware does not already expect the switch tag in use, the checksum must be calculated before any -tag is inserted (i.e. inside the tagger). Otherwise, the DSA master would +tag is inserted (i.e. inside the tagger). Otherwise, the DSA conduit would include the tail tag in the (software or hardware) checksum calculation. Then, when the tag gets stripped by the switch during transmission, it will leave an incorrect IP checksum in place. Due to various reasons (most common being category 1 taggers being associated -with DSA-unaware masters, mangling what the master perceives as MAC DA), the -tagging protocol may require the DSA master to operate in promiscuous mode, to +with DSA-unaware conduits, mangling what the conduit perceives as MAC DA), the +tagging protocol may require the DSA conduit to operate in promiscuous mode, to receive all frames regardless of the value of the MAC DA. This can be done by -setting the ``promisc_on_master`` property of the ``struct dsa_device_ops``. -Note that this assumes a DSA-unaware master driver, which is the norm. +setting the ``promisc_on_conduit`` property of the ``struct dsa_device_ops``. +Note that this assumes a DSA-unaware conduit driver, which is the norm. -Master network devices ----------------------- +Conduit network devices +----------------------- -Master network devices are regular, unmodified Linux network device drivers for +Conduit network devices are regular, unmodified Linux network device drivers for the CPU/management Ethernet interface. Such a driver might occasionally need to know whether DSA is enabled (e.g.: to enable/disable specific offload features), but the DSA subsystem has been proven to work with industry standard drivers: @@ -232,14 +236,14 @@ Ethernet switch. Networking stack hooks ---------------------- -When a master netdev is used with DSA, a small hook is placed in the +When a conduit netdev is used with DSA, a small hook is placed in the networking stack is in order to have the DSA subsystem process the Ethernet switch specific tagging protocol. DSA accomplishes this by registering a specific (and fake) Ethernet type (later becoming ``skb->protocol``) with the networking stack, this is also known as a ``ptype`` or ``packet_type``. A typical Ethernet Frame receive sequence looks like this: -Master network device (e.g.: e1000e): +Conduit network device (e.g.: e1000e): 1. Receive interrupt fires: @@ -269,16 +273,16 @@ Master network device (e.g.: e1000e): - inspect and strip switch tag protocol to determine originating port - locate per-port network device - - invoke ``eth_type_trans()`` with the DSA slave network device + - invoke ``eth_type_trans()`` with the DSA user network device - invoked ``netif_receive_skb()`` -Past this point, the DSA slave network devices get delivered regular Ethernet +Past this point, the DSA user network devices get delivered regular Ethernet frames that can be processed by the networking stack. -Slave network devices ---------------------- +User network devices +-------------------- -Slave network devices created by DSA are stacked on top of their master network +User network devices created by DSA are stacked on top of their conduit network device, each of these network interfaces will be responsible for being a controlling and data-flowing end-point for each front-panel port of the switch. These interfaces are specialized in order to: @@ -289,31 +293,31 @@ These interfaces are specialized in order to: Wake-on-LAN, register dumps... - manage external/internal PHY: link, auto-negotiation, etc. -These slave network devices have custom net_device_ops and ethtool_ops function +These user network devices have custom net_device_ops and ethtool_ops function pointers which allow DSA to introduce a level of layering between the networking stack/ethtool and the switch driver implementation. -Upon frame transmission from these slave network devices, DSA will look up which +Upon frame transmission from these user network devices, DSA will look up which switch tagging protocol is currently registered with these network devices and invoke a specific transmit routine which takes care of adding the relevant switch tag in the Ethernet frames. -These frames are then queued for transmission using the master network device +These frames are then queued for transmission using the conduit network device ``ndo_start_xmit()`` function. Since they contain the appropriate switch tag, the Ethernet switch will be able to process these incoming frames from the management interface and deliver them to the physical switch port. When using multiple CPU ports, it is possible to stack a LAG (bonding/team) -device between the DSA slave devices and the physical DSA masters. The LAG -device is thus also a DSA master, but the LAG slave devices continue to be DSA -masters as well (just with no user port assigned to them; this is needed for -recovery in case the LAG DSA master disappears). Thus, the data path of the LAG -DSA master is used asymmetrically. On RX, the ``ETH_P_XDSA`` handler, which -calls ``dsa_switch_rcv()``, is invoked early (on the physical DSA master; -LAG slave). Therefore, the RX data path of the LAG DSA master is not used. -On the other hand, TX takes place linearly: ``dsa_slave_xmit`` calls -``dsa_enqueue_skb``, which calls ``dev_queue_xmit`` towards the LAG DSA master. -The latter calls ``dev_queue_xmit`` towards one physical DSA master or the +device between the DSA user devices and the physical DSA conduits. The LAG +device is thus also a DSA conduit, but the LAG slave devices continue to be DSA +conduits as well (just with no user port assigned to them; this is needed for +recovery in case the LAG DSA conduit disappears). Thus, the data path of the LAG +DSA conduit is used asymmetrically. On RX, the ``ETH_P_XDSA`` handler, which +calls ``dsa_switch_rcv()``, is invoked early (on the physical DSA conduit; +LAG slave). Therefore, the RX data path of the LAG DSA conduit is not used. +On the other hand, TX takes place linearly: ``dsa_user_xmit`` calls +``dsa_enqueue_skb``, which calls ``dev_queue_xmit`` towards the LAG DSA conduit. +The latter calls ``dev_queue_xmit`` towards one physical DSA conduit or the other, and in both cases, the packet exits the system through a hardware path towards the switch. @@ -352,11 +356,11 @@ perspective:: || swp0 | | swp1 | | swp2 | | swp3 || ++------+-+------+-+------+-+------++ -Slave MDIO bus --------------- +User MDIO bus +------------- -In order to be able to read to/from a switch PHY built into it, DSA creates a -slave MDIO bus which allows a specific switch driver to divert and intercept +In order to be able to read to/from a switch PHY built into it, DSA creates an +user MDIO bus which allows a specific switch driver to divert and intercept MDIO reads/writes towards specific PHY addresses. In most MDIO-connected switches, these functions would utilize direct or indirect PHY addressing mode to return standard MII registers from the switch builtin PHYs, allowing the PHY @@ -364,7 +368,7 @@ library and/or to return link status, link partner pages, auto-negotiation results, etc. For Ethernet switches which have both external and internal MDIO buses, the -slave MII bus can be utilized to mux/demux MDIO reads and writes towards either +user MII bus can be utilized to mux/demux MDIO reads and writes towards either internal or external MDIO devices this switch might be connected to: internal PHYs, external PHYs, or even external switches. @@ -381,10 +385,10 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as - ``dsa_platform_data``: platform device configuration data which can reference a collection of dsa_chip_data structures if multiple switches are cascaded, - the master network device this switch tree is attached to needs to be + the conduit network device this switch tree is attached to needs to be referenced -- ``dsa_switch_tree``: structure assigned to the master network device under +- ``dsa_switch_tree``: structure assigned to the conduit network device under ``dsa_ptr``, this structure references a dsa_platform_data structure as well as the tagging protocol supported by the switch tree, and which receive/transmit function hooks should be invoked, information about the directly attached @@ -392,7 +396,7 @@ DSA data structures are defined in ``include/net/dsa.h`` as well as referenced to address individual switches in the tree. - ``dsa_switch``: structure describing a switch device in the tree, referencing - a ``dsa_switch_tree`` as a backpointer, slave network devices, master network + a ``dsa_switch_tree`` as a backpointer, user network devices, conduit network device, and a reference to the backing``dsa_switch_ops`` - ``dsa_switch_ops``: structure referencing function pointers, see below for a @@ -404,7 +408,7 @@ Design limitations Lack of CPU/DSA network devices ------------------------------- -DSA does not currently create slave network devices for the CPU or DSA ports, as +DSA does not currently create user network devices for the CPU or DSA ports, as described before. This might be an issue in the following cases: - inability to fetch switch CPU port statistics counters using ethtool, which @@ -419,7 +423,7 @@ described before. This might be an issue in the following cases: Common pitfalls using DSA setups -------------------------------- -Once a master network device is configured to use DSA (dev->dsa_ptr becomes +Once a conduit network device is configured to use DSA (dev->dsa_ptr becomes non-NULL), and the switch behind it expects a tagging protocol, this network interface can only exclusively be used as a conduit interface. Sending packets directly through this interface (e.g.: opening a socket using this interface) @@ -440,7 +444,7 @@ DSA currently leverages the following subsystems: MDIO/PHY library ---------------- -Slave network devices exposed by DSA may or may not be interfacing with PHY +User network devices exposed by DSA may or may not be interfacing with PHY devices (``struct phy_device`` as defined in ``include/linux/phy.h)``, but the DSA subsystem deals with all possible combinations: @@ -450,7 +454,7 @@ subsystem deals with all possible combinations: - special, non-autonegotiated or non MDIO-managed PHY devices: SFPs, MoCA; a.k.a fixed PHYs -The PHY configuration is done by the ``dsa_slave_phy_setup()`` function and the +The PHY configuration is done by the ``dsa_user_phy_setup()`` function and the logic basically looks like this: - if Device Tree is used, the PHY device is looked up using the standard @@ -463,7 +467,7 @@ logic basically looks like this: and connected transparently using the special fixed MDIO bus driver - finally, if the PHY is built into the switch, as is very common with - standalone switch packages, the PHY is probed using the slave MII bus created + standalone switch packages, the PHY is probed using the user MII bus created by DSA @@ -472,7 +476,7 @@ SWITCHDEV DSA directly utilizes SWITCHDEV when interfacing with the bridge layer, and more specifically with its VLAN filtering portion when configuring VLANs on top -of per-port slave network devices. As of today, the only SWITCHDEV objects +of per-port user network devices. As of today, the only SWITCHDEV objects supported by DSA are the FDB and VLAN objects. Devlink @@ -589,8 +593,8 @@ is torn down when the first switch unregisters. It is mandatory for DSA switch drivers to implement the ``shutdown()`` callback of their respective bus, and call ``dsa_switch_shutdown()`` from it (a minimal version of the full teardown performed by ``dsa_unregister_switch()``). -The reason is that DSA keeps a reference on the master net device, and if the -driver for the master device decides to unbind on shutdown, DSA's reference +The reason is that DSA keeps a reference on the conduit net device, and if the +driver for the conduit device decides to unbind on shutdown, DSA's reference will block that operation from finalizing. Either ``dsa_switch_shutdown()`` or ``dsa_unregister_switch()`` must be called, @@ -615,7 +619,7 @@ Switch configuration tag formats. - ``change_tag_protocol``: when the default tagging protocol has compatibility - problems with the master or other issues, the driver may support changing it + problems with the conduit or other issues, the driver may support changing it at runtime, either through a device tree property or through sysfs. In that case, further calls to ``get_tag_protocol`` should report the protocol in current use. @@ -643,22 +647,22 @@ Switch configuration PHY cannot be found. In this case, probing of the DSA switch continues without that particular port. -- ``port_change_master``: method through which the affinity (association used +- ``port_change_conduit``: method through which the affinity (association used for traffic termination purposes) between a user port and a CPU port can be changed. By default all user ports from a tree are assigned to the first available CPU port that makes sense for them (most of the times this means the user ports of a tree are all assigned to the same CPU port, except for H topologies as described in commit 2c0b03258b8b). The ``port`` argument - represents the index of the user port, and the ``master`` argument represents - the new DSA master ``net_device``. The CPU port associated with the new - master can be retrieved by looking at ``struct dsa_port *cpu_dp = - master->dsa_ptr``. Additionally, the master can also be a LAG device where - all the slave devices are physical DSA masters. LAG DSA masters also have a - valid ``master->dsa_ptr`` pointer, however this is not unique, but rather a - duplicate of the first physical DSA master's (LAG slave) ``dsa_ptr``. In case - of a LAG DSA master, a further call to ``port_lag_join`` will be emitted + represents the index of the user port, and the ``conduit`` argument represents + the new DSA conduit ``net_device``. The CPU port associated with the new + conduit can be retrieved by looking at ``struct dsa_port *cpu_dp = + conduit->dsa_ptr``. Additionally, the conduit can also be a LAG device where + all the slave devices are physical DSA conduits. LAG DSA also have a + valid ``conduit->dsa_ptr`` pointer, however this is not unique, but rather a + duplicate of the first physical DSA conduit's (LAG slave) ``dsa_ptr``. In case + of a LAG DSA conduit, a further call to ``port_lag_join`` will be emitted separately for the physical CPU ports associated with the physical DSA - masters, requesting them to create a hardware LAG associated with the LAG + conduits, requesting them to create a hardware LAG associated with the LAG interface. PHY devices and link management @@ -670,16 +674,16 @@ PHY devices and link management should return a 32-bit bitmask of "flags" that is private between the switch driver and the Ethernet PHY driver in ``drivers/net/phy/\*``. -- ``phy_read``: Function invoked by the DSA slave MDIO bus when attempting to read +- ``phy_read``: Function invoked by the DSA user MDIO bus when attempting to read the switch port MDIO registers. If unavailable, return 0xffff for each read. For builtin switch Ethernet PHYs, this function should allow reading the link status, auto-negotiation results, link partner pages, etc. -- ``phy_write``: Function invoked by the DSA slave MDIO bus when attempting to write +- ``phy_write``: Function invoked by the DSA user MDIO bus when attempting to write to the switch port MDIO registers. If unavailable return a negative error code. -- ``adjust_link``: Function invoked by the PHY library when a slave network device +- ``adjust_link``: Function invoked by the PHY library when a user network device is attached to a PHY device. This function is responsible for appropriately configuring the switch port link parameters: speed, duplex, pause based on what the ``phy_device`` is providing. @@ -698,14 +702,14 @@ Ethtool operations typically return statistics strings, private flags strings, etc. - ``get_ethtool_stats``: ethtool function used to query per-port statistics and - return their values. DSA overlays slave network devices general statistics: + return their values. DSA overlays user network devices general statistics: RX/TX counters from the network device, with switch driver specific statistics per port - ``get_sset_count``: ethtool function used to query the number of statistics items - ``get_wol``: ethtool function used to obtain Wake-on-LAN settings per-port, this - function may for certain implementations also query the master network device + function may for certain implementations also query the conduit network device Wake-on-LAN settings if this interface needs to participate in Wake-on-LAN - ``set_wol``: ethtool function used to configure Wake-on-LAN settings per-port, @@ -747,13 +751,13 @@ Power management should resume all Ethernet switch activities and re-configure the switch to be in a fully active state -- ``port_enable``: function invoked by the DSA slave network device ndo_open +- ``port_enable``: function invoked by the DSA user network device ndo_open function when a port is administratively brought up, this function should fully enable a given switch port. DSA takes care of marking the port with ``BR_STATE_BLOCKING`` if the port is a bridge member, or ``BR_STATE_FORWARDING`` if it was not, and propagating these changes down to the hardware -- ``port_disable``: function invoked by the DSA slave network device ndo_close +- ``port_disable``: function invoked by the DSA user network device ndo_close function when a port is administratively brought down, this function should fully disable a given switch port. DSA takes care of marking the port with ``BR_STATE_DISABLED`` and propagating changes to the hardware if this port is diff --git a/Documentation/networking/dsa/lan9303.rst b/Documentation/networking/dsa/lan9303.rst index e3c820db28ad..ab81b4e0139e 100644 --- a/Documentation/networking/dsa/lan9303.rst +++ b/Documentation/networking/dsa/lan9303.rst @@ -4,7 +4,7 @@ LAN9303 Ethernet switch driver The LAN9303 is a three port 10/100 Mbps ethernet switch with integrated phys for the two external ethernet ports. The third port is an RMII/MII interface to a -host master network interface (e.g. fixed link). +host conduit network interface (e.g. fixed link). Driver details diff --git a/Documentation/networking/dsa/sja1105.rst b/Documentation/networking/dsa/sja1105.rst index e0219c1452ab..8ab60eef07d4 100644 --- a/Documentation/networking/dsa/sja1105.rst +++ b/Documentation/networking/dsa/sja1105.rst @@ -79,7 +79,7 @@ The hardware tags all traffic internally with a port-based VLAN (pvid), or it decodes the VLAN information from the 802.1Q tag. Advanced VLAN classification is not possible. Once attributed a VLAN tag, frames are checked against the port's membership rules and dropped at ingress if they don't match any VLAN. -This behavior is available when switch ports are enslaved to a bridge with +This behavior is available when switch ports join a bridge with ``vlan_filtering 1``. Normally the hardware is not configurable with respect to VLAN awareness, but @@ -122,7 +122,7 @@ on egress. Using ``vlan_filtering=1``, the behavior is the other way around: offloaded flows can be steered to TX queues based on the VLAN PCP, but the DSA net devices are no longer able to do that. To inject frames into a hardware TX queue with VLAN awareness active, it is necessary to create a VLAN -sub-interface on the DSA master port, and send normal (0x8100) VLAN-tagged +sub-interface on the DSA conduit port, and send normal (0x8100) VLAN-tagged towards the switch, with the VLAN PCP bits set appropriately. Management traffic (having DMAC 01-80-C2-xx-xx-xx or 01-19-1B-xx-xx-xx) is the @@ -389,7 +389,7 @@ MDIO bus and PHY management The SJA1105 does not have an MDIO bus and does not perform in-band AN either. Therefore there is no link state notification coming from the switch device. A board would need to hook up the PHYs connected to the switch to any other -MDIO bus available to Linux within the system (e.g. to the DSA master's MDIO +MDIO bus available to Linux within the system (e.g. to the DSA conduit's MDIO bus). Link state management then works by the driver manually keeping in sync (over SPI commands) the MAC link speed with the settings negotiated by the PHY. diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index e7ec9026e5db..4dfe0d9a57bb 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2502,12 +2502,18 @@ use_tempaddr - INTEGER * -1 (for point-to-point devices and loopback devices) temp_valid_lft - INTEGER - valid lifetime (in seconds) for temporary addresses. + valid lifetime (in seconds) for temporary addresses. If less than the + minimum required lifetime (typically 5 seconds), temporary addresses + will not be created. Default: 172800 (2 days) temp_prefered_lft - INTEGER - Preferred lifetime (in seconds) for temporary addresses. + Preferred lifetime (in seconds) for temporary addresses. If + temp_prefered_lft is less than the minimum required lifetime (typically + 5 seconds), the preferred lifetime is the minimum required. If + temp_prefered_lft is greater than temp_valid_lft, the preferred lifetime + is temp_valid_lft. Default: 86400 (1 day) diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst index 15f1919d640c..69975ce25a02 100644 --- a/Documentation/networking/mptcp-sysctl.rst +++ b/Documentation/networking/mptcp-sysctl.rst @@ -25,6 +25,17 @@ add_addr_timeout - INTEGER (seconds) Default: 120 +close_timeout - INTEGER (seconds) + Set the make-after-break timeout: in absence of any close or + shutdown syscall, MPTCP sockets will maintain the status + unchanged for such time, after the last subflow removal, before + moving to TCP_CLOSE. + + The default value matches TCP_TIMEWAIT_LEN. This is a per-namespace + sysctl. + + Default: 60 + checksum_enabled - BOOLEAN Control whether DSS checksum can be enabled. diff --git a/Documentation/networking/page_pool.rst b/Documentation/networking/page_pool.rst index 215ebc92752c..60993cb56b32 100644 --- a/Documentation/networking/page_pool.rst +++ b/Documentation/networking/page_pool.rst @@ -58,7 +58,9 @@ a page will cause no race conditions is enough. .. kernel-doc:: include/net/page_pool/helpers.h :identifiers: page_pool_put_page page_pool_put_full_page - page_pool_recycle_direct page_pool_dev_alloc_pages + page_pool_recycle_direct page_pool_free_va + page_pool_dev_alloc_pages page_pool_dev_alloc_frag + page_pool_dev_alloc page_pool_dev_alloc_va page_pool_get_dma_addr page_pool_get_dma_dir .. kernel-doc:: net/core/page_pool.c diff --git a/Documentation/networking/representors.rst b/Documentation/networking/representors.rst index ee1f5cd54496..decb39c19b9e 100644 --- a/Documentation/networking/representors.rst +++ b/Documentation/networking/representors.rst @@ -162,9 +162,11 @@ How are representors identified? The representor netdevice should *not* directly refer to a PCIe device (e.g. through ``net_dev->dev.parent`` / ``SET_NETDEV_DEV()``), either of the representee or of the switchdev function. -Instead, it should implement the ``ndo_get_devlink_port()`` netdevice op, which -the kernel uses to provide the ``phys_switch_id`` and ``phys_port_name`` sysfs -nodes. (Some legacy drivers implement ``ndo_get_port_parent_id()`` and +Instead, the driver should use the ``SET_NETDEV_DEVLINK_PORT`` macro to +assign a devlink port instance to the netdevice before registering the +netdevice; the kernel uses the devlink port to provide the ``phys_switch_id`` +and ``phys_port_name`` sysfs nodes. +(Some legacy drivers implement ``ndo_get_port_parent_id()`` and ``ndo_get_phys_port_name()`` directly, but this is deprecated.) See :ref:`Documentation/networking/devlink/devlink-port.rst <devlink_port>` for the details of this API. diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst index 92c9fb46d6a2..03ae19a689fc 100644 --- a/Documentation/networking/scaling.rst +++ b/Documentation/networking/scaling.rst @@ -105,6 +105,48 @@ a separate CPU. For interrupt handling, HT has shown no benefit in initial tests, so limit the number of queues to the number of CPU cores in the system. +Dedicated RSS contexts +~~~~~~~~~~~~~~~~~~~~~~ + +Modern NICs support creating multiple co-existing RSS configurations +which are selected based on explicit matching rules. This can be very +useful when application wants to constrain the set of queues receiving +traffic for e.g. a particular destination port or IP address. +The example below shows how to direct all traffic to TCP port 22 +to queues 0 and 1. + +To create an additional RSS context use:: + + # ethtool -X eth0 hfunc toeplitz context new + New RSS context is 1 + +Kernel reports back the ID of the allocated context (the default, always +present RSS context has ID of 0). The new context can be queried and +modified using the same APIs as the default context:: + + # ethtool -x eth0 context 1 + RX flow hash indirection table for eth0 with 13 RX ring(s): + 0: 0 1 2 3 4 5 6 7 + 8: 8 9 10 11 12 0 1 2 + [...] + # ethtool -X eth0 equal 2 context 1 + # ethtool -x eth0 context 1 + RX flow hash indirection table for eth0 with 13 RX ring(s): + 0: 0 1 0 1 0 1 0 1 + 8: 0 1 0 1 0 1 0 1 + [...] + +To make use of the new context direct traffic to it using an n-tuple +filter:: + + # ethtool -N eth0 flow-type tcp6 dst-port 22 context 1 + Added rule with ID 1023 + +When done, remove the context and the rule:: + + # ethtool -N eth0 delete 1023 + # ethtool -X eth0 context 1 delete + RPS: Receive Packet Steering ============================ diff --git a/Documentation/process/embargoed-hardware-issues.rst b/Documentation/process/embargoed-hardware-issues.rst index ac7c52f130c9..31000f075707 100644 --- a/Documentation/process/embargoed-hardware-issues.rst +++ b/Documentation/process/embargoed-hardware-issues.rst @@ -25,15 +25,15 @@ Contact The Linux kernel hardware security team is separate from the regular Linux kernel security team. -The team only handles the coordination of embargoed hardware security -issues. Reports of pure software security bugs in the Linux kernel are not +The team only handles developing fixes for embargoed hardware security +issues. Reports of pure software security bugs in the Linux kernel are not handled by this team and the reporter will be guided to contact the regular Linux kernel security team (:ref:`Documentation/admin-guide/ <securitybugs>`) instead. The team can be contacted by email at <[email protected]>. This -is a private list of security officers who will help you to coordinate an -issue according to our documented process. +is a private list of security officers who will help you to coordinate a +fix according to our documented process. The list is encrypted and email to the list can be sent by either PGP or S/MIME encrypted and must be signed with the reporter's PGP key or S/MIME @@ -132,11 +132,11 @@ other hardware could be affected. The hardware security team will provide an incident-specific encrypted mailing-list which will be used for initial discussion with the reporter, -further disclosure and coordination. +further disclosure, and coordination of fixes. The hardware security team will provide the disclosing party a list of developers (domain experts) who should be informed initially about the -issue after confirming with the developers that they will adhere to this +issue after confirming with the developers that they will adhere to this Memorandum of Understanding and the documented process. These developers form the initial response team and will be responsible for handling the issue after initial contact. The hardware security team is supporting the @@ -209,13 +209,18 @@ five work days this is taken as silent acknowledgement. After acknowledgement or resolution of an objection the expert is disclosed by the incident team and brought into the development process. +List participants may not communicate about the issue outside of the +private mailing list. List participants may not use any shared resources +(e.g. employer build farms, CI systems, etc) when working on patches. + Coordinated release """"""""""""""""""" The involved parties will negotiate the date and time where the embargo ends. At that point the prepared mitigations are integrated into the -relevant kernel trees and published. +relevant kernel trees and published. There is no pre-notification process: +fixes are published in public and available to everyone at the same time. While we understand that hardware security issues need coordinated embargo time, the embargo time should be constrained to the minimum time which is diff --git a/Documentation/rust/general-information.rst b/Documentation/rust/general-information.rst index 49029ee82e55..081397827a7e 100644 --- a/Documentation/rust/general-information.rst +++ b/Documentation/rust/general-information.rst @@ -29,7 +29,7 @@ target with the same invocation used for compilation, e.g.:: To read the docs locally in your web browser, run e.g.:: - xdg-open rust/doc/kernel/index.html + xdg-open Documentation/output/rust/rustdoc/kernel/index.html To learn about how to write the documentation, please see coding-guidelines.rst. diff --git a/Documentation/trace/fprobe.rst b/Documentation/trace/fprobe.rst index 7a895514b537..196f52386aaa 100644 --- a/Documentation/trace/fprobe.rst +++ b/Documentation/trace/fprobe.rst @@ -91,9 +91,9 @@ The prototype of the entry/exit callback function are as follows: .. code-block:: c - int entry_callback(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); + int entry_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data); - void exit_callback(struct fprobe *fp, unsigned long entry_ip, struct pt_regs *regs, void *entry_data); + void exit_callback(struct fprobe *fp, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, void *entry_data); Note that the @entry_ip is saved at function entry and passed to exit handler. If the entry callback function returns !0, the corresponding exit callback will be cancelled. @@ -108,6 +108,10 @@ If the entry callback function returns !0, the corresponding exit callback will Note that this may not be the actual entry address of the function but the address where the ftrace is instrumented. +@ret_ip + This is the return address that the traced function will return to, + somewhere in the caller. This can be used at both entry and exit. + @regs This is the `pt_regs` data structure at the entry and exit. Note that the instruction pointer of @regs may be different from the @entry_ip diff --git a/Documentation/translations/zh_CN/core-api/workqueue.rst b/Documentation/translations/zh_CN/core-api/workqueue.rst index 6c1b5ec31d75..7fac6f75d078 100644 --- a/Documentation/translations/zh_CN/core-api/workqueue.rst +++ b/Documentation/translations/zh_CN/core-api/workqueue.rst @@ -202,7 +202,7 @@ workqueue将自动创建与属性相匹配的后备工作者池。调节并发� 同的排序属性。 在目前的实现中，上述配置只保证了特定NUMA节点内的ST行为。相反， -``alloc_ordered_queue()`` 应该被用来实现全系统的ST行为。 +``alloc_ordered_workqueue()`` 应该被用来实现全系统的ST行为。 执行场景示例 diff --git a/Documentation/userspace-api/netlink/genetlink-legacy.rst b/Documentation/userspace-api/netlink/genetlink-legacy.rst index 0b3febd57ff5..70a77387f6c4 100644 --- a/Documentation/userspace-api/netlink/genetlink-legacy.rst +++ b/Documentation/userspace-api/netlink/genetlink-legacy.rst @@ -182,7 +182,7 @@ members - ``name`` - The attribute name of the struct member - ``type`` - One of the scalar types ``u8``, ``u16``, ``u32``, ``u64``, ``s8``, - ``s16``, ``s32``, ``s64``, ``string`` or ``binary``. + ``s16``, ``s32``, ``s64``, ``string``, ``binary`` or ``bitfield32``. - ``byte-order`` - ``big-endian`` or ``little-endian`` - ``doc``, ``enum``, ``enum-as-flags``, ``display-hint`` - Same as for :ref:`attribute definitions <attribute_properties>` diff --git a/Documentation/userspace-api/netlink/specs.rst b/Documentation/userspace-api/netlink/specs.rst index 40dd7442d2c3..c1b951649113 100644 --- a/Documentation/userspace-api/netlink/specs.rst +++ b/Documentation/userspace-api/netlink/specs.rst @@ -403,10 +403,21 @@ This section describes the attribute types supported by the ``genetlink`` compatibility level. Refer to documentation of different levels for additional attribute types. -Scalar integer types +Common integer types -------------------- -Fixed-width integer types: +``sint`` and ``uint`` represent signed and unsigned 64 bit integers. +If the value can fit on 32 bits only 32 bits are carried in netlink +messages, otherwise full 64 bits are carried. Note that the payload +is only aligned to 4B, so the full 64 bit value may be unaligned! + +Common integer types should be preferred over fix-width types in majority +of cases. + +Fix-width integer types +----------------------- + +Fixed-width integer types include: ``u8``, ``u16``, ``u32``, ``u64``, ``s8``, ``s16``, ``s32``, ``s64``. Note that types smaller than 32 bit should be avoided as using them @@ -416,6 +427,9 @@ See :ref:`pad_type` for padding of 64 bit attributes. The payload of the attribute is the integer in host order unless ``byte-order`` specifies otherwise. +64 bit values are usually aligned by the kernel but it is recommended +that the user space is able to deal with unaligned values. + .. _pad_type: pad diff --git a/MAINTAINERS b/MAINTAINERS index 3b7a62c68b34..2cd5160d7241 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -378,8 +378,9 @@ F: drivers/acpi/viot.c F: include/linux/acpi_viot.h ACPI WMI DRIVER +M: Armin Wolf <[email protected]> -S: Orphan +S: Maintained F: Documentation/driver-api/wmi.rst F: Documentation/wmi/ F: drivers/platform/x86/wmi.c @@ -3795,6 +3796,15 @@ L: [email protected] S: Odd Fixes K: (?:\b|_)bpf(?:\b|_) +BPF [NETKIT] (BPF-programmable network device) +M: Daniel Borkmann <[email protected]> +M: Nikolay Aleksandrov <[email protected]> +S: Supported +F: drivers/net/netkit.c +F: include/net/netkit.h + BPF [NETWORKING] (struct_ops, reuseport) M: Martin KaFai Lau <[email protected]> @@ -6769,7 +6779,7 @@ F: drivers/gpu/drm/panel/panel-sitronix-st7701.c DRM DRIVER FOR SITRONIX ST7703 PANELS M: Guido Günther <[email protected]> R: Purism Kernel Team <[email protected]> -R: Ondrej Jirman <[email protected]> +R: Ondrej Jirman <[email protected]> S: Maintained F: Documentation/devicetree/bindings/display/panel/rocktech,jh057n00900.yaml F: drivers/gpu/drm/panel/panel-sitronix-st7703.c @@ -8114,7 +8124,7 @@ F: include/linux/arm_ffa.h FIRMWARE LOADER (request_firmware) M: Luis Chamberlain <[email protected]> -M: Russ Weight <[email protected]> +M: Russ Weight <[email protected]> S: Maintained F: Documentation/firmware_class/ @@ -14960,10 +14970,11 @@ W: https://github.com/multipath-tcp/mptcp_net-next/wiki B: https://github.com/multipath-tcp/mptcp_net-next/issues T: git https://github.com/multipath-tcp/mptcp_net-next.git export-net T: git https://github.com/multipath-tcp/mptcp_net-next.git export +F: Documentation/netlink/specs/mptcp.yaml F: Documentation/networking/mptcp-sysctl.rst F: include/net/mptcp.h F: include/trace/events/mptcp.h -F: include/uapi/linux/mptcp.h +F: include/uapi/linux/mptcp*.h F: net/mptcp/ F: tools/testing/selftests/bpf/*/*mptcp*.c F: tools/testing/selftests/net/mptcp/ @@ -15136,7 +15147,7 @@ NOLIBC HEADER FILE M: Willy Tarreau <[email protected]> M: Thomas Weißschuh <[email protected]> S: Maintained -T: git git://git.kernel.org/pub/scm/linux/kernel/git/wtarreau/nolibc.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/nolibc/linux-nolibc.git F: tools/include/nolibc/ F: tools/testing/selftests/nolibc/ @@ -23039,7 +23050,7 @@ F: drivers/scsi/vmw_pvscsi.c F: drivers/scsi/vmw_pvscsi.h VMWARE VIRTUAL PTP CLOCK DRIVER -M: Deep Shah <[email protected]> +M: Jeff Sipek <[email protected]> R: Ajay Kaher <[email protected]> R: Alexey Makhalov <[email protected]> R: VMware PV-Drivers Reviewers <[email protected]> @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 6 SUBLEVEL = 0 -EXTRAVERSION = -rc5 +EXTRAVERSION = -rc7 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* @@ -1474,7 +1474,7 @@ endif # CONFIG_MODULES # Directories & files removed with 'make clean' CLEAN_FILES += vmlinux.symvers modules-only.symvers \ modules.builtin modules.builtin.modinfo modules.nsdeps \ - compile_commands.json .thinlto-cache rust/test rust/doc \ + compile_commands.json .thinlto-cache rust/test \ rust-project.json .vmlinux.objs .vmlinux.export.c # Directories & files removed with 'make mrproper' diff --git a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi index 5fc613d24151..49cbdb55b4b3 100644 --- a/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi +++ b/arch/arm64/boot/dts/marvell/armada-3720-espressobin.dtsi @@ -13,7 +13,7 @@ / { aliases { ethernet0 = ð0; - /* for dsa slave device */ + /* for DSA user port device */ ethernet1 = &switch0port1; ethernet2 = &switch0port2; ethernet3 = &switch0port3; diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index 5882b2415596..1095c6647e96 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -344,14 +344,14 @@ */ #define __HFGRTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51)) #define __HFGRTR_EL2_MASK GENMASK(49, 0) -#define __HFGRTR_EL2_nMASK (GENMASK(55, 54) | BIT(50)) +#define __HFGRTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50)) #define __HFGWTR_EL2_RES0 (GENMASK(63, 56) | GENMASK(53, 51) | \ BIT(46) | BIT(42) | BIT(40) | BIT(28) | \ GENMASK(26, 25) | BIT(21) | BIT(18) | \ GENMASK(15, 14) | GENMASK(10, 9) | BIT(2)) #define __HFGWTR_EL2_MASK GENMASK(49, 0) -#define __HFGWTR_EL2_nMASK (GENMASK(55, 54) | BIT(50)) +#define __HFGWTR_EL2_nMASK (GENMASK(58, 57) | GENMASK(55, 54) | BIT(50)) #define __HFGITR_EL2_RES0 GENMASK(63, 57) #define __HFGITR_EL2_MASK GENMASK(54, 0) diff --git a/arch/arm64/kvm/arch_timer.c b/arch/arm64/kvm/arch_timer.c index 6dcdae4d38cb..a1e24228aaaa 100644 --- a/arch/arm64/kvm/arch_timer.c +++ b/arch/arm64/kvm/arch_timer.c @@ -55,11 +55,6 @@ static struct irq_ops arch_timer_irq_ops = { .get_input_level = kvm_arch_timer_get_input_level, }; -static bool has_cntpoff(void) -{ - return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); -} - static int nr_timers(struct kvm_vcpu *vcpu) { if (!vcpu_has_nv(vcpu)) @@ -180,7 +175,7 @@ u64 kvm_phys_timer_read(void) return timecounter->cc->read(timecounter->cc); } -static void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) +void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map) { if (vcpu_has_nv(vcpu)) { if (is_hyp_ctxt(vcpu)) { @@ -548,8 +543,7 @@ static void timer_save_state(struct arch_timer_context *ctx) timer_set_ctl(ctx, read_sysreg_el0(SYS_CNTP_CTL)); cval = read_sysreg_el0(SYS_CNTP_CVAL); - if (!has_cntpoff()) - cval -= timer_get_offset(ctx); + cval -= timer_get_offset(ctx); timer_set_cval(ctx, cval); @@ -636,8 +630,7 @@ static void timer_restore_state(struct arch_timer_context *ctx) cval = timer_get_cval(ctx); offset = timer_get_offset(ctx); set_cntpoff(offset); - if (!has_cntpoff()) - cval += offset; + cval += offset; write_sysreg_el0(cval, SYS_CNTP_CVAL); isb(); write_sysreg_el0(timer_get_ctl(ctx), SYS_CNTP_CTL); diff --git a/arch/arm64/kvm/emulate-nested.c b/arch/arm64/kvm/emulate-nested.c index 9ced1bf0c2b7..ee902ff2a50f 100644 --- a/arch/arm64/kvm/emulate-nested.c +++ b/arch/arm64/kvm/emulate-nested.c @@ -977,6 +977,8 @@ enum fg_filter_id { static const struct encoding_to_trap_config encoding_to_fgt[] __initconst = { /* HFGRTR_EL2, HFGWTR_EL2 */ + SR_FGT(SYS_PIR_EL1, HFGxTR, nPIR_EL1, 0), + SR_FGT(SYS_PIRE0_EL1, HFGxTR, nPIRE0_EL1, 0), SR_FGT(SYS_TPIDR2_EL0, HFGxTR, nTPIDR2_EL0, 0), SR_FGT(SYS_SMPRI_EL1, HFGxTR, nSMPRI_EL1, 0), SR_FGT(SYS_ACCDATA_EL1, HFGxTR, nACCDATA_EL1, 0), diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 6537f58b1a8c..448b17080d36 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -39,6 +39,26 @@ static void __activate_traps(struct kvm_vcpu *vcpu) ___activate_traps(vcpu); + if (has_cntpoff()) { + struct timer_map map; + + get_timer_map(vcpu, &map); + + /* + * We're entrering the guest. Reload the correct + * values from memory now that TGE is clear. + */ + if (map.direct_ptimer == vcpu_ptimer(vcpu)) + val = __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0); + if (map.direct_ptimer == vcpu_hptimer(vcpu)) + val = __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2); + + if (map.direct_ptimer) { + write_sysreg_el0(val, SYS_CNTP_CVAL); + isb(); + } + } + val = read_sysreg(cpacr_el1); val |= CPACR_ELx_TTA; val &= ~(CPACR_EL1_ZEN_EL0EN | CPACR_EL1_ZEN_EL1EN | @@ -77,6 +97,30 @@ static void __deactivate_traps(struct kvm_vcpu *vcpu) write_sysreg(HCR_HOST_VHE_FLAGS, hcr_el2); + if (has_cntpoff()) { + struct timer_map map; + u64 val, offset; + + get_timer_map(vcpu, &map); + + /* + * We're exiting the guest. Save the latest CVAL value + * to memory and apply the offset now that TGE is set. + */ + val = read_sysreg_el0(SYS_CNTP_CVAL); + if (map.direct_ptimer == vcpu_ptimer(vcpu)) + __vcpu_sys_reg(vcpu, CNTP_CVAL_EL0) = val; + if (map.direct_ptimer == vcpu_hptimer(vcpu)) + __vcpu_sys_reg(vcpu, CNTHP_CVAL_EL2) = val; + + offset = read_sysreg_s(SYS_CNTPOFF_EL2); + + if (map.direct_ptimer && offset) { + write_sysreg_el0(val + offset, SYS_CNTP_CVAL); + isb(); + } + } + /* * ARM errata 1165522 and 1530923 require the actual execution of the * above before we can switch to the EL2/EL0 translation regime used by diff --git a/arch/arm64/kvm/pmu.c b/arch/arm64/kvm/pmu.c index 0eea225fd09a..a243934c5568 100644 --- a/arch/arm64/kvm/pmu.c +++ b/arch/arm64/kvm/pmu.c @@ -39,7 +39,7 @@ void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !pmu || !kvm_pmu_switch_needed(attr)) + if (!kvm_arm_support_pmu_v3() || !kvm_pmu_switch_needed(attr)) return; if (!attr->exclude_host) @@ -55,7 +55,7 @@ void kvm_clr_pmu_events(u32 clr) { struct kvm_pmu_events *pmu = kvm_get_pmu_events(); - if (!kvm_arm_support_pmu_v3() || !pmu) + if (!kvm_arm_support_pmu_v3()) return; pmu->events_host &= ~clr; diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index e92ec810d449..0afd6136e275 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -2122,8 +2122,8 @@ static const struct sys_reg_desc sys_reg_descs[] = { { SYS_DESC(SYS_PMMIR_EL1), trap_raz_wi }, { SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 }, - { SYS_DESC(SYS_PIRE0_EL1), access_vm_reg, reset_unknown, PIRE0_EL1 }, - { SYS_DESC(SYS_PIR_EL1), access_vm_reg, reset_unknown, PIR_EL1 }, + { SYS_DESC(SYS_PIRE0_EL1), NULL, reset_unknown, PIRE0_EL1 }, + { SYS_DESC(SYS_PIR_EL1), NULL, reset_unknown, PIR_EL1 }, { SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 }, { SYS_DESC(SYS_LORSA_EL1), trap_loregion }, diff --git a/arch/ia64/include/asm/cpu.h b/arch/ia64/include/asm/cpu.h index db125df9e088..642d71675ddb 100644 --- a/arch/ia64/include/asm/cpu.h +++ b/arch/ia64/include/asm/cpu.h @@ -15,9 +15,4 @@ DECLARE_PER_CPU(struct ia64_cpu, cpu_devices); DECLARE_PER_CPU(int, cpu_state); -#ifdef CONFIG_HOTPLUG_CPU -extern int arch_register_cpu(int num); -extern void arch_unregister_cpu(int); -#endif - #endif /* _ASM_IA64_CPU_H_ */ diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 94a848b06f15..741863a187a6 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -59,7 +59,7 @@ void __ref arch_unregister_cpu(int num) } EXPORT_SYMBOL(arch_unregister_cpu); #else -static int __init arch_register_cpu(int num) +int __init arch_register_cpu(int num) { return register_cpu(&sysfs_cpus[num].cpu, num); } diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h index 0dcb36b32cb2..c486c2341b66 100644 --- a/arch/loongarch/include/asm/io.h +++ b/arch/loongarch/include/asm/io.h @@ -52,10 +52,9 @@ static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size, * @offset: bus address of the memory * @size: size of the resource to map */ -extern pgprot_t pgprot_wc; - #define ioremap_wc(offset, size) \ - ioremap_prot((offset), (size), pgprot_val(pgprot_wc)) + ioremap_prot((offset), (size), \ + pgprot_val(wc_enabled ? PAGE_KERNEL_WUC : PAGE_KERNEL_SUC)) #define ioremap_cache(offset, size) \ ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL)) diff --git a/arch/loongarch/include/asm/linkage.h b/arch/loongarch/include/asm/linkage.h index 81b0c4cfbf4f..e2eca1a25b4e 100644 --- a/arch/loongarch/include/asm/linkage.h +++ b/arch/loongarch/include/asm/linkage.h @@ -33,4 +33,12 @@ .cfi_endproc; \ SYM_END(name, SYM_T_FUNC) +#define SYM_CODE_START(name) \ + SYM_START(name, SYM_L_GLOBAL, SYM_A_ALIGN) \ + .cfi_startproc; + +#define SYM_CODE_END(name) \ + .cfi_endproc; \ + SYM_END(name, SYM_T_NONE) + #endif diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h index 35348d4c4209..21319c1e045c 100644 --- a/arch/loongarch/include/asm/pgtable-bits.h +++ b/arch/loongarch/include/asm/pgtable-bits.h @@ -105,13 +105,15 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot) return __pgprot(prot); } +extern bool wc_enabled; + #define pgprot_writecombine pgprot_writecombine static inline pgprot_t pgprot_writecombine(pgprot_t _prot) { unsigned long prot = pgprot_val(_prot); - prot = (prot & ~_CACHE_MASK) | _CACHE_WUC; + prot = (prot & ~_CACHE_MASK) | (wc_enabled ? _CACHE_WUC : _CACHE_SUC); return __pgprot(prot); } diff --git a/arch/loongarch/kernel/entry.S b/arch/loongarch/kernel/entry.S index 65518bb8f472..1ec8e4c4cc2b 100644 --- a/arch/loongarch/kernel/entry.S +++ b/arch/loongarch/kernel/entry.S @@ -18,7 +18,7 @@ .text .cfi_sections .debug_frame .align 5 -SYM_FUNC_START(handle_syscall) +SYM_CODE_START(handle_syscall) csrrd t0, PERCPU_BASE_KS la.pcrel t1, kernelsp add.d t1, t1, t0 @@ -71,7 +71,7 @@ SYM_FUNC_START(handle_syscall) bl do_syscall RESTORE_ALL_AND_RET -SYM_FUNC_END(handle_syscall) +SYM_CODE_END(handle_syscall) _ASM_NOKPROBE(handle_syscall) SYM_CODE_START(ret_from_fork) diff --git a/arch/loongarch/kernel/genex.S b/arch/loongarch/kernel/genex.S index 78f066384657..2bb3aa2dcfcb 100644 --- a/arch/loongarch/kernel/genex.S +++ b/arch/loongarch/kernel/genex.S @@ -31,7 +31,7 @@ SYM_FUNC_START(__arch_cpu_idle) 1: jr ra SYM_FUNC_END(__arch_cpu_idle) -SYM_FUNC_START(handle_vint) +SYM_CODE_START(handle_vint) BACKUP_T0T1 SAVE_ALL la_abs t1, __arch_cpu_idle @@ -46,11 +46,11 @@ SYM_FUNC_START(handle_vint) la_abs t0, do_vint jirl ra, t0, 0 RESTORE_ALL_AND_RET -SYM_FUNC_END(handle_vint) +SYM_CODE_END(handle_vint) -SYM_FUNC_START(except_vec_cex) +SYM_CODE_START(except_vec_cex) b cache_parity_error -SYM_FUNC_END(except_vec_cex) +SYM_CODE_END(except_vec_cex) .macro build_prep_badv csrrd t0, LOONGARCH_CSR_BADV @@ -66,7 +66,7 @@ SYM_FUNC_END(except_vec_cex) .macro BUILD_HANDLER exception handler prep .align 5 - SYM_FUNC_START(handle_\exception) + SYM_CODE_START(handle_\exception) 666: BACKUP_T0T1 SAVE_ALL @@ -76,7 +76,7 @@ SYM_FUNC_END(except_vec_cex) jirl ra, t0, 0 668: RESTORE_ALL_AND_RET - SYM_FUNC_END(handle_\exception) + SYM_CODE_END(handle_\exception) SYM_DATA(unwind_hint_\exception, .word 668b - 666b) .endm @@ -93,7 +93,7 @@ SYM_FUNC_END(except_vec_cex) BUILD_HANDLER watch watch none BUILD_HANDLER reserved reserved none /* others */ -SYM_FUNC_START(handle_sys) +SYM_CODE_START(handle_sys) la_abs t0, handle_syscall jr t0 -SYM_FUNC_END(handle_sys) +SYM_CODE_END(handle_sys) diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index 7783f0a3d742..aed65915e932 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -161,19 +161,19 @@ static void __init smbios_parse(void) } #ifdef CONFIG_ARCH_WRITECOMBINE -pgprot_t pgprot_wc = PAGE_KERNEL_WUC; +bool wc_enabled = true; #else -pgprot_t pgprot_wc = PAGE_KERNEL_SUC; +bool wc_enabled = false; #endif -EXPORT_SYMBOL(pgprot_wc); +EXPORT_SYMBOL(wc_enabled); static int __init setup_writecombine(char *p) { if (!strcmp(p, "on")) - pgprot_wc = PAGE_KERNEL_WUC; + wc_enabled = true; else if (!strcmp(p, "off")) - pgprot_wc = PAGE_KERNEL_SUC; + wc_enabled = false; else pr_warn("Unknown writecombine setting \"%s\".\n", p); diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c index f3fe8c06ba4d..4dd53427f657 100644 --- a/arch/loongarch/mm/init.c +++ b/arch/loongarch/mm/init.c @@ -43,11 +43,11 @@ void copy_user_highpage(struct page *to, struct page *from, { void *vfrom, *vto; - vto = kmap_atomic(to); - vfrom = kmap_atomic(from); + vfrom = kmap_local_page(from); + vto = kmap_local_page(to); copy_page(vto, vfrom); - kunmap_atomic(vfrom); - kunmap_atomic(vto); + kunmap_local(vfrom); + kunmap_local(vto); /* Make sure this page is cleared on other CPU's too before using it */ smp_wmb(); } @@ -240,6 +240,7 @@ pgd_t swapper_pg_dir[_PTRS_PER_PGD] __section(".bss..swapper_pg_dir"); pgd_t invalid_pg_dir[_PTRS_PER_PGD] __page_aligned_bss; #ifndef __PAGETABLE_PUD_FOLDED pud_t invalid_pud_table[PTRS_PER_PUD] __page_aligned_bss; +EXPORT_SYMBOL(invalid_pud_table); #endif #ifndef __PAGETABLE_PMD_FOLDED pmd_t invalid_pmd_table[PTRS_PER_PMD] __page_aligned_bss; diff --git a/arch/loongarch/mm/tlbex.S b/arch/loongarch/mm/tlbex.S index ca17dd3a1915..d5d682f3d29f 100644 --- a/arch/loongarch/mm/tlbex.S +++ b/arch/loongarch/mm/tlbex.S @@ -17,7 +17,7 @@ #define PTRS_PER_PTE_BITS (PAGE_SHIFT - 3) .macro tlb_do_page_fault, write - SYM_FUNC_START(tlb_do_page_fault_\write) + SYM_CODE_START(tlb_do_page_fault_\write) SAVE_ALL csrrd a2, LOONGARCH_CSR_BADV move a0, sp @@ -25,13 +25,13 @@ li.w a1, \write bl do_page_fault RESTORE_ALL_AND_RET - SYM_FUNC_END(tlb_do_page_fault_\write) + SYM_CODE_END(tlb_do_page_fault_\write) .endm tlb_do_page_fault 0 tlb_do_page_fault 1 -SYM_FUNC_START(handle_tlb_protect) +SYM_CODE_START(handle_tlb_protect) BACKUP_T0T1 SAVE_ALL move a0, sp @@ -41,9 +41,9 @@ SYM_FUNC_START(handle_tlb_protect) la_abs t0, do_page_fault jirl ra, t0, 0 RESTORE_ALL_AND_RET -SYM_FUNC_END(handle_tlb_protect) +SYM_CODE_END(handle_tlb_protect) -SYM_FUNC_START(handle_tlb_load) +SYM_CODE_START(handle_tlb_load) csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -187,16 +187,16 @@ nopage_tlb_load: csrrd ra, EXCEPTION_KS2 la_abs t0, tlb_do_page_fault_0 jr t0 -SYM_FUNC_END(handle_tlb_load) +SYM_CODE_END(handle_tlb_load) -SYM_FUNC_START(handle_tlb_load_ptw) +SYM_CODE_START(handle_tlb_load_ptw) csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_0 jr t0 -SYM_FUNC_END(handle_tlb_load_ptw) +SYM_CODE_END(handle_tlb_load_ptw) -SYM_FUNC_START(handle_tlb_store) +SYM_CODE_START(handle_tlb_store) csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -343,16 +343,16 @@ nopage_tlb_store: csrrd ra, EXCEPTION_KS2 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_store) +SYM_CODE_END(handle_tlb_store) -SYM_FUNC_START(handle_tlb_store_ptw) +SYM_CODE_START(handle_tlb_store_ptw) csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_store_ptw) +SYM_CODE_END(handle_tlb_store_ptw) -SYM_FUNC_START(handle_tlb_modify) +SYM_CODE_START(handle_tlb_modify) csrwr t0, EXCEPTION_KS0 csrwr t1, EXCEPTION_KS1 csrwr ra, EXCEPTION_KS2 @@ -497,16 +497,16 @@ nopage_tlb_modify: csrrd ra, EXCEPTION_KS2 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_modify) +SYM_CODE_END(handle_tlb_modify) -SYM_FUNC_START(handle_tlb_modify_ptw) +SYM_CODE_START(handle_tlb_modify_ptw) csrwr t0, LOONGARCH_CSR_KS0 csrwr t1, LOONGARCH_CSR_KS1 la_abs t0, tlb_do_page_fault_1 jr t0 -SYM_FUNC_END(handle_tlb_modify_ptw) +SYM_CODE_END(handle_tlb_modify_ptw) -SYM_FUNC_START(handle_tlb_refill) +SYM_CODE_START(handle_tlb_refill) csrwr t0, LOONGARCH_CSR_TLBRSAVE csrrd t0, LOONGARCH_CSR_PGD lddir t0, t0, 3 @@ -521,4 +521,4 @@ SYM_FUNC_START(handle_tlb_refill) tlbfill csrrd t0, LOONGARCH_CSR_TLBRSAVE ertn -SYM_FUNC_END(handle_tlb_refill) +SYM_CODE_END(handle_tlb_refill) diff --git a/arch/mips/kvm/mmu.c b/arch/mips/kvm/mmu.c index 7b2ac1319d70..467ee6b95ae1 100644 --- a/arch/mips/kvm/mmu.c +++ b/arch/mips/kvm/mmu.c @@ -592,7 +592,7 @@ static int kvm_mips_map_page(struct kvm_vcpu *vcpu, unsigned long gpa, gfn_t gfn = gpa >> PAGE_SHIFT; int srcu_idx, err; kvm_pfn_t pfn; - pte_t *ptep, entry, old_pte; + pte_t *ptep, entry; bool writeable; unsigned long prot_bits; unsigned long mmu_seq; @@ -664,7 +664,6 @@ retry: entry = pfn_pte(pfn, __pgprot(prot_bits)); /* Write the PTE */ - old_pte = *ptep; set_pte(ptep, entry); err = 0; diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 3aaadfd2c8eb..d5d5388973ac 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -910,7 +910,7 @@ config ARCH_FORCE_MAX_ORDER default "6" if PPC32 && PPC_64K_PAGES range 4 10 if PPC32 && PPC_256K_PAGES default "4" if PPC32 && PPC_256K_PAGES - range 10 10 + range 10 12 default "10" help The kernel page allocator limits the size of maximal physically diff --git a/arch/powerpc/include/asm/nohash/32/pte-8xx.h b/arch/powerpc/include/asm/nohash/32/pte-8xx.h index 21f681ee535a..e6fe1d5731f2 100644 --- a/arch/powerpc/include/asm/nohash/32/pte-8xx.h +++ b/arch/powerpc/include/asm/nohash/32/pte-8xx.h @@ -94,6 +94,13 @@ static inline pte_t pte_wrprotect(pte_t pte) #define pte_wrprotect pte_wrprotect +static inline int pte_read(pte_t pte) +{ + return (pte_val(pte) & _PAGE_RO) != _PAGE_NA; +} + +#define pte_read pte_read + static inline int pte_write(pte_t pte) { return !(pte_val(pte) & _PAGE_RO); diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 5cd9acf58a7d..eb6891e34cbd 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -197,7 +197,7 @@ static inline int __ptep_test_and_clear_young(struct mm_struct *mm, { unsigned long old; - if (pte_young(*ptep)) + if (!pte_young(*ptep)) return 0; old = pte_update(mm, addr, ptep, _PAGE_ACCESSED, 0, 0); return (old & _PAGE_ACCESSED) != 0; diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h index 56ea48276356..c721478c5934 100644 --- a/arch/powerpc/include/asm/nohash/pgtable.h +++ b/arch/powerpc/include/asm/nohash/pgtable.h @@ -25,7 +25,9 @@ static inline int pte_write(pte_t pte) return pte_val(pte) & _PAGE_RW; } #endif +#ifndef pte_read static inline int pte_read(pte_t pte) { return 1; } +#endif static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; } static inline int pte_special(pte_t pte) { return pte_val(pte) & _PAGE_SPECIAL; } static inline int pte_none(pte_t pte) { return (pte_val(pte) & ~_PTE_NONE_MASK) == 0; } diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S index 9692acb0361f..7eda33a24bb4 100644 --- a/arch/powerpc/kernel/entry_32.S +++ b/arch/powerpc/kernel/entry_32.S @@ -137,8 +137,9 @@ ret_from_syscall: lis r4,icache_44x_need_flush@ha lwz r5,icache_44x_need_flush@l(r4) cmplwi cr0,r5,0 - bne- 2f + bne- .L44x_icache_flush #endif /* CONFIG_PPC_47x */ +.L44x_icache_flush_return: kuep_unlock lwz r4,_LINK(r1) lwz r5,_CCR(r1) @@ -172,10 +173,11 @@ syscall_exit_finish: b 1b #ifdef CONFIG_44x -2: li r7,0 +.L44x_icache_flush: + li r7,0 iccci r0,r0 stw r7,icache_44x_need_flush@l(r4) - b 1b + b .L44x_icache_flush_return #endif /* CONFIG_44x */ .globl ret_from_fork diff --git a/arch/powerpc/kernel/head_85xx.S b/arch/powerpc/kernel/head_85xx.S index 97e9ea0c7297..0f1641a31250 100644 --- a/arch/powerpc/kernel/head_85xx.S +++ b/arch/powerpc/kernel/head_85xx.S @@ -395,7 +395,7 @@ interrupt_base: #ifdef CONFIG_PPC_FPU FP_UNAVAILABLE_EXCEPTION #else - EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, unknown_exception) + EXCEPTION(0x0800, FP_UNAVAIL, FloatingPointUnavailable, emulation_assist_interrupt) #endif /* System Call Interrupt */ diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c index 253620979d0c..6dd2f46bd3ef 100644 --- a/arch/powerpc/lib/qspinlock.c +++ b/arch/powerpc/lib/qspinlock.c @@ -406,6 +406,9 @@ static __always_inline bool yield_to_prev(struct qspinlock *lock, struct qnode * if ((yield_count & 1) == 0) goto yield_prev; /* owner vcpu is running */ + if (get_owner_cpu(READ_ONCE(lock->val)) != yield_cpu) + goto yield_prev; /* re-sample lock owner */ + spin_end(); preempted = true; diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c index 39acc2cbab4c..9e1f6558d026 100644 --- a/arch/powerpc/mm/book3s64/radix_tlb.c +++ b/arch/powerpc/mm/book3s64/radix_tlb.c @@ -1212,14 +1212,7 @@ void radix__tlb_flush(struct mmu_gather *tlb) smp_mb(); /* see radix__flush_tlb_mm */ exit_flush_lazy_tlbs(mm); - _tlbiel_pid(mm->context.id, RIC_FLUSH_ALL); - - /* - * It should not be possible to have coprocessors still - * attached here. - */ - if (WARN_ON_ONCE(atomic_read(&mm->context.copros) > 0)) - __flush_all_mm(mm, true); + __flush_all_mm(mm, true); preempt_enable(); } else { diff --git a/arch/powerpc/platforms/pseries/hvCall.S b/arch/powerpc/platforms/pseries/hvCall.S index bae45b358a09..2b0cac6fb61f 100644 --- a/arch/powerpc/platforms/pseries/hvCall.S +++ b/arch/powerpc/platforms/pseries/hvCall.S @@ -184,9 +184,6 @@ _GLOBAL_TOC(plpar_hcall) plpar_hcall_trace: HCALL_INST_PRECALL(R5) - std r4,STK_PARAM(R4)(r1) - mr r0,r4 - mr r4,r5 mr r5,r6 mr r6,r7 @@ -196,7 +193,7 @@ plpar_hcall_trace: HVSC - ld r12,STK_PARAM(R4)(r1) + ld r12,STACK_FRAME_MIN_SIZE+STK_PARAM(R4)(r1) std r4,0(r12) std r5,8(r12) std r6,16(r12) @@ -296,9 +293,6 @@ _GLOBAL_TOC(plpar_hcall9) plpar_hcall9_trace: HCALL_INST_PRECALL(R5) - std r4,STK_PARAM(R4)(r1) - mr r0,r4 - mr r4,r5 mr r5,r6 mr r6,r7 diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile index 1329e060c548..b43a6bb7e4dc 100644 --- a/arch/riscv/Makefile +++ b/arch/riscv/Makefile @@ -6,7 +6,6 @@ # for more details. # -OBJCOPYFLAGS := -O binary LDFLAGS_vmlinux := -z norelro ifeq ($(CONFIG_RELOCATABLE),y) LDFLAGS_vmlinux += -shared -Bsymbolic -z notext --emit-relocs diff --git a/arch/riscv/errata/andes/Makefile b/arch/riscv/errata/andes/Makefile index 2d644e19caef..6278c389b801 100644 --- a/arch/riscv/errata/andes/Makefile +++ b/arch/riscv/errata/andes/Makefile @@ -1 +1,5 @@ +ifdef CONFIG_RISCV_ALTERNATIVE_EARLY +CFLAGS_errata.o := -mcmodel=medany +endif + obj-y += errata.o diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h index 740a979171e5..2b2f5df7ef2c 100644 --- a/arch/riscv/include/asm/ftrace.h +++ b/arch/riscv/include/asm/ftrace.h @@ -31,6 +31,27 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr) return addr; } +/* + * Let's do like x86/arm64 and ignore the compat syscalls. + */ +#define ARCH_TRACE_IGNORE_COMPAT_SYSCALLS +static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs) +{ + return is_compat_task(); +} + +#define ARCH_HAS_SYSCALL_MATCH_SYM_NAME +static inline bool arch_syscall_match_sym_name(const char *sym, + const char *name) +{ + /* + * Since all syscall functions have __riscv_ prefix, we must skip it. + * However, as we described above, we decided to ignore compat + * syscalls, so we don't care about __riscv_compat_ prefix here. + */ + return !strcmp(sym + 8, name); +} + struct dyn_arch_ftrace { }; #endif diff --git a/arch/riscv/include/asm/kprobes.h b/arch/riscv/include/asm/kprobes.h index e7882ccb0fd4..78ea44f76718 100644 --- a/arch/riscv/include/asm/kprobes.h +++ b/arch/riscv/include/asm/kprobes.h @@ -40,6 +40,15 @@ void arch_remove_kprobe(struct kprobe *p); int kprobe_fault_handler(struct pt_regs *regs, unsigned int trapnr); bool kprobe_breakpoint_handler(struct pt_regs *regs); bool kprobe_single_step_handler(struct pt_regs *regs); - +#else +static inline bool kprobe_breakpoint_handler(struct pt_regs *regs) +{ + return false; +} + +static inline bool kprobe_single_step_handler(struct pt_regs *regs) +{ + return false; +} #endif /* CONFIG_KPROBES */ #endif /* _ASM_RISCV_KPROBES_H */ diff --git a/arch/riscv/include/asm/uprobes.h b/arch/riscv/include/asm/uprobes.h index f2183e00fdd2..3fc7deda9190 100644 --- a/arch/riscv/include/asm/uprobes.h +++ b/arch/riscv/include/asm/uprobes.h @@ -34,7 +34,18 @@ struct arch_uprobe { bool simulate; }; +#ifdef CONFIG_UPROBES bool uprobe_breakpoint_handler(struct pt_regs *regs); bool uprobe_single_step_handler(struct pt_regs *regs); - +#else +static inline bool uprobe_breakpoint_handler(struct pt_regs *regs) +{ + return false; +} + +static inline bool uprobe_single_step_handler(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ #endif /* _ASM_RISCV_UPROBES_H */ diff --git a/arch/riscv/kernel/irq.c b/arch/riscv/kernel/irq.c index a8efa053c4a5..9cc0a7669271 100644 --- a/arch/riscv/kernel/irq.c +++ b/arch/riscv/kernel/irq.c @@ -60,7 +60,7 @@ static void init_irq_stacks(void) } #endif /* CONFIG_VMAP_STACK */ -#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void) { #ifdef CONFIG_IRQ_STACKS @@ -92,7 +92,7 @@ void do_softirq_own_stack(void) #endif __do_softirq(); } -#endif /* CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK */ +#endif /* CONFIG_SOFTIRQ_ON_OWN_STACK */ #else static void init_irq_stacks(void) {} diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c index e600aab116a4..aac853ae4eb7 100644 --- a/arch/riscv/kernel/setup.c +++ b/arch/riscv/kernel/setup.c @@ -173,19 +173,6 @@ static void __init init_resources(void) if (ret < 0) goto error; -#ifdef CONFIG_KEXEC_CORE - if (crashk_res.start != crashk_res.end) { - ret = add_resource(&iomem_resource, &crashk_res); - if (ret < 0) - goto error; - } - if (crashk_low_res.start != crashk_low_res.end) { - ret = add_resource(&iomem_resource, &crashk_low_res); - if (ret < 0) - goto error; - } -#endif - #ifdef CONFIG_CRASH_DUMP if (elfcorehdr_size > 0) { elfcorehdr_res.start = elfcorehdr_addr; diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c index 180d951d3624..21a4d0e111bc 100644 --- a/arch/riscv/kernel/signal.c +++ b/arch/riscv/kernel/signal.c @@ -311,13 +311,6 @@ static inline void __user *get_sigframe(struct ksignal *ksig, /* Align the stack frame. */ sp &= ~0xfUL; - /* - * Fail if the size of the altstack is not large enough for the - * sigframe construction. - */ - if (current->sas_ss_size && sp < current->sas_ss_sp) - return (void __user __force *)-1UL; - return (void __user *)sp; } diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c index 19807c4d3805..fae8f610d867 100644 --- a/arch/riscv/kernel/traps.c +++ b/arch/riscv/kernel/traps.c @@ -13,6 +13,8 @@ #include <linux/kdebug.h> #include <linux/uaccess.h> #include <linux/kprobes.h> +#include <linux/uprobes.h> +#include <asm/uprobes.h> #include <linux/mm.h> #include <linux/module.h> #include <linux/irq.h> @@ -247,22 +249,28 @@ static inline unsigned long get_break_insn_length(unsigned long pc) return GET_INSN_LENGTH(insn); } +static bool probe_single_step_handler(struct pt_regs *regs) +{ + bool user = user_mode(regs); + + return user ? uprobe_single_step_handler(regs) : kprobe_single_step_handler(regs); +} + +static bool probe_breakpoint_handler(struct pt_regs *regs) +{ + bool user = user_mode(regs); + + return user ? uprobe_breakpoint_handler(regs) : kprobe_breakpoint_handler(regs); +} + void handle_break(struct pt_regs *regs) { -#ifdef CONFIG_KPROBES - if (kprobe_single_step_handler(regs)) + if (probe_single_step_handler(regs)) return; - if (kprobe_breakpoint_handler(regs)) - return; -#endif -#ifdef CONFIG_UPROBES - if (uprobe_single_step_handler(regs)) + if (probe_breakpoint_handler(regs)) return; - if (uprobe_breakpoint_handler(regs)) - return; -#endif current->thread.bad_cause = regs->cause; if (user_mode(regs)) diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 6115d7514972..90d4ba36d1d0 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -72,7 +72,7 @@ static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_f } pagefault_out_of_memory(); return; - } else if (fault & VM_FAULT_SIGBUS) { + } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) { /* Kernel mode? Handle exceptions or die */ if (!user_mode(regs)) { no_context(regs, addr); diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c index e4a2ace92dbe..b52f0210481f 100644 --- a/arch/riscv/mm/hugetlbpage.c +++ b/arch/riscv/mm/hugetlbpage.c @@ -183,15 +183,22 @@ void set_huge_pte_at(struct mm_struct *mm, pte_t pte, unsigned long sz) { + unsigned long hugepage_shift; int i, pte_num; - if (!pte_napot(pte)) { - set_pte_at(mm, addr, ptep, pte); - return; - } + if (sz >= PGDIR_SIZE) + hugepage_shift = PGDIR_SHIFT; + else if (sz >= P4D_SIZE) + hugepage_shift = P4D_SHIFT; + else if (sz >= PUD_SIZE) + hugepage_shift = PUD_SHIFT; + else if (sz >= PMD_SIZE) + hugepage_shift = PMD_SHIFT; + else + hugepage_shift = PAGE_SHIFT; - pte_num = napot_pte_num(napot_cont_order(pte)); - for (i = 0; i < pte_num; i++, ptep++, addr += PAGE_SIZE) + pte_num = sz >> hugepage_shift; + for (i = 0; i < pte_num; i++, ptep++, addr += (1 << hugepage_shift)) set_pte_at(mm, addr, ptep, pte); } diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c index 01257ce3b89c..442a74f113cb 100644 --- a/arch/s390/boot/vmem.c +++ b/arch/s390/boot/vmem.c @@ -57,6 +57,7 @@ static void kasan_populate_shadow(void) pmd_t pmd_z = __pmd(__pa(kasan_early_shadow_pte) | _SEGMENT_ENTRY); pud_t pud_z = __pud(__pa(kasan_early_shadow_pmd) | _REGION3_ENTRY); p4d_t p4d_z = __p4d(__pa(kasan_early_shadow_pud) | _REGION2_ENTRY); + unsigned long memgap_start = 0; unsigned long untracked_end; unsigned long start, end; int i; @@ -101,8 +102,12 @@ static void kasan_populate_shadow(void) * +- shadow end ----+---------+- shadow end ---+ */ - for_each_physmem_usable_range(i, &start, &end) + for_each_physmem_usable_range(i, &start, &end) { kasan_populate(start, end, POPULATE_KASAN_MAP_SHADOW); + if (memgap_start && physmem_info.info_source == MEM_DETECT_DIAG260) + kasan_populate(memgap_start, start, POPULATE_KASAN_ZERO_SHADOW); + memgap_start = end; + } if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) { untracked_end = VMALLOC_START; /* shallowly populate kasan shadow for vmalloc and modules */ diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c index c1b47d608a2b..efaebba5ee19 100644 --- a/arch/s390/kvm/interrupt.c +++ b/arch/s390/kvm/interrupt.c @@ -303,11 +303,6 @@ static inline u8 gisa_get_ipm_or_restore_iam(struct kvm_s390_gisa_interrupt *gi) return 0; } -static inline int gisa_in_alert_list(struct kvm_s390_gisa *gisa) -{ - return READ_ONCE(gisa->next_alert) != (u32)virt_to_phys(gisa); -} - static inline void gisa_set_ipm_gisc(struct kvm_s390_gisa *gisa, u32 gisc) { set_bit_inv(IPM_BIT_OFFSET + gisc, (unsigned long *) gisa); @@ -3216,11 +3211,12 @@ void kvm_s390_gisa_destroy(struct kvm *kvm) if (!gi->origin) return; - if (gi->alert.mask) - KVM_EVENT(3, "vm 0x%pK has unexpected iam 0x%02x", - kvm, gi->alert.mask); - while (gisa_in_alert_list(gi->origin)) - cpu_relax(); + WARN(gi->alert.mask != 0x00, + "unexpected non zero alert.mask 0x%02x", + gi->alert.mask); + gi->alert.mask = 0x00; + if (gisa_set_iam(gi->origin, gi->alert.mask)) + process_gib_alert_list(); hrtimer_cancel(&gi->timer); gi->origin = NULL; VM_EVENT(kvm, 3, "gisa 0x%pK destroyed", gisa); diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c index 2d9b01d7ca4c..99209085c75b 100644 --- a/arch/s390/pci/pci_dma.c +++ b/arch/s390/pci/pci_dma.c @@ -564,6 +564,17 @@ static void s390_dma_unmap_sg(struct device *dev, struct scatterlist *sg, s->dma_length = 0; } } + +static unsigned long *bitmap_vzalloc(size_t bits, gfp_t flags) +{ + size_t n = BITS_TO_LONGS(bits); + size_t bytes; + + if (unlikely(check_mul_overflow(n, sizeof(unsigned long), &bytes))) + return NULL; + + return vzalloc(bytes); +} int zpci_dma_init_device(struct zpci_dev *zdev) { @@ -604,13 +615,13 @@ int zpci_dma_init_device(struct zpci_dev *zdev) zdev->end_dma - zdev->start_dma + 1); zdev->end_dma = zdev->start_dma + zdev->iommu_size - 1; zdev->iommu_pages = zdev->iommu_size >> PAGE_SHIFT; - zdev->iommu_bitmap = vzalloc(zdev->iommu_pages / 8); + zdev->iommu_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL); if (!zdev->iommu_bitmap) { rc = -ENOMEM; goto free_dma_table; } if (!s390_iommu_strict) { - zdev->lazy_bitmap = vzalloc(zdev->iommu_pages / 8); + zdev->lazy_bitmap = bitmap_vzalloc(zdev->iommu_pages, GFP_KERNEL); if (!zdev->lazy_bitmap) { rc = -ENOMEM; goto free_bitmap; diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index dc8c876fbd8f..80d76aea1f7b 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -103,6 +103,16 @@ static enum es_result vc_read_mem(struct es_em_ctxt *ctxt, return ES_OK; } +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + return ES_OK; +} + +static bool fault_in_kernel_space(unsigned long address) +{ + return false; +} + #undef __init #define __init diff --git a/arch/x86/events/utils.c b/arch/x86/events/utils.c index 76b1f8bb0fd5..dab4ed199227 100644 --- a/arch/x86/events/utils.c +++ b/arch/x86/events/utils.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <asm/insn.h> +#include <linux/mm.h> #include "perf_event.h" @@ -132,9 +133,9 @@ static int get_branch_type(unsigned long from, unsigned long to, int abort, * The LBR logs any address in the IP, even if the IP just * faulted. This means userspace can control the from address. * Ensure we don't blindly read any address by validating it is - * a known text address. + * a known text address and not a vsyscall address. */ - if (kernel_text_address(from)) { + if (kernel_text_address(from) && !in_gate_area_no_mm(from)) { addr = (void *)from; /* * Assume we can get the maximum possible size diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index 3a233ebff712..25050d953eee 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -28,8 +28,6 @@ struct x86_cpu { }; #ifdef CONFIG_HOTPLUG_CPU -extern int arch_register_cpu(int num); -extern void arch_unregister_cpu(int); extern void soft_restart_cpu(void); #endif diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h index 31089b851c4f..a2be3aefff9f 100644 --- a/arch/x86/include/asm/fpu/api.h +++ b/arch/x86/include/asm/fpu/api.h @@ -157,7 +157,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) { static inline void fpu_sync_guest_vmexit_xfd_state(void) { } #endif -extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru); +extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, + unsigned int size, u64 xfeatures, u32 pkru); extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru); static inline void fpstate_set_confidential(struct fpu_guest *gfpu) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 17715cb8731d..70d139406bc8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -528,7 +528,6 @@ struct kvm_pmu { u64 raw_event_mask; struct kvm_pmc gp_counters[KVM_INTEL_PMC_MAX_GENERIC]; struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED]; - struct irq_work irq_work; /* * Overlay the bitmap with a 64-bit atomic so that all bits can be diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 1d111350197f..b37abb55e948 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -637,12 +637,17 @@ /* AMD Last Branch Record MSRs */ #define MSR_AMD64_LBR_SELECT 0xc000010e -/* Fam 17h MSRs */ -#define MSR_F17H_IRPERF 0xc00000e9 +/* Zen4 */ +#define MSR_ZEN4_BP_CFG 0xc001102e +#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5 +/* Zen 2 */ #define MSR_ZEN2_SPECTRAL_CHICKEN 0xc00110e3 #define MSR_ZEN2_SPECTRAL_CHICKEN_BIT BIT_ULL(1) +/* Fam 17h MSRs */ +#define MSR_F17H_IRPERF 0xc00000e9 + /* Fam 16h MSRs */ #define MSR_F16H_L2I_PERF_CTL 0xc0010230 #define MSR_F16H_L2I_PERF_CTR 0xc0010231 diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index ad98dd1d9cfb..c31c633419fe 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -129,7 +129,6 @@ void native_smp_send_reschedule(int cpu); void native_send_call_func_ipi(const struct cpumask *mask); void native_send_call_func_single_ipi(int cpu); -bool smp_park_other_cpus_in_init(void); void smp_store_cpu_info(int id); asmlinkage __visible void smp_reboot_interrupt(void); diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h index 19bf955b67e0..3ac0ffc4f3e2 100644 --- a/arch/x86/include/asm/svm.h +++ b/arch/x86/include/asm/svm.h @@ -268,6 +268,7 @@ enum avic_ipi_failure_cause { AVIC_IPI_FAILURE_TARGET_NOT_RUNNING, AVIC_IPI_FAILURE_INVALID_TARGET, AVIC_IPI_FAILURE_INVALID_BACKING_PAGE, + AVIC_IPI_FAILURE_INVALID_IPI_VECTOR, }; #define AVIC_PHYSICAL_MAX_INDEX_MASK GENMASK_ULL(8, 0) diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 517ee01503be..73be3931e4f0 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -403,6 +403,17 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, u8 insn_buff[MAX_PATCH_LEN]; DPRINTK(ALT, "alt table %px, -> %px", start, end); + + /* + * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using + * cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here. + * During the process, KASAN becomes confused seeing partial LA57 + * conversion and triggers a false-positive out-of-bound report. + * + * Disable KASAN until the patching is complete. + */ + kasan_disable_current(); + /* * The scan order should be from start to end. A later scanned * alternative code can overwrite previously scanned alternative code. @@ -452,6 +463,8 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, text_poke_early(instr, insn_buff, insn_buff_sz); } + + kasan_enable_current(); } static inline bool is_jcc32(struct insn *insn) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 03ef962a6992..ece2b5b7b0fe 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -80,6 +80,10 @@ static const int amd_div0[] = AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); +static const int amd_erratum_1485[] = + AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf), + AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf)); + static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) { int osvw_id = *erratum++; @@ -1149,6 +1153,10 @@ static void init_amd(struct cpuinfo_x86 *c) pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); setup_force_cpu_bug(X86_BUG_DIV0); } + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && + cpu_has_amd_erratum(c, amd_erratum_1485)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); } #ifdef CONFIG_X86_32 diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c index ded1fc7cb7cb..f136ac046851 100644 --- a/arch/x86/kernel/cpu/resctrl/monitor.c +++ b/arch/x86/kernel/cpu/resctrl/monitor.c @@ -30,15 +30,15 @@ struct rmid_entry { struct list_head list; }; -/** - * @rmid_free_lru A least recently used list of free RMIDs +/* + * @rmid_free_lru - A least recently used list of free RMIDs * These RMIDs are guaranteed to have an occupancy less than the * threshold occupancy */ static LIST_HEAD(rmid_free_lru); -/** - * @rmid_limbo_count count of currently unused but (potentially) +/* + * @rmid_limbo_count - count of currently unused but (potentially) * dirty RMIDs. * This counts RMIDs that no one is currently using but that * may have a occupancy value > resctrl_rmid_realloc_threshold. User can @@ -46,7 +46,7 @@ static LIST_HEAD(rmid_free_lru); */ static unsigned int rmid_limbo_count; -/** +/* * @rmid_entry - The entry in the limbo and free lists. */ static struct rmid_entry *rmid_ptrs; diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index a86d37052a64..a21a4d0ecc34 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest) EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate); void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, - unsigned int size, u32 pkru) + unsigned int size, u64 xfeatures, u32 pkru) { struct fpstate *kstate = gfpu->fpstate; union fpregs_state *ustate = buf; struct membuf mb = { .p = buf, .left = size }; if (cpu_feature_enabled(X86_FEATURE_XSAVE)) { - __copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE); + __copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru, + XSTATE_COPY_XSAVE); } else { memcpy(&ustate->fxsave, &kstate->regs.fxsave, sizeof(ustate->fxsave)); diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index cadf68737e6b..ef6906107c54 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -1049,6 +1049,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer * @to: membuf descriptor * @fpstate: The fpstate buffer from which to copy + * @xfeatures: The mask of xfeatures to save (XSAVE mode only) * @pkru_val: The PKRU value to store in the PKRU component * @copy_mode: The requested copy mode * @@ -1059,7 +1060,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate, * It supports partial copy but @to.pos always starts from zero. */ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode) + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode) { const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr); struct xregs_state *xinit = &init_fpstate.regs.xsave; @@ -1083,7 +1085,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, break; case XSTATE_COPY_XSAVE: - header.xfeatures &= fpstate->user_xfeatures; + header.xfeatures &= fpstate->user_xfeatures & xfeatures; break; } @@ -1185,6 +1187,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode copy_mode) { __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate, + tsk->thread.fpu.fpstate->user_xfeatures, tsk->thread.pkru, copy_mode); } @@ -1536,10 +1539,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize, fpregs_restore_userregs(); newfps->xfeatures = curfps->xfeatures | xfeatures; - - if (!guest_fpu) - newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; - + newfps->user_xfeatures = curfps->user_xfeatures | xfeatures; newfps->xfd = curfps->xfd & ~xfeatures; /* Do the final updates within the locked region */ diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index a4ecb04d8d64..3518fb26d06b 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -43,7 +43,8 @@ enum xstate_copy_mode { struct membuf; extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate, - u32 pkru_val, enum xstate_copy_mode copy_mode); + u64 xfeatures, u32 pkru_val, + enum xstate_copy_mode copy_mode); extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk, enum xstate_copy_mode mode); extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru); diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index dcf325b7b022..ccb0915e84e1 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -632,6 +632,23 @@ fail: sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); } +static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt, + unsigned long address, + bool write) +{ + if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) { + ctxt->fi.vector = X86_TRAP_PF; + ctxt->fi.error_code = X86_PF_USER; + ctxt->fi.cr2 = address; + if (write) + ctxt->fi.error_code |= X86_PF_WRITE; + + return ES_EXCEPTION; + } + + return ES_OK; +} + static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, void *src, char *buf, unsigned int data_size, @@ -639,7 +656,12 @@ static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt, bool backwards) { int i, b = backwards ? -1 : 1; - enum es_result ret = ES_OK; + unsigned long address = (unsigned long)src; + enum es_result ret; + + ret = vc_insn_string_check(ctxt, address, false); + if (ret != ES_OK) + return ret; for (i = 0; i < count; i++) { void *s = src + (i * data_size * b); @@ -660,7 +682,12 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, bool backwards) { int i, s = backwards ? -1 : 1; - enum es_result ret = ES_OK; + unsigned long address = (unsigned long)dst; + enum es_result ret; + + ret = vc_insn_string_check(ctxt, address, true); + if (ret != ES_OK) + return ret; for (i = 0; i < count; i++) { void *d = dst + (i * data_size * s); @@ -696,6 +723,9 @@ static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt, static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) { struct insn *insn = &ctxt->insn; + size_t size; + u64 port; + *exitinfo = 0; switch (insn->opcode.bytes[0]) { @@ -704,7 +734,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0x6d: *exitinfo |= IOIO_TYPE_INS; *exitinfo |= IOIO_SEG_ES; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* OUTS opcodes */ @@ -712,41 +742,43 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0x6f: *exitinfo |= IOIO_TYPE_OUTS; *exitinfo |= IOIO_SEG_DS; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* IN immediate opcodes */ case 0xe4: case 0xe5: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (u8)insn->immediate.value << 16; + port = (u8)insn->immediate.value & 0xffff; break; /* OUT immediate opcodes */ case 0xe6: case 0xe7: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (u8)insn->immediate.value << 16; + port = (u8)insn->immediate.value & 0xffff; break; /* IN register opcodes */ case 0xec: case 0xed: *exitinfo |= IOIO_TYPE_IN; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; /* OUT register opcodes */ case 0xee: case 0xef: *exitinfo |= IOIO_TYPE_OUT; - *exitinfo |= (ctxt->regs->dx & 0xffff) << 16; + port = ctxt->regs->dx & 0xffff; break; default: return ES_DECODE_FAILED; } + *exitinfo |= port << 16; + switch (insn->opcode.bytes[0]) { case 0x6c: case 0x6e: @@ -756,12 +788,15 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) case 0xee: /* Single byte opcodes */ *exitinfo |= IOIO_DATA_8; + size = 1; break; default: /* Length determined by instruction parsing */ *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16 : IOIO_DATA_32; + size = (insn->opnd_bytes == 2) ? 2 : 4; } + switch (insn->addr_bytes) { case 2: *exitinfo |= IOIO_ADDR_16; @@ -777,7 +812,7 @@ static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo) if (insn_has_rep_prefix(insn)) *exitinfo |= IOIO_REP; - return ES_OK; + return vc_ioio_check(ctxt, (u16)port, size); } static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index d8c1e3be74c0..6395bfd87b68 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -524,6 +524,33 @@ static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt return ES_OK; } +static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size) +{ + BUG_ON(size > 4); + + if (user_mode(ctxt->regs)) { + struct thread_struct *t = ¤t->thread; + struct io_bitmap *iobm = t->io_bitmap; + size_t idx; + + if (!iobm) + goto fault; + + for (idx = port; idx < port + size; ++idx) { + if (test_bit(idx, iobm->bitmap)) + goto fault; + } + } + + return ES_OK; + +fault: + ctxt->fi.vector = X86_TRAP_GP; + ctxt->fi.error_code = 0; + + return ES_EXCEPTION; +} + /* Include code shared with pre-decompression boot stage */ #include "sev-shared.c" @@ -1508,6 +1535,9 @@ static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt) return ES_DECODE_FAILED; } + if (user_mode(ctxt->regs)) + return ES_UNSUPPORTED; + switch (mmio) { case INSN_MMIO_WRITE: memcpy(ghcb->shared_buffer, reg_data, bytes); diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c index 6eb06d001bcc..96a771f9f930 100644 --- a/arch/x86/kernel/smp.c +++ b/arch/x86/kernel/smp.c @@ -131,7 +131,7 @@ static int smp_stop_nmi_callback(unsigned int val, struct pt_regs *regs) } /* - * Disable virtualization, APIC etc. and park the CPU in a HLT loop + * this function calls the 'stop' function on all other CPUs in the system. */ DEFINE_IDTENTRY_SYSVEC(sysvec_reboot) { @@ -172,17 +172,13 @@ static void native_stop_other_cpus(int wait) * 2) Wait for all other CPUs to report that they reached the * HLT loop in stop_this_cpu() * - * 3) If the system uses INIT/STARTUP for CPU bringup, then - * send all present CPUs an INIT vector, which brings them - * completely out of the way. + * 3) If #2 timed out send an NMI to the CPUs which did not + * yet report * - * 4) If #3 is not possible and #2 timed out send an NMI to the - * CPUs which did not yet report - * - * 5) Wait for all other CPUs to report that they reached the + * 4) Wait for all other CPUs to report that they reached the * HLT loop in stop_this_cpu() * - * #4 can obviously race against a CPU reaching the HLT loop late. + * #3 can obviously race against a CPU reaching the HLT loop late. * That CPU will have reported already and the "have all CPUs * reached HLT" condition will be true despite the fact that the * other CPU is still handling the NMI. Again, there is no @@ -198,7 +194,7 @@ static void native_stop_other_cpus(int wait) /* * Don't wait longer than a second for IPI completion. The * wait request is not checked here because that would - * prevent an NMI/INIT shutdown in case that not all + * prevent an NMI shutdown attempt in case that not all * CPUs reach shutdown state. */ timeout = USEC_PER_SEC; @@ -206,27 +202,7 @@ static void native_stop_other_cpus(int wait) udelay(1); } - /* - * Park all other CPUs in INIT including "offline" CPUs, if - * possible. That's a safe place where they can't resume execution - * of HLT and then execute the HLT loop from overwritten text or - * page tables. - * - * The only downside is a broadcast MCE, but up to the point where - * the kexec() kernel brought all APs online again an MCE will just - * make HLT resume and handle the MCE. The machine crashes and burns - * due to overwritten text, page tables and data. So there is a - * choice between fire and frying pan. The result is pretty much - * the same. Chose frying pan until x86 provides a sane mechanism - * to park a CPU. - */ - if (smp_park_other_cpus_in_init()) - goto done; - - /* - * If park with INIT was not possible and the REBOOT_VECTOR didn't - * take all secondary CPUs offline, try with the NMI. - */ + /* if the REBOOT_VECTOR didn't work, try with the NMI */ if (!cpumask_empty(&cpus_stop_mask)) { /* * If NMI IPI is enabled, try to register the stop handler @@ -249,7 +225,6 @@ static void native_stop_other_cpus(int wait) udelay(1); } -done: local_irq_save(flags); disable_local_APIC(); mcheck_cpu_clear(this_cpu_ptr(&cpu_info)); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 48e040618731..2a187c0cbd5b 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1240,33 +1240,6 @@ void arch_thaw_secondary_cpus_end(void) cache_aps_init(); } -bool smp_park_other_cpus_in_init(void) -{ - unsigned int cpu, this_cpu = smp_processor_id(); - unsigned int apicid; - - if (apic->wakeup_secondary_cpu_64 || apic->wakeup_secondary_cpu) - return false; - - /* - * If this is a crash stop which does not execute on the boot CPU, - * then this cannot use the INIT mechanism because INIT to the boot - * CPU will reset the machine. - */ - if (this_cpu) - return false; - - for_each_cpu_and(cpu, &cpus_booted_once_mask, cpu_present_mask) { - if (cpu == this_cpu) - continue; - apicid = apic->cpu_present_to_apicid(cpu); - if (apicid == BAD_APICID) - continue; - send_init_sequence(apicid); - } - return true; -} - /* * Early setup to make printk work. */ diff --git a/arch/x86/kernel/topology.c b/arch/x86/kernel/topology.c index ca004e2e4469..0bab03130033 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -54,7 +54,7 @@ void arch_unregister_cpu(int num) EXPORT_SYMBOL(arch_unregister_cpu); #else /* CONFIG_HOTPLUG_CPU */ -static int __init arch_register_cpu(int num) +int __init arch_register_cpu(int num) { return register_cpu(&per_cpu(cpu_devices, num).cpu, num); } diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0544e30b4946..773132c3bf5a 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -360,14 +360,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); - /* - * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if - * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't - * supported by the host. - */ - vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 | - XFEATURE_MASK_FPSSE; - kvm_update_pv_runtime(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index dcd60b39e794..3e977dbbf993 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2759,13 +2759,17 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) { u32 reg = kvm_lapic_get_reg(apic, lvt_type); int vector, mode, trig_mode; + int r; if (kvm_apic_hw_enabled(apic) && !(reg & APIC_LVT_MASKED)) { vector = reg & APIC_VECTOR_MASK; mode = reg & APIC_MODE_MASK; trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; - return __apic_accept_irq(apic, mode, vector, 1, trig_mode, - NULL); + + r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); + if (r && lvt_type == APIC_LVTPC) + kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); + return r; } return 0; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index edb89b51b383..9ae07db6f0f6 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,14 +93,6 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static void kvm_pmi_trigger_fn(struct irq_work *irq_work) -{ - struct kvm_pmu *pmu = container_of(irq_work, struct kvm_pmu, irq_work); - struct kvm_vcpu *vcpu = pmu_to_vcpu(pmu); - - kvm_pmu_deliver_pmi(vcpu); -} - static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -124,20 +116,7 @@ static inline void __kvm_perf_overflow(struct kvm_pmc *pmc, bool in_pmi) __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); } - if (!pmc->intr || skip_pmi) - return; - - /* - * Inject PMI. If vcpu was in a guest mode during NMI PMI - * can be ejected on a guest mode re-entry. Otherwise we can't - * be sure that vcpu wasn't executing hlt instruction at the - * time of vmexit and is not going to re-enter guest mode until - * woken up. So we should wake it, but this is impossible from - * NMI context. Do it from irq work instead. - */ - if (in_pmi && !kvm_handling_nmi_from_guest(pmc->vcpu)) - irq_work_queue(&pmc_to_pmu(pmc)->irq_work); - else + if (pmc->intr && !skip_pmi) kvm_make_request(KVM_REQ_PMI, pmc->vcpu); } @@ -675,9 +654,6 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) void kvm_pmu_reset(struct kvm_vcpu *vcpu) { - struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); - - irq_work_sync(&pmu->irq_work); static_call(kvm_x86_pmu_reset)(vcpu); } @@ -687,7 +663,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - init_irq_work(&pmu->irq_work, kvm_pmi_trigger_fn); pmu->event_count = 0; pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index 7d9ba301c090..1d64113de488 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -74,6 +74,12 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } +static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); +} + static inline void pmc_release_perf_event(struct kvm_pmc *pmc) { if (pmc->perf_event) { diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c index 2092db892d7d..4b74ea91f4e6 100644 --- a/arch/x86/kvm/svm/avic.c +++ b/arch/x86/kvm/svm/avic.c @@ -529,8 +529,11 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu) case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE: WARN_ONCE(1, "Invalid backing page\n"); break; + case AVIC_IPI_FAILURE_INVALID_IPI_VECTOR: + /* Invalid IPI with vector < 16 */ + break; default: - pr_err("Unknown IPI interception\n"); + vcpu_unimpl(vcpu, "Unknown avic incomplete IPI interception\n"); } return 1; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index dd496c9e5f91..3fea8c47679e 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -1253,6 +1253,9 @@ void svm_leave_nested(struct kvm_vcpu *vcpu) nested_svm_uninit_mmu_context(vcpu); vmcb_mark_all_dirty(svm->vmcb); + + if (kvm_apicv_activated(vcpu->kvm)) + kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cef5a3d0abd0..373ff6a6687b 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -160,7 +160,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) /* MSR_PERFCTRn */ pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); return 0; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 9507df93f410..beea99c8e8e0 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -691,7 +691,7 @@ static int svm_hardware_enable(void) */ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { struct sev_es_save_area *hostsa; - u32 msr_hi; + u32 __maybe_unused msr_hi; hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); @@ -913,8 +913,7 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept) if (intercept == svm->x2avic_msrs_intercepted) return; - if (!x2avic_enabled || - !apic_x2apic_mode(svm->vcpu.arch.apic)) + if (!x2avic_enabled) return; for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) { diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index f2efa0bf7ae8..820d3e1f6b4f 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -436,11 +436,11 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { - pmc->counter += data - pmc_read_counter(pmc); + pmc_write_counter(pmc, data); pmc_update_sample_period(pmc); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9f18b06bbda6..41cce5031126 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5382,26 +5382,37 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, return 0; } -static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, - struct kvm_xsave *guest_xsave) -{ - if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) - return; - - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - guest_xsave->region, - sizeof(guest_xsave->region), - vcpu->arch.pkru); -} static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, u8 *state, unsigned int size) { + /* + * Only copy state for features that are enabled for the guest. The + * state itself isn't problematic, but setting bits in the header for + * features that are supported in *this* host but not exposed to the + * guest can result in KVM_SET_XSAVE failing when live migrating to a + * compatible host without the features that are NOT exposed to the + * guest. + * + * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if + * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't + * supported by the host. + */ + u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 | + XFEATURE_MASK_FPSSE; + if (fpstate_is_confidential(&vcpu->arch.guest_fpu)) return; - fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, - state, size, vcpu->arch.pkru); + fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size, + supported_xcr0, vcpu->arch.pkru); +} + +static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, + struct kvm_xsave *guest_xsave) +{ + return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, @@ -12843,6 +12854,9 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) return true; #endif + if (kvm_test_request(KVM_REQ_PMI, vcpu)) + return true; + if (kvm_arch_interrupt_allowed(vcpu) && (kvm_cpu_has_interrupt(vcpu) || kvm_guest_apic_has_interrupt(vcpu))) diff --git a/block/fops.c b/block/fops.c index acff3d5d22d4..73e42742543f 100644 --- a/block/fops.c +++ b/block/fops.c @@ -772,24 +772,35 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start, filemap_invalidate_lock(inode->i_mapping); - /* Invalidate the page cache, including dirty pages. */ - error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end); - if (error) - goto fail; - + /* + * Invalidate the page cache, including dirty pages, for valid + * de-allocate mode calls to fallocate(). + */ switch (mode) { case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE: + error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end); + if (error) + goto fail; + error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE: + error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end); + if (error) + goto fail; + error = blkdev_issue_zeroout(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK); break; case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE: + error = truncate_bdev_range(bdev, file_to_blk_mode(file), start, end); + if (error) + goto fail; + error = blkdev_issue_discard(bdev, start >> SECTOR_SHIFT, len >> SECTOR_SHIFT, GFP_KERNEL); break; diff --git a/block/sed-opal.c b/block/sed-opal.c index 6d7f25d1711b..04f38a3f5d95 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -2888,12 +2888,11 @@ static int opal_lock_unlock(struct opal_dev *dev, if (lk_unlk->session.who > OPAL_USER9) return -EINVAL; - ret = opal_get_key(dev, &lk_unlk->session.opal_key); - if (ret) - return ret; mutex_lock(&dev->dev_lock); opal_lock_check_for_saved_key(dev, lk_unlk); - ret = __opal_lock_unlock(dev, lk_unlk); + ret = opal_get_key(dev, &lk_unlk->session.opal_key); + if (!ret) + ret = __opal_lock_unlock(dev, lk_unlk); mutex_unlock(&dev->dev_lock); return ret; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index abeecb8329b3..1dcab27986a6 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -81,14 +81,13 @@ software_key_determine_akcipher(const struct public_key *pkey, * RSA signatures usually use EMSA-PKCS1-1_5 [RFC3447 sec 8.2]. */ if (strcmp(encoding, "pkcs1") == 0) { + *sig = op == kernel_pkey_sign || + op == kernel_pkey_verify; if (!hash_algo) { - *sig = false; n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s)", pkey->pkey_algo); } else { - *sig = op == kernel_pkey_sign || - op == kernel_pkey_verify; n = snprintf(alg_name, CRYPTO_MAX_ALG_NAME, "pkcs1pad(%s,%s)", pkey->pkey_algo, hash_algo); diff --git a/drivers/accel/ivpu/ivpu_drv.c b/drivers/accel/ivpu/ivpu_drv.c index 467a60235370..7e9359611d69 100644 --- a/drivers/accel/ivpu/ivpu_drv.c +++ b/drivers/accel/ivpu/ivpu_drv.c @@ -367,14 +367,19 @@ int ivpu_boot(struct ivpu_device *vdev) return 0; } -int ivpu_shutdown(struct ivpu_device *vdev) +void ivpu_prepare_for_reset(struct ivpu_device *vdev) { - int ret; - ivpu_hw_irq_disable(vdev); disable_irq(vdev->irq); ivpu_ipc_disable(vdev); ivpu_mmu_disable(vdev); +} + +int ivpu_shutdown(struct ivpu_device *vdev) +{ + int ret; + + ivpu_prepare_for_reset(vdev); ret = ivpu_hw_power_down(vdev); if (ret) diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index 03b3d6532fb6..2adc349126bb 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -151,6 +151,7 @@ void ivpu_file_priv_put(struct ivpu_file_priv **link); int ivpu_boot(struct ivpu_device *vdev); int ivpu_shutdown(struct ivpu_device *vdev); +void ivpu_prepare_for_reset(struct ivpu_device *vdev); static inline u8 ivpu_revision(struct ivpu_device *vdev) { diff --git a/drivers/accel/ivpu/ivpu_fw.c b/drivers/accel/ivpu/ivpu_fw.c index 0191cf8e5964..a277bbae78fc 100644 --- a/drivers/accel/ivpu/ivpu_fw.c +++ b/drivers/accel/ivpu/ivpu_fw.c @@ -220,8 +220,7 @@ static int ivpu_fw_mem_init(struct ivpu_device *vdev) if (ret) return ret; - fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size, - DRM_IVPU_BO_CACHED | DRM_IVPU_BO_NOSNOOP); + fw->mem = ivpu_bo_alloc_internal(vdev, fw->runtime_addr, fw->runtime_size, DRM_IVPU_BO_WC); if (!fw->mem) { ivpu_err(vdev, "Failed to allocate firmware runtime memory\n"); return -ENOMEM; @@ -331,7 +330,7 @@ int ivpu_fw_load(struct ivpu_device *vdev) memset(start, 0, size); } - clflush_cache_range(fw->mem->kvaddr, fw->mem->base.size); + wmb(); /* Flush WC buffers after writing fw->mem */ return 0; } @@ -433,7 +432,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params if (!ivpu_fw_is_cold_boot(vdev)) { boot_params->save_restore_ret_address = 0; vdev->pm->is_warmboot = true; - clflush_cache_range(vdev->fw->mem->kvaddr, SZ_4K); + wmb(); /* Flush WC buffers after writing save_restore_ret_address */ return; } @@ -495,7 +494,7 @@ void ivpu_fw_boot_params_setup(struct ivpu_device *vdev, struct vpu_boot_params boot_params->punit_telemetry_sram_size = ivpu_hw_reg_telemetry_size_get(vdev); boot_params->vpu_telemetry_enable = ivpu_hw_reg_telemetry_enable_get(vdev); - clflush_cache_range(vdev->fw->mem->kvaddr, SZ_4K); + wmb(); /* Flush WC buffers after writing bootparams */ ivpu_fw_boot_params_print(vdev, boot_params); } diff --git a/drivers/accel/ivpu/ivpu_gem.h b/drivers/accel/ivpu/ivpu_gem.h index f4130586ff1b..6b0ceda5f253 100644 --- a/drivers/accel/ivpu/ivpu_gem.h +++ b/drivers/accel/ivpu/ivpu_gem.h @@ -8,8 +8,6 @@ #include <drm/drm_gem.h> #include <drm/drm_mm.h> -#define DRM_IVPU_BO_NOSNOOP 0x10000000 - struct dma_buf; struct ivpu_bo_ops; struct ivpu_file_priv; @@ -85,9 +83,6 @@ static inline u32 ivpu_bo_cache_mode(struct ivpu_bo *bo) static inline bool ivpu_bo_is_snooped(struct ivpu_bo *bo) { - if (bo->flags & DRM_IVPU_BO_NOSNOOP) - return false; - return ivpu_bo_cache_mode(bo) == DRM_IVPU_BO_CACHED; } diff --git a/drivers/accel/ivpu/ivpu_hw.h b/drivers/accel/ivpu/ivpu_hw.h index ab341237bcf9..1079e06255ba 100644 --- a/drivers/accel/ivpu/ivpu_hw.h +++ b/drivers/accel/ivpu/ivpu_hw.h @@ -13,6 +13,7 @@ struct ivpu_hw_ops { int (*power_up)(struct ivpu_device *vdev); int (*boot_fw)(struct ivpu_device *vdev); int (*power_down)(struct ivpu_device *vdev); + int (*reset)(struct ivpu_device *vdev); bool (*is_idle)(struct ivpu_device *vdev); void (*wdt_disable)(struct ivpu_device *vdev); void (*diagnose_failure)(struct ivpu_device *vdev); @@ -91,6 +92,13 @@ static inline int ivpu_hw_power_down(struct ivpu_device *vdev) return vdev->hw->ops->power_down(vdev); }; +static inline int ivpu_hw_reset(struct ivpu_device *vdev) +{ + ivpu_dbg(vdev, PM, "HW reset\n"); + + return vdev->hw->ops->reset(vdev); +}; + static inline void ivpu_hw_wdt_disable(struct ivpu_device *vdev) { vdev->hw->ops->wdt_disable(vdev); diff --git a/drivers/accel/ivpu/ivpu_hw_37xx.c b/drivers/accel/ivpu/ivpu_hw_37xx.c index 9eae1c241bc0..976019429164 100644 --- a/drivers/accel/ivpu/ivpu_hw_37xx.c +++ b/drivers/accel/ivpu/ivpu_hw_37xx.c @@ -1029,6 +1029,7 @@ const struct ivpu_hw_ops ivpu_hw_37xx_ops = { .power_up = ivpu_hw_37xx_power_up, .is_idle = ivpu_hw_37xx_is_idle, .power_down = ivpu_hw_37xx_power_down, + .reset = ivpu_hw_37xx_reset, .boot_fw = ivpu_hw_37xx_boot_fw, .wdt_disable = ivpu_hw_37xx_wdt_disable, .diagnose_failure = ivpu_hw_37xx_diagnose_failure, diff --git a/drivers/accel/ivpu/ivpu_hw_40xx.c b/drivers/accel/ivpu/ivpu_hw_40xx.c index 8bdb59a45da6..85171a408363 100644 --- a/drivers/accel/ivpu/ivpu_hw_40xx.c +++ b/drivers/accel/ivpu/ivpu_hw_40xx.c @@ -1179,6 +1179,7 @@ const struct ivpu_hw_ops ivpu_hw_40xx_ops = { .power_up = ivpu_hw_40xx_power_up, .is_idle = ivpu_hw_40xx_is_idle, .power_down = ivpu_hw_40xx_power_down, + .reset = ivpu_hw_40xx_reset, .boot_fw = ivpu_hw_40xx_boot_fw, .wdt_disable = ivpu_hw_40xx_wdt_disable, .diagnose_failure = ivpu_hw_40xx_diagnose_failure, diff --git a/drivers/accel/ivpu/ivpu_mmu_context.c b/drivers/accel/ivpu/ivpu_mmu_context.c index 1d2e554e2c4a..ce94f4029127 100644 --- a/drivers/accel/ivpu/ivpu_mmu_context.c +++ b/drivers/accel/ivpu/ivpu_mmu_context.c @@ -11,6 +11,7 @@ #include "ivpu_mmu.h" #include "ivpu_mmu_context.h" +#define IVPU_MMU_VPU_ADDRESS_MASK GENMASK(47, 12) #define IVPU_MMU_PGD_INDEX_MASK GENMASK(47, 39) #define IVPU_MMU_PUD_INDEX_MASK GENMASK(38, 30) #define IVPU_MMU_PMD_INDEX_MASK GENMASK(29, 21) @@ -328,12 +329,8 @@ ivpu_mmu_context_map_sgt(struct ivpu_device *vdev, struct ivpu_mmu_context *ctx, if (!IS_ALIGNED(vpu_addr, IVPU_MMU_PAGE_SIZE)) return -EINVAL; - /* - * VPU is only 32 bit, but DMA engine is 38 bit - * Ranges < 2 GB are reserved for VPU internal registers - * Limit range to 8 GB - */ - if (vpu_addr < SZ_2G || vpu_addr > SZ_8G) + + if (vpu_addr & ~IVPU_MMU_VPU_ADDRESS_MASK) return -EINVAL; prot = IVPU_MMU_ENTRY_MAPPED; diff --git a/drivers/accel/ivpu/ivpu_pm.c b/drivers/accel/ivpu/ivpu_pm.c index e6f27daf5560..ffff2496e8e8 100644 --- a/drivers/accel/ivpu/ivpu_pm.c +++ b/drivers/accel/ivpu/ivpu_pm.c @@ -261,7 +261,8 @@ void ivpu_pm_reset_prepare_cb(struct pci_dev *pdev) ivpu_dbg(vdev, PM, "Pre-reset..\n"); atomic_inc(&vdev->pm->reset_counter); atomic_set(&vdev->pm->in_reset, 1); - ivpu_shutdown(vdev); + ivpu_prepare_for_reset(vdev); + ivpu_hw_reset(vdev); ivpu_pm_prepare_cold_boot(vdev); ivpu_jobs_abort_all(vdev); ivpu_dbg(vdev, PM, "Pre-reset done.\n"); diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index c711db8a9c33..0f5218e361df 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) "ACPI: " fmt #include <linux/acpi.h> +#include <linux/cpu.h> #include <linux/device.h> #include <linux/dmi.h> #include <linux/kernel.h> diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c index f41dda2d3493..a4aa53b7e2bb 100644 --- a/drivers/acpi/bus.c +++ b/drivers/acpi/bus.c @@ -1410,10 +1410,10 @@ static int __init acpi_init(void) acpi_init_ffh(); pci_mmcfg_late_init(); - acpi_arm_init(); acpi_viot_early_init(); acpi_hest_init(); acpi_ghes_init(); + acpi_arm_init(); acpi_scan_init(); acpi_ec_init(); acpi_debugfs_init(); diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 660834a49c1f..c95d0edb0be9 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1915,6 +1915,17 @@ static const struct dmi_system_id ec_dmi_table[] __initconst = { }, { /* + * HP Pavilion Gaming Laptop 15-dk1xxx + * https://github.com/systemd/systemd/issues/28942 + */ + .callback = ec_honor_dsdt_gpe, + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "HP"), + DMI_MATCH(DMI_PRODUCT_NAME, "HP Pavilion Gaming Laptop 15-dk1xxx"), + }, + }, + { + /* * Samsung hardware * https://bugzilla.kernel.org/show_bug.cgi?id=44161 */ diff --git a/drivers/acpi/irq.c b/drivers/acpi/irq.c index c2c786eb95ab..1687483ff319 100644 --- a/drivers/acpi/irq.c +++ b/drivers/acpi/irq.c @@ -57,6 +57,7 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, int polarity) { struct irq_fwspec fwspec; + unsigned int irq; fwspec.fwnode = acpi_get_gsi_domain_id(gsi); if (WARN_ON(!fwspec.fwnode)) { @@ -68,7 +69,11 @@ int acpi_register_gsi(struct device *dev, u32 gsi, int trigger, fwspec.param[1] = acpi_dev_get_irq_type(trigger, polarity); fwspec.param_count = 2; - return irq_create_fwspec_mapping(&fwspec); + irq = irq_create_fwspec_mapping(&fwspec); + if (!irq) + return -EINVAL; + + return irq; } EXPORT_SYMBOL_GPL(acpi_register_gsi); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index f96bf32cd368..7d88db451cfb 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -3339,6 +3339,16 @@ static int acpi_nfit_add(struct acpi_device *adev) acpi_size sz; int rc = 0; + rc = acpi_dev_install_notify_handler(adev, ACPI_DEVICE_NOTIFY, + acpi_nfit_notify); + if (rc) + return rc; + + rc = devm_add_action_or_reset(dev, acpi_nfit_remove_notify_handler, + adev); + if (rc) + return rc; + status = acpi_get_table(ACPI_SIG_NFIT, 0, &tbl); if (ACPI_FAILURE(status)) { /* The NVDIMM root device allows OS to trigger enumeration of @@ -3386,17 +3396,7 @@ static int acpi_nfit_add(struct acpi_device *adev) if (rc) return rc; - rc = devm_add_action_or_reset(dev, acpi_nfit_shutdown, acpi_desc); - if (rc) - return rc; - - rc = acpi_dev_install_notify_handler(adev, ACPI_DEVICE_NOTIFY, - acpi_nfit_notify); - if (rc) - return rc; - - return devm_add_action_or_reset(dev, acpi_nfit_remove_notify_handler, - adev); + return devm_add_action_or_reset(dev, acpi_nfit_shutdown, acpi_desc); } static void acpi_nfit_update_notify(struct device *dev, acpi_handle handle) diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index 32cfa3f4efd3..297a88587031 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -440,6 +440,13 @@ static const struct dmi_system_id asus_laptop[] = { }, }, { + .ident = "Asus ExpertBook B1402CBA", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B1402CBA"), + }, + }, + { .ident = "Asus ExpertBook B1502CBA", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), @@ -500,16 +507,23 @@ static const struct dmi_system_id maingear_laptop[] = { static const struct dmi_system_id pcspecialist_laptop[] = { { - .ident = "PCSpecialist Elimina Pro 16 M", - /* - * Some models have product-name "Elimina Pro 16 M", - * others "GM6BGEQ". Match on board-name to match both. - */ + /* TongFang GM6BGEQ / PCSpecialist Elimina Pro 16 M, RTX 3050 */ .matches = { - DMI_MATCH(DMI_SYS_VENDOR, "PCSpecialist"), DMI_MATCH(DMI_BOARD_NAME, "GM6BGEQ"), }, }, + { + /* TongFang GM6BG5Q, RTX 4050 */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM6BG5Q"), + }, + }, + { + /* TongFang GM6BG0Q / PCSpecialist Elimina Pro 16 M, RTX 4060 */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GM6BG0Q"), + }, + }, { } }; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 367afac5f1bf..92128aae2d06 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -4812,6 +4812,8 @@ static void binder_release_work(struct binder_proc *proc, "undelivered TRANSACTION_ERROR: %u\n", e->cmd); } break; + case BINDER_WORK_TRANSACTION_PENDING: + case BINDER_WORK_TRANSACTION_ONEWAY_SPAM_SUSPECT: case BINDER_WORK_TRANSACTION_COMPLETE: { binder_debug(BINDER_DEBUG_DEAD_TRANSACTION, "undelivered TRANSACTION_COMPLETE\n"); diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c index 884cb51c8f67..234a84ecde8b 100644 --- a/drivers/base/regmap/regmap.c +++ b/drivers/base/regmap/regmap.c @@ -1478,7 +1478,7 @@ static int dev_get_regmap_match(struct device *dev, void *res, void *data) /* If the user didn't specify a name match any */ if (data) - return !strcmp((*r)->name, data); + return (*r)->name && !strcmp((*r)->name, data); else return 1; } diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c index f9a3444753c2..ff4868c83cd8 100644 --- a/drivers/bluetooth/btmtksdio.c +++ b/drivers/bluetooth/btmtksdio.c @@ -118,6 +118,7 @@ MODULE_DEVICE_TABLE(sdio, btmtksdio_table); #define BTMTKSDIO_FUNC_ENABLED 3 #define BTMTKSDIO_PATCH_ENABLED 4 #define BTMTKSDIO_HW_RESET_ACTIVE 5 +#define BTMTKSDIO_BT_WAKE_ENABLED 6 struct mtkbtsdio_hdr { __le16 len; @@ -554,7 +555,7 @@ static void btmtksdio_txrx_work(struct work_struct *work) sdio_claim_host(bdev->func); /* Disable interrupt */ - sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, 0); + sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, NULL); txrx_timeout = jiffies + 5 * HZ; @@ -576,7 +577,7 @@ static void btmtksdio_txrx_work(struct work_struct *work) if ((int_status & FW_MAILBOX_INT) && bdev->data->chipid == 0x7921) { sdio_writel(bdev->func, PH2DSM0R_DRIVER_OWN, - MTK_REG_PH2DSM0R, 0); + MTK_REG_PH2DSM0R, NULL); } if (int_status & FW_OWN_BACK_INT) @@ -608,7 +609,7 @@ static void btmtksdio_txrx_work(struct work_struct *work) } while (int_status || time_is_before_jiffies(txrx_timeout)); /* Enable interrupt */ - sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, 0); + sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, NULL); sdio_release_host(bdev->func); @@ -620,8 +621,14 @@ static void btmtksdio_interrupt(struct sdio_func *func) { struct btmtksdio_dev *bdev = sdio_get_drvdata(func); + if (test_bit(BTMTKSDIO_BT_WAKE_ENABLED, &bdev->tx_state)) { + if (bdev->hdev->suspended) + pm_wakeup_event(bdev->dev, 0); + clear_bit(BTMTKSDIO_BT_WAKE_ENABLED, &bdev->tx_state); + } + /* Disable interrupt */ - sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, 0); + sdio_writel(bdev->func, C_INT_EN_CLR, MTK_REG_CHLPCR, NULL); schedule_work(&bdev->txrx_work); } @@ -1454,6 +1461,23 @@ static int btmtksdio_runtime_suspend(struct device *dev) return err; } +static int btmtksdio_system_suspend(struct device *dev) +{ + struct sdio_func *func = dev_to_sdio_func(dev); + struct btmtksdio_dev *bdev; + + bdev = sdio_get_drvdata(func); + if (!bdev) + return 0; + + if (!test_bit(BTMTKSDIO_FUNC_ENABLED, &bdev->tx_state)) + return 0; + + set_bit(BTMTKSDIO_BT_WAKE_ENABLED, &bdev->tx_state); + + return btmtksdio_runtime_suspend(dev); +} + static int btmtksdio_runtime_resume(struct device *dev) { struct sdio_func *func = dev_to_sdio_func(dev); @@ -1474,8 +1498,16 @@ static int btmtksdio_runtime_resume(struct device *dev) return err; } -static UNIVERSAL_DEV_PM_OPS(btmtksdio_pm_ops, btmtksdio_runtime_suspend, - btmtksdio_runtime_resume, NULL); +static int btmtksdio_system_resume(struct device *dev) +{ + return btmtksdio_runtime_resume(dev); +} + +static const struct dev_pm_ops btmtksdio_pm_ops = { + SYSTEM_SLEEP_PM_OPS(btmtksdio_system_suspend, btmtksdio_system_resume) + RUNTIME_PM_OPS(btmtksdio_runtime_suspend, btmtksdio_runtime_resume, NULL) +}; + #define BTMTKSDIO_PM_OPS (&btmtksdio_pm_ops) #else /* CONFIG_PM */ #define BTMTKSDIO_PM_OPS NULL diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c index 5a35ac4138c6..fdb0fae88d1c 100644 --- a/drivers/bluetooth/btqca.c +++ b/drivers/bluetooth/btqca.c @@ -205,6 +205,44 @@ static int qca_send_reset(struct hci_dev *hdev) return 0; } +static int qca_read_fw_board_id(struct hci_dev *hdev, u16 *bid) +{ + u8 cmd; + struct sk_buff *skb; + struct edl_event_hdr *edl; + int err = 0; + + cmd = EDL_GET_BID_REQ_CMD; + skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN, + &cmd, 0, HCI_INIT_TIMEOUT); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + bt_dev_err(hdev, "Reading QCA board ID failed (%d)", err); + return err; + } + + edl = skb_pull_data(skb, sizeof(*edl)); + if (!edl) { + bt_dev_err(hdev, "QCA read board ID with no header"); + err = -EILSEQ; + goto out; + } + + if (edl->cresp != EDL_CMD_REQ_RES_EVT || + edl->rtype != EDL_GET_BID_REQ_CMD) { + bt_dev_err(hdev, "QCA Wrong packet: %d %d", edl->cresp, edl->rtype); + err = -EIO; + goto out; + } + + *bid = (edl->data[1] << 8) + edl->data[2]; + bt_dev_dbg(hdev, "%s: bid = %x", __func__, *bid); + +out: + kfree_skb(skb); + return err; +} + int qca_send_pre_shutdown_cmd(struct hci_dev *hdev) { struct sk_buff *skb; @@ -574,6 +612,23 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr) } EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome); +static void qca_generate_hsp_nvm_name(char *fwname, size_t max_size, + struct qca_btsoc_version ver, u8 rom_ver, u16 bid) +{ + const char *variant; + + /* hsp gf chip */ + if ((le32_to_cpu(ver.soc_id) & QCA_HSP_GF_SOC_MASK) == QCA_HSP_GF_SOC_ID) + variant = "g"; + else + variant = ""; + + if (bid == 0x0) + snprintf(fwname, max_size, "qca/hpnv%02x%s.bin", rom_ver, variant); + else + snprintf(fwname, max_size, "qca/hpnv%02x%s.%x", rom_ver, variant, bid); +} + int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, enum qca_btsoc_type soc_type, struct qca_btsoc_version ver, const char *firmware_name) @@ -582,6 +637,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, int err; u8 rom_ver = 0; u32 soc_ver; + u16 boardid = 0; bt_dev_dbg(hdev, "QCA setup on UART"); @@ -615,6 +671,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, snprintf(config.fwname, sizeof(config.fwname), "qca/apbtfw%02x.tlv", rom_ver); break; + case QCA_QCA2066: + snprintf(config.fwname, sizeof(config.fwname), + "qca/hpbtfw%02x.tlv", rom_ver); + break; case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), "qca/htbtfw%02x.tlv", rom_ver); @@ -649,6 +709,9 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, /* Give the controller some time to get ready to receive the NVM */ msleep(10); + if (soc_type == QCA_QCA2066) + qca_read_fw_board_id(hdev, &boardid); + /* Download NVM configuration */ config.type = TLV_TYPE_NVM; if (firmware_name) { @@ -671,6 +734,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, snprintf(config.fwname, sizeof(config.fwname), "qca/apnv%02x.bin", rom_ver); break; + case QCA_QCA2066: + qca_generate_hsp_nvm_name(config.fwname, + sizeof(config.fwname), ver, rom_ver, boardid); + break; case QCA_QCA6390: snprintf(config.fwname, sizeof(config.fwname), "qca/htnv%02x.bin", rom_ver); @@ -702,6 +769,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate, switch (soc_type) { case QCA_WCN3991: + case QCA_QCA2066: case QCA_QCA6390: case QCA_WCN6750: case QCA_WCN6855: diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h index 03bff5c0059d..dc31984f71dc 100644 --- a/drivers/bluetooth/btqca.h +++ b/drivers/bluetooth/btqca.h @@ -12,6 +12,7 @@ #define EDL_PATCH_VER_REQ_CMD (0x19) #define EDL_PATCH_TLV_REQ_CMD (0x1E) #define EDL_GET_BUILD_INFO_CMD (0x20) +#define EDL_GET_BID_REQ_CMD (0x23) #define EDL_NVM_ACCESS_SET_REQ_CMD (0x01) #define EDL_PATCH_CONFIG_CMD (0x28) #define MAX_SIZE_PER_TLV_SEGMENT (243) @@ -47,7 +48,8 @@ ((le32_to_cpu(soc_id) << 16) | (le16_to_cpu(rom_ver))) #define QCA_FW_BUILD_VER_LEN 255 - +#define QCA_HSP_GF_SOC_ID 0x1200 +#define QCA_HSP_GF_SOC_MASK 0x0000ff00 enum qca_baudrate { QCA_BAUDRATE_115200 = 0, @@ -146,6 +148,7 @@ enum qca_btsoc_type { QCA_WCN3990, QCA_WCN3998, QCA_WCN3991, + QCA_QCA2066, QCA_QCA6390, QCA_WCN6750, QCA_WCN6855, diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 84c2c2e1122f..277d039ecbb4 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -962,13 +962,10 @@ static void btrtl_dmp_hdr(struct hci_dev *hdev, struct sk_buff *skb) skb_put_data(skb, buf, strlen(buf)); } -static int btrtl_register_devcoredump_support(struct hci_dev *hdev) +static void btrtl_register_devcoredump_support(struct hci_dev *hdev) { - int err; + hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL); - err = hci_devcd_register(hdev, btrtl_coredump, btrtl_dmp_hdr, NULL); - - return err; } void btrtl_set_driver_name(struct hci_dev *hdev, const char *driver_name) @@ -1255,8 +1252,7 @@ int btrtl_download_firmware(struct hci_dev *hdev, } done: - if (!err) - err = btrtl_register_devcoredump_support(hdev); + btrtl_register_devcoredump_support(hdev); return err; } diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 499f4809fcdf..b8e9de887b5d 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -477,6 +477,7 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x8087, 0x0033), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x0035), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x0036), .driver_info = BTUSB_INTEL_COMBINED }, + { USB_DEVICE(0x8087, 0x0038), .driver_info = BTUSB_INTEL_COMBINED }, { USB_DEVICE(0x8087, 0x07da), .driver_info = BTUSB_CSR }, { USB_DEVICE(0x8087, 0x07dc), .driver_info = BTUSB_INTEL_COMBINED | BTUSB_INTEL_NO_WBS_SUPPORT | @@ -543,6 +544,10 @@ static const struct usb_device_id quirks_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x0bda, 0x887b), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0bda, 0xb85b), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3570), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, @@ -644,6 +649,9 @@ static const struct usb_device_id quirks_table[] = { { USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK | BTUSB_WIDEBAND_SPEECH | BTUSB_VALID_LE_STATES }, + { USB_DEVICE(0x35f5, 0x7922), .driver_info = BTUSB_MEDIATEK | + BTUSB_WIDEBAND_SPEECH | + BTUSB_VALID_LE_STATES }, /* Additional Realtek 8723AE Bluetooth devices */ { USB_DEVICE(0x0930, 0x021d), .driver_info = BTUSB_REALTEK }, @@ -2818,6 +2826,9 @@ static int btusb_mtk_hci_wmt_sync(struct hci_dev *hdev, goto err_free_wc; } + if (data->evt_skb == NULL) + goto err_free_wc; + /* Parse and handle the return WMT event */ wmt_evt = (struct btmtk_hci_wmt_evt *)data->evt_skb->data; if (wmt_evt->whdr.op != hdr->op) { diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c index 19ad0e788646..a61757835695 100644 --- a/drivers/bluetooth/hci_bcm4377.c +++ b/drivers/bluetooth/hci_bcm4377.c @@ -512,6 +512,7 @@ struct bcm4377_hw { unsigned long disable_aspm : 1; unsigned long broken_ext_scan : 1; unsigned long broken_mws_transport_config : 1; + unsigned long broken_le_coded : 1; int (*send_calibration)(struct bcm4377_data *bcm4377); int (*send_ptb)(struct bcm4377_data *bcm4377, @@ -2372,6 +2373,8 @@ static int bcm4377_probe(struct pci_dev *pdev, const struct pci_device_id *id) set_bit(HCI_QUIRK_BROKEN_MWS_TRANSPORT_CONFIG, &hdev->quirks); if (bcm4377->hw->broken_ext_scan) set_bit(HCI_QUIRK_BROKEN_EXT_SCAN, &hdev->quirks); + if (bcm4377->hw->broken_le_coded) + set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks); pci_set_drvdata(pdev, bcm4377); hci_set_drvdata(hdev, bcm4377); @@ -2461,6 +2464,7 @@ static const struct bcm4377_hw bcm4377_hw_variants[] = { .bar0_core2_window2 = 0x18107000, .has_bar0_core2_window2 = true, .broken_mws_transport_config = true, + .broken_le_coded = true, .send_calibration = bcm4378_send_calibration, .send_ptb = bcm4378_send_ptb, }, @@ -2474,6 +2478,7 @@ static const struct bcm4377_hw bcm4377_hw_variants[] = { .has_bar0_core2_window2 = true, .clear_pciecfg_subsystem_ctrl_bit19 = true, .broken_mws_transport_config = true, + .broken_le_coded = true, .send_calibration = bcm4387_send_calibration, .send_ptb = bcm4378_send_ptb, }, diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c index 4b57e15f9c7a..067e248e3599 100644 --- a/drivers/bluetooth/hci_qca.c +++ b/drivers/bluetooth/hci_qca.c @@ -1841,6 +1841,10 @@ static int qca_setup(struct hci_uart *hu) set_bit(HCI_QUIRK_SIMULTANEOUS_DISCOVERY, &hdev->quirks); switch (soc_type) { + case QCA_QCA2066: + soc_name = "qca2066"; + break; + case QCA_WCN3988: case QCA_WCN3990: case QCA_WCN3991: @@ -2032,6 +2036,11 @@ static const struct qca_device_data qca_soc_data_wcn3998 __maybe_unused = { .num_vregs = 4, }; +static const struct qca_device_data qca_soc_data_qca2066 __maybe_unused = { + .soc_type = QCA_QCA2066, + .num_vregs = 0, +}; + static const struct qca_device_data qca_soc_data_qca6390 __maybe_unused = { .soc_type = QCA_QCA6390, .num_vregs = 0, @@ -2559,6 +2568,7 @@ static SIMPLE_DEV_PM_OPS(qca_pm_ops, qca_suspend, qca_resume); #ifdef CONFIG_OF static const struct of_device_id qca_bluetooth_of_match[] = { + { .compatible = "qcom,qca2066-bt", .data = &qca_soc_data_qca2066}, { .compatible = "qcom,qca6174-bt" }, { .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390}, { .compatible = "qcom,qca9377-bt" }, @@ -2576,6 +2586,7 @@ MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match); #ifdef CONFIG_ACPI static const struct acpi_device_id qca_bluetooth_acpi_match[] = { + { "QCOM2066", (kernel_ulong_t)&qca_soc_data_qca2066 }, { "QCOM6390", (kernel_ulong_t)&qca_soc_data_qca6390 }, { "DLA16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, { "DLB16390", (kernel_ulong_t)&qca_soc_data_qca6390 }, diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c index 40e2b9fa11a2..f3892e9ce800 100644 --- a/drivers/bluetooth/hci_vhci.c +++ b/drivers/bluetooth/hci_vhci.c @@ -74,7 +74,10 @@ static int vhci_send_frame(struct hci_dev *hdev, struct sk_buff *skb) struct vhci_data *data = hci_get_drvdata(hdev); memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1); + + mutex_lock(&data->open_mutex); skb_queue_tail(&data->readq, skb); + mutex_unlock(&data->open_mutex); wake_up_interruptible(&data->read_wait); return 0; diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 05d562e9c8b1..44b19e696176 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -54,7 +54,7 @@ static int cn_filter(struct sock *dsk, struct sk_buff *skb, void *data) enum proc_cn_mcast_op mc_op; uintptr_t val; - if (!dsk || !data) + if (!dsk || !dsk->sk_user_data || !data) return 0; ptr = (__u32 *)data; diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c index 80acdf62794a..afc94d0062b1 100644 --- a/drivers/counter/counter-chrdev.c +++ b/drivers/counter/counter-chrdev.c @@ -247,8 +247,8 @@ static int counter_get_ext(const struct counter_comp *const ext, if (*id == component_id) return 0; - if (ext->type == COUNTER_COMP_ARRAY) { - element = ext->priv; + if (ext[*ext_idx].type == COUNTER_COMP_ARRAY) { + element = ext[*ext_idx].priv; if (component_id - *id < element->length) return 0; diff --git a/drivers/counter/microchip-tcb-capture.c b/drivers/counter/microchip-tcb-capture.c index 975e431d1590..b3e615cbd2ca 100644 --- a/drivers/counter/microchip-tcb-capture.c +++ b/drivers/counter/microchip-tcb-capture.c @@ -97,7 +97,7 @@ static int mchp_tc_count_function_write(struct counter_device *counter, priv->qdec_mode = 0; /* Set highest rate based on whether soc has gclk or not */ bmr &= ~(ATMEL_TC_QDEN | ATMEL_TC_POSEN); - if (priv->tc_cfg->has_gclk) + if (!priv->tc_cfg->has_gclk) cmr |= ATMEL_TC_TIMER_CLOCK2; else cmr |= ATMEL_TC_TIMER_CLOCK1; diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h index 59a4c0259456..154590e1f764 100644 --- a/drivers/crypto/virtio/virtio_crypto_common.h +++ b/drivers/crypto/virtio/virtio_crypto_common.h @@ -35,6 +35,9 @@ struct virtio_crypto { struct virtqueue *ctrl_vq; struct data_queue *data_vq; + /* Work struct for config space updates */ + struct work_struct config_work; + /* To protect the vq operations for the controlq */ spinlock_t ctrl_lock; diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c index 94849fa3bd74..43a0838d31ff 100644 --- a/drivers/crypto/virtio/virtio_crypto_core.c +++ b/drivers/crypto/virtio/virtio_crypto_core.c @@ -335,6 +335,14 @@ static void virtcrypto_del_vqs(struct virtio_crypto *vcrypto) virtcrypto_free_queues(vcrypto); } +static void vcrypto_config_changed_work(struct work_struct *work) +{ + struct virtio_crypto *vcrypto = + container_of(work, struct virtio_crypto, config_work); + + virtcrypto_update_status(vcrypto); +} + static int virtcrypto_probe(struct virtio_device *vdev) { int err = -EFAULT; @@ -454,6 +462,8 @@ static int virtcrypto_probe(struct virtio_device *vdev) if (err) goto free_engines; + INIT_WORK(&vcrypto->config_work, vcrypto_config_changed_work); + return 0; free_engines: @@ -490,6 +500,7 @@ static void virtcrypto_remove(struct virtio_device *vdev) dev_info(&vdev->dev, "Start virtcrypto_remove.\n"); + flush_work(&vcrypto->config_work); if (virtcrypto_dev_started(vcrypto)) virtcrypto_dev_stop(vcrypto); virtio_reset_device(vdev); @@ -504,7 +515,7 @@ static void virtcrypto_config_changed(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; - virtcrypto_update_status(vcrypto); + schedule_work(&vcrypto->config_work); } #ifdef CONFIG_PM_SLEEP @@ -512,6 +523,7 @@ static int virtcrypto_freeze(struct virtio_device *vdev) { struct virtio_crypto *vcrypto = vdev->priv; + flush_work(&vcrypto->config_work); virtio_reset_device(vdev); virtcrypto_free_unused_reqs(vcrypto); if (virtcrypto_dev_started(vcrypto)) diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c index c625bb2b5d56..628af51c81af 100644 --- a/drivers/dma-buf/dma-fence-unwrap.c +++ b/drivers/dma-buf/dma-fence-unwrap.c @@ -76,16 +76,11 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences, dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) { if (!dma_fence_is_signaled(tmp)) { ++count; - } else if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, - &tmp->flags)) { - if (ktime_after(tmp->timestamp, timestamp)) - timestamp = tmp->timestamp; } else { - /* - * Use the current time if the fence is - * currently signaling. - */ - timestamp = ktime_get(); + ktime_t t = dma_fence_timestamp(tmp); + + if (ktime_after(t, timestamp)) + timestamp = t; } } } diff --git a/drivers/dma-buf/sync_file.c b/drivers/dma-buf/sync_file.c index af57799c86ce..2e9a316c596a 100644 --- a/drivers/dma-buf/sync_file.c +++ b/drivers/dma-buf/sync_file.c @@ -268,13 +268,10 @@ static int sync_fill_fence_info(struct dma_fence *fence, sizeof(info->driver_name)); info->status = dma_fence_get_status(fence); - while (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) && - !test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) - cpu_relax(); info->timestamp_ns = - test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags) ? - ktime_to_ns(fence->timestamp) : - ktime_set(0, 0); + dma_fence_is_signaled(fence) ? + ktime_to_ns(dma_fence_timestamp(fence)) : + ktime_set(0, 0); return info->status; } diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c index a0f5741abcc4..6a3abe5b1790 100644 --- a/drivers/dma/fsl-edma-common.c +++ b/drivers/dma/fsl-edma-common.c @@ -92,8 +92,14 @@ static void fsl_edma3_enable_request(struct fsl_edma_chan *fsl_chan) edma_writel_chreg(fsl_chan, val, ch_sbr); - if (flags & FSL_EDMA_DRV_HAS_CHMUX) - edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux); + if (flags & FSL_EDMA_DRV_HAS_CHMUX) { + /* + * ch_mux: With the exception of 0, attempts to write a value + * already in use will be forced to 0. + */ + if (!edma_readl_chreg(fsl_chan, ch_mux)) + edma_writel_chreg(fsl_chan, fsl_chan->srcid, ch_mux); + } val = edma_readl_chreg(fsl_chan, ch_csr); val |= EDMA_V3_CH_CSR_ERQ; @@ -448,12 +454,25 @@ static void fsl_edma_set_tcd_regs(struct fsl_edma_chan *fsl_chan, edma_write_tcdreg(fsl_chan, tcd->dlast_sga, dlast_sga); + csr = le16_to_cpu(tcd->csr); + if (fsl_chan->is_sw) { - csr = le16_to_cpu(tcd->csr); csr |= EDMA_TCD_CSR_START; tcd->csr = cpu_to_le16(csr); } + /* + * Must clear CHn_CSR[DONE] bit before enable TCDn_CSR[ESG] at EDMAv3 + * eDMAv4 have not such requirement. + * Change MLINK need clear CHn_CSR[DONE] for both eDMAv3 and eDMAv4. + */ + if (((fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_CLEAR_DONE_E_SG) && + (csr & EDMA_TCD_CSR_E_SG)) || + ((fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_CLEAR_DONE_E_LINK) && + (csr & EDMA_TCD_CSR_E_LINK))) + edma_writel_chreg(fsl_chan, edma_readl_chreg(fsl_chan, ch_csr), ch_csr); + + edma_write_tcdreg(fsl_chan, tcd->csr, csr); } diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h index 3cc0cc8fc2d0..40d50cc3d75a 100644 --- a/drivers/dma/fsl-edma-common.h +++ b/drivers/dma/fsl-edma-common.h @@ -183,11 +183,23 @@ struct fsl_edma_desc { #define FSL_EDMA_DRV_BUS_8BYTE BIT(10) #define FSL_EDMA_DRV_DEV_TO_DEV BIT(11) #define FSL_EDMA_DRV_ALIGN_64BYTE BIT(12) +/* Need clean CHn_CSR DONE before enable TCD's ESG */ +#define FSL_EDMA_DRV_CLEAR_DONE_E_SG BIT(13) +/* Need clean CHn_CSR DONE before enable TCD's MAJORELINK */ +#define FSL_EDMA_DRV_CLEAR_DONE_E_LINK BIT(14) #define FSL_EDMA_DRV_EDMA3 (FSL_EDMA_DRV_SPLIT_REG | \ FSL_EDMA_DRV_BUS_8BYTE | \ FSL_EDMA_DRV_DEV_TO_DEV | \ - FSL_EDMA_DRV_ALIGN_64BYTE) + FSL_EDMA_DRV_ALIGN_64BYTE | \ + FSL_EDMA_DRV_CLEAR_DONE_E_SG | \ + FSL_EDMA_DRV_CLEAR_DONE_E_LINK) + +#define FSL_EDMA_DRV_EDMA4 (FSL_EDMA_DRV_SPLIT_REG | \ + FSL_EDMA_DRV_BUS_8BYTE | \ + FSL_EDMA_DRV_DEV_TO_DEV | \ + FSL_EDMA_DRV_ALIGN_64BYTE | \ + FSL_EDMA_DRV_CLEAR_DONE_E_LINK) struct fsl_edma_drvdata { u32 dmamuxs; /* only used before v3 */ diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c index 63d48d046f04..8c4ed7012e23 100644 --- a/drivers/dma/fsl-edma-main.c +++ b/drivers/dma/fsl-edma-main.c @@ -154,18 +154,20 @@ static struct dma_chan *fsl_edma3_xlate(struct of_phandle_args *dma_spec, fsl_chan = to_fsl_edma_chan(chan); i = fsl_chan - fsl_edma->chans; - chan = dma_get_slave_channel(chan); - chan->device->privatecnt++; fsl_chan->priority = dma_spec->args[1]; fsl_chan->is_rxchan = dma_spec->args[2] & ARGS_RX; fsl_chan->is_remote = dma_spec->args[2] & ARGS_REMOTE; fsl_chan->is_multi_fifo = dma_spec->args[2] & ARGS_MULTI_FIFO; if (!b_chmux && i == dma_spec->args[0]) { + chan = dma_get_slave_channel(chan); + chan->device->privatecnt++; mutex_unlock(&fsl_edma->fsl_edma_mutex); return chan; } else if (b_chmux && !fsl_chan->srcid) { /* if controller support channel mux, choose a free channel */ + chan = dma_get_slave_channel(chan); + chan->device->privatecnt++; fsl_chan->srcid = dma_spec->args[0]; mutex_unlock(&fsl_edma->fsl_edma_mutex); return chan; @@ -355,7 +357,7 @@ static struct fsl_edma_drvdata imx93_data3 = { }; static struct fsl_edma_drvdata imx93_data4 = { - .flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA3, + .flags = FSL_EDMA_DRV_HAS_CHMUX | FSL_EDMA_DRV_HAS_DMACLK | FSL_EDMA_DRV_EDMA4, .chreg_space_sz = 0x8000, .chreg_off = 0x10000, .setup_irq = fsl_edma3_irq_init, diff --git a/drivers/dma/idxd/device.c b/drivers/dma/idxd/device.c index 22d6f4e455b7..8f754f922217 100644 --- a/drivers/dma/idxd/device.c +++ b/drivers/dma/idxd/device.c @@ -477,6 +477,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand, union idxd_command_reg cmd; DECLARE_COMPLETION_ONSTACK(done); u32 stat; + unsigned long flags; if (idxd_device_is_halted(idxd)) { dev_warn(&idxd->pdev->dev, "Device is HALTED!\n"); @@ -490,7 +491,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand, cmd.operand = operand; cmd.int_req = 1; - spin_lock(&idxd->cmd_lock); + spin_lock_irqsave(&idxd->cmd_lock, flags); wait_event_lock_irq(idxd->cmd_waitq, !test_bit(IDXD_FLAG_CMD_RUNNING, &idxd->flags), idxd->cmd_lock); @@ -507,7 +508,7 @@ static void idxd_cmd_exec(struct idxd_device *idxd, int cmd_code, u32 operand, * After command submitted, release lock and go to sleep until * the command completes via interrupt. */ - spin_unlock(&idxd->cmd_lock); + spin_unlock_irqrestore(&idxd->cmd_lock, flags); wait_for_completion(&done); stat = ioread32(idxd->reg_base + IDXD_CMDSTS_OFFSET); spin_lock(&idxd->cmd_lock); diff --git a/drivers/dma/mediatek/mtk-uart-apdma.c b/drivers/dma/mediatek/mtk-uart-apdma.c index c51dc017b48a..06d12ac39144 100644 --- a/drivers/dma/mediatek/mtk-uart-apdma.c +++ b/drivers/dma/mediatek/mtk-uart-apdma.c @@ -450,9 +450,8 @@ static int mtk_uart_apdma_device_pause(struct dma_chan *chan) mtk_uart_apdma_write(c, VFF_EN, VFF_EN_CLR_B); mtk_uart_apdma_write(c, VFF_INT_EN, VFF_INT_EN_CLR_B); - synchronize_irq(c->irq); - spin_unlock_irqrestore(&c->vc.lock, flags); + synchronize_irq(c->irq); return 0; } diff --git a/drivers/dma/ste_dma40.c b/drivers/dma/ste_dma40.c index 89e82508c133..002833fb1fa0 100644 --- a/drivers/dma/ste_dma40.c +++ b/drivers/dma/ste_dma40.c @@ -3668,6 +3668,7 @@ static int __init d40_probe(struct platform_device *pdev) regulator_disable(base->lcpa_regulator); regulator_put(base->lcpa_regulator); } + pm_runtime_disable(base->dev); report_failure: d40_err(dev, "probe failed\n"); diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 5c36811aa134..0b30151fb45c 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -1113,8 +1113,10 @@ static struct dma_async_tx_descriptor *stm32_dma_prep_slave_sg( chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_PFCTRL; /* Activate Double Buffer Mode if DMA triggers STM32 MDMA and more than 1 sg */ - if (chan->trig_mdma && sg_len > 1) + if (chan->trig_mdma && sg_len > 1) { chan->chan_reg.dma_scr |= STM32_DMA_SCR_DBM; + chan->chan_reg.dma_scr &= ~STM32_DMA_SCR_CT; + } for_each_sg(sgl, sg, sg_len, i) { ret = stm32_dma_set_xfer_param(chan, direction, &buswidth, @@ -1387,11 +1389,12 @@ static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan, residue = stm32_dma_get_remaining_bytes(chan); - if (chan->desc->cyclic && !stm32_dma_is_current_sg(chan)) { + if ((chan->desc->cyclic || chan->trig_mdma) && !stm32_dma_is_current_sg(chan)) { n_sg++; if (n_sg == chan->desc->num_sgs) n_sg = 0; - residue = sg_req->len; + if (!chan->trig_mdma) + residue = sg_req->len; } /* @@ -1401,7 +1404,7 @@ static size_t stm32_dma_desc_residue(struct stm32_dma_chan *chan, * residue = remaining bytes from NDTR + remaining * periods/sg to be transferred */ - if (!chan->desc->cyclic || n_sg != 0) + if ((!chan->desc->cyclic && !chan->trig_mdma) || n_sg != 0) for (i = n_sg; i < desc->num_sgs; i++) residue += desc->sg_req[i].len; diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 0de234022c6d..bae08b3f55c7 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -777,8 +777,6 @@ static int stm32_mdma_setup_xfer(struct stm32_mdma_chan *chan, /* Enable interrupts */ ccr &= ~STM32_MDMA_CCR_IRQ_MASK; ccr |= STM32_MDMA_CCR_TEIE | STM32_MDMA_CCR_CTCIE; - if (sg_len > 1) - ccr |= STM32_MDMA_CCR_BTIE; desc->ccr = ccr; return 0; @@ -1236,6 +1234,10 @@ static int stm32_mdma_resume(struct dma_chan *c) unsigned long flags; u32 status, reg; + /* Transfer can be terminated */ + if (!chan->desc || (stm32_mdma_read(dmadev, STM32_MDMA_CCR(chan->id)) & STM32_MDMA_CCR_EN)) + return -EPERM; + hwdesc = chan->desc->node[chan->curr_hwdesc].hwdesc; spin_lock_irqsave(&chan->vchan.lock, flags); @@ -1316,21 +1318,35 @@ static int stm32_mdma_slave_config(struct dma_chan *c, static size_t stm32_mdma_desc_residue(struct stm32_mdma_chan *chan, struct stm32_mdma_desc *desc, - u32 curr_hwdesc) + u32 curr_hwdesc, + struct dma_tx_state *state) { struct stm32_mdma_device *dmadev = stm32_mdma_get_dev(chan); struct stm32_mdma_hwdesc *hwdesc; - u32 cbndtr, residue, modulo, burst_size; + u32 cisr, clar, cbndtr, residue, modulo, burst_size; int i; + cisr = stm32_mdma_read(dmadev, STM32_MDMA_CISR(chan->id)); + residue = 0; - for (i = curr_hwdesc + 1; i < desc->count; i++) { + /* Get the next hw descriptor to process from current transfer */ + clar = stm32_mdma_read(dmadev, STM32_MDMA_CLAR(chan->id)); + for (i = desc->count - 1; i >= 0; i--) { hwdesc = desc->node[i].hwdesc; + + if (hwdesc->clar == clar) + break;/* Current transfer found, stop cumulating */ + + /* Cumulate residue of unprocessed hw descriptors */ residue += STM32_MDMA_CBNDTR_BNDT(hwdesc->cbndtr); } cbndtr = stm32_mdma_read(dmadev, STM32_MDMA_CBNDTR(chan->id)); residue += cbndtr & STM32_MDMA_CBNDTR_BNDT_MASK; + state->in_flight_bytes = 0; + if (chan->chan_config.m2m_hw && (cisr & STM32_MDMA_CISR_CRQA)) + state->in_flight_bytes = cbndtr & STM32_MDMA_CBNDTR_BNDT_MASK; + if (!chan->mem_burst) return residue; @@ -1360,11 +1376,10 @@ static enum dma_status stm32_mdma_tx_status(struct dma_chan *c, vdesc = vchan_find_desc(&chan->vchan, cookie); if (chan->desc && cookie == chan->desc->vdesc.tx.cookie) - residue = stm32_mdma_desc_residue(chan, chan->desc, - chan->curr_hwdesc); + residue = stm32_mdma_desc_residue(chan, chan->desc, chan->curr_hwdesc, state); else if (vdesc) - residue = stm32_mdma_desc_residue(chan, - to_stm32_mdma_desc(vdesc), 0); + residue = stm32_mdma_desc_residue(chan, to_stm32_mdma_desc(vdesc), 0, state); + dma_set_residue(state, residue); spin_unlock_irqrestore(&chan->vchan.lock, flags); diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c index ce20a60676f0..1974f0ad32ba 100644 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@ -273,9 +273,13 @@ static __init int efivar_ssdt_load(void) if (status == EFI_NOT_FOUND) { break; } else if (status == EFI_BUFFER_TOO_SMALL) { - name = krealloc(name, name_size, GFP_KERNEL); - if (!name) + efi_char16_t *name_tmp = + krealloc(name, name_size, GFP_KERNEL); + if (!name_tmp) { + kfree(name); return -ENOMEM; + } + name = name_tmp; continue; } diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index 2fee52ed335d..9d5df683f882 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -605,11 +605,8 @@ setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_s break; case EFI_UNACCEPTED_MEMORY: - if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) { - efi_warn_once( -"The system has unaccepted memory, but kernel does not support it\nConsider enabling CONFIG_UNACCEPTED_MEMORY\n"); + if (!IS_ENABLED(CONFIG_UNACCEPTED_MEMORY)) continue; - } e820_type = E820_TYPE_RAM; process_unaccepted_memory(d->phys_addr, d->phys_addr + PAGE_SIZE * d->num_pages); @@ -852,6 +849,8 @@ void __noreturn efi_stub_entry(efi_handle_t handle, unsigned long kernel_entry; efi_status_t status; + boot_params_pointer = boot_params; + efi_system_table = sys_table_arg; /* Check if we were booted by the EFI firmware */ if (efi_system_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE) diff --git a/drivers/firmware/efi/libstub/x86-stub.h b/drivers/firmware/efi/libstub/x86-stub.h index 37c5a36b9d8c..2748bca192df 100644 --- a/drivers/firmware/efi/libstub/x86-stub.h +++ b/drivers/firmware/efi/libstub/x86-stub.h @@ -2,6 +2,8 @@ #include <linux/efi.h> +extern struct boot_params *boot_params_pointer asm("boot_params"); + extern void trampoline_32bit_src(void *, bool); extern const u16 trampoline_ljmp_imm_offset; diff --git a/drivers/firmware/efi/unaccepted_memory.c b/drivers/firmware/efi/unaccepted_memory.c index 853f7dc3c21d..135278ddaf62 100644 --- a/drivers/firmware/efi/unaccepted_memory.c +++ b/drivers/firmware/efi/unaccepted_memory.c @@ -5,9 +5,17 @@ #include <linux/spinlock.h> #include <asm/unaccepted_memory.h> -/* Protects unaccepted memory bitmap */ +/* Protects unaccepted memory bitmap and accepting_list */ static DEFINE_SPINLOCK(unaccepted_memory_lock); +struct accept_range { + struct list_head list; + unsigned long start; + unsigned long end; +}; + +static LIST_HEAD(accepting_list); + /* * accept_memory() -- Consult bitmap and accept the memory if needed. * @@ -24,6 +32,7 @@ void accept_memory(phys_addr_t start, phys_addr_t end) { struct efi_unaccepted_memory *unaccepted; unsigned long range_start, range_end; + struct accept_range range, *entry; unsigned long flags; u64 unit_size; @@ -78,20 +87,67 @@ void accept_memory(phys_addr_t start, phys_addr_t end) if (end > unaccepted->size * unit_size * BITS_PER_BYTE) end = unaccepted->size * unit_size * BITS_PER_BYTE; - range_start = start / unit_size; - + range.start = start / unit_size; + range.end = DIV_ROUND_UP(end, unit_size); +retry: spin_lock_irqsave(&unaccepted_memory_lock, flags); + + /* + * Check if anybody works on accepting the same range of the memory. + * + * The check is done with unit_size granularity. It is crucial to catch + * all accept requests to the same unit_size block, even if they don't + * overlap on physical address level. + */ + list_for_each_entry(entry, &accepting_list, list) { + if (entry->end < range.start) + continue; + if (entry->start >= range.end) + continue; + + /* + * Somebody else accepting the range. Or at least part of it. + * + * Drop the lock and retry until it is complete. + */ + spin_unlock_irqrestore(&unaccepted_memory_lock, flags); + goto retry; + } + + /* + * Register that the range is about to be accepted. + * Make sure nobody else will accept it. + */ + list_add(&range.list, &accepting_list); + + range_start = range.start; for_each_set_bitrange_from(range_start, range_end, unaccepted->bitmap, - DIV_ROUND_UP(end, unit_size)) { + range.end) { unsigned long phys_start, phys_end; unsigned long len = range_end - range_start; phys_start = range_start * unit_size + unaccepted->phys_base; phys_end = range_end * unit_size + unaccepted->phys_base; + /* + * Keep interrupts disabled until the accept operation is + * complete in order to prevent deadlocks. + * + * Enabling interrupts before calling arch_accept_memory() + * creates an opportunity for an interrupt handler to request + * acceptance for the same memory. The handler will continuously + * spin with interrupts disabled, preventing other task from + * making progress with the acceptance process. + */ + spin_unlock(&unaccepted_memory_lock); + arch_accept_memory(phys_start, phys_end); + + spin_lock(&unaccepted_memory_lock); bitmap_clear(unaccepted->bitmap, range_start, len); } + + list_del(&range.list); spin_unlock_irqrestore(&unaccepted_memory_lock, flags); } diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c index dbc7ba0ee72c..656d6b1dddb5 100644 --- a/drivers/gpio/gpio-vf610.c +++ b/drivers/gpio/gpio-vf610.c @@ -126,14 +126,14 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned gpio, unsigned long mask = BIT(gpio); u32 val; + vf610_gpio_set(chip, gpio, value); + if (port->sdata && port->sdata->have_paddr) { val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR); val |= mask; vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR); } - vf610_gpio_set(chip, gpio, value); - return pinctrl_gpio_direction_output(chip->base + gpio); } @@ -246,7 +246,8 @@ static const struct irq_chip vf610_irqchip = { .irq_unmask = vf610_gpio_irq_unmask, .irq_set_type = vf610_gpio_irq_set_type, .irq_set_wake = vf610_gpio_irq_set_wake, - .flags = IRQCHIP_IMMUTABLE, + .flags = IRQCHIP_IMMUTABLE | IRQCHIP_MASK_ON_SUSPEND + | IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND, GPIOCHIP_IRQ_RESOURCE_HELPERS, }; diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c index fbda452fb4d6..51e41676de0b 100644 --- a/drivers/gpio/gpiolib-acpi.c +++ b/drivers/gpio/gpiolib-acpi.c @@ -951,6 +951,7 @@ static struct gpio_desc *acpi_get_gpiod_from_data(struct fwnode_handle *fwnode, if (!propname) return ERR_PTR(-EINVAL); + memset(&lookup, 0, sizeof(lookup)); lookup.index = index; ret = acpi_gpio_property_lookup(fwnode, propname, index, &lookup); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 0dc9c655c4fb..aac52d9754e6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -47,7 +47,6 @@ const unsigned int amdgpu_ctx_num_entities[AMDGPU_HW_IP_NUM] = { bool amdgpu_ctx_priority_is_valid(int32_t ctx_prio) { switch (ctx_prio) { - case AMDGPU_CTX_PRIORITY_UNSET: case AMDGPU_CTX_PRIORITY_VERY_LOW: case AMDGPU_CTX_PRIORITY_LOW: case AMDGPU_CTX_PRIORITY_NORMAL: @@ -55,6 +54,7 @@ bool amdgpu_ctx_priority_is_valid(int32_t ctx_prio) case AMDGPU_CTX_PRIORITY_VERY_HIGH: return true; default: + case AMDGPU_CTX_PRIORITY_UNSET: return false; } } @@ -64,7 +64,8 @@ amdgpu_ctx_to_drm_sched_prio(int32_t ctx_prio) { switch (ctx_prio) { case AMDGPU_CTX_PRIORITY_UNSET: - return DRM_SCHED_PRIORITY_UNSET; + pr_warn_once("AMD-->DRM context priority value UNSET-->NORMAL"); + return DRM_SCHED_PRIORITY_NORMAL; case AMDGPU_CTX_PRIORITY_VERY_LOW: return DRM_SCHED_PRIORITY_MIN; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c index 12210598e5b8..ba3a87cb88cc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dma_buf.c @@ -403,7 +403,10 @@ amdgpu_dma_buf_move_notify(struct dma_buf_attachment *attach) continue; } - r = amdgpu_vm_clear_freed(adev, vm, NULL); + /* Reserve fences for two SDMA page table updates */ + r = dma_resv_reserve_fences(resv, 2); + if (!r) + r = amdgpu_vm_clear_freed(adev, vm, NULL); if (!r) r = amdgpu_vm_handle_moved(adev, vm); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c index da4be0bbb446..8eee5d783a92 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_doorbell_mgr.c @@ -142,6 +142,10 @@ int amdgpu_doorbell_create_kernel_doorbells(struct amdgpu_device *adev) int r; int size; + /* SI HW does not have doorbells, skip allocation */ + if (adev->doorbell.num_kernel_doorbells == 0) + return 0; + /* Reserve first num_kernel_doorbells (page-aligned) for kernel ops */ size = ALIGN(adev->doorbell.num_kernel_doorbells * sizeof(u32), PAGE_SIZE); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h index f3ee83cdf97e..d28e21baef16 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h @@ -252,7 +252,7 @@ static inline bool amdgpu_bo_in_cpu_visible_vram(struct amdgpu_bo *bo) struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev); struct amdgpu_res_cursor cursor; - if (bo->tbo.resource->mem_type != TTM_PL_VRAM) + if (!bo->tbo.resource || bo->tbo.resource->mem_type != TTM_PL_VRAM) return false; amdgpu_res_first(bo->tbo.resource, 0, amdgpu_bo_size(bo), &cursor); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c index f5daadcec865..82f25996ff5e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c @@ -1090,7 +1090,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev, struct amdgpu_bo_va *bo_va, struct drm_gem_object *gobj = dma_buf->priv; struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj); - if (abo->tbo.resource->mem_type == TTM_PL_VRAM) + if (abo->tbo.resource && + abo->tbo.resource->mem_type == TTM_PL_VRAM) bo = gem_to_amdgpu_bo(gobj); } mem = bo->tbo.resource; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 3a9077b60029..d08e60dff46d 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1262,6 +1262,9 @@ static void disable_vbios_mode_if_required( if (stream == NULL) continue; + if (stream->apply_seamless_boot_optimization) + continue; + // only looking for first odm pipe if (pipe->prev_odm_pipe) continue; diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index f448b903e190..84148a79414b 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -692,7 +692,7 @@ static struct ti_sn65dsi86 *bridge_to_ti_sn65dsi86(struct drm_bridge *bridge) return container_of(bridge, struct ti_sn65dsi86, bridge); } -static int ti_sn_attach_host(struct ti_sn65dsi86 *pdata) +static int ti_sn_attach_host(struct auxiliary_device *adev, struct ti_sn65dsi86 *pdata) { int val; struct mipi_dsi_host *host; @@ -707,7 +707,7 @@ static int ti_sn_attach_host(struct ti_sn65dsi86 *pdata) if (!host) return -EPROBE_DEFER; - dsi = devm_mipi_dsi_device_register_full(dev, host, &info); + dsi = devm_mipi_dsi_device_register_full(&adev->dev, host, &info); if (IS_ERR(dsi)) return PTR_ERR(dsi); @@ -725,7 +725,7 @@ static int ti_sn_attach_host(struct ti_sn65dsi86 *pdata) pdata->dsi = dsi; - return devm_mipi_dsi_attach(dev, dsi); + return devm_mipi_dsi_attach(&adev->dev, dsi); } static int ti_sn_bridge_attach(struct drm_bridge *bridge, @@ -1298,9 +1298,9 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, struct device_node *np = pdata->dev->of_node; int ret; - pdata->next_bridge = devm_drm_of_get_bridge(pdata->dev, np, 1, 0); + pdata->next_bridge = devm_drm_of_get_bridge(&adev->dev, np, 1, 0); if (IS_ERR(pdata->next_bridge)) - return dev_err_probe(pdata->dev, PTR_ERR(pdata->next_bridge), + return dev_err_probe(&adev->dev, PTR_ERR(pdata->next_bridge), "failed to create panel bridge\n"); ti_sn_bridge_parse_lanes(pdata, np); @@ -1319,9 +1319,9 @@ static int ti_sn_bridge_probe(struct auxiliary_device *adev, drm_bridge_add(&pdata->bridge); - ret = ti_sn_attach_host(pdata); + ret = ti_sn_attach_host(adev, pdata); if (ret) { - dev_err_probe(pdata->dev, ret, "failed to attach dsi host\n"); + dev_err_probe(&adev->dev, ret, "failed to attach dsi host\n"); goto err_remove_bridge; } diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c index 292e38eb6218..60794fcde1d5 100644 --- a/drivers/gpu/drm/drm_atomic_helper.c +++ b/drivers/gpu/drm/drm_atomic_helper.c @@ -290,7 +290,8 @@ static int update_connector_routing(struct drm_atomic_state *state, struct drm_connector *connector, struct drm_connector_state *old_connector_state, - struct drm_connector_state *new_connector_state) + struct drm_connector_state *new_connector_state, + bool added_by_user) { const struct drm_connector_helper_funcs *funcs; struct drm_encoder *new_encoder; @@ -339,9 +340,13 @@ update_connector_routing(struct drm_atomic_state *state, * there's a chance the connector may have been destroyed during the * process, but it's better to ignore that then cause * drm_atomic_helper_resume() to fail. + * + * Last, we want to ignore connector registration when the connector + * was not pulled in the atomic state by user-space (ie, was pulled + * in by the driver, e.g. when updating a DP-MST stream). */ if (!state->duplicated && drm_connector_is_unregistered(connector) && - crtc_state->active) { + added_by_user && crtc_state->active) { drm_dbg_atomic(connector->dev, "[CONNECTOR:%d:%s] is not registered\n", connector->base.id, connector->name); @@ -620,7 +625,10 @@ drm_atomic_helper_check_modeset(struct drm_device *dev, struct drm_connector *connector; struct drm_connector_state *old_connector_state, *new_connector_state; int i, ret; - unsigned int connectors_mask = 0; + unsigned int connectors_mask = 0, user_connectors_mask = 0; + + for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) + user_connectors_mask |= BIT(i); for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state, new_crtc_state, i) { bool has_connectors = @@ -685,7 +693,8 @@ drm_atomic_helper_check_modeset(struct drm_device *dev, */ ret = update_connector_routing(state, connector, old_connector_state, - new_connector_state); + new_connector_state, + BIT(i) & user_connectors_mask); if (ret) return ret; if (old_connector_state->crtc) { diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 340da8257b51..4b71040ae5be 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -123,6 +123,9 @@ static const struct edid_quirk { /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */ EDID_QUIRK('A', 'E', 'O', 0, EDID_QUIRK_FORCE_6BPC), + /* BenQ GW2765 */ + EDID_QUIRK('B', 'N', 'Q', 0x78d6, EDID_QUIRK_FORCE_8BPC), + /* BOE model on HP Pavilion 15-n233sl reports 8 bpc, but is a 6 bpc panel */ EDID_QUIRK('B', 'O', 'E', 0x78b, EDID_QUIRK_FORCE_6BPC), diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c index 6129b89bb366..44a948b80ee1 100644 --- a/drivers/gpu/drm/drm_gem.c +++ b/drivers/gpu/drm/drm_gem.c @@ -540,7 +540,7 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj) struct page **pages; struct folio *folio; struct folio_batch fbatch; - int i, j, npages; + long i, j, npages; if (WARN_ON(!obj->filp)) return ERR_PTR(-EINVAL); @@ -564,11 +564,13 @@ struct page **drm_gem_get_pages(struct drm_gem_object *obj) i = 0; while (i < npages) { + long nr; folio = shmem_read_folio_gfp(mapping, i, mapping_gfp_mask(mapping)); if (IS_ERR(folio)) goto fail; - for (j = 0; j < folio_nr_pages(folio); j++, i++) + nr = min(npages - i, folio_nr_pages(folio)); + for (j = 0; j < nr; j++, i++) pages[i] = folio_file_page(folio, i); /* Make sure shmem keeps __GFP_DMA32 allocated pages in the diff --git a/drivers/gpu/drm/i915/display/intel_cx0_phy.c b/drivers/gpu/drm/i915/display/intel_cx0_phy.c index 1b00ef2c6185..80e4ec6ee403 100644 --- a/drivers/gpu/drm/i915/display/intel_cx0_phy.c +++ b/drivers/gpu/drm/i915/display/intel_cx0_phy.c @@ -2553,8 +2553,7 @@ static void intel_cx0_phy_lane_reset(struct drm_i915_private *i915, drm_warn(&i915->drm, "PHY %c failed to bring out of SOC reset after %dus.\n", phy_name(phy), XELPDP_PORT_BUF_SOC_READY_TIMEOUT_US); - intel_de_rmw(i915, XELPDP_PORT_BUF_CTL2(port), - XELPDP_LANE_PIPE_RESET(0) | XELPDP_LANE_PIPE_RESET(1), + intel_de_rmw(i915, XELPDP_PORT_BUF_CTL2(port), lane_pipe_reset, lane_pipe_reset); if (__intel_de_wait_for_register(i915, XELPDP_PORT_BUF_CTL2(port), diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index aa4d842d4c5a..310654542b42 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -235,6 +235,7 @@ static vm_fault_t i915_error_to_vmf_fault(int err) case 0: case -EAGAIN: case -ENOSPC: /* transient failure to evict? */ + case -ENOBUFS: /* temporarily out of fences? */ case -ERESTARTSYS: case -EINTR: case -EBUSY: diff --git a/drivers/gpu/drm/mediatek/mtk_drm_gem.c b/drivers/gpu/drm/mediatek/mtk_drm_gem.c index 9f364df52478..0e0a41b2f57f 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_gem.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_gem.c @@ -239,6 +239,7 @@ int mtk_drm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) npages = obj->size >> PAGE_SHIFT; mtk_gem->pages = kcalloc(npages, sizeof(*mtk_gem->pages), GFP_KERNEL); if (!mtk_gem->pages) { + sg_free_table(sgt); kfree(sgt); return -ENOMEM; } @@ -248,12 +249,15 @@ int mtk_drm_gem_prime_vmap(struct drm_gem_object *obj, struct iosys_map *map) mtk_gem->kvaddr = vmap(mtk_gem->pages, npages, VM_MAP, pgprot_writecombine(PAGE_KERNEL)); if (!mtk_gem->kvaddr) { + sg_free_table(sgt); kfree(sgt); kfree(mtk_gem->pages); return -ENOMEM; } -out: + sg_free_table(sgt); kfree(sgt); + +out: iosys_map_set_vaddr(map, mtk_gem->kvaddr); return 0; diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index c2aaaded07ed..0be195f9149c 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -119,6 +119,7 @@ static u64 _dpu_plane_calc_bw(const struct dpu_mdss_cfg *catalog, struct dpu_sw_pipe_cfg *pipe_cfg) { int src_width, src_height, dst_height, fps; + u64 plane_pixel_rate, plane_bit_rate; u64 plane_prefill_bw; u64 plane_bw; u32 hw_latency_lines; @@ -136,13 +137,12 @@ static u64 _dpu_plane_calc_bw(const struct dpu_mdss_cfg *catalog, scale_factor = src_height > dst_height ? mult_frac(src_height, 1, dst_height) : 1; - plane_bw = - src_width * mode->vtotal * fps * fmt->bpp * - scale_factor; + plane_pixel_rate = src_width * mode->vtotal * fps; + plane_bit_rate = plane_pixel_rate * fmt->bpp; - plane_prefill_bw = - src_width * hw_latency_lines * fps * fmt->bpp * - scale_factor * mode->vtotal; + plane_bw = plane_bit_rate * scale_factor; + + plane_prefill_bw = plane_bw * hw_latency_lines; if ((vbp+vpw) > hw_latency_lines) do_div(plane_prefill_bw, (vbp+vpw)); @@ -733,9 +733,11 @@ static int dpu_plane_check_inline_rotation(struct dpu_plane *pdpu, static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe, struct dpu_sw_pipe_cfg *pipe_cfg, - const struct dpu_format *fmt) + const struct dpu_format *fmt, + const struct drm_display_mode *mode) { uint32_t min_src_size; + struct dpu_kms *kms = _dpu_plane_get_kms(&pdpu->base); min_src_size = DPU_FORMAT_IS_YUV(fmt) ? 2 : 1; @@ -774,6 +776,12 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu, return -EINVAL; } + /* max clk check */ + if (_dpu_plane_calc_clk(mode, pipe_cfg) > kms->perf.max_core_clk_rate) { + DPU_DEBUG_PLANE(pdpu, "plane exceeds max mdp core clk limits\n"); + return -E2BIG; + } + return 0; } @@ -899,12 +907,13 @@ static int dpu_plane_atomic_check(struct drm_plane *plane, r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2; } - ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt); + ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode); if (ret) return ret; if (r_pipe->sspp) { - ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt); + ret = dpu_plane_atomic_check_pipe(pdpu, r_pipe, r_pipe_cfg, fmt, + &crtc_state->adjusted_mode); if (ret) return ret; } diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index a7a5c7e0ab92..77a8d9366ed7 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1774,13 +1774,6 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl) return rc; while (--link_train_max_retries) { - rc = dp_ctrl_reinitialize_mainlink(ctrl); - if (rc) { - DRM_ERROR("Failed to reinitialize mainlink. rc=%d\n", - rc); - break; - } - training_step = DP_TRAINING_NONE; rc = dp_ctrl_setup_main_link(ctrl, &training_step); if (rc == 0) { @@ -1832,6 +1825,12 @@ int dp_ctrl_on_link(struct dp_ctrl *dp_ctrl) /* stop link training before start re training */ dp_ctrl_clear_training_pattern(ctrl); } + + rc = dp_ctrl_reinitialize_mainlink(ctrl); + if (rc) { + DRM_ERROR("Failed to reinitialize mainlink. rc=%d\n", rc); + break; + } } if (ctrl->link->sink_request & DP_TEST_LINK_PHY_TEST_PATTERN) diff --git a/drivers/gpu/drm/msm/dp/dp_link.c b/drivers/gpu/drm/msm/dp/dp_link.c index 42427129acea..6375daaeb98e 100644 --- a/drivers/gpu/drm/msm/dp/dp_link.c +++ b/drivers/gpu/drm/msm/dp/dp_link.c @@ -1090,7 +1090,7 @@ int dp_link_process_request(struct dp_link *dp_link) } else if (dp_link_read_psr_error_status(link)) { DRM_ERROR("PSR IRQ_HPD received\n"); } else if (dp_link_psr_capability_changed(link)) { - drm_dbg_dp(link->drm_dev, "PSR Capability changed"); + drm_dbg_dp(link->drm_dev, "PSR Capability changed\n"); } else { ret = dp_link_process_link_status_update(link); if (!ret) { @@ -1107,7 +1107,7 @@ int dp_link_process_request(struct dp_link *dp_link) } } - drm_dbg_dp(link->drm_dev, "sink request=%#x", + drm_dbg_dp(link->drm_dev, "sink request=%#x\n", dp_link->sink_request); return ret; } diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index 5d9ec27c89d3..3d6fb708dc22 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -1082,9 +1082,21 @@ static void dsi_wait4video_done(struct msm_dsi_host *msm_host) static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host) { + u32 data; + if (!(msm_host->mode_flags & MIPI_DSI_MODE_VIDEO)) return; + data = dsi_read(msm_host, REG_DSI_STATUS0); + + /* if video mode engine is not busy, its because + * either timing engine was not turned on or the + * DSI controller has finished transmitting the video + * data already, so no need to wait in those cases + */ + if (!(data & DSI_STATUS0_VIDEO_MODE_ENGINE_BUSY)) + return; + if (msm_host->power_on && msm_host->enabled) { dsi_wait4video_done(msm_host); /* delay 4 ms to skip BLLP */ @@ -1894,10 +1906,9 @@ int msm_dsi_host_init(struct msm_dsi *msm_dsi) } msm_host->irq = irq_of_parse_and_map(pdev->dev.of_node, 0); - if (msm_host->irq < 0) { - ret = msm_host->irq; - dev_err(&pdev->dev, "failed to get irq: %d\n", ret); - return ret; + if (!msm_host->irq) { + dev_err(&pdev->dev, "failed to get irq\n"); + return -EINVAL; } /* do not autoenable, will be enabled later */ diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c index 2e87dd6cb17b..348c66b14683 100644 --- a/drivers/gpu/drm/msm/msm_mdss.c +++ b/drivers/gpu/drm/msm/msm_mdss.c @@ -511,7 +511,7 @@ static int mdss_remove(struct platform_device *pdev) static const struct msm_mdss_data msm8998_data = { .ubwc_enc_version = UBWC_1_0, .ubwc_dec_version = UBWC_1_0, - .highest_bank_bit = 1, + .highest_bank_bit = 2, }; static const struct msm_mdss_data qcm2290_data = { diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c index 46b057fe1412..3249e5c1c893 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/uconn.c @@ -62,6 +62,18 @@ nvkm_uconn_uevent_gpio(struct nvkm_object *object, u64 token, u32 bits) return object->client->event(token, &args, sizeof(args.v0)); } +static bool +nvkm_connector_is_dp_dms(u8 type) +{ + switch (type) { + case DCB_CONNECTOR_DMS59_DP0: + case DCB_CONNECTOR_DMS59_DP1: + return true; + default: + return false; + } +} + static int nvkm_uconn_uevent(struct nvkm_object *object, void *argv, u32 argc, struct nvkm_uevent *uevent) { @@ -101,7 +113,7 @@ nvkm_uconn_uevent(struct nvkm_object *object, void *argv, u32 argc, struct nvkm_ if (args->v0.types & NVIF_CONN_EVENT_V0_UNPLUG) bits |= NVKM_GPIO_LO; if (args->v0.types & NVIF_CONN_EVENT_V0_IRQ) { /* TODO: support DP IRQ on ANX9805 and remove this hack. */ - if (!outp->info.location) + if (!outp->info.location && !nvkm_connector_is_dp_dms(conn->info.type)) return -EINVAL; } diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 5ac926281d2c..c9087f474cbc 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1342,9 +1342,7 @@ static const struct panel_init_cmd starry_himax83102_j02_init_cmd[] = { _INIT_DCS_CMD(0xB1, 0x01, 0xBF, 0x11), _INIT_DCS_CMD(0xCB, 0x86), _INIT_DCS_CMD(0xD2, 0x3C, 0xFA), - _INIT_DCS_CMD(0xE9, 0xC5), - _INIT_DCS_CMD(0xD3, 0x00, 0x00, 0x00, 0x00, 0x80, 0x0C, 0x01), - _INIT_DCS_CMD(0xE9, 0x3F), + _INIT_DCS_CMD(0xD3, 0x00, 0x00, 0x44, 0x00, 0x00, 0x00, 0x00, 0x00, 0x80, 0x0C, 0x01), _INIT_DCS_CMD(0xE7, 0x02, 0x00, 0x28, 0x01, 0x7E, 0x0F, 0x7E, 0x10, 0xA0, 0x00, 0x00, 0x20, 0x40, 0x50, 0x40), _INIT_DCS_CMD(0xBD, 0x02), _INIT_DCS_CMD(0xD8, 0xFF, 0xFF, 0xBF, 0xFE, 0xAA, 0xA0, 0xFF, 0xFF, 0xBF, 0xFE, 0xAA, 0xA0), diff --git a/drivers/gpu/drm/panel/panel-edp.c b/drivers/gpu/drm/panel/panel-edp.c index feb665df35a1..95c8472d878a 100644 --- a/drivers/gpu/drm/panel/panel-edp.c +++ b/drivers/gpu/drm/panel/panel-edp.c @@ -976,32 +976,6 @@ static const struct panel_desc auo_b116xak01 = { }, }; -static const struct drm_display_mode auo_b116xw03_mode = { - .clock = 70589, - .hdisplay = 1366, - .hsync_start = 1366 + 40, - .hsync_end = 1366 + 40 + 40, - .htotal = 1366 + 40 + 40 + 32, - .vdisplay = 768, - .vsync_start = 768 + 10, - .vsync_end = 768 + 10 + 12, - .vtotal = 768 + 10 + 12 + 6, - .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, -}; - -static const struct panel_desc auo_b116xw03 = { - .modes = &auo_b116xw03_mode, - .num_modes = 1, - .bpc = 6, - .size = { - .width = 256, - .height = 144, - }, - .delay = { - .enable = 400, - }, -}; - static const struct drm_display_mode auo_b133han05_mode = { .clock = 142600, .hdisplay = 1920, @@ -1726,9 +1700,6 @@ static const struct of_device_id platform_of_match[] = { .compatible = "auo,b116xa01", .data = &auo_b116xak01, }, { - .compatible = "auo,b116xw03", - .data = &auo_b116xw03, - }, { .compatible = "auo,b133han05", .data = &auo_b133han05, }, { diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index 95959dcc6e0e..dd7928d9570f 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -919,6 +919,38 @@ static const struct panel_desc auo_b101xtn01 = { }, }; +static const struct drm_display_mode auo_b116xw03_mode = { + .clock = 70589, + .hdisplay = 1366, + .hsync_start = 1366 + 40, + .hsync_end = 1366 + 40 + 40, + .htotal = 1366 + 40 + 40 + 32, + .vdisplay = 768, + .vsync_start = 768 + 10, + .vsync_end = 768 + 10 + 12, + .vtotal = 768 + 10 + 12 + 6, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, +}; + +static const struct panel_desc auo_b116xw03 = { + .modes = &auo_b116xw03_mode, + .num_modes = 1, + .bpc = 6, + .size = { + .width = 256, + .height = 144, + }, + .delay = { + .prepare = 1, + .enable = 200, + .disable = 200, + .unprepare = 500, + }, + .bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG, + .bus_flags = DRM_BUS_FLAG_DE_HIGH, + .connector_type = DRM_MODE_CONNECTOR_LVDS, +}; + static const struct display_timing auo_g070vvn01_timings = { .pixelclock = { 33300000, 34209000, 45000000 }, .hactive = { 800, 800, 800 }, @@ -4103,6 +4135,9 @@ static const struct of_device_id platform_of_match[] = { .compatible = "auo,b101xtn01", .data = &auo_b101xtn01, }, { + .compatible = "auo,b116xw03", + .data = &auo_b116xw03, + }, { .compatible = "auo,g070vvn01", .data = &auo_g070vvn01, }, { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 506371c42745..5a3a622fc672 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -929,7 +929,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched) if (next) { next->s_fence->scheduled.timestamp = - job->s_fence->finished.timestamp; + dma_fence_timestamp(&job->s_fence->finished); /* start TO timer for next job */ drm_sched_start_timeout(sched); } diff --git a/drivers/gpu/drm/tiny/simpledrm.c b/drivers/gpu/drm/tiny/simpledrm.c index ff86ba1ae1b8..8ea120eb8674 100644 --- a/drivers/gpu/drm/tiny/simpledrm.c +++ b/drivers/gpu/drm/tiny/simpledrm.c @@ -745,7 +745,7 @@ static struct simpledrm_device *simpledrm_device_create(struct drm_driver *drv, ret = devm_aperture_acquire_from_firmware(dev, res->start, resource_size(res)); if (ret) { - drm_err(dev, "could not acquire memory range %pr: %d\n", &res, ret); + drm_err(dev, "could not acquire memory range %pr: %d\n", res, ret); return ERR_PTR(ret); } diff --git a/drivers/gpu/drm/ttm/ttm_device.c b/drivers/gpu/drm/ttm/ttm_device.c index 7726a72befc5..d48b39132b32 100644 --- a/drivers/gpu/drm/ttm/ttm_device.c +++ b/drivers/gpu/drm/ttm/ttm_device.c @@ -232,10 +232,6 @@ void ttm_device_fini(struct ttm_device *bdev) struct ttm_resource_manager *man; unsigned i; - man = ttm_manager_type(bdev, TTM_PL_SYSTEM); - ttm_resource_manager_set_used(man, false); - ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, NULL); - mutex_lock(&ttm_global_mutex); list_del(&bdev->device_list); mutex_unlock(&ttm_global_mutex); @@ -243,6 +239,10 @@ void ttm_device_fini(struct ttm_device *bdev) drain_workqueue(bdev->wq); destroy_workqueue(bdev->wq); + man = ttm_manager_type(bdev, TTM_PL_SYSTEM); + ttm_resource_manager_set_used(man, false); + ttm_set_driver_manager(bdev, TTM_PL_SYSTEM, NULL); + spin_lock(&bdev->lru_lock); for (i = 0; i < TTM_MAX_BO_PRIORITY; ++i) if (list_empty(&man->lru[0])) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c index c43853597776..2bfac3aad7b7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c @@ -34,6 +34,8 @@ static void vmw_bo_release(struct vmw_bo *vbo) { + WARN_ON(vbo->tbo.base.funcs && + kref_read(&vbo->tbo.base.refcount) != 0); vmw_bo_unmap(vbo); drm_gem_object_release(&vbo->tbo.base); } @@ -497,7 +499,7 @@ static int vmw_user_bo_synccpu_release(struct drm_file *filp, if (!(flags & drm_vmw_synccpu_allow_cs)) { atomic_dec(&vmw_bo->cpu_writers); } - vmw_user_bo_unref(vmw_bo); + vmw_user_bo_unref(&vmw_bo); } return ret; @@ -539,7 +541,7 @@ int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data, return ret; ret = vmw_user_bo_synccpu_grab(vbo, arg->flags); - vmw_user_bo_unref(vbo); + vmw_user_bo_unref(&vbo); if (unlikely(ret != 0)) { if (ret == -ERESTARTSYS || ret == -EBUSY) return -EBUSY; @@ -612,7 +614,6 @@ int vmw_user_bo_lookup(struct drm_file *filp, } *out = to_vmw_bo(gobj); - ttm_bo_get(&(*out)->tbo); return 0; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h index 1d433fceed3d..0d496dc9c6af 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h @@ -195,12 +195,19 @@ static inline struct vmw_bo *vmw_bo_reference(struct vmw_bo *buf) return buf; } -static inline void vmw_user_bo_unref(struct vmw_bo *vbo) +static inline struct vmw_bo *vmw_user_bo_ref(struct vmw_bo *vbo) { - if (vbo) { - ttm_bo_put(&vbo->tbo); - drm_gem_object_put(&vbo->tbo.base); - } + drm_gem_object_get(&vbo->tbo.base); + return vbo; +} + +static inline void vmw_user_bo_unref(struct vmw_bo **buf) +{ + struct vmw_bo *tmp_buf = *buf; + + *buf = NULL; + if (tmp_buf) + drm_gem_object_put(&tmp_buf->tbo.base); } static inline struct vmw_bo *to_vmw_bo(struct drm_gem_object *gobj) diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c index c0b24d1cacbf..a7c07692262b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c @@ -432,7 +432,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) * for the new COTable. Initially pin the buffer object to make sure * we can use tryreserve without failure. */ - ret = vmw_bo_create(dev_priv, &bo_params, &buf); + ret = vmw_gem_object_create(dev_priv, &bo_params, &buf); if (ret) { DRM_ERROR("Failed initializing new cotable MOB.\n"); goto out_done; @@ -502,7 +502,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size) vmw_resource_mob_attach(res); /* Let go of the old mob. */ - vmw_bo_unreference(&old_buf); + vmw_user_bo_unref(&old_buf); res->id = vcotbl->type; ret = dma_resv_reserve_fences(bo->base.resv, 1); @@ -521,7 +521,7 @@ out_map_new: out_wait: ttm_bo_unpin(bo); ttm_bo_unreserve(bo); - vmw_bo_unreference(&buf); + vmw_user_bo_unref(&buf); out_done: MKS_STAT_TIME_POP(MKSSTAT_KERN_COTABLE_RESIZE); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 58bfdf203eca..3cd5090dedfc 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -853,6 +853,10 @@ static inline bool vmw_resource_mob_attached(const struct vmw_resource *res) /** * GEM related functionality - vmwgfx_gem.c */ +struct vmw_bo_params; +int vmw_gem_object_create(struct vmw_private *vmw, + struct vmw_bo_params *params, + struct vmw_bo **p_vbo); extern int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, struct drm_file *filp, uint32_t size, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 98e0723ca6f5..36987ef3fc30 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1151,7 +1151,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, SVGAMobId *id, struct vmw_bo **vmw_bo_p) { - struct vmw_bo *vmw_bo; + struct vmw_bo *vmw_bo, *tmp_bo; uint32_t handle = *id; struct vmw_relocation *reloc; int ret; @@ -1164,7 +1164,8 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv, } vmw_bo_placement_set(vmw_bo, VMW_BO_DOMAIN_MOB, VMW_BO_DOMAIN_MOB); ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo); - vmw_user_bo_unref(vmw_bo); + tmp_bo = vmw_bo; + vmw_user_bo_unref(&tmp_bo); if (unlikely(ret != 0)) return ret; @@ -1206,7 +1207,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, SVGAGuestPtr *ptr, struct vmw_bo **vmw_bo_p) { - struct vmw_bo *vmw_bo; + struct vmw_bo *vmw_bo, *tmp_bo; uint32_t handle = ptr->gmrId; struct vmw_relocation *reloc; int ret; @@ -1220,7 +1221,8 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv, vmw_bo_placement_set(vmw_bo, VMW_BO_DOMAIN_GMR | VMW_BO_DOMAIN_VRAM, VMW_BO_DOMAIN_GMR | VMW_BO_DOMAIN_VRAM); ret = vmw_validation_add_bo(sw_context->ctx, vmw_bo); - vmw_user_bo_unref(vmw_bo); + tmp_bo = vmw_bo; + vmw_user_bo_unref(&tmp_bo); if (unlikely(ret != 0)) return ret; @@ -1619,7 +1621,7 @@ static int vmw_cmd_tex_state(struct vmw_private *dev_priv, { VMW_DECLARE_CMD_VAR(*cmd, SVGA3dCmdSetTextureState); SVGA3dTextureState *last_state = (SVGA3dTextureState *) - ((unsigned long) header + header->size + sizeof(header)); + ((unsigned long) header + header->size + sizeof(*header)); SVGA3dTextureState *cur_state = (SVGA3dTextureState *) ((unsigned long) header + sizeof(*cmd)); struct vmw_resource *ctx; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c index c0da89e16e6f..8b1eb0061610 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gem.c @@ -111,6 +111,20 @@ static const struct drm_gem_object_funcs vmw_gem_object_funcs = { .vm_ops = &vmw_vm_ops, }; +int vmw_gem_object_create(struct vmw_private *vmw, + struct vmw_bo_params *params, + struct vmw_bo **p_vbo) +{ + int ret = vmw_bo_create(vmw, params, p_vbo); + + if (ret != 0) + goto out_no_bo; + + (*p_vbo)->tbo.base.funcs = &vmw_gem_object_funcs; +out_no_bo: + return ret; +} + int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, struct drm_file *filp, uint32_t size, @@ -126,12 +140,10 @@ int vmw_gem_object_create_with_handle(struct vmw_private *dev_priv, .pin = false }; - ret = vmw_bo_create(dev_priv, ¶ms, p_vbo); + ret = vmw_gem_object_create(dev_priv, ¶ms, p_vbo); if (ret != 0) goto out_no_bo; - (*p_vbo)->tbo.base.funcs = &vmw_gem_object_funcs; - ret = drm_gem_handle_create(filp, &(*p_vbo)->tbo.base, handle); out_no_bo: return ret; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 1489ad73c103..818b7f109f53 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -1471,8 +1471,8 @@ static int vmw_create_bo_proxy(struct drm_device *dev, /* Reserve and switch the backing mob. */ mutex_lock(&res->dev_priv->cmdbuf_mutex); (void) vmw_resource_reserve(res, false, true); - vmw_bo_unreference(&res->guest_memory_bo); - res->guest_memory_bo = vmw_bo_reference(bo_mob); + vmw_user_bo_unref(&res->guest_memory_bo); + res->guest_memory_bo = vmw_user_bo_ref(bo_mob); res->guest_memory_offset = 0; vmw_resource_unreserve(res, false, false, false, NULL, 0); mutex_unlock(&res->dev_priv->cmdbuf_mutex); @@ -1666,7 +1666,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev, err_out: /* vmw_user_lookup_handle takes one ref so does new_fb */ if (bo) - vmw_user_bo_unref(bo); + vmw_user_bo_unref(&bo); if (surface) vmw_surface_unreference(&surface); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c index fb85f244c3d0..c45b4724e414 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c @@ -451,7 +451,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data, ret = vmw_overlay_update_stream(dev_priv, buf, arg, true); - vmw_user_bo_unref(buf); + vmw_user_bo_unref(&buf); out_unlock: mutex_unlock(&overlay->mutex); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c index 71eeabf001c8..ca300c7427d2 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c @@ -141,7 +141,7 @@ static void vmw_resource_release(struct kref *kref) if (res->coherent) vmw_bo_dirty_release(res->guest_memory_bo); ttm_bo_unreserve(bo); - vmw_bo_unreference(&res->guest_memory_bo); + vmw_user_bo_unref(&res->guest_memory_bo); } if (likely(res->hw_destroy != NULL)) { @@ -338,7 +338,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res, return 0; } - ret = vmw_bo_create(res->dev_priv, &bo_params, &gbo); + ret = vmw_gem_object_create(res->dev_priv, &bo_params, &gbo); if (unlikely(ret != 0)) goto out_no_bo; @@ -457,11 +457,11 @@ void vmw_resource_unreserve(struct vmw_resource *res, vmw_resource_mob_detach(res); if (res->coherent) vmw_bo_dirty_release(res->guest_memory_bo); - vmw_bo_unreference(&res->guest_memory_bo); + vmw_user_bo_unref(&res->guest_memory_bo); } if (new_guest_memory_bo) { - res->guest_memory_bo = vmw_bo_reference(new_guest_memory_bo); + res->guest_memory_bo = vmw_user_bo_ref(new_guest_memory_bo); /* * The validation code should already have added a @@ -551,7 +551,7 @@ out_no_reserve: ttm_bo_put(val_buf->bo); val_buf->bo = NULL; if (guest_memory_dirty) - vmw_bo_unreference(&res->guest_memory_bo); + vmw_user_bo_unref(&res->guest_memory_bo); return ret; } @@ -727,7 +727,7 @@ int vmw_resource_validate(struct vmw_resource *res, bool intr, goto out_no_validate; else if (!res->func->needs_guest_memory && res->guest_memory_bo) { WARN_ON_ONCE(vmw_resource_mob_attached(res)); - vmw_bo_unreference(&res->guest_memory_bo); + vmw_user_bo_unref(&res->guest_memory_bo); } return 0; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c index 1e81ff2422cf..a01ca3226d0a 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c @@ -180,7 +180,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv, res->guest_memory_size = size; if (byte_code) { - res->guest_memory_bo = vmw_bo_reference(byte_code); + res->guest_memory_bo = vmw_user_bo_ref(byte_code); res->guest_memory_offset = offset; } shader->size = size; @@ -809,7 +809,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv, shader_type, num_input_sig, num_output_sig, tfile, shader_handle); out_bad_arg: - vmw_user_bo_unref(buffer); + vmw_user_bo_unref(&buffer); return ret; } diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c index 5db403ee8261..3829be282ff0 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c @@ -686,9 +686,6 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base) container_of(base, struct vmw_user_surface, prime.base); struct vmw_resource *res = &user_srf->srf.res; - if (res->guest_memory_bo) - drm_gem_object_put(&res->guest_memory_bo->tbo.base); - *p_base = NULL; vmw_resource_unreference(&res); } @@ -855,23 +852,21 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data, * expect a backup buffer to be present. */ if (dev_priv->has_mob && req->shareable) { - uint32_t backup_handle; - - ret = vmw_gem_object_create_with_handle(dev_priv, - file_priv, - res->guest_memory_size, - &backup_handle, - &res->guest_memory_bo); + struct vmw_bo_params params = { + .domain = VMW_BO_DOMAIN_SYS, + .busy_domain = VMW_BO_DOMAIN_SYS, + .bo_type = ttm_bo_type_device, + .size = res->guest_memory_size, + .pin = false + }; + + ret = vmw_gem_object_create(dev_priv, + ¶ms, + &res->guest_memory_bo); if (unlikely(ret != 0)) { vmw_resource_unreference(&res); goto out_unlock; } - vmw_bo_reference(res->guest_memory_bo); - /* - * We don't expose the handle to the userspace and surface - * already holds a gem reference - */ - drm_gem_handle_delete(file_priv, backup_handle); } tmp = vmw_resource_reference(&srf->res); @@ -1512,7 +1507,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev, if (ret == 0) { if (res->guest_memory_bo->tbo.base.size < res->guest_memory_size) { VMW_DEBUG_USER("Surface backup buffer too small.\n"); - vmw_bo_unreference(&res->guest_memory_bo); + vmw_user_bo_unref(&res->guest_memory_bo); ret = -EINVAL; goto out_unlock; } else { @@ -1526,8 +1521,6 @@ vmw_gb_surface_define_internal(struct drm_device *dev, res->guest_memory_size, &backup_handle, &res->guest_memory_bo); - if (ret == 0) - vmw_bo_reference(res->guest_memory_bo); } if (unlikely(ret != 0)) { diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c index 66dc5f97a009..8311e1028ddb 100644 --- a/drivers/hwtracing/coresight/coresight-tmc-etr.c +++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c @@ -610,7 +610,8 @@ static int tmc_etr_alloc_flat_buf(struct tmc_drvdata *drvdata, flat_buf->vaddr = dma_alloc_noncoherent(real_dev, etr_buf->size, &flat_buf->daddr, - DMA_FROM_DEVICE, GFP_KERNEL); + DMA_FROM_DEVICE, + GFP_KERNEL | __GFP_NOWARN); if (!flat_buf->vaddr) { kfree(flat_buf); return -ENOMEM; @@ -1174,16 +1175,6 @@ static struct etr_buf *tmc_etr_get_sysfs_buffer(struct coresight_device *csdev) } /* - * In sysFS mode we can have multiple writers per sink. Since this - * sink is already enabled no memory is needed and the HW need not be - * touched, even if the buffer size has changed. - */ - if (drvdata->mode == CS_MODE_SYSFS) { - atomic_inc(&csdev->refcnt); - goto out; - } - - /* * If we don't have a buffer or it doesn't match the requested size, * use the buffer allocated above. Otherwise reuse the existing buffer. */ @@ -1204,7 +1195,7 @@ out: static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) { - int ret; + int ret = 0; unsigned long flags; struct tmc_drvdata *drvdata = dev_get_drvdata(csdev->dev.parent); struct etr_buf *sysfs_buf = tmc_etr_get_sysfs_buffer(csdev); @@ -1213,12 +1204,24 @@ static int tmc_enable_etr_sink_sysfs(struct coresight_device *csdev) return PTR_ERR(sysfs_buf); spin_lock_irqsave(&drvdata->spinlock, flags); + + /* + * In sysFS mode we can have multiple writers per sink. Since this + * sink is already enabled no memory is needed and the HW need not be + * touched, even if the buffer size has changed. + */ + if (drvdata->mode == CS_MODE_SYSFS) { + atomic_inc(&csdev->refcnt); + goto out; + } + ret = tmc_etr_enable_hw(drvdata, sysfs_buf); if (!ret) { drvdata->mode = CS_MODE_SYSFS; atomic_inc(&csdev->refcnt); } +out: spin_unlock_irqrestore(&drvdata->spinlock, flags); if (!ret) diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c index 69d1103b9508..b64fd365f83f 100644 --- a/drivers/iio/adc/ad7192.c +++ b/drivers/iio/adc/ad7192.c @@ -177,6 +177,7 @@ struct ad7192_chip_info { struct ad7192_state { const struct ad7192_chip_info *chip_info; struct regulator *avdd; + struct regulator *vref; struct clk *mclk; u16 int_vref_mv; u32 fclk; @@ -1008,10 +1009,30 @@ static int ad7192_probe(struct spi_device *spi) if (ret) return dev_err_probe(&spi->dev, ret, "Failed to enable specified DVdd supply\n"); - ret = regulator_get_voltage(st->avdd); - if (ret < 0) { - dev_err(&spi->dev, "Device tree error, reference voltage undefined\n"); - return ret; + st->vref = devm_regulator_get_optional(&spi->dev, "vref"); + if (IS_ERR(st->vref)) { + if (PTR_ERR(st->vref) != -ENODEV) + return PTR_ERR(st->vref); + + ret = regulator_get_voltage(st->avdd); + if (ret < 0) + return dev_err_probe(&spi->dev, ret, + "Device tree error, AVdd voltage undefined\n"); + } else { + ret = regulator_enable(st->vref); + if (ret) { + dev_err(&spi->dev, "Failed to enable specified Vref supply\n"); + return ret; + } + + ret = devm_add_action_or_reset(&spi->dev, ad7192_reg_disable, st->vref); + if (ret) + return ret; + + ret = regulator_get_voltage(st->vref); + if (ret < 0) + return dev_err_probe(&spi->dev, ret, + "Device tree error, Vref voltage undefined\n"); } st->int_vref_mv = ret / 1000; diff --git a/drivers/iio/adc/imx8qxp-adc.c b/drivers/iio/adc/imx8qxp-adc.c index f5a0fc9e64c5..fff6e5a2d956 100644 --- a/drivers/iio/adc/imx8qxp-adc.c +++ b/drivers/iio/adc/imx8qxp-adc.c @@ -38,8 +38,8 @@ #define IMX8QXP_ADR_ADC_FCTRL 0x30 #define IMX8QXP_ADR_ADC_SWTRIG 0x34 #define IMX8QXP_ADR_ADC_TCTRL(tid) (0xc0 + (tid) * 4) -#define IMX8QXP_ADR_ADC_CMDH(cid) (0x100 + (cid) * 8) -#define IMX8QXP_ADR_ADC_CMDL(cid) (0x104 + (cid) * 8) +#define IMX8QXP_ADR_ADC_CMDL(cid) (0x100 + (cid) * 8) +#define IMX8QXP_ADR_ADC_CMDH(cid) (0x104 + (cid) * 8) #define IMX8QXP_ADR_ADC_RESFIFO 0x300 #define IMX8QXP_ADR_ADC_TST 0xffc diff --git a/drivers/iio/addac/Kconfig b/drivers/iio/addac/Kconfig index 877f9124803c..397544f23b85 100644 --- a/drivers/iio/addac/Kconfig +++ b/drivers/iio/addac/Kconfig @@ -24,6 +24,8 @@ config AD74413R depends on GPIOLIB && SPI select REGMAP_SPI select CRC8 + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER help Say yes here to build support for Analog Devices AD74412R/AD74413R quad-channel software configurable input/output solution. 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 b72d39fc2434..6bfe5d6847e7 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 @@ -190,8 +190,11 @@ int cros_ec_sensors_push_data(struct iio_dev *indio_dev, /* * Ignore samples if the buffer is not set: it is needed if the ODR is * set but the buffer is not enabled yet. + * + * Note: iio_device_claim_buffer_mode() returns -EBUSY if the buffer + * is not enabled. */ - if (!iio_buffer_enabled(indio_dev)) + if (iio_device_claim_buffer_mode(indio_dev) < 0) return 0; out = (s16 *)st->samples; @@ -210,6 +213,7 @@ int cros_ec_sensors_push_data(struct iio_dev *indio_dev, iio_push_to_buffers_with_timestamp(indio_dev, st->samples, timestamp + delta); + iio_device_release_buffer_mode(indio_dev); return 0; } EXPORT_SYMBOL_GPL(cros_ec_sensors_push_data); diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c index d5ea1a1be122..a492e8f2fc0f 100644 --- a/drivers/iio/dac/ad3552r.c +++ b/drivers/iio/dac/ad3552r.c @@ -140,8 +140,8 @@ enum ad3552r_ch_vref_select { }; enum ad3542r_id { - AD3542R_ID = 0x4008, - AD3552R_ID = 0x4009, + AD3542R_ID = 0x4009, + AD3552R_ID = 0x4008, }; enum ad3552r_ch_output_range { diff --git a/drivers/iio/frequency/admv1013.c b/drivers/iio/frequency/admv1013.c index 6355c1f28423..92923074f930 100644 --- a/drivers/iio/frequency/admv1013.c +++ b/drivers/iio/frequency/admv1013.c @@ -351,9 +351,9 @@ static int admv1013_update_mixer_vgate(struct admv1013_state *st) if (vcm < 0) return vcm; - if (vcm < 1800000) + if (vcm <= 1800000) mixer_vgate = (2389 * vcm / 1000000 + 8100) / 100; - else if (vcm > 1800000 && vcm < 2600000) + else if (vcm > 1800000 && vcm <= 2600000) mixer_vgate = (2375 * vcm / 1000000 + 125) / 100; else return -EINVAL; diff --git a/drivers/iio/imu/bno055/Kconfig b/drivers/iio/imu/bno055/Kconfig index fa79b1ac4f85..83e53acfbe88 100644 --- a/drivers/iio/imu/bno055/Kconfig +++ b/drivers/iio/imu/bno055/Kconfig @@ -2,6 +2,8 @@ config BOSCH_BNO055 tristate + select IIO_BUFFER + select IIO_TRIGGERED_BUFFER config BOSCH_BNO055_SERIAL tristate "Bosch BNO055 attached via UART" diff --git a/drivers/iio/light/vcnl4000.c b/drivers/iio/light/vcnl4000.c index 3a52b09c2823..fdf763a04b0b 100644 --- a/drivers/iio/light/vcnl4000.c +++ b/drivers/iio/light/vcnl4000.c @@ -1513,7 +1513,6 @@ static int vcnl4040_write_event_config(struct iio_dev *indio_dev, out: mutex_unlock(&data->vcnl4000_lock); - data->chip_spec->set_power_state(data, data->ps_int || data->als_int); return ret; } diff --git a/drivers/iio/pressure/bmp280-core.c b/drivers/iio/pressure/bmp280-core.c index 6089f3f9d8f4..a2ef1373a274 100644 --- a/drivers/iio/pressure/bmp280-core.c +++ b/drivers/iio/pressure/bmp280-core.c @@ -2179,7 +2179,7 @@ int bmp280_common_probe(struct device *dev, * however as it happens, the BMP085 shares the chip ID of BMP180 * so we look for an IRQ if we have that. */ - if (irq > 0 || (chip_id == BMP180_CHIP_ID)) { + if (irq > 0 && (chip_id == BMP180_CHIP_ID)) { ret = bmp085_fetch_eoc_irq(dev, name, irq, data); if (ret) return ret; diff --git a/drivers/iio/pressure/dps310.c b/drivers/iio/pressure/dps310.c index b10dbf5cf494..1ff091b2f764 100644 --- a/drivers/iio/pressure/dps310.c +++ b/drivers/iio/pressure/dps310.c @@ -57,8 +57,8 @@ #define DPS310_RESET_MAGIC 0x09 #define DPS310_COEF_BASE 0x10 -/* Make sure sleep time is <= 20ms for usleep_range */ -#define DPS310_POLL_SLEEP_US(t) min(20000, (t) / 8) +/* Make sure sleep time is <= 30ms for usleep_range */ +#define DPS310_POLL_SLEEP_US(t) min(30000, (t) / 8) /* Silently handle error in rate value here */ #define DPS310_POLL_TIMEOUT_US(rc) ((rc) <= 0 ? 1000000 : 1000000 / (rc)) @@ -402,8 +402,8 @@ static int dps310_reset_wait(struct dps310_data *data) if (rc) return rc; - /* Wait for device chip access: 2.5ms in specification */ - usleep_range(2500, 12000); + /* Wait for device chip access: 15ms in specification */ + usleep_range(15000, 55000); return 0; } diff --git a/drivers/iio/pressure/ms5611_core.c b/drivers/iio/pressure/ms5611_core.c index 627497e61a63..2fc706f9d8ae 100644 --- a/drivers/iio/pressure/ms5611_core.c +++ b/drivers/iio/pressure/ms5611_core.c @@ -76,7 +76,7 @@ static bool ms5611_prom_is_valid(u16 *prom, size_t len) crc = (crc >> 12) & 0x000F; - return crc_orig != 0x0000 && crc == crc_orig; + return crc == crc_orig; } static int ms5611_read_prom(struct iio_dev *indio_dev) diff --git a/drivers/iio/proximity/irsd200.c b/drivers/iio/proximity/irsd200.c index 5bd791b46d98..bdff91f6b1a3 100644 --- a/drivers/iio/proximity/irsd200.c +++ b/drivers/iio/proximity/irsd200.c @@ -759,14 +759,14 @@ static irqreturn_t irsd200_trigger_handler(int irq, void *pollf) { struct iio_dev *indio_dev = ((struct iio_poll_func *)pollf)->indio_dev; struct irsd200_data *data = iio_priv(indio_dev); - s16 buf = 0; + s64 buf[2] = {}; int ret; - ret = irsd200_read_data(data, &buf); + ret = irsd200_read_data(data, (s16 *)buf); if (ret) goto end; - iio_push_to_buffers_with_timestamp(indio_dev, &buf, + iio_push_to_buffers_with_timestamp(indio_dev, buf, iio_get_time_ns(indio_dev)); end: diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c index ede380551e55..f5c21565bb3c 100644 --- a/drivers/input/joystick/xpad.c +++ b/drivers/input/joystick/xpad.c @@ -130,6 +130,7 @@ static const struct xpad_device { { 0x0079, 0x18d4, "GPD Win 2 X-Box Controller", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff01, "Wooting One (Legacy)", 0, XTYPE_XBOX360 }, { 0x03eb, 0xff02, "Wooting Two (Legacy)", 0, XTYPE_XBOX360 }, + { 0x03f0, 0x0495, "HyperX Clutch Gladiate", 0, XTYPE_XBOXONE }, { 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX }, { 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX }, @@ -272,6 +273,7 @@ static const struct xpad_device { { 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 }, { 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 }, + { 0x11ff, 0x0511, "PXN V900", 0, XTYPE_XBOX360 }, { 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 }, { 0x12ab, 0x0004, "Honey Bee Xbox360 dancepad", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 }, { 0x12ab, 0x0301, "PDP AFTERGLOW AX.1", 0, XTYPE_XBOX360 }, @@ -459,6 +461,7 @@ static const struct usb_device_id xpad_table[] = { { USB_INTERFACE_INFO('X', 'B', 0) }, /* Xbox USB-IF not-approved class */ XPAD_XBOX360_VENDOR(0x0079), /* GPD Win 2 controller */ XPAD_XBOX360_VENDOR(0x03eb), /* Wooting Keyboards (Legacy) */ + XPAD_XBOXONE_VENDOR(0x03f0), /* HP HyperX Xbox One controllers */ XPAD_XBOX360_VENDOR(0x044f), /* Thrustmaster Xbox 360 controllers */ XPAD_XBOX360_VENDOR(0x045e), /* Microsoft Xbox 360 controllers */ XPAD_XBOXONE_VENDOR(0x045e), /* Microsoft Xbox One controllers */ @@ -477,6 +480,7 @@ static const struct usb_device_id xpad_table[] = { XPAD_XBOX360_VENDOR(0x1038), /* SteelSeries controllers */ XPAD_XBOXONE_VENDOR(0x10f5), /* Turtle Beach Controllers */ XPAD_XBOX360_VENDOR(0x11c9), /* Nacon GC100XF */ + XPAD_XBOX360_VENDOR(0x11ff), /* PXN V900 */ XPAD_XBOX360_VENDOR(0x1209), /* Ardwiino Controllers */ XPAD_XBOX360_VENDOR(0x12ab), /* Xbox 360 dance pads */ XPAD_XBOX360_VENDOR(0x1430), /* RedOctane Xbox 360 controllers */ diff --git a/drivers/input/misc/powermate.c b/drivers/input/misc/powermate.c index c1c733a9cb89..db2ba89adaef 100644 --- a/drivers/input/misc/powermate.c +++ b/drivers/input/misc/powermate.c @@ -425,6 +425,7 @@ static void powermate_disconnect(struct usb_interface *intf) pm->requires_update = 0; usb_kill_urb(pm->irq); input_unregister_device(pm->input); + usb_kill_urb(pm->config); usb_free_urb(pm->irq); usb_free_urb(pm->config); powermate_free_buffers(interface_to_usbdev(intf), pm); diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c index 2118b2075f43..4e38229404b4 100644 --- a/drivers/input/mouse/elantech.c +++ b/drivers/input/mouse/elantech.c @@ -2114,6 +2114,7 @@ static int elantech_setup_ps2(struct psmouse *psmouse, psmouse->protocol_handler = elantech_process_byte; psmouse->disconnect = elantech_disconnect; psmouse->reconnect = elantech_reconnect; + psmouse->fast_reconnect = NULL; psmouse->pktsize = info->hw_version > 1 ? 6 : 4; return 0; diff --git a/drivers/input/mouse/psmouse-smbus.c b/drivers/input/mouse/psmouse-smbus.c index 7b13de979908..2a2459b1b4f2 100644 --- a/drivers/input/mouse/psmouse-smbus.c +++ b/drivers/input/mouse/psmouse-smbus.c @@ -5,7 +5,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/delay.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/libps2.h> @@ -119,18 +118,13 @@ static psmouse_ret_t psmouse_smbus_process_byte(struct psmouse *psmouse) return PSMOUSE_FULL_PACKET; } -static void psmouse_activate_smbus_mode(struct psmouse_smbus_dev *smbdev) -{ - if (smbdev->need_deactivate) { - psmouse_deactivate(smbdev->psmouse); - /* Give the device time to switch into SMBus mode */ - msleep(30); - } -} - static int psmouse_smbus_reconnect(struct psmouse *psmouse) { - psmouse_activate_smbus_mode(psmouse->private); + struct psmouse_smbus_dev *smbdev = psmouse->private; + + if (smbdev->need_deactivate) + psmouse_deactivate(psmouse); + return 0; } @@ -263,7 +257,8 @@ int psmouse_smbus_init(struct psmouse *psmouse, } } - psmouse_activate_smbus_mode(smbdev); + if (need_deactivate) + psmouse_deactivate(psmouse); psmouse->private = smbdev; psmouse->protocol_handler = psmouse_smbus_process_byte; diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c index ada299ec5bba..22d16d80efb9 100644 --- a/drivers/input/mouse/synaptics.c +++ b/drivers/input/mouse/synaptics.c @@ -1623,6 +1623,7 @@ static int synaptics_init_ps2(struct psmouse *psmouse, psmouse->set_rate = synaptics_set_rate; psmouse->disconnect = synaptics_disconnect; psmouse->reconnect = synaptics_reconnect; + psmouse->fast_reconnect = NULL; psmouse->cleanup = synaptics_reset; /* Synaptics can usually stay in sync without extra help */ psmouse->resync_time = 0; @@ -1752,6 +1753,7 @@ static int synaptics_create_intertouch(struct psmouse *psmouse, psmouse_matches_pnp_id(psmouse, topbuttonpad_pnp_ids) && !SYN_CAP_EXT_BUTTONS_STICK(info->ext_cap_10); const struct rmi_device_platform_data pdata = { + .reset_delay_ms = 30, .sensor_pdata = { .sensor_type = rmi_sensor_touchpad, .axis_align.flip_y = true, diff --git a/drivers/input/rmi4/rmi_smbus.c b/drivers/input/rmi4/rmi_smbus.c index 7059a2762aeb..b0b099b5528a 100644 --- a/drivers/input/rmi4/rmi_smbus.c +++ b/drivers/input/rmi4/rmi_smbus.c @@ -235,12 +235,29 @@ static void rmi_smb_clear_state(struct rmi_smb_xport *rmi_smb) static int rmi_smb_enable_smbus_mode(struct rmi_smb_xport *rmi_smb) { - int retval; + struct i2c_client *client = rmi_smb->client; + int smbus_version; + + /* + * psmouse driver resets the controller, we only need to wait + * to give the firmware chance to fully reinitialize. + */ + if (rmi_smb->xport.pdata.reset_delay_ms) + msleep(rmi_smb->xport.pdata.reset_delay_ms); /* we need to get the smbus version to activate the touchpad */ - retval = rmi_smb_get_version(rmi_smb); - if (retval < 0) - return retval; + smbus_version = rmi_smb_get_version(rmi_smb); + if (smbus_version < 0) + return smbus_version; + + rmi_dbg(RMI_DEBUG_XPORT, &client->dev, "Smbus version is %d", + smbus_version); + + if (smbus_version != 2 && smbus_version != 3) { + dev_err(&client->dev, "Unrecognized SMB version %d\n", + smbus_version); + return -ENODEV; + } return 0; } @@ -253,11 +270,10 @@ static int rmi_smb_reset(struct rmi_transport_dev *xport, u16 reset_addr) rmi_smb_clear_state(rmi_smb); /* - * we do not call the actual reset command, it has to be handled in - * PS/2 or there will be races between PS/2 and SMBus. - * PS/2 should ensure that a psmouse_reset is called before - * intializing the device and after it has been removed to be in a known - * state. + * We do not call the actual reset command, it has to be handled in + * PS/2 or there will be races between PS/2 and SMBus. PS/2 should + * ensure that a psmouse_reset is called before initializing the + * device and after it has been removed to be in a known state. */ return rmi_smb_enable_smbus_mode(rmi_smb); } @@ -272,7 +288,6 @@ static int rmi_smb_probe(struct i2c_client *client) { struct rmi_device_platform_data *pdata = dev_get_platdata(&client->dev); struct rmi_smb_xport *rmi_smb; - int smbus_version; int error; if (!pdata) { @@ -311,18 +326,9 @@ static int rmi_smb_probe(struct i2c_client *client) rmi_smb->xport.proto_name = "smb"; rmi_smb->xport.ops = &rmi_smb_ops; - smbus_version = rmi_smb_get_version(rmi_smb); - if (smbus_version < 0) - return smbus_version; - - rmi_dbg(RMI_DEBUG_XPORT, &client->dev, "Smbus version is %d", - smbus_version); - - if (smbus_version != 2 && smbus_version != 3) { - dev_err(&client->dev, "Unrecognized SMB version %d\n", - smbus_version); - return -ENODEV; - } + error = rmi_smb_enable_smbus_mode(rmi_smb); + if (error) + return error; i2c_set_clientdata(client, rmi_smb); diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 1724d6cb8649..9c39553d30fa 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -619,6 +619,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX) }, { + /* Fujitsu Lifebook E5411 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU CLIENT COMPUTING LIMITED"), + DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E5411"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOAUX) + }, + { /* Gigabyte M912 */ .matches = { DMI_MATCH(DMI_SYS_VENDOR, "GIGABYTE"), diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c index da9954d6df44..af32fbe57b63 100644 --- a/drivers/input/touchscreen/goodix.c +++ b/drivers/input/touchscreen/goodix.c @@ -900,6 +900,25 @@ static int goodix_add_acpi_gpio_mappings(struct goodix_ts_data *ts) dev_info(dev, "No ACPI GpioInt resource, assuming that the GPIO order is reset, int\n"); ts->irq_pin_access_method = IRQ_PIN_ACCESS_ACPI_GPIO; gpio_mapping = acpi_goodix_int_last_gpios; + } else if (ts->gpio_count == 1 && ts->gpio_int_idx == 0) { + /* + * On newer devices there is only 1 GpioInt resource and _PS0 + * does the whole reset sequence for us. + */ + acpi_device_fix_up_power(ACPI_COMPANION(dev)); + + /* + * Before the _PS0 call the int GPIO may have been in output + * mode and the call should have put the int GPIO in input mode, + * but the GPIO subsys cached state may still think it is + * in output mode, causing gpiochip_lock_as_irq() failure. + * + * Add a mapping for the int GPIO to make the + * gpiod_int = gpiod_get(..., GPIOD_IN) call succeed, + * which will explicitly set the direction to input. + */ + ts->irq_pin_access_method = IRQ_PIN_ACCESS_NONE; + gpio_mapping = acpi_goodix_int_first_gpios; } else { dev_warn(dev, "Unexpected ACPI resources: gpio_count %d, gpio_int_idx %d\n", ts->gpio_count, ts->gpio_int_idx); diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c index 1efd17979f24..b82b89888a5e 100644 --- a/drivers/isdn/hardware/mISDN/hfcsusb.c +++ b/drivers/isdn/hardware/mISDN/hfcsusb.c @@ -678,7 +678,7 @@ ph_state(struct dchannel *dch) } /* - * disable/enable BChannel for desired protocoll + * disable/enable BChannel for desired protocol */ static int hfcsusb_setup_bch(struct bchannel *bch, int protocol) diff --git a/drivers/mcb/mcb-core.c b/drivers/mcb/mcb-core.c index 978fdfc19a06..0cac5bead84f 100644 --- a/drivers/mcb/mcb-core.c +++ b/drivers/mcb/mcb-core.c @@ -387,17 +387,13 @@ EXPORT_SYMBOL_NS_GPL(mcb_free_dev, MCB); static int __mcb_bus_add_devices(struct device *dev, void *data) { - struct mcb_device *mdev = to_mcb_device(dev); int retval; - if (mdev->is_added) - return 0; - retval = device_attach(dev); - if (retval < 0) + if (retval < 0) { dev_err(dev, "Error adding device (%d)\n", retval); - - mdev->is_added = true; + return retval; + } return 0; } diff --git a/drivers/mcb/mcb-parse.c b/drivers/mcb/mcb-parse.c index 2aef990f379f..656b6b71c768 100644 --- a/drivers/mcb/mcb-parse.c +++ b/drivers/mcb/mcb-parse.c @@ -99,8 +99,6 @@ static int chameleon_parse_gdd(struct mcb_bus *bus, mdev->mem.end = mdev->mem.start + size - 1; mdev->mem.flags = IORESOURCE_MEM; - mdev->is_added = false; - ret = mcb_device_register(bus, mdev); if (ret < 0) goto err; diff --git a/drivers/media/i2c/ov8858.c b/drivers/media/i2c/ov8858.c index 3af6125a2eee..4d9fd76e2f60 100644 --- a/drivers/media/i2c/ov8858.c +++ b/drivers/media/i2c/ov8858.c @@ -1850,9 +1850,9 @@ static int ov8858_parse_of(struct ov8858 *ov8858) } ret = v4l2_fwnode_endpoint_parse(endpoint, &vep); + fwnode_handle_put(endpoint); if (ret) { dev_err(dev, "Failed to parse endpoint: %d\n", ret); - fwnode_handle_put(endpoint); return ret; } @@ -1864,12 +1864,9 @@ static int ov8858_parse_of(struct ov8858 *ov8858) default: dev_err(dev, "Unsupported number of data lanes %u\n", ov8858->num_lanes); - fwnode_handle_put(endpoint); return -EINVAL; } - ov8858->subdev.fwnode = endpoint; - return 0; } @@ -1913,7 +1910,7 @@ static int ov8858_probe(struct i2c_client *client) ret = ov8858_init_ctrls(ov8858); if (ret) - goto err_put_fwnode; + return ret; sd = &ov8858->subdev; sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS; @@ -1964,8 +1961,6 @@ err_clean_entity: media_entity_cleanup(&sd->entity); err_free_handler: v4l2_ctrl_handler_free(&ov8858->ctrl_handler); -err_put_fwnode: - fwnode_handle_put(ov8858->subdev.fwnode); return ret; } @@ -1978,7 +1973,6 @@ static void ov8858_remove(struct i2c_client *client) v4l2_async_unregister_subdev(sd); media_entity_cleanup(&sd->entity); v4l2_ctrl_handler_free(&ov8858->ctrl_handler); - fwnode_handle_put(ov8858->subdev.fwnode); pm_runtime_disable(&client->dev); if (!pm_runtime_status_suspended(&client->dev)) diff --git a/drivers/media/pci/intel/ipu-bridge.c b/drivers/media/pci/intel/ipu-bridge.c index 1bde8b6e0b11..e38198e259c0 100644 --- a/drivers/media/pci/intel/ipu-bridge.c +++ b/drivers/media/pci/intel/ipu-bridge.c @@ -107,8 +107,10 @@ static struct acpi_device *ipu_bridge_get_ivsc_acpi_dev(struct acpi_device *adev for_each_acpi_dev_match(ivsc_adev, acpi_id->id, NULL, -1) /* camera sensor depends on IVSC in DSDT if exist */ for_each_acpi_consumer_dev(ivsc_adev, consumer) - if (consumer->handle == handle) + if (consumer->handle == handle) { + acpi_dev_put(consumer); return ivsc_adev; + } } return NULL; diff --git a/drivers/media/platform/xilinx/xilinx-vipp.c b/drivers/media/platform/xilinx/xilinx-vipp.c index 4285770fde18..996684a73038 100644 --- a/drivers/media/platform/xilinx/xilinx-vipp.c +++ b/drivers/media/platform/xilinx/xilinx-vipp.c @@ -55,11 +55,18 @@ xvip_graph_find_entity(struct xvip_composite_device *xdev, { struct xvip_graph_entity *entity; struct v4l2_async_connection *asd; - - list_for_each_entry(asd, &xdev->notifier.done_list, asc_entry) { - entity = to_xvip_entity(asd); - if (entity->asd.match.fwnode == fwnode) - return entity; + struct list_head *lists[] = { + &xdev->notifier.done_list, + &xdev->notifier.waiting_list + }; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(lists); i++) { + list_for_each_entry(asd, lists[i], asc_entry) { + entity = to_xvip_entity(asd); + if (entity->asd.match.fwnode == fwnode) + return entity; + } } return NULL; diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c index b92348ad61f6..31752c06d1f0 100644 --- a/drivers/media/v4l2-core/v4l2-subdev.c +++ b/drivers/media/v4l2-core/v4l2-subdev.c @@ -502,6 +502,13 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg, V4L2_SUBDEV_CLIENT_CAP_STREAMS; int rval; + /* + * If the streams API is not enabled, remove V4L2_SUBDEV_CAP_STREAMS. + * Remove this when the API is no longer experimental. + */ + if (!v4l2_subdev_enable_streams_api) + streams_subdev = false; + switch (cmd) { case VIDIOC_SUBDEV_QUERYCAP: { struct v4l2_subdev_capability *cap = arg; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index b5b414a71e0b..3a8f27c3e310 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -179,6 +179,7 @@ static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq, struct mmc_queue *mq); static void mmc_blk_hsq_req_done(struct mmc_request *mrq); static int mmc_spi_err_check(struct mmc_card *card); +static int mmc_blk_busy_cb(void *cb_data, bool *busy); static struct mmc_blk_data *mmc_blk_get(struct gendisk *disk) { @@ -470,7 +471,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct mmc_data data = {}; struct mmc_request mrq = {}; struct scatterlist sg; - bool r1b_resp, use_r1b_resp = false; + bool r1b_resp; unsigned int busy_timeout_ms; int err; unsigned int target_part; @@ -551,8 +552,7 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, busy_timeout_ms = idata->ic.cmd_timeout_ms ? : MMC_BLK_TIMEOUT_MS; r1b_resp = (cmd.flags & MMC_RSP_R1B) == MMC_RSP_R1B; if (r1b_resp) - use_r1b_resp = mmc_prepare_busy_cmd(card->host, &cmd, - busy_timeout_ms); + mmc_prepare_busy_cmd(card->host, &cmd, busy_timeout_ms); mmc_wait_for_req(card->host, &mrq); memcpy(&idata->ic.response, cmd.resp, sizeof(cmd.resp)); @@ -605,19 +605,28 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, if (idata->ic.postsleep_min_us) usleep_range(idata->ic.postsleep_min_us, idata->ic.postsleep_max_us); - /* No need to poll when using HW busy detection. */ - if ((card->host->caps & MMC_CAP_WAIT_WHILE_BUSY) && use_r1b_resp) - return 0; - if (mmc_host_is_spi(card->host)) { if (idata->ic.write_flag || r1b_resp || cmd.flags & MMC_RSP_SPI_BUSY) return mmc_spi_err_check(card); return err; } - /* Ensure RPMB/R1B command has completed by polling with CMD13. */ - if (idata->rpmb || r1b_resp) - err = mmc_poll_for_busy(card, busy_timeout_ms, false, - MMC_BUSY_IO); + + /* + * Ensure RPMB, writes and R1B responses are completed by polling with + * CMD13. Note that, usually we don't need to poll when using HW busy + * detection, but here it's needed since some commands may indicate the + * error through the R1 status bits. + */ + if (idata->rpmb || idata->ic.write_flag || r1b_resp) { + struct mmc_blk_busy_data cb_data = { + .card = card, + }; + + err = __mmc_poll_for_busy(card->host, 0, busy_timeout_ms, + &mmc_blk_busy_cb, &cb_data); + + idata->ic.response[0] = cb_data.status; + } return err; } diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 89cd48fcec79..4a4bab9aa726 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -104,7 +104,7 @@ static int mmc_decode_cid(struct mmc_card *card) case 3: /* MMC v3.1 - v3.3 */ case 4: /* MMC v4 */ card->cid.manfid = UNSTUFF_BITS(resp, 120, 8); - card->cid.oemid = UNSTUFF_BITS(resp, 104, 16); + card->cid.oemid = UNSTUFF_BITS(resp, 104, 8); card->cid.prod_name[0] = UNSTUFF_BITS(resp, 96, 8); card->cid.prod_name[1] = UNSTUFF_BITS(resp, 88, 8); card->cid.prod_name[2] = UNSTUFF_BITS(resp, 80, 8); diff --git a/drivers/mmc/core/sdio.c b/drivers/mmc/core/sdio.c index f64b9ac76a5c..5914516df2f7 100644 --- a/drivers/mmc/core/sdio.c +++ b/drivers/mmc/core/sdio.c @@ -1089,8 +1089,14 @@ static int mmc_sdio_resume(struct mmc_host *host) } err = mmc_sdio_reinit_card(host); } else if (mmc_card_wake_sdio_irq(host)) { - /* We may have switched to 1-bit mode during suspend */ + /* + * We may have switched to 1-bit mode during suspend, + * need to hold retuning, because tuning only supprt + * 4-bit mode or 8 bit mode. + */ + mmc_retune_hold_now(host); err = sdio_enable_4bit_bus(host->card); + mmc_retune_release(host); } if (err) diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c index 5392200cfdf7..97f7c3d4be6e 100644 --- a/drivers/mmc/host/mtk-sd.c +++ b/drivers/mmc/host/mtk-sd.c @@ -669,11 +669,11 @@ static void msdc_reset_hw(struct msdc_host *host) u32 val; sdr_set_bits(host->base + MSDC_CFG, MSDC_CFG_RST); - readl_poll_timeout(host->base + MSDC_CFG, val, !(val & MSDC_CFG_RST), 0, 0); + readl_poll_timeout_atomic(host->base + MSDC_CFG, val, !(val & MSDC_CFG_RST), 0, 0); sdr_set_bits(host->base + MSDC_FIFOCS, MSDC_FIFOCS_CLR); - readl_poll_timeout(host->base + MSDC_FIFOCS, val, - !(val & MSDC_FIFOCS_CLR), 0, 0); + readl_poll_timeout_atomic(host->base + MSDC_FIFOCS, val, + !(val & MSDC_FIFOCS_CLR), 0, 0); val = readl(host->base + MSDC_INT); writel(val, host->base + MSDC_INT); diff --git a/drivers/mmc/host/sdhci-pci-gli.c b/drivers/mmc/host/sdhci-pci-gli.c index ae8c307b7aa7..109d4b010f97 100644 --- a/drivers/mmc/host/sdhci-pci-gli.c +++ b/drivers/mmc/host/sdhci-pci-gli.c @@ -1144,42 +1144,6 @@ static u32 sdhci_gl9750_readl(struct sdhci_host *host, int reg) return value; } -#ifdef CONFIG_PM_SLEEP -static int sdhci_pci_gli_resume(struct sdhci_pci_chip *chip) -{ - struct sdhci_pci_slot *slot = chip->slots[0]; - - pci_free_irq_vectors(slot->chip->pdev); - gli_pcie_enable_msi(slot); - - return sdhci_pci_resume_host(chip); -} - -static int sdhci_cqhci_gli_resume(struct sdhci_pci_chip *chip) -{ - struct sdhci_pci_slot *slot = chip->slots[0]; - int ret; - - ret = sdhci_pci_gli_resume(chip); - if (ret) - return ret; - - return cqhci_resume(slot->host->mmc); -} - -static int sdhci_cqhci_gli_suspend(struct sdhci_pci_chip *chip) -{ - struct sdhci_pci_slot *slot = chip->slots[0]; - int ret; - - ret = cqhci_suspend(slot->host->mmc); - if (ret) - return ret; - - return sdhci_suspend_host(slot->host); -} -#endif - static void gl9763e_hs400_enhanced_strobe(struct mmc_host *mmc, struct mmc_ios *ios) { @@ -1420,6 +1384,70 @@ static int gl9763e_runtime_resume(struct sdhci_pci_chip *chip) } #endif +#ifdef CONFIG_PM_SLEEP +static int sdhci_pci_gli_resume(struct sdhci_pci_chip *chip) +{ + struct sdhci_pci_slot *slot = chip->slots[0]; + + pci_free_irq_vectors(slot->chip->pdev); + gli_pcie_enable_msi(slot); + + return sdhci_pci_resume_host(chip); +} + +static int gl9763e_resume(struct sdhci_pci_chip *chip) +{ + struct sdhci_pci_slot *slot = chip->slots[0]; + int ret; + + ret = sdhci_pci_gli_resume(chip); + if (ret) + return ret; + + ret = cqhci_resume(slot->host->mmc); + if (ret) + return ret; + + /* + * Disable LPM negotiation to bring device back in sync + * with its runtime_pm state. + */ + gl9763e_set_low_power_negotiation(slot, false); + + return 0; +} + +static int gl9763e_suspend(struct sdhci_pci_chip *chip) +{ + struct sdhci_pci_slot *slot = chip->slots[0]; + int ret; + + /* + * Certain SoCs can suspend only with the bus in low- + * power state, notably x86 SoCs when using S0ix. + * Re-enable LPM negotiation to allow entering L1 state + * and entering system suspend. + */ + gl9763e_set_low_power_negotiation(slot, true); + + ret = cqhci_suspend(slot->host->mmc); + if (ret) + goto err_suspend; + + ret = sdhci_suspend_host(slot->host); + if (ret) + goto err_suspend_host; + + return 0; + +err_suspend_host: + cqhci_resume(slot->host->mmc); +err_suspend: + gl9763e_set_low_power_negotiation(slot, false); + return ret; +} +#endif + static int gli_probe_slot_gl9763e(struct sdhci_pci_slot *slot) { struct pci_dev *pdev = slot->chip->pdev; @@ -1527,8 +1555,8 @@ const struct sdhci_pci_fixes sdhci_gl9763e = { .probe_slot = gli_probe_slot_gl9763e, .ops = &sdhci_gl9763e_ops, #ifdef CONFIG_PM_SLEEP - .resume = sdhci_cqhci_gli_resume, - .suspend = sdhci_cqhci_gli_suspend, + .resume = gl9763e_resume, + .suspend = gl9763e_suspend, #endif #ifdef CONFIG_PM .runtime_suspend = gl9763e_runtime_suspend, diff --git a/drivers/mmc/host/sdhci-sprd.c b/drivers/mmc/host/sdhci-sprd.c index 649ae075e229..6b84ba27e6ab 100644 --- a/drivers/mmc/host/sdhci-sprd.c +++ b/drivers/mmc/host/sdhci-sprd.c @@ -644,6 +644,7 @@ static int sdhci_sprd_tuning(struct mmc_host *mmc, struct mmc_card *card, best_clk_sample = sdhci_sprd_get_best_clk_sample(mmc, value); if (best_clk_sample < 0) { dev_err(mmc_dev(host->mmc), "all tuning phase fail!\n"); + err = best_clk_sample; goto out; } diff --git a/drivers/mtd/maps/physmap-core.c b/drivers/mtd/maps/physmap-core.c index 78710fbc8e7f..fc8721339282 100644 --- a/drivers/mtd/maps/physmap-core.c +++ b/drivers/mtd/maps/physmap-core.c @@ -551,6 +551,17 @@ static int physmap_flash_probe(struct platform_device *dev) if (info->probe_type) { info->mtds[i] = do_map_probe(info->probe_type, &info->maps[i]); + + /* Fall back to mapping region as ROM */ + if (!info->mtds[i] && IS_ENABLED(CONFIG_MTD_ROM) && + strcmp(info->probe_type, "map_rom")) { + dev_warn(&dev->dev, + "map_probe() failed for type %s\n", + info->probe_type); + + info->mtds[i] = do_map_probe("map_rom", + &info->maps[i]); + } } else { int j; diff --git a/drivers/mtd/nand/raw/arasan-nand-controller.c b/drivers/mtd/nand/raw/arasan-nand-controller.c index 4621ec549cc7..a492051c46f5 100644 --- a/drivers/mtd/nand/raw/arasan-nand-controller.c +++ b/drivers/mtd/nand/raw/arasan-nand-controller.c @@ -515,6 +515,7 @@ static int anfc_write_page_hw_ecc(struct nand_chip *chip, const u8 *buf, struct mtd_info *mtd = nand_to_mtd(chip); unsigned int len = mtd->writesize + (oob_required ? mtd->oobsize : 0); dma_addr_t dma_addr; + u8 status; int ret; struct anfc_op nfc_op = { .pkt_reg = @@ -561,10 +562,21 @@ static int anfc_write_page_hw_ecc(struct nand_chip *chip, const u8 *buf, } /* Spare data is not protected */ - if (oob_required) + if (oob_required) { ret = nand_write_oob_std(chip, page); + if (ret) + return ret; + } - return ret; + /* Check write status on the chip side */ + ret = nand_status_op(chip, &status); + if (ret) + return ret; + + if (status & NAND_STATUS_FAIL) + return -EIO; + + return 0; } static int anfc_sel_write_page_hw_ecc(struct nand_chip *chip, const u8 *buf, diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c index 2c94da7a3b3a..b841a81cb128 100644 --- a/drivers/mtd/nand/raw/marvell_nand.c +++ b/drivers/mtd/nand/raw/marvell_nand.c @@ -1165,6 +1165,7 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip, .ndcb[2] = NDCB2_ADDR5_PAGE(page), }; unsigned int oob_bytes = lt->spare_bytes + (raw ? lt->ecc_bytes : 0); + u8 status; int ret; /* NFCv2 needs more information about the operation being executed */ @@ -1198,7 +1199,18 @@ static int marvell_nfc_hw_ecc_hmg_do_write_page(struct nand_chip *chip, ret = marvell_nfc_wait_op(chip, PSEC_TO_MSEC(sdr->tPROG_max)); - return ret; + if (ret) + return ret; + + /* Check write status on the chip side */ + ret = nand_status_op(chip, &status); + if (ret) + return ret; + + if (status & NAND_STATUS_FAIL) + return -EIO; + + return 0; } static int marvell_nfc_hw_ecc_hmg_write_page_raw(struct nand_chip *chip, @@ -1627,6 +1639,7 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct nand_chip *chip, int data_len = lt->data_bytes; int spare_len = lt->spare_bytes; int chunk, ret; + u8 status; marvell_nfc_select_target(chip, chip->cur_cs); @@ -1663,6 +1676,14 @@ static int marvell_nfc_hw_ecc_bch_write_page(struct nand_chip *chip, if (ret) return ret; + /* Check write status on the chip side */ + ret = nand_status_op(chip, &status); + if (ret) + return ret; + + if (status & NAND_STATUS_FAIL) + return -EIO; + return 0; } diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c index d4b55155aeae..1fcac403cee6 100644 --- a/drivers/mtd/nand/raw/nand_base.c +++ b/drivers/mtd/nand/raw/nand_base.c @@ -5110,6 +5110,9 @@ static void rawnand_check_cont_read_support(struct nand_chip *chip) { struct mtd_info *mtd = nand_to_mtd(chip); + if (!chip->parameters.supports_read_cache) + return; + if (chip->read_retries) return; diff --git a/drivers/mtd/nand/raw/nand_jedec.c b/drivers/mtd/nand/raw/nand_jedec.c index 836757717660..b3cc8f360529 100644 --- a/drivers/mtd/nand/raw/nand_jedec.c +++ b/drivers/mtd/nand/raw/nand_jedec.c @@ -94,6 +94,9 @@ int nand_jedec_detect(struct nand_chip *chip) goto free_jedec_param_page; } + if (p->opt_cmd[0] & JEDEC_OPT_CMD_READ_CACHE) + chip->parameters.supports_read_cache = true; + memorg->pagesize = le32_to_cpu(p->byte_per_page); mtd->writesize = memorg->pagesize; diff --git a/drivers/mtd/nand/raw/nand_onfi.c b/drivers/mtd/nand/raw/nand_onfi.c index f15ef90aec8c..861975e44b55 100644 --- a/drivers/mtd/nand/raw/nand_onfi.c +++ b/drivers/mtd/nand/raw/nand_onfi.c @@ -303,6 +303,9 @@ int nand_onfi_detect(struct nand_chip *chip) ONFI_FEATURE_ADDR_TIMING_MODE, 1); } + if (le16_to_cpu(p->opt_cmd) & ONFI_OPT_CMD_READ_CACHE) + chip->parameters.supports_read_cache = true; + onfi = kzalloc(sizeof(*onfi), GFP_KERNEL); if (!onfi) { ret = -ENOMEM; diff --git a/drivers/mtd/nand/raw/pl35x-nand-controller.c b/drivers/mtd/nand/raw/pl35x-nand-controller.c index 8da5fee321b5..c506e92a3e45 100644 --- a/drivers/mtd/nand/raw/pl35x-nand-controller.c +++ b/drivers/mtd/nand/raw/pl35x-nand-controller.c @@ -511,6 +511,7 @@ static int pl35x_nand_write_page_hwecc(struct nand_chip *chip, u32 addr1 = 0, addr2 = 0, row; u32 cmd_addr; int i, ret; + u8 status; ret = pl35x_smc_set_ecc_mode(nfc, chip, PL35X_SMC_ECC_CFG_MODE_APB); if (ret) @@ -563,6 +564,14 @@ static int pl35x_nand_write_page_hwecc(struct nand_chip *chip, if (ret) goto disable_ecc_engine; + /* Check write status on the chip side */ + ret = nand_status_op(chip, &status); + if (ret) + goto disable_ecc_engine; + + if (status & NAND_STATUS_FAIL) + ret = -EIO; + disable_ecc_engine: pl35x_smc_set_ecc_mode(nfc, chip, PL35X_SMC_ECC_CFG_MODE_BYPASS); diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c index 64499c1b3603..b079605c84d3 100644 --- a/drivers/mtd/nand/raw/qcom_nandc.c +++ b/drivers/mtd/nand/raw/qcom_nandc.c @@ -3444,7 +3444,7 @@ err_nandc_alloc: err_aon_clk: clk_disable_unprepare(nandc->core_clk); err_core_clk: - dma_unmap_resource(dev, res->start, resource_size(res), + dma_unmap_resource(dev, nandc->base_dma, resource_size(res), DMA_BIDIRECTIONAL, 0); return ret; } diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c index 50b7295bc922..12601bc4227a 100644 --- a/drivers/mtd/nand/spi/micron.c +++ b/drivers/mtd/nand/spi/micron.c @@ -12,7 +12,7 @@ #define SPINAND_MFR_MICRON 0x2c -#define MICRON_STATUS_ECC_MASK GENMASK(7, 4) +#define MICRON_STATUS_ECC_MASK GENMASK(6, 4) #define MICRON_STATUS_ECC_NO_BITFLIPS (0 << 4) #define MICRON_STATUS_ECC_1TO3_BITFLIPS (1 << 4) #define MICRON_STATUS_ECC_4TO6_BITFLIPS (3 << 4) diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 44eeb5d61ba9..af0da4bb429b 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -448,6 +448,15 @@ config NLMON diagnostics, etc. This is mostly intended for developers or support to debug netlink issues. If unsure, say N. +config NETKIT + bool "BPF-programmable network device" + depends on BPF_SYSCALL + help + The netkit device is a virtual networking device where BPF programs + can be attached to the device(s) transmission routine in order to + implement the driver's internal logic. The device can be configured + to operate in L3 or L2 mode. If unsure, say N. + config NET_VRF tristate "Virtual Routing and Forwarding (Lite)" depends on IP_MULTIPLE_TABLES diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 8a83db32509d..7cab36f94782 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -22,6 +22,7 @@ obj-$(CONFIG_MDIO) += mdio.o obj-$(CONFIG_NET) += loopback.o obj-$(CONFIG_NETDEV_LEGACY_INIT) += Space.o obj-$(CONFIG_NETCONSOLE) += netconsole.o +obj-$(CONFIG_NETKIT) += netkit.o obj-y += phy/ obj-y += pse-pd/ obj-y += mdio/ diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c index 47a9c2a5583c..31377bb1cc97 100644 --- a/drivers/net/bareudp.c +++ b/drivers/net/bareudp.c @@ -306,8 +306,11 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (!sock) return -ESHUTDOWN; + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); rt = udp_tunnel_dst_lookup(skb, dev, bareudp->net, 0, &saddr, &info->key, - 0, 0, key->tos, + sport, bareudp->port, key->tos, use_cache ? (struct dst_cache *)&info->dst_cache : NULL); @@ -317,9 +320,6 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev, skb_tunnel_check_pmtu(skb, &rt->dst, BAREUDP_IPV4_HLEN + info->options_len, false); - sport = udp_flow_src_port(bareudp->net, skb, - bareudp->sport_min, USHRT_MAX, - true); tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; @@ -371,17 +371,19 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (!sock) return -ESHUTDOWN; - dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, &saddr, info, - IPPROTO_UDP, use_cache); + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); + dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, 0, &saddr, + key, sport, bareudp->port, key->tos, + use_cache ? + (struct dst_cache *) &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); skb_tunnel_check_pmtu(skb, dst, BAREUDP_IPV6_HLEN + info->options_len, false); - sport = udp_flow_src_port(bareudp->net, skb, - bareudp->sport_min, USHRT_MAX, - true); prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; @@ -478,15 +480,20 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, struct ip_tunnel_info *info = skb_tunnel_info(skb); struct bareudp_dev *bareudp = netdev_priv(dev); bool use_cache; + __be16 sport; use_cache = ip_tunnel_dst_cache_usable(skb, info); + sport = udp_flow_src_port(bareudp->net, skb, + bareudp->sport_min, USHRT_MAX, + true); if (!ipv6_mod_enabled() || ip_tunnel_info_af(info) == AF_INET) { struct rtable *rt; __be32 saddr; rt = udp_tunnel_dst_lookup(skb, dev, bareudp->net, 0, &saddr, - &info->key, 0, 0, info->key.tos, + &info->key, sport, bareudp->port, + info->key.tos, use_cache ? &info->dst_cache : NULL); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -498,9 +505,10 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, struct in6_addr saddr; struct socket *sock = rcu_dereference(bareudp->sock); - dst = ip6_dst_lookup_tunnel(skb, dev, bareudp->net, sock, - &saddr, info, IPPROTO_UDP, - use_cache); + dst = udp_tunnel6_dst_lookup(skb, dev, bareudp->net, sock, + 0, &saddr, &info->key, + sport, bareudp->port, info->key.tos, + use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -510,9 +518,7 @@ static int bareudp_fill_metadata_dst(struct net_device *dev, return -EINVAL; } - info->key.tp_src = udp_flow_src_port(bareudp->net, skb, - bareudp->sport_min, - USHRT_MAX, true); + info->key.tp_src = sport; info->key.tp_dst = bareudp->port; return 0; } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index ed7212e61c54..51d47eda1c87 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -4023,7 +4023,7 @@ static inline const void *bond_pull_data(struct sk_buff *skb, if (likely(n <= hlen)) return data; else if (skb && likely(pskb_may_pull(skb, n))) - return skb->head; + return skb->data; return NULL; } diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c index 27cbe148f0db..cfa74cf8bb1a 100644 --- a/drivers/net/bonding/bond_netlink.c +++ b/drivers/net/bonding/bond_netlink.c @@ -85,7 +85,7 @@ nla_put_failure: } /* Limit the max delay range to 300s */ -static struct netlink_range_validation delay_range = { +static const struct netlink_range_validation delay_range = { .max = 300000, }; diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 4e27dc913cf7..0d628b35fd5c 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -757,7 +757,7 @@ int b53_configure_vlan(struct dsa_switch *ds) /* Create an untagged VLAN entry for the default PVID in case * CONFIG_VLAN_8021Q is disabled and there are no calls to - * dsa_slave_vlan_rx_add_vid() to create the default VLAN + * dsa_user_vlan_rx_add_vid() to create the default VLAN * entry. Do this only when the tagging protocol is not * DSA_TAG_PROTO_NONE */ @@ -958,7 +958,7 @@ static struct phy_device *b53_get_phy_device(struct dsa_switch *ds, int port) return NULL; } - return mdiobus_get_phy(ds->slave_mii_bus, port); + return mdiobus_get_phy(ds->user_mii_bus, port); } void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset, diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c index 4d55d8d18376..897e5e8b3d69 100644 --- a/drivers/net/dsa/b53/b53_mdio.c +++ b/drivers/net/dsa/b53/b53_mdio.c @@ -329,7 +329,7 @@ static int b53_mdio_probe(struct mdio_device *mdiodev) * layer setup */ if (of_machine_is_compatible("brcm,bcm7445d0") && - strcmp(mdiodev->bus->name, "sf2 slave mii")) + strcmp(mdiodev->bus->name, "sf2 user mii")) return -EPROBE_DEFER; dev = b53_switch_alloc(&mdiodev->dev, &b53_mdio_ops, mdiodev->bus); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 0b62bd78ac50..cadee5505c29 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -617,26 +617,25 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) dn = of_find_compatible_node(NULL, NULL, "brcm,unimac-mdio"); priv->master_mii_bus = of_mdio_find_bus(dn); if (!priv->master_mii_bus) { - of_node_put(dn); - return -EPROBE_DEFER; + err = -EPROBE_DEFER; + goto err_of_node_put; } - get_device(&priv->master_mii_bus->dev); priv->master_mii_dn = dn; - priv->slave_mii_bus = mdiobus_alloc(); - if (!priv->slave_mii_bus) { - of_node_put(dn); - return -ENOMEM; + priv->user_mii_bus = mdiobus_alloc(); + if (!priv->user_mii_bus) { + err = -ENOMEM; + goto err_put_master_mii_bus_dev; } - priv->slave_mii_bus->priv = priv; - priv->slave_mii_bus->name = "sf2 slave mii"; - priv->slave_mii_bus->read = bcm_sf2_sw_mdio_read; - priv->slave_mii_bus->write = bcm_sf2_sw_mdio_write; - snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "sf2-%d", + priv->user_mii_bus->priv = priv; + priv->user_mii_bus->name = "sf2 user mii"; + priv->user_mii_bus->read = bcm_sf2_sw_mdio_read; + priv->user_mii_bus->write = bcm_sf2_sw_mdio_write; + snprintf(priv->user_mii_bus->id, MII_BUS_ID_SIZE, "sf2-%d", index++); - priv->slave_mii_bus->dev.of_node = dn; + priv->user_mii_bus->dev.of_node = dn; /* Include the pseudo-PHY address to divert reads towards our * workaround. This is only required for 7445D0, since 7445E0 @@ -654,9 +653,9 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) priv->indir_phy_mask = 0; ds->phys_mii_mask = priv->indir_phy_mask; - ds->slave_mii_bus = priv->slave_mii_bus; - priv->slave_mii_bus->parent = ds->dev->parent; - priv->slave_mii_bus->phy_mask = ~priv->indir_phy_mask; + ds->user_mii_bus = priv->user_mii_bus; + priv->user_mii_bus->parent = ds->dev->parent; + priv->user_mii_bus->phy_mask = ~priv->indir_phy_mask; /* We need to make sure that of_phy_connect() will not work by * removing the 'phandle' and 'linux,phandle' properties and @@ -683,20 +682,26 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds) phy_device_remove(phydev); } - err = mdiobus_register(priv->slave_mii_bus); - if (err && dn) { - mdiobus_free(priv->slave_mii_bus); - of_node_put(dn); - } + err = mdiobus_register(priv->user_mii_bus); + if (err && dn) + goto err_free_user_mii_bus; + + return 0; +err_free_user_mii_bus: + mdiobus_free(priv->user_mii_bus); +err_put_master_mii_bus_dev: + put_device(&priv->master_mii_bus->dev); +err_of_node_put: + of_node_put(dn); return err; } static void bcm_sf2_mdio_unregister(struct bcm_sf2_priv *priv) { - mdiobus_unregister(priv->slave_mii_bus); - mdiobus_free(priv->slave_mii_bus); - of_node_put(priv->master_mii_dn); + mdiobus_unregister(priv->user_mii_bus); + mdiobus_free(priv->user_mii_bus); + put_device(&priv->master_mii_bus->dev); } static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) @@ -909,7 +914,7 @@ static void bcm_sf2_sw_fixed_state(struct dsa_switch *ds, int port, * state machine and make it go in PHY_FORCING state instead. */ if (!status->link) - netif_carrier_off(dsa_to_port(ds, port)->slave); + netif_carrier_off(dsa_to_port(ds, port)->user); status->duplex = DUPLEX_FULL; } else { status->link = true; @@ -983,7 +988,7 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds) static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = dsa_port_to_master(dsa_to_port(ds, port)); + struct net_device *p = dsa_port_to_conduit(dsa_to_port(ds, port)); struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); struct ethtool_wolinfo pwol = { }; @@ -1007,7 +1012,7 @@ static void bcm_sf2_sw_get_wol(struct dsa_switch *ds, int port, static int bcm_sf2_sw_set_wol(struct dsa_switch *ds, int port, struct ethtool_wolinfo *wol) { - struct net_device *p = dsa_port_to_master(dsa_to_port(ds, port)); + struct net_device *p = dsa_port_to_conduit(dsa_to_port(ds, port)); struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); s8 cpu_port = dsa_to_port(ds, port)->cpu_dp->index; struct ethtool_wolinfo pwol = { }; diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h index 00afc94ce522..424f896b5a6f 100644 --- a/drivers/net/dsa/bcm_sf2.h +++ b/drivers/net/dsa/bcm_sf2.h @@ -108,7 +108,7 @@ struct bcm_sf2_priv { /* Master and slave MDIO bus controller */ unsigned int indir_phy_mask; struct device_node *master_mii_dn; - struct mii_bus *slave_mii_bus; + struct mii_bus *user_mii_bus; struct mii_bus *master_mii_bus; /* Bitmask of ports needing BRCM tags */ diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c index c4010b7bf089..c88ee3dd4299 100644 --- a/drivers/net/dsa/bcm_sf2_cfp.c +++ b/drivers/net/dsa/bcm_sf2_cfp.c @@ -1102,7 +1102,7 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv, int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc, u32 *rule_locs) { - struct net_device *p = dsa_port_to_master(dsa_to_port(ds, port)); + struct net_device *p = dsa_port_to_conduit(dsa_to_port(ds, port)); struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); int ret = 0; @@ -1145,7 +1145,7 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port, int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port, struct ethtool_rxnfc *nfc) { - struct net_device *p = dsa_port_to_master(dsa_to_port(ds, port)); + struct net_device *p = dsa_port_to_conduit(dsa_to_port(ds, port)); struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); int ret = 0; diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index ee67adeb2cdb..fcb20eac332a 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1084,7 +1084,7 @@ static int lan9303_port_enable(struct dsa_switch *ds, int port, if (!dsa_port_is_user(dp)) return 0; - vlan_vid_add(dsa_port_to_master(dp), htons(ETH_P_8021Q), port); + vlan_vid_add(dsa_port_to_conduit(dp), htons(ETH_P_8021Q), port); return lan9303_enable_processing_port(chip, port); } @@ -1097,7 +1097,7 @@ static void lan9303_port_disable(struct dsa_switch *ds, int port) if (!dsa_port_is_user(dp)) return; - vlan_vid_del(dsa_port_to_master(dp), htons(ETH_P_8021Q), port); + vlan_vid_del(dsa_port_to_conduit(dp), htons(ETH_P_8021Q), port); lan9303_disable_processing_port(chip, port); lan9303_phy_write(ds, chip->phy_addr_base + port, MII_BMCR, BMCR_PDOWN); diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 1a2d5797bf98..9c185c9f0963 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -510,22 +510,22 @@ static int gswip_mdio(struct gswip_priv *priv, struct device_node *mdio_np) struct dsa_switch *ds = priv->ds; int err; - ds->slave_mii_bus = mdiobus_alloc(); - if (!ds->slave_mii_bus) + ds->user_mii_bus = mdiobus_alloc(); + if (!ds->user_mii_bus) return -ENOMEM; - ds->slave_mii_bus->priv = priv; - ds->slave_mii_bus->read = gswip_mdio_rd; - ds->slave_mii_bus->write = gswip_mdio_wr; - ds->slave_mii_bus->name = "lantiq,xrx200-mdio"; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "%s-mii", + ds->user_mii_bus->priv = priv; + ds->user_mii_bus->read = gswip_mdio_rd; + ds->user_mii_bus->write = gswip_mdio_wr; + ds->user_mii_bus->name = "lantiq,xrx200-mdio"; + snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev)); - ds->slave_mii_bus->parent = priv->dev; - ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; + ds->user_mii_bus->parent = priv->dev; + ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; - err = of_mdiobus_register(ds->slave_mii_bus, mdio_np); + err = of_mdiobus_register(ds->user_mii_bus, mdio_np); if (err) - mdiobus_free(ds->slave_mii_bus); + mdiobus_free(ds->user_mii_bus); return err; } @@ -2196,8 +2196,8 @@ disable_switch: dsa_unregister_switch(priv->ds); mdio_bus: if (mdio_np) { - mdiobus_unregister(priv->ds->slave_mii_bus); - mdiobus_free(priv->ds->slave_mii_bus); + mdiobus_unregister(priv->ds->user_mii_bus); + mdiobus_free(priv->ds->user_mii_bus); } put_mdio_node: of_node_put(mdio_np); @@ -2219,10 +2219,10 @@ static void gswip_remove(struct platform_device *pdev) dsa_unregister_switch(priv->ds); - if (priv->ds->slave_mii_bus) { - mdiobus_unregister(priv->ds->slave_mii_bus); - of_node_put(priv->ds->slave_mii_bus->dev.of_node); - mdiobus_free(priv->ds->slave_mii_bus); + if (priv->ds->user_mii_bus) { + mdiobus_unregister(priv->ds->user_mii_bus); + of_node_put(priv->ds->user_mii_bus->dev.of_node); + mdiobus_free(priv->ds->user_mii_bus); } for (i = 0; i < priv->num_gphy_fw; i++) diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 91aba470fb2f..4bf4d67557dc 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -632,6 +632,50 @@ static void ksz8_w_vlan_table(struct ksz_device *dev, u16 vid, u16 vlan) ksz8_w_table(dev, TABLE_VLAN, addr, buf); } +/** + * ksz8_r_phy_ctrl - Translates and reads from the SMI interface to a MIIM PHY + * Control register (Reg. 31). + * @dev: The KSZ device instance. + * @port: The port number to be read. + * @val: The value read from the SMI interface. + * + * This function reads the SMI interface and translates the hardware register + * bit values into their corresponding control settings for a MIIM PHY Control + * register. + * + * Return: 0 on success, error code on failure. + */ +static int ksz8_r_phy_ctrl(struct ksz_device *dev, int port, u16 *val) +{ + const u16 *regs = dev->info->regs; + u8 reg_val; + int ret; + + *val = 0; + + ret = ksz_pread8(dev, port, regs[P_LINK_STATUS], ®_val); + if (ret < 0) + return ret; + + if (reg_val & PORT_MDIX_STATUS) + *val |= KSZ886X_CTRL_MDIX_STAT; + + ret = ksz_pread8(dev, port, REG_PORT_LINK_MD_CTRL, ®_val); + if (ret < 0) + return ret; + + if (reg_val & PORT_FORCE_LINK) + *val |= KSZ886X_CTRL_FORCE_LINK; + + if (reg_val & PORT_POWER_SAVING) + *val |= KSZ886X_CTRL_PWRSAVE; + + if (reg_val & PORT_PHY_REMOTE_LOOPBACK) + *val |= KSZ886X_CTRL_REMOTE_LOOPBACK; + + return 0; +} + int ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) { u8 restart, speed, ctrl, link; @@ -769,12 +813,10 @@ int ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) FIELD_GET(PORT_CABLE_FAULT_COUNTER_L, val2)); break; case PHY_REG_PHY_CTRL: - ret = ksz_pread8(dev, p, regs[P_LINK_STATUS], &link); + ret = ksz8_r_phy_ctrl(dev, p, &data); if (ret) return ret; - if (link & PORT_MDIX_STATUS) - data |= KSZ886X_CTRL_MDIX_STAT; break; default: processed = false; @@ -786,6 +828,38 @@ int ksz8_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val) return 0; } +/** + * ksz8_w_phy_ctrl - Translates and writes to the SMI interface from a MIIM PHY + * Control register (Reg. 31). + * @dev: The KSZ device instance. + * @port: The port number to be configured. + * @val: The register value to be written. + * + * This function translates control settings from a MIIM PHY Control register + * into their corresponding hardware register bit values for the SMI + * interface. + * + * Return: 0 on success, error code on failure. + */ +static int ksz8_w_phy_ctrl(struct ksz_device *dev, int port, u16 val) +{ + u8 reg_val = 0; + int ret; + + if (val & KSZ886X_CTRL_FORCE_LINK) + reg_val |= PORT_FORCE_LINK; + + if (val & KSZ886X_CTRL_PWRSAVE) + reg_val |= PORT_POWER_SAVING; + + if (val & KSZ886X_CTRL_REMOTE_LOOPBACK) + reg_val |= PORT_PHY_REMOTE_LOOPBACK; + + ret = ksz_prmw8(dev, port, REG_PORT_LINK_MD_CTRL, PORT_FORCE_LINK | + PORT_POWER_SAVING | PORT_PHY_REMOTE_LOOPBACK, reg_val); + return ret; +} + int ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) { u8 restart, speed, ctrl, data; @@ -926,6 +1000,12 @@ int ksz8_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val) if (val & PHY_START_CABLE_DIAG) ksz_port_cfg(dev, p, REG_PORT_LINK_MD_CTRL, PORT_START_CABLE_DIAG, true); break; + + case PHY_REG_PHY_CTRL: + ret = ksz8_w_phy_ctrl(dev, p, val); + if (ret) + return ret; + break; default: break; } diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index cde8ef33d029..2534c3d122e4 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -56,6 +56,103 @@ int ksz9477_change_mtu(struct ksz_device *dev, int port, int mtu) REG_SW_MTU_MASK, frame_size); } +/** + * ksz9477_handle_wake_reason - Handle wake reason on a specified port. + * @dev: The device structure. + * @port: The port number. + * + * This function reads the PME (Power Management Event) status register of a + * specified port to determine the wake reason. If there is no wake event, it + * returns early. Otherwise, it logs the wake reason which could be due to a + * "Magic Packet", "Link Up", or "Energy Detect" event. The PME status register + * is then cleared to acknowledge the handling of the wake event. + * + * Return: 0 on success, or an error code on failure. + */ +static int ksz9477_handle_wake_reason(struct ksz_device *dev, int port) +{ + u8 pme_status; + int ret; + + ret = ksz_pread8(dev, port, REG_PORT_PME_STATUS, &pme_status); + if (ret) + return ret; + + if (!pme_status) + return 0; + + dev_dbg(dev->dev, "Wake event on port %d due to:%s%s\n", port, + pme_status & PME_WOL_LINKUP ? " \"Link Up\"" : "", + pme_status & PME_WOL_ENERGY ? " \"Enery detect\"" : ""); + + return ksz_pwrite8(dev, port, REG_PORT_PME_STATUS, pme_status); +} + +/** + * ksz9477_get_wol - Get Wake-on-LAN settings for a specified port. + * @dev: The device structure. + * @port: The port number. + * @wol: Pointer to ethtool Wake-on-LAN settings structure. + * + * This function checks the PME Pin Control Register to see if PME Pin Output + * Enable is set, indicating PME is enabled. If enabled, it sets the supported + * and active WoL flags. + */ +void ksz9477_get_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol) +{ + u8 pme_ctrl; + int ret; + + if (!dev->wakeup_source) + return; + + wol->supported = WAKE_PHY; + + ret = ksz_pread8(dev, port, REG_PORT_PME_CTRL, &pme_ctrl); + if (ret) + return; + + if (pme_ctrl & (PME_WOL_LINKUP | PME_WOL_ENERGY)) + wol->wolopts |= WAKE_PHY; +} + +/** + * ksz9477_set_wol - Set Wake-on-LAN settings for a specified port. + * @dev: The device structure. + * @port: The port number. + * @wol: Pointer to ethtool Wake-on-LAN settings structure. + * + * This function configures Wake-on-LAN (WoL) settings for a specified port. + * It validates the provided WoL options, checks if PME is enabled via the + * switch's PME Pin Control Register, clears any previous wake reasons, + * and sets the Magic Packet flag in the port's PME control register if + * specified. + * + * Return: 0 on success, or other error codes on failure. + */ +int ksz9477_set_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol) +{ + u8 pme_ctrl = 0; + int ret; + + if (wol->wolopts & ~WAKE_PHY) + return -EINVAL; + + if (!dev->wakeup_source) + return -EOPNOTSUPP; + + ret = ksz9477_handle_wake_reason(dev, port); + if (ret) + return ret; + + if (wol->wolopts & WAKE_PHY) + pme_ctrl |= PME_WOL_LINKUP | PME_WOL_ENERGY; + + return ksz_pwrite8(dev, port, REG_PORT_PME_CTRL, pme_ctrl); +} + static int ksz9477_wait_vlan_ctrl_ready(struct ksz_device *dev) { unsigned int val; @@ -1006,6 +1103,9 @@ void ksz9477_port_setup(struct ksz_device *dev, int port, bool cpu_port) ksz_pread16(dev, port, REG_PORT_PHY_INT_ENABLE, &data16); ksz9477_port_acl_init(dev, port); + + /* clear pending wake flags */ + ksz9477_handle_wake_reason(dev, port); } void ksz9477_config_cpu_port(struct dsa_switch *ds) @@ -1170,7 +1270,7 @@ int ksz9477_tc_cbs_set_cinc(struct ksz_device *dev, int port, u32 val) void ksz9477_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr) { struct ksz_device *dev = ds->priv; - struct net_device *slave; + struct net_device *user; struct dsa_port *hsr_dp; u8 data, hsr_ports = 0; @@ -1202,8 +1302,8 @@ void ksz9477_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr) ksz_port_cfg(dev, port, REG_PORT_LUE_CTRL, PORT_SRC_ADDR_FILTER, true); /* Setup HW supported features for lan HSR ports */ - slave = dsa_to_port(ds, port)->slave; - slave->features |= KSZ9477_SUPPORTED_HSR_FEATURES; + user = dsa_to_port(ds, port)->user; + user->features |= KSZ9477_SUPPORTED_HSR_FEATURES; } void ksz9477_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr) diff --git a/drivers/net/dsa/microchip/ksz9477.h b/drivers/net/dsa/microchip/ksz9477.h index f90e2e8ebe80..fa8d0318b437 100644 --- a/drivers/net/dsa/microchip/ksz9477.h +++ b/drivers/net/dsa/microchip/ksz9477.h @@ -58,6 +58,10 @@ void ksz9477_switch_exit(struct ksz_device *dev); void ksz9477_port_queue_split(struct ksz_device *dev, int port); void ksz9477_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr); void ksz9477_hsr_leave(struct dsa_switch *ds, int port, struct net_device *hsr); +void ksz9477_get_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol); +int ksz9477_set_wol(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol); int ksz9477_port_acl_init(struct ksz_device *dev, int port); void ksz9477_port_acl_free(struct ksz_device *dev, int port); diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index b800ace40ce1..de788f424a3f 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -319,6 +319,8 @@ static const struct ksz_dev_ops ksz9477_dev_ops = { .mdb_del = ksz9477_mdb_del, .change_mtu = ksz9477_change_mtu, .phylink_mac_link_up = ksz9477_phylink_mac_link_up, + .get_wol = ksz9477_get_wol, + .set_wol = ksz9477_set_wol, .config_cpu_port = ksz9477_config_cpu_port, .tc_cbs_set_cinc = ksz9477_tc_cbs_set_cinc, .enable_stp_addr = ksz9477_enable_stp_addr, @@ -441,6 +443,7 @@ static const u8 ksz8795_shifts[] = { }; static const u16 ksz8863_regs[] = { + [REG_SW_MAC_ADDR] = 0x70, [REG_IND_CTRL_0] = 0x79, [REG_IND_DATA_8] = 0x7B, [REG_IND_DATA_CHECK] = 0x7B, @@ -1945,14 +1948,14 @@ static int ksz_irq_phy_setup(struct ksz_device *dev) ret = irq; goto out; } - ds->slave_mii_bus->irq[phy] = irq; + ds->user_mii_bus->irq[phy] = irq; } } return 0; out: while (phy--) if (BIT(phy) & ds->phys_mii_mask) - irq_dispose_mapping(ds->slave_mii_bus->irq[phy]); + irq_dispose_mapping(ds->user_mii_bus->irq[phy]); return ret; } @@ -1964,7 +1967,7 @@ static void ksz_irq_phy_free(struct ksz_device *dev) for (phy = 0; phy < KSZ_MAX_NUM_PORTS; phy++) if (BIT(phy) & ds->phys_mii_mask) - irq_dispose_mapping(ds->slave_mii_bus->irq[phy]); + irq_dispose_mapping(ds->user_mii_bus->irq[phy]); } static int ksz_mdio_register(struct ksz_device *dev) @@ -1987,12 +1990,12 @@ static int ksz_mdio_register(struct ksz_device *dev) bus->priv = dev; bus->read = ksz_sw_mdio_read; bus->write = ksz_sw_mdio_write; - bus->name = "ksz slave smi"; + bus->name = "ksz user smi"; snprintf(bus->id, MII_BUS_ID_SIZE, "SMI-%d", ds->index); bus->parent = ds->dev; bus->phy_mask = ~ds->phys_mii_mask; - ds->slave_mii_bus = bus; + ds->user_mii_bus = bus; if (dev->irq > 0) { ret = ksz_irq_phy_setup(dev); @@ -2344,7 +2347,7 @@ static void ksz_mib_read_work(struct work_struct *work) if (!p->read) { const struct dsa_port *dp = dsa_to_port(dev->ds, i); - if (!netif_carrier_ok(dp->slave)) + if (!netif_carrier_ok(dp->user)) mib->cnt_ptr = dev->info->reg_mib_cnt; } port_r_cnt(dev, i); @@ -2464,7 +2467,7 @@ static void ksz_get_ethtool_stats(struct dsa_switch *ds, int port, mutex_lock(&mib->cnt_mutex); /* Only read dropped counters if no link. */ - if (!netif_carrier_ok(dp->slave)) + if (!netif_carrier_ok(dp->user)) mib->cnt_ptr = dev->info->reg_mib_cnt; port_r_cnt(dev, port); memcpy(buf, mib->counters, dev->info->mib_cnt * sizeof(u64)); @@ -2574,7 +2577,7 @@ static int ksz_port_setup(struct dsa_switch *ds, int port) if (!dsa_is_user_port(ds, port)) return 0; - /* setup slave port */ + /* setup user port */ dev->dev_ops->port_setup(dev, port, false); /* port_stp_state_set() will be called after to enable the port so @@ -3542,6 +3545,26 @@ static int ksz_setup_tc(struct dsa_switch *ds, int port, } } +static void ksz_get_wol(struct dsa_switch *ds, int port, + struct ethtool_wolinfo *wol) +{ + struct ksz_device *dev = ds->priv; + + if (dev->dev_ops->get_wol) + dev->dev_ops->get_wol(dev, port, wol); +} + +static int ksz_set_wol(struct dsa_switch *ds, int port, + struct ethtool_wolinfo *wol) +{ + struct ksz_device *dev = ds->priv; + + if (dev->dev_ops->set_wol) + return dev->dev_ops->set_wol(dev, port, wol); + + return -EOPNOTSUPP; +} + static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, const unsigned char *addr) { @@ -3567,8 +3590,8 @@ static int ksz_port_set_mac_address(struct dsa_switch *ds, int port, static int ksz_switch_macaddr_get(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack) { - struct net_device *slave = dsa_to_port(ds, port)->slave; - const unsigned char *addr = slave->dev_addr; + struct net_device *user = dsa_to_port(ds, port)->user; + const unsigned char *addr = user->dev_addr; struct ksz_switch_macaddr *switch_macaddr; struct ksz_device *dev = ds->priv; const u16 *regs = dev->info->regs; @@ -3726,6 +3749,8 @@ static const struct dsa_switch_ops ksz_switch_ops = { .get_pause_stats = ksz_get_pause_stats, .port_change_mtu = ksz_change_mtu, .port_max_mtu = ksz_max_mtu, + .get_wol = ksz_get_wol, + .set_wol = ksz_set_wol, .get_ts_info = ksz_get_ts_info, .port_hwtstamp_get = ksz_hwtstamp_get, .port_hwtstamp_set = ksz_hwtstamp_set, @@ -4158,6 +4183,9 @@ int ksz_switch_register(struct ksz_device *dev) dev_err(dev->dev, "inconsistent synclko settings\n"); return -EINVAL; } + + dev->wakeup_source = of_property_read_bool(dev->dev->of_node, + "wakeup-source"); } ret = dsa_register_switch(dev->ds); diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 8842efca0871..a7394175fcf6 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -163,6 +163,7 @@ struct ksz_device { phy_interface_t compat_interface; bool synclko_125; bool synclko_disable; + bool wakeup_source; struct vlan_table *vlan_cache; @@ -373,6 +374,10 @@ struct ksz_dev_ops { int duplex, bool tx_pause, bool rx_pause); void (*setup_rgmii_delay)(struct ksz_device *dev, int port); int (*tc_cbs_set_cinc)(struct ksz_device *dev, int port, u32 val); + void (*get_wol)(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol); + int (*set_wol)(struct ksz_device *dev, int port, + struct ethtool_wolinfo *wol); void (*config_cpu_port)(struct dsa_switch *ds); int (*enable_stp_addr)(struct ksz_device *dev); int (*reset)(struct ksz_device *dev); diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index 4e22a695a64c..1fe105913c75 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -557,7 +557,7 @@ static void ksz_ptp_txtstamp_skb(struct ksz_device *dev, struct skb_shared_hwtstamps hwtstamps = {}; int ret; - /* timeout must include DSA master to transmit data, tstamp latency, + /* timeout must include DSA conduit to transmit data, tstamp latency, * IRQ latency and time for reading the time stamp. */ ret = wait_for_completion_timeout(&prt->tstamp_msg_comp, diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index ecf5d3deb36e..d27c6b70a2f6 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -1113,7 +1113,7 @@ mt7530_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) u32 val; /* When a new MTU is set, DSA always set the CPU port's MTU to the - * largest MTU of the slave ports. Because the switch only has a global + * largest MTU of the user ports. Because the switch only has a global * RX length register, only allowing CPU port here is enough. */ if (!dsa_is_cpu_port(ds, port)) @@ -2069,7 +2069,7 @@ mt7530_setup_mdio_irq(struct mt7530_priv *priv) unsigned int irq; irq = irq_create_mapping(priv->irq_domain, p); - ds->slave_mii_bus->irq[p] = irq; + ds->user_mii_bus->irq[p] = irq; } } } @@ -2163,7 +2163,7 @@ mt7530_setup_mdio(struct mt7530_priv *priv) if (!bus) return -ENOMEM; - ds->slave_mii_bus = bus; + ds->user_mii_bus = bus; bus->priv = priv; bus->name = KBUILD_MODNAME "-mii"; snprintf(bus->id, MII_BUS_ID_SIZE, KBUILD_MODNAME "-%d", idx++); @@ -2200,20 +2200,20 @@ mt7530_setup(struct dsa_switch *ds) u32 id, val; int ret, i; - /* The parent node of master netdev which holds the common system + /* The parent node of conduit netdev which holds the common system * controller also is the container for two GMACs nodes representing * as two netdev instances. */ dsa_switch_for_each_cpu_port(cpu_dp, ds) { - dn = cpu_dp->master->dev.of_node->parent; + dn = cpu_dp->conduit->dev.of_node->parent; /* It doesn't matter which CPU port is found first, - * their masters should share the same parent OF node + * their conduits should share the same parent OF node */ break; } if (!dn) { - dev_err(ds->dev, "parent OF node of DSA master not found"); + dev_err(ds->dev, "parent OF node of DSA conduit not found"); return -EINVAL; } @@ -2488,7 +2488,7 @@ mt7531_setup(struct dsa_switch *ds) if (mt7531_dual_sgmii_supported(priv)) { priv->p5_intf_sel = P5_INTF_SEL_GMAC5_SGMII; - /* Let ds->slave_mii_bus be able to access external phy. */ + /* Let ds->user_mii_bus be able to access external phy. */ mt7530_rmw(priv, MT7531_GPIO_MODE1, MT7531_GPIO11_RG_RXD2_MASK, MT7531_EXT_P_MDC_11); mt7530_rmw(priv, MT7531_GPIO_MODE1, MT7531_GPIO12_RG_RXD3_MASK, @@ -2717,7 +2717,7 @@ mt7531_mac_config(struct dsa_switch *ds, int port, unsigned int mode, case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: dp = dsa_to_port(ds, port); - phydev = dp->slave->phydev; + phydev = dp->user->phydev; return mt7531_rgmii_setup(priv, port, interface, phydev); case PHY_INTERFACE_MODE_SGMII: case PHY_INTERFACE_MODE_NA: diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index ab434a77b059..42b1acaca33a 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -2486,7 +2486,7 @@ static int mv88e6xxx_port_vlan_add(struct dsa_switch *ds, int port, else member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_TAGGED; - /* net/dsa/slave.c will call dsa_port_vlan_add() for the affected port + /* net/dsa/user.c will call dsa_port_vlan_add() for the affected port * and then the CPU port. Do not warn for duplicates for the CPU port. */ warn = !dsa_is_cpu_port(ds, port) && !dsa_is_dsa_port(ds, port); @@ -3719,7 +3719,7 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) return err; chip->ds = ds; - ds->slave_mii_bus = mv88e6xxx_default_mdio_bus(chip); + ds->user_mii_bus = mv88e6xxx_default_mdio_bus(chip); /* Since virtual bridges are mapped in the PVT, the number we support * depends on the physical switch topology. We need to let DSA figure diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c index ea17231dc34e..56391e09b325 100644 --- a/drivers/net/dsa/mv88e6xxx/ptp.c +++ b/drivers/net/dsa/mv88e6xxx/ptp.c @@ -182,6 +182,10 @@ static void mv88e6352_tai_event_work(struct work_struct *ugly) mv88e6xxx_reg_lock(chip); err = mv88e6xxx_tai_write(chip, MV88E6XXX_TAI_EVENT_STATUS, status[0]); mv88e6xxx_reg_unlock(chip); + if (err) { + dev_err(chip->dev, "failed to write TAI status register\n"); + return; + } /* This is an external timestamp */ ev.type = PTP_CLOCK_EXTTS; diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 9a3e5ec16972..61e95487732d 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -42,22 +42,22 @@ static struct net_device *felix_classify_db(struct dsa_db db) } } -static int felix_cpu_port_for_master(struct dsa_switch *ds, - struct net_device *master) +static int felix_cpu_port_for_conduit(struct dsa_switch *ds, + struct net_device *conduit) { struct ocelot *ocelot = ds->priv; struct dsa_port *cpu_dp; int lag; - if (netif_is_lag_master(master)) { + if (netif_is_lag_master(conduit)) { mutex_lock(&ocelot->fwd_domain_lock); - lag = ocelot_bond_get_id(ocelot, master); + lag = ocelot_bond_get_id(ocelot, conduit); mutex_unlock(&ocelot->fwd_domain_lock); return lag; } - cpu_dp = master->dsa_ptr; + cpu_dp = conduit->dsa_ptr; return cpu_dp->index; } @@ -366,7 +366,7 @@ static int felix_update_trapping_destinations(struct dsa_switch *ds, * is the mode through which frames can be injected from and extracted to an * external CPU, over Ethernet. In NXP SoCs, the "external CPU" is the ARM CPU * running Linux, and this forms a DSA setup together with the enetc or fman - * DSA master. + * DSA conduit. */ static void felix_npi_port_init(struct ocelot *ocelot, int port) { @@ -441,16 +441,16 @@ static unsigned long felix_tag_npi_get_host_fwd_mask(struct dsa_switch *ds) return BIT(ocelot->num_phys_ports); } -static int felix_tag_npi_change_master(struct dsa_switch *ds, int port, - struct net_device *master, - struct netlink_ext_ack *extack) +static int felix_tag_npi_change_conduit(struct dsa_switch *ds, int port, + struct net_device *conduit, + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_to_port(ds, port), *other_dp; struct ocelot *ocelot = ds->priv; - if (netif_is_lag_master(master)) { + if (netif_is_lag_master(conduit)) { NL_SET_ERR_MSG_MOD(extack, - "LAG DSA master only supported using ocelot-8021q"); + "LAG DSA conduit only supported using ocelot-8021q"); return -EOPNOTSUPP; } @@ -459,24 +459,24 @@ static int felix_tag_npi_change_master(struct dsa_switch *ds, int port, * come back up until they're all changed to the new one. */ dsa_switch_for_each_user_port(other_dp, ds) { - struct net_device *slave = other_dp->slave; + struct net_device *user = other_dp->user; - if (other_dp != dp && (slave->flags & IFF_UP) && - dsa_port_to_master(other_dp) != master) { + if (other_dp != dp && (user->flags & IFF_UP) && + dsa_port_to_conduit(other_dp) != conduit) { NL_SET_ERR_MSG_MOD(extack, - "Cannot change while old master still has users"); + "Cannot change while old conduit still has users"); return -EOPNOTSUPP; } } felix_npi_port_deinit(ocelot, ocelot->npi); - felix_npi_port_init(ocelot, felix_cpu_port_for_master(ds, master)); + felix_npi_port_init(ocelot, felix_cpu_port_for_conduit(ds, conduit)); return 0; } /* Alternatively to using the NPI functionality, that same hardware MAC - * connected internally to the enetc or fman DSA master can be configured to + * connected internally to the enetc or fman DSA conduit can be configured to * use the software-defined tag_8021q frame format. As far as the hardware is * concerned, it thinks it is a "dumb switch" - the queues of the CPU port * module are now disconnected from it, but can still be accessed through @@ -486,7 +486,7 @@ static const struct felix_tag_proto_ops felix_tag_npi_proto_ops = { .setup = felix_tag_npi_setup, .teardown = felix_tag_npi_teardown, .get_host_fwd_mask = felix_tag_npi_get_host_fwd_mask, - .change_master = felix_tag_npi_change_master, + .change_conduit = felix_tag_npi_change_conduit, }; static int felix_tag_8021q_setup(struct dsa_switch *ds) @@ -561,11 +561,11 @@ static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds) return dsa_cpu_ports(ds); } -static int felix_tag_8021q_change_master(struct dsa_switch *ds, int port, - struct net_device *master, - struct netlink_ext_ack *extack) +static int felix_tag_8021q_change_conduit(struct dsa_switch *ds, int port, + struct net_device *conduit, + struct netlink_ext_ack *extack) { - int cpu = felix_cpu_port_for_master(ds, master); + int cpu = felix_cpu_port_for_conduit(ds, conduit); struct ocelot *ocelot = ds->priv; ocelot_port_unassign_dsa_8021q_cpu(ocelot, port); @@ -578,7 +578,7 @@ static const struct felix_tag_proto_ops felix_tag_8021q_proto_ops = { .setup = felix_tag_8021q_setup, .teardown = felix_tag_8021q_teardown, .get_host_fwd_mask = felix_tag_8021q_get_host_fwd_mask, - .change_master = felix_tag_8021q_change_master, + .change_conduit = felix_tag_8021q_change_conduit, }; static void felix_set_host_flood(struct dsa_switch *ds, unsigned long mask, @@ -741,14 +741,14 @@ static void felix_port_set_host_flood(struct dsa_switch *ds, int port, !!felix->host_flood_mc_mask, true); } -static int felix_port_change_master(struct dsa_switch *ds, int port, - struct net_device *master, - struct netlink_ext_ack *extack) +static int felix_port_change_conduit(struct dsa_switch *ds, int port, + struct net_device *conduit, + struct netlink_ext_ack *extack) { struct ocelot *ocelot = ds->priv; struct felix *felix = ocelot_to_felix(ocelot); - return felix->tag_proto_ops->change_master(ds, port, master, extack); + return felix->tag_proto_ops->change_conduit(ds, port, conduit, extack); } static int felix_set_ageing_time(struct dsa_switch *ds, @@ -953,7 +953,7 @@ static int felix_lag_join(struct dsa_switch *ds, int port, if (!dsa_is_cpu_port(ds, port)) return 0; - return felix_port_change_master(ds, port, lag.dev, extack); + return felix_port_change_conduit(ds, port, lag.dev, extack); } static int felix_lag_leave(struct dsa_switch *ds, int port, @@ -967,7 +967,7 @@ static int felix_lag_leave(struct dsa_switch *ds, int port, if (!dsa_is_cpu_port(ds, port)) return 0; - return felix_port_change_master(ds, port, lag.dev, NULL); + return felix_port_change_conduit(ds, port, lag.dev, NULL); } static int felix_lag_change(struct dsa_switch *ds, int port) @@ -1116,10 +1116,10 @@ static int felix_port_enable(struct dsa_switch *ds, int port, return 0; if (ocelot->npi >= 0) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); - if (felix_cpu_port_for_master(ds, master) != ocelot->npi) { - dev_err(ds->dev, "Multiple masters are not allowed\n"); + if (felix_cpu_port_for_conduit(ds, conduit) != ocelot->npi) { + dev_err(ds->dev, "Multiple conduits are not allowed\n"); return -EINVAL; } } @@ -2164,7 +2164,7 @@ const struct dsa_switch_ops felix_switch_ops = { .port_add_dscp_prio = felix_port_add_dscp_prio, .port_del_dscp_prio = felix_port_del_dscp_prio, .port_set_host_flood = felix_port_set_host_flood, - .port_change_master = felix_port_change_master, + .port_change_conduit = felix_port_change_conduit, }; EXPORT_SYMBOL_GPL(felix_switch_ops); @@ -2176,7 +2176,7 @@ struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port) if (!dsa_is_user_port(ds, port)) return NULL; - return dsa_to_port(ds, port)->slave; + return dsa_to_port(ds, port)->user; } EXPORT_SYMBOL_GPL(felix_port_to_netdev); diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 1d4befe7cfe8..dbf5872fe367 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -77,9 +77,9 @@ struct felix_tag_proto_ops { int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); unsigned long (*get_host_fwd_mask)(struct dsa_switch *ds); - int (*change_master)(struct dsa_switch *ds, int port, - struct net_device *master, - struct netlink_ext_ack *extack); + int (*change_conduit)(struct dsa_switch *ds, int port, + struct net_device *conduit, + struct netlink_ext_ack *extack); }; extern const struct dsa_switch_ops felix_switch_ops; diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c index 4ce68e655a63..ec57d9d52072 100644 --- a/drivers/net/dsa/qca/qca8k-8xxx.c +++ b/drivers/net/dsa/qca/qca8k-8xxx.c @@ -323,14 +323,14 @@ static int qca8k_read_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) mutex_lock(&mgmt_eth_data->mutex); - /* Check mgmt_master if is operational */ - if (!priv->mgmt_master) { + /* Check if the mgmt_conduit if is operational */ + if (!priv->mgmt_conduit) { kfree_skb(skb); mutex_unlock(&mgmt_eth_data->mutex); return -EINVAL; } - skb->dev = priv->mgmt_master; + skb->dev = priv->mgmt_conduit; reinit_completion(&mgmt_eth_data->rw_done); @@ -375,14 +375,14 @@ static int qca8k_write_eth(struct qca8k_priv *priv, u32 reg, u32 *val, int len) mutex_lock(&mgmt_eth_data->mutex); - /* Check mgmt_master if is operational */ - if (!priv->mgmt_master) { + /* Check if the mgmt_conduit if is operational */ + if (!priv->mgmt_conduit) { kfree_skb(skb); mutex_unlock(&mgmt_eth_data->mutex); return -EINVAL; } - skb->dev = priv->mgmt_master; + skb->dev = priv->mgmt_conduit; reinit_completion(&mgmt_eth_data->rw_done); @@ -508,7 +508,7 @@ qca8k_bulk_read(void *ctx, const void *reg_buf, size_t reg_len, struct qca8k_priv *priv = ctx; u32 reg = *(u16 *)reg_buf; - if (priv->mgmt_master && + if (priv->mgmt_conduit && !qca8k_read_eth(priv, reg, val_buf, val_len)) return 0; @@ -531,7 +531,7 @@ qca8k_bulk_gather_write(void *ctx, const void *reg_buf, size_t reg_len, u32 reg = *(u16 *)reg_buf; u32 *val = (u32 *)val_buf; - if (priv->mgmt_master && + if (priv->mgmt_conduit && !qca8k_write_eth(priv, reg, val, val_len)) return 0; @@ -626,7 +626,7 @@ qca8k_phy_eth_command(struct qca8k_priv *priv, bool read, int phy, struct sk_buff *write_skb, *clear_skb, *read_skb; struct qca8k_mgmt_eth_data *mgmt_eth_data; u32 write_val, clear_val = 0, val; - struct net_device *mgmt_master; + struct net_device *mgmt_conduit; int ret, ret1; bool ack; @@ -683,18 +683,18 @@ qca8k_phy_eth_command(struct qca8k_priv *priv, bool read, int phy, */ mutex_lock(&mgmt_eth_data->mutex); - /* Check if mgmt_master is operational */ - mgmt_master = priv->mgmt_master; - if (!mgmt_master) { + /* Check if mgmt_conduit is operational */ + mgmt_conduit = priv->mgmt_conduit; + if (!mgmt_conduit) { mutex_unlock(&mgmt_eth_data->mutex); mutex_unlock(&priv->bus->mdio_lock); ret = -EINVAL; - goto err_mgmt_master; + goto err_mgmt_conduit; } - read_skb->dev = mgmt_master; - clear_skb->dev = mgmt_master; - write_skb->dev = mgmt_master; + read_skb->dev = mgmt_conduit; + clear_skb->dev = mgmt_conduit; + write_skb->dev = mgmt_conduit; reinit_completion(&mgmt_eth_data->rw_done); @@ -780,7 +780,7 @@ exit: return ret; /* Error handling before lock */ -err_mgmt_master: +err_mgmt_conduit: kfree_skb(read_skb); err_read_skb: kfree_skb(clear_skb); @@ -959,12 +959,12 @@ qca8k_mdio_register(struct qca8k_priv *priv) ds->dst->index, ds->index); bus->parent = ds->dev; bus->phy_mask = ~ds->phys_mii_mask; - ds->slave_mii_bus = bus; + ds->user_mii_bus = bus; /* Check if the devicetree declare the port:phy mapping */ mdio = of_get_child_by_name(priv->dev->of_node, "mdio"); if (of_device_is_available(mdio)) { - bus->name = "qca8k slave mii"; + bus->name = "qca8k user mii"; bus->read = qca8k_internal_mdio_read; bus->write = qca8k_internal_mdio_write; return devm_of_mdiobus_register(priv->dev, bus, mdio); @@ -973,7 +973,7 @@ qca8k_mdio_register(struct qca8k_priv *priv) /* If a mapping can't be found the legacy mapping is used, * using the qca8k_port_to_phy function */ - bus->name = "qca8k-legacy slave mii"; + bus->name = "qca8k-legacy user mii"; bus->read = qca8k_legacy_mdio_read; bus->write = qca8k_legacy_mdio_write; return devm_mdiobus_register(priv->dev, bus); @@ -1728,10 +1728,10 @@ qca8k_get_tag_protocol(struct dsa_switch *ds, int port, } static void -qca8k_master_change(struct dsa_switch *ds, const struct net_device *master, - bool operational) +qca8k_conduit_change(struct dsa_switch *ds, const struct net_device *conduit, + bool operational) { - struct dsa_port *dp = master->dsa_ptr; + struct dsa_port *dp = conduit->dsa_ptr; struct qca8k_priv *priv = ds->priv; /* Ethernet MIB/MDIO is only supported for CPU port 0 */ @@ -1741,7 +1741,7 @@ qca8k_master_change(struct dsa_switch *ds, const struct net_device *master, mutex_lock(&priv->mgmt_eth_data.mutex); mutex_lock(&priv->mib_eth_data.mutex); - priv->mgmt_master = operational ? (struct net_device *)master : NULL; + priv->mgmt_conduit = operational ? (struct net_device *)conduit : NULL; mutex_unlock(&priv->mib_eth_data.mutex); mutex_unlock(&priv->mgmt_eth_data.mutex); @@ -2016,7 +2016,7 @@ static const struct dsa_switch_ops qca8k_switch_ops = { .get_phy_flags = qca8k_get_phy_flags, .port_lag_join = qca8k_port_lag_join, .port_lag_leave = qca8k_port_lag_leave, - .master_state_change = qca8k_master_change, + .conduit_state_change = qca8k_conduit_change, .connect_tag_protocol = qca8k_connect_tag_protocol, }; diff --git a/drivers/net/dsa/qca/qca8k-common.c b/drivers/net/dsa/qca/qca8k-common.c index 9ff0a3c1cb91..9243eff8918d 100644 --- a/drivers/net/dsa/qca/qca8k-common.c +++ b/drivers/net/dsa/qca/qca8k-common.c @@ -499,7 +499,7 @@ void qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, u32 hi = 0; int ret; - if (priv->mgmt_master && priv->info->ops->autocast_mib && + if (priv->mgmt_conduit && priv->info->ops->autocast_mib && priv->info->ops->autocast_mib(ds, port, data) > 0) return; @@ -761,7 +761,7 @@ int qca8k_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) int ret; /* We have only have a general MTU setting. - * DSA always set the CPU port's MTU to the largest MTU of the slave + * DSA always set the CPU port's MTU to the largest MTU of the user * ports. * Setting MTU just for the CPU port is sufficient to correctly set a * value for every port. diff --git a/drivers/net/dsa/qca/qca8k-leds.c b/drivers/net/dsa/qca/qca8k-leds.c index e8c16e76e34b..90e30c2909e4 100644 --- a/drivers/net/dsa/qca/qca8k-leds.c +++ b/drivers/net/dsa/qca/qca8k-leds.c @@ -356,8 +356,8 @@ static struct device *qca8k_cled_hw_control_get_device(struct led_classdev *ldev dp = dsa_to_port(priv->ds, qca8k_phy_to_port(led->port_num)); if (!dp) return NULL; - if (dp->slave) - return &dp->slave->dev; + if (dp->user) + return &dp->user->dev; return NULL; } @@ -429,7 +429,7 @@ qca8k_parse_port_leds(struct qca8k_priv *priv, struct fwnode_handle *port, int p init_data.default_label = ":port"; init_data.fwnode = led; init_data.devname_mandatory = true; - init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d", ds->slave_mii_bus->id, + init_data.devicename = kasprintf(GFP_KERNEL, "%s:0%d", ds->user_mii_bus->id, port_num); if (!init_data.devicename) return -ENOMEM; diff --git a/drivers/net/dsa/qca/qca8k.h b/drivers/net/dsa/qca/qca8k.h index 8f88b7db384d..2ac7e88f8da5 100644 --- a/drivers/net/dsa/qca/qca8k.h +++ b/drivers/net/dsa/qca/qca8k.h @@ -458,7 +458,7 @@ struct qca8k_priv { struct mutex reg_mutex; struct device *dev; struct gpio_desc *reset_gpio; - struct net_device *mgmt_master; /* Track if mdio/mib Ethernet is available */ + struct net_device *mgmt_conduit; /* Track if mdio/mib Ethernet is available */ struct qca8k_mgmt_eth_data mgmt_eth_data; struct qca8k_mib_eth_data mib_eth_data; struct qca8k_mdio_cache mdio_cache; diff --git a/drivers/net/dsa/realtek/realtek-smi.c b/drivers/net/dsa/realtek/realtek-smi.c index bfd11591faf4..755546ed8db6 100644 --- a/drivers/net/dsa/realtek/realtek-smi.c +++ b/drivers/net/dsa/realtek/realtek-smi.c @@ -378,25 +378,25 @@ static int realtek_smi_setup_mdio(struct dsa_switch *ds) return -ENODEV; } - priv->slave_mii_bus = devm_mdiobus_alloc(priv->dev); - if (!priv->slave_mii_bus) { + priv->user_mii_bus = devm_mdiobus_alloc(priv->dev); + if (!priv->user_mii_bus) { ret = -ENOMEM; goto err_put_node; } - priv->slave_mii_bus->priv = priv; - priv->slave_mii_bus->name = "SMI slave MII"; - priv->slave_mii_bus->read = realtek_smi_mdio_read; - priv->slave_mii_bus->write = realtek_smi_mdio_write; - snprintf(priv->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d", + priv->user_mii_bus->priv = priv; + priv->user_mii_bus->name = "SMI user MII"; + priv->user_mii_bus->read = realtek_smi_mdio_read; + priv->user_mii_bus->write = realtek_smi_mdio_write; + snprintf(priv->user_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d", ds->index); - priv->slave_mii_bus->dev.of_node = mdio_np; - priv->slave_mii_bus->parent = priv->dev; - ds->slave_mii_bus = priv->slave_mii_bus; + priv->user_mii_bus->dev.of_node = mdio_np; + priv->user_mii_bus->parent = priv->dev; + ds->user_mii_bus = priv->user_mii_bus; - ret = devm_of_mdiobus_register(priv->dev, priv->slave_mii_bus, mdio_np); + ret = devm_of_mdiobus_register(priv->dev, priv->user_mii_bus, mdio_np); if (ret) { dev_err(priv->dev, "unable to register MDIO bus %s\n", - priv->slave_mii_bus->id); + priv->user_mii_bus->id); goto err_put_node; } @@ -514,8 +514,8 @@ static void realtek_smi_remove(struct platform_device *pdev) return; dsa_unregister_switch(priv->ds); - if (priv->slave_mii_bus) - of_node_put(priv->slave_mii_bus->dev.of_node); + if (priv->user_mii_bus) + of_node_put(priv->user_mii_bus->dev.of_node); /* leave the device reset asserted */ if (priv->reset) diff --git a/drivers/net/dsa/realtek/realtek.h b/drivers/net/dsa/realtek/realtek.h index 4fa7c6ba874a..790488e9c667 100644 --- a/drivers/net/dsa/realtek/realtek.h +++ b/drivers/net/dsa/realtek/realtek.h @@ -54,7 +54,7 @@ struct realtek_priv { struct regmap *map; struct regmap *map_nolock; struct mutex map_lock; - struct mii_bus *slave_mii_bus; + struct mii_bus *user_mii_bus; struct mii_bus *bus; int mdio_addr; diff --git a/drivers/net/dsa/realtek/rtl8365mb.c b/drivers/net/dsa/realtek/rtl8365mb.c index d171c18dd354..0875e4fc9f57 100644 --- a/drivers/net/dsa/realtek/rtl8365mb.c +++ b/drivers/net/dsa/realtek/rtl8365mb.c @@ -1144,7 +1144,7 @@ static int rtl8365mb_port_change_mtu(struct dsa_switch *ds, int port, int frame_size; /* When a new MTU is set, DSA always sets the CPU port's MTU to the - * largest MTU of the slave ports. Because the switch only has a global + * largest MTU of the user ports. Because the switch only has a global * RX length register, only allowing CPU port here is enough. */ if (!dsa_is_cpu_port(ds, port)) diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 1a367e64bc3b..74cee39d73df 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -2688,7 +2688,7 @@ static int sja1105_mgmt_xmit(struct dsa_switch *ds, int port, int slot, } /* Transfer skb to the host port. */ - dsa_enqueue_skb(skb, dsa_to_port(ds, port)->slave); + dsa_enqueue_skb(skb, dsa_to_port(ds, port)->user); /* Wait until the switch has processed the frame */ do { @@ -3081,7 +3081,7 @@ static int sja1105_port_bridge_flags(struct dsa_switch *ds, int port, * ref_clk pin. So port clocking needs to be initialized early, before * connecting to PHYs is attempted, otherwise they won't respond through MDIO. * Setting correct PHY link speed does not matter now. - * But dsa_slave_phy_setup is called later than sja1105_setup, so the PHY + * But dsa_user_phy_setup is called later than sja1105_setup, so the PHY * bindings are not yet parsed by DSA core. We need to parse early so that we * can populate the xMII mode parameters table. */ diff --git a/drivers/net/dsa/xrs700x/xrs700x.c b/drivers/net/dsa/xrs700x/xrs700x.c index 5b02e9e426fd..96db032b478f 100644 --- a/drivers/net/dsa/xrs700x/xrs700x.c +++ b/drivers/net/dsa/xrs700x/xrs700x.c @@ -554,7 +554,7 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, unsigned int val = XRS_HSR_CFG_HSR_PRP; struct dsa_port *partner = NULL, *dp; struct xrs700x *priv = ds->priv; - struct net_device *slave; + struct net_device *user; int ret, i, hsr_pair[2]; enum hsr_version ver; bool fwd = false; @@ -638,8 +638,8 @@ static int xrs700x_hsr_join(struct dsa_switch *ds, int port, hsr_pair[0] = port; hsr_pair[1] = partner->index; for (i = 0; i < ARRAY_SIZE(hsr_pair); i++) { - slave = dsa_to_port(ds, hsr_pair[i])->slave; - slave->features |= XRS7000X_SUPPORTED_HSR_FEATURES; + user = dsa_to_port(ds, hsr_pair[i])->user; + user->features |= XRS7000X_SUPPORTED_HSR_FEATURES; } return 0; @@ -650,7 +650,7 @@ static int xrs700x_hsr_leave(struct dsa_switch *ds, int port, { struct dsa_port *partner = NULL, *dp; struct xrs700x *priv = ds->priv; - struct net_device *slave; + struct net_device *user; int i, hsr_pair[2]; unsigned int val; @@ -692,8 +692,8 @@ static int xrs700x_hsr_leave(struct dsa_switch *ds, int port, hsr_pair[0] = port; hsr_pair[1] = partner->index; for (i = 0; i < ARRAY_SIZE(hsr_pair); i++) { - slave = dsa_to_port(ds, hsr_pair[i])->slave; - slave->features &= ~XRS7000X_SUPPORTED_HSR_FEATURES; + user = dsa_to_port(ds, hsr_pair[i])->user; + user->features &= ~XRS7000X_SUPPORTED_HSR_FEATURES; } return 0; diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c index ca66b747b7c5..d7c274af6d4d 100644 --- a/drivers/net/ethernet/adi/adin1110.c +++ b/drivers/net/ethernet/adi/adin1110.c @@ -294,7 +294,7 @@ static int adin1110_read_fifo(struct adin1110_port_priv *port_priv) { struct adin1110_priv *priv = port_priv->priv; u32 header_len = ADIN1110_RD_HEADER_LEN; - struct spi_transfer t; + struct spi_transfer t = {0}; u32 frame_size_no_fcs; struct sk_buff *rxb; u32 frame_size; diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 2a8643e167e1..0d2091e9eb28 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -152,11 +152,8 @@ void pdsc_qcq_free(struct pdsc *pdsc, struct pdsc_qcq *qcq) dma_free_coherent(dev, qcq->cq_size, qcq->cq_base, qcq->cq_base_pa); - if (qcq->cq.info) - vfree(qcq->cq.info); - - if (qcq->q.info) - vfree(qcq->q.info); + vfree(qcq->cq.info); + vfree(qcq->q.info); memset(qcq, 0, sizeof(*qcq)); } diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index d9607033bbf2..57f88c8b37de 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -124,6 +124,8 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, snprintf(buf, sizeof(buf), "fw.slot_%d", i); err = devlink_info_version_stored_put(req, buf, fw_list.fw_names[i].fw_version); + if (err) + return err; } err = devlink_info_version_running_put(req, @@ -154,33 +156,20 @@ int pdsc_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct netlink_ext_ack *extack) { struct pdsc *pdsc = devlink_health_reporter_priv(reporter); - int err; mutex_lock(&pdsc->config_lock); - if (test_bit(PDSC_S_FW_DEAD, &pdsc->state)) - err = devlink_fmsg_string_pair_put(fmsg, "Status", "dead"); + devlink_fmsg_string_pair_put(fmsg, "Status", "dead"); else if (!pdsc_is_fw_good(pdsc)) - err = devlink_fmsg_string_pair_put(fmsg, "Status", "unhealthy"); + devlink_fmsg_string_pair_put(fmsg, "Status", "unhealthy"); else - err = devlink_fmsg_string_pair_put(fmsg, "Status", "healthy"); - + devlink_fmsg_string_pair_put(fmsg, "Status", "healthy"); mutex_unlock(&pdsc->config_lock); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "State", - pdsc->fw_status & - ~PDS_CORE_FW_STS_F_GENERATION); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "Generation", - pdsc->fw_generation >> 4); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "State", + pdsc->fw_status & ~PDS_CORE_FW_STS_F_GENERATION); + devlink_fmsg_u32_pair_put(fmsg, "Generation", pdsc->fw_generation >> 4); + devlink_fmsg_u32_pair_put(fmsg, "Recoveries", pdsc->fw_recoveries); - return devlink_fmsg_u32_pair_put(fmsg, "Recoveries", - pdsc->fw_recoveries); + return 0; } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 56f2b3c229af..44900026d11b 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -2155,7 +2155,7 @@ static void xgene_enet_shutdown(struct platform_device *pdev) static struct platform_driver xgene_enet_driver = { .driver = { .name = "xgene-enet", - .of_match_table = of_match_ptr(xgene_enet_of_match), + .of_match_table = xgene_enet_of_match, .acpi_match_table = ACPI_PTR(xgene_enet_acpi_match), }, .probe = xgene_enet_probe, diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index ab096795e805..c9faa8540859 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -2430,7 +2430,7 @@ static int bcm_sysport_netdevice_event(struct notifier_block *nb, if (dev->netdev_ops != &bcm_sysport_netdev_ops) return NOTIFY_DONE; - if (!dsa_slave_dev_check(info->upper_dev)) + if (!dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; if (info->linking) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 16eb7a7af970..d0359b569afe 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2129,6 +2129,48 @@ static u16 bnxt_agg_ring_id_to_grp_idx(struct bnxt *bp, u16 ring_id) return INVALID_HW_RING_ID; } +static u16 bnxt_get_force_speed(struct bnxt_link_info *link_info) +{ + if (link_info->req_signal_mode == BNXT_SIG_MODE_PAM4) + return link_info->force_pam4_link_speed; + return link_info->force_link_speed; +} + +static void bnxt_set_force_speed(struct bnxt_link_info *link_info) +{ + link_info->req_link_speed = link_info->force_link_speed; + link_info->req_signal_mode = BNXT_SIG_MODE_NRZ; + if (link_info->force_pam4_link_speed) { + link_info->req_link_speed = link_info->force_pam4_link_speed; + link_info->req_signal_mode = BNXT_SIG_MODE_PAM4; + } +} + +static void bnxt_set_auto_speed(struct bnxt_link_info *link_info) +{ + link_info->advertising = link_info->auto_link_speeds; + link_info->advertising_pam4 = link_info->auto_pam4_link_speeds; +} + +static bool bnxt_force_speed_updated(struct bnxt_link_info *link_info) +{ + if (link_info->req_signal_mode == BNXT_SIG_MODE_NRZ && + link_info->req_link_speed != link_info->force_link_speed) + return true; + if (link_info->req_signal_mode == BNXT_SIG_MODE_PAM4 && + link_info->req_link_speed != link_info->force_pam4_link_speed) + return true; + return false; +} + +static bool bnxt_auto_speed_updated(struct bnxt_link_info *link_info) +{ + if (link_info->advertising != link_info->auto_link_speeds || + link_info->advertising_pam4 != link_info->auto_pam4_link_speeds) + return true; + return false; +} + #define BNXT_EVENT_THERMAL_CURRENT_TEMP(data2) \ ((data2) & \ ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_MASK) @@ -2147,7 +2189,8 @@ static u16 bnxt_agg_ring_id_to_grp_idx(struct bnxt *bp, u16 ring_id) ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR) ==\ ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING) -static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) +/* Return true if the workqueue has to be scheduled */ +static bool bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) { u32 err_type = BNXT_EVENT_ERROR_REPORT_TYPE(data1); @@ -2165,6 +2208,7 @@ static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) case ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD: { u32 type = EVENT_DATA1_THERMAL_THRESHOLD_TYPE(data1); char *threshold_type; + bool notify = false; char *dir_str; switch (type) { @@ -2182,25 +2226,32 @@ static void bnxt_event_error_report(struct bnxt *bp, u32 data1, u32 data2) break; default: netdev_err(bp->dev, "Unknown Thermal threshold type event\n"); - return; + return false; } - if (EVENT_DATA1_THERMAL_THRESHOLD_DIR_INCREASING(data1)) + if (EVENT_DATA1_THERMAL_THRESHOLD_DIR_INCREASING(data1)) { dir_str = "above"; - else + notify = true; + } else { dir_str = "below"; + } netdev_warn(bp->dev, "Chip temperature has gone %s the %s thermal threshold!\n", dir_str, threshold_type); netdev_warn(bp->dev, "Temperature (In Celsius), Current: %lu, threshold: %lu\n", BNXT_EVENT_THERMAL_CURRENT_TEMP(data2), BNXT_EVENT_THERMAL_THRESHOLD_TEMP(data2)); - bnxt_hwmon_notify_event(bp, type); - break; + if (notify) { + bp->thermal_threshold_type = type; + set_bit(BNXT_THERMAL_THRESHOLD_SP_EVENT, &bp->sp_event); + return true; + } + return false; } default: netdev_err(bp->dev, "FW reported unknown error type %u\n", err_type); break; } + return false; } #define BNXT_GET_EVENT_PORT(data) \ @@ -2246,7 +2297,7 @@ static int bnxt_async_event_process(struct bnxt *bp, /* print unsupported speed warning in forced speed mode only */ if (!(link_info->autoneg & BNXT_AUTONEG_SPEED) && (data1 & 0x20000)) { - u16 fw_speed = link_info->force_link_speed; + u16 fw_speed = bnxt_get_force_speed(link_info); u32 speed = bnxt_fw_to_ethtool_speed(fw_speed); if (speed != SPEED_UNKNOWN) @@ -2401,7 +2452,8 @@ static int bnxt_async_event_process(struct bnxt *bp, goto async_event_process_exit; } case ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT: { - bnxt_event_error_report(bp, data1, data2); + if (bnxt_event_error_report(bp, data1, data2)) + break; goto async_event_process_exit; } case ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE: { @@ -3250,8 +3302,6 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, pp.dma_dir = bp->rx_dir; pp.max_len = PAGE_SIZE; pp.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; - if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) - pp.flags |= PP_FLAG_PAGE_FRAG; rxr->page_pool = page_pool_create(&pp); if (IS_ERR(rxr->page_pool)) { @@ -9679,13 +9729,31 @@ static bool bnxt_support_dropped(u16 advertising, u16 supported) return ((supported | diff) != supported); } +static bool bnxt_support_speed_dropped(struct bnxt_link_info *link_info) +{ + /* Check if any advertised speeds are no longer supported. The caller + * holds the link_lock mutex, so we can modify link_info settings. + */ + if (bnxt_support_dropped(link_info->advertising, + link_info->support_auto_speeds)) { + link_info->advertising = link_info->support_auto_speeds; + return true; + } + if (bnxt_support_dropped(link_info->advertising_pam4, + link_info->support_pam4_auto_speeds)) { + link_info->advertising_pam4 = link_info->support_pam4_auto_speeds; + return true; + } + return false; +} + int bnxt_update_link(struct bnxt *bp, bool chng_link_state) { struct bnxt_link_info *link_info = &bp->link_info; struct hwrm_port_phy_qcfg_output *resp; struct hwrm_port_phy_qcfg_input *req; u8 link_state = link_info->link_state; - bool support_changed = false; + bool support_changed; int rc; rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_QCFG); @@ -9799,19 +9867,7 @@ int bnxt_update_link(struct bnxt *bp, bool chng_link_state) if (!BNXT_PHY_CFG_ABLE(bp)) return 0; - /* Check if any advertised speeds are no longer supported. The caller - * holds the link_lock mutex, so we can modify link_info settings. - */ - if (bnxt_support_dropped(link_info->advertising, - link_info->support_auto_speeds)) { - link_info->advertising = link_info->support_auto_speeds; - support_changed = true; - } - if (bnxt_support_dropped(link_info->advertising_pam4, - link_info->support_pam4_auto_speeds)) { - link_info->advertising_pam4 = link_info->support_pam4_auto_speeds; - support_changed = true; - } + support_changed = bnxt_support_speed_dropped(link_info); if (support_changed && (link_info->autoneg & BNXT_AUTONEG_SPEED)) bnxt_hwrm_set_link_setting(bp, true, false); return 0; @@ -10352,19 +10408,14 @@ static int bnxt_update_phy_setting(struct bnxt *bp) if (!(link_info->autoneg & BNXT_AUTONEG_SPEED)) { if (BNXT_AUTO_MODE(link_info->auto_mode)) update_link = true; - if (link_info->req_signal_mode == BNXT_SIG_MODE_NRZ && - link_info->req_link_speed != link_info->force_link_speed) - update_link = true; - else if (link_info->req_signal_mode == BNXT_SIG_MODE_PAM4 && - link_info->req_link_speed != link_info->force_pam4_link_speed) + if (bnxt_force_speed_updated(link_info)) update_link = true; if (link_info->req_duplex != link_info->duplex_setting) update_link = true; } else { if (link_info->auto_mode == BNXT_LINK_AUTO_NONE) update_link = true; - if (link_info->advertising != link_info->auto_link_speeds || - link_info->advertising_pam4 != link_info->auto_pam4_link_speeds) + if (bnxt_auto_speed_updated(link_info)) update_link = true; } @@ -11982,16 +12033,9 @@ static void bnxt_init_ethtool_link_settings(struct bnxt *bp) } else { link_info->autoneg |= BNXT_AUTONEG_FLOW_CTRL; } - link_info->advertising = link_info->auto_link_speeds; - link_info->advertising_pam4 = link_info->auto_pam4_link_speeds; + bnxt_set_auto_speed(link_info); } else { - link_info->req_link_speed = link_info->force_link_speed; - link_info->req_signal_mode = BNXT_SIG_MODE_NRZ; - if (link_info->force_pam4_link_speed) { - link_info->req_link_speed = - link_info->force_pam4_link_speed; - link_info->req_signal_mode = BNXT_SIG_MODE_PAM4; - } + bnxt_set_force_speed(link_info); link_info->req_duplex = link_info->duplex_setting; } if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) @@ -12085,6 +12129,9 @@ static void bnxt_sp_task(struct work_struct *work) if (test_and_clear_bit(BNXT_FW_ECHO_REQUEST_SP_EVENT, &bp->sp_event)) bnxt_fw_echo_reply(bp); + if (test_and_clear_bit(BNXT_THERMAL_THRESHOLD_SP_EVENT, &bp->sp_event)) + bnxt_hwmon_notify_event(bp); + /* These functions below will clear BNXT_STATE_IN_SP_TASK. They * must be the last functions to be called before exiting. */ diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 9ce0193798d4..e702dbc3e6b1 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -1295,6 +1295,7 @@ struct bnxt_link_info { u8 req_signal_mode; #define BNXT_SIG_MODE_NRZ PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ #define BNXT_SIG_MODE_PAM4 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4 +#define BNXT_SIG_MODE_MAX (PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST + 1) u8 req_duplex; u8 req_flow_ctrl; u16 req_link_speed; @@ -2094,6 +2095,7 @@ struct bnxt { #define BNXT_FW_RESET_NOTIFY_SP_EVENT 18 #define BNXT_FW_EXCEPTION_SP_EVENT 19 #define BNXT_LINK_CFG_CHANGE_SP_EVENT 21 +#define BNXT_THERMAL_THRESHOLD_SP_EVENT 22 #define BNXT_FW_ECHO_REQUEST_SP_EVENT 23 struct delayed_work fw_reset_task; @@ -2196,6 +2198,7 @@ struct bnxt { u8 fatal_thresh_temp; u8 shutdown_thresh_temp; #endif + u32 thermal_threshold_type; enum board_idx board_idx; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index c3beadc1205b..f302dac56599 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -104,20 +104,21 @@ static int bnxt_fw_diagnose(struct devlink_health_reporter *reporter, struct bnxt *bp = devlink_health_reporter_priv(reporter); struct bnxt_fw_health *h = bp->fw_health; u32 fw_status, fw_resets; - int rc; - if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) - return devlink_fmsg_string_pair_put(fmsg, "Status", "recovering"); + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + devlink_fmsg_string_pair_put(fmsg, "Status", "recovering"); + return 0; + } - if (!h->status_reliable) - return devlink_fmsg_string_pair_put(fmsg, "Status", "unknown"); + if (!h->status_reliable) { + devlink_fmsg_string_pair_put(fmsg, "Status", "unknown"); + return 0; + } mutex_lock(&h->lock); fw_status = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); if (BNXT_FW_IS_BOOTING(fw_status)) { - rc = devlink_fmsg_string_pair_put(fmsg, "Status", "initializing"); - if (rc) - goto unlock; + devlink_fmsg_string_pair_put(fmsg, "Status", "initializing"); } else if (h->severity || fw_status != BNXT_FW_STATUS_HEALTHY) { if (!h->severity) { h->severity = SEVERITY_FATAL; @@ -126,58 +127,35 @@ static int bnxt_fw_diagnose(struct devlink_health_reporter *reporter, devlink_health_report(h->fw_reporter, "FW error diagnosed", h); } - rc = devlink_fmsg_string_pair_put(fmsg, "Status", "error"); - if (rc) - goto unlock; - rc = devlink_fmsg_u32_pair_put(fmsg, "Syndrome", fw_status); - if (rc) - goto unlock; + devlink_fmsg_string_pair_put(fmsg, "Status", "error"); + devlink_fmsg_u32_pair_put(fmsg, "Syndrome", fw_status); } else { - rc = devlink_fmsg_string_pair_put(fmsg, "Status", "healthy"); - if (rc) - goto unlock; + devlink_fmsg_string_pair_put(fmsg, "Status", "healthy"); } - rc = devlink_fmsg_string_pair_put(fmsg, "Severity", - bnxt_health_severity_str(h->severity)); - if (rc) - goto unlock; + devlink_fmsg_string_pair_put(fmsg, "Severity", + bnxt_health_severity_str(h->severity)); if (h->severity) { - rc = devlink_fmsg_string_pair_put(fmsg, "Remedy", - bnxt_health_remedy_str(h->remedy)); - if (rc) - goto unlock; - if (h->remedy == REMEDY_DEVLINK_RECOVER) { - rc = devlink_fmsg_string_pair_put(fmsg, "Impact", - "traffic+ntuple_cfg"); - if (rc) - goto unlock; - } + devlink_fmsg_string_pair_put(fmsg, "Remedy", + bnxt_health_remedy_str(h->remedy)); + if (h->remedy == REMEDY_DEVLINK_RECOVER) + devlink_fmsg_string_pair_put(fmsg, "Impact", + "traffic+ntuple_cfg"); } -unlock: mutex_unlock(&h->lock); - if (rc || !h->resets_reliable) - return rc; + if (!h->resets_reliable) + return 0; fw_resets = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); - rc = devlink_fmsg_u32_pair_put(fmsg, "Resets", fw_resets); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "Arrests", h->arrests); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "Survivals", h->survivals); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "Discoveries", h->discoveries); - if (rc) - return rc; - rc = devlink_fmsg_u32_pair_put(fmsg, "Fatalities", h->fatalities); - if (rc) - return rc; - return devlink_fmsg_u32_pair_put(fmsg, "Diagnoses", h->diagnoses); + devlink_fmsg_u32_pair_put(fmsg, "Resets", fw_resets); + devlink_fmsg_u32_pair_put(fmsg, "Arrests", h->arrests); + devlink_fmsg_u32_pair_put(fmsg, "Survivals", h->survivals); + devlink_fmsg_u32_pair_put(fmsg, "Discoveries", h->discoveries); + devlink_fmsg_u32_pair_put(fmsg, "Fatalities", h->fatalities); + devlink_fmsg_u32_pair_put(fmsg, "Diagnoses", h->diagnoses); + return 0; } static int bnxt_fw_dump(struct devlink_health_reporter *reporter, @@ -203,19 +181,12 @@ static int bnxt_fw_dump(struct devlink_health_reporter *reporter, rc = bnxt_get_coredump(bp, BNXT_DUMP_LIVE, data, &dump_len); if (!rc) { - rc = devlink_fmsg_pair_nest_start(fmsg, "core"); - if (rc) - goto exit; - rc = devlink_fmsg_binary_pair_put(fmsg, "data", data, dump_len); - if (rc) - goto exit; - rc = devlink_fmsg_u32_pair_put(fmsg, "size", dump_len); - if (rc) - goto exit; - rc = devlink_fmsg_pair_nest_end(fmsg); + devlink_fmsg_pair_nest_start(fmsg, "core"); + devlink_fmsg_binary_pair_put(fmsg, "data", data, dump_len); + devlink_fmsg_u32_pair_put(fmsg, "size", dump_len); + devlink_fmsg_pair_nest_end(fmsg); } -exit: vfree(data); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 547247d98eba..f3f384773ac0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -8,6 +8,7 @@ * the Free Software Foundation. */ +#include <linux/bitops.h> #include <linux/ctype.h> #include <linux/stringify.h> #include <linux/ethtool.h> @@ -534,6 +535,7 @@ static int bnxt_get_num_ring_stats(struct bnxt *bp) static int bnxt_get_num_stats(struct bnxt *bp) { int num_stats = bnxt_get_num_ring_stats(bp); + int len; num_stats += BNXT_NUM_RING_ERR_STATS; @@ -541,8 +543,12 @@ static int bnxt_get_num_stats(struct bnxt *bp) num_stats += BNXT_NUM_PORT_STATS; if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { - num_stats += bp->fw_rx_stats_ext_size + - bp->fw_tx_stats_ext_size; + len = min_t(int, bp->fw_rx_stats_ext_size, + ARRAY_SIZE(bnxt_port_stats_ext_arr)); + num_stats += len; + len = min_t(int, bp->fw_tx_stats_ext_size, + ARRAY_SIZE(bnxt_tx_port_stats_ext_arr)); + num_stats += len; if (bp->pri2cos_valid) num_stats += BNXT_NUM_STATS_PRI; } @@ -652,12 +658,17 @@ skip_ring_stats: if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { u64 *rx_port_stats_ext = bp->rx_port_stats_ext.sw_stats; u64 *tx_port_stats_ext = bp->tx_port_stats_ext.sw_stats; + u32 len; - for (i = 0; i < bp->fw_rx_stats_ext_size; i++, j++) { + len = min_t(u32, bp->fw_rx_stats_ext_size, + ARRAY_SIZE(bnxt_port_stats_ext_arr)); + for (i = 0; i < len; i++, j++) { buf[j] = *(rx_port_stats_ext + bnxt_port_stats_ext_arr[i].offset); } - for (i = 0; i < bp->fw_tx_stats_ext_size; i++, j++) { + len = min_t(u32, bp->fw_tx_stats_ext_size, + ARRAY_SIZE(bnxt_tx_port_stats_ext_arr)); + for (i = 0; i < len; i++, j++) { buf[j] = *(tx_port_stats_ext + bnxt_tx_port_stats_ext_arr[i].offset); } @@ -756,11 +767,17 @@ skip_tpa_stats: } } if (bp->flags & BNXT_FLAG_PORT_STATS_EXT) { - for (i = 0; i < bp->fw_rx_stats_ext_size; i++) { + u32 len; + + len = min_t(u32, bp->fw_rx_stats_ext_size, + ARRAY_SIZE(bnxt_port_stats_ext_arr)); + for (i = 0; i < len; i++) { strcpy(buf, bnxt_port_stats_ext_arr[i].string); buf += ETH_GSTRING_LEN; } - for (i = 0; i < bp->fw_tx_stats_ext_size; i++) { + len = min_t(u32, bp->fw_tx_stats_ext_size, + ARRAY_SIZE(bnxt_tx_port_stats_ext_arr)); + for (i = 0; i < len; i++) { strcpy(buf, bnxt_tx_port_stats_ext_arr[i].string); buf += ETH_GSTRING_LEN; @@ -1506,94 +1523,388 @@ u32 _bnxt_fw_to_ethtool_adv_spds(u16 fw_speeds, u8 fw_pause) return speed_mask; } -#define BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, name)\ -{ \ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_100MB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 100baseT_Full); \ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_1GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 1000baseT_Full); \ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_10GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 10000baseT_Full); \ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_25GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 25000baseCR_Full); \ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_40GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 40000baseCR4_Full);\ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_50GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 50000baseCR2_Full);\ - if ((fw_speeds) & BNXT_LINK_SPEED_MSK_100GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 100000baseCR4_Full);\ - if ((fw_pause) & BNXT_LINK_PAUSE_RX) { \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - Pause); \ - if (!((fw_pause) & BNXT_LINK_PAUSE_TX)) \ - ethtool_link_ksettings_add_link_mode( \ - lk_ksettings, name, Asym_Pause);\ - } else if ((fw_pause) & BNXT_LINK_PAUSE_TX) { \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - Asym_Pause); \ - } \ +enum bnxt_media_type { + BNXT_MEDIA_UNKNOWN = 0, + BNXT_MEDIA_TP, + BNXT_MEDIA_CR, + BNXT_MEDIA_SR, + BNXT_MEDIA_LR_ER_FR, + BNXT_MEDIA_KR, + BNXT_MEDIA_KX, + BNXT_MEDIA_X, + __BNXT_MEDIA_END, +}; + +static const enum bnxt_media_type bnxt_phy_types[] = { + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASECR] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR4] = BNXT_MEDIA_KR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASELR] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASESR] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR2] = BNXT_MEDIA_KR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKX] = BNXT_MEDIA_KX, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR] = BNXT_MEDIA_KR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASET] = BNXT_MEDIA_TP, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE] = BNXT_MEDIA_TP, + [PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_L] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_S] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_N] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASESR] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR4] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR4] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR4] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER4] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR10] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASECR4] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASESR4] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET] = BNXT_MEDIA_TP, + [PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX] = BNXT_MEDIA_X, + [PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX] = BNXT_MEDIA_X, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR4] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2] = BNXT_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2] = BNXT_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2] = BNXT_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2] = BNXT_MEDIA_LR_ER_FR, +}; + +static enum bnxt_media_type +bnxt_get_media(struct bnxt_link_info *link_info) +{ + switch (link_info->media_type) { + case PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP: + return BNXT_MEDIA_TP; + case PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC: + return BNXT_MEDIA_CR; + default: + if (link_info->phy_type < ARRAY_SIZE(bnxt_phy_types)) + return bnxt_phy_types[link_info->phy_type]; + return BNXT_MEDIA_UNKNOWN; + } +} + +enum bnxt_link_speed_indices { + BNXT_LINK_SPEED_UNKNOWN = 0, + BNXT_LINK_SPEED_100MB_IDX, + BNXT_LINK_SPEED_1GB_IDX, + BNXT_LINK_SPEED_10GB_IDX, + BNXT_LINK_SPEED_25GB_IDX, + BNXT_LINK_SPEED_40GB_IDX, + BNXT_LINK_SPEED_50GB_IDX, + BNXT_LINK_SPEED_100GB_IDX, + BNXT_LINK_SPEED_200GB_IDX, + __BNXT_LINK_SPEED_END +}; + +static enum bnxt_link_speed_indices bnxt_fw_speed_idx(u16 speed) +{ + switch (speed) { + case BNXT_LINK_SPEED_100MB: return BNXT_LINK_SPEED_100MB_IDX; + case BNXT_LINK_SPEED_1GB: return BNXT_LINK_SPEED_1GB_IDX; + case BNXT_LINK_SPEED_10GB: return BNXT_LINK_SPEED_10GB_IDX; + case BNXT_LINK_SPEED_25GB: return BNXT_LINK_SPEED_25GB_IDX; + case BNXT_LINK_SPEED_40GB: return BNXT_LINK_SPEED_40GB_IDX; + case BNXT_LINK_SPEED_50GB: return BNXT_LINK_SPEED_50GB_IDX; + case BNXT_LINK_SPEED_100GB: return BNXT_LINK_SPEED_100GB_IDX; + case BNXT_LINK_SPEED_200GB: return BNXT_LINK_SPEED_200GB_IDX; + default: return BNXT_LINK_SPEED_UNKNOWN; + } +} + +static const enum ethtool_link_mode_bit_indices +bnxt_link_modes[__BNXT_LINK_SPEED_END][BNXT_SIG_MODE_MAX][__BNXT_MEDIA_END] = { + [BNXT_LINK_SPEED_100MB_IDX] = { + { + [BNXT_MEDIA_TP] = ETHTOOL_LINK_MODE_100baseT_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_1GB_IDX] = { + { + [BNXT_MEDIA_TP] = ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + /* historically baseT, but DAC is more correctly baseX */ + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + [BNXT_MEDIA_KX] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + [BNXT_MEDIA_X] = ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_10GB_IDX] = { + { + [BNXT_MEDIA_TP] = ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + [BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + [BNXT_MEDIA_KX] = ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_25GB_IDX] = { + { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_40GB_IDX] = { + { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + [BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_50GB_IDX] = { + [BNXT_SIG_MODE_NRZ] = { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + }, + [BNXT_SIG_MODE_PAM4] = { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + [BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_100GB_IDX] = { + [BNXT_SIG_MODE_NRZ] = { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + [BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + }, + [BNXT_SIG_MODE_PAM4] = { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + [BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, + }, + }, + [BNXT_LINK_SPEED_200GB_IDX] = { + [BNXT_SIG_MODE_PAM4] = { + [BNXT_MEDIA_CR] = ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, + [BNXT_MEDIA_SR] = ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, + [BNXT_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, + [BNXT_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, + }, + }, +}; + +#define BNXT_LINK_MODE_UNKNOWN -1 + +static enum ethtool_link_mode_bit_indices +bnxt_get_link_mode(struct bnxt_link_info *link_info) +{ + enum ethtool_link_mode_bit_indices link_mode; + enum bnxt_link_speed_indices speed; + enum bnxt_media_type media; + u8 sig_mode; + + if (link_info->phy_link_status != BNXT_LINK_LINK) + return BNXT_LINK_MODE_UNKNOWN; + + media = bnxt_get_media(link_info); + if (BNXT_AUTO_MODE(link_info->auto_mode)) { + speed = bnxt_fw_speed_idx(link_info->link_speed); + sig_mode = link_info->active_fec_sig_mode & + PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK; + } else { + speed = bnxt_fw_speed_idx(link_info->req_link_speed); + sig_mode = link_info->req_signal_mode; + } + if (sig_mode >= BNXT_SIG_MODE_MAX) + return BNXT_LINK_MODE_UNKNOWN; + + /* Note ETHTOOL_LINK_MODE_10baseT_Half_BIT == 0 is a legal Linux + * link mode, but since no such devices exist, the zeroes in the + * map can be conveniently used to represent unknown link modes. + */ + link_mode = bnxt_link_modes[speed][sig_mode][media]; + if (!link_mode) + return BNXT_LINK_MODE_UNKNOWN; + + switch (link_mode) { + case ETHTOOL_LINK_MODE_100baseT_Full_BIT: + if (~link_info->duplex & BNXT_LINK_DUPLEX_FULL) + link_mode = ETHTOOL_LINK_MODE_100baseT_Half_BIT; + break; + case ETHTOOL_LINK_MODE_1000baseT_Full_BIT: + if (~link_info->duplex & BNXT_LINK_DUPLEX_FULL) + link_mode = ETHTOOL_LINK_MODE_1000baseT_Half_BIT; + break; + default: + break; + } + + return link_mode; +} + +static void bnxt_get_ethtool_modes(struct bnxt_link_info *link_info, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnxt *bp = container_of(link_info, struct bnxt, link_info); + + if (!(bp->phy_flags & BNXT_PHY_FL_NO_PAUSE)) { + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + lk_ksettings->link_modes.supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + lk_ksettings->link_modes.supported); + } + + if (link_info->support_auto_speeds || link_info->support_pam4_auto_speeds) + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lk_ksettings->link_modes.supported); + + if (~link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) + return; + + if (link_info->auto_pause_setting & BNXT_LINK_PAUSE_RX) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + lk_ksettings->link_modes.advertising); + if (hweight8(link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH) == 1) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + lk_ksettings->link_modes.advertising); + if (link_info->lp_pause & BNXT_LINK_PAUSE_RX) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + lk_ksettings->link_modes.lp_advertising); + if (hweight8(link_info->lp_pause & BNXT_LINK_PAUSE_BOTH) == 1) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + lk_ksettings->link_modes.lp_advertising); } -#define BNXT_ETHTOOL_TO_FW_SPDS(fw_speeds, lk_ksettings, name) \ -{ \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 100baseT_Full) || \ - ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 100baseT_Half)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_100MB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 1000baseT_Full) || \ - ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 1000baseT_Half)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_1GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 10000baseT_Full)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_10GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 25000baseCR_Full)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_25GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 40000baseCR4_Full)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_40GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 50000baseCR2_Full)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_50GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 100000baseCR4_Full)) \ - (fw_speeds) |= BNXT_LINK_SPEED_MSK_100GB; \ +static const u16 bnxt_nrz_speed_masks[] = { + [BNXT_LINK_SPEED_100MB_IDX] = BNXT_LINK_SPEED_MSK_100MB, + [BNXT_LINK_SPEED_1GB_IDX] = BNXT_LINK_SPEED_MSK_1GB, + [BNXT_LINK_SPEED_10GB_IDX] = BNXT_LINK_SPEED_MSK_10GB, + [BNXT_LINK_SPEED_25GB_IDX] = BNXT_LINK_SPEED_MSK_25GB, + [BNXT_LINK_SPEED_40GB_IDX] = BNXT_LINK_SPEED_MSK_40GB, + [BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_SPEED_MSK_50GB, + [BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_SPEED_MSK_100GB, + [__BNXT_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */ +}; + +static const u16 bnxt_pam4_speed_masks[] = { + [BNXT_LINK_SPEED_50GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_50GB, + [BNXT_LINK_SPEED_100GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_100GB, + [BNXT_LINK_SPEED_200GB_IDX] = BNXT_LINK_PAM4_SPEED_MSK_200GB, +}; + +static enum bnxt_link_speed_indices +bnxt_encoding_speed_idx(u8 sig_mode, u16 speed_msk) +{ + const u16 *speeds; + int idx, len; + + switch (sig_mode) { + case BNXT_SIG_MODE_NRZ: + speeds = bnxt_nrz_speed_masks; + len = ARRAY_SIZE(bnxt_nrz_speed_masks); + break; + case BNXT_SIG_MODE_PAM4: + speeds = bnxt_pam4_speed_masks; + len = ARRAY_SIZE(bnxt_pam4_speed_masks); + break; + default: + return BNXT_LINK_SPEED_UNKNOWN; + } + + for (idx = 0; idx < len; idx++) { + if (speeds[idx] == speed_msk) + return idx; + } + + return BNXT_LINK_SPEED_UNKNOWN; } -#define BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, name) \ -{ \ - if ((fw_speeds) & BNXT_LINK_PAM4_SPEED_MSK_50GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 50000baseCR_Full); \ - if ((fw_speeds) & BNXT_LINK_PAM4_SPEED_MSK_100GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 100000baseCR2_Full);\ - if ((fw_speeds) & BNXT_LINK_PAM4_SPEED_MSK_200GB) \ - ethtool_link_ksettings_add_link_mode(lk_ksettings, name,\ - 200000baseCR4_Full);\ +#define BNXT_FW_SPEED_MSK_BITS 16 + +static void +__bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media, + u8 sig_mode, unsigned long *et_mask) +{ + enum ethtool_link_mode_bit_indices link_mode; + enum bnxt_link_speed_indices speed; + u8 bit; + + for_each_set_bit(bit, &fw_mask, BNXT_FW_SPEED_MSK_BITS) { + speed = bnxt_encoding_speed_idx(sig_mode, 1 << bit); + if (!speed) + continue; + + link_mode = bnxt_link_modes[speed][sig_mode][media]; + if (!link_mode) + continue; + + linkmode_set_bit(link_mode, et_mask); + } } -#define BNXT_ETHTOOL_TO_FW_PAM4_SPDS(fw_speeds, lk_ksettings, name) \ -{ \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 50000baseCR_Full)) \ - (fw_speeds) |= BNXT_LINK_PAM4_SPEED_MSK_50GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 100000baseCR2_Full)) \ - (fw_speeds) |= BNXT_LINK_PAM4_SPEED_MSK_100GB; \ - if (ethtool_link_ksettings_test_link_mode(lk_ksettings, name, \ - 200000baseCR4_Full)) \ - (fw_speeds) |= BNXT_LINK_PAM4_SPEED_MSK_200GB; \ +static void +bnxt_get_ethtool_speeds(unsigned long fw_mask, enum bnxt_media_type media, + u8 sig_mode, unsigned long *et_mask) +{ + if (media) { + __bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, et_mask); + return; + } + + /* list speeds for all media if unknown */ + for (media = 1; media < __BNXT_MEDIA_END; media++) + __bnxt_get_ethtool_speeds(fw_mask, media, sig_mode, et_mask); +} + +static void bnxt_update_speed(u32 *delta, bool installed_media, u16 *speeds, + u16 speed_msk, const unsigned long *et_mask, + enum ethtool_link_mode_bit_indices mode) +{ + bool mode_desired = linkmode_test_bit(mode, et_mask); + + if (!mode) + return; + + /* enabled speeds for installed media should override */ + if (installed_media && mode_desired) { + *speeds |= speed_msk; + *delta |= speed_msk; + return; + } + + /* many to one mapping, only allow one change per fw_speed bit */ + if (!(*delta & speed_msk) && (mode_desired == !(*speeds & speed_msk))) { + *speeds ^= speed_msk; + *delta |= speed_msk; + } +} + +static void bnxt_set_ethtool_speeds(struct bnxt_link_info *link_info, + const unsigned long *et_mask) +{ + enum bnxt_media_type media = bnxt_get_media(link_info); + u32 delta_pam4 = 0; + u32 delta_nrz = 0; + int i, m; + + for (i = 1; i < __BNXT_LINK_SPEED_END; i++) { + /* accept any legal media from user */ + for (m = 1; m < __BNXT_MEDIA_END; m++) { + bnxt_update_speed(&delta_nrz, m == media, + &link_info->advertising, + bnxt_nrz_speed_masks[i], et_mask, + bnxt_link_modes[i][BNXT_SIG_MODE_NRZ][m]); + bnxt_update_speed(&delta_pam4, m == media, + &link_info->advertising_pam4, + bnxt_pam4_speed_masks[i], et_mask, + bnxt_link_modes[i][BNXT_SIG_MODE_PAM4][m]); + } + } } static void bnxt_fw_to_ethtool_advertised_fec(struct bnxt_link_info *link_info, @@ -1617,36 +1928,6 @@ static void bnxt_fw_to_ethtool_advertised_fec(struct bnxt_link_info *link_info, lk_ksettings->link_modes.advertising); } -static void bnxt_fw_to_ethtool_advertised_spds(struct bnxt_link_info *link_info, - struct ethtool_link_ksettings *lk_ksettings) -{ - u16 fw_speeds = link_info->advertising; - u8 fw_pause = 0; - - if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) - fw_pause = link_info->auto_pause_setting; - - BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, advertising); - fw_speeds = link_info->advertising_pam4; - BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, advertising); - bnxt_fw_to_ethtool_advertised_fec(link_info, lk_ksettings); -} - -static void bnxt_fw_to_ethtool_lp_adv(struct bnxt_link_info *link_info, - struct ethtool_link_ksettings *lk_ksettings) -{ - u16 fw_speeds = link_info->lp_auto_link_speeds; - u8 fw_pause = 0; - - if (link_info->autoneg & BNXT_AUTONEG_FLOW_CTRL) - fw_pause = link_info->lp_pause; - - BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, fw_pause, lk_ksettings, - lp_advertising); - fw_speeds = link_info->lp_auto_pam4_link_speeds; - BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, lp_advertising); -} - static void bnxt_fw_to_ethtool_support_fec(struct bnxt_link_info *link_info, struct ethtool_link_ksettings *lk_ksettings) { @@ -1668,30 +1949,6 @@ static void bnxt_fw_to_ethtool_support_fec(struct bnxt_link_info *link_info, lk_ksettings->link_modes.supported); } -static void bnxt_fw_to_ethtool_support_spds(struct bnxt_link_info *link_info, - struct ethtool_link_ksettings *lk_ksettings) -{ - struct bnxt *bp = container_of(link_info, struct bnxt, link_info); - u16 fw_speeds = link_info->support_speeds; - - BNXT_FW_TO_ETHTOOL_SPDS(fw_speeds, 0, lk_ksettings, supported); - fw_speeds = link_info->support_pam4_speeds; - BNXT_FW_TO_ETHTOOL_PAM4_SPDS(fw_speeds, lk_ksettings, supported); - - if (!(bp->phy_flags & BNXT_PHY_FL_NO_PAUSE)) { - ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, - Pause); - ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, - Asym_Pause); - } - - if (link_info->support_auto_speeds || - link_info->support_pam4_auto_speeds) - ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, - Autoneg); - bnxt_fw_to_ethtool_support_fec(link_info, lk_ksettings); -} - u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed) { switch (fw_link_speed) { @@ -1720,60 +1977,95 @@ u32 bnxt_fw_to_ethtool_speed(u16 fw_link_speed) } } +static void bnxt_get_default_speeds(struct ethtool_link_ksettings *lk_ksettings, + struct bnxt_link_info *link_info) +{ + struct ethtool_link_settings *base = &lk_ksettings->base; + + if (link_info->link_state == BNXT_LINK_STATE_UP) { + base->speed = bnxt_fw_to_ethtool_speed(link_info->link_speed); + base->duplex = DUPLEX_HALF; + if (link_info->duplex & BNXT_LINK_DUPLEX_FULL) + base->duplex = DUPLEX_FULL; + } else if (!link_info->autoneg) { + base->speed = bnxt_fw_to_ethtool_speed(link_info->req_link_speed); + base->duplex = DUPLEX_HALF; + if (link_info->req_duplex == BNXT_LINK_DUPLEX_FULL) + base->duplex = DUPLEX_FULL; + } +} + static int bnxt_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *lk_ksettings) { - struct bnxt *bp = netdev_priv(dev); - struct bnxt_link_info *link_info = &bp->link_info; struct ethtool_link_settings *base = &lk_ksettings->base; - u32 ethtool_speed; + enum ethtool_link_mode_bit_indices link_mode; + struct bnxt *bp = netdev_priv(dev); + struct bnxt_link_info *link_info; + enum bnxt_media_type media; + ethtool_link_ksettings_zero_link_mode(lk_ksettings, lp_advertising); + ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising); ethtool_link_ksettings_zero_link_mode(lk_ksettings, supported); + base->duplex = DUPLEX_UNKNOWN; + base->speed = SPEED_UNKNOWN; + link_info = &bp->link_info; + mutex_lock(&bp->link_lock); - bnxt_fw_to_ethtool_support_spds(link_info, lk_ksettings); + bnxt_get_ethtool_modes(link_info, lk_ksettings); + media = bnxt_get_media(link_info); + bnxt_get_ethtool_speeds(link_info->support_speeds, + media, BNXT_SIG_MODE_NRZ, + lk_ksettings->link_modes.supported); + bnxt_get_ethtool_speeds(link_info->support_pam4_speeds, + media, BNXT_SIG_MODE_PAM4, + lk_ksettings->link_modes.supported); + bnxt_fw_to_ethtool_support_fec(link_info, lk_ksettings); + link_mode = bnxt_get_link_mode(link_info); + if (link_mode != BNXT_LINK_MODE_UNKNOWN) + ethtool_params_from_link_mode(lk_ksettings, link_mode); + else + bnxt_get_default_speeds(lk_ksettings, link_info); - ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising); if (link_info->autoneg) { - bnxt_fw_to_ethtool_advertised_spds(link_info, lk_ksettings); - ethtool_link_ksettings_add_link_mode(lk_ksettings, - advertising, Autoneg); + bnxt_fw_to_ethtool_advertised_fec(link_info, lk_ksettings); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lk_ksettings->link_modes.advertising); base->autoneg = AUTONEG_ENABLE; - base->duplex = DUPLEX_UNKNOWN; + bnxt_get_ethtool_speeds(link_info->advertising, + media, BNXT_SIG_MODE_NRZ, + lk_ksettings->link_modes.advertising); + bnxt_get_ethtool_speeds(link_info->advertising_pam4, + media, BNXT_SIG_MODE_PAM4, + lk_ksettings->link_modes.advertising); if (link_info->phy_link_status == BNXT_LINK_LINK) { - bnxt_fw_to_ethtool_lp_adv(link_info, lk_ksettings); - if (link_info->duplex & BNXT_LINK_DUPLEX_FULL) - base->duplex = DUPLEX_FULL; - else - base->duplex = DUPLEX_HALF; + bnxt_get_ethtool_speeds(link_info->lp_auto_link_speeds, + media, BNXT_SIG_MODE_NRZ, + lk_ksettings->link_modes.lp_advertising); + bnxt_get_ethtool_speeds(link_info->lp_auto_pam4_link_speeds, + media, BNXT_SIG_MODE_PAM4, + lk_ksettings->link_modes.lp_advertising); } - ethtool_speed = bnxt_fw_to_ethtool_speed(link_info->link_speed); } else { base->autoneg = AUTONEG_DISABLE; - ethtool_speed = - bnxt_fw_to_ethtool_speed(link_info->req_link_speed); - base->duplex = DUPLEX_HALF; - if (link_info->req_duplex == BNXT_LINK_DUPLEX_FULL) - base->duplex = DUPLEX_FULL; } - base->speed = ethtool_speed; base->port = PORT_NONE; if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) { base->port = PORT_TP; - ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, - TP); - ethtool_link_ksettings_add_link_mode(lk_ksettings, advertising, - TP); + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, + lk_ksettings->link_modes.supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, + lk_ksettings->link_modes.advertising); } else { - ethtool_link_ksettings_add_link_mode(lk_ksettings, supported, - FIBRE); - ethtool_link_ksettings_add_link_mode(lk_ksettings, advertising, - FIBRE); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + lk_ksettings->link_modes.supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + lk_ksettings->link_modes.advertising); if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC) base->port = PORT_DA; - else if (link_info->media_type == - PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE) + else base->port = PORT_FIBRE; } base->phy_address = link_info->phy_addr; @@ -1782,13 +2074,15 @@ static int bnxt_get_link_ksettings(struct net_device *dev, return 0; } -static int bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed) +static int +bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes) { struct bnxt *bp = netdev_priv(dev); struct bnxt_link_info *link_info = &bp->link_info; u16 support_pam4_spds = link_info->support_pam4_speeds; u16 support_spds = link_info->support_speeds; u8 sig_mode = BNXT_SIG_MODE_NRZ; + u32 lanes_needed = 1; u16 fw_speed = 0; switch (ethtool_speed) { @@ -1809,37 +2103,46 @@ static int bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed) fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB; break; case SPEED_20000: - if (support_spds & BNXT_LINK_SPEED_MSK_20GB) + if (support_spds & BNXT_LINK_SPEED_MSK_20GB) { fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_20GB; + lanes_needed = 2; + } break; case SPEED_25000: if (support_spds & BNXT_LINK_SPEED_MSK_25GB) fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB; break; case SPEED_40000: - if (support_spds & BNXT_LINK_SPEED_MSK_40GB) + if (support_spds & BNXT_LINK_SPEED_MSK_40GB) { fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB; + lanes_needed = 4; + } break; case SPEED_50000: - if (support_spds & BNXT_LINK_SPEED_MSK_50GB) { + if ((support_spds & BNXT_LINK_SPEED_MSK_50GB) && lanes != 1) { fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB; + lanes_needed = 2; } else if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_50GB) { fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB; sig_mode = BNXT_SIG_MODE_PAM4; } break; case SPEED_100000: - if (support_spds & BNXT_LINK_SPEED_MSK_100GB) { + if ((support_spds & BNXT_LINK_SPEED_MSK_100GB) && + lanes != 2 && lanes != 1) { fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB; + lanes_needed = 4; } else if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_100GB) { fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB; sig_mode = BNXT_SIG_MODE_PAM4; + lanes_needed = 2; } break; case SPEED_200000: if (support_pam4_spds & BNXT_LINK_PAM4_SPEED_MSK_200GB) { fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB; sig_mode = BNXT_SIG_MODE_PAM4; + lanes_needed = 4; } break; } @@ -1849,6 +2152,11 @@ static int bnxt_force_link_speed(struct net_device *dev, u32 ethtool_speed) return -EINVAL; } + if (lanes && lanes != lanes_needed) { + netdev_err(dev, "unsupported number of lanes for speed\n"); + return -EINVAL; + } + if (link_info->req_link_speed == fw_speed && link_info->req_signal_mode == sig_mode && link_info->autoneg == 0) @@ -1893,7 +2201,7 @@ static int bnxt_set_link_ksettings(struct net_device *dev, struct bnxt_link_info *link_info = &bp->link_info; const struct ethtool_link_settings *base = &lk_ksettings->base; bool set_pause = false; - u32 speed; + u32 speed, lanes = 0; int rc = 0; if (!BNXT_PHY_CFG_ABLE(bp)) @@ -1901,12 +2209,8 @@ static int bnxt_set_link_ksettings(struct net_device *dev, mutex_lock(&bp->link_lock); if (base->autoneg == AUTONEG_ENABLE) { - link_info->advertising = 0; - link_info->advertising_pam4 = 0; - BNXT_ETHTOOL_TO_FW_SPDS(link_info->advertising, lk_ksettings, - advertising); - BNXT_ETHTOOL_TO_FW_PAM4_SPDS(link_info->advertising_pam4, - lk_ksettings, advertising); + bnxt_set_ethtool_speeds(link_info, + lk_ksettings->link_modes.advertising); link_info->autoneg |= BNXT_AUTONEG_SPEED; if (!link_info->advertising && !link_info->advertising_pam4) { link_info->advertising = link_info->support_auto_speeds; @@ -1934,7 +2238,8 @@ static int bnxt_set_link_ksettings(struct net_device *dev, goto set_setting_exit; } speed = base->speed; - rc = bnxt_force_link_speed(dev, speed); + lanes = lk_ksettings->lanes; + rc = bnxt_force_link_speed(dev, speed, lanes); if (rc) { if (rc == -EALREADY) rc = 0; @@ -4140,6 +4445,7 @@ void bnxt_ethtool_free(struct bnxt *bp) } const struct ethtool_ops bnxt_ethtool_ops = { + .cap_link_lanes_supported = 1, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS_IRQ | diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c index e48094043c3b..669d24ba0e87 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c @@ -18,14 +18,14 @@ #include "bnxt_hwrm.h" #include "bnxt_hwmon.h" -void bnxt_hwmon_notify_event(struct bnxt *bp, u32 type) +void bnxt_hwmon_notify_event(struct bnxt *bp) { u32 attr; if (!bp->hwmon_dev) return; - switch (type) { + switch (bp->thermal_threshold_type) { case ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_WARN: attr = hwmon_temp_max_alarm; break; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.h index 76d9f599ebc0..de54a562e06a 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.h @@ -11,11 +11,11 @@ #define BNXT_HWMON_H #ifdef CONFIG_BNXT_HWMON -void bnxt_hwmon_notify_event(struct bnxt *bp, u32 type); +void bnxt_hwmon_notify_event(struct bnxt *bp); void bnxt_hwmon_uninit(struct bnxt *bp); void bnxt_hwmon_init(struct bnxt *bp); #else -static inline void bnxt_hwmon_notify_event(struct bnxt *bp, u32 type) +static inline void bnxt_hwmon_notify_event(struct bnxt *bp) { } diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index dfe4e0102960..6268f96cb4aa 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -2501,14 +2501,6 @@ static int napi_rx_handler(struct napi_struct *napi, int budget) return work_done; } -/* - * Returns true if the device is already scheduled for polling. - */ -static inline int napi_is_scheduled(struct napi_struct *napi) -{ - return test_bit(NAPI_STATE_SCHED, &napi->state); -} - /** * process_pure_responses - process pure responses from a response queue * @adap: the adapter diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 8d719f82854a..76de55306c4d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -3816,6 +3816,8 @@ int t4_load_phy_fw(struct adapter *adap, int win, FW_PARAMS_PARAM_Z_V(FW_PARAMS_PARAM_DEV_PHYFW_DOWNLOAD)); ret = t4_set_params_timeout(adap, adap->mbox, adap->pf, 0, 1, ¶m, &val, 30000); + if (ret) + return ret; /* If we have version number support, then check to see that the new * firmware got loaded properly. diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 7750702900fa..6f6525983130 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -2259,7 +2259,7 @@ static void chtls_rx_ack(struct sock *sk, struct sk_buff *skb) if (tp->snd_una != snd_una) { tp->snd_una = snd_una; - tp->rcv_tstamp = tcp_time_stamp(tp); + tp->rcv_tstamp = tcp_jiffies32; if (tp->snd_una == tp->snd_nxt && !csk_flag_nochk(csk, CSK_TX_FAILOVER)) csk_reset_flag(csk, CSK_TX_WAIT_IDLE); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index 5fc64e47568a..d567e42e1760 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -911,7 +911,7 @@ static int csk_wait_memory(struct chtls_dev *cdev, struct sock *sk, long *timeo_p) { DEFINE_WAIT_FUNC(wait, woken_wake_function); - int err = 0; + int ret, err = 0; long current_timeo; long vm_wait = 0; bool noblock; @@ -942,10 +942,13 @@ static int csk_wait_memory(struct chtls_dev *cdev, set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, sk->sk_err || - (sk->sk_shutdown & SEND_SHUTDOWN) || - (csk_mem_free(cdev, sk) && !vm_wait), &wait); + ret = sk_wait_event(sk, ¤t_timeo, sk->sk_err || + (sk->sk_shutdown & SEND_SHUTDOWN) || + (csk_mem_free(cdev, sk) && !vm_wait), + &wait); sk->sk_write_pending--; + if (ret < 0) + goto do_error; if (vm_wait) { vm_wait -= current_timeo; @@ -1348,6 +1351,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int copied = 0; int target; long timeo; + int ret; buffers_freed = 0; @@ -1423,7 +1427,11 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (copied >= target) break; chtls_cleanup_rbuf(sk, copied); - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) { + copied = copied ? : ret; + goto unlock; + } continue; found_ok_skb: if (!skb->len) { @@ -1518,6 +1526,8 @@ skip_copy: if (buffers_freed) chtls_cleanup_rbuf(sk, copied); + +unlock: release_sock(sk); return copied; } @@ -1534,6 +1544,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg, int copied = 0; size_t avail; /* amount of available data in current skb */ long timeo; + int ret; lock_sock(sk); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); @@ -1585,7 +1596,12 @@ static int peekmsg(struct sock *sk, struct msghdr *msg, release_sock(sk); lock_sock(sk); } else { - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) { + /* here 'copied' is 0 due to previous checks */ + copied = ret; + break; + } } if (unlikely(peek_seq != tp->copied_seq)) { @@ -1656,6 +1672,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int copied = 0; long timeo; int target; /* Read at least this many bytes */ + int ret; buffers_freed = 0; @@ -1747,7 +1764,11 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (copied >= target) break; chtls_cleanup_rbuf(sk, copied); - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) { + copied = copied ? : ret; + goto unlock; + } continue; found_ok_skb: @@ -1816,6 +1837,7 @@ skip_copy: if (buffers_freed) chtls_cleanup_rbuf(sk, copied); +unlock: release_sock(sk); return copied; } diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h index 6e14c918e3fb..f188fba021a6 100644 --- a/drivers/net/ethernet/engleder/tsnep.h +++ b/drivers/net/ethernet/engleder/tsnep.h @@ -143,7 +143,7 @@ struct tsnep_rx { struct tsnep_queue { struct tsnep_adapter *adapter; - char name[IFNAMSIZ + 9]; + char name[IFNAMSIZ + 16]; struct tsnep_tx *tx; struct tsnep_rx *rx; diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index f16b6b3e21a6..df40c720e7b2 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -1830,14 +1830,14 @@ static int tsnep_request_irq(struct tsnep_queue *queue, bool first) dev = queue->adapter; } else { if (queue->tx && queue->rx) - sprintf(queue->name, "%s-txrx-%d", name, - queue->rx->queue_index); + snprintf(queue->name, sizeof(queue->name), "%s-txrx-%d", + name, queue->rx->queue_index); else if (queue->tx) - sprintf(queue->name, "%s-tx-%d", name, - queue->tx->queue_index); + snprintf(queue->name, sizeof(queue->name), "%s-tx-%d", + name, queue->tx->queue_index); else - sprintf(queue->name, "%s-rx-%d", name, - queue->rx->queue_index); + snprintf(queue->name, sizeof(queue->name), "%s-rx-%d", + name, queue->rx->queue_index); handler = tsnep_irq_txrx; dev = queue; } diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 5eb756871a96..032c15b541ff 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -187,65 +187,22 @@ static struct platform_device_id fec_devtype[] = { .name = DRIVER_NAME, .driver_data = 0, }, { - .name = "imx25-fec", - .driver_data = (kernel_ulong_t)&fec_imx25_info, - }, { - .name = "imx27-fec", - .driver_data = (kernel_ulong_t)&fec_imx27_info, - }, { - .name = "imx28-fec", - .driver_data = (kernel_ulong_t)&fec_imx28_info, - }, { - .name = "imx6q-fec", - .driver_data = (kernel_ulong_t)&fec_imx6q_info, - }, { - .name = "mvf600-fec", - .driver_data = (kernel_ulong_t)&fec_mvf600_info, - }, { - .name = "imx6sx-fec", - .driver_data = (kernel_ulong_t)&fec_imx6x_info, - }, { - .name = "imx6ul-fec", - .driver_data = (kernel_ulong_t)&fec_imx6ul_info, - }, { - .name = "imx8mq-fec", - .driver_data = (kernel_ulong_t)&fec_imx8mq_info, - }, { - .name = "imx8qm-fec", - .driver_data = (kernel_ulong_t)&fec_imx8qm_info, - }, { - .name = "s32v234-fec", - .driver_data = (kernel_ulong_t)&fec_s32v234_info, - }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(platform, fec_devtype); -enum imx_fec_type { - IMX25_FEC = 1, /* runs on i.mx25/50/53 */ - IMX27_FEC, /* runs on i.mx27/35/51 */ - IMX28_FEC, - IMX6Q_FEC, - MVF600_FEC, - IMX6SX_FEC, - IMX6UL_FEC, - IMX8MQ_FEC, - IMX8QM_FEC, - S32V234_FEC, -}; - static const struct of_device_id fec_dt_ids[] = { - { .compatible = "fsl,imx25-fec", .data = &fec_devtype[IMX25_FEC], }, - { .compatible = "fsl,imx27-fec", .data = &fec_devtype[IMX27_FEC], }, - { .compatible = "fsl,imx28-fec", .data = &fec_devtype[IMX28_FEC], }, - { .compatible = "fsl,imx6q-fec", .data = &fec_devtype[IMX6Q_FEC], }, - { .compatible = "fsl,mvf600-fec", .data = &fec_devtype[MVF600_FEC], }, - { .compatible = "fsl,imx6sx-fec", .data = &fec_devtype[IMX6SX_FEC], }, - { .compatible = "fsl,imx6ul-fec", .data = &fec_devtype[IMX6UL_FEC], }, - { .compatible = "fsl,imx8mq-fec", .data = &fec_devtype[IMX8MQ_FEC], }, - { .compatible = "fsl,imx8qm-fec", .data = &fec_devtype[IMX8QM_FEC], }, - { .compatible = "fsl,s32v234-fec", .data = &fec_devtype[S32V234_FEC], }, + { .compatible = "fsl,imx25-fec", .data = &fec_imx25_info, }, + { .compatible = "fsl,imx27-fec", .data = &fec_imx27_info, }, + { .compatible = "fsl,imx28-fec", .data = &fec_imx28_info, }, + { .compatible = "fsl,imx6q-fec", .data = &fec_imx6q_info, }, + { .compatible = "fsl,mvf600-fec", .data = &fec_mvf600_info, }, + { .compatible = "fsl,imx6sx-fec", .data = &fec_imx6x_info, }, + { .compatible = "fsl,imx6ul-fec", .data = &fec_imx6ul_info, }, + { .compatible = "fsl,imx8mq-fec", .data = &fec_imx8mq_info, }, + { .compatible = "fsl,imx8qm-fec", .data = &fec_imx8qm_info, }, + { .compatible = "fsl,s32v234-fec", .data = &fec_s32v234_info, }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, fec_dt_ids); diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c index d1da7413dc4d..e84a066aa1a4 100644 --- a/drivers/net/ethernet/google/gve/gve_rx.c +++ b/drivers/net/ethernet/google/gve/gve_rx.c @@ -146,7 +146,7 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) err = gve_rx_alloc_buffer(priv, &priv->pdev->dev, &rx->data.page_info[i], &rx->data.data_ring[i]); if (err) - goto alloc_err; + goto alloc_err_rda; } if (!rx->data.raw_addressing) { @@ -171,12 +171,26 @@ static int gve_prefill_rx_pages(struct gve_rx_ring *rx) return slots; alloc_err_qpl: + /* Fully free the copy pool pages. */ while (j--) { page_ref_sub(rx->qpl_copy_pool[j].page, rx->qpl_copy_pool[j].pagecnt_bias - 1); put_page(rx->qpl_copy_pool[j].page); } -alloc_err: + + /* Do not fully free QPL pages - only remove the bias added in this + * function with gve_setup_rx_buffer. + */ + while (i--) + page_ref_sub(rx->data.page_info[i].page, + rx->data.page_info[i].pagecnt_bias - 1); + + gve_unassign_qpl(priv, rx->data.qpl->id); + rx->data.qpl = NULL; + + return err; + +alloc_err_rda: while (i--) gve_rx_free_buffer(&priv->pdev->dev, &rx->data.page_info[i], diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cf50368441b7..06117502001f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -4940,8 +4940,7 @@ static void hns3_put_ring_config(struct hns3_nic_priv *priv) static void hns3_alloc_page_pool(struct hns3_enet_ring *ring) { struct page_pool_params pp_params = { - .flags = PP_FLAG_DMA_MAP | PP_FLAG_PAGE_FRAG | - PP_FLAG_DMA_SYNC_DEV, + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, .order = hns3_page_order(ring), .pool_size = ring->desc_num * hns3_buf_size(ring) / (PAGE_SIZE << hns3_page_order(ring)), diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 99c0576e6383..66e5807903a0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -881,8 +881,8 @@ static const struct hclge_speed_bit_map speed_bit_map[] = { {HCLGE_MAC_SPEED_10G, HCLGE_SUPPORT_10G_BIT}, {HCLGE_MAC_SPEED_25G, HCLGE_SUPPORT_25G_BIT}, {HCLGE_MAC_SPEED_40G, HCLGE_SUPPORT_40G_BIT}, - {HCLGE_MAC_SPEED_50G, HCLGE_SUPPORT_50G_BIT}, - {HCLGE_MAC_SPEED_100G, HCLGE_SUPPORT_100G_BIT}, + {HCLGE_MAC_SPEED_50G, HCLGE_SUPPORT_50G_BITS}, + {HCLGE_MAC_SPEED_100G, HCLGE_SUPPORT_100G_BITS}, {HCLGE_MAC_SPEED_200G, HCLGE_SUPPORT_200G_BIT}, }; @@ -939,100 +939,98 @@ static void hclge_update_fec_support(struct hclge_mac *mac) mac->supported); } +static const struct hclge_link_mode_bmap hclge_sr_link_mode_bmap[8] = { + {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseSR_Full_BIT}, + {HCLGE_SUPPORT_25G_BIT, ETHTOOL_LINK_MODE_25000baseSR_Full_BIT}, + {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT}, + {HCLGE_SUPPORT_50G_R2_BIT, ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT}, + {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseSR_Full_BIT}, + {HCLGE_SUPPORT_100G_R4_BIT, ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT}, + {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT}, + {HCLGE_SUPPORT_200G_BIT, ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT}, +}; + +static const struct hclge_link_mode_bmap hclge_lr_link_mode_bmap[6] = { + {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseLR_Full_BIT}, + {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT}, + {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT}, + {HCLGE_SUPPORT_100G_R4_BIT, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT}, + {HCLGE_SUPPORT_100G_R2_BIT, + ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT}, + {HCLGE_SUPPORT_200G_BIT, + ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT}, +}; + +static const struct hclge_link_mode_bmap hclge_cr_link_mode_bmap[8] = { + {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseCR_Full_BIT}, + {HCLGE_SUPPORT_25G_BIT, ETHTOOL_LINK_MODE_25000baseCR_Full_BIT}, + {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT}, + {HCLGE_SUPPORT_50G_R2_BIT, ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT}, + {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseCR_Full_BIT}, + {HCLGE_SUPPORT_100G_R4_BIT, ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT}, + {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT}, + {HCLGE_SUPPORT_200G_BIT, ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT}, +}; + +static const struct hclge_link_mode_bmap hclge_kr_link_mode_bmap[9] = { + {HCLGE_SUPPORT_1G_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, + {HCLGE_SUPPORT_10G_BIT, ETHTOOL_LINK_MODE_10000baseKR_Full_BIT}, + {HCLGE_SUPPORT_25G_BIT, ETHTOOL_LINK_MODE_25000baseKR_Full_BIT}, + {HCLGE_SUPPORT_40G_BIT, ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT}, + {HCLGE_SUPPORT_50G_R2_BIT, ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT}, + {HCLGE_SUPPORT_50G_R1_BIT, ETHTOOL_LINK_MODE_50000baseKR_Full_BIT}, + {HCLGE_SUPPORT_100G_R4_BIT, ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT}, + {HCLGE_SUPPORT_100G_R2_BIT, ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT}, + {HCLGE_SUPPORT_200G_BIT, ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT}, +}; + static void hclge_convert_setting_sr(u16 speed_ability, unsigned long *link_mode) { - if (speed_ability & HCLGE_SUPPORT_10G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_25G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_40G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_50G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_100G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_200G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, - link_mode); + int i; + + for (i = 0; i < ARRAY_SIZE(hclge_sr_link_mode_bmap); i++) { + if (speed_ability & hclge_sr_link_mode_bmap[i].support_bit) + linkmode_set_bit(hclge_sr_link_mode_bmap[i].link_mode, + link_mode); + } } static void hclge_convert_setting_lr(u16 speed_ability, unsigned long *link_mode) { - if (speed_ability & HCLGE_SUPPORT_10G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_25G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_50G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_40G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_100G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_200G_BIT) - linkmode_set_bit( - ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, - link_mode); + int i; + + for (i = 0; i < ARRAY_SIZE(hclge_lr_link_mode_bmap); i++) { + if (speed_ability & hclge_lr_link_mode_bmap[i].support_bit) + linkmode_set_bit(hclge_lr_link_mode_bmap[i].link_mode, + link_mode); + } } static void hclge_convert_setting_cr(u16 speed_ability, unsigned long *link_mode) { - if (speed_ability & HCLGE_SUPPORT_10G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_25G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_40G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_50G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_100G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_200G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, - link_mode); + int i; + + for (i = 0; i < ARRAY_SIZE(hclge_cr_link_mode_bmap); i++) { + if (speed_ability & hclge_cr_link_mode_bmap[i].support_bit) + linkmode_set_bit(hclge_cr_link_mode_bmap[i].link_mode, + link_mode); + } } static void hclge_convert_setting_kr(u16 speed_ability, unsigned long *link_mode) { - if (speed_ability & HCLGE_SUPPORT_1G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_10G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_25G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_40G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_50G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_100G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, - link_mode); - if (speed_ability & HCLGE_SUPPORT_200G_BIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, - link_mode); + int i; + + for (i = 0; i < ARRAY_SIZE(hclge_kr_link_mode_bmap); i++) { + if (speed_ability & hclge_kr_link_mode_bmap[i].support_bit) + linkmode_set_bit(hclge_kr_link_mode_bmap[i].link_mode, + link_mode); + } } static void hclge_convert_setting_fec(struct hclge_mac *mac) @@ -1158,10 +1156,10 @@ static u32 hclge_get_max_speed(u16 speed_ability) if (speed_ability & HCLGE_SUPPORT_200G_BIT) return HCLGE_MAC_SPEED_200G; - if (speed_ability & HCLGE_SUPPORT_100G_BIT) + if (speed_ability & HCLGE_SUPPORT_100G_BITS) return HCLGE_MAC_SPEED_100G; - if (speed_ability & HCLGE_SUPPORT_50G_BIT) + if (speed_ability & HCLGE_SUPPORT_50G_BITS) return HCLGE_MAC_SPEED_50G; if (speed_ability & HCLGE_SUPPORT_40G_BIT) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 02c7aab3546e..51979cf71262 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -185,15 +185,22 @@ enum HLCGE_PORT_TYPE { #define HCLGE_SUPPORT_1G_BIT BIT(0) #define HCLGE_SUPPORT_10G_BIT BIT(1) #define HCLGE_SUPPORT_25G_BIT BIT(2) -#define HCLGE_SUPPORT_50G_BIT BIT(3) -#define HCLGE_SUPPORT_100G_BIT BIT(4) +#define HCLGE_SUPPORT_50G_R2_BIT BIT(3) +#define HCLGE_SUPPORT_100G_R4_BIT BIT(4) /* to be compatible with exsit board */ #define HCLGE_SUPPORT_40G_BIT BIT(5) #define HCLGE_SUPPORT_100M_BIT BIT(6) #define HCLGE_SUPPORT_10M_BIT BIT(7) #define HCLGE_SUPPORT_200G_BIT BIT(8) +#define HCLGE_SUPPORT_50G_R1_BIT BIT(9) +#define HCLGE_SUPPORT_100G_R2_BIT BIT(10) + #define HCLGE_SUPPORT_GE \ (HCLGE_SUPPORT_1G_BIT | HCLGE_SUPPORT_100M_BIT | HCLGE_SUPPORT_10M_BIT) +#define HCLGE_SUPPORT_50G_BITS \ + (HCLGE_SUPPORT_50G_R2_BIT | HCLGE_SUPPORT_50G_R1_BIT) +#define HCLGE_SUPPORT_100G_BITS \ + (HCLGE_SUPPORT_100G_R4_BIT | HCLGE_SUPPORT_100G_R2_BIT) enum HCLGE_DEV_STATE { HCLGE_STATE_REINITING, @@ -1076,6 +1083,11 @@ struct hclge_mac_speed_map { u32 speed_fw; /* speed defined in firmware */ }; +struct hclge_link_mode_bmap { + u16 support_bit; + enum ethtool_link_mode_bit_indices link_mode; +}; + int hclge_set_vport_promisc_mode(struct hclge_vport *vport, bool en_uc_pmc, bool en_mc_pmc, bool en_bc_pmc); int hclge_add_uc_addr_common(struct hclge_vport *vport, diff --git a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c index 1749d26f4bef..03e42512a2d5 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_devlink.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_devlink.c @@ -315,136 +315,76 @@ void hinic_devlink_unregister(struct hinic_devlink_priv *priv) devlink_unregister(devlink); } -static int chip_fault_show(struct devlink_fmsg *fmsg, - struct hinic_fault_event *event) +static void chip_fault_show(struct devlink_fmsg *fmsg, + struct hinic_fault_event *event) { const char * const level_str[FAULT_LEVEL_MAX + 1] = { "fatal", "reset", "flr", "general", "suggestion", "Unknown"}; u8 fault_level; - int err; fault_level = (event->event.chip.err_level < FAULT_LEVEL_MAX) ? event->event.chip.err_level : FAULT_LEVEL_MAX; - if (fault_level == FAULT_LEVEL_SERIOUS_FLR) { - err = devlink_fmsg_u32_pair_put(fmsg, "Function level err func_id", - (u32)event->event.chip.func_id); - if (err) - return err; - } - - err = devlink_fmsg_u8_pair_put(fmsg, "module_id", event->event.chip.node_id); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "err_type", (u32)event->event.chip.err_type); - if (err) - return err; - - err = devlink_fmsg_string_pair_put(fmsg, "err_level", level_str[fault_level]); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "err_csr_addr", - event->event.chip.err_csr_addr); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "err_csr_value", - event->event.chip.err_csr_value); - if (err) - return err; - - return 0; + if (fault_level == FAULT_LEVEL_SERIOUS_FLR) + devlink_fmsg_u32_pair_put(fmsg, "Function level err func_id", + (u32)event->event.chip.func_id); + devlink_fmsg_u8_pair_put(fmsg, "module_id", event->event.chip.node_id); + devlink_fmsg_u32_pair_put(fmsg, "err_type", (u32)event->event.chip.err_type); + devlink_fmsg_string_pair_put(fmsg, "err_level", level_str[fault_level]); + devlink_fmsg_u32_pair_put(fmsg, "err_csr_addr", + event->event.chip.err_csr_addr); + devlink_fmsg_u32_pair_put(fmsg, "err_csr_value", + event->event.chip.err_csr_value); } -static int fault_report_show(struct devlink_fmsg *fmsg, - struct hinic_fault_event *event) +static void fault_report_show(struct devlink_fmsg *fmsg, + struct hinic_fault_event *event) { const char * const type_str[FAULT_TYPE_MAX + 1] = { "chip", "ucode", "mem rd timeout", "mem wr timeout", "reg rd timeout", "reg wr timeout", "phy fault", "Unknown"}; u8 fault_type; - int err; fault_type = (event->type < FAULT_TYPE_MAX) ? event->type : FAULT_TYPE_MAX; - err = devlink_fmsg_string_pair_put(fmsg, "Fault type", type_str[fault_type]); - if (err) - return err; - - err = devlink_fmsg_binary_pair_put(fmsg, "Fault raw data", - event->event.val, sizeof(event->event.val)); - if (err) - return err; + devlink_fmsg_string_pair_put(fmsg, "Fault type", type_str[fault_type]); + devlink_fmsg_binary_pair_put(fmsg, "Fault raw data", event->event.val, + sizeof(event->event.val)); switch (event->type) { case FAULT_TYPE_CHIP: - err = chip_fault_show(fmsg, event); - if (err) - return err; + chip_fault_show(fmsg, event); break; case FAULT_TYPE_UCODE: - err = devlink_fmsg_u8_pair_put(fmsg, "Cause_id", event->event.ucode.cause_id); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "core_id", event->event.ucode.core_id); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "c_id", event->event.ucode.c_id); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "epc", event->event.ucode.epc); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "Cause_id", event->event.ucode.cause_id); + devlink_fmsg_u8_pair_put(fmsg, "core_id", event->event.ucode.core_id); + devlink_fmsg_u8_pair_put(fmsg, "c_id", event->event.ucode.c_id); + devlink_fmsg_u8_pair_put(fmsg, "epc", event->event.ucode.epc); break; case FAULT_TYPE_MEM_RD_TIMEOUT: case FAULT_TYPE_MEM_WR_TIMEOUT: - err = devlink_fmsg_u32_pair_put(fmsg, "Err_csr_ctrl", - event->event.mem_timeout.err_csr_ctrl); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "err_csr_data", - event->event.mem_timeout.err_csr_data); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "ctrl_tab", - event->event.mem_timeout.ctrl_tab); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "mem_index", - event->event.mem_timeout.mem_index); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "Err_csr_ctrl", + event->event.mem_timeout.err_csr_ctrl); + devlink_fmsg_u32_pair_put(fmsg, "err_csr_data", + event->event.mem_timeout.err_csr_data); + devlink_fmsg_u32_pair_put(fmsg, "ctrl_tab", + event->event.mem_timeout.ctrl_tab); + devlink_fmsg_u32_pair_put(fmsg, "mem_index", + event->event.mem_timeout.mem_index); break; case FAULT_TYPE_REG_RD_TIMEOUT: case FAULT_TYPE_REG_WR_TIMEOUT: - err = devlink_fmsg_u32_pair_put(fmsg, "Err_csr", event->event.reg_timeout.err_csr); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "Err_csr", event->event.reg_timeout.err_csr); break; case FAULT_TYPE_PHY_FAULT: - err = devlink_fmsg_u8_pair_put(fmsg, "Op_type", event->event.phy_fault.op_type); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "port_id", event->event.phy_fault.port_id); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "dev_ad", event->event.phy_fault.dev_ad); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "csr_addr", event->event.phy_fault.csr_addr); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "op_data", event->event.phy_fault.op_data); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "Op_type", event->event.phy_fault.op_type); + devlink_fmsg_u8_pair_put(fmsg, "port_id", event->event.phy_fault.port_id); + devlink_fmsg_u8_pair_put(fmsg, "dev_ad", event->event.phy_fault.dev_ad); + devlink_fmsg_u32_pair_put(fmsg, "csr_addr", event->event.phy_fault.csr_addr); + devlink_fmsg_u32_pair_put(fmsg, "op_data", event->event.phy_fault.op_data); break; default: break; } - - return 0; } static int hinic_hw_reporter_dump(struct devlink_health_reporter *reporter, @@ -452,75 +392,30 @@ static int hinic_hw_reporter_dump(struct devlink_health_reporter *reporter, struct netlink_ext_ack *extack) { if (priv_ctx) - return fault_report_show(fmsg, priv_ctx); + fault_report_show(fmsg, priv_ctx); return 0; } -static int mgmt_watchdog_report_show(struct devlink_fmsg *fmsg, - struct hinic_mgmt_watchdog_info *watchdog_info) +static void mgmt_watchdog_report_show(struct devlink_fmsg *fmsg, + struct hinic_mgmt_watchdog_info *winfo) { - int err; - - err = devlink_fmsg_u32_pair_put(fmsg, "Mgmt deadloop time_h", watchdog_info->curr_time_h); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "time_l", watchdog_info->curr_time_l); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "task_id", watchdog_info->task_id); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "sp", watchdog_info->sp); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "stack_current_used", watchdog_info->curr_used); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "peak_used", watchdog_info->peak_used); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "\n Overflow_flag", watchdog_info->is_overflow); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "stack_top", watchdog_info->stack_top); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "stack_bottom", watchdog_info->stack_bottom); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "mgmt_pc", watchdog_info->pc); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "lr", watchdog_info->lr); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "cpsr", watchdog_info->cpsr); - if (err) - return err; - - err = devlink_fmsg_binary_pair_put(fmsg, "Mgmt register info", - watchdog_info->reg, sizeof(watchdog_info->reg)); - if (err) - return err; - - err = devlink_fmsg_binary_pair_put(fmsg, "Mgmt dump stack(start from sp)", - watchdog_info->data, sizeof(watchdog_info->data)); - if (err) - return err; - - return 0; + devlink_fmsg_u32_pair_put(fmsg, "Mgmt deadloop time_h", winfo->curr_time_h); + devlink_fmsg_u32_pair_put(fmsg, "time_l", winfo->curr_time_l); + devlink_fmsg_u32_pair_put(fmsg, "task_id", winfo->task_id); + devlink_fmsg_u32_pair_put(fmsg, "sp", winfo->sp); + devlink_fmsg_u32_pair_put(fmsg, "stack_current_used", winfo->curr_used); + devlink_fmsg_u32_pair_put(fmsg, "peak_used", winfo->peak_used); + devlink_fmsg_u32_pair_put(fmsg, "\n Overflow_flag", winfo->is_overflow); + devlink_fmsg_u32_pair_put(fmsg, "stack_top", winfo->stack_top); + devlink_fmsg_u32_pair_put(fmsg, "stack_bottom", winfo->stack_bottom); + devlink_fmsg_u32_pair_put(fmsg, "mgmt_pc", winfo->pc); + devlink_fmsg_u32_pair_put(fmsg, "lr", winfo->lr); + devlink_fmsg_u32_pair_put(fmsg, "cpsr", winfo->cpsr); + devlink_fmsg_binary_pair_put(fmsg, "Mgmt register info", winfo->reg, + sizeof(winfo->reg)); + devlink_fmsg_binary_pair_put(fmsg, "Mgmt dump stack(start from sp)", + winfo->data, sizeof(winfo->data)); } static int hinic_fw_reporter_dump(struct devlink_health_reporter *reporter, @@ -528,7 +423,7 @@ static int hinic_fw_reporter_dump(struct devlink_health_reporter *reporter, struct netlink_ext_ack *extack) { if (priv_ctx) - return mgmt_watchdog_report_show(fmsg, priv_ctx); + mgmt_watchdog_report_show(fmsg, priv_ctx); return 0; } diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index d3fdc290937f..01f0f12035ca 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -2841,7 +2841,7 @@ static int e100_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &e100_netdev_ops; netdev->ethtool_ops = &e100_ethtool_ops; netdev->watchdog_timeo = E100_WATCHDOG_PERIOD; - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); nic = netdev_priv(netdev); netif_napi_add_weight(netdev, &nic->napi, e100_poll, E100_NAPI_WEIGHT); diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index da6e303ad99b..1d1e93686af2 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1014,7 +1014,7 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->watchdog_timeo = 5 * HZ; netif_napi_add(netdev, &adapter->napi, e1000_clean); - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); adapter->bd_number = cards_found; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index d53369e30040..13a05604dcc0 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -448,10 +448,10 @@ static void fm10k_get_drvinfo(struct net_device *dev, { struct fm10k_intfc *interface = netdev_priv(dev); - strncpy(info->driver, fm10k_driver_name, - sizeof(info->driver) - 1); - strncpy(info->bus_info, pci_name(interface->pdev), - sizeof(info->bus_info) - 1); + strscpy(info->driver, fm10k_driver_name, + sizeof(info->driver)); + strscpy(info->bus_info, pci_name(interface->pdev), + sizeof(info->bus_info)); } static void fm10k_get_pauseparam(struct net_device *dev, diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index c4cd54aa4dd5..1bf424ac3145 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -528,7 +528,6 @@ struct i40e_pf { #define I40E_FLAG_DISABLE_FW_LLDP BIT(24) #define I40E_FLAG_RS_FEC BIT(25) #define I40E_FLAG_BASE_R_FEC BIT(26) -#define I40E_FLAG_VF_VLAN_PRUNING BIT(27) /* TOTAL_PORT_SHUTDOWN * Allows to physically disable the link on the NIC's port. * If enabled, (after link down request from the OS) @@ -551,6 +550,7 @@ struct i40e_pf { * in abilities field of i40e_aq_set_phy_config structure */ #define I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENABLED BIT(27) +#define I40E_FLAG_VF_VLAN_PRUNING BIT(28) struct i40e_client_instance *cinst; bool stat_offsets_loaded; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 04db9cdc7d94..d7e24d661724 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1095,7 +1095,7 @@ void i40e_clear_hw(struct i40e_hw *hw) I40E_PFLAN_QALLOC_FIRSTQ_SHIFT; j = (val & I40E_PFLAN_QALLOC_LASTQ_MASK) >> I40E_PFLAN_QALLOC_LASTQ_SHIFT; - if (val & I40E_PFLAN_QALLOC_VALID_MASK) + if (val & I40E_PFLAN_QALLOC_VALID_MASK && j >= base_queue) num_queues = (j - base_queue) + 1; else num_queues = 0; @@ -1105,7 +1105,7 @@ void i40e_clear_hw(struct i40e_hw *hw) I40E_PF_VT_PFALLOC_FIRSTVF_SHIFT; j = (val & I40E_PF_VT_PFALLOC_LASTVF_MASK) >> I40E_PF_VT_PFALLOC_LASTVF_SHIFT; - if (val & I40E_PF_VT_PFALLOC_VALID_MASK) + if (val & I40E_PF_VT_PFALLOC_VALID_MASK && j >= i) num_vfs = (j - i) + 1; else num_vfs = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ddp.c b/drivers/net/ethernet/intel/i40e/i40e_ddp.c index 6b68b6575a1d..cf25bfc5dc3f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ddp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ddp.c @@ -456,10 +456,9 @@ int i40e_ddp_flash(struct net_device *netdev, struct ethtool_flash *flash) char profile_name[sizeof(I40E_DDP_PROFILE_PATH) + I40E_DDP_PROFILE_NAME_MAX]; - profile_name[sizeof(profile_name) - 1] = 0; - strncpy(profile_name, I40E_DDP_PROFILE_PATH, - sizeof(profile_name) - 1); - strncat(profile_name, flash->data, I40E_DDP_PROFILE_NAME_MAX); + scnprintf(profile_name, sizeof(profile_name), "%s%s", + I40E_DDP_PROFILE_PATH, flash->data); + /* Load DDP recipe. */ status = request_firmware(&ddp_config, profile_name, &netdev->dev); diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.c b/drivers/net/ethernet/intel/i40e/i40e_devlink.c index 9168ade8da47..74bc111b4849 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_devlink.c +++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.c @@ -18,8 +18,14 @@ static void i40e_info_fw_mgmt(struct i40e_hw *hw, char *buf, size_t len) { struct i40e_adminq_info *aq = &hw->aq; - snprintf(buf, len, "%u.%u.%05d", - aq->fw_maj_ver, aq->fw_min_ver, aq->fw_build); + snprintf(buf, len, "%u.%u", aq->fw_maj_ver, aq->fw_min_ver); +} + +static void i40e_info_fw_mgmt_build(struct i40e_hw *hw, char *buf, size_t len) +{ + struct i40e_adminq_info *aq = &hw->aq; + + snprintf(buf, len, "%05d", aq->fw_build); } static void i40e_info_fw_api(struct i40e_hw *hw, char *buf, size_t len) @@ -77,6 +83,12 @@ static int i40e_devlink_info_get(struct devlink *dl, if (err) return err; + i40e_info_fw_mgmt_build(hw, buf, sizeof(buf)); + err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, + "fw.mgmt.build", buf); + if (err) + return err; + i40e_info_fw_api(hw, buf, sizeof(buf)); err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, DEVLINK_INFO_VERSION_GENERIC_FW_MGMT_API, @@ -86,7 +98,7 @@ static int i40e_devlink_info_get(struct devlink *dl, i40e_info_nvm_ver(hw, buf, sizeof(buf)); err = i40e_devlink_info_put(req, I40E_DL_VERSION_RUNNING, - DEVLINK_INFO_VERSION_GENERIC_FW_PSID, buf); + "fw.psid.api", buf); if (err) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index ebf36f76c0d7..fd7163128c4d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -2514,11 +2514,13 @@ static void i40e_get_priv_flag_strings(struct net_device *netdev, u8 *data) u8 *p = data; for (i = 0; i < I40E_PRIV_FLAGS_STR_LEN; i++) - ethtool_sprintf(&p, i40e_gstrings_priv_flags[i].flag_string); + ethtool_sprintf(&p, "%s", + i40e_gstrings_priv_flags[i].flag_string); if (pf->hw.pf_id != 0) return; for (i = 0; i < I40E_GL_PRIV_FLAGS_STR_LEN; i++) - ethtool_sprintf(&p, i40e_gl_gstrings_priv_flags[i].flag_string); + ethtool_sprintf(&p, "%s", + i40e_gl_gstrings_priv_flags[i].flag_string); } static void i40e_get_strings(struct net_device *netdev, u32 stringset, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d1400cb7f1fc..dd410b15000f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2543,7 +2543,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, rx_buffer = i40e_rx_bi(rx_ring, ntp); i40e_inc_ntp(rx_ring); i40e_reuse_rx_page(rx_ring, rx_buffer); - cleaned_count++; + /* Update ntc and bump cleaned count if not in the + * middle of mb packet. + */ + if (rx_ring->next_to_clean == ntp) { + rx_ring->next_to_clean = + rx_ring->next_to_process; + cleaned_count++; + } continue; } @@ -2846,7 +2853,7 @@ tx_only: return budget; } - if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) + if (q_vector->tx.ring[0].flags & I40E_TXR_FLAGS_WB_ON_ITR) q_vector->arm_wb_state = false; /* Exit the polling mode, but don't re-enable interrupts if stack might diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 4a49848f7781..e99fa854d17f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -433,12 +433,12 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 next_to_process = rx_ring->next_to_process; u16 next_to_clean = rx_ring->next_to_clean; - u16 count_mask = rx_ring->count - 1; unsigned int xdp_res, xdp_xmit = 0; struct xdp_buff *first = NULL; + u32 count = rx_ring->count; struct bpf_prog *xdp_prog; + u32 entries_to_alloc; bool failure = false; - u16 cleaned_count; if (next_to_process != next_to_clean) first = *i40e_rx_bi(rx_ring, next_to_clean); @@ -471,7 +471,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) qword); bi = *i40e_rx_bi(rx_ring, next_to_process); xsk_buff_free(bi); - next_to_process = (next_to_process + 1) & count_mask; + if (++next_to_process == count) + next_to_process = 0; continue; } @@ -489,7 +490,8 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) else if (i40e_add_xsk_frag(rx_ring, first, bi, size)) break; - next_to_process = (next_to_process + 1) & count_mask; + if (++next_to_process == count) + next_to_process = 0; if (i40e_is_non_eop(rx_ring, rx_desc)) continue; @@ -509,10 +511,10 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) rx_ring->next_to_clean = next_to_clean; rx_ring->next_to_process = next_to_process; - cleaned_count = (next_to_clean - rx_ring->next_to_use - 1) & count_mask; - if (cleaned_count >= I40E_RX_BUFFER_WRITE) - failure |= !i40e_alloc_rx_buffers_zc(rx_ring, cleaned_count); + entries_to_alloc = I40E_DESC_UNUSED(rx_ring); + if (entries_to_alloc >= I40E_RX_BUFFER_WRITE) + failure |= !i40e_alloc_rx_buffers_zc(rx_ring, entries_to_alloc); i40e_finalize_xdp_rx(rx_ring, xdp_xmit); i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); @@ -748,14 +750,16 @@ int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) void i40e_xsk_clean_rx_ring(struct i40e_ring *rx_ring) { - u16 count_mask = rx_ring->count - 1; u16 ntc = rx_ring->next_to_clean; u16 ntu = rx_ring->next_to_use; - for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) { + while (ntc != ntu) { struct xdp_buff *rx_bi = *i40e_rx_bi(rx_ring, ntc); xsk_buff_free(rx_bi); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; } } diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 1afd761d8052..8091e6feca01 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -7,38 +7,6 @@ #include <linux/avf/virtchnl.h> /** - * iavf_set_mac_type - Sets MAC type - * @hw: pointer to the HW structure - * - * This function sets the mac type of the adapter based on the - * vendor ID and device ID stored in the hw structure. - **/ -enum iavf_status iavf_set_mac_type(struct iavf_hw *hw) -{ - enum iavf_status status = 0; - - if (hw->vendor_id == PCI_VENDOR_ID_INTEL) { - switch (hw->device_id) { - case IAVF_DEV_ID_X722_VF: - hw->mac.type = IAVF_MAC_X722_VF; - break; - case IAVF_DEV_ID_VF: - case IAVF_DEV_ID_VF_HV: - case IAVF_DEV_ID_ADAPTIVE_VF: - hw->mac.type = IAVF_MAC_VF; - break; - default: - hw->mac.type = IAVF_MAC_GENERIC; - break; - } - } else { - status = IAVF_ERR_DEVICE_NOT_SUPPORTED; - } - - return status; -} - -/** * iavf_aq_str - convert AQ err code to a string * @hw: pointer to the HW structure * @aq_err: the AQ error code to convert diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 90397293525f..6f236d1a6444 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -395,11 +395,9 @@ static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data) { unsigned int i; - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { - snprintf(data, ETH_GSTRING_LEN, "%s", - iavf_gstrings_priv_flags[i].flag_string); - data += ETH_GSTRING_LEN; - } + for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) + ethtool_sprintf(&data, "%s", + iavf_gstrings_priv_flags[i].flag_string); } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 43c47c633162..3431d9b064f8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1438,9 +1438,9 @@ void iavf_down(struct iavf_adapter *adapter) adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; if (!list_empty(&adapter->adv_rss_list_head)) adapter->aq_required |= IAVF_FLAG_AQ_DEL_ADV_RSS_CFG; - adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; } + adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } @@ -2356,11 +2356,6 @@ static void iavf_startup(struct iavf_adapter *adapter) /* driver loaded, probe complete */ adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - status = iavf_set_mac_type(hw); - if (status) { - dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", status); - goto err; - } ret = iavf_check_reset_complete(hw); if (ret) { @@ -5030,8 +5025,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->finish_config, iavf_finish_config); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); - queue_delayed_work(adapter->wq, &adapter->watchdog_task, - msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); @@ -5042,6 +5035,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + msecs_to_jiffies(5 * (pdev->devfn & 0x07))); + /* Initialization goes on in the work. Do not add more of it below. */ return 0; err_ioremap: diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h index 940cb4203fbe..4a48e6171405 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -45,8 +45,6 @@ enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid, enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid, struct iavf_aqc_get_set_rss_key_data *key); -enum iavf_status iavf_set_mac_type(struct iavf_hw *hw); - extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index 9f1f523807c4..2b6a207fa441 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -69,15 +69,6 @@ enum iavf_debug_mask { * the Firmware and AdminQ are intended to insulate the driver from most of the * future changes, but these structures will also do part of the job. */ -enum iavf_mac_type { - IAVF_MAC_UNKNOWN = 0, - IAVF_MAC_XL710, - IAVF_MAC_VF, - IAVF_MAC_X722, - IAVF_MAC_X722_VF, - IAVF_MAC_GENERIC, -}; - enum iavf_vsi_type { IAVF_VSI_MAIN = 0, IAVF_VSI_VMDQ1 = 1, @@ -110,11 +101,8 @@ struct iavf_hw_capabilities { }; struct iavf_mac_info { - enum iavf_mac_type type; u8 addr[ETH_ALEN]; u8 perm_addr[ETH_ALEN]; - u8 san_addr[ETH_ALEN]; - u16 max_fcoeq; }; /* PCI bus types */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 8ce6389b5815..82b84a93bcc8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1378,8 +1378,6 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid) VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2); } -#define IAVF_MAX_SPEED_STRLEN 13 - /** * iavf_print_link_message - print link up or down * @adapter: adapter structure @@ -1397,10 +1395,6 @@ static void iavf_print_link_message(struct iavf_adapter *adapter) return; } - speed = kzalloc(IAVF_MAX_SPEED_STRLEN, GFP_KERNEL); - if (!speed) - return; - if (ADV_LINK_SUPPORT(adapter)) { link_speed_mbps = adapter->link_speed_mbps; goto print_link_msg; @@ -1438,17 +1432,17 @@ static void iavf_print_link_message(struct iavf_adapter *adapter) print_link_msg: if (link_speed_mbps > SPEED_1000) { - if (link_speed_mbps == SPEED_2500) - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "2.5 Gbps"); - else + if (link_speed_mbps == SPEED_2500) { + speed = kasprintf(GFP_KERNEL, "%s", "2.5 Gbps"); + } else { /* convert to Gbps inline */ - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "%d %s", - link_speed_mbps / 1000, "Gbps"); + speed = kasprintf(GFP_KERNEL, "%d Gbps", + link_speed_mbps / 1000); + } } else if (link_speed_mbps == SPEED_UNKNOWN) { - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "%s", "Unknown Mbps"); + speed = kasprintf(GFP_KERNEL, "%s", "Unknown Mbps"); } else { - snprintf(speed, IAVF_MAX_SPEED_STRLEN, "%d %s", - link_speed_mbps, "Mbps"); + speed = kasprintf(GFP_KERNEL, "%d Mbps", link_speed_mbps); } netdev_info(netdev, "NIC Link is Up Speed is %s Full Duplex\n", speed); diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index fcaa5c3b8ec0..351e0d36df44 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -554,6 +554,8 @@ struct ice_pf { * MSIX vectors allowed on this PF. */ u16 sriov_base_vector; + unsigned long *sriov_irq_bm; /* bitmap to track irq usage */ + u16 sriov_irq_size; /* size of the irq_bm bitmap */ u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ @@ -960,6 +962,7 @@ int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); +void ice_adv_lnk_speed_maps_init(void); /** * ice_set_rdma_cap - enable RDMA support diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 8cbe63401378..377fae41bbae 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -473,41 +473,41 @@ ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd, * @node_part_number: node part number to look for * @node_handle: output parameter if node found - optional * - * Find and return the node handle for a given node type and part number in the - * netlist. When found ICE_SUCCESS is returned, ICE_ERR_DOES_NOT_EXIST - * otherwise. If node_handle provided, it would be set to found node handle. + * Scan the netlist for a node handle of the given node type and part number. + * + * If node_handle is non-NULL it will be modified on function exit. It is only + * valid if the function returns zero, and should be ignored on any non-zero + * return value. + * + * Returns: 0 if the node is found, -ENOENT if no handle was found, and + * a negative error code on failure to access the AQ. */ static int ice_find_netlist_node(struct ice_hw *hw, u8 node_type_ctx, u8 node_part_number, u16 *node_handle) { - struct ice_aqc_get_link_topo cmd; - u8 rec_node_part_number; - u16 rec_node_handle; u8 idx; for (idx = 0; idx < ICE_MAX_NETLIST_SIZE; idx++) { + struct ice_aqc_get_link_topo cmd = {}; + u8 rec_node_part_number; int status; - memset(&cmd, 0, sizeof(cmd)); - cmd.addr.topo_params.node_type_ctx = - (node_type_ctx << ICE_AQC_LINK_TOPO_NODE_TYPE_S); + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_TYPE_M, + node_type_ctx); cmd.addr.topo_params.index = idx; status = ice_aq_get_netlist_node(hw, &cmd, &rec_node_part_number, - &rec_node_handle); + node_handle); if (status) return status; - if (rec_node_part_number == node_part_number) { - if (node_handle) - *node_handle = rec_node_handle; + if (rec_node_part_number == node_part_number) return 0; - } } - return -ENOTBLK; + return -ENOENT; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c index 67bfd1f61cdd..6ae0269bdf73 100644 --- a/drivers/net/ethernet/intel/ice/ice_eswitch_br.c +++ b/drivers/net/ethernet/intel/ice/ice_eswitch_br.c @@ -73,7 +73,7 @@ ice_eswitch_br_ingress_rule_setup(struct ice_adv_rule_info *rule_info, rule_info->sw_act.vsi_handle = vf_vsi_idx; rule_info->sw_act.flag |= ICE_FLTR_RX; rule_info->sw_act.src = pf_id; - rule_info->priority = 5; + rule_info->priority = 2; } static void @@ -84,7 +84,7 @@ ice_eswitch_br_egress_rule_setup(struct ice_adv_rule_info *rule_info, rule_info->sw_act.flag |= ICE_FLTR_TX; rule_info->flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; rule_info->flags_info.act_valid = true; - rule_info->priority = 5; + rule_info->priority = 2; } static int @@ -207,7 +207,7 @@ ice_eswitch_br_guard_rule_create(struct ice_hw *hw, u16 vsi_idx, rule_info.allow_pass_l2 = true; rule_info.sw_act.vsi_handle = vsi_idx; rule_info.sw_act.fltr_act = ICE_NOP; - rule_info.priority = 5; + rule_info.priority = 2; err = ice_add_adv_rule(hw, list, lkups_cnt, &rule_info, rule); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index d3cb08e66dcb..7870a3984547 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -345,6 +345,79 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) +static const u32 ice_adv_lnk_speed_100[] __initconst = { + ETHTOOL_LINK_MODE_100baseT_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_1000[] __initconst = { + ETHTOOL_LINK_MODE_1000baseX_Full_BIT, + ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_2500[] __initconst = { + ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + ETHTOOL_LINK_MODE_2500baseX_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_5000[] __initconst = { + ETHTOOL_LINK_MODE_5000baseT_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_10000[] __initconst = { + ETHTOOL_LINK_MODE_10000baseT_Full_BIT, + ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_25000[] __initconst = { + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_40000[] __initconst = { + ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, + ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_50000[] __initconst = { + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, +}; + +static const u32 ice_adv_lnk_speed_100000[] __initconst = { + ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, +}; + +static struct ethtool_forced_speed_map ice_adv_lnk_speed_maps[] __ro_after_init = { + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 100), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 1000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 2500), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 5000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 10000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 25000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 40000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 50000), + ETHTOOL_FORCED_SPEED_MAP(ice_adv_lnk_speed, 100000), +}; + +void __init ice_adv_lnk_speed_maps_init(void) +{ + ethtool_forced_speed_maps_init(ice_adv_lnk_speed_maps, + ARRAY_SIZE(ice_adv_lnk_speed_maps)); +} + static void __ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo, struct ice_vsi *vsi) @@ -1060,7 +1133,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, switch (stringset) { case ETH_SS_STATS: for (i = 0; i < ICE_VSI_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ice_gstrings_vsi_stats[i].stat_string); if (ice_is_port_repr_netdev(netdev)) @@ -1080,7 +1153,7 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, return; for (i = 0; i < ICE_PF_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ice_gstrings_pf_stats[i].stat_string); for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { @@ -1097,7 +1170,8 @@ __ice_get_strings(struct net_device *netdev, u32 stringset, u8 *data, break; case ETH_SS_PRIV_FLAGS: for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) - ethtool_sprintf(&p, ice_gstrings_priv_flags[i].name); + ethtool_sprintf(&p, "%s", + ice_gstrings_priv_flags[i].name); break; default: break; @@ -2008,79 +2082,69 @@ done: } /** + * ice_speed_to_aq_link - Get AQ link speed by Ethtool forced speed + * @speed: ethtool forced speed + */ +static u16 ice_speed_to_aq_link(int speed) +{ + int aq_speed; + + switch (speed) { + case SPEED_10: + aq_speed = ICE_AQ_LINK_SPEED_10MB; + break; + case SPEED_100: + aq_speed = ICE_AQ_LINK_SPEED_100MB; + break; + case SPEED_1000: + aq_speed = ICE_AQ_LINK_SPEED_1000MB; + break; + case SPEED_2500: + aq_speed = ICE_AQ_LINK_SPEED_2500MB; + break; + case SPEED_5000: + aq_speed = ICE_AQ_LINK_SPEED_5GB; + break; + case SPEED_10000: + aq_speed = ICE_AQ_LINK_SPEED_10GB; + break; + case SPEED_20000: + aq_speed = ICE_AQ_LINK_SPEED_20GB; + break; + case SPEED_25000: + aq_speed = ICE_AQ_LINK_SPEED_25GB; + break; + case SPEED_40000: + aq_speed = ICE_AQ_LINK_SPEED_40GB; + break; + case SPEED_50000: + aq_speed = ICE_AQ_LINK_SPEED_50GB; + break; + case SPEED_100000: + aq_speed = ICE_AQ_LINK_SPEED_100GB; + break; + default: + aq_speed = ICE_AQ_LINK_SPEED_UNKNOWN; + break; + } + return aq_speed; +} + +/** * ice_ksettings_find_adv_link_speed - Find advertising link speed * @ks: ethtool ksettings */ static u16 ice_ksettings_find_adv_link_speed(const struct ethtool_link_ksettings *ks) { + const struct ethtool_forced_speed_map *map; u16 adv_link_speed = 0; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 100baseT_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_100MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseX_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseT_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 1000baseKX_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_1000MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 2500baseT_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 2500baseX_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_2500MB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 5000baseT_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_5GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseT_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseKR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseSR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseLR_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_10GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 25000baseCR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 25000baseSR_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 25000baseKR_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_25GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseCR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseSR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseLR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 40000baseKR4_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_40GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseCR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseKR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 50000baseSR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_50GB; - if (ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseCR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseSR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseLR4_ER4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR4_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseCR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseSR2_Full) || - ethtool_link_ksettings_test_link_mode(ks, advertising, - 100000baseKR2_Full)) - adv_link_speed |= ICE_AQ_LINK_SPEED_100GB; + for (u32 i = 0; i < ARRAY_SIZE(ice_adv_lnk_speed_maps); i++) { + map = ice_adv_lnk_speed_maps + i; + if (linkmode_intersects(ks->link_modes.advertising, map->caps)) + adv_link_speed |= ice_speed_to_aq_link(map->speed); + } return adv_link_speed; } diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 85cca572c22a..fb8b925aaf8b 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -1318,7 +1318,6 @@ ice_flow_rem_entry_sync(struct ice_hw *hw, enum ice_block __always_unused blk, list_del(&entry->l_entry); - devm_kfree(ice_hw_to_dev(hw), entry->entry); devm_kfree(ice_hw_to_dev(hw), entry); return 0; @@ -1645,10 +1644,8 @@ ice_flow_add_entry(struct ice_hw *hw, enum ice_block blk, u64 prof_id, *entry_h = ICE_FLOW_ENTRY_HNDL(e); out: - if (status && e) { - devm_kfree(ice_hw_to_dev(hw), e->entry); + if (status) devm_kfree(ice_hw_to_dev(hw), e); - } return status; } diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index b465d27d9b80..96923ef0a5a8 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -350,11 +350,8 @@ struct ice_flow_entry { u64 id; struct ice_flow_prof *prof; - /* Flow entry's content */ - void *entry; enum ice_flow_priority priority; u16 vsi_handle; - u16 entry_sz; }; #define ICE_FLOW_ENTRY_HNDL(e) ((u64)(uintptr_t)e) diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index 165a9d512ce2..b980f89dc892 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -19,8 +19,11 @@ static const u8 lacp_train_pkt[LACP_TRAIN_PKT_LEN] = { 0, 0, 0, 0, 0, 0, static const u8 ice_dflt_vsi_rcp[ICE_RECIPE_LEN] = { 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x85, 0, 0x01, 0, 0, 0, 0xff, 0xff, 0x08, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0x30, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; + 0, 0, 0, 0, 0, 0, 0x30 }; +static const u8 ice_lport_rcp[ICE_RECIPE_LEN] = { + 0x05, 0, 0, 0, 0x20, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x85, 0, 0x16, 0, 0, 0, 0xff, 0xff, 0x07, 0, 0, 0, 0, 0, 0, 0, + 0, 0, 0, 0, 0, 0, 0x30 }; /** * ice_lag_set_primary - set PF LAG state as Primary @@ -173,18 +176,22 @@ static struct ice_lag *ice_lag_find_primary(struct ice_lag *lag) } /** - * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG + * ice_lag_cfg_fltr - Add/Remove rule for LAG * @lag: lag struct for local interface + * @act: rule action + * @recipe_id: recipe id for the new rule + * @rule_idx: pointer to rule index * @add: boolean on whether we are adding filters */ static int -ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) +ice_lag_cfg_fltr(struct ice_lag *lag, u32 act, u16 recipe_id, u16 *rule_idx, + bool add) { struct ice_sw_rule_lkup_rx_tx *s_rule; u16 s_rule_sz, vsi_num; struct ice_hw *hw; - u32 act, opc; u8 *eth_hdr; + u32 opc; int err; hw = &lag->pf->hw; @@ -193,7 +200,7 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) s_rule_sz = ICE_SW_RULE_RX_TX_ETH_HDR_SIZE(s_rule); s_rule = kzalloc(s_rule_sz, GFP_KERNEL); if (!s_rule) { - dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG default VSI\n"); + dev_err(ice_pf_to_dev(lag->pf), "error allocating rule for LAG\n"); return -ENOMEM; } @@ -201,19 +208,17 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) eth_hdr = s_rule->hdr_data; ice_fill_eth_hdr(eth_hdr); - act = (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & + act |= (vsi_num << ICE_SINGLE_ACT_VSI_ID_S) & ICE_SINGLE_ACT_VSI_ID_M; - act |= ICE_SINGLE_ACT_VSI_FORWARDING | - ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; s_rule->hdr.type = cpu_to_le16(ICE_AQC_SW_RULES_T_LKUP_RX); - s_rule->recipe_id = cpu_to_le16(lag->pf_recipe); + s_rule->recipe_id = cpu_to_le16(recipe_id); s_rule->src = cpu_to_le16(hw->port_info->lport); s_rule->act = cpu_to_le32(act); s_rule->hdr_len = cpu_to_le16(DUMMY_ETH_HDR_LEN); opc = ice_aqc_opc_add_sw_rules; } else { - s_rule->index = cpu_to_le16(lag->pf_rule_id); + s_rule->index = cpu_to_le16(*rule_idx); opc = ice_aqc_opc_remove_sw_rules; } @@ -222,9 +227,9 @@ ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) goto dflt_fltr_free; if (add) - lag->pf_rule_id = le16_to_cpu(s_rule->index); + *rule_idx = le16_to_cpu(s_rule->index); else - lag->pf_rule_id = 0; + *rule_idx = 0; dflt_fltr_free: kfree(s_rule); @@ -232,6 +237,37 @@ dflt_fltr_free: } /** + * ice_lag_cfg_dflt_fltr - Add/Remove default VSI rule for LAG + * @lag: lag struct for local interface + * @add: boolean on whether to add filter + */ +static int +ice_lag_cfg_dflt_fltr(struct ice_lag *lag, bool add) +{ + u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | ICE_SINGLE_ACT_LAN_ENABLE; + + return ice_lag_cfg_fltr(lag, act, lag->pf_recipe, + &lag->pf_rule_id, add); +} + +/** + * ice_lag_cfg_drop_fltr - Add/Remove lport drop rule + * @lag: lag struct for local interface + * @add: boolean on whether to add filter + */ +static int +ice_lag_cfg_drop_fltr(struct ice_lag *lag, bool add) +{ + u32 act = ICE_SINGLE_ACT_VSI_FORWARDING | + ICE_SINGLE_ACT_VALID_BIT | + ICE_SINGLE_ACT_DROP; + + return ice_lag_cfg_fltr(lag, act, lag->lport_recipe, + &lag->lport_rule_idx, add); +} + +/** * ice_lag_cfg_pf_fltrs - set filters up for new active port * @lag: local interfaces lag struct * @ptr: opaque data containing notifier event @@ -257,13 +293,18 @@ ice_lag_cfg_pf_fltrs(struct ice_lag *lag, void *ptr) if (bonding_info->slave.state && lag->pf_rule_id) { if (ice_lag_cfg_dflt_fltr(lag, false)) dev_err(dev, "Error removing old default VSI filter\n"); + if (ice_lag_cfg_drop_fltr(lag, true)) + dev_err(dev, "Error adding new drop filter\n"); return; } /* interface becoming active - add new default VSI rule */ - if (!bonding_info->slave.state && !lag->pf_rule_id) + if (!bonding_info->slave.state && !lag->pf_rule_id) { if (ice_lag_cfg_dflt_fltr(lag, true)) dev_err(dev, "Error adding new default VSI filter\n"); + if (lag->lport_rule_idx && ice_lag_cfg_drop_fltr(lag, false)) + dev_err(dev, "Error removing old drop filter\n"); + } } /** @@ -1179,6 +1220,7 @@ static void ice_lag_changeupper_event(struct ice_lag *lag, void *ptr) swid = primary_lag->pf->hw.port_info->sw_id; ice_lag_set_swid(swid, lag, true); ice_lag_add_prune_list(primary_lag, lag->pf); + ice_lag_cfg_drop_fltr(lag, true); } /* add filter for primary control packets */ ice_lag_cfg_cp_fltr(lag, true); @@ -1929,11 +1971,16 @@ int ice_init_lag(struct ice_pf *pf) goto lag_error; } - err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, ice_dflt_vsi_rcp, - 1); + err = ice_create_lag_recipe(&pf->hw, &lag->pf_recipe, + ice_dflt_vsi_rcp, 1); if (err) goto lag_error; + err = ice_create_lag_recipe(&pf->hw, &lag->lport_recipe, + ice_lport_rcp, 3); + if (err) + goto free_rcp_res; + /* associate recipes to profiles */ for (n = 0; n < ICE_PROFID_IPV6_GTPU_IPV6_TCP_INNER; n++) { err = ice_aq_get_recipe_to_profile(&pf->hw, n, @@ -1942,7 +1989,8 @@ int ice_init_lag(struct ice_pf *pf) continue; if (recipe_bits & BIT(ICE_SW_LKUP_DFLT)) { - recipe_bits |= BIT(lag->pf_recipe); + recipe_bits |= BIT(lag->pf_recipe) | + BIT(lag->lport_recipe); ice_aq_map_recipe_to_profile(&pf->hw, n, (u8 *)&recipe_bits, NULL); } @@ -1953,6 +2001,9 @@ int ice_init_lag(struct ice_pf *pf) dev_dbg(dev, "INIT LAG complete\n"); return 0; +free_rcp_res: + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->pf_recipe); lag_error: kfree(lag); pf->lag = NULL; @@ -1982,6 +2033,8 @@ void ice_deinit_lag(struct ice_pf *pf) ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, &pf->lag->pf_recipe); + ice_free_hw_res(&pf->hw, ICE_AQC_RES_TYPE_RECIPE, 1, + &pf->lag->lport_recipe); kfree(lag); diff --git a/drivers/net/ethernet/intel/ice/ice_lag.h b/drivers/net/ethernet/intel/ice/ice_lag.h index facb6c894b6d..9557e8605a07 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.h +++ b/drivers/net/ethernet/intel/ice/ice_lag.h @@ -39,8 +39,10 @@ struct ice_lag { u8 bonded:1; /* currently bonded */ u8 primary:1; /* this is primary */ u16 pf_recipe; + u16 lport_recipe; u16 pf_rule_id; u16 cp_rule_idx; + u16 lport_rule_idx; u8 role; }; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 1f45f0c3963d..4b1e56396293 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -229,7 +229,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) * of queues vectors, subtract 1 (ICE_NONQ_VECS_VF) from the * original vector count */ - vsi->num_q_vectors = pf->vfs.num_msix_per - ICE_NONQ_VECS_VF; + vsi->num_q_vectors = vf->num_msix - ICE_NONQ_VECS_VF; break; case ICE_VSI_CTRL: vsi->alloc_txq = 1; @@ -1201,8 +1201,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) ctxt->info.q_opt_rss = ((lut_type << ICE_AQ_VSI_Q_OPT_RSS_LUT_S) & ICE_AQ_VSI_Q_OPT_RSS_LUT_M) | - ((hash_type << ICE_AQ_VSI_Q_OPT_RSS_HASH_S) & - ICE_AQ_VSI_Q_OPT_RSS_HASH_M); + (hash_type & ICE_AQ_VSI_Q_OPT_RSS_HASH_M); } static void diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index c726913bc635..b67c806a5a4d 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -6,6 +6,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <generated/utsrelease.h> +#include <linux/crash_dump.h> #include "ice.h" #include "ice_base.h" #include "ice_lib.h" @@ -4687,6 +4688,9 @@ static void ice_init_features(struct ice_pf *pf) static void ice_deinit_features(struct ice_pf *pf) { + if (ice_is_safe_mode(pf)) + return; + ice_deinit_lag(pf); if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags)) ice_cfg_lldp_mib_change(&pf->hw, false); @@ -5020,6 +5024,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) return -EINVAL; } + /* when under a kdump kernel initiate a reset before enabling the + * device in order to clear out any pending DMA transactions. These + * transactions can cause some systems to machine check when doing + * the pcim_enable_device() below. + */ + if (is_kdump_kernel()) { + pci_save_state(pdev); + pci_clear_master(pdev); + err = pcie_flr(pdev); + if (err) + return err; + pci_restore_state(pdev); + } + /* this driver uses devres, see * Documentation/driver-api/driver-model/devres.rst */ @@ -5523,7 +5541,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev) return; } - ice_restore_all_vfs_msi_state(pdev); + ice_restore_all_vfs_msi_state(pf); ice_do_reset(pf, ICE_RESET_PFR); ice_service_task_restart(pf); @@ -5617,6 +5635,8 @@ static struct pci_driver ice_driver = { #endif /* CONFIG_PM */ .shutdown = ice_shutdown, .sriov_configure = ice_sriov_configure, + .sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix, + .sriov_set_msix_vec_count = ice_sriov_set_msix_vec_count, .err_handler = &ice_pci_err_handler }; @@ -5633,6 +5653,8 @@ static int __init ice_module_init(void) pr_info("%s\n", ice_driver_string); pr_info("%s\n", ice_copyright); + ice_adv_lnk_speed_maps_init(); + ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME); if (!ice_wq) { pr_err("Failed to create workqueue\n"); diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index 5293df2d57a8..1eddcbe89b0c 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -39,8 +39,8 @@ ice_get_sma_config_e810t(struct ice_hw *hw, struct ptp_pin_desc *ptp_pins) /* initialize with defaults */ for (i = 0; i < NUM_PTP_PINS_E810T; i++) { - snprintf(ptp_pins[i].name, sizeof(ptp_pins[i].name), - "%s", ice_pin_desc_e810t[i].name); + strscpy(ptp_pins[i].name, ice_pin_desc_e810t[i].name, + sizeof(ptp_pins[i].name)); ptp_pins[i].index = ice_pin_desc_e810t[i].index; ptp_pins[i].func = ice_pin_desc_e810t[i].func; ptp_pins[i].chan = ice_pin_desc_e810t[i].chan; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index de16cf14c4b2..6d573908de7a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -3564,7 +3564,7 @@ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) * * 0 - success * * negative - failure */ -int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) +static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) { struct ice_aqc_get_link_topo cmd; u8 node_part_number; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 18a993134826..36aeeef99ec0 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -271,7 +271,6 @@ int ice_read_sma_ctrl_e810t(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl_e810t(struct ice_hw *hw, u8 data); int ice_read_pca9575_reg_e810t(struct ice_hw *hw, u8 offset, u8 *data); bool ice_is_pca9575_present(struct ice_hw *hw); -int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx); enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); struct dpll_pin_frequency * ice_cgu_get_pin_freq_supp(struct ice_hw *hw, u8 pin, bool input, u8 *num); diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 31314e7540f8..2a5e6616cc0a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -64,7 +64,7 @@ static void ice_free_vf_res(struct ice_vf *vf) vf->num_mac = 0; } - last_vector_idx = vf->first_vector_idx + pf->vfs.num_msix_per - 1; + last_vector_idx = vf->first_vector_idx + vf->num_msix - 1; /* clear VF MDD event information */ memset(&vf->mdd_tx_events, 0, sizeof(vf->mdd_tx_events)); @@ -102,7 +102,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0); first = vf->first_vector_idx; - last = first + pf->vfs.num_msix_per - 1; + last = first + vf->num_msix - 1; for (v = first; v <= last; v++) { u32 reg; @@ -138,6 +138,8 @@ static int ice_sriov_free_msix_res(struct ice_pf *pf) if (!pf) return -EINVAL; + bitmap_free(pf->sriov_irq_bm); + pf->sriov_irq_size = 0; pf->sriov_base_vector = 0; return 0; @@ -244,22 +246,6 @@ static struct ice_vsi *ice_vf_vsi_setup(struct ice_vf *vf) return vsi; } -/** - * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space - * @pf: pointer to PF structure - * @vf: pointer to VF that the first MSIX vector index is being calculated for - * - * This returns the first MSIX vector index in PF space that is used by this VF. - * This index is used when accessing PF relative registers such as - * GLINT_VECT2FUNC and GLINT_DYN_CTL. - * This will always be the OICR index in the AVF driver so any functionality - * using vf->first_vector_idx for queue configuration will have to increment by - * 1 to avoid meddling with the OICR index. - */ -static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf) -{ - return pf->sriov_base_vector + vf->vf_id * pf->vfs.num_msix_per; -} /** * ice_ena_vf_msix_mappings - enable VF MSIX mappings in hardware @@ -280,12 +266,12 @@ static void ice_ena_vf_msix_mappings(struct ice_vf *vf) hw = &pf->hw; pf_based_first_msix = vf->first_vector_idx; - pf_based_last_msix = (pf_based_first_msix + pf->vfs.num_msix_per) - 1; + pf_based_last_msix = (pf_based_first_msix + vf->num_msix) - 1; device_based_first_msix = pf_based_first_msix + pf->hw.func_caps.common_cap.msix_vector_first_id; device_based_last_msix = - (device_based_first_msix + pf->vfs.num_msix_per) - 1; + (device_based_first_msix + vf->num_msix) - 1; device_based_vf_id = vf->vf_id + hw->func_caps.vf_base_id; reg = (((device_based_first_msix << VPINT_ALLOC_FIRST_S) & @@ -527,6 +513,52 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) } /** + * ice_sriov_get_irqs - get irqs for SR-IOV usacase + * @pf: pointer to PF structure + * @needed: number of irqs to get + * + * This returns the first MSI-X vector index in PF space that is used by this + * VF. This index is used when accessing PF relative registers such as + * GLINT_VECT2FUNC and GLINT_DYN_CTL. + * This will always be the OICR index in the AVF driver so any functionality + * using vf->first_vector_idx for queue configuration_id: id of VF which will + * use this irqs + * + * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are + * allocated from the end of global irq index. First bit in sriov_irq_bm means + * last irq index etc. It simplifies extension of SRIOV vectors. + * They will be always located from sriov_base_vector to the last irq + * index. While increasing/decreasing sriov_base_vector can be moved. + */ +static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed) +{ + int res = bitmap_find_next_zero_area(pf->sriov_irq_bm, + pf->sriov_irq_size, 0, needed, 0); + /* conversion from number in bitmap to global irq index */ + int index = pf->sriov_irq_size - res - needed; + + if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector) + return -ENOENT; + + bitmap_set(pf->sriov_irq_bm, res, needed); + return index; +} + +/** + * ice_sriov_free_irqs - free irqs used by the VF + * @pf: pointer to PF structure + * @vf: pointer to VF structure + */ +static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf) +{ + /* Move back from first vector index to first index in bitmap */ + int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix; + + bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix); + vf->first_vector_idx = 0; +} + +/** * ice_init_vf_vsi_res - initialize/setup VF VSI resources * @vf: VF to initialize/setup the VSI for * @@ -539,7 +571,9 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) struct ice_vsi *vsi; int err; - vf->first_vector_idx = ice_calc_vf_first_vector_idx(pf, vf); + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + return -ENOMEM; vsi = ice_vf_vsi_setup(vf); if (!vsi) @@ -789,14 +823,19 @@ static const struct ice_vf_ops ice_sriov_vf_ops = { */ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) { + struct pci_dev *pdev = pf->pdev; struct ice_vfs *vfs = &pf->vfs; + struct pci_dev *vfdev = NULL; struct ice_vf *vf; - u16 vf_id; - int err; + u16 vf_pdev_id; + int err, pos; lockdep_assert_held(&vfs->table_lock); - for (vf_id = 0; vf_id < num_vfs; vf_id++) { + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_pdev_id); + + for (u16 vf_id = 0; vf_id < num_vfs; vf_id++) { vf = kzalloc(sizeof(*vf), GFP_KERNEL); if (!vf) { err = -ENOMEM; @@ -812,11 +851,28 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs) ice_initialize_vf_entry(vf); + do { + vfdev = pci_get_device(pdev->vendor, vf_pdev_id, vfdev); + } while (vfdev && vfdev->physfn != pdev); + vf->vfdev = vfdev; vf->vf_sw_id = pf->first_sw; + pci_dev_get(vfdev); + + /* set default number of MSI-X */ + vf->num_msix = pf->vfs.num_msix_per; + vf->num_vf_qs = pf->vfs.num_qps_per; + ice_vc_set_default_allowlist(vf); + hash_add_rcu(vfs->table, &vf->entry, vf_id); } + /* Decrement of refcount done by pci_get_device() inside the loop does + * not touch the last iteration's vfdev, so it has to be done manually + * to balance pci_dev_get() added within the loop. + */ + pci_dev_put(vfdev); + return 0; err_free_entries: @@ -831,10 +887,16 @@ err_free_entries: */ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) { + int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int ret; + pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL); + if (!pf->sriov_irq_bm) + return -ENOMEM; + pf->sriov_irq_size = total_vectors; + /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); @@ -893,6 +955,7 @@ err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); clear_bit(ICE_OICR_INTR_DIS, pf->state); + bitmap_free(pf->sriov_irq_bm); return ret; } @@ -957,6 +1020,175 @@ static int ice_check_sriov_allowed(struct ice_pf *pf) } /** + * ice_sriov_get_vf_total_msix - return number of MSI-X used by VFs + * @pdev: pointer to pci_dev struct + * + * The function is called via sysfs ops + */ +u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) +{ + struct ice_pf *pf = pci_get_drvdata(pdev); + + return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf); +} + +static int ice_sriov_move_base_vector(struct ice_pf *pf, int move) +{ + if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf)) + return -ENOMEM; + + pf->sriov_base_vector -= move; + return 0; +} + +static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) +{ + u16 vf_ids[ICE_MAX_SRIOV_VFS]; + struct ice_vf *tmp_vf; + int to_remap = 0, bkt; + + /* For better irqs usage try to remap irqs of VFs + * that aren't running yet + */ + ice_for_each_vf(pf, bkt, tmp_vf) { + /* skip VF which is changing the number of MSI-X */ + if (restricted_id == tmp_vf->vf_id || + test_bit(ICE_VF_STATE_ACTIVE, tmp_vf->vf_states)) + continue; + + ice_dis_vf_mappings(tmp_vf); + ice_sriov_free_irqs(pf, tmp_vf); + + vf_ids[to_remap] = tmp_vf->vf_id; + to_remap += 1; + } + + for (int i = 0; i < to_remap; i++) { + tmp_vf = ice_get_vf_by_id(pf, vf_ids[i]); + if (!tmp_vf) + continue; + + tmp_vf->first_vector_idx = + ice_sriov_get_irqs(pf, tmp_vf->num_msix); + /* there is no need to rebuild VSI as we are only changing the + * vector indexes not amount of MSI-X or queues + */ + ice_ena_vf_mappings(tmp_vf); + ice_put_vf(tmp_vf); + } +} + +/** + * ice_sriov_set_msix_vec_count + * @vf_dev: pointer to pci_dev struct of VF device + * @msix_vec_count: new value for MSI-X amount on this VF + * + * Set requested MSI-X, queues and registers for @vf_dev. + * + * First do some sanity checks like if there are any VFs, if the new value + * is correct etc. Then disable old mapping (MSI-X and queues registers), change + * MSI-X and queues, rebuild VSI and enable new mapping. + * + * If it is possible (driver not binded to VF) try to remap also other VFs to + * linearize irqs register usage. + */ +int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) +{ + struct pci_dev *pdev = pci_physfn(vf_dev); + struct ice_pf *pf = pci_get_drvdata(pdev); + u16 prev_msix, prev_queues, queues; + bool needs_rebuild = false; + struct ice_vf *vf; + int id; + + if (!ice_get_num_vfs(pf)) + return -ENOENT; + + if (!msix_vec_count) + return 0; + + queues = msix_vec_count; + /* add 1 MSI-X for OICR */ + msix_vec_count += 1; + + if (queues > min(ice_get_avail_txq_count(pf), + ice_get_avail_rxq_count(pf))) + return -EINVAL; + + if (msix_vec_count < ICE_MIN_INTR_PER_VF) + return -EINVAL; + + /* Transition of PCI VF function number to function_id */ + for (id = 0; id < pci_num_vf(pdev); id++) { + if (vf_dev->devfn == pci_iov_virtfn_devfn(pdev, id)) + break; + } + + if (id == pci_num_vf(pdev)) + return -ENOENT; + + vf = ice_get_vf_by_id(pf, id); + + if (!vf) + return -ENOENT; + + prev_msix = vf->num_msix; + prev_queues = vf->num_vf_qs; + + if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) { + ice_put_vf(vf); + return -ENOSPC; + } + + ice_dis_vf_mappings(vf); + ice_sriov_free_irqs(pf, vf); + + /* Remap all VFs beside the one is now configured */ + ice_sriov_remap_vectors(pf, vf->vf_id); + + vf->num_msix = msix_vec_count; + vf->num_vf_qs = queues; + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + goto unroll; + + ice_vf_vsi_release(vf); + if (vf->vf_ops->create_vsi(vf)) { + /* Try to rebuild with previous values */ + needs_rebuild = true; + goto unroll; + } + + dev_info(ice_pf_to_dev(pf), + "Changing VF %d resources to %d vectors and %d queues\n", + vf->vf_id, vf->num_msix, vf->num_vf_qs); + + ice_ena_vf_mappings(vf); + ice_put_vf(vf); + + return 0; + +unroll: + dev_info(ice_pf_to_dev(pf), + "Can't set %d vectors on VF %d, falling back to %d\n", + vf->num_msix, vf->vf_id, prev_msix); + + vf->num_msix = prev_msix; + vf->num_vf_qs = prev_queues; + vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + if (vf->first_vector_idx < 0) + return -EINVAL; + + if (needs_rebuild) + vf->vf_ops->create_vsi(vf); + + ice_ena_vf_mappings(vf); + ice_put_vf(vf); + + return -EINVAL; +} + +/** * ice_sriov_configure - Enable or change number of VFs via sysfs * @pdev: pointer to a pci_dev structure * @num_vfs: number of VFs to allocate or 0 to free VFs @@ -1709,31 +1941,16 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf) /** * ice_restore_all_vfs_msi_state - restore VF MSI state after PF FLR - * @pdev: pointer to a pci_dev structure + * @pf: pointer to the PF structure * * Called when recovering from a PF FLR to restore interrupt capability to * the VFs. */ -void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) +void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { - u16 vf_id; - int pos; - - if (!pci_num_vf(pdev)) - return; + struct ice_vf *vf; + u32 bkt; - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); - if (pos) { - struct pci_dev *vfdev; - - pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, - &vf_id); - vfdev = pci_get_device(pdev->vendor, vf_id, NULL); - while (vfdev) { - if (vfdev->is_virtfn && vfdev->physfn == pdev) - pci_restore_msi_state(vfdev); - vfdev = pci_get_device(pdev->vendor, vf_id, - vfdev); - } - } + ice_for_each_vf(pf, bkt, vf) + pci_restore_msi_state(vf->vfdev); } diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 346cb2666f3a..8488df38b586 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -33,7 +33,7 @@ int ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); void ice_free_vfs(struct ice_pf *pf); -void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); +void ice_restore_all_vfs_msi_state(struct ice_pf *pf); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -60,6 +60,8 @@ void ice_print_vfs_mdd_events(struct ice_pf *pf); void ice_print_vf_rx_mdd_event(struct ice_vf *vf); bool ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto); +u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev); +int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count); #else /* CONFIG_PCI_IOV */ static inline void ice_process_vflr_event(struct ice_pf *pf) { } static inline void ice_free_vfs(struct ice_pf *pf) { } @@ -67,7 +69,7 @@ static inline void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } -static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { } +static inline void ice_restore_all_vfs_msi_state(struct ice_pf *pf) { } static inline int ice_sriov_configure(struct pci_dev __always_unused *pdev, @@ -142,5 +144,16 @@ ice_get_vf_stats(struct net_device __always_unused *netdev, { return -EOPNOTSUPP; } + +static inline u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) +{ + return 0; +} + +static inline int +ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 24e4f4d897b6..aca1f2ea5034 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -56,6 +56,8 @@ static void ice_release_vf(struct kref *ref) { struct ice_vf *vf = container_of(ref, struct ice_vf, refcnt); + pci_dev_put(vf->vfdev); + vf->vf_ops->free(vf); } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 31a082e8a827..93c774f2f437 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -72,7 +72,7 @@ struct ice_vfs { struct mutex table_lock; /* Lock for protecting the hash table */ u16 num_supported; /* max supported VFs on this PF */ u16 num_qps_per; /* number of queue pairs per VF */ - u16 num_msix_per; /* number of MSI-X vectors per VF */ + u16 num_msix_per; /* default MSI-X vectors per VF */ unsigned long last_printed_mdd_jiffies; /* MDD message rate limit */ }; @@ -82,7 +82,7 @@ struct ice_vf { struct rcu_head rcu; struct kref refcnt; struct ice_pf *pf; - + struct pci_dev *vfdev; /* Used during virtchnl message handling and NDO ops against the VF * that will trigger a VFR */ @@ -136,6 +136,8 @@ struct ice_vf { /* devlink port data */ struct devlink_port devlink_port; + + u16 num_msix; /* num of MSI-X configured on this VF */ }; /* Flags for controlling behavior of ice_reset_vf */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index 01e88b6e43a1..cdf17b1e2f25 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -501,7 +501,7 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; - vfres->max_vectors = vf->pf->vfs.num_msix_per; + vfres->max_vectors = vf->num_msix; vfres->rss_key_size = ICE_VSIQF_HKEY_ARRAY_SIZE; vfres->rss_lut_size = ICE_LUT_VSI_SIZE; vfres->max_mtu = ice_vc_get_max_frame_size(vf); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 6fa79898c42c..5e1ef70d54fe 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -595,9 +595,6 @@ static struct page_pool *idpf_rx_create_page_pool(struct idpf_queue *rxbufq) .offset = 0, }; - if (rxbufq->rx_buf_size == IDPF_RX_BUF_2048) - pp.flags |= PP_FLAG_PAGE_FRAG; - return page_pool_create(&pp); } @@ -1160,6 +1157,7 @@ static void idpf_rxq_set_descids(struct idpf_vport *vport, struct idpf_queue *q) */ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) { + bool flow_sch_en; int err, i; vport->txq_grps = kcalloc(vport->num_txq_grp, @@ -1167,6 +1165,9 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) if (!vport->txq_grps) return -ENOMEM; + flow_sch_en = !idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, + VIRTCHNL2_CAP_SPLITQ_QSCHED); + for (i = 0; i < vport->num_txq_grp; i++) { struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; struct idpf_adapter *adapter = vport->adapter; @@ -1195,8 +1196,7 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) q->txq_grp = tx_qgrp; hash_init(q->sched_buf_hash); - if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, - VIRTCHNL2_CAP_SPLITQ_QSCHED)) + if (flow_sch_en) set_bit(__IDPF_Q_FLOW_SCH_EN, q->flags); } @@ -1215,6 +1215,9 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq) tx_qgrp->complq->desc_count = vport->complq_desc_count; tx_qgrp->complq->vport = vport; tx_qgrp->complq->txq_grp = tx_qgrp; + + if (flow_sch_en) + __set_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags); } return 0; diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c index 9bc85b2f1709..2c1b051fdc0d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c +++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c @@ -1473,7 +1473,7 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) /* Populate the queue info buffer with all queue context info */ for (i = 0; i < vport->num_txq_grp; i++) { struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i]; - int j; + int j, sched_mode; for (j = 0; j < tx_qgrp->num_txq; j++, k++) { qi[k].queue_id = @@ -1514,6 +1514,12 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport) qi[k].ring_len = cpu_to_le16(tx_qgrp->complq->desc_count); qi[k].dma_ring_addr = cpu_to_le64(tx_qgrp->complq->dma); + if (test_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags)) + sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_FLOW; + else + sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE; + qi[k].sched_mode = cpu_to_le16(sched_mode); + k++; } @@ -3140,6 +3146,7 @@ restart: err_intr_req: cancel_delayed_work_sync(&adapter->serv_task); + cancel_delayed_work_sync(&adapter->mbx_task); idpf_vport_params_buf_rel(adapter); err_netdev_alloc: kfree(adapter->vports); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 319ed601eaa1..16d2a55d5e17 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2356,10 +2356,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) break; case ETH_SS_STATS: for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", igb_gstrings_stats[i].stat_string); for (i = 0; i < IGB_NETDEV_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", igb_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); @@ -2978,11 +2978,15 @@ static int igb_add_ethtool_nfc_entry(struct igb_adapter *adapter, if (err) goto err_out_w_lock; - igb_update_ethtool_nfc_entry(adapter, input, input->sw_idx); + err = igb_update_ethtool_nfc_entry(adapter, input, input->sw_idx); + if (err) + goto err_out_input_filter; spin_unlock(&adapter->nfc_lock); return 0; +err_out_input_filter: + igb_erase_filter(adapter, input); err_out_w_lock: spin_unlock(&adapter->nfc_lock); err_out: diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 2ac9dffd0bf8..b2295caa2f0a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -3069,6 +3069,7 @@ void igb_set_fw_version(struct igb_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_fw_version fw; + char *lbuf; igb_get_fw_version(hw, &fw); @@ -3076,36 +3077,34 @@ void igb_set_fw_version(struct igb_adapter *adapter) case e1000_i210: case e1000_i211: if (!(igb_get_flash_presence_i210(hw))) { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%2d.%2d-%d", - fw.invm_major, fw.invm_minor, - fw.invm_img_type); + lbuf = kasprintf(GFP_KERNEL, "%2d.%2d-%d", + fw.invm_major, fw.invm_minor, + fw.invm_img_type); break; } fallthrough; default: - /* if option is rom valid, display its version too */ + /* if option rom is valid, display its version too */ if (fw.or_valid) { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d, 0x%08x, %d.%d.%d", - fw.eep_major, fw.eep_minor, fw.etrack_id, - fw.or_major, fw.or_build, fw.or_patch); + lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x, %d.%d.%d", + fw.eep_major, fw.eep_minor, + fw.etrack_id, fw.or_major, fw.or_build, + fw.or_patch); /* no option rom */ } else if (fw.etrack_id != 0X0000) { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d, 0x%08x", - fw.eep_major, fw.eep_minor, fw.etrack_id); + lbuf = kasprintf(GFP_KERNEL, "%d.%d, 0x%08x", + fw.eep_major, fw.eep_minor, + fw.etrack_id); } else { - snprintf(adapter->fw_version, - sizeof(adapter->fw_version), - "%d.%d.%d", - fw.eep_major, fw.eep_minor, fw.eep_build); + lbuf = kasprintf(GFP_KERNEL, "%d.%d.%d", fw.eep_major, + fw.eep_minor, fw.eep_build); } break; } + + /* the truncate happens here if it doesn't fit */ + strscpy(adapter->fw_version, lbuf, sizeof(adapter->fw_version)); + kfree(lbuf); } /** @@ -3264,7 +3263,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) igb_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); netdev->mem_start = pci_resource_start(pdev, 0); netdev->mem_end = pci_resource_end(pdev, 0); @@ -7857,7 +7856,8 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, { struct pci_dev *pdev = adapter->pdev; struct vf_data_storage *vf_data = &adapter->vf_data[vf]; - struct vf_mac_filter *entry = NULL; + struct vf_mac_filter *entry; + bool found = false; int ret = 0; if ((vf_data->flags & IGB_VF_FLAG_PF_SET_MAC) && @@ -7888,11 +7888,13 @@ static int igb_set_vf_mac_filter(struct igb_adapter *adapter, const int vf, case E1000_VF_MAC_FILTER_ADD: /* try to find empty slot in the list */ list_for_each_entry(entry, &adapter->vf_macs.l, l) { - if (entry->free) + if (entry->free) { + found = true; break; + } } - if (entry && entry->free) { + if (found) { entry->free = false; entry->vf = vf; ether_addr_copy(entry->vf_mac, addr); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 7ff2752dd763..fd712585af27 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2785,7 +2785,7 @@ static int igbvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) igbvf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); + strscpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); adapter->bd_number = cards_found++; diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 7ab6dd58e400..785eaa8e0ba8 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -773,9 +773,10 @@ static void igc_ethtool_get_strings(struct net_device *netdev, u32 stringset, break; case ETH_SS_STATS: for (i = 0; i < IGC_GLOBAL_STATS_LEN; i++) - ethtool_sprintf(&p, igc_gstrings_stats[i].stat_string); + ethtool_sprintf(&p, "%s", + igc_gstrings_stats[i].stat_string); for (i = 0; i < IGC_NETDEV_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", igc_gstrings_net_stats[i].stat_string); for (i = 0; i < adapter->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); @@ -1817,7 +1818,7 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, struct igc_adapter *adapter = netdev_priv(netdev); struct net_device *dev = adapter->netdev; struct igc_hw *hw = &adapter->hw; - u32 advertising; + u16 advertised = 0; /* When adapter in resetting mode, autoneg/speed/duplex * cannot be changed @@ -1842,18 +1843,33 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, while (test_and_set_bit(__IGC_RESETTING, &adapter->state)) usleep_range(1000, 2000); - ethtool_convert_link_mode_to_legacy_u32(&advertising, - cmd->link_modes.advertising); - /* Converting to legacy u32 drops ETHTOOL_LINK_MODE_2500baseT_Full_BIT. - * We have to check this and convert it to ADVERTISE_2500_FULL - * (aka ETHTOOL_LINK_MODE_2500baseX_Full_BIT) explicitly. - */ - if (ethtool_link_ksettings_test_link_mode(cmd, advertising, 2500baseT_Full)) - advertising |= ADVERTISE_2500_FULL; + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 2500baseT_Full)) + advertised |= ADVERTISE_2500_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 1000baseT_Full)) + advertised |= ADVERTISE_1000_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 100baseT_Full)) + advertised |= ADVERTISE_100_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 100baseT_Half)) + advertised |= ADVERTISE_100_HALF; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10baseT_Full)) + advertised |= ADVERTISE_10_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10baseT_Half)) + advertised |= ADVERTISE_10_HALF; if (cmd->base.autoneg == AUTONEG_ENABLE) { hw->mac.autoneg = 1; - hw->phy.autoneg_advertised = advertising; + hw->phy.autoneg_advertised = advertised; if (adapter->fc_autoneg) hw->fc.requested_mode = igc_fc_default; } else { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 98de34d0ce07..e9bb403bbacf 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -6935,7 +6935,7 @@ static int igc_probe(struct pci_dev *pdev, */ igc_get_hw_control(adapter); - strncpy(netdev->name, "eth%d", IFNAMSIZ); + strscpy(netdev->name, "eth%d", sizeof(netdev->name)); err = register_netdev(netdev); if (err) goto err_register; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 0bbad4a5cc2f..4dd897806fa5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1413,11 +1413,11 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, switch (stringset) { case ETH_SS_TEST: for (i = 0; i < IXGBE_TEST_LEN; i++) - ethtool_sprintf(&p, ixgbe_gstrings_test[i]); + ethtool_sprintf(&p, "%s", ixgbe_gstrings_test[i]); break; case ETH_SS_STATS: for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) - ethtool_sprintf(&p, + ethtool_sprintf(&p, "%s", ixgbe_gstrings_stats[i].stat_string); for (i = 0; i < netdev->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index cd593f5719e1..9cfdfa8a4355 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -640,6 +640,7 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, int vf, int index, unsigned char *mac_addr) { struct vf_macvlans *entry; + bool found = false; int retval = 0; if (index <= 1) { @@ -661,22 +662,22 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, if (!index) return 0; - entry = NULL; - list_for_each_entry(entry, &adapter->vf_mvs.l, l) { - if (entry->free) + if (entry->free) { + found = true; break; + } } /* * If we traversed the entire list and didn't find a free entry - * then we're out of space on the RAR table. Also entry may - * be NULL because the original memory allocation for the list - * failed, which is not fatal but does mean we can't support - * VF requests for MACVLAN because we couldn't allocate - * memory for the list management required. + * then we're out of space on the RAR table. It's also possible + * for the &adapter->vf_mvs.l list to be empty because the original + * memory allocation for the list failed, which is not fatal but does + * mean we can't support VF requests for MACVLAN because we couldn't + * allocate memory for the list management required. */ - if (!entry || !entry->free) + if (!found) return -ENOSPC; retval = ixgbe_add_mac_filter(adapter, mac_addr, vf); diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c index 7a386af041ec..552970c7dec0 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_main.c +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_main.c @@ -898,20 +898,19 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb, hw_desc->dptr = tx_buffer->sglist_dma; } - /* Flush the hw descriptor before writing to doorbell */ - wmb(); - - /* Ring Doorbell to notify the NIC there is a new packet */ - writel(1, iq->doorbell_reg); + netdev_tx_sent_queue(iq->netdev_q, skb->len); + skb_tx_timestamp(skb); atomic_inc(&iq->instr_pending); wi++; if (wi == iq->max_count) wi = 0; iq->host_write_index = wi; + /* Flush the hw descriptor before writing to doorbell */ + wmb(); - netdev_tx_sent_queue(iq->netdev_q, skb->len); + /* Ring Doorbell to notify the NIC there is a new packet */ + writel(1, iq->doorbell_reg); iq->stats.instr_posted++; - skb_tx_timestamp(skb); return NETDEV_TX_OK; dma_map_sg_err: diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h index 782a24f27f3e..49feae80d7d2 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_rx.h @@ -20,6 +20,7 @@ struct octep_oq_desc_hw { dma_addr_t buffer_ptr; u64 info_ptr; }; +static_assert(sizeof(struct octep_oq_desc_hw) == 16); #define OCTEP_OQ_DESC_SIZE (sizeof(struct octep_oq_desc_hw)) @@ -39,6 +40,7 @@ struct octep_oq_resp_hw_ext { /* checksum verified. */ u64 csum_verified:2; }; +static_assert(sizeof(struct octep_oq_resp_hw_ext) == 8); #define OCTEP_OQ_RESP_HW_EXT_SIZE (sizeof(struct octep_oq_resp_hw_ext)) @@ -50,6 +52,7 @@ struct octep_oq_resp_hw { /* The Length of the packet. */ __be64 length; }; +static_assert(sizeof(struct octep_oq_resp_hw) == 8); #define OCTEP_OQ_RESP_HW_SIZE (sizeof(struct octep_oq_resp_hw)) diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h index 21e75ff9f5e7..86c98b13fc44 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_tx.h @@ -36,6 +36,7 @@ struct octep_tx_sglist_desc { u16 len[4]; dma_addr_t dma_ptr[4]; }; +static_assert(sizeof(struct octep_tx_sglist_desc) == 40); /* Each Scatter/Gather entry sent to hardwar hold four pointers. * So, number of entries required is (MAX_SKB_FRAGS + 1)/4, where '+1' @@ -239,6 +240,7 @@ struct octep_instr_hdr { /* Reserved3 */ u64 reserved3:1; }; +static_assert(sizeof(struct octep_instr_hdr) == 8); /* Hardware Tx completion response header */ struct octep_instr_resp_hdr { @@ -263,6 +265,7 @@ struct octep_instr_resp_hdr { /* Opcode for the return packet */ u64 opcode:16; }; +static_assert(sizeof(struct octep_instr_hdr) == 8); /* 64-byte Tx instruction format. * Format of instruction for a 64-byte mode input queue. @@ -293,6 +296,7 @@ struct octep_tx_desc_hw { /* Additional headers available in a 64-byte instruction. */ u64 exhdr[4]; }; +static_assert(sizeof(struct octep_tx_desc_hw) == 64); #define OCTEP_IQ_DESC_SIZE (sizeof(struct octep_tx_desc_hw)) #endif /* _OCTEP_TX_H_ */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c index 41df5ac23f92..c70932625d0d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_devlink.c @@ -14,26 +14,16 @@ #define DRV_NAME "octeontx2-af" -static int rvu_report_pair_start(struct devlink_fmsg *fmsg, const char *name) +static void rvu_report_pair_start(struct devlink_fmsg *fmsg, const char *name) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - return devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_obj_nest_start(fmsg); } -static int rvu_report_pair_end(struct devlink_fmsg *fmsg) +static void rvu_report_pair_end(struct devlink_fmsg *fmsg) { - int err; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - - return devlink_fmsg_pair_nest_end(fmsg); + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); } static bool rvu_common_request_irq(struct rvu *rvu, int offset, @@ -284,175 +274,81 @@ static int rvu_nix_report_show(struct devlink_fmsg *fmsg, void *ctx, { struct rvu_nix_event_ctx *nix_event_context; u64 intr_val; - int err; nix_event_context = ctx; switch (health_reporter) { case NIX_AF_RVU_INTR: intr_val = nix_event_context->nix_af_rvu_int; - err = rvu_report_pair_start(fmsg, "NIX_AF_RVU"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNIX RVU Interrupt Reg ", - nix_event_context->nix_af_rvu_int); - if (err) - return err; - if (intr_val & BIT_ULL(0)) { - err = devlink_fmsg_string_put(fmsg, "\n\tUnmap Slot Error"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + rvu_report_pair_start(fmsg, "NIX_AF_RVU"); + devlink_fmsg_u64_pair_put(fmsg, "\tNIX RVU Interrupt Reg ", + nix_event_context->nix_af_rvu_int); + if (intr_val & BIT_ULL(0)) + devlink_fmsg_string_put(fmsg, "\n\tUnmap Slot Error"); + rvu_report_pair_end(fmsg); break; case NIX_AF_RVU_GEN: intr_val = nix_event_context->nix_af_rvu_gen; - err = rvu_report_pair_start(fmsg, "NIX_AF_GENERAL"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNIX General Interrupt Reg ", - nix_event_context->nix_af_rvu_gen); - if (err) - return err; - if (intr_val & BIT_ULL(0)) { - err = devlink_fmsg_string_put(fmsg, "\n\tRx multicast pkt drop"); - if (err) - return err; - } - if (intr_val & BIT_ULL(1)) { - err = devlink_fmsg_string_put(fmsg, "\n\tRx mirror pkt drop"); - if (err) - return err; - } - if (intr_val & BIT_ULL(4)) { - err = devlink_fmsg_string_put(fmsg, "\n\tSMQ flush done"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + rvu_report_pair_start(fmsg, "NIX_AF_GENERAL"); + devlink_fmsg_u64_pair_put(fmsg, "\tNIX General Interrupt Reg ", + nix_event_context->nix_af_rvu_gen); + if (intr_val & BIT_ULL(0)) + devlink_fmsg_string_put(fmsg, "\n\tRx multicast pkt drop"); + if (intr_val & BIT_ULL(1)) + devlink_fmsg_string_put(fmsg, "\n\tRx mirror pkt drop"); + if (intr_val & BIT_ULL(4)) + devlink_fmsg_string_put(fmsg, "\n\tSMQ flush done"); + rvu_report_pair_end(fmsg); break; case NIX_AF_RVU_ERR: intr_val = nix_event_context->nix_af_rvu_err; - err = rvu_report_pair_start(fmsg, "NIX_AF_ERR"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNIX Error Interrupt Reg ", - nix_event_context->nix_af_rvu_err); - if (err) - return err; - if (intr_val & BIT_ULL(14)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on NIX_AQ_INST_S read"); - if (err) - return err; - } - if (intr_val & BIT_ULL(13)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on NIX_AQ_RES_S write"); - if (err) - return err; - } - if (intr_val & BIT_ULL(12)) { - err = devlink_fmsg_string_put(fmsg, "\n\tAQ Doorbell Error"); - if (err) - return err; - } - if (intr_val & BIT_ULL(6)) { - err = devlink_fmsg_string_put(fmsg, "\n\tRx on unmapped PF_FUNC"); - if (err) - return err; - } - if (intr_val & BIT_ULL(5)) { - err = devlink_fmsg_string_put(fmsg, "\n\tRx multicast replication error"); - if (err) - return err; - } - if (intr_val & BIT_ULL(4)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on NIX_RX_MCE_S read"); - if (err) - return err; - } - if (intr_val & BIT_ULL(3)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on multicast WQE read"); - if (err) - return err; - } - if (intr_val & BIT_ULL(2)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on mirror WQE read"); - if (err) - return err; - } - if (intr_val & BIT_ULL(1)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on mirror pkt write"); - if (err) - return err; - } - if (intr_val & BIT_ULL(0)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on multicast pkt write"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + rvu_report_pair_start(fmsg, "NIX_AF_ERR"); + devlink_fmsg_u64_pair_put(fmsg, "\tNIX Error Interrupt Reg ", + nix_event_context->nix_af_rvu_err); + if (intr_val & BIT_ULL(14)) + devlink_fmsg_string_put(fmsg, "\n\tFault on NIX_AQ_INST_S read"); + if (intr_val & BIT_ULL(13)) + devlink_fmsg_string_put(fmsg, "\n\tFault on NIX_AQ_RES_S write"); + if (intr_val & BIT_ULL(12)) + devlink_fmsg_string_put(fmsg, "\n\tAQ Doorbell Error"); + if (intr_val & BIT_ULL(6)) + devlink_fmsg_string_put(fmsg, "\n\tRx on unmapped PF_FUNC"); + if (intr_val & BIT_ULL(5)) + devlink_fmsg_string_put(fmsg, "\n\tRx multicast replication error"); + if (intr_val & BIT_ULL(4)) + devlink_fmsg_string_put(fmsg, "\n\tFault on NIX_RX_MCE_S read"); + if (intr_val & BIT_ULL(3)) + devlink_fmsg_string_put(fmsg, "\n\tFault on multicast WQE read"); + if (intr_val & BIT_ULL(2)) + devlink_fmsg_string_put(fmsg, "\n\tFault on mirror WQE read"); + if (intr_val & BIT_ULL(1)) + devlink_fmsg_string_put(fmsg, "\n\tFault on mirror pkt write"); + if (intr_val & BIT_ULL(0)) + devlink_fmsg_string_put(fmsg, "\n\tFault on multicast pkt write"); + rvu_report_pair_end(fmsg); break; case NIX_AF_RVU_RAS: intr_val = nix_event_context->nix_af_rvu_err; - err = rvu_report_pair_start(fmsg, "NIX_AF_RAS"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNIX RAS Interrupt Reg ", - nix_event_context->nix_af_rvu_err); - if (err) - return err; - err = devlink_fmsg_string_put(fmsg, "\n\tPoison Data on:"); - if (err) - return err; - if (intr_val & BIT_ULL(34)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_INST_S"); - if (err) - return err; - } - if (intr_val & BIT_ULL(33)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_RES_S"); - if (err) - return err; - } - if (intr_val & BIT_ULL(32)) { - err = devlink_fmsg_string_put(fmsg, "\n\tHW ctx"); - if (err) - return err; - } - if (intr_val & BIT_ULL(4)) { - err = devlink_fmsg_string_put(fmsg, "\n\tPacket from mirror buffer"); - if (err) - return err; - } - if (intr_val & BIT_ULL(3)) { - err = devlink_fmsg_string_put(fmsg, "\n\tPacket from multicast buffer"); - - if (err) - return err; - } - if (intr_val & BIT_ULL(2)) { - err = devlink_fmsg_string_put(fmsg, "\n\tWQE read from mirror buffer"); - if (err) - return err; - } - if (intr_val & BIT_ULL(1)) { - err = devlink_fmsg_string_put(fmsg, "\n\tWQE read from multicast buffer"); - if (err) - return err; - } - if (intr_val & BIT_ULL(0)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX_RX_MCE_S read"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + rvu_report_pair_start(fmsg, "NIX_AF_RAS"); + devlink_fmsg_u64_pair_put(fmsg, "\tNIX RAS Interrupt Reg ", + nix_event_context->nix_af_rvu_err); + devlink_fmsg_string_put(fmsg, "\n\tPoison Data on:"); + if (intr_val & BIT_ULL(34)) + devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_INST_S"); + if (intr_val & BIT_ULL(33)) + devlink_fmsg_string_put(fmsg, "\n\tNIX_AQ_RES_S"); + if (intr_val & BIT_ULL(32)) + devlink_fmsg_string_put(fmsg, "\n\tHW ctx"); + if (intr_val & BIT_ULL(4)) + devlink_fmsg_string_put(fmsg, "\n\tPacket from mirror buffer"); + if (intr_val & BIT_ULL(3)) + devlink_fmsg_string_put(fmsg, "\n\tPacket from multicast buffer"); + if (intr_val & BIT_ULL(2)) + devlink_fmsg_string_put(fmsg, "\n\tWQE read from mirror buffer"); + if (intr_val & BIT_ULL(1)) + devlink_fmsg_string_put(fmsg, "\n\tWQE read from multicast buffer"); + if (intr_val & BIT_ULL(0)) + devlink_fmsg_string_put(fmsg, "\n\tNIX_RX_MCE_S read"); + rvu_report_pair_end(fmsg); break; default: return -EINVAL; @@ -922,181 +818,87 @@ static int rvu_npa_report_show(struct devlink_fmsg *fmsg, void *ctx, struct rvu_npa_event_ctx *npa_event_context; unsigned int alloc_dis, free_dis; u64 intr_val; - int err; npa_event_context = ctx; switch (health_reporter) { case NPA_AF_RVU_GEN: intr_val = npa_event_context->npa_af_rvu_gen; - err = rvu_report_pair_start(fmsg, "NPA_AF_GENERAL"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNPA General Interrupt Reg ", - npa_event_context->npa_af_rvu_gen); - if (err) - return err; - if (intr_val & BIT_ULL(32)) { - err = devlink_fmsg_string_put(fmsg, "\n\tUnmap PF Error"); - if (err) - return err; - } + rvu_report_pair_start(fmsg, "NPA_AF_GENERAL"); + devlink_fmsg_u64_pair_put(fmsg, "\tNPA General Interrupt Reg ", + npa_event_context->npa_af_rvu_gen); + if (intr_val & BIT_ULL(32)) + devlink_fmsg_string_put(fmsg, "\n\tUnmap PF Error"); free_dis = FIELD_GET(GENMASK(15, 0), intr_val); - if (free_dis & BIT(NPA_INPQ_NIX0_RX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX0: free disabled RX"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_NIX0_TX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX0:free disabled TX"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_NIX1_RX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX1: free disabled RX"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_NIX1_TX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX1:free disabled TX"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_SSO)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for SSO"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_TIM)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for TIM"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_DPI)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for DPI"); - if (err) - return err; - } - if (free_dis & BIT(NPA_INPQ_AURA_OP)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for AURA"); - if (err) - return err; - } + if (free_dis & BIT(NPA_INPQ_NIX0_RX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX0: free disabled RX"); + if (free_dis & BIT(NPA_INPQ_NIX0_TX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX0:free disabled TX"); + if (free_dis & BIT(NPA_INPQ_NIX1_RX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX1: free disabled RX"); + if (free_dis & BIT(NPA_INPQ_NIX1_TX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX1:free disabled TX"); + if (free_dis & BIT(NPA_INPQ_SSO)) + devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for SSO"); + if (free_dis & BIT(NPA_INPQ_TIM)) + devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for TIM"); + if (free_dis & BIT(NPA_INPQ_DPI)) + devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for DPI"); + if (free_dis & BIT(NPA_INPQ_AURA_OP)) + devlink_fmsg_string_put(fmsg, "\n\tFree Disabled for AURA"); alloc_dis = FIELD_GET(GENMASK(31, 16), intr_val); - if (alloc_dis & BIT(NPA_INPQ_NIX0_RX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX0: alloc disabled RX"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_NIX0_TX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX0:alloc disabled TX"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_NIX1_RX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX1: alloc disabled RX"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_NIX1_TX)) { - err = devlink_fmsg_string_put(fmsg, "\n\tNIX1:alloc disabled TX"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_SSO)) { - err = devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for SSO"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_TIM)) { - err = devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for TIM"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_DPI)) { - err = devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for DPI"); - if (err) - return err; - } - if (alloc_dis & BIT(NPA_INPQ_AURA_OP)) { - err = devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for AURA"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + if (alloc_dis & BIT(NPA_INPQ_NIX0_RX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX0: alloc disabled RX"); + if (alloc_dis & BIT(NPA_INPQ_NIX0_TX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX0:alloc disabled TX"); + if (alloc_dis & BIT(NPA_INPQ_NIX1_RX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX1: alloc disabled RX"); + if (alloc_dis & BIT(NPA_INPQ_NIX1_TX)) + devlink_fmsg_string_put(fmsg, "\n\tNIX1:alloc disabled TX"); + if (alloc_dis & BIT(NPA_INPQ_SSO)) + devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for SSO"); + if (alloc_dis & BIT(NPA_INPQ_TIM)) + devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for TIM"); + if (alloc_dis & BIT(NPA_INPQ_DPI)) + devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for DPI"); + if (alloc_dis & BIT(NPA_INPQ_AURA_OP)) + devlink_fmsg_string_put(fmsg, "\n\tAlloc Disabled for AURA"); + + rvu_report_pair_end(fmsg); break; case NPA_AF_RVU_ERR: - err = rvu_report_pair_start(fmsg, "NPA_AF_ERR"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNPA Error Interrupt Reg ", - npa_event_context->npa_af_rvu_err); - if (err) - return err; - - if (npa_event_context->npa_af_rvu_err & BIT_ULL(14)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on NPA_AQ_INST_S read"); - if (err) - return err; - } - if (npa_event_context->npa_af_rvu_err & BIT_ULL(13)) { - err = devlink_fmsg_string_put(fmsg, "\n\tFault on NPA_AQ_RES_S write"); - if (err) - return err; - } - if (npa_event_context->npa_af_rvu_err & BIT_ULL(12)) { - err = devlink_fmsg_string_put(fmsg, "\n\tAQ Doorbell Error"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + rvu_report_pair_start(fmsg, "NPA_AF_ERR"); + devlink_fmsg_u64_pair_put(fmsg, "\tNPA Error Interrupt Reg ", + npa_event_context->npa_af_rvu_err); + if (npa_event_context->npa_af_rvu_err & BIT_ULL(14)) + devlink_fmsg_string_put(fmsg, "\n\tFault on NPA_AQ_INST_S read"); + if (npa_event_context->npa_af_rvu_err & BIT_ULL(13)) + devlink_fmsg_string_put(fmsg, "\n\tFault on NPA_AQ_RES_S write"); + if (npa_event_context->npa_af_rvu_err & BIT_ULL(12)) + devlink_fmsg_string_put(fmsg, "\n\tAQ Doorbell Error"); + rvu_report_pair_end(fmsg); break; case NPA_AF_RVU_RAS: - err = rvu_report_pair_start(fmsg, "NPA_AF_RVU_RAS"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNPA RAS Interrupt Reg ", - npa_event_context->npa_af_rvu_ras); - if (err) - return err; - if (npa_event_context->npa_af_rvu_ras & BIT_ULL(34)) { - err = devlink_fmsg_string_put(fmsg, "\n\tPoison data on NPA_AQ_INST_S"); - if (err) - return err; - } - if (npa_event_context->npa_af_rvu_ras & BIT_ULL(33)) { - err = devlink_fmsg_string_put(fmsg, "\n\tPoison data on NPA_AQ_RES_S"); - if (err) - return err; - } - if (npa_event_context->npa_af_rvu_ras & BIT_ULL(32)) { - err = devlink_fmsg_string_put(fmsg, "\n\tPoison data on HW context"); - if (err) - return err; - } - err = rvu_report_pair_end(fmsg); - if (err) - return err; + rvu_report_pair_start(fmsg, "NPA_AF_RVU_RAS"); + devlink_fmsg_u64_pair_put(fmsg, "\tNPA RAS Interrupt Reg ", + npa_event_context->npa_af_rvu_ras); + if (npa_event_context->npa_af_rvu_ras & BIT_ULL(34)) + devlink_fmsg_string_put(fmsg, "\n\tPoison data on NPA_AQ_INST_S"); + if (npa_event_context->npa_af_rvu_ras & BIT_ULL(33)) + devlink_fmsg_string_put(fmsg, "\n\tPoison data on NPA_AQ_RES_S"); + if (npa_event_context->npa_af_rvu_ras & BIT_ULL(32)) + devlink_fmsg_string_put(fmsg, "\n\tPoison data on HW context"); + rvu_report_pair_end(fmsg); break; case NPA_AF_RVU_INTR: - err = rvu_report_pair_start(fmsg, "NPA_AF_RVU"); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "\tNPA RVU Interrupt Reg ", - npa_event_context->npa_af_rvu_int); - if (err) - return err; - if (npa_event_context->npa_af_rvu_int & BIT_ULL(0)) { - err = devlink_fmsg_string_put(fmsg, "\n\tUnmap Slot Error"); - if (err) - return err; - } - return rvu_report_pair_end(fmsg); + rvu_report_pair_start(fmsg, "NPA_AF_RVU"); + devlink_fmsg_u64_pair_put(fmsg, "\tNPA RVU Interrupt Reg ", + npa_event_context->npa_af_rvu_int); + if (npa_event_context->npa_af_rvu_int & BIT_ULL(0)) + devlink_fmsg_string_put(fmsg, "\n\tUnmap Slot Error"); + rvu_report_pair_end(fmsg); + break; default: return -EINVAL; } diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 818ce76185b2..1a42bfded872 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1404,7 +1404,7 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, } pp_params.order = get_order(buf_size); - pp_params.flags = PP_FLAG_PAGE_FRAG | PP_FLAG_DMA_MAP; + pp_params.flags = PP_FLAG_DMA_MAP; pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs); pp_params.nid = NUMA_NO_NODE; pp_params.dev = pfvf->dev; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 60d49b0f595f..3cf6589cfdac 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3329,7 +3329,7 @@ static int mtk_device_event(struct notifier_block *n, unsigned long event, void return NOTIFY_DONE; found: - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; if (__ethtool_get_link_ksettings(dev, &s)) diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c index e073d2b5542c..fbb5e9d5af13 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c @@ -175,7 +175,7 @@ mtk_flow_get_dsa_port(struct net_device **dev) if (dp->cpu_dp->tag_ops->proto != DSA_TAG_PROTO_MTK) return -ENODEV; - *dev = dsa_port_to_master(dp); + *dev = dsa_port_to_conduit(dp); return dp->index; #else diff --git a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c index 65a78e274009..ea0884186d76 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed_mcu.c +++ b/drivers/net/ethernet/mediatek/mtk_wed_mcu.c @@ -32,12 +32,12 @@ static struct mtk_wed_wo_memory_region mem_region[] = { }, }; -static u32 wo_r32(struct mtk_wed_wo *wo, u32 reg) +static u32 wo_r32(u32 reg) { return readl(mem_region[MTK_WED_WO_REGION_BOOT].addr + reg); } -static void wo_w32(struct mtk_wed_wo *wo, u32 reg, u32 val) +static void wo_w32(u32 reg, u32 val) { writel(val, mem_region[MTK_WED_WO_REGION_BOOT].addr + reg); } @@ -258,16 +258,12 @@ mtk_wed_get_memory_region(struct mtk_wed_hw *hw, int index, } static int -mtk_wed_mcu_run_firmware(struct mtk_wed_wo *wo, const struct firmware *fw, - struct mtk_wed_wo_memory_region *region) +mtk_wed_mcu_run_firmware(struct mtk_wed_wo *wo, const struct firmware *fw) { const u8 *first_region_ptr, *region_ptr, *trailer_ptr, *ptr = fw->data; const struct mtk_wed_fw_trailer *trailer; const struct mtk_wed_fw_region *fw_region; - if (!region->phy_addr || !region->size) - return 0; - trailer_ptr = fw->data + fw->size - sizeof(*trailer); trailer = (const struct mtk_wed_fw_trailer *)trailer_ptr; region_ptr = trailer_ptr - trailer->num_region * sizeof(*fw_region); @@ -275,33 +271,41 @@ mtk_wed_mcu_run_firmware(struct mtk_wed_wo *wo, const struct firmware *fw, while (region_ptr < trailer_ptr) { u32 length; + int i; fw_region = (const struct mtk_wed_fw_region *)region_ptr; length = le32_to_cpu(fw_region->len); - - if (region->phy_addr != le32_to_cpu(fw_region->addr)) + if (first_region_ptr < ptr + length) goto next; - if (region->size < length) - goto next; + for (i = 0; i < ARRAY_SIZE(mem_region); i++) { + struct mtk_wed_wo_memory_region *region; - if (first_region_ptr < ptr + length) - goto next; + region = &mem_region[i]; + if (region->phy_addr != le32_to_cpu(fw_region->addr)) + continue; - if (region->shared && region->consumed) - return 0; + if (region->size < length) + continue; - if (!region->shared || !region->consumed) { - memcpy_toio(region->addr, ptr, length); - region->consumed = true; - return 0; + if (region->shared && region->consumed) + break; + + if (!region->shared || !region->consumed) { + memcpy_toio(region->addr, ptr, length); + region->consumed = true; + break; + } } + + if (i == ARRAY_SIZE(mem_region)) + return -EINVAL; next: region_ptr += sizeof(*fw_region); ptr += length; } - return -EINVAL; + return 0; } static int @@ -360,24 +364,22 @@ mtk_wed_mcu_load_firmware(struct mtk_wed_wo *wo) dev_info(wo->hw->dev, "MTK WED WO Chip ID %02x Region %d\n", trailer->chip_id, trailer->num_region); - for (i = 0; i < ARRAY_SIZE(mem_region); i++) { - ret = mtk_wed_mcu_run_firmware(wo, fw, &mem_region[i]); - if (ret) - goto out; - } + ret = mtk_wed_mcu_run_firmware(wo, fw); + if (ret) + goto out; /* set the start address */ if (!mtk_wed_is_v3_or_greater(wo->hw) && wo->hw->index) boot_cr = MTK_WO_MCU_CFG_LS_WA_BOOT_ADDR_ADDR; else boot_cr = MTK_WO_MCU_CFG_LS_WM_BOOT_ADDR_ADDR; - wo_w32(wo, boot_cr, mem_region[MTK_WED_WO_REGION_EMI].phy_addr >> 16); + wo_w32(boot_cr, mem_region[MTK_WED_WO_REGION_EMI].phy_addr >> 16); /* wo firmware reset */ - wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR, 0xc00); + wo_w32(MTK_WO_MCU_CFG_LS_WF_MCCR_CLR_ADDR, 0xc00); - val = wo_r32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR) | + val = wo_r32(MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR) | MTK_WO_MCU_CFG_LS_WF_WM_WA_WM_CPU_RSTB_MASK; - wo_w32(wo, MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR, val); + wo_w32(MTK_WO_MCU_CFG_LS_WF_MCU_CFG_WM_WA_ADDR, val); out: release_firmware(fw); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 7671c5727ed1..f8f0a712c943 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -2256,52 +2256,23 @@ static u16 cmdif_rev(struct mlx5_core_dev *dev) int mlx5_cmd_init(struct mlx5_core_dev *dev) { - int size = sizeof(struct mlx5_cmd_prot_block); - int align = roundup_pow_of_two(size); struct mlx5_cmd *cmd = &dev->cmd; - u32 cmd_l; - int err; - - cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0); - if (!cmd->pool) - return -ENOMEM; - err = alloc_cmd_page(dev, cmd); - if (err) - goto err_free_pool; - - cmd_l = (u32)(cmd->dma); - if (cmd_l & 0xfff) { - mlx5_core_err(dev, "invalid command queue address\n"); - err = -ENOMEM; - goto err_cmd_page; - } cmd->checksum_disabled = 1; spin_lock_init(&cmd->alloc_lock); spin_lock_init(&cmd->token_lock); - create_msg_cache(dev); - set_wqname(dev); cmd->wq = create_singlethread_workqueue(cmd->wq_name); if (!cmd->wq) { mlx5_core_err(dev, "failed to create command workqueue\n"); - err = -ENOMEM; - goto err_cache; + return -ENOMEM; } mlx5_cmdif_debugfs_init(dev); return 0; - -err_cache: - destroy_msg_cache(dev); -err_cmd_page: - free_cmd_page(dev, cmd); -err_free_pool: - dma_pool_destroy(cmd->pool); - return err; } void mlx5_cmd_cleanup(struct mlx5_core_dev *dev) @@ -2310,15 +2281,15 @@ void mlx5_cmd_cleanup(struct mlx5_core_dev *dev) mlx5_cmdif_debugfs_cleanup(dev); destroy_workqueue(cmd->wq); - destroy_msg_cache(dev); - free_cmd_page(dev, cmd); - dma_pool_destroy(cmd->pool); } int mlx5_cmd_enable(struct mlx5_core_dev *dev) { + int size = sizeof(struct mlx5_cmd_prot_block); + int align = roundup_pow_of_two(size); struct mlx5_cmd *cmd = &dev->cmd; u32 cmd_h, cmd_l; + int err; memset(&cmd->vars, 0, sizeof(cmd->vars)); cmd->vars.cmdif_rev = cmdif_rev(dev); @@ -2351,10 +2322,21 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev) sema_init(&cmd->vars.pages_sem, 1); sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2)); + cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0); + if (!cmd->pool) + return -ENOMEM; + + err = alloc_cmd_page(dev, cmd); + if (err) + goto err_free_pool; + cmd_h = (u32)((u64)(cmd->dma) >> 32); cmd_l = (u32)(cmd->dma); - if (WARN_ON(cmd_l & 0xfff)) - return -EINVAL; + if (cmd_l & 0xfff) { + mlx5_core_err(dev, "invalid command queue address\n"); + err = -ENOMEM; + goto err_cmd_page; + } iowrite32be(cmd_h, &dev->iseg->cmdq_addr_h); iowrite32be(cmd_l, &dev->iseg->cmdq_addr_l_sz); @@ -2367,17 +2349,27 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev) cmd->mode = CMD_MODE_POLLING; cmd->allowed_opcode = CMD_ALLOWED_OPCODE_ALL; + create_msg_cache(dev); create_debugfs_files(dev); return 0; + +err_cmd_page: + free_cmd_page(dev, cmd); +err_free_pool: + dma_pool_destroy(cmd->pool); + return err; } void mlx5_cmd_disable(struct mlx5_core_dev *dev) { struct mlx5_cmd *cmd = &dev->cmd; - clean_debug_files(dev); flush_workqueue(cmd->wq); + clean_debug_files(dev); + destroy_msg_cache(dev); + free_cmd_page(dev, cmd); + dma_pool_destroy(cmd->pool); } void mlx5_cmd_set_state(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 7c0f2adbea00..76d27d2ee40c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -848,7 +848,7 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work) mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner); if (tracer->owner) { - tracer->owner = false; + mlx5_fw_tracer_ownership_acquire(tracer); return; } @@ -889,36 +889,16 @@ int mlx5_fw_tracer_trigger_core_dump_general(struct mlx5_core_dev *dev) return 0; } -static int +static void mlx5_devlink_fmsg_fill_trace(struct devlink_fmsg *fmsg, struct mlx5_fw_trace_data *trace_data) { - int err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "timestamp", trace_data->timestamp); - if (err) - return err; - - err = devlink_fmsg_bool_pair_put(fmsg, "lost", trace_data->lost); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "event_id", trace_data->event_id); - if (err) - return err; - - err = devlink_fmsg_string_pair_put(fmsg, "msg", trace_data->msg); - if (err) - return err; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - return 0; + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_u64_pair_put(fmsg, "timestamp", trace_data->timestamp); + devlink_fmsg_bool_pair_put(fmsg, "lost", trace_data->lost); + devlink_fmsg_u8_pair_put(fmsg, "event_id", trace_data->event_id); + devlink_fmsg_string_pair_put(fmsg, "msg", trace_data->msg); + devlink_fmsg_obj_nest_end(fmsg); } int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer, @@ -927,7 +907,6 @@ int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer, struct mlx5_fw_trace_data *straces = tracer->st_arr.straces; u32 index, start_index, end_index; u32 saved_traces_index; - int err; if (!straces[0].timestamp) return -ENOMSG; @@ -940,22 +919,18 @@ int mlx5_fw_tracer_get_saved_traces_objects(struct mlx5_fw_tracer *tracer, start_index = 0; end_index = (saved_traces_index - 1) & (SAVED_TRACES_NUM - 1); - err = devlink_fmsg_arr_pair_nest_start(fmsg, "dump fw traces"); - if (err) - goto unlock; + devlink_fmsg_arr_pair_nest_start(fmsg, "dump fw traces"); index = start_index; while (index != end_index) { - err = mlx5_devlink_fmsg_fill_trace(fmsg, &straces[index]); - if (err) - goto unlock; + mlx5_devlink_fmsg_fill_trace(fmsg, &straces[index]); index = (index + 1) & (SAVED_TRACES_NUM - 1); } - err = devlink_fmsg_arr_pair_nest_end(fmsg); -unlock: + devlink_fmsg_arr_pair_nest_end(fmsg); mutex_unlock(&tracer->st_arr.lock); - return err; + + return 0; } static void mlx5_fw_tracer_update_db(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c index e869c65d8e90..c7216e84ef8c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c @@ -13,106 +13,55 @@ struct mlx5_vnic_diag_stats { __be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)]; }; -int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, - struct devlink_fmsg *fmsg, - u16 vport_num, bool other_vport) +void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, + struct devlink_fmsg *fmsg, + u16 vport_num, bool other_vport) { u32 in[MLX5_ST_SZ_DW(query_vnic_env_in)] = {}; struct mlx5_vnic_diag_stats vnic; - int err; MLX5_SET(query_vnic_env_in, in, opcode, MLX5_CMD_OP_QUERY_VNIC_ENV); MLX5_SET(query_vnic_env_in, in, vport_number, vport_num); MLX5_SET(query_vnic_env_in, in, other_vport, !!other_vport); - err = mlx5_cmd_exec_inout(dev, query_vnic_env, in, &vnic.query_vnic_env_out); - if (err) - return err; + mlx5_cmd_exec_inout(dev, query_vnic_env, in, &vnic.query_vnic_env_out); - err = devlink_fmsg_pair_nest_start(fmsg, "vNIC env counters"); - if (err) - return err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; + devlink_fmsg_pair_nest_start(fmsg, "vNIC env counters"); + devlink_fmsg_obj_nest_start(fmsg); if (MLX5_CAP_GEN(dev, vnic_env_queue_counters)) { - err = devlink_fmsg_u32_pair_put(fmsg, "total_error_queues", - VNIC_ENV_GET(&vnic, total_error_queues)); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "send_queue_priority_update_flow", - VNIC_ENV_GET(&vnic, - send_queue_priority_update_flow)); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "total_error_queues", + VNIC_ENV_GET(&vnic, total_error_queues)); + devlink_fmsg_u32_pair_put(fmsg, "send_queue_priority_update_flow", + VNIC_ENV_GET(&vnic, send_queue_priority_update_flow)); } - if (MLX5_CAP_GEN(dev, eq_overrun_count)) { - err = devlink_fmsg_u32_pair_put(fmsg, "comp_eq_overrun", - VNIC_ENV_GET(&vnic, comp_eq_overrun)); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "async_eq_overrun", - VNIC_ENV_GET(&vnic, async_eq_overrun)); - if (err) - return err; - } - - if (MLX5_CAP_GEN(dev, vnic_env_cq_overrun)) { - err = devlink_fmsg_u32_pair_put(fmsg, "cq_overrun", - VNIC_ENV_GET(&vnic, cq_overrun)); - if (err) - return err; - } - - if (MLX5_CAP_GEN(dev, invalid_command_count)) { - err = devlink_fmsg_u32_pair_put(fmsg, "invalid_command", - VNIC_ENV_GET(&vnic, invalid_command)); - if (err) - return err; - } - - if (MLX5_CAP_GEN(dev, quota_exceeded_count)) { - err = devlink_fmsg_u32_pair_put(fmsg, "quota_exceeded_command", - VNIC_ENV_GET(&vnic, quota_exceeded_command)); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "comp_eq_overrun", + VNIC_ENV_GET(&vnic, comp_eq_overrun)); + devlink_fmsg_u32_pair_put(fmsg, "async_eq_overrun", + VNIC_ENV_GET(&vnic, async_eq_overrun)); } - - if (MLX5_CAP_GEN(dev, nic_receive_steering_discard)) { - err = devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", - VNIC_ENV_GET64(&vnic, - nic_receive_steering_discard)); - if (err) - return err; - } - + if (MLX5_CAP_GEN(dev, vnic_env_cq_overrun)) + devlink_fmsg_u32_pair_put(fmsg, "cq_overrun", + VNIC_ENV_GET(&vnic, cq_overrun)); + if (MLX5_CAP_GEN(dev, invalid_command_count)) + devlink_fmsg_u32_pair_put(fmsg, "invalid_command", + VNIC_ENV_GET(&vnic, invalid_command)); + if (MLX5_CAP_GEN(dev, quota_exceeded_count)) + devlink_fmsg_u32_pair_put(fmsg, "quota_exceeded_command", + VNIC_ENV_GET(&vnic, quota_exceeded_command)); + if (MLX5_CAP_GEN(dev, nic_receive_steering_discard)) + devlink_fmsg_u64_pair_put(fmsg, "nic_receive_steering_discard", + VNIC_ENV_GET64(&vnic, nic_receive_steering_discard)); if (MLX5_CAP_GEN(dev, vnic_env_cnt_steering_fail)) { - err = devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", - VNIC_ENV_GET64(&vnic, - generated_pkt_steering_fail)); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", - VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); - if (err) - return err; + devlink_fmsg_u64_pair_put(fmsg, "generated_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, generated_pkt_steering_fail)); + devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail", + VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail)); } - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); } static int mlx5_reporter_vnic_diagnose(struct devlink_health_reporter *reporter, @@ -121,7 +70,8 @@ static int mlx5_reporter_vnic_diagnose(struct devlink_health_reporter *reporter, { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); - return mlx5_reporter_vnic_diagnose_counters(dev, fmsg, 0, false); + mlx5_reporter_vnic_diagnose_counters(dev, fmsg, 0, false); + return 0; } static const struct devlink_health_reporter_ops mlx5_reporter_vnic_ops = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.h index eba87a39e9b1..fbc31256f7fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.h @@ -9,8 +9,8 @@ void mlx5_reporter_vnic_create(struct mlx5_core_dev *dev); void mlx5_reporter_vnic_destroy(struct mlx5_core_dev *dev); -int mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, - struct devlink_fmsg *fmsg, - u16 vport_num, bool other_vport); +void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev, + struct devlink_fmsg *fmsg, + u16 vport_num, bool other_vport); #endif /* __MLX5_REPORTER_VNIC_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 6f4e6c34b2a2..81523825faa2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -5,134 +5,59 @@ #include "lib/eq.h" #include "lib/mlx5.h" -int mlx5e_health_fmsg_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name) +void mlx5e_health_fmsg_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_obj_nest_start(fmsg); } -int mlx5e_health_fmsg_named_obj_nest_end(struct devlink_fmsg *fmsg) +void mlx5e_health_fmsg_named_obj_nest_end(struct devlink_fmsg *fmsg) { - int err; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); } -int mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) +void mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) { u32 out[MLX5_ST_SZ_DW(query_cq_out)] = {}; u8 hw_status; void *cqc; - int err; - - err = mlx5_core_query_cq(cq->mdev, &cq->mcq, out); - if (err) - return err; + mlx5_core_query_cq(cq->mdev, &cq->mcq, out); cqc = MLX5_ADDR_OF(query_cq_out, out, cq_context); hw_status = MLX5_GET(cqc, cqc, status); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "CQ"); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "cqn", cq->mcq.cqn); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "HW status", hw_status); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "ci", mlx5_cqwq_get_ci(&cq->wq)); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "size", mlx5_cqwq_get_size(&cq->wq)); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - return 0; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "CQ"); + devlink_fmsg_u32_pair_put(fmsg, "cqn", cq->mcq.cqn); + devlink_fmsg_u8_pair_put(fmsg, "HW status", hw_status); + devlink_fmsg_u32_pair_put(fmsg, "ci", mlx5_cqwq_get_ci(&cq->wq)); + devlink_fmsg_u32_pair_put(fmsg, "size", mlx5_cqwq_get_size(&cq->wq)); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -int mlx5e_health_cq_common_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) +void mlx5e_health_cq_common_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) { u8 cq_log_stride; u32 cq_sz; - int err; cq_sz = mlx5_cqwq_get_size(&cq->wq); cq_log_stride = mlx5_cqwq_get_log_stride_size(&cq->wq); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "CQ"); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "stride size", BIT(cq_log_stride)); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "size", cq_sz); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - return 0; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "CQ"); + devlink_fmsg_u64_pair_put(fmsg, "stride size", BIT(cq_log_stride)); + devlink_fmsg_u32_pair_put(fmsg, "size", cq_sz); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -int mlx5e_health_eq_diag_fmsg(struct mlx5_eq_comp *eq, struct devlink_fmsg *fmsg) +void mlx5e_health_eq_diag_fmsg(struct mlx5_eq_comp *eq, struct devlink_fmsg *fmsg) { - int err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "EQ"); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "eqn", eq->core.eqn); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "irqn", eq->core.irqn); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "vecidx", eq->core.vecidx); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "ci", eq->core.cons_index); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "size", eq_get_size(&eq->core)); - if (err) - return err; - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "EQ"); + devlink_fmsg_u8_pair_put(fmsg, "eqn", eq->core.eqn); + devlink_fmsg_u32_pair_put(fmsg, "irqn", eq->core.irqn); + devlink_fmsg_u32_pair_put(fmsg, "vecidx", eq->core.vecidx); + devlink_fmsg_u32_pair_put(fmsg, "ci", eq->core.cons_index); + devlink_fmsg_u32_pair_put(fmsg, "size", eq_get_size(&eq->core)); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } void mlx5e_health_create_reporters(struct mlx5e_priv *priv) @@ -235,23 +160,19 @@ int mlx5e_health_report(struct mlx5e_priv *priv, } #define MLX5_HEALTH_DEVLINK_MAX_SIZE 1024 -static int mlx5e_health_rsc_fmsg_binary(struct devlink_fmsg *fmsg, - const void *value, u32 value_len) +static void mlx5e_health_rsc_fmsg_binary(struct devlink_fmsg *fmsg, + const void *value, u32 value_len) { u32 data_size; - int err = 0; u32 offset; for (offset = 0; offset < value_len; offset += data_size) { data_size = value_len - offset; if (data_size > MLX5_HEALTH_DEVLINK_MAX_SIZE) data_size = MLX5_HEALTH_DEVLINK_MAX_SIZE; - err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); - if (err) - break; + devlink_fmsg_binary_put(fmsg, value + offset, data_size); } - return err; } int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key, @@ -259,9 +180,8 @@ int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key { struct mlx5_core_dev *mdev = priv->mdev; struct mlx5_rsc_dump_cmd *cmd; + int cmd_err, err = 0; struct page *page; - int cmd_err, err; - int end_err; int size; if (IS_ERR_OR_NULL(mdev->rsc_dump)) @@ -271,9 +191,7 @@ int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key if (!page) return -ENOMEM; - err = devlink_fmsg_binary_pair_nest_start(fmsg, "data"); - if (err) - goto free_page; + devlink_fmsg_binary_pair_nest_start(fmsg, "data"); cmd = mlx5_rsc_dump_cmd_create(mdev, key); if (IS_ERR(cmd)) { @@ -288,52 +206,31 @@ int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key goto destroy_cmd; } - err = mlx5e_health_rsc_fmsg_binary(fmsg, page_address(page), size); - if (err) - goto destroy_cmd; - + mlx5e_health_rsc_fmsg_binary(fmsg, page_address(page), size); } while (cmd_err > 0); destroy_cmd: mlx5_rsc_dump_cmd_destroy(cmd); - end_err = devlink_fmsg_binary_pair_nest_end(fmsg); - if (end_err) - err = end_err; + devlink_fmsg_binary_pair_nest_end(fmsg); free_page: __free_page(page); return err; } -int mlx5e_health_queue_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, - int queue_idx, char *lbl) +void mlx5e_health_queue_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + int queue_idx, char *lbl) { struct mlx5_rsc_key key = {}; - int err; key.rsc = MLX5_SGMT_TYPE_FULL_QPC; key.index1 = queue_idx; key.size = PAGE_SIZE; key.num_of_obj1 = 1; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, lbl); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "index", queue_idx); - if (err) - return err; - - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - return devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_obj_nest_start(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, lbl); + devlink_fmsg_u32_pair_put(fmsg, "index", queue_idx); + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); + devlink_fmsg_obj_nest_end(fmsg); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h index 415840c3ef84..84be3dd6f747 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -20,11 +20,11 @@ void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq); int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq); void mlx5e_reporter_tx_ptpsq_unhealthy(struct mlx5e_ptpsq *ptpsq); -int mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); -int mlx5e_health_cq_common_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); -int mlx5e_health_eq_diag_fmsg(struct mlx5_eq_comp *eq, struct devlink_fmsg *fmsg); -int mlx5e_health_fmsg_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name); -int mlx5e_health_fmsg_named_obj_nest_end(struct devlink_fmsg *fmsg); +void mlx5e_health_cq_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); +void mlx5e_health_cq_common_diag_fmsg(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); +void mlx5e_health_eq_diag_fmsg(struct mlx5_eq_comp *eq, struct devlink_fmsg *fmsg); +void mlx5e_health_fmsg_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name); +void mlx5e_health_fmsg_named_obj_nest_end(struct devlink_fmsg *fmsg); void mlx5e_reporter_rx_create(struct mlx5e_priv *priv); void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv); @@ -54,6 +54,6 @@ void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv); void mlx5e_health_channels_update(struct mlx5e_priv *priv); int mlx5e_health_rsc_fmsg_dump(struct mlx5e_priv *priv, struct mlx5_rsc_key *key, struct devlink_fmsg *fmsg); -int mlx5e_health_queue_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, - int queue_idx, char *lbl); +void mlx5e_health_queue_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, + int queue_idx, char *lbl); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 0fef853eab62..5d128c5b4529 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -467,6 +467,17 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb, /* only handle the event on peers */ if (mlx5_esw_bridge_is_local(dev, rep, esw)) break; + + fdb_info = container_of(info, + struct switchdev_notifier_fdb_info, + info); + /* Mark for deletion to prevent the update wq task from + * spuriously refreshing the entry which would mark it again as + * offloaded in SW bridge. After this fallthrough to regular + * async delete code. + */ + mlx5_esw_bridge_fdb_mark_deleted(dev, vport_num, esw_owner_vhca_id, br_offloads, + fdb_info); fallthrough; case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index e8eea9ffd5eb..fea8c0a5fe89 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -199,78 +199,38 @@ static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter, mlx5e_health_recover_channels(priv); } -static int mlx5e_reporter_icosq_diagnose(struct mlx5e_icosq *icosq, u8 hw_state, - struct devlink_fmsg *fmsg) +static void mlx5e_reporter_icosq_diagnose(struct mlx5e_icosq *icosq, u8 hw_state, + struct devlink_fmsg *fmsg) { - int err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "ICOSQ"); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "sqn", icosq->sqn); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "cc", icosq->cc); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "pc", icosq->pc); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "WQE size", - mlx5_wq_cyc_get_size(&icosq->wq)); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "CQ"); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "cqn", icosq->cq.mcq.cqn); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "cc", icosq->cq.wq.cc); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "size", mlx5_cqwq_get_size(&icosq->cq.wq)); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "ICOSQ"); + devlink_fmsg_u32_pair_put(fmsg, "sqn", icosq->sqn); + devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state); + devlink_fmsg_u32_pair_put(fmsg, "cc", icosq->cc); + devlink_fmsg_u32_pair_put(fmsg, "pc", icosq->pc); + devlink_fmsg_u32_pair_put(fmsg, "WQE size", mlx5_wq_cyc_get_size(&icosq->wq)); + + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "CQ"); + devlink_fmsg_u32_pair_put(fmsg, "cqn", icosq->cq.mcq.cqn); + devlink_fmsg_u32_pair_put(fmsg, "cc", icosq->cq.wq.cc); + devlink_fmsg_u32_pair_put(fmsg, "size", mlx5_cqwq_get_size(&icosq->cq.wq)); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); + + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -static int mlx5e_health_rq_put_sw_state(struct devlink_fmsg *fmsg, struct mlx5e_rq *rq) +static void mlx5e_health_rq_put_sw_state(struct devlink_fmsg *fmsg, struct mlx5e_rq *rq) { - int err; int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(rq_sw_state_type_name) != MLX5E_NUM_RQ_STATES, "rq_sw_state_type_name string array must be consistent with MLX5E_RQ_STATE_* enum in en.h"); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SW State"); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SW State"); - for (i = 0; i < ARRAY_SIZE(rq_sw_state_type_name); ++i) { - err = devlink_fmsg_u32_pair_put(fmsg, rq_sw_state_type_name[i], - test_bit(i, &rq->state)); - if (err) - return err; - } + for (i = 0; i < ARRAY_SIZE(rq_sw_state_type_name); ++i) + devlink_fmsg_u32_pair_put(fmsg, rq_sw_state_type_name[i], + test_bit(i, &rq->state)); - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } static int @@ -291,184 +251,93 @@ mlx5e_rx_reporter_build_diagnose_output_rq_common(struct mlx5e_rq *rq, wq_head = mlx5e_rqwq_get_head(rq); wqe_counter = mlx5e_rqwq_get_wqe_counter(rq); - err = devlink_fmsg_u32_pair_put(fmsg, "rqn", rq->rqn); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "WQE counter", wqe_counter); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "posted WQEs", wqes_sz); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "cc", wq_head); - if (err) - return err; - - err = mlx5e_health_rq_put_sw_state(fmsg, rq); - if (err) - return err; - - err = mlx5e_health_cq_diag_fmsg(&rq->cq, fmsg); - if (err) - return err; - - err = mlx5e_health_eq_diag_fmsg(rq->cq.mcq.eq, fmsg); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "rqn", rq->rqn); + devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state); + devlink_fmsg_u32_pair_put(fmsg, "WQE counter", wqe_counter); + devlink_fmsg_u32_pair_put(fmsg, "posted WQEs", wqes_sz); + devlink_fmsg_u32_pair_put(fmsg, "cc", wq_head); + mlx5e_health_rq_put_sw_state(fmsg, rq); + mlx5e_health_cq_diag_fmsg(&rq->cq, fmsg); + mlx5e_health_eq_diag_fmsg(rq->cq.mcq.eq, fmsg); if (rq->icosq) { struct mlx5e_icosq *icosq = rq->icosq; u8 icosq_hw_state; + int err; err = mlx5_core_query_sq_state(rq->mdev, icosq->sqn, &icosq_hw_state); if (err) return err; - err = mlx5e_reporter_icosq_diagnose(icosq, icosq_hw_state, fmsg); - if (err) - return err; + mlx5e_reporter_icosq_diagnose(icosq, icosq_hw_state, fmsg); } return 0; } -static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, - struct devlink_fmsg *fmsg) +static void mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, + struct devlink_fmsg *fmsg) { - int err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->ix); - if (err) - return err; - - err = mlx5e_rx_reporter_build_diagnose_output_rq_common(rq, fmsg); - if (err) - return err; - - return devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->ix); + mlx5e_rx_reporter_build_diagnose_output_rq_common(rq, fmsg); + devlink_fmsg_obj_nest_end(fmsg); } -static int mlx5e_rx_reporter_diagnose_generic_rq(struct mlx5e_rq *rq, - struct devlink_fmsg *fmsg) +static void mlx5e_rx_reporter_diagnose_generic_rq(struct mlx5e_rq *rq, + struct devlink_fmsg *fmsg) { struct mlx5e_priv *priv = rq->priv; struct mlx5e_params *params; u32 rq_stride, rq_sz; bool real_time; - int err; params = &priv->channels.params; rq_sz = mlx5e_rqwq_get_size(rq); real_time = mlx5_is_real_time_rq(priv->mdev); rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL)); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type); - if (err) - return err; - - err = devlink_fmsg_u64_pair_put(fmsg, "stride size", rq_stride); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "size", rq_sz); - if (err) - return err; - - err = devlink_fmsg_string_pair_put(fmsg, "ts_format", real_time ? "RT" : "FRC"); - if (err) - return err; - - err = mlx5e_health_cq_common_diag_fmsg(&rq->cq, fmsg); - if (err) - return err; - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); + devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type); + devlink_fmsg_u64_pair_put(fmsg, "stride size", rq_stride); + devlink_fmsg_u32_pair_put(fmsg, "size", rq_sz); + devlink_fmsg_string_pair_put(fmsg, "ts_format", real_time ? "RT" : "FRC"); + mlx5e_health_cq_common_diag_fmsg(&rq->cq, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -static int +static void mlx5e_rx_reporter_diagnose_common_ptp_config(struct mlx5e_priv *priv, struct mlx5e_ptp *ptp_ch, struct devlink_fmsg *fmsg) { - int err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP"); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "filter_type", priv->tstamp.rx_filter); - if (err) - return err; - - err = mlx5e_rx_reporter_diagnose_generic_rq(&ptp_ch->rq, fmsg); - if (err) - return err; - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP"); + devlink_fmsg_u32_pair_put(fmsg, "filter_type", priv->tstamp.rx_filter); + mlx5e_rx_reporter_diagnose_generic_rq(&ptp_ch->rq, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -static int +static void mlx5e_rx_reporter_diagnose_common_config(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_rq *generic_rq = &priv->channels.c[0]->rq; struct mlx5e_ptp *ptp_ch = priv->channels.ptp; - int err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Common config"); - if (err) - return err; - - err = mlx5e_rx_reporter_diagnose_generic_rq(generic_rq, fmsg); - if (err) - return err; - if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state)) { - err = mlx5e_rx_reporter_diagnose_common_ptp_config(priv, ptp_ch, fmsg); - if (err) - return err; - } - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Common config"); + mlx5e_rx_reporter_diagnose_generic_rq(generic_rq, fmsg); + if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state)) + mlx5e_rx_reporter_diagnose_common_ptp_config(priv, ptp_ch, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -static int mlx5e_rx_reporter_build_diagnose_output_ptp_rq(struct mlx5e_rq *rq, - struct devlink_fmsg *fmsg) +static void mlx5e_rx_reporter_build_diagnose_output_ptp_rq(struct mlx5e_rq *rq, + struct devlink_fmsg *fmsg) { - int err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = devlink_fmsg_string_pair_put(fmsg, "channel", "ptp"); - if (err) - return err; - - err = mlx5e_rx_reporter_build_diagnose_output_rq_common(rq, fmsg); - if (err) - return err; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_string_pair_put(fmsg, "channel", "ptp"); + mlx5e_rx_reporter_build_diagnose_output_rq_common(rq, fmsg); + devlink_fmsg_obj_nest_end(fmsg); } static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter, @@ -477,20 +346,15 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter, { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_ptp *ptp_ch = priv->channels.ptp; - int i, err = 0; + int i; mutex_lock(&priv->state_lock); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; - err = mlx5e_rx_reporter_diagnose_common_config(reporter, fmsg); - if (err) - goto unlock; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "RQs"); - if (err) - goto unlock; + mlx5e_rx_reporter_diagnose_common_config(reporter, fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "RQs"); for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; @@ -499,19 +363,14 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter, rq = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state) ? &c->xskrq : &c->rq; - err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg); - if (err) - goto unlock; - } - if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state)) { - err = mlx5e_rx_reporter_build_diagnose_output_ptp_rq(&ptp_ch->rq, fmsg); - if (err) - goto unlock; + mlx5e_rx_reporter_build_diagnose_output(rq, fmsg); } - err = devlink_fmsg_arr_pair_nest_end(fmsg); + if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state)) + mlx5e_rx_reporter_build_diagnose_output_ptp_rq(&ptp_ch->rq, fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); unlock: mutex_unlock(&priv->state_lock); - return err; + return 0; } static int mlx5e_rx_reporter_dump_icosq(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, @@ -519,61 +378,34 @@ static int mlx5e_rx_reporter_dump_icosq(struct mlx5e_priv *priv, struct devlink_ { struct mlx5e_txqsq *icosq = ctx; struct mlx5_rsc_key key = {}; - int err; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SX Slice"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SX Slice"); key.size = PAGE_SIZE; key.rsc = MLX5_SGMT_TYPE_SX_SLICE_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "ICOSQ"); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "QPC"); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "ICOSQ"); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "QPC"); key.rsc = MLX5_SGMT_TYPE_FULL_QPC; key.index1 = icosq->sqn; key.num_of_obj1 = 1; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "send_buff"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "send_buff"); key.rsc = MLX5_SGMT_TYPE_SND_BUFF; key.num_of_obj2 = MLX5_RSC_DUMP_ALL; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + return 0; } static int mlx5e_rx_reporter_dump_rq(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, @@ -581,60 +413,34 @@ static int mlx5e_rx_reporter_dump_rq(struct mlx5e_priv *priv, struct devlink_fms { struct mlx5_rsc_key key = {}; struct mlx5e_rq *rq = ctx; - int err; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX Slice"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX Slice"); key.size = PAGE_SIZE; key.rsc = MLX5_SGMT_TYPE_RX_SLICE_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "QPC"); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RQ"); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "QPC"); key.rsc = MLX5_SGMT_TYPE_FULL_QPC; key.index1 = rq->rqn; key.num_of_obj1 = 1; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "receive_buff"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "receive_buff"); key.rsc = MLX5_SGMT_TYPE_RCV_BUFF; key.num_of_obj2 = MLX5_RSC_DUMP_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + return 0; } static int mlx5e_rx_reporter_dump_all_rqs(struct mlx5e_priv *priv, @@ -642,44 +448,28 @@ static int mlx5e_rx_reporter_dump_all_rqs(struct mlx5e_priv *priv, { struct mlx5e_ptp *ptp_ch = priv->channels.ptp; struct mlx5_rsc_key key = {}; - int i, err; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX Slice"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX Slice"); key.size = PAGE_SIZE; key.rsc = MLX5_SGMT_TYPE_RX_SLICE_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "RQs"); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "RQs"); - for (i = 0; i < priv->channels.num; i++) { + for (int i = 0; i < priv->channels.num; i++) { struct mlx5e_rq *rq = &priv->channels.c[i]->rq; - err = mlx5e_health_queue_dump(priv, fmsg, rq->rqn, "RQ"); - if (err) - return err; + mlx5e_health_queue_dump(priv, fmsg, rq->rqn, "RQ"); } - if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state)) { - err = mlx5e_health_queue_dump(priv, fmsg, ptp_ch->rq.rqn, "PTP RQ"); - if (err) - return err; - } + if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state)) + mlx5e_health_queue_dump(priv, fmsg, ptp_ch->rq.rqn, "PTP RQ"); - return devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); + return 0; } static int mlx5e_rx_reporter_dump_from_ctx(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index ff8242f67c54..6b44ddce14e9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -50,25 +50,19 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) sq->pc = 0; } -static int mlx5e_health_sq_put_sw_state(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq) +static void mlx5e_health_sq_put_sw_state(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq) { - int err; int i; BUILD_BUG_ON_MSG(ARRAY_SIZE(sq_sw_state_type_name) != MLX5E_NUM_SQ_STATES, "sq_sw_state_type_name string array must be consistent with MLX5E_SQ_STATE_* enum in en.h"); - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SW State"); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SW State"); - for (i = 0; i < ARRAY_SIZE(sq_sw_state_type_name); ++i) { - err = devlink_fmsg_u32_pair_put(fmsg, sq_sw_state_type_name[i], - test_bit(i, &sq->state)); - if (err) - return err; - } + for (i = 0; i < ARRAY_SIZE(sq_sw_state_type_name); ++i) + devlink_fmsg_u32_pair_put(fmsg, sq_sw_state_type_name[i], + test_bit(i, &sq->state)); - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) @@ -220,7 +214,7 @@ static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, mlx5e_health_recover_channels(priv); } -static int +static void mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq, int tc) { @@ -229,164 +223,71 @@ mlx5e_tx_reporter_build_diagnose_output_sq_common(struct devlink_fmsg *fmsg, u8 state; int err; - err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "tc", tc); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn); - if (err) - return err; - - err = devlink_fmsg_u8_pair_put(fmsg, "HW state", state); - if (err) - return err; - - err = devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "tc", tc); + devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix); + devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn); - err = devlink_fmsg_u32_pair_put(fmsg, "cc", sq->cc); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "pc", sq->pc); - if (err) - return err; - - err = mlx5e_health_sq_put_sw_state(fmsg, sq); - if (err) - return err; - - err = mlx5e_health_cq_diag_fmsg(&sq->cq, fmsg); - if (err) - return err; - - return mlx5e_health_eq_diag_fmsg(sq->cq.mcq.eq, fmsg); + err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + if (!err) + devlink_fmsg_u8_pair_put(fmsg, "HW state", state); + + devlink_fmsg_bool_pair_put(fmsg, "stopped", stopped); + devlink_fmsg_u32_pair_put(fmsg, "cc", sq->cc); + devlink_fmsg_u32_pair_put(fmsg, "pc", sq->pc); + mlx5e_health_sq_put_sw_state(fmsg, sq); + mlx5e_health_cq_diag_fmsg(&sq->cq, fmsg); + mlx5e_health_eq_diag_fmsg(sq->cq.mcq.eq, fmsg); } -static int +static void mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *sq, int tc) { - int err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->ch_ix); - if (err) - return err; - - err = mlx5e_tx_reporter_build_diagnose_output_sq_common(fmsg, sq, tc); - if (err) - return err; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->ch_ix); + mlx5e_tx_reporter_build_diagnose_output_sq_common(fmsg, sq, tc); + devlink_fmsg_obj_nest_end(fmsg); } -static int +static void mlx5e_tx_reporter_build_diagnose_output_ptpsq(struct devlink_fmsg *fmsg, struct mlx5e_ptpsq *ptpsq, int tc) { - int err; - - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - - err = devlink_fmsg_string_pair_put(fmsg, "channel", "ptp"); - if (err) - return err; - - err = mlx5e_tx_reporter_build_diagnose_output_sq_common(fmsg, &ptpsq->txqsq, tc); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Port TS"); - if (err) - return err; - - err = mlx5e_health_cq_diag_fmsg(&ptpsq->ts_cq, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_string_pair_put(fmsg, "channel", "ptp"); + mlx5e_tx_reporter_build_diagnose_output_sq_common(fmsg, &ptpsq->txqsq, tc); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Port TS"); + mlx5e_health_cq_diag_fmsg(&ptpsq->ts_cq, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); + devlink_fmsg_obj_nest_end(fmsg); } -static int +static void mlx5e_tx_reporter_diagnose_generic_txqsq(struct devlink_fmsg *fmsg, struct mlx5e_txqsq *txqsq) { - u32 sq_stride, sq_sz; - bool real_time; - int err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SQ"); - if (err) - return err; - - real_time = mlx5_is_real_time_sq(txqsq->mdev); - sq_sz = mlx5_wq_cyc_get_size(&txqsq->wq); - sq_stride = MLX5_SEND_WQE_BB; - - err = devlink_fmsg_u64_pair_put(fmsg, "stride size", sq_stride); - if (err) - return err; - - err = devlink_fmsg_u32_pair_put(fmsg, "size", sq_sz); - if (err) - return err; - - err = devlink_fmsg_string_pair_put(fmsg, "ts_format", real_time ? "RT" : "FRC"); - if (err) - return err; - - err = mlx5e_health_cq_common_diag_fmsg(&txqsq->cq, fmsg); - if (err) - return err; - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + bool real_time = mlx5_is_real_time_sq(txqsq->mdev); + u32 sq_sz = mlx5_wq_cyc_get_size(&txqsq->wq); + u32 sq_stride = MLX5_SEND_WQE_BB; + + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SQ"); + devlink_fmsg_u64_pair_put(fmsg, "stride size", sq_stride); + devlink_fmsg_u32_pair_put(fmsg, "size", sq_sz); + devlink_fmsg_string_pair_put(fmsg, "ts_format", real_time ? "RT" : "FRC"); + mlx5e_health_cq_common_diag_fmsg(&txqsq->cq, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -static int +static void mlx5e_tx_reporter_diagnose_generic_tx_port_ts(struct devlink_fmsg *fmsg, struct mlx5e_ptpsq *ptpsq) { - int err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Port TS"); - if (err) - return err; - - err = mlx5e_health_cq_common_diag_fmsg(&ptpsq->ts_cq, fmsg); - if (err) - return err; - - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Port TS"); + mlx5e_health_cq_common_diag_fmsg(&ptpsq->ts_cq, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } -static int +static void mlx5e_tx_reporter_diagnose_common_config(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg) { @@ -394,39 +295,20 @@ mlx5e_tx_reporter_diagnose_common_config(struct devlink_health_reporter *reporte struct mlx5e_txqsq *generic_sq = priv->txq2sq[0]; struct mlx5e_ptp *ptp_ch = priv->channels.ptp; struct mlx5e_ptpsq *generic_ptpsq; - int err; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Common Config"); - if (err) - return err; - - err = mlx5e_tx_reporter_diagnose_generic_txqsq(fmsg, generic_sq); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "Common Config"); + mlx5e_tx_reporter_diagnose_generic_txqsq(fmsg, generic_sq); if (!ptp_ch || !test_bit(MLX5E_PTP_STATE_TX, ptp_ch->state)) goto out; generic_ptpsq = &ptp_ch->ptpsq[0]; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP"); - if (err) - return err; - - err = mlx5e_tx_reporter_diagnose_generic_txqsq(fmsg, &generic_ptpsq->txqsq); - if (err) - return err; - - err = mlx5e_tx_reporter_diagnose_generic_tx_port_ts(fmsg, generic_ptpsq); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP"); + mlx5e_tx_reporter_diagnose_generic_txqsq(fmsg, &generic_ptpsq->txqsq); + mlx5e_tx_reporter_diagnose_generic_tx_port_ts(fmsg, generic_ptpsq); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); out: - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); } static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, @@ -436,20 +318,15 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_ptp *ptp_ch = priv->channels.ptp; - int i, tc, err = 0; + int i, tc; mutex_lock(&priv->state_lock); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; - err = mlx5e_tx_reporter_diagnose_common_config(reporter, fmsg); - if (err) - goto unlock; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); - if (err) - goto unlock; + mlx5e_tx_reporter_diagnose_common_config(reporter, fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; @@ -457,31 +334,23 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { struct mlx5e_txqsq *sq = &c->sq[tc]; - err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq, tc); - if (err) - goto unlock; + mlx5e_tx_reporter_build_diagnose_output(fmsg, sq, tc); } } if (!ptp_ch || !test_bit(MLX5E_PTP_STATE_TX, ptp_ch->state)) goto close_sqs_nest; - for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { - err = mlx5e_tx_reporter_build_diagnose_output_ptpsq(fmsg, - &ptp_ch->ptpsq[tc], - tc); - if (err) - goto unlock; - } + for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) + mlx5e_tx_reporter_build_diagnose_output_ptpsq(fmsg, + &ptp_ch->ptpsq[tc], + tc); close_sqs_nest: - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - goto unlock; - + devlink_fmsg_arr_pair_nest_end(fmsg); unlock: mutex_unlock(&priv->state_lock); - return err; + return 0; } static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, @@ -489,60 +358,33 @@ static int mlx5e_tx_reporter_dump_sq(struct mlx5e_priv *priv, struct devlink_fms { struct mlx5_rsc_key key = {}; struct mlx5e_txqsq *sq = ctx; - int err; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SX Slice"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SX Slice"); key.size = PAGE_SIZE; key.rsc = MLX5_SGMT_TYPE_SX_SLICE_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SQ"); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "QPC"); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SQ"); + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "QPC"); key.rsc = MLX5_SGMT_TYPE_FULL_QPC; key.index1 = sq->sqn; key.num_of_obj1 = 1; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "send_buff"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "send_buff"); key.rsc = MLX5_SGMT_TYPE_SND_BUFF; key.num_of_obj2 = MLX5_RSC_DUMP_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; + mlx5e_health_fmsg_named_obj_nest_end(fmsg); - return mlx5e_health_fmsg_named_obj_nest_end(fmsg); + return 0; } static int mlx5e_tx_reporter_timeout_dump(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg, @@ -567,28 +409,17 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, { struct mlx5e_ptp *ptp_ch = priv->channels.ptp; struct mlx5_rsc_key key = {}; - int i, tc, err; + int i, tc; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; - err = mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SX Slice"); - if (err) - return err; - + mlx5e_health_fmsg_named_obj_nest_start(fmsg, "SX Slice"); key.size = PAGE_SIZE; key.rsc = MLX5_SGMT_TYPE_SX_SLICE_ALL; - err = mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); - if (err) - return err; - - err = mlx5e_health_fmsg_named_obj_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); - if (err) - return err; + mlx5e_health_rsc_fmsg_dump(priv, &key, fmsg); + mlx5e_health_fmsg_named_obj_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; @@ -596,9 +427,7 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { struct mlx5e_txqsq *sq = &c->sq[tc]; - err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "SQ"); - if (err) - return err; + mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "SQ"); } } @@ -606,13 +435,12 @@ static int mlx5e_tx_reporter_dump_all_sqs(struct mlx5e_priv *priv, for (tc = 0; tc < mlx5e_get_dcb_num_tc(&priv->channels.params); tc++) { struct mlx5e_txqsq *sq = &ptp_ch->ptpsq[tc].txqsq; - err = mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "PTP SQ"); - if (err) - return err; + mlx5e_health_queue_dump(priv, fmsg, sq->sqn, "PTP SQ"); } } - return devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); + return 0; } static int mlx5e_tx_reporter_dump_from_ctx(struct mlx5e_priv *priv, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c index 1730f6a716ee..b10e40e1a9c1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c @@ -24,7 +24,8 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv, route_dev = dev_get_by_index(dev_net(e->out_dev), e->route_dev_ifindex); - if (!route_dev || !netif_is_ovs_master(route_dev)) + if (!route_dev || !netif_is_ovs_master(route_dev) || + attr->parse_attr->filter_dev == e->out_dev) goto out; err = mlx5e_set_fwd_to_int_port_actions(priv, attr, e->route_dev_ifindex, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index cc3fcd24b36d..7decc81ed33a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -874,11 +874,11 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, } out: - if (flags & XDP_XMIT_FLUSH) { - if (sq->mpwqe.wqe) - mlx5e_xdp_mpwqe_complete(sq); + if (sq->mpwqe.wqe) + mlx5e_xdp_mpwqe_complete(sq); + + if (flags & XDP_XMIT_FLUSH) mlx5e_xmit_xdp_doorbell(sq); - } return nxmit; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9325b8f00af0..ea58c6917433 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -897,7 +897,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params, struct page_pool_params pp_params = { 0 }; pp_params.order = 0; - pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | PP_FLAG_PAGE_FRAG; + pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; pp_params.pool_size = pool_size; pp_params.nid = node; pp_params.dev = rq->pdev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 82dc27e31d9b..693e55b010d9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -701,7 +701,7 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) /* update HW stats in background for next time */ mlx5e_queue_update_stats(priv); - memcpy(stats, &priv->stats.vf_vport, sizeof(*stats)); + mlx5e_stats_copy_rep_stats(stats, &priv->stats.rep_stats); } static int mlx5e_rep_change_mtu(struct net_device *netdev, int new_mtu) @@ -769,6 +769,7 @@ static int mlx5e_rep_max_nch_limit(struct mlx5_core_dev *mdev) static void mlx5e_build_rep_params(struct net_device *netdev) { + const bool take_rtnl = netdev->reg_state == NETREG_REGISTERED; struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep = rpriv->rep; @@ -794,8 +795,15 @@ static void mlx5e_build_rep_params(struct net_device *netdev) /* RQ */ mlx5e_build_rq_params(mdev, params); + /* If netdev is already registered (e.g. move from nic profile to uplink, + * RTNL lock must be held before triggering netdev notifiers. + */ + if (take_rtnl) + rtnl_lock(); /* update XDP supported features */ mlx5e_set_xdp_feature(netdev); + if (take_rtnl) + rtnl_unlock(); /* CQ moderation params */ params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); @@ -1348,8 +1356,9 @@ mlx5e_rep_vnic_reporter_diagnose(struct devlink_health_reporter *reporter, struct mlx5e_rep_priv *rpriv = devlink_health_reporter_priv(reporter); struct mlx5_eswitch_rep *rep = rpriv->rep; - return mlx5_reporter_vnic_diagnose_counters(rep->esw->dev, fmsg, - rep->vport, true); + mlx5_reporter_vnic_diagnose_counters(rep->esw->dev, fmsg, rep->vport, + true); + return 0; } static const struct devlink_health_reporter_ops mlx5_rep_vnic_reporter_ops = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 3fd11b0761e0..8d9743a5e42c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -457,26 +457,41 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk) static int mlx5e_refill_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk) { int remaining = wqe_bulk; - int i = 0; + int total_alloc = 0; + int refill_alloc; + int refill; /* The WQE bulk is split into smaller bulks that are sized * according to the page pool cache refill size to avoid overflowing * the page pool cache due to too many page releases at once. */ do { - int refill = min_t(u16, rq->wqe.info.refill_unit, remaining); - int alloc_count; + refill = min_t(u16, rq->wqe.info.refill_unit, remaining); - mlx5e_free_rx_wqes(rq, ix + i, refill); - alloc_count = mlx5e_alloc_rx_wqes(rq, ix + i, refill); - i += alloc_count; - if (unlikely(alloc_count != refill)) - break; + mlx5e_free_rx_wqes(rq, ix + total_alloc, refill); + refill_alloc = mlx5e_alloc_rx_wqes(rq, ix + total_alloc, refill); + if (unlikely(refill_alloc != refill)) + goto err_free; + total_alloc += refill_alloc; remaining -= refill; } while (remaining); - return i; + return total_alloc; + +err_free: + mlx5e_free_rx_wqes(rq, ix, total_alloc + refill_alloc); + + for (int i = 0; i < total_alloc + refill; i++) { + int j = mlx5_wq_cyc_ctr2ix(&rq->wqe.wq, ix + i); + struct mlx5e_wqe_frag_info *frag; + + frag = get_frag(rq, j); + for (int k = 0; k < rq->wqe.info.num_frags; k++, frag++) + frag->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE); + } + + return 0; } static void @@ -816,6 +831,8 @@ err_unmap: mlx5e_page_release_fragmented(rq, frag_page); } + bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe); + err: rq->stats->buff_alloc_err++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 176fa5976259..477c547dcc04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -484,11 +484,20 @@ struct mlx5e_stats { struct mlx5e_vnic_env_stats vnic; struct mlx5e_vport_stats vport; struct mlx5e_pport_stats pport; - struct rtnl_link_stats64 vf_vport; struct mlx5e_pcie_stats pcie; struct mlx5e_rep_stats rep_stats; }; +static inline void mlx5e_stats_copy_rep_stats(struct rtnl_link_stats64 *vf_vport, + struct mlx5e_rep_stats *rep_stats) +{ + memset(vf_vport, 0, sizeof(*vf_vport)); + vf_vport->rx_packets = rep_stats->vport_rx_packets; + vf_vport->tx_packets = rep_stats->vport_tx_packets; + vf_vport->rx_bytes = rep_stats->vport_rx_bytes; + vf_vport->tx_bytes = rep_stats->vport_tx_bytes; +} + extern mlx5e_stats_grp_t mlx5e_nic_stats_grps[]; unsigned int mlx5e_nic_stats_grps_num(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 4e09ebcfff3b..9a5a5c2c7da9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -4974,7 +4974,8 @@ static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, if (err) return err; - rpriv->prev_vf_vport_stats = priv->stats.vf_vport; + mlx5e_stats_copy_rep_stats(&rpriv->prev_vf_vport_stats, + &priv->stats.rep_stats); break; default: NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall"); @@ -5014,7 +5015,7 @@ void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, u64 dbytes; u64 dpkts; - cur_stats = priv->stats.vf_vport; + mlx5e_stats_copy_rep_stats(&cur_stats, &priv->stats.rep_stats); dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; rpriv->prev_vf_vport_stats = cur_stats; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c index e36294b7ade2..1b9bc32efd6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c @@ -1748,6 +1748,28 @@ void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 entry->lastuse = jiffies; } +void mlx5_esw_bridge_fdb_mark_deleted(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct switchdev_notifier_fdb_info *fdb_info) +{ + struct mlx5_esw_bridge_fdb_entry *entry; + struct mlx5_esw_bridge *bridge; + + bridge = mlx5_esw_bridge_from_port_lookup(vport_num, esw_owner_vhca_id, br_offloads); + if (!bridge) + return; + + entry = mlx5_esw_bridge_fdb_lookup(bridge, fdb_info->addr, fdb_info->vid); + if (!entry) { + esw_debug(br_offloads->esw->dev, + "FDB mark deleted entry with specified key not found (MAC=%pM,vid=%u,vport=%u)\n", + fdb_info->addr, fdb_info->vid, vport_num); + return; + } + + entry->flags |= MLX5_ESW_BRIDGE_FLAG_DELETED; +} + void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct switchdev_notifier_fdb_info *fdb_info) @@ -1810,7 +1832,8 @@ void mlx5_esw_bridge_update(struct mlx5_esw_bridge_offloads *br_offloads) unsigned long lastuse = (unsigned long)mlx5_fc_query_lastuse(entry->ingress_counter); - if (entry->flags & MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER) + if (entry->flags & (MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER | + MLX5_ESW_BRIDGE_FLAG_DELETED)) continue; if (time_after(lastuse, entry->lastuse)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h index c2c7c70d99eb..d6f539161993 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.h @@ -62,6 +62,9 @@ int mlx5_esw_bridge_vport_peer_unlink(struct net_device *br_netdev, u16 vport_nu void mlx5_esw_bridge_fdb_update_used(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct switchdev_notifier_fdb_info *fdb_info); +void mlx5_esw_bridge_fdb_mark_deleted(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, + struct mlx5_esw_bridge_offloads *br_offloads, + struct switchdev_notifier_fdb_info *fdb_info); void mlx5_esw_bridge_fdb_create(struct net_device *dev, u16 vport_num, u16 esw_owner_vhca_id, struct mlx5_esw_bridge_offloads *br_offloads, struct switchdev_notifier_fdb_info *fdb_info); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h index 4911cc32161b..7c251af566c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge_priv.h @@ -133,6 +133,7 @@ struct mlx5_esw_bridge_mdb_key { enum { MLX5_ESW_BRIDGE_FLAG_ADDED_BY_USER = BIT(0), MLX5_ESW_BRIDGE_FLAG_PEER = BIT(1), + MLX5_ESW_BRIDGE_FLAG_DELETED = BIT(2), }; enum { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index d4cde6555063..8d0b915a3121 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -1038,11 +1038,8 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev) return ERR_PTR(err); } -static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw) +static void mlx5_eswitch_event_handler_register(struct mlx5_eswitch *esw) { - MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE); - mlx5_eq_notifier_register(esw->dev, &esw->nb); - if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) { MLX5_NB_INIT(&esw->esw_funcs.nb, mlx5_esw_funcs_changed_handler, ESW_FUNCTIONS_CHANGED); @@ -1050,13 +1047,11 @@ static void mlx5_eswitch_event_handlers_register(struct mlx5_eswitch *esw) } } -static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) +static void mlx5_eswitch_event_handler_unregister(struct mlx5_eswitch *esw) { if (esw->mode == MLX5_ESWITCH_OFFLOADS && mlx5_eswitch_is_funcs_handler(esw->dev)) mlx5_eq_notifier_unregister(esw->dev, &esw->esw_funcs.nb); - mlx5_eq_notifier_unregister(esw->dev, &esw->nb); - flush_workqueue(esw->work_queue); } @@ -1483,6 +1478,9 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) mlx5_eswitch_update_num_of_vfs(esw, num_vfs); + MLX5_NB_INIT(&esw->nb, eswitch_vport_event, NIC_VPORT_CHANGE); + mlx5_eq_notifier_register(esw->dev, &esw->nb); + if (esw->mode == MLX5_ESWITCH_LEGACY) { err = esw_legacy_enable(esw); } else { @@ -1495,7 +1493,7 @@ int mlx5_eswitch_enable_locked(struct mlx5_eswitch *esw, int num_vfs) esw->fdb_table.flags |= MLX5_ESW_FDB_CREATED; - mlx5_eswitch_event_handlers_register(esw); + mlx5_eswitch_event_handler_register(esw); esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", @@ -1622,7 +1620,8 @@ void mlx5_eswitch_disable_locked(struct mlx5_eswitch *esw) */ mlx5_esw_mode_change_notify(esw, MLX5_ESWITCH_LEGACY); - mlx5_eswitch_event_handlers_unregister(esw); + mlx5_eq_notifier_unregister(esw->dev, &esw->nb); + mlx5_eswitch_event_handler_unregister(esw); esw_info(esw->dev, "Disable: mode(%s), nvfs(%d), necvfs(%d), active vports(%d)\n", esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index 1c220048ae9a..8ff6dc9bc803 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -450,14 +450,15 @@ mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; - u8 synd; - int err; + u8 synd = ioread8(&h->synd); - synd = ioread8(&h->synd); - err = devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); - if (err || !synd) - return err; - return devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd)); + if (!synd) + return 0; + + devlink_fmsg_u8_pair_put(fmsg, "Syndrome", synd); + devlink_fmsg_string_pair_put(fmsg, "Description", hsynd_str(synd)); + + return 0; } struct mlx5_fw_reporter_ctx { @@ -465,94 +466,47 @@ struct mlx5_fw_reporter_ctx { int miss_counter; }; -static int +static void mlx5_fw_reporter_ctx_pairs_put(struct devlink_fmsg *fmsg, struct mlx5_fw_reporter_ctx *fw_reporter_ctx) { - int err; - - err = devlink_fmsg_u8_pair_put(fmsg, "syndrome", - fw_reporter_ctx->err_synd); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "fw_miss_counter", - fw_reporter_ctx->miss_counter); - if (err) - return err; - return 0; + devlink_fmsg_u8_pair_put(fmsg, "syndrome", fw_reporter_ctx->err_synd); + devlink_fmsg_u32_pair_put(fmsg, "fw_miss_counter", fw_reporter_ctx->miss_counter); } -static int +static void mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, struct devlink_fmsg *fmsg) { struct mlx5_core_health *health = &dev->priv.health; struct health_buffer __iomem *h = health->health; u8 rfr_severity; - int err; int i; if (!ioread8(&h->synd)) - return 0; - - err = devlink_fmsg_pair_nest_start(fmsg, "health buffer"); - if (err) - return err; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "assert_var"); - if (err) - return err; + return; - for (i = 0; i < ARRAY_SIZE(h->assert_var); i++) { - err = devlink_fmsg_u32_put(fmsg, ioread32be(h->assert_var + i)); - if (err) - return err; - } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "assert_exit_ptr", - ioread32be(&h->assert_exit_ptr)); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "assert_callra", - ioread32be(&h->assert_callra)); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "time", ioread32be(&h->time)); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id)); - if (err) - return err; + devlink_fmsg_pair_nest_start(fmsg, "health buffer"); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "assert_var"); + for (i = 0; i < ARRAY_SIZE(h->assert_var); i++) + devlink_fmsg_u32_put(fmsg, ioread32be(h->assert_var + i)); + devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_u32_pair_put(fmsg, "assert_exit_ptr", + ioread32be(&h->assert_exit_ptr)); + devlink_fmsg_u32_pair_put(fmsg, "assert_callra", + ioread32be(&h->assert_callra)); + devlink_fmsg_u32_pair_put(fmsg, "time", ioread32be(&h->time)); + devlink_fmsg_u32_pair_put(fmsg, "hw_id", ioread32be(&h->hw_id)); rfr_severity = ioread8(&h->rfr_severity); - err = devlink_fmsg_u8_pair_put(fmsg, "rfr", mlx5_health_get_rfr(rfr_severity)); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "severity", mlx5_health_get_severity(rfr_severity)); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "irisc_index", - ioread8(&h->irisc_index)); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "synd", ioread8(&h->synd)); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "ext_synd", - ioread16be(&h->ext_synd)); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "raw_fw_ver", - ioread32be(&h->fw_ver)); - if (err) - return err; - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - return devlink_fmsg_pair_nest_end(fmsg); + devlink_fmsg_u8_pair_put(fmsg, "rfr", mlx5_health_get_rfr(rfr_severity)); + devlink_fmsg_u8_pair_put(fmsg, "severity", mlx5_health_get_severity(rfr_severity)); + devlink_fmsg_u8_pair_put(fmsg, "irisc_index", ioread8(&h->irisc_index)); + devlink_fmsg_u8_pair_put(fmsg, "synd", ioread8(&h->synd)); + devlink_fmsg_u32_pair_put(fmsg, "ext_synd", ioread16be(&h->ext_synd)); + devlink_fmsg_u32_pair_put(fmsg, "raw_fw_ver", ioread32be(&h->fw_ver)); + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); } static int @@ -570,14 +524,11 @@ mlx5_fw_reporter_dump(struct devlink_health_reporter *reporter, if (priv_ctx) { struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; - err = mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx); - if (err) - return err; + mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx); } - err = mlx5_fw_reporter_heath_buffer_data_put(dev, fmsg); - if (err) - return err; + mlx5_fw_reporter_heath_buffer_data_put(dev, fmsg); + return mlx5_fw_tracer_get_saved_traces_objects(dev->tracer, fmsg); } @@ -643,12 +594,10 @@ mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, if (priv_ctx) { struct mlx5_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; - err = mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx); - if (err) - goto free_data; + mlx5_fw_reporter_ctx_pairs_put(fmsg, fw_reporter_ctx); } - err = devlink_fmsg_binary_pair_put(fmsg, "crdump_data", cr_data, crdump_size); + devlink_fmsg_binary_pair_put(fmsg, "crdump_data", cr_data, crdump_size); free_data: kvfree(cr_data); diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index 09bef04b11d1..e827c78be114 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -276,6 +276,12 @@ MLXSW_ITEM32(cmd_mbox, query_fw, fw_month, 0x14, 8, 8); */ MLXSW_ITEM32(cmd_mbox, query_fw, fw_day, 0x14, 0, 8); +/* cmd_mbox_query_fw_lag_mode_support + * 0: CONFIG_PROFILE.lag_mode is not supported by FW + * 1: CONFIG_PROFILE.lag_mode is supported by FW + */ +MLXSW_ITEM32(cmd_mbox, query_fw, lag_mode_support, 0x18, 1, 1); + /* cmd_mbox_query_fw_clr_int_base_offset * Clear Interrupt register's offset from clr_int_bar register * in PCI address space. @@ -659,42 +665,48 @@ MLXSW_ITEM32(cmd_mbox, config_profile, */ MLXSW_ITEM32(cmd_mbox, config_profile, set_ar_sec, 0x0C, 15, 1); -/* cmd_mbox_config_set_ubridge +/* cmd_mbox_config_profile_set_ubridge * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ MLXSW_ITEM32(cmd_mbox, config_profile, set_ubridge, 0x0C, 22, 1); -/* cmd_mbox_config_set_kvd_linear_size +/* cmd_mbox_config_profile_set_kvd_linear_size * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_linear_size, 0x0C, 24, 1); -/* cmd_mbox_config_set_kvd_hash_single_size +/* cmd_mbox_config_profile_set_kvd_hash_single_size * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_single_size, 0x0C, 25, 1); -/* cmd_mbox_config_set_kvd_hash_double_size +/* cmd_mbox_config_profile_set_kvd_hash_double_size * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1); -/* cmd_mbox_config_set_cqe_version +/* cmd_mbox_config_profile_set_cqe_version * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1); -/* cmd_mbox_config_set_cqe_time_stamp_type +/* cmd_mbox_config_profile_set_cqe_time_stamp_type * Capability bit. Setting a bit to 1 configures the profile * according to the mailbox contents. */ MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_time_stamp_type, 0x08, 2, 1); +/* cmd_mbox_config_profile_set_lag_mode + * Capability bit. Setting a bit to 1 configures the lag_mode + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_lag_mode, 0x08, 7, 1); + /* cmd_mbox_config_profile_max_vepa_channels * Maximum number of VEPA channels per port (0 through 16) * 0 - multi-channel VEPA is disabled @@ -840,6 +852,21 @@ MLXSW_ITEM32(cmd_mbox, config_profile, arn, 0x50, 31, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, ubridge, 0x50, 4, 1); +enum mlxsw_cmd_mbox_config_profile_lag_mode { + /* FW manages PGT LAG table */ + MLXSW_CMD_MBOX_CONFIG_PROFILE_LAG_MODE_FW, + /* SW manages PGT LAG table */ + MLXSW_CMD_MBOX_CONFIG_PROFILE_LAG_MODE_SW, +}; + +/* cmd_mbox_config_profile_lag_mode + * LAG mode + * Configured if set_lag_mode is set + * Supported from Spectrum-2 and above. + * Supported only when ubridge = 1 + */ +MLXSW_ITEM32(cmd_mbox, config_profile, lag_mode, 0x50, 3, 1); + /* cmd_mbox_config_kvd_linear_size * KVD Linear Size * Valid for Spectrum only @@ -847,7 +874,7 @@ MLXSW_ITEM32(cmd_mbox, config_profile, ubridge, 0x50, 4, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, kvd_linear_size, 0x54, 0, 24); -/* cmd_mbox_config_kvd_hash_single_size +/* cmd_mbox_config_profile_kvd_hash_single_size * KVD Hash single-entries size * Valid for Spectrum only * Allowed values are 128*N where N=0 or higher @@ -856,7 +883,7 @@ MLXSW_ITEM32(cmd_mbox, config_profile, kvd_linear_size, 0x54, 0, 24); */ MLXSW_ITEM32(cmd_mbox, config_profile, kvd_hash_single_size, 0x58, 0, 24); -/* cmd_mbox_config_kvd_hash_double_size +/* cmd_mbox_config_profile_kvd_hash_double_size * KVD Hash double-entries size (units of single-size entries) * Valid for Spectrum only * Allowed values are 128*N where N=0 or higher diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 1ccf3b73ed72..f23421f038f3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -204,6 +204,13 @@ int mlxsw_core_max_lag(struct mlxsw_core *mlxsw_core, u16 *p_max_lag) } EXPORT_SYMBOL(mlxsw_core_max_lag); +enum mlxsw_cmd_mbox_config_profile_lag_mode +mlxsw_core_lag_mode(struct mlxsw_core *mlxsw_core) +{ + return mlxsw_core->bus->lag_mode(mlxsw_core->bus_priv); +} +EXPORT_SYMBOL(mlxsw_core_lag_mode); + void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core) { return mlxsw_core->driver_priv; @@ -1792,122 +1799,78 @@ static void mlxsw_core_health_listener_func(const struct mlxsw_reg_info *reg, static const struct mlxsw_listener mlxsw_core_health_listener = MLXSW_CORE_EVENTL(mlxsw_core_health_listener_func, MFDE); -static int +static void mlxsw_core_health_fw_fatal_dump_fatal_cause(const char *mfde_pl, struct devlink_fmsg *fmsg) { u32 val, tile_v; - int err; val = mlxsw_reg_mfde_fatal_cause_id_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "cause_id", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "cause_id", val); tile_v = mlxsw_reg_mfde_fatal_cause_tile_v_get(mfde_pl); if (tile_v) { val = mlxsw_reg_mfde_fatal_cause_tile_index_get(mfde_pl); - err = devlink_fmsg_u8_pair_put(fmsg, "tile_index", val); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "tile_index", val); } - - return 0; } -static int +static void mlxsw_core_health_fw_fatal_dump_fw_assert(const char *mfde_pl, struct devlink_fmsg *fmsg) { u32 val, tile_v; - int err; val = mlxsw_reg_mfde_fw_assert_var0_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "var0", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "var0", val); val = mlxsw_reg_mfde_fw_assert_var1_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "var1", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "var1", val); val = mlxsw_reg_mfde_fw_assert_var2_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "var2", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "var2", val); val = mlxsw_reg_mfde_fw_assert_var3_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "var3", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "var3", val); val = mlxsw_reg_mfde_fw_assert_var4_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "var4", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "var4", val); val = mlxsw_reg_mfde_fw_assert_existptr_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "existptr", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "existptr", val); val = mlxsw_reg_mfde_fw_assert_callra_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "callra", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "callra", val); val = mlxsw_reg_mfde_fw_assert_oe_get(mfde_pl); - err = devlink_fmsg_bool_pair_put(fmsg, "old_event", val); - if (err) - return err; + devlink_fmsg_bool_pair_put(fmsg, "old_event", val); tile_v = mlxsw_reg_mfde_fw_assert_tile_v_get(mfde_pl); if (tile_v) { val = mlxsw_reg_mfde_fw_assert_tile_index_get(mfde_pl); - err = devlink_fmsg_u8_pair_put(fmsg, "tile_index", val); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "tile_index", val); } val = mlxsw_reg_mfde_fw_assert_ext_synd_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "ext_synd", val); - if (err) - return err; - - return 0; + devlink_fmsg_u32_pair_put(fmsg, "ext_synd", val); } -static int +static void mlxsw_core_health_fw_fatal_dump_kvd_im_stop(const char *mfde_pl, struct devlink_fmsg *fmsg) { u32 val; - int err; val = mlxsw_reg_mfde_kvd_im_stop_oe_get(mfde_pl); - err = devlink_fmsg_bool_pair_put(fmsg, "old_event", val); - if (err) - return err; + devlink_fmsg_bool_pair_put(fmsg, "old_event", val); val = mlxsw_reg_mfde_kvd_im_stop_pipes_mask_get(mfde_pl); - return devlink_fmsg_u32_pair_put(fmsg, "pipes_mask", val); + devlink_fmsg_u32_pair_put(fmsg, "pipes_mask", val); } -static int +static void mlxsw_core_health_fw_fatal_dump_crspace_to(const char *mfde_pl, struct devlink_fmsg *fmsg) { u32 val; - int err; val = mlxsw_reg_mfde_crspace_to_log_address_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "log_address", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "log_address", val); val = mlxsw_reg_mfde_crspace_to_oe_get(mfde_pl); - err = devlink_fmsg_bool_pair_put(fmsg, "old_event", val); - if (err) - return err; + devlink_fmsg_bool_pair_put(fmsg, "old_event", val); val = mlxsw_reg_mfde_crspace_to_log_id_get(mfde_pl); - err = devlink_fmsg_u8_pair_put(fmsg, "log_irisc_id", val); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "log_irisc_id", val); val = mlxsw_reg_mfde_crspace_to_log_ip_get(mfde_pl); - err = devlink_fmsg_u64_pair_put(fmsg, "log_ip", val); - if (err) - return err; - - return 0; + devlink_fmsg_u64_pair_put(fmsg, "log_ip", val); } static int mlxsw_core_health_fw_fatal_dump(struct devlink_health_reporter *reporter, @@ -1918,24 +1881,17 @@ static int mlxsw_core_health_fw_fatal_dump(struct devlink_health_reporter *repor char *val_str; u8 event_id; u32 val; - int err; if (!priv_ctx) /* User-triggered dumps are not possible */ return -EOPNOTSUPP; val = mlxsw_reg_mfde_irisc_id_get(mfde_pl); - err = devlink_fmsg_u8_pair_put(fmsg, "irisc_id", val); - if (err) - return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "event"); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "irisc_id", val); + devlink_fmsg_arr_pair_nest_start(fmsg, "event"); event_id = mlxsw_reg_mfde_event_id_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "id", event_id); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "id", event_id); switch (event_id) { case MLXSW_REG_MFDE_EVENT_ID_CRSPACE_TO: val_str = "CR space timeout"; @@ -1955,24 +1911,13 @@ static int mlxsw_core_health_fw_fatal_dump(struct devlink_health_reporter *repor default: val_str = NULL; } - if (val_str) { - err = devlink_fmsg_string_pair_put(fmsg, "desc", val_str); - if (err) - return err; - } - - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, "severity"); - if (err) - return err; + if (val_str) + devlink_fmsg_string_pair_put(fmsg, "desc", val_str); + devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "severity"); val = mlxsw_reg_mfde_severity_get(mfde_pl); - err = devlink_fmsg_u8_pair_put(fmsg, "id", val); - if (err) - return err; + devlink_fmsg_u8_pair_put(fmsg, "id", val); switch (val) { case MLXSW_REG_MFDE_SEVERITY_FATL: val_str = "Fatal"; @@ -1986,15 +1931,9 @@ static int mlxsw_core_health_fw_fatal_dump(struct devlink_health_reporter *repor default: val_str = NULL; } - if (val_str) { - err = devlink_fmsg_string_pair_put(fmsg, "desc", val_str); - if (err) - return err; - } - - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; + if (val_str) + devlink_fmsg_string_pair_put(fmsg, "desc", val_str); + devlink_fmsg_arr_pair_nest_end(fmsg); val = mlxsw_reg_mfde_method_get(mfde_pl); switch (val) { @@ -2007,16 +1946,11 @@ static int mlxsw_core_health_fw_fatal_dump(struct devlink_health_reporter *repor default: val_str = NULL; } - if (val_str) { - err = devlink_fmsg_string_pair_put(fmsg, "method", val_str); - if (err) - return err; - } + if (val_str) + devlink_fmsg_string_pair_put(fmsg, "method", val_str); val = mlxsw_reg_mfde_long_process_get(mfde_pl); - err = devlink_fmsg_bool_pair_put(fmsg, "long_process", val); - if (err) - return err; + devlink_fmsg_bool_pair_put(fmsg, "long_process", val); val = mlxsw_reg_mfde_command_type_get(mfde_pl); switch (val) { @@ -2032,29 +1966,25 @@ static int mlxsw_core_health_fw_fatal_dump(struct devlink_health_reporter *repor default: val_str = NULL; } - if (val_str) { - err = devlink_fmsg_string_pair_put(fmsg, "command_type", val_str); - if (err) - return err; - } + if (val_str) + devlink_fmsg_string_pair_put(fmsg, "command_type", val_str); val = mlxsw_reg_mfde_reg_attr_id_get(mfde_pl); - err = devlink_fmsg_u32_pair_put(fmsg, "reg_attr_id", val); - if (err) - return err; + devlink_fmsg_u32_pair_put(fmsg, "reg_attr_id", val); switch (event_id) { case MLXSW_REG_MFDE_EVENT_ID_CRSPACE_TO: - return mlxsw_core_health_fw_fatal_dump_crspace_to(mfde_pl, - fmsg); + mlxsw_core_health_fw_fatal_dump_crspace_to(mfde_pl, fmsg); + break; case MLXSW_REG_MFDE_EVENT_ID_KVD_IM_STOP: - return mlxsw_core_health_fw_fatal_dump_kvd_im_stop(mfde_pl, - fmsg); + mlxsw_core_health_fw_fatal_dump_kvd_im_stop(mfde_pl, fmsg); + break; case MLXSW_REG_MFDE_EVENT_ID_FW_ASSERT: - return mlxsw_core_health_fw_fatal_dump_fw_assert(mfde_pl, fmsg); + mlxsw_core_health_fw_fatal_dump_fw_assert(mfde_pl, fmsg); + break; case MLXSW_REG_MFDE_EVENT_ID_FATAL_CAUSE: - return mlxsw_core_health_fw_fatal_dump_fatal_cause(mfde_pl, - fmsg); + mlxsw_core_health_fw_fatal_dump_fatal_cause(mfde_pl, fmsg); + break; } return 0; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index c6bc5819ce43..764d14bd5bc0 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -36,6 +36,8 @@ struct mlxsw_fw_rev; unsigned int mlxsw_core_max_ports(const struct mlxsw_core *mlxsw_core); int mlxsw_core_max_lag(struct mlxsw_core *mlxsw_core, u16 *p_max_lag); +enum mlxsw_cmd_mbox_config_profile_lag_mode +mlxsw_core_lag_mode(struct mlxsw_core *mlxsw_core); void *mlxsw_core_driver_priv(struct mlxsw_core *mlxsw_core); @@ -335,6 +337,7 @@ struct mlxsw_config_profile { u8 kvd_hash_single_parts; u8 kvd_hash_double_parts; u8 cqe_time_stamp_type; + bool lag_mode_prefer_sw; struct mlxsw_swid_config swid_config[MLXSW_CONFIG_PROFILE_SWID_COUNT]; }; @@ -485,6 +488,7 @@ struct mlxsw_bus { u32 (*read_frc_l)(void *bus_priv); u32 (*read_utc_sec)(void *bus_priv); u32 (*read_utc_nsec)(void *bus_priv); + enum mlxsw_cmd_mbox_config_profile_lag_mode (*lag_mode)(void *bus_priv); u8 features; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 7fae963b2608..e4b25e187467 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -105,6 +105,8 @@ struct mlxsw_pci { u64 free_running_clock_offset; u64 utc_sec_offset; u64 utc_nsec_offset; + bool lag_mode_support; + enum mlxsw_cmd_mbox_config_profile_lag_mode lag_mode; struct mlxsw_pci_queue_type_group queues[MLXSW_PCI_QUEUE_TYPE_COUNT]; u32 doorbell_offset; struct mlxsw_core *core; @@ -1312,6 +1314,16 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, profile->cqe_time_stamp_type); } + if (profile->lag_mode_prefer_sw && mlxsw_pci->lag_mode_support) { + enum mlxsw_cmd_mbox_config_profile_lag_mode lag_mode = + MLXSW_CMD_MBOX_CONFIG_PROFILE_LAG_MODE_SW; + + mlxsw_cmd_mbox_config_profile_set_lag_mode_set(mbox, 1); + mlxsw_cmd_mbox_config_profile_lag_mode_set(mbox, lag_mode); + mlxsw_pci->lag_mode = lag_mode; + } else { + mlxsw_pci->lag_mode = MLXSW_CMD_MBOX_CONFIG_PROFILE_LAG_MODE_FW; + } return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox); } @@ -1587,6 +1599,8 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, mlxsw_pci->utc_nsec_offset = mlxsw_cmd_mbox_query_fw_utc_nsec_offset_get(mbox); + mlxsw_pci->lag_mode_support = + mlxsw_cmd_mbox_query_fw_lag_mode_support_get(mbox); num_pages = mlxsw_cmd_mbox_query_fw_fw_pages_get(mbox); err = mlxsw_pci_fw_area_init(mlxsw_pci, mbox, num_pages); if (err) @@ -1619,9 +1633,8 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_config_profile; - /* Some resources depend on unified bridge model, which is configured - * as part of config_profile. Query the resources again to get correct - * values. + /* Some resources depend on details of config_profile, such as unified + * bridge model. Query the resources again to get correct values. */ err = mlxsw_core_resources_query(mlxsw_core, mbox, res); if (err) @@ -1896,6 +1909,14 @@ static u32 mlxsw_pci_read_utc_nsec(void *bus_priv) return mlxsw_pci_read32_off(mlxsw_pci, mlxsw_pci->utc_nsec_offset); } +static enum mlxsw_cmd_mbox_config_profile_lag_mode +mlxsw_pci_lag_mode(void *bus_priv) +{ + struct mlxsw_pci *mlxsw_pci = bus_priv; + + return mlxsw_pci->lag_mode; +} + static const struct mlxsw_bus mlxsw_pci_bus = { .kind = "pci", .init = mlxsw_pci_init, @@ -1907,6 +1928,7 @@ static const struct mlxsw_bus mlxsw_pci_bus = { .read_frc_l = mlxsw_pci_read_frc_l, .read_utc_sec = mlxsw_pci_read_utc_sec, .read_utc_nsec = mlxsw_pci_read_utc_nsec, + .lag_mode = mlxsw_pci_lag_mode, .features = MLXSW_BUS_F_TXRX | MLXSW_BUS_F_RESET, }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 9970921ceef3..25b294fdeb3d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -38,18 +38,18 @@ static const struct mlxsw_reg_info mlxsw_reg_##_name = { \ MLXSW_REG_DEFINE(sgcr, MLXSW_REG_SGCR_ID, MLXSW_REG_SGCR_LEN); -/* reg_sgcr_llb - * Link Local Broadcast (Default=0) - * When set, all Link Local packets (224.0.0.X) will be treated as broadcast - * packets and ignore the IGMP snooping entries. +/* reg_sgcr_lag_lookup_pgt_base + * Base address used for lookup in PGT table + * Supported when CONFIG_PROFILE.lag_mode = 1 + * Note: when IGCR.ddd_lag_mode=0, the address shall be aligned to 8 entries. * Access: RW */ -MLXSW_ITEM32(reg, sgcr, llb, 0x04, 0, 1); +MLXSW_ITEM32(reg, sgcr, lag_lookup_pgt_base, 0x0C, 0, 16); -static inline void mlxsw_reg_sgcr_pack(char *payload, bool llb) +static inline void mlxsw_reg_sgcr_pack(char *payload, u16 lag_lookup_pgt_base) { MLXSW_REG_ZERO(sgcr, payload); - mlxsw_reg_sgcr_llb_set(payload, !!llb); + mlxsw_reg_sgcr_lag_lookup_pgt_base_set(payload, lag_lookup_pgt_base); } /* SPAD - Switch Physical Address Register diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9dbd5edff0b0..cec72d99d9c9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -2692,6 +2692,63 @@ static void mlxsw_sp_traps_fini(struct mlxsw_sp *mlxsw_sp) kfree(mlxsw_sp->trap); } +static int mlxsw_sp_lag_pgt_init(struct mlxsw_sp *mlxsw_sp) +{ + char sgcr_pl[MLXSW_REG_SGCR_LEN]; + u16 max_lag; + int err; + + if (mlxsw_core_lag_mode(mlxsw_sp->core) != + MLXSW_CMD_MBOX_CONFIG_PROFILE_LAG_MODE_SW) + return 0; + + err = mlxsw_core_max_lag(mlxsw_sp->core, &max_lag); + if (err) + return err; + + /* In DDD mode, which we by default use, each LAG entry is 8 PGT + * entries. The LAG table address needs to be 8-aligned, but that ought + * to be the case, since the LAG table is allocated first. + */ + err = mlxsw_sp_pgt_mid_alloc_range(mlxsw_sp, &mlxsw_sp->lag_pgt_base, + max_lag * 8); + if (err) + return err; + if (WARN_ON_ONCE(mlxsw_sp->lag_pgt_base % 8)) { + err = -EINVAL; + goto err_mid_alloc_range; + } + + mlxsw_reg_sgcr_pack(sgcr_pl, mlxsw_sp->lag_pgt_base); + err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sgcr), sgcr_pl); + if (err) + goto err_mid_alloc_range; + + return 0; + +err_mid_alloc_range: + mlxsw_sp_pgt_mid_free_range(mlxsw_sp, mlxsw_sp->lag_pgt_base, + max_lag * 8); + return err; +} + +static void mlxsw_sp_lag_pgt_fini(struct mlxsw_sp *mlxsw_sp) +{ + u16 max_lag; + int err; + + if (mlxsw_core_lag_mode(mlxsw_sp->core) != + MLXSW_CMD_MBOX_CONFIG_PROFILE_LAG_MODE_SW) + return; + + err = mlxsw_core_max_lag(mlxsw_sp->core, &max_lag); + if (err) + return; + + mlxsw_sp_pgt_mid_free_range(mlxsw_sp, mlxsw_sp->lag_pgt_base, + max_lag * 8); +} + #define MLXSW_SP_LAG_SEED_INIT 0xcafecafe static int mlxsw_sp_lag_init(struct mlxsw_sp *mlxsw_sp) @@ -2723,16 +2780,27 @@ static int mlxsw_sp_lag_init(struct mlxsw_sp *mlxsw_sp) if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_LAG_MEMBERS)) return -EIO; + err = mlxsw_sp_lag_pgt_init(mlxsw_sp); + if (err) + return err; + mlxsw_sp->lags = kcalloc(max_lag, sizeof(struct mlxsw_sp_upper), GFP_KERNEL); - if (!mlxsw_sp->lags) - return -ENOMEM; + if (!mlxsw_sp->lags) { + err = -ENOMEM; + goto err_kcalloc; + } return 0; + +err_kcalloc: + mlxsw_sp_lag_pgt_fini(mlxsw_sp); + return err; } static void mlxsw_sp_lag_fini(struct mlxsw_sp *mlxsw_sp) { + mlxsw_sp_lag_pgt_fini(mlxsw_sp); kfree(mlxsw_sp->lags); } @@ -3113,6 +3181,15 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_pgt_init; } + /* Initialize before FIDs so that the LAG table is at the start of PGT + * and 8-aligned without overallocation. + */ + err = mlxsw_sp_lag_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize LAG\n"); + goto err_lag_init; + } + err = mlxsw_sp_fids_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize FIDs\n"); @@ -3143,12 +3220,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_buffers_init; } - err = mlxsw_sp_lag_init(mlxsw_sp); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize LAG\n"); - goto err_lag_init; - } - /* Initialize SPAN before router and switchdev, so that those components * can call mlxsw_sp_span_respin(). */ @@ -3300,8 +3371,6 @@ err_counter_pool_init: err_switchdev_init: mlxsw_sp_span_fini(mlxsw_sp); err_span_init: - mlxsw_sp_lag_fini(mlxsw_sp); -err_lag_init: mlxsw_sp_buffers_fini(mlxsw_sp); err_buffers_init: mlxsw_sp_devlink_traps_fini(mlxsw_sp); @@ -3312,6 +3381,8 @@ err_traps_init: err_policers_init: mlxsw_sp_fids_fini(mlxsw_sp); err_fids_init: + mlxsw_sp_lag_fini(mlxsw_sp); +err_lag_init: mlxsw_sp_pgt_fini(mlxsw_sp); err_pgt_init: mlxsw_sp_kvdl_fini(mlxsw_sp); @@ -3477,12 +3548,12 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); mlxsw_sp_span_fini(mlxsw_sp); - mlxsw_sp_lag_fini(mlxsw_sp); mlxsw_sp_buffers_fini(mlxsw_sp); mlxsw_sp_devlink_traps_fini(mlxsw_sp); mlxsw_sp_traps_fini(mlxsw_sp); mlxsw_sp_policers_fini(mlxsw_sp); mlxsw_sp_fids_fini(mlxsw_sp); + mlxsw_sp_lag_fini(mlxsw_sp); mlxsw_sp_pgt_fini(mlxsw_sp); mlxsw_sp_kvdl_fini(mlxsw_sp); mlxsw_sp_parsing_fini(mlxsw_sp); @@ -3526,6 +3597,7 @@ static const struct mlxsw_config_profile mlxsw_sp2_config_profile = { }, .used_cqe_time_stamp_type = 1, .cqe_time_stamp_type = MLXSW_CMD_MBOX_CONFIG_PROFILE_CQE_TIME_STAMP_TYPE_UTC, + .lag_mode_prefer_sw = true, }; /* Reduce number of LAGs from full capacity (256) to the maximum supported LAGs @@ -3553,6 +3625,7 @@ static const struct mlxsw_config_profile mlxsw_sp4_config_profile = { }, .used_cqe_time_stamp_type = 1, .cqe_time_stamp_type = MLXSW_CMD_MBOX_CONFIG_PROFILE_CQE_TIME_STAMP_TYPE_UTC, + .lag_mode_prefer_sw = true, }; static void diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 02ca2871b6f9..c70333b460ea 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -212,6 +212,7 @@ struct mlxsw_sp { struct mutex ipv6_addr_ht_lock; /* Protects ipv6_addr_ht */ struct mlxsw_sp_pgt *pgt; bool pgt_smpe_index_valid; + u16 lag_pgt_base; }; struct mlxsw_sp_ptp_ops { @@ -1480,7 +1481,7 @@ int mlxsw_sp_policer_resources_register(struct mlxsw_core *mlxsw_core); /* spectrum_pgt.c */ int mlxsw_sp_pgt_mid_alloc(struct mlxsw_sp *mlxsw_sp, u16 *p_mid); void mlxsw_sp_pgt_mid_free(struct mlxsw_sp *mlxsw_sp, u16 mid_base); -int mlxsw_sp_pgt_mid_alloc_range(struct mlxsw_sp *mlxsw_sp, u16 mid_base, +int mlxsw_sp_pgt_mid_alloc_range(struct mlxsw_sp *mlxsw_sp, u16 *mid_base, u16 count); void mlxsw_sp_pgt_mid_free_range(struct mlxsw_sp *mlxsw_sp, u16 mid_base, u16 count); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c index 9df098474743..e954b8cd2ee8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c @@ -321,6 +321,14 @@ mlxsw_sp_fid_family_num_fids(const struct mlxsw_sp_fid_family *fid_family) } static u16 +mlxsw_sp_fid_family_pgt_size(const struct mlxsw_sp_fid_family *fid_family) +{ + u16 num_fids = mlxsw_sp_fid_family_num_fids(fid_family); + + return num_fids * fid_family->nr_flood_tables; +} + +static u16 mlxsw_sp_fid_flood_table_mid(const struct mlxsw_sp_fid_family *fid_family, const struct mlxsw_sp_flood_table *flood_table, u16 fid_offset) @@ -1068,8 +1076,6 @@ static const struct mlxsw_sp_fid_ops mlxsw_sp_fid_8021d_ops = { #define MLXSW_SP_FID_8021Q_MAX (VLAN_N_VID - 2) #define MLXSW_SP_FID_RFID_MAX (11 * 1024) -#define MLXSW_SP_FID_8021Q_PGT_BASE 0 -#define MLXSW_SP_FID_8021D_PGT_BASE (3 * MLXSW_SP_FID_8021Q_MAX) static const struct mlxsw_sp_flood_table mlxsw_sp_fid_8021d_flood_tables[] = { { @@ -1434,7 +1440,6 @@ static const struct mlxsw_sp_fid_family mlxsw_sp1_fid_8021q_family = { .ops = &mlxsw_sp_fid_8021q_ops, .flood_rsp = false, .bridge_type = MLXSW_REG_BRIDGE_TYPE_0, - .pgt_base = MLXSW_SP_FID_8021Q_PGT_BASE, .smpe_index_valid = false, }; @@ -1448,7 +1453,6 @@ static const struct mlxsw_sp_fid_family mlxsw_sp1_fid_8021d_family = { .rif_type = MLXSW_SP_RIF_TYPE_FID, .ops = &mlxsw_sp_fid_8021d_ops, .bridge_type = MLXSW_REG_BRIDGE_TYPE_1, - .pgt_base = MLXSW_SP_FID_8021D_PGT_BASE, .smpe_index_valid = false, }; @@ -1490,7 +1494,6 @@ static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021q_family = { .ops = &mlxsw_sp_fid_8021q_ops, .flood_rsp = false, .bridge_type = MLXSW_REG_BRIDGE_TYPE_0, - .pgt_base = MLXSW_SP_FID_8021Q_PGT_BASE, .smpe_index_valid = true, }; @@ -1504,7 +1507,6 @@ static const struct mlxsw_sp_fid_family mlxsw_sp2_fid_8021d_family = { .rif_type = MLXSW_SP_RIF_TYPE_FID, .ops = &mlxsw_sp_fid_8021d_ops, .bridge_type = MLXSW_REG_BRIDGE_TYPE_1, - .pgt_base = MLXSW_SP_FID_8021D_PGT_BASE, .smpe_index_valid = true, }; @@ -1654,14 +1656,10 @@ mlxsw_sp_fid_flood_table_init(struct mlxsw_sp_fid_family *fid_family, enum mlxsw_sp_flood_type packet_type = flood_table->packet_type; struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp; const int *sfgc_packet_types; - u16 num_fids, mid_base; + u16 mid_base; int err, i; mid_base = mlxsw_sp_fid_flood_table_mid(fid_family, flood_table, 0); - num_fids = mlxsw_sp_fid_family_num_fids(fid_family); - err = mlxsw_sp_pgt_mid_alloc_range(mlxsw_sp, mid_base, num_fids); - if (err) - return err; sfgc_packet_types = mlxsw_sp_packet_type_sfgc_types[packet_type]; for (i = 0; i < MLXSW_REG_SFGC_TYPE_MAX; i++) { @@ -1675,57 +1673,56 @@ mlxsw_sp_fid_flood_table_init(struct mlxsw_sp_fid_family *fid_family, err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sfgc), sfgc_pl); if (err) - goto err_reg_write; + return err; } return 0; - -err_reg_write: - mlxsw_sp_pgt_mid_free_range(mlxsw_sp, mid_base, num_fids); - return err; -} - -static void -mlxsw_sp_fid_flood_table_fini(struct mlxsw_sp_fid_family *fid_family, - const struct mlxsw_sp_flood_table *flood_table) -{ - struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp; - u16 num_fids, mid_base; - - mid_base = mlxsw_sp_fid_flood_table_mid(fid_family, flood_table, 0); - num_fids = mlxsw_sp_fid_family_num_fids(fid_family); - mlxsw_sp_pgt_mid_free_range(mlxsw_sp, mid_base, num_fids); } static int mlxsw_sp_fid_flood_tables_init(struct mlxsw_sp_fid_family *fid_family) { + struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp; + u16 pgt_size; + int err; int i; + if (!fid_family->nr_flood_tables) + return 0; + + pgt_size = mlxsw_sp_fid_family_pgt_size(fid_family); + err = mlxsw_sp_pgt_mid_alloc_range(mlxsw_sp, &fid_family->pgt_base, + pgt_size); + if (err) + return err; + for (i = 0; i < fid_family->nr_flood_tables; i++) { const struct mlxsw_sp_flood_table *flood_table; - int err; flood_table = &fid_family->flood_tables[i]; err = mlxsw_sp_fid_flood_table_init(fid_family, flood_table); if (err) - return err; + goto err_flood_table_init; } return 0; + +err_flood_table_init: + mlxsw_sp_pgt_mid_free_range(mlxsw_sp, fid_family->pgt_base, pgt_size); + return err; } static void mlxsw_sp_fid_flood_tables_fini(struct mlxsw_sp_fid_family *fid_family) { - int i; + struct mlxsw_sp *mlxsw_sp = fid_family->mlxsw_sp; + u16 pgt_size; - for (i = 0; i < fid_family->nr_flood_tables; i++) { - const struct mlxsw_sp_flood_table *flood_table; + if (!fid_family->nr_flood_tables) + return; - flood_table = &fid_family->flood_tables[i]; - mlxsw_sp_fid_flood_table_fini(fid_family, flood_table); - } + pgt_size = mlxsw_sp_fid_family_pgt_size(fid_family); + mlxsw_sp_pgt_mid_free_range(mlxsw_sp, fid_family->pgt_base, pgt_size); } static int mlxsw_sp_fid_family_register(struct mlxsw_sp *mlxsw_sp, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c index 7dd3dba0fa83..4ef81bac17d6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_pgt.c @@ -54,25 +54,15 @@ void mlxsw_sp_pgt_mid_free(struct mlxsw_sp *mlxsw_sp, u16 mid_base) mutex_unlock(&mlxsw_sp->pgt->lock); } -int -mlxsw_sp_pgt_mid_alloc_range(struct mlxsw_sp *mlxsw_sp, u16 mid_base, u16 count) +int mlxsw_sp_pgt_mid_alloc_range(struct mlxsw_sp *mlxsw_sp, u16 *p_mid_base, + u16 count) { - unsigned int idr_cursor; + unsigned int mid_base; int i, err; mutex_lock(&mlxsw_sp->pgt->lock); - /* This function is supposed to be called several times as part of - * driver init, in specific order. Verify that the mid_index is the - * first free index in the idr, to be able to free the indexes in case - * of error. - */ - idr_cursor = idr_get_cursor(&mlxsw_sp->pgt->pgt_idr); - if (WARN_ON(idr_cursor != mid_base)) { - err = -EINVAL; - goto err_idr_cursor; - } - + mid_base = idr_get_cursor(&mlxsw_sp->pgt->pgt_idr); for (i = 0; i < count; i++) { err = idr_alloc_cyclic(&mlxsw_sp->pgt->pgt_idr, NULL, mid_base, mid_base + count, GFP_KERNEL); @@ -81,12 +71,12 @@ mlxsw_sp_pgt_mid_alloc_range(struct mlxsw_sp *mlxsw_sp, u16 mid_base, u16 count) } mutex_unlock(&mlxsw_sp->pgt->lock); + *p_mid_base = mid_base; return 0; err_idr_alloc_cyclic: for (i--; i >= 0; i--) idr_remove(&mlxsw_sp->pgt->pgt_idr, mid_base + i); -err_idr_cursor: mutex_unlock(&mlxsw_sp->pgt->lock); return err; } diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c index 2db5949b4c7e..6961cfc55fb9 100644 --- a/drivers/net/ethernet/microchip/lan743x_ethtool.c +++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c @@ -1047,7 +1047,8 @@ static int lan743x_ethtool_get_ts_info(struct net_device *netdev, BIT(HWTSTAMP_TX_ON) | BIT(HWTSTAMP_TX_ONESTEP_SYNC); ts_info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | - BIT(HWTSTAMP_FILTER_ALL); + BIT(HWTSTAMP_FILTER_ALL) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); return 0; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index f940895b14e8..45e209a7d083 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1870,6 +1870,50 @@ static int lan743x_tx_get_avail_desc(struct lan743x_tx *tx) return last_head - last_tail - 1; } +static void lan743x_rx_cfg_b_tstamp_config(struct lan743x_adapter *adapter, + int rx_ts_config) +{ + int channel_number; + int index; + u32 data; + + for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++) { + channel_number = adapter->rx[index].channel_number; + data = lan743x_csr_read(adapter, RX_CFG_B(channel_number)); + data &= RX_CFG_B_TS_MASK_; + data |= rx_ts_config; + lan743x_csr_write(adapter, RX_CFG_B(channel_number), + data); + } +} + +int lan743x_rx_set_tstamp_mode(struct lan743x_adapter *adapter, + int rx_filter) +{ + u32 data; + + switch (rx_filter) { + case HWTSTAMP_FILTER_PTP_V2_EVENT: + lan743x_rx_cfg_b_tstamp_config(adapter, + RX_CFG_B_TS_DESCR_EN_); + data = lan743x_csr_read(adapter, PTP_RX_TS_CFG); + data |= PTP_RX_TS_CFG_EVENT_MSGS_; + lan743x_csr_write(adapter, PTP_RX_TS_CFG, data); + break; + case HWTSTAMP_FILTER_NONE: + lan743x_rx_cfg_b_tstamp_config(adapter, + RX_CFG_B_TS_NONE_); + break; + case HWTSTAMP_FILTER_ALL: + lan743x_rx_cfg_b_tstamp_config(adapter, + RX_CFG_B_TS_ALL_RX_); + break; + default: + return -ERANGE; + } + return 0; +} + void lan743x_tx_set_timestamping_mode(struct lan743x_tx *tx, bool enable_timestamping, bool enable_onestep_sync) @@ -2944,7 +2988,6 @@ static int lan743x_rx_open(struct lan743x_rx *rx) data |= RX_CFG_B_RX_PAD_2_; data &= ~RX_CFG_B_RX_RING_LEN_MASK_; data |= ((rx->ring_size) & RX_CFG_B_RX_RING_LEN_MASK_); - data |= RX_CFG_B_TS_ALL_RX_; if (!(adapter->csr.flags & LAN743X_CSR_FLAG_IS_A0)) data |= RX_CFG_B_RDMABL_512_; diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h index 52609fc13ad9..b648461787d2 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.h +++ b/drivers/net/ethernet/microchip/lan743x_main.h @@ -522,6 +522,8 @@ (((u32)(rx_latency)) & 0x0000FFFF) #define PTP_CAP_INFO (0x0A60) #define PTP_CAP_INFO_TX_TS_CNT_GET_(reg_val) (((reg_val) & 0x00000070) >> 4) +#define PTP_RX_TS_CFG (0x0A68) +#define PTP_RX_TS_CFG_EVENT_MSGS_ GENMASK(3, 0) #define PTP_TX_MOD (0x0AA4) #define PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_ (0x10000000) @@ -657,6 +659,9 @@ #define RX_CFG_B(channel) (0xC44 + ((channel) << 6)) #define RX_CFG_B_TS_ALL_RX_ BIT(29) +#define RX_CFG_B_TS_DESCR_EN_ BIT(28) +#define RX_CFG_B_TS_NONE_ 0 +#define RX_CFG_B_TS_MASK_ (0xCFFFFFFF) #define RX_CFG_B_RX_PAD_MASK_ (0x03000000) #define RX_CFG_B_RX_PAD_0_ (0x00000000) #define RX_CFG_B_RX_PAD_2_ (0x02000000) @@ -991,6 +996,9 @@ struct lan743x_rx { struct sk_buff *skb_head, *skb_tail; }; +int lan743x_rx_set_tstamp_mode(struct lan743x_adapter *adapter, + int rx_filter); + /* SGMII Link Speed Duplex status */ enum lan743x_sgmii_lsd { POWER_DOWN = 0, diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index 39e1066ecd5f..2f04bc77a118 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -1493,6 +1493,10 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter) temp = lan743x_csr_read(adapter, PTP_TX_MOD2); temp |= PTP_TX_MOD2_TX_PTP_CLR_UDPV4_CHKSUM_; lan743x_csr_write(adapter, PTP_TX_MOD2, temp); + + /* Default Timestamping */ + lan743x_rx_set_tstamp_mode(adapter, HWTSTAMP_FILTER_NONE); + lan743x_ptp_enable(adapter); lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_); lan743x_csr_write(adapter, PTP_INT_EN_SET, @@ -1653,6 +1657,9 @@ static void lan743x_ptp_disable(struct lan743x_adapter *adapter) { struct lan743x_ptp *ptp = &adapter->ptp; + /* Disable Timestamping */ + lan743x_rx_set_tstamp_mode(adapter, HWTSTAMP_FILTER_NONE); + mutex_lock(&ptp->command_lock); if (!lan743x_ptp_is_enabled(adapter)) { netif_warn(adapter, drv, adapter->netdev, @@ -1785,6 +1792,8 @@ int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) break; } + ret = lan743x_rx_set_tstamp_mode(adapter, config.rx_filter); + if (!ret) return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c index 8e4101628fbd..2635ef8958c8 100644 --- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c +++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c @@ -671,7 +671,6 @@ static irqreturn_t lan966x_xtr_irq_handler(int irq, void *args) skb = netdev_alloc_skb(dev, len); if (unlikely(!skb)) { netdev_err(dev, "Unable to allocate sk_buff\n"); - err = -ENOMEM; break; } buf_len = len - ETH_FCS_LEN; diff --git a/drivers/net/ethernet/qlogic/qed/qed_devlink.c b/drivers/net/ethernet/qlogic/qed/qed_devlink.c index be5cc8b79bd5..dad8e617c393 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_devlink.c +++ b/drivers/net/ethernet/qlogic/qed/qed_devlink.c @@ -66,12 +66,12 @@ qed_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, return err; } - err = devlink_fmsg_binary_pair_put(fmsg, "dump_data", - p_dbg_data_buf, dbg_data_buf_size); + devlink_fmsg_binary_pair_put(fmsg, "dump_data", p_dbg_data_buf, + dbg_data_buf_size); vfree(p_dbg_data_buf); - return err; + return 0; } static int diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 717a0b3f89bd..ab5ef254a748 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -113,7 +113,10 @@ static void qed_ll2b_complete_tx_packet(void *cxt, static int qed_ll2_alloc_buffer(struct qed_dev *cdev, u8 **data, dma_addr_t *phys_addr) { - *data = kmalloc(cdev->ll2->rx_size, GFP_ATOMIC); + size_t size = cdev->ll2->rx_size + NET_SKB_PAD + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + *data = kmalloc(size, GFP_ATOMIC); if (!(*data)) { DP_INFO(cdev, "Failed to allocate LL2 buffer data\n"); return -ENOMEM; @@ -2589,7 +2592,7 @@ static int qed_ll2_start(struct qed_dev *cdev, struct qed_ll2_params *params) INIT_LIST_HEAD(&cdev->ll2->list); spin_lock_init(&cdev->ll2->lock); - cdev->ll2->rx_size = NET_SKB_PAD + ETH_HLEN + + cdev->ll2->rx_size = PRM_DMA_PAD_BYTES_NUM + ETH_HLEN + L1_CACHE_BYTES + params->mtu; /* Allocate memory for LL2. diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index 95820cf1cd6c..b6b849a079ed 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -201,21 +201,6 @@ static const char qede_tests_str_arr[QEDE_ETHTOOL_TEST_MAX][ETH_GSTRING_LEN] = { /* Forced speed capabilities maps */ -struct qede_forced_speed_map { - u32 speed; - __ETHTOOL_DECLARE_LINK_MODE_MASK(caps); - - const u32 *cap_arr; - u32 arr_size; -}; - -#define QEDE_FORCED_SPEED_MAP(value) \ -{ \ - .speed = SPEED_##value, \ - .cap_arr = qede_forced_speed_##value, \ - .arr_size = ARRAY_SIZE(qede_forced_speed_##value), \ -} - static const u32 qede_forced_speed_1000[] __initconst = { ETHTOOL_LINK_MODE_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, @@ -263,28 +248,21 @@ static const u32 qede_forced_speed_100000[] __initconst = { ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, }; -static struct qede_forced_speed_map qede_forced_speed_maps[] __ro_after_init = { - QEDE_FORCED_SPEED_MAP(1000), - QEDE_FORCED_SPEED_MAP(10000), - QEDE_FORCED_SPEED_MAP(20000), - QEDE_FORCED_SPEED_MAP(25000), - QEDE_FORCED_SPEED_MAP(40000), - QEDE_FORCED_SPEED_MAP(50000), - QEDE_FORCED_SPEED_MAP(100000), +static struct ethtool_forced_speed_map +qede_forced_speed_maps[] __ro_after_init = { + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 1000), + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 10000), + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 20000), + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 25000), + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 40000), + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 50000), + ETHTOOL_FORCED_SPEED_MAP(qede_forced_speed, 100000), }; void __init qede_forced_speed_maps_init(void) { - struct qede_forced_speed_map *map; - u32 i; - - for (i = 0; i < ARRAY_SIZE(qede_forced_speed_maps); i++) { - map = qede_forced_speed_maps + i; - - linkmode_set_bit_array(map->cap_arr, map->arr_size, map->caps); - map->cap_arr = NULL; - map->arr_size = 0; - } + ethtool_forced_speed_maps_init(qede_forced_speed_maps, + ARRAY_SIZE(qede_forced_speed_maps)); } /* Ethtool callbacks */ @@ -564,8 +542,8 @@ static int qede_set_link_ksettings(struct net_device *dev, const struct ethtool_link_ksettings *cmd) { const struct ethtool_link_settings *base = &cmd->base; + const struct ethtool_forced_speed_map *map; struct qede_dev *edev = netdev_priv(dev); - const struct qede_forced_speed_map *map; struct qed_link_output current_link; struct qed_link_params params; u32 i; diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index df0df4d09f05..a987defb575c 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -4364,7 +4364,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp, unsigned int entry = dirty_tx % NUM_TX_DESC; u32 status; - status = le32_to_cpu(tp->TxDescArray[entry].opts1); + status = le32_to_cpu(READ_ONCE(tp->TxDescArray[entry].opts1)); if (status & DescOwn) break; @@ -4394,7 +4394,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp, * If skb is NULL then we come here again once a tx irq is * triggered after the last fragment is marked transmitted. */ - if (tp->cur_tx != dirty_tx && skb) + if (READ_ONCE(tp->cur_tx) != dirty_tx && skb) rtl8169_doorbell(tp); } } @@ -4427,7 +4427,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, int budget dma_addr_t addr; u32 status; - status = le32_to_cpu(desc->opts1); + status = le32_to_cpu(READ_ONCE(desc->opts1)); if (status & DescOwn) break; diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 3ceb57408ed0..8ef5b0241e64 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 # -# Renesas device configuration +# Renesas network device configuration # config NET_VENDOR_RENESAS @@ -25,9 +25,6 @@ config SH_ETH select PHYLIB help Renesas SuperH Ethernet device driver. - This driver supporting CPUs are: - - SH7619, SH7710, SH7712, SH7724, SH7734, SH7763, SH7757, - R8A7740, R8A774x, R8A777x and R8A779x. config RAVB tristate "Renesas Ethernet AVB support" @@ -39,8 +36,6 @@ config RAVB select PHYLIB help Renesas Ethernet AVB device driver. - This driver supports the following SoCs: - - R8A779x. config RENESAS_ETHER_SWITCH tristate "Renesas Ethernet Switch support" @@ -51,7 +46,5 @@ config RENESAS_ETHER_SWITCH select PHYLINK help Renesas Ethernet Switch device driver. - This driver supports the following SoCs: - - R8A779Fx. endif # NET_VENDOR_RENESAS diff --git a/drivers/net/ethernet/renesas/Makefile b/drivers/net/ethernet/renesas/Makefile index 592005893464..e8fd85b5fe8f 100644 --- a/drivers/net/ethernet/renesas/Makefile +++ b/drivers/net/ethernet/renesas/Makefile @@ -1,14 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 # -# Makefile for the Renesas device drivers. +# Makefile for the Renesas network device drivers # obj-$(CONFIG_SH_ETH) += sh_eth.o ravb-objs := ravb_main.o ravb_ptp.o - obj-$(CONFIG_RAVB) += ravb.o rswitch_drv-objs := rswitch.o rcar_gen4_ptp.o - obj-$(CONFIG_RENESAS_ETHER_SWITCH) += rswitch_drv.o diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c index 112e605f104a..43a7795d6591 100644 --- a/drivers/net/ethernet/renesas/rswitch.c +++ b/drivers/net/ethernet/renesas/rswitch.c @@ -17,6 +17,7 @@ #include <linux/of_net.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/pm.h> #include <linux/pm_runtime.h> #include <linux/rtnetlink.h> #include <linux/slab.h> @@ -1315,6 +1316,7 @@ static int rswitch_phy_device_init(struct rswitch_device *rdev) if (!phydev) goto out; __set_bit(rdev->etha->phy_interface, phydev->host_interfaces); + phydev->mac_managed_pm = true; phydev = of_phy_connect(rdev->ndev, phy, rswitch_adjust_link, 0, rdev->etha->phy_interface); @@ -1405,7 +1407,8 @@ static void rswitch_ether_port_deinit_one(struct rswitch_device *rdev) static int rswitch_ether_port_init_all(struct rswitch_private *priv) { - int i, err; + unsigned int i; + int err; rswitch_for_each_enabled_port(priv, i) { err = rswitch_ether_port_init_one(priv->rdev[i]); @@ -1786,7 +1789,8 @@ static void rswitch_device_free(struct rswitch_private *priv, int index) static int rswitch_init(struct rswitch_private *priv) { - int i, err; + unsigned int i; + int err; for (i = 0; i < RSWITCH_NUM_PORTS; i++) rswitch_etha_init(priv, i); @@ -1816,7 +1820,7 @@ static int rswitch_init(struct rswitch_private *priv) for (i = 0; i < RSWITCH_NUM_PORTS; i++) { err = rswitch_device_alloc(priv, i); if (err < 0) { - for (i--; i >= 0; i--) + for (; i-- > 0; ) rswitch_device_free(priv, i); goto err_device_alloc; } @@ -1959,7 +1963,7 @@ static int renesas_eth_sw_probe(struct platform_device *pdev) static void rswitch_deinit(struct rswitch_private *priv) { - int i; + unsigned int i; rswitch_gwca_hw_deinit(priv); rcar_gen4_ptp_unregister(priv->ptp_priv); @@ -1993,11 +1997,52 @@ static void renesas_eth_sw_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); } +static int renesas_eth_sw_suspend(struct device *dev) +{ + struct rswitch_private *priv = dev_get_drvdata(dev); + struct net_device *ndev; + unsigned int i; + + rswitch_for_each_enabled_port(priv, i) { + ndev = priv->rdev[i]->ndev; + if (netif_running(ndev)) { + netif_device_detach(ndev); + rswitch_stop(ndev); + } + if (priv->rdev[i]->serdes->init_count) + phy_exit(priv->rdev[i]->serdes); + } + + return 0; +} + +static int renesas_eth_sw_resume(struct device *dev) +{ + struct rswitch_private *priv = dev_get_drvdata(dev); + struct net_device *ndev; + unsigned int i; + + rswitch_for_each_enabled_port(priv, i) { + phy_init(priv->rdev[i]->serdes); + ndev = priv->rdev[i]->ndev; + if (netif_running(ndev)) { + rswitch_open(ndev); + netif_device_attach(ndev); + } + } + + return 0; +} + +static DEFINE_SIMPLE_DEV_PM_OPS(renesas_eth_sw_pm_ops, renesas_eth_sw_suspend, + renesas_eth_sw_resume); + static struct platform_driver renesas_eth_sw_driver_platform = { .probe = renesas_eth_sw_probe, .remove_new = renesas_eth_sw_remove, .driver = { .name = "renesas_eth_sw", + .pm = pm_sleep_ptr(&renesas_eth_sw_pm_ops), .of_match_table = renesas_eth_sw_of_table, } }; diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index 04f49a7a5843..27c9d3872c0e 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -20,7 +20,7 @@ else #define rswitch_for_each_enabled_port_continue_reverse(priv, i) \ - for (i--; i >= 0; i--) \ + for (; i-- > 0; ) \ if (priv->rdev[i]->disabled) \ continue; \ else diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c index 6db3d7ed3a86..82e8891a619a 100644 --- a/drivers/net/ethernet/sfc/tc.c +++ b/drivers/net/ethernet/sfc/tc.c @@ -629,14 +629,14 @@ static int efx_tc_flower_record_encap_match(struct efx_nic *efx, } if (child_ip_tos_mask != old->child_ip_tos_mask) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Pseudo encap match for TOS mask %#04x conflicts with existing pseudo(MASK) entry for TOS mask %#04x", + "Pseudo encap match for TOS mask %#04x conflicts with existing mask %#04x", child_ip_tos_mask, old->child_ip_tos_mask); return -EEXIST; } if (child_udp_sport_mask != old->child_udp_sport_mask) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Pseudo encap match for UDP src port mask %#x conflicts with existing pseudo(MASK) entry for mask %#x", + "Pseudo encap match for UDP src port mask %#x conflicts with existing mask %#x", child_udp_sport_mask, old->child_udp_sport_mask); return -EEXIST; @@ -1180,7 +1180,7 @@ static int efx_tc_pedit_add(struct efx_nic *efx, struct efx_tc_action_set *act, /* check that we do not decrement ttl twice */ if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_DEC_TTL)) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported: multiple dec ttl"); + NL_SET_ERR_MSG_MOD(extack, "multiple dec ttl are not supported"); return -EOPNOTSUPP; } act->do_ttl_dec = 1; @@ -1205,7 +1205,7 @@ static int efx_tc_pedit_add(struct efx_nic *efx, struct efx_tc_action_set *act, /* check that we do not decrement hoplimit twice */ if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_DEC_TTL)) { - NL_SET_ERR_MSG_MOD(extack, "Unsupported: multiple dec ttl"); + NL_SET_ERR_MSG_MOD(extack, "multiple dec ttl are not supported"); return -EOPNOTSUPP; } act->do_ttl_dec = 1; @@ -1219,7 +1219,7 @@ static int efx_tc_pedit_add(struct efx_nic *efx, struct efx_tc_action_set *act, } NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: ttl add action type %x %x %x/%x", + "ttl add action type %x %x %x/%x is not supported", fa->mangle.htype, fa->mangle.offset, fa->mangle.val, fa->mangle.mask); return -EOPNOTSUPP; @@ -1263,7 +1263,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, case 0: if (fa->mangle.mask) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: mask (%#x) of eth.dst32 mangle", + "mask (%#x) of eth.dst32 mangle is not supported", fa->mangle.mask); return -EOPNOTSUPP; } @@ -1283,7 +1283,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, mung->dst_mac_16 = 1; } else { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: mask (%#x) of eth+4 mangle is not high or low 16b", + "mask (%#x) of eth+4 mangle is not high or low 16b", fa->mangle.mask); return -EOPNOTSUPP; } @@ -1291,7 +1291,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, case 8: if (fa->mangle.mask) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: mask (%#x) of eth.src32 mangle", + "mask (%#x) of eth.src32 mangle is not supported", fa->mangle.mask); return -EOPNOTSUPP; } @@ -1300,7 +1300,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, mung->src_mac_32 = 1; return efx_tc_complete_mac_mangle(efx, act, mung, extack); default: - NL_SET_ERR_MSG_FMT_MOD(extack, "Unsupported: mangle eth+%u %x/%x", + NL_SET_ERR_MSG_FMT_MOD(extack, "mangle eth+%u %x/%x is not supported", fa->mangle.offset, fa->mangle.val, fa->mangle.mask); return -EOPNOTSUPP; } @@ -1316,7 +1316,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, /* check that pedit applies to ttl only */ if (fa->mangle.mask != ~EFX_TC_HDR_TYPE_TTL_MASK) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: mask (%#x) out of range, only support mangle action on ipv4.ttl", + "mask (%#x) out of range, only support mangle action on ipv4.ttl", fa->mangle.mask); return -EOPNOTSUPP; } @@ -1326,7 +1326,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, */ if (match->mask.ip_ttl != U8_MAX) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: only support mangle ipv4.ttl when we have an exact match on ttl, mask used for match (%#x)", + "only support mangle ttl when we have an exact match, current mask (%#x)", match->mask.ip_ttl); return -EOPNOTSUPP; } @@ -1336,7 +1336,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, */ if (match->value.ip_ttl == 0) { NL_SET_ERR_MSG_MOD(extack, - "Unsupported: we cannot decrement ttl past 0"); + "decrement ttl past 0 is not supported"); return -EOPNOTSUPP; } @@ -1344,7 +1344,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_DEC_TTL)) { NL_SET_ERR_MSG_MOD(extack, - "Unsupported: multiple dec ttl"); + "multiple dec ttl is not supported"); return -EOPNOTSUPP; } @@ -1358,7 +1358,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, fallthrough; default: NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: only support mangle on the ttl field (offset is %u)", + "only support mangle on the ttl field (offset is %u)", fa->mangle.offset); return -EOPNOTSUPP; } @@ -1374,7 +1374,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, /* check that pedit applies to ttl only */ if (fa->mangle.mask != EFX_TC_HDR_TYPE_HLIMIT_MASK) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: mask (%#x) out of range, only support mangle action on ipv6.hop_limit", + "mask (%#x) out of range, only support mangle action on ipv6.hop_limit", fa->mangle.mask); return -EOPNOTSUPP; @@ -1385,7 +1385,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, */ if (match->mask.ip_ttl != U8_MAX) { NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: only support mangle ipv6.hop_limit when we have an exact match on ttl, mask used for match (%#x)", + "only support hop_limit when we have an exact match, current mask (%#x)", match->mask.ip_ttl); return -EOPNOTSUPP; } @@ -1395,7 +1395,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, */ if (match->value.ip_ttl == 0) { NL_SET_ERR_MSG_MOD(extack, - "Unsupported: we cannot decrement hop_limit past 0"); + "decrementing hop_limit past 0 is not supported"); return -EOPNOTSUPP; } @@ -1403,7 +1403,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, if (!efx_tc_flower_action_order_ok(act, EFX_TC_AO_DEC_TTL)) { NL_SET_ERR_MSG_MOD(extack, - "Unsupported: multiple dec ttl"); + "multiple dec ttl is not supported"); return -EOPNOTSUPP; } @@ -1417,7 +1417,7 @@ static int efx_tc_mangle(struct efx_nic *efx, struct efx_tc_action_set *act, fallthrough; default: NL_SET_ERR_MSG_FMT_MOD(extack, - "Unsupported: only support mangle on the hop_limit field"); + "only support mangle on the hop_limit field"); return -EOPNOTSUPP; } default: diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 1e996c29043d..e3f650e88f82 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -293,7 +293,7 @@ struct stmmac_safety_stats { #define MIN_DMA_RIWT 0x10 #define DEF_DMA_RIWT 0xa0 /* Tx coalesce parameters */ -#define STMMAC_COAL_TX_TIMER 1000 +#define STMMAC_COAL_TX_TIMER 5000 #define STMMAC_MAX_COAL_TX_TICK 100000 #define STMMAC_TX_MAX_FRAMES 256 #define STMMAC_TX_FRAMES 25 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index a3a249c63598..60283543ffc8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -605,7 +605,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->mdio_bus_data->phy_mask |= 1 << INTEL_MGBE_XPCS_ADDR; plat->int_snapshot_num = AUX_SNAPSHOT1; - plat->ext_snapshot_num = AUX_SNAPSHOT0; plat->crosststamp = intel_crosststamp; plat->flags &= ~STMMAC_FLAG_INT_SNAPSHOT_EN; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 6aa5c0556d22..f628411ae4ae 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -981,7 +981,7 @@ static int __stmmac_set_coalesce(struct net_device *dev, else if (queue >= max_cnt) return -EINVAL; - if (priv->use_riwt && (ec->rx_coalesce_usecs > 0)) { + if (priv->use_riwt) { rx_riwt = stmmac_usec2riwt(ec->rx_coalesce_usecs, priv); if ((rx_riwt > MAX_DMA_RIWT) || (rx_riwt < MIN_DMA_RIWT)) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index bb1dbf4c9f6c..3e50fd53a617 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1197,6 +1197,17 @@ static int stmmac_init_phy(struct net_device *dev) return ret; } +static void stmmac_set_half_duplex(struct stmmac_priv *priv) +{ + /* Half-Duplex can only work with single tx queue */ + if (priv->plat->tx_queues_to_use > 1) + priv->phylink_config.mac_capabilities &= + ~(MAC_10HD | MAC_100HD | MAC_1000HD); + else + priv->phylink_config.mac_capabilities |= + (MAC_10HD | MAC_100HD | MAC_1000HD); +} + static int stmmac_phy_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data; @@ -1228,10 +1239,7 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) MAC_10FD | MAC_100FD | MAC_1000FD; - /* Half-Duplex can only work with single queue */ - if (priv->plat->tx_queues_to_use <= 1) - priv->phylink_config.mac_capabilities |= MAC_10HD | MAC_100HD | - MAC_1000HD; + stmmac_set_half_duplex(priv); /* Get the MAC specific capabilities */ stmmac_mac_phylink_get_caps(priv); @@ -2543,9 +2551,13 @@ static void stmmac_bump_dma_threshold(struct stmmac_priv *priv, u32 chan) * @priv: driver private structure * @budget: napi budget limiting this functions packet handling * @queue: TX queue index + * @pending_packets: signal to arm the TX coal timer * Description: it reclaims the transmit resources after transmission completes. + * If some packets still needs to be handled, due to TX coalesce, set + * pending_packets to true to make NAPI arm the TX coal timer. */ -static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) +static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue, + bool *pending_packets) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; struct stmmac_txq_stats *txq_stats = &priv->xstats.txq_stats[queue]; @@ -2706,7 +2718,7 @@ static int stmmac_tx_clean(struct stmmac_priv *priv, int budget, u32 queue) /* We still have pending packets, let's call for a new scheduling */ if (tx_q->dirty_tx != tx_q->cur_tx) - stmmac_tx_timer_arm(priv, queue); + *pending_packets = true; flags = u64_stats_update_begin_irqsave(&txq_stats->syncp); txq_stats->tx_packets += tx_packets; @@ -2996,13 +3008,25 @@ static void stmmac_tx_timer_arm(struct stmmac_priv *priv, u32 queue) { struct stmmac_tx_queue *tx_q = &priv->dma_conf.tx_queue[queue]; u32 tx_coal_timer = priv->tx_coal_timer[queue]; + struct stmmac_channel *ch; + struct napi_struct *napi; if (!tx_coal_timer) return; - hrtimer_start(&tx_q->txtimer, - STMMAC_COAL_TIMER(tx_coal_timer), - HRTIMER_MODE_REL); + ch = &priv->channel[tx_q->queue_index]; + napi = tx_q->xsk_pool ? &ch->rxtx_napi : &ch->tx_napi; + + /* Arm timer only if napi is not already scheduled. + * Try to cancel any timer if napi is scheduled, timer will be armed + * again in the next scheduled napi. + */ + if (unlikely(!napi_is_scheduled(napi))) + hrtimer_start(&tx_q->txtimer, + STMMAC_COAL_TIMER(tx_coal_timer), + HRTIMER_MODE_REL); + else + hrtimer_try_to_cancel(&tx_q->txtimer); } /** @@ -5560,6 +5584,7 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) container_of(napi, struct stmmac_channel, tx_napi); struct stmmac_priv *priv = ch->priv_data; struct stmmac_txq_stats *txq_stats; + bool pending_packets = false; u32 chan = ch->index; unsigned long flags; int work_done; @@ -5569,7 +5594,7 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) txq_stats->napi_poll++; u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); - work_done = stmmac_tx_clean(priv, budget, chan); + work_done = stmmac_tx_clean(priv, budget, chan, &pending_packets); work_done = min(work_done, budget); if (work_done < budget && napi_complete_done(napi, work_done)) { @@ -5580,6 +5605,10 @@ static int stmmac_napi_poll_tx(struct napi_struct *napi, int budget) spin_unlock_irqrestore(&ch->lock, flags); } + /* TX still have packet to handle, check if we need to arm tx timer */ + if (pending_packets) + stmmac_tx_timer_arm(priv, chan); + return work_done; } @@ -5588,6 +5617,7 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget) struct stmmac_channel *ch = container_of(napi, struct stmmac_channel, rxtx_napi); struct stmmac_priv *priv = ch->priv_data; + bool tx_pending_packets = false; int rx_done, tx_done, rxtx_done; struct stmmac_rxq_stats *rxq_stats; struct stmmac_txq_stats *txq_stats; @@ -5604,7 +5634,7 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget) txq_stats->napi_poll++; u64_stats_update_end_irqrestore(&txq_stats->syncp, flags); - tx_done = stmmac_tx_clean(priv, budget, chan); + tx_done = stmmac_tx_clean(priv, budget, chan, &tx_pending_packets); tx_done = min(tx_done, budget); rx_done = stmmac_rx_zc(priv, budget, chan); @@ -5629,6 +5659,10 @@ static int stmmac_napi_poll_rxtx(struct napi_struct *napi, int budget) spin_unlock_irqrestore(&ch->lock, flags); } + /* TX still have packet to handle, check if we need to arm tx timer */ + if (tx_pending_packets) + stmmac_tx_timer_arm(priv, chan); + return min(rxtx_done, budget - 1); } @@ -7182,6 +7216,7 @@ int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt) priv->rss.table[i] = ethtool_rxfh_indir_default(i, rx_cnt); + stmmac_set_half_duplex(priv); stmmac_napi_add(dev); if (netif_running(dev)) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 1be06b96c35f..bffa5c017032 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -191,26 +191,33 @@ static int stmmac_enable(struct ptp_clock_info *ptp, priv->systime_flags); write_unlock_irqrestore(&priv->ptp_lock, flags); break; - case PTP_CLK_REQ_EXTTS: - if (on) - priv->plat->flags |= STMMAC_FLAG_EXT_SNAPSHOT_EN; - else - priv->plat->flags &= ~STMMAC_FLAG_EXT_SNAPSHOT_EN; + case PTP_CLK_REQ_EXTTS: { + u8 channel; + mutex_lock(&priv->aux_ts_lock); acr_value = readl(ptpaddr + PTP_ACR); + channel = ilog2(FIELD_GET(PTP_ACR_MASK, acr_value)); acr_value &= ~PTP_ACR_MASK; + if (on) { + if (FIELD_GET(PTP_ACR_MASK, acr_value)) { + netdev_err(priv->dev, + "Cannot enable auxiliary snapshot %d as auxiliary snapshot %d is already enabled", + rq->extts.index, channel); + mutex_unlock(&priv->aux_ts_lock); + return -EBUSY; + } + + priv->plat->flags |= STMMAC_FLAG_EXT_SNAPSHOT_EN; + /* Enable External snapshot trigger */ - acr_value |= priv->plat->ext_snapshot_num; + acr_value |= PTP_ACR_ATSEN(rq->extts.index); acr_value |= PTP_ACR_ATSFC; - netdev_dbg(priv->dev, "Auxiliary Snapshot %d enabled.\n", - priv->plat->ext_snapshot_num >> - PTP_ACR_ATSEN_SHIFT); } else { - netdev_dbg(priv->dev, "Auxiliary Snapshot %d disabled.\n", - priv->plat->ext_snapshot_num >> - PTP_ACR_ATSEN_SHIFT); + priv->plat->flags &= ~STMMAC_FLAG_EXT_SNAPSHOT_EN; } + netdev_dbg(priv->dev, "Auxiliary Snapshot %d %s.\n", + rq->extts.index, on ? "enabled" : "disabled"); writel(acr_value, ptpaddr + PTP_ACR); mutex_unlock(&priv->aux_ts_lock); /* wait for auxts fifo clear to finish */ @@ -218,6 +225,7 @@ static int stmmac_enable(struct ptp_clock_info *ptp, !(acr_value & PTP_ACR_ATSFC), 10, 10000); break; + } default: break; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h index d1fe4b46f162..fce3fba2ffd2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h @@ -79,7 +79,7 @@ #define PTP_ACR_ATSEN1 BIT(5) /* Auxiliary Snapshot 1 Enable */ #define PTP_ACR_ATSEN2 BIT(6) /* Auxiliary Snapshot 2 Enable */ #define PTP_ACR_ATSEN3 BIT(7) /* Auxiliary Snapshot 3 Enable */ -#define PTP_ACR_ATSEN_SHIFT 5 /* Auxiliary Snapshot shift */ +#define PTP_ACR_ATSEN(index) (PTP_ACR_ATSEN0 << (index)) #define PTP_ACR_MASK GENMASK(7, 4) /* Aux Snapshot Mask */ #define PMC_ART_VALUE0 0x01 /* PMC_ART[15:0] timer value */ #define PMC_ART_VALUE1 0x02 /* PMC_ART[31:16] timer value */ diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 0784a3d0bbff..e60b557d59b9 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -90,12 +90,16 @@ config TI_CPTS The unit can time stamp PTP UDP/IPv4 and Layer 2 packets, and the driver offers a PTP Hardware Clock. +config TI_K3_CPPI_DESC_POOL + tristate + config TI_K3_AM65_CPSW_NUSS tristate "TI K3 AM654x/J721E CPSW Ethernet driver" depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER select NET_DEVLINK select TI_DAVINCI_MDIO select PHYLINK + select TI_K3_CPPI_DESC_POOL imply PHY_TI_GMII_SEL depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS help @@ -180,6 +184,7 @@ config TI_ICSSG_PRUETH tristate "TI Gigabit PRU Ethernet driver" select PHYLIB select TI_ICSS_IEP + select TI_K3_CPPI_DESC_POOL depends on PRU_REMOTEPROC depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER help diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index e38ec9d6c99b..27de1d697134 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -23,14 +23,15 @@ keystone_netcp-y := netcp_core.o cpsw_ale.o obj-$(CONFIG_TI_KEYSTONE_NETCP_ETHSS) += keystone_netcp_ethss.o keystone_netcp_ethss-y := netcp_ethss.o netcp_sgmii.o netcp_xgbepcsr.o cpsw_ale.o +obj-$(CONFIG_TI_K3_CPPI_DESC_POOL) += k3-cppi-desc-pool.o + obj-$(CONFIG_TI_K3_AM65_CPSW_NUSS) += ti-am65-cpsw-nuss.o -ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o k3-cppi-desc-pool.o am65-cpsw-qos.o +ti-am65-cpsw-nuss-y := am65-cpsw-nuss.o cpsw_sl.o am65-cpsw-ethtool.o cpsw_ale.o am65-cpsw-qos.o ti-am65-cpsw-nuss-$(CONFIG_TI_K3_AM65_CPSW_SWITCHDEV) += am65-cpsw-switchdev.o obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o obj-$(CONFIG_TI_ICSSG_PRUETH) += icssg-prueth.o -icssg-prueth-y := k3-cppi-desc-pool.o \ - icssg/icssg_prueth.o \ +icssg-prueth-y := icssg/icssg_prueth.o \ icssg/icssg_classifier.o \ icssg/icssg_queues.o \ icssg/icssg_config.o \ diff --git a/drivers/net/ethernet/ti/davinci_emac.c b/drivers/net/ethernet/ti/davinci_emac.c index 23f8bc1cd20d..b0950a318c42 100644 --- a/drivers/net/ethernet/ti/davinci_emac.c +++ b/drivers/net/ethernet/ti/davinci_emac.c @@ -1928,18 +1928,20 @@ static int davinci_emac_probe(struct platform_device *pdev) goto err_free_rxchan; ndev->irq = rc; - rc = davinci_emac_try_get_mac(pdev, res_ctrl ? 0 : 1, priv->mac_addr); - if (!rc) - eth_hw_addr_set(ndev, priv->mac_addr); - + /* If the MAC address is not present, read the registers from the SoC */ if (!is_valid_ether_addr(priv->mac_addr)) { - /* Use random MAC if still none obtained. */ - eth_hw_addr_random(ndev); - memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len); - dev_warn(&pdev->dev, "using random MAC addr: %pM\n", - priv->mac_addr); + rc = davinci_emac_try_get_mac(pdev, res_ctrl ? 0 : 1, priv->mac_addr); + if (!rc) + eth_hw_addr_set(ndev, priv->mac_addr); + + if (!is_valid_ether_addr(priv->mac_addr)) { + /* Use random MAC if still none obtained. */ + eth_hw_addr_random(ndev); + memcpy(priv->mac_addr, ndev->dev_addr, ndev->addr_len); + dev_warn(&pdev->dev, "using random MAC addr: %pM\n", + priv->mac_addr); + } } - ndev->netdev_ops = &emac_netdev_ops; ndev->ethtool_ops = ðtool_ops; netif_napi_add(ndev, &priv->napi, emac_poll); diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index c1da70f247d4..99de8a40ed60 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -379,9 +379,9 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice) /* Bitmask for ICSSG r30 commands */ static const struct icssg_r30_cmd emac_r32_bitmask[] = { - {{0xffff0004, 0xffff0100, 0xffff0100, EMAC_NONE}}, /* EMAC_PORT_DISABLE */ + {{0xffff0004, 0xffff0100, 0xffff0004, EMAC_NONE}}, /* EMAC_PORT_DISABLE */ {{0xfffb0040, 0xfeff0200, 0xfeff0200, EMAC_NONE}}, /* EMAC_PORT_BLOCK */ - {{0xffbb0000, 0xfcff0000, 0xdcff0000, EMAC_NONE}}, /* EMAC_PORT_FORWARD */ + {{0xffbb0000, 0xfcff0000, 0xdcfb0000, EMAC_NONE}}, /* EMAC_PORT_FORWARD */ {{0xffbb0000, 0xfcff0000, 0xfcff2000, EMAC_NONE}}, /* EMAC_PORT_FORWARD_WO_LEARNING */ {{0xffff0001, EMAC_NONE, EMAC_NONE, EMAC_NONE}}, /* ACCEPT ALL */ {{0xfffe0002, EMAC_NONE, EMAC_NONE, EMAC_NONE}}, /* ACCEPT TAGGED */ diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index de3bb9da3b13..6c4b64227ac8 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1659,6 +1659,19 @@ static void emac_ndo_get_stats64(struct net_device *ndev, stats->tx_dropped = ndev->stats.tx_dropped; } +static int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name, + size_t len) +{ + struct prueth_emac *emac = netdev_priv(ndev); + int ret; + + ret = snprintf(name, len, "p%d", emac->port_id); + if (ret >= len) + return -EINVAL; + + return 0; +} + static const struct net_device_ops emac_netdev_ops = { .ndo_open = emac_ndo_open, .ndo_stop = emac_ndo_stop, @@ -1669,6 +1682,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_set_rx_mode = emac_ndo_set_rx_mode, .ndo_eth_ioctl = emac_ndo_ioctl, .ndo_get_stats64 = emac_ndo_get_stats64, + .ndo_get_phys_port_name = emac_ndo_get_phys_port_name, }; /* get emac_port corresponding to eth_node name */ diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c index bb0b33927e3b..3dbadddd7e35 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_stats.c +++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c @@ -9,6 +9,9 @@ #include "icssg_stats.h" #include <linux/regmap.h> +#define ICSSG_TX_PACKET_OFFSET 0xA0 +#define ICSSG_TX_BYTE_OFFSET 0xEC + static u32 stats_base[] = { 0x54c, /* Slice 0 stats start */ 0xb18, /* Slice 1 stats start */ }; @@ -18,6 +21,7 @@ void emac_update_hardware_stats(struct prueth_emac *emac) struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); u32 base = stats_base[slice]; + u32 tx_pkt_cnt = 0; u32 val; int i; @@ -29,7 +33,12 @@ void emac_update_hardware_stats(struct prueth_emac *emac) base + icssg_all_stats[i].offset, val); + if (icssg_all_stats[i].offset == ICSSG_TX_PACKET_OFFSET) + tx_pkt_cnt = val; + emac->stats[i] += val; + if (icssg_all_stats[i].offset == ICSSG_TX_BYTE_OFFSET) + emac->stats[i] -= tx_pkt_cnt * 8; } } diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c index 38cc12f9f133..05cc7aab1ec8 100644 --- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c +++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c @@ -39,6 +39,7 @@ void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool) gen_pool_destroy(pool->gen_pool); /* frees pool->name */ } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_destroy); struct k3_cppi_desc_pool * k3_cppi_desc_pool_create_name(struct device *dev, size_t size, @@ -98,29 +99,38 @@ gen_pool_create_fail: devm_kfree(pool->dev, pool); return ERR_PTR(ret); } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_create_name); dma_addr_t k3_cppi_desc_pool_virt2dma(struct k3_cppi_desc_pool *pool, void *addr) { return addr ? pool->dma_addr + (addr - pool->cpumem) : 0; } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_virt2dma); void *k3_cppi_desc_pool_dma2virt(struct k3_cppi_desc_pool *pool, dma_addr_t dma) { return dma ? pool->cpumem + (dma - pool->dma_addr) : NULL; } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_dma2virt); void *k3_cppi_desc_pool_alloc(struct k3_cppi_desc_pool *pool) { return (void *)gen_pool_alloc(pool->gen_pool, pool->desc_size); } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_alloc); void k3_cppi_desc_pool_free(struct k3_cppi_desc_pool *pool, void *addr) { gen_pool_free(pool->gen_pool, (unsigned long)addr, pool->desc_size); } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_free); size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool) { return gen_pool_avail(pool->gen_pool) / pool->desc_size; } +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_avail); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("TI K3 CPPI5 descriptors pool API"); diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c index dc14a66583ff..44488c153ea2 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_wireless.c @@ -1217,7 +1217,7 @@ static int gelic_wl_set_encodeext(struct net_device *netdev, key_index = wl->current_key; if (!enc->length && (ext->ext_flags & IW_ENCODE_EXT_SET_TX_KEY)) { - /* reques to change default key index */ + /* request to change default key index */ pr_debug("%s: request to change default key to %d\n", __func__, key_index); wl->current_key = key_index; diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c index 652e6576e36a..3d43f808c86b 100644 --- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c +++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c @@ -679,11 +679,6 @@ static int ngbe_probe(struct pci_dev *pdev, pci_set_drvdata(pdev, wx); - netif_info(wx, probe, netdev, - "PHY: %s, PBA No: Wang Xun GbE Family Controller\n", - wx->mac_type == em_mac_type_mdi ? "Internal" : "External"); - netif_info(wx, probe, netdev, "%pM\n", netdev->dev_addr); - return 0; err_register: diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c index 474d55524e82..d6b2b3c781b6 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c @@ -71,114 +71,6 @@ static void txgbe_init_thermal_sensor_thresh(struct wx *wx) } /** - * txgbe_read_pba_string - Reads part number string from EEPROM - * @wx: pointer to hardware structure - * @pba_num: stores the part number string from the EEPROM - * @pba_num_size: part number string buffer length - * - * Reads the part number string from the EEPROM. - **/ -int txgbe_read_pba_string(struct wx *wx, u8 *pba_num, u32 pba_num_size) -{ - u16 pba_ptr, offset, length, data; - int ret_val; - - if (!pba_num) { - wx_err(wx, "PBA string buffer was null\n"); - return -EINVAL; - } - - ret_val = wx_read_ee_hostif(wx, - wx->eeprom.sw_region_offset + TXGBE_PBANUM0_PTR, - &data); - if (ret_val != 0) { - wx_err(wx, "NVM Read Error\n"); - return ret_val; - } - - ret_val = wx_read_ee_hostif(wx, - wx->eeprom.sw_region_offset + TXGBE_PBANUM1_PTR, - &pba_ptr); - if (ret_val != 0) { - wx_err(wx, "NVM Read Error\n"); - return ret_val; - } - - /* if data is not ptr guard the PBA must be in legacy format which - * means pba_ptr is actually our second data word for the PBA number - * and we can decode it into an ascii string - */ - if (data != TXGBE_PBANUM_PTR_GUARD) { - wx_err(wx, "NVM PBA number is not stored as string\n"); - - /* we will need 11 characters to store the PBA */ - if (pba_num_size < 11) { - wx_err(wx, "PBA string buffer too small\n"); - return -ENOMEM; - } - - /* extract hex string from data and pba_ptr */ - pba_num[0] = (data >> 12) & 0xF; - pba_num[1] = (data >> 8) & 0xF; - pba_num[2] = (data >> 4) & 0xF; - pba_num[3] = data & 0xF; - pba_num[4] = (pba_ptr >> 12) & 0xF; - pba_num[5] = (pba_ptr >> 8) & 0xF; - pba_num[6] = '-'; - pba_num[7] = 0; - pba_num[8] = (pba_ptr >> 4) & 0xF; - pba_num[9] = pba_ptr & 0xF; - - /* put a null character on the end of our string */ - pba_num[10] = '\0'; - - /* switch all the data but the '-' to hex char */ - for (offset = 0; offset < 10; offset++) { - if (pba_num[offset] < 0xA) - pba_num[offset] += '0'; - else if (pba_num[offset] < 0x10) - pba_num[offset] += 'A' - 0xA; - } - - return 0; - } - - ret_val = wx_read_ee_hostif(wx, pba_ptr, &length); - if (ret_val != 0) { - wx_err(wx, "NVM Read Error\n"); - return ret_val; - } - - if (length == 0xFFFF || length == 0) { - wx_err(wx, "NVM PBA number section invalid length\n"); - return -EINVAL; - } - - /* check if pba_num buffer is big enough */ - if (pba_num_size < (((u32)length * 2) - 1)) { - wx_err(wx, "PBA string buffer too small\n"); - return -ENOMEM; - } - - /* trim pba length from start of string */ - pba_ptr++; - length--; - - for (offset = 0; offset < length; offset++) { - ret_val = wx_read_ee_hostif(wx, pba_ptr + offset, &data); - if (ret_val != 0) { - wx_err(wx, "NVM Read Error\n"); - return ret_val; - } - pba_num[offset * 2] = (u8)(data >> 8); - pba_num[(offset * 2) + 1] = (u8)(data & 0xFF); - } - pba_num[offset * 2] = '\0'; - - return 0; -} - -/** * txgbe_calc_eeprom_checksum - Calculates and returns the checksum * @wx: pointer to hardware structure * @checksum: pointer to cheksum diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h index abc729eb187a..1f3ecf60e3c4 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.h @@ -6,7 +6,6 @@ int txgbe_disable_sec_tx_path(struct wx *wx); void txgbe_enable_sec_tx_path(struct wx *wx); -int txgbe_read_pba_string(struct wx *wx, u8 *pba_num, u32 pba_num_size); int txgbe_validate_eeprom_checksum(struct wx *wx, u16 *checksum_val); int txgbe_reset_hw(struct wx *wx); diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index 394f699c51da..70f0b5c01dac 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -540,7 +540,6 @@ static int txgbe_probe(struct pci_dev *pdev, u16 eeprom_verh = 0, eeprom_verl = 0, offset = 0; u16 eeprom_cfg_blkh = 0, eeprom_cfg_blkl = 0; u16 build = 0, major = 0, patch = 0; - u8 part_str[TXGBE_PBANUM_LENGTH]; u32 etrack_id = 0; err = pci_enable_device_mem(pdev); @@ -738,13 +737,6 @@ static int txgbe_probe(struct pci_dev *pdev, else dev_warn(&pdev->dev, "Failed to enumerate PF devices.\n"); - /* First try to read PBA as a string */ - err = txgbe_read_pba_string(wx, part_str, TXGBE_PBANUM_LENGTH); - if (err) - strncpy(part_str, "Unknown", TXGBE_PBANUM_LENGTH); - - netif_info(wx, probe, netdev, "%pM\n", netdev->dev_addr); - return 0; err_remove_phy: diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 51199c355f95..3ba9ce43f394 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -88,9 +88,6 @@ #define TXGBE_XPCS_IDA_ADDR 0x13000 #define TXGBE_XPCS_IDA_DATA 0x13004 -/* Part Number String Length */ -#define TXGBE_PBANUM_LENGTH 32 - /* Checksum and EEPROM pointers */ #define TXGBE_EEPROM_LAST_WORD 0x800 #define TXGBE_EEPROM_CHECKSUM 0x2F @@ -98,9 +95,6 @@ #define TXGBE_EEPROM_VERSION_L 0x1D #define TXGBE_EEPROM_VERSION_H 0x1E #define TXGBE_ISCSI_BOOT_CONFIG 0x07 -#define TXGBE_PBANUM0_PTR 0x05 -#define TXGBE_PBANUM1_PTR 0x06 -#define TXGBE_PBANUM_PTR_GUARD 0xFAFA #define TXGBE_MAX_MSIX_VECTORS 64 #define TXGBE_MAX_FDIR_INDICES 63 diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 23041eeec121..acd9c615d1f4 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -800,57 +800,6 @@ static u8 geneve_get_dsfield(struct sk_buff *skb, struct net_device *dev, return dsfield; } -#if IS_ENABLED(CONFIG_IPV6) -static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, - struct net_device *dev, - struct geneve_sock *gs6, - struct flowi6 *fl6, - const struct ip_tunnel_info *info, - __be16 dport, __be16 sport) -{ - bool use_cache = ip_tunnel_dst_cache_usable(skb, info); - struct geneve_dev *geneve = netdev_priv(dev); - struct dst_entry *dst = NULL; - struct dst_cache *dst_cache; - __u8 prio; - - if (!gs6) - return ERR_PTR(-EIO); - - memset(fl6, 0, sizeof(*fl6)); - fl6->flowi6_mark = skb->mark; - fl6->flowi6_proto = IPPROTO_UDP; - fl6->daddr = info->key.u.ipv6.dst; - fl6->saddr = info->key.u.ipv6.src; - fl6->fl6_dport = dport; - fl6->fl6_sport = sport; - - prio = geneve_get_dsfield(skb, dev, info, &use_cache); - fl6->flowlabel = ip6_make_flowinfo(prio, info->key.label); - dst_cache = (struct dst_cache *)&info->dst_cache; - if (use_cache) { - dst = dst_cache_get_ip6(dst_cache, &fl6->saddr); - if (dst) - return dst; - } - dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6, - NULL); - if (IS_ERR(dst)) { - netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr); - return ERR_PTR(-ENETUNREACH); - } - if (dst->dev == dev) { /* is this necessary? */ - netdev_dbg(dev, "circular route to %pI6\n", &fl6->daddr); - dst_release(dst); - return ERR_PTR(-ELOOP); - } - - if (use_cache) - dst_cache_set_ip6(dst_cache, dst, &fl6->saddr); - return dst; -} -#endif - static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_dev *geneve, const struct ip_tunnel_info *info) @@ -967,7 +916,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); const struct ip_tunnel_key *key = &info->key; struct dst_entry *dst = NULL; - struct flowi6 fl6; + struct in6_addr saddr; + bool use_cache; __u8 prio, ttl; __be16 sport; int err; @@ -975,9 +925,18 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, if (!pskb_inet_may_pull(skb)) return -EINVAL; + if (!gs6) + return -EIO; + + use_cache = ip_tunnel_dst_cache_usable(skb, info); + prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); - dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info, - geneve->cfg.info.key.tp_dst, sport); + + dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, + &saddr, key, sport, + geneve->cfg.info.key.tp_dst, prio, + use_cache ? + (struct dst_cache *)&info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); @@ -999,8 +958,8 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, return -ENOMEM; } - unclone->key.u.ipv6.dst = fl6.saddr; - unclone->key.u.ipv6.src = fl6.daddr; + unclone->key.u.ipv6.dst = saddr; + unclone->key.u.ipv6.src = info->key.u.ipv6.dst; } if (!pskb_may_pull(skb, ETH_HLEN)) { @@ -1014,12 +973,10 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, return -EMSGSIZE; } + prio = ip_tunnel_ecn_encap(prio, ip_hdr(skb), skb); if (geneve->cfg.collect_md) { - prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); ttl = key->ttl; } else { - prio = ip_tunnel_ecn_encap(ip6_tclass(fl6.flowlabel), - ip_hdr(skb), skb); if (geneve->cfg.ttl_inherit) ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb); else @@ -1032,7 +989,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, return err; udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, - &fl6.saddr, &fl6.daddr, prio, ttl, + &saddr, &key->u.ipv6.dst, prio, ttl, info->key.label, sport, geneve->cfg.info.key.tp_dst, !(info->key.tun_flags & TUNNEL_CSUM)); return 0; @@ -1126,19 +1083,28 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) #if IS_ENABLED(CONFIG_IPV6) } else if (ip_tunnel_info_af(info) == AF_INET6) { struct dst_entry *dst; - struct flowi6 fl6; - struct geneve_sock *gs6 = rcu_dereference(geneve->sock6); + struct in6_addr saddr; + bool use_cache; + u8 prio; + + if (!gs6) + return -EIO; + + use_cache = ip_tunnel_dst_cache_usable(skb, info); + prio = geneve_get_dsfield(skb, dev, info, &use_cache); sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); - dst = geneve_get_v6_dst(skb, dev, gs6, &fl6, info, - geneve->cfg.info.key.tp_dst, sport); + dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0, + &saddr, &info->key, sport, + geneve->cfg.info.key.tp_dst, prio, + use_cache ? &info->dst_cache : NULL); if (IS_ERR(dst)) return PTR_ERR(dst); dst_release(dst); - info->key.u.ipv6.src = fl6.saddr; + info->key.u.ipv6.src = saddr; #endif } else { return -EINVAL; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index b3aa0c3d5826..b1919278e931 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -872,8 +872,9 @@ static int gtp_build_skb_ip4(struct sk_buff *skb, struct net_device *dev, skb_dst_update_pmtu_no_confirm(skb, mtu); - if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) && - mtu < ntohs(iph->tot_len)) { + if (iph->frag_off & htons(IP_DF) && + ((!skb_is_gso(skb) && skb->len > mtu) || + (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu)))) { netdev_dbg(dev, "packet too big, fragmentation needed\n"); icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/drivers/net/ieee802154/adf7242.c b/drivers/net/ieee802154/adf7242.c index a03490ba2e5b..cc7ddc40020f 100644 --- a/drivers/net/ieee802154/adf7242.c +++ b/drivers/net/ieee802154/adf7242.c @@ -1162,9 +1162,10 @@ static int adf7242_stats_show(struct seq_file *file, void *offset) static void adf7242_debugfs_init(struct adf7242_local *lp) { - char debugfs_dir_name[DNAME_INLINE_LEN + 1] = "adf7242-"; + char debugfs_dir_name[DNAME_INLINE_LEN + 1]; - strncat(debugfs_dir_name, dev_name(&lp->spi->dev), DNAME_INLINE_LEN); + snprintf(debugfs_dir_name, sizeof(debugfs_dir_name), + "adf7242-%s", dev_name(&lp->spi->dev)); lp->debugfs_root = debugfs_create_dir(debugfs_dir_name, NULL); diff --git a/drivers/net/mdio/mdio-mux.c b/drivers/net/mdio/mdio-mux.c index a881e3523328..bef4cce71287 100644 --- a/drivers/net/mdio/mdio-mux.c +++ b/drivers/net/mdio/mdio-mux.c @@ -55,6 +55,27 @@ out: return r; } +static int mdio_mux_read_c45(struct mii_bus *bus, int phy_id, int dev_addr, + int regnum) +{ + struct mdio_mux_child_bus *cb = bus->priv; + struct mdio_mux_parent_bus *pb = cb->parent; + int r; + + mutex_lock_nested(&pb->mii_bus->mdio_lock, MDIO_MUTEX_MUX); + r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data); + if (r) + goto out; + + pb->current_child = cb->bus_number; + + r = pb->mii_bus->read_c45(pb->mii_bus, phy_id, dev_addr, regnum); +out: + mutex_unlock(&pb->mii_bus->mdio_lock); + + return r; +} + /* * The parent bus' lock is used to order access to the switch_fn. */ @@ -80,6 +101,28 @@ out: return r; } +static int mdio_mux_write_c45(struct mii_bus *bus, int phy_id, int dev_addr, + int regnum, u16 val) +{ + struct mdio_mux_child_bus *cb = bus->priv; + struct mdio_mux_parent_bus *pb = cb->parent; + + int r; + + mutex_lock_nested(&pb->mii_bus->mdio_lock, MDIO_MUTEX_MUX); + r = pb->switch_fn(pb->current_child, cb->bus_number, pb->switch_data); + if (r) + goto out; + + pb->current_child = cb->bus_number; + + r = pb->mii_bus->write_c45(pb->mii_bus, phy_id, dev_addr, regnum, val); +out: + mutex_unlock(&pb->mii_bus->mdio_lock); + + return r; +} + static int parent_count; static void mdio_mux_uninit_children(struct mdio_mux_parent_bus *pb) @@ -173,6 +216,10 @@ int mdio_mux_init(struct device *dev, cb->mii_bus->parent = dev; cb->mii_bus->read = mdio_mux_read; cb->mii_bus->write = mdio_mux_write; + if (parent_bus->read_c45) + cb->mii_bus->read_c45 = mdio_mux_read_c45; + if (parent_bus->write_c45) + cb->mii_bus->write_c45 = mdio_mux_write_c45; r = of_mdiobus_register(cb->mii_bus, child_bus_node); if (r) { mdiobus_free(cb->mii_bus); diff --git a/drivers/net/mdio/mdio-xgene.c b/drivers/net/mdio/mdio-xgene.c index 495fbe35b6ce..2772a3098543 100644 --- a/drivers/net/mdio/mdio-xgene.c +++ b/drivers/net/mdio/mdio-xgene.c @@ -437,7 +437,7 @@ static void xgene_mdio_remove(struct platform_device *pdev) static struct platform_driver xgene_mdio_driver = { .driver = { .name = "xgene-mdio", - .of_match_table = of_match_ptr(xgene_mdio_of_match), + .of_match_table = xgene_mdio_of_match, .acpi_match_table = ACPI_PTR(xgene_mdio_acpi_match), }, .probe = xgene_mdio_probe, diff --git a/drivers/net/netdevsim/health.c b/drivers/net/netdevsim/health.c index eb04ed715d2d..70e8bdf34be9 100644 --- a/drivers/net/netdevsim/health.c +++ b/drivers/net/netdevsim/health.c @@ -63,91 +63,45 @@ nsim_dev_dummy_reporter_recover(struct devlink_health_reporter *reporter, static int nsim_dev_dummy_fmsg_put(struct devlink_fmsg *fmsg, u32 binary_len) { char *binary; - int err; int i; - err = devlink_fmsg_bool_pair_put(fmsg, "test_bool", true); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "test_u8", 1); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "test_u32", 3); - if (err) - return err; - err = devlink_fmsg_u64_pair_put(fmsg, "test_u64", 4); - if (err) - return err; - err = devlink_fmsg_string_pair_put(fmsg, "test_string", "somestring"); - if (err) - return err; + devlink_fmsg_bool_pair_put(fmsg, "test_bool", true); + devlink_fmsg_u8_pair_put(fmsg, "test_u8", 1); + devlink_fmsg_u32_pair_put(fmsg, "test_u32", 3); + devlink_fmsg_u64_pair_put(fmsg, "test_u64", 4); + devlink_fmsg_string_pair_put(fmsg, "test_string", "somestring"); binary = kmalloc(binary_len, GFP_KERNEL | __GFP_NOWARN); if (!binary) return -ENOMEM; get_random_bytes(binary, binary_len); - err = devlink_fmsg_binary_pair_put(fmsg, "test_binary", binary, binary_len); + devlink_fmsg_binary_pair_put(fmsg, "test_binary", binary, binary_len); kfree(binary); - if (err) - return err; - err = devlink_fmsg_pair_nest_start(fmsg, "test_nest"); - if (err) - return err; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - err = devlink_fmsg_bool_pair_put(fmsg, "nested_test_bool", false); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, "nested_test_u8", false); - if (err) - return err; - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; + devlink_fmsg_pair_nest_start(fmsg, "test_nest"); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_bool_pair_put(fmsg, "nested_test_bool", false); + devlink_fmsg_u8_pair_put(fmsg, "nested_test_u8", false); + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "test_u32_array"); - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; + for (i = 0; i < 10; i++) + devlink_fmsg_u32_put(fmsg, i); + devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_start(fmsg, "test_array_of_objects"); - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_u32_array"); - if (err) - return err; for (i = 0; i < 10; i++) { - err = devlink_fmsg_u32_put(fmsg, i); - if (err) - return err; + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_bool_pair_put(fmsg, "in_array_nested_test_bool", + false); + devlink_fmsg_u8_pair_put(fmsg, "in_array_nested_test_u8", i); + devlink_fmsg_obj_nest_end(fmsg); } - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; + devlink_fmsg_arr_pair_nest_end(fmsg); - err = devlink_fmsg_arr_pair_nest_start(fmsg, "test_array_of_objects"); - if (err) - return err; - for (i = 0; i < 10; i++) { - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - err = devlink_fmsg_bool_pair_put(fmsg, - "in_array_nested_test_bool", - false); - if (err) - return err; - err = devlink_fmsg_u8_pair_put(fmsg, - "in_array_nested_test_u8", - i); - if (err) - return err; - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - } - return devlink_fmsg_arr_pair_nest_end(fmsg); + return 0; } static int @@ -157,14 +111,10 @@ nsim_dev_dummy_reporter_dump(struct devlink_health_reporter *reporter, { struct nsim_dev_health *health = devlink_health_reporter_priv(reporter); struct nsim_dev_dummy_reporter_ctx *ctx = priv_ctx; - int err; - if (ctx) { - err = devlink_fmsg_string_pair_put(fmsg, "break_message", - ctx->break_msg); - if (err) - return err; - } + if (ctx) + devlink_fmsg_string_pair_put(fmsg, "break_message", ctx->break_msg); + return nsim_dev_dummy_fmsg_put(fmsg, health->binary_len); } @@ -174,15 +124,11 @@ nsim_dev_dummy_reporter_diagnose(struct devlink_health_reporter *reporter, struct netlink_ext_ack *extack) { struct nsim_dev_health *health = devlink_health_reporter_priv(reporter); - int err; - if (health->recovered_break_msg) { - err = devlink_fmsg_string_pair_put(fmsg, - "recovered_break_message", - health->recovered_break_msg); - if (err) - return err; - } + if (health->recovered_break_msg) + devlink_fmsg_string_pair_put(fmsg, "recovered_break_message", + health->recovered_break_msg); + return nsim_dev_dummy_fmsg_put(fmsg, health->binary_len); } diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c new file mode 100644 index 000000000000..5a0f86f38f09 --- /dev/null +++ b/drivers/net/netkit.c @@ -0,0 +1,936 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2023 Isovalent */ + +#include <linux/netdevice.h> +#include <linux/ethtool.h> +#include <linux/etherdevice.h> +#include <linux/filter.h> +#include <linux/netfilter_netdev.h> +#include <linux/bpf_mprog.h> + +#include <net/netkit.h> +#include <net/dst.h> +#include <net/tcx.h> + +#define DRV_NAME "netkit" + +struct netkit { + /* Needed in fast-path */ + struct net_device __rcu *peer; + struct bpf_mprog_entry __rcu *active; + enum netkit_action policy; + struct bpf_mprog_bundle bundle; + + /* Needed in slow-path */ + enum netkit_mode mode; + bool primary; + u32 headroom; +}; + +struct netkit_link { + struct bpf_link link; + struct net_device *dev; + u32 location; +}; + +static __always_inline int +netkit_run(const struct bpf_mprog_entry *entry, struct sk_buff *skb, + enum netkit_action ret) +{ + const struct bpf_mprog_fp *fp; + const struct bpf_prog *prog; + + bpf_mprog_foreach_prog(entry, fp, prog) { + bpf_compute_data_pointers(skb); + ret = bpf_prog_run(prog, skb); + if (ret != NETKIT_NEXT) + break; + } + return ret; +} + +static void netkit_prep_forward(struct sk_buff *skb, bool xnet) +{ + skb_scrub_packet(skb, xnet); + skb->priority = 0; + nf_skip_egress(skb, true); +} + +static struct netkit *netkit_priv(const struct net_device *dev) +{ + return netdev_priv(dev); +} + +static netdev_tx_t netkit_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + enum netkit_action ret = READ_ONCE(nk->policy); + netdev_tx_t ret_dev = NET_XMIT_SUCCESS; + const struct bpf_mprog_entry *entry; + struct net_device *peer; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (unlikely(!peer || !(peer->flags & IFF_UP) || + !pskb_may_pull(skb, ETH_HLEN) || + skb_orphan_frags(skb, GFP_ATOMIC))) + goto drop; + netkit_prep_forward(skb, !net_eq(dev_net(dev), dev_net(peer))); + skb->dev = peer; + entry = rcu_dereference(nk->active); + if (entry) + ret = netkit_run(entry, skb, ret); + switch (ret) { + case NETKIT_NEXT: + case NETKIT_PASS: + skb->protocol = eth_type_trans(skb, skb->dev); + skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); + __netif_rx(skb); + break; + case NETKIT_REDIRECT: + skb_do_redirect(skb); + break; + case NETKIT_DROP: + default: +drop: + kfree_skb(skb); + dev_core_stats_tx_dropped_inc(dev); + ret_dev = NET_XMIT_DROP; + break; + } + rcu_read_unlock(); + return ret_dev; +} + +static int netkit_open(struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + if (!peer) + return -ENOTCONN; + if (peer->flags & IFF_UP) { + netif_carrier_on(dev); + netif_carrier_on(peer); + } + return 0; +} + +static int netkit_close(struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + netif_carrier_off(dev); + if (peer) + netif_carrier_off(peer); + return 0; +} + +static int netkit_get_iflink(const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer; + int iflink = 0; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (peer) + iflink = peer->ifindex; + rcu_read_unlock(); + return iflink; +} + +static void netkit_set_multicast(struct net_device *dev) +{ + /* Nothing to do, we receive whatever gets pushed to us! */ +} + +static void netkit_set_headroom(struct net_device *dev, int headroom) +{ + struct netkit *nk = netkit_priv(dev), *nk2; + struct net_device *peer; + + if (headroom < 0) + headroom = NET_SKB_PAD; + + rcu_read_lock(); + peer = rcu_dereference(nk->peer); + if (unlikely(!peer)) + goto out; + + nk2 = netkit_priv(peer); + nk->headroom = headroom; + headroom = max(nk->headroom, nk2->headroom); + + peer->needed_headroom = headroom; + dev->needed_headroom = headroom; +out: + rcu_read_unlock(); +} + +static struct net_device *netkit_peer_dev(struct net_device *dev) +{ + return rcu_dereference(netkit_priv(dev)->peer); +} + +static void netkit_uninit(struct net_device *dev); + +static const struct net_device_ops netkit_netdev_ops = { + .ndo_open = netkit_open, + .ndo_stop = netkit_close, + .ndo_start_xmit = netkit_xmit, + .ndo_set_rx_mode = netkit_set_multicast, + .ndo_set_rx_headroom = netkit_set_headroom, + .ndo_get_iflink = netkit_get_iflink, + .ndo_get_peer_dev = netkit_peer_dev, + .ndo_uninit = netkit_uninit, + .ndo_features_check = passthru_features_check, +}; + +static void netkit_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strscpy(info->driver, DRV_NAME, sizeof(info->driver)); +} + +static const struct ethtool_ops netkit_ethtool_ops = { + .get_drvinfo = netkit_get_drvinfo, +}; + +static void netkit_setup(struct net_device *dev) +{ + static const netdev_features_t netkit_features_hw_vlan = + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_STAG_TX | + NETIF_F_HW_VLAN_STAG_RX; + static const netdev_features_t netkit_features = + netkit_features_hw_vlan | + NETIF_F_SG | + NETIF_F_FRAGLIST | + NETIF_F_HW_CSUM | + NETIF_F_RXCSUM | + NETIF_F_SCTP_CRC | + NETIF_F_HIGHDMA | + NETIF_F_GSO_SOFTWARE | + NETIF_F_GSO_ENCAP_ALL; + + ether_setup(dev); + dev->max_mtu = ETH_MAX_MTU; + + dev->flags |= IFF_NOARP; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + dev->priv_flags |= IFF_PHONY_HEADROOM; + dev->priv_flags |= IFF_NO_QUEUE; + + dev->ethtool_ops = &netkit_ethtool_ops; + dev->netdev_ops = &netkit_netdev_ops; + + dev->features |= netkit_features | NETIF_F_LLTX; + dev->hw_features = netkit_features; + dev->hw_enc_features = netkit_features; + dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE; + dev->vlan_features = dev->features & ~netkit_features_hw_vlan; + + dev->needs_free_netdev = true; + + netif_set_tso_max_size(dev, GSO_MAX_SIZE); +} + +static struct net *netkit_get_link_net(const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + return peer ? dev_net(peer) : dev_net(dev); +} + +static int netkit_check_policy(int policy, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + switch (policy) { + case NETKIT_PASS: + case NETKIT_DROP: + return 0; + default: + NL_SET_ERR_MSG_ATTR(extack, tb, + "Provided default xmit policy not supported"); + return -EINVAL; + } +} + +static int netkit_check_mode(int mode, struct nlattr *tb, + struct netlink_ext_ack *extack) +{ + switch (mode) { + case NETKIT_L2: + case NETKIT_L3: + return 0; + default: + NL_SET_ERR_MSG_ATTR(extack, tb, + "Provided device mode can only be L2 or L3"); + return -EINVAL; + } +} + +static int netkit_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct nlattr *attr = tb[IFLA_ADDRESS]; + + if (!attr) + return 0; + NL_SET_ERR_MSG_ATTR(extack, attr, + "Setting Ethernet address is not supported"); + return -EOPNOTSUPP; +} + +static struct rtnl_link_ops netkit_link_ops; + +static int netkit_new_link(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr; + enum netkit_action default_prim = NETKIT_PASS; + enum netkit_action default_peer = NETKIT_PASS; + enum netkit_mode mode = NETKIT_L3; + unsigned char ifname_assign_type; + struct ifinfomsg *ifmp = NULL; + struct net_device *peer; + char ifname[IFNAMSIZ]; + struct netkit *nk; + struct net *net; + int err; + + if (data) { + if (data[IFLA_NETKIT_MODE]) { + attr = data[IFLA_NETKIT_MODE]; + mode = nla_get_u32(attr); + err = netkit_check_mode(mode, attr, extack); + if (err < 0) + return err; + } + if (data[IFLA_NETKIT_PEER_INFO]) { + attr = data[IFLA_NETKIT_PEER_INFO]; + ifmp = nla_data(attr); + err = rtnl_nla_parse_ifinfomsg(peer_tb, attr, extack); + if (err < 0) + return err; + err = netkit_validate(peer_tb, NULL, extack); + if (err < 0) + return err; + tbp = peer_tb; + } + if (data[IFLA_NETKIT_POLICY]) { + attr = data[IFLA_NETKIT_POLICY]; + default_prim = nla_get_u32(attr); + err = netkit_check_policy(default_prim, attr, extack); + if (err < 0) + return err; + } + if (data[IFLA_NETKIT_PEER_POLICY]) { + attr = data[IFLA_NETKIT_PEER_POLICY]; + default_peer = nla_get_u32(attr); + err = netkit_check_policy(default_peer, attr, extack); + if (err < 0) + return err; + } + } + + if (ifmp && tbp[IFLA_IFNAME]) { + nla_strscpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); + ifname_assign_type = NET_NAME_USER; + } else { + strscpy(ifname, "nk%d", IFNAMSIZ); + ifname_assign_type = NET_NAME_ENUM; + } + + net = rtnl_link_get_net(src_net, tbp); + if (IS_ERR(net)) + return PTR_ERR(net); + + peer = rtnl_create_link(net, ifname, ifname_assign_type, + &netkit_link_ops, tbp, extack); + if (IS_ERR(peer)) { + put_net(net); + return PTR_ERR(peer); + } + + netif_inherit_tso_max(peer, dev); + + if (mode == NETKIT_L2) + eth_hw_addr_random(peer); + if (ifmp && dev->ifindex) + peer->ifindex = ifmp->ifi_index; + + nk = netkit_priv(peer); + nk->primary = false; + nk->policy = default_peer; + nk->mode = mode; + bpf_mprog_bundle_init(&nk->bundle); + + err = register_netdevice(peer); + put_net(net); + if (err < 0) + goto err_register_peer; + netif_carrier_off(peer); + if (mode == NETKIT_L2) + dev_change_flags(peer, peer->flags & ~IFF_NOARP, NULL); + + err = rtnl_configure_link(peer, NULL, 0, NULL); + if (err < 0) + goto err_configure_peer; + + if (mode == NETKIT_L2) + eth_hw_addr_random(dev); + if (tb[IFLA_IFNAME]) + nla_strscpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); + else + strscpy(dev->name, "nk%d", IFNAMSIZ); + + nk = netkit_priv(dev); + nk->primary = true; + nk->policy = default_prim; + nk->mode = mode; + bpf_mprog_bundle_init(&nk->bundle); + + err = register_netdevice(dev); + if (err < 0) + goto err_configure_peer; + netif_carrier_off(dev); + if (mode == NETKIT_L2) + dev_change_flags(dev, dev->flags & ~IFF_NOARP, NULL); + + rcu_assign_pointer(netkit_priv(dev)->peer, peer); + rcu_assign_pointer(netkit_priv(peer)->peer, dev); + return 0; +err_configure_peer: + unregister_netdevice(peer); + return err; +err_register_peer: + free_netdev(peer); + return err; +} + +static struct bpf_mprog_entry *netkit_entry_fetch(struct net_device *dev, + bool bundle_fallback) +{ + struct netkit *nk = netkit_priv(dev); + struct bpf_mprog_entry *entry; + + ASSERT_RTNL(); + entry = rcu_dereference_rtnl(nk->active); + if (entry) + return entry; + if (bundle_fallback) + return &nk->bundle.a; + return NULL; +} + +static void netkit_entry_update(struct net_device *dev, + struct bpf_mprog_entry *entry) +{ + struct netkit *nk = netkit_priv(dev); + + ASSERT_RTNL(); + rcu_assign_pointer(nk->active, entry); +} + +static void netkit_entry_sync(void) +{ + synchronize_rcu(); +} + +static struct net_device *netkit_dev_fetch(struct net *net, u32 ifindex, u32 which) +{ + struct net_device *dev; + struct netkit *nk; + + ASSERT_RTNL(); + + switch (which) { + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + break; + default: + return ERR_PTR(-EINVAL); + } + + dev = __dev_get_by_index(net, ifindex); + if (!dev) + return ERR_PTR(-ENODEV); + if (dev->netdev_ops != &netkit_netdev_ops) + return ERR_PTR(-ENXIO); + + nk = netkit_priv(dev); + if (!nk->primary) + return ERR_PTR(-EACCES); + if (which == BPF_NETKIT_PEER) { + dev = rcu_dereference_rtnl(nk->peer); + if (!dev) + return ERR_PTR(-ENODEV); + } + return dev; +} + +int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_mprog_entry *entry, *entry_new; + struct bpf_prog *replace_prog = NULL; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex, + attr->attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + entry = netkit_entry_fetch(dev, true); + if (attr->attach_flags & BPF_F_REPLACE) { + replace_prog = bpf_prog_get_type(attr->replace_bpf_fd, + prog->type); + if (IS_ERR(replace_prog)) { + ret = PTR_ERR(replace_prog); + replace_prog = NULL; + goto out; + } + } + ret = bpf_mprog_attach(entry, &entry_new, prog, NULL, replace_prog, + attr->attach_flags, attr->relative_fd, + attr->expected_revision); + if (!ret) { + if (entry != entry_new) { + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + } + bpf_mprog_commit(entry); + } +out: + if (replace_prog) + bpf_prog_put(replace_prog); + rtnl_unlock(); + return ret; +} + +int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, attr->target_ifindex, + attr->attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, prog, NULL, attr->attach_flags, + attr->relative_fd, attr->expected_revision); + if (!ret) { + if (!bpf_mprog_total(entry_new)) + entry_new = NULL; + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) +{ + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, + attr->query.target_ifindex, + attr->query.attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + ret = bpf_mprog_query(attr, uattr, netkit_entry_fetch(dev, false)); +out: + rtnl_unlock(); + return ret; +} + +static struct netkit_link *netkit_link(const struct bpf_link *link) +{ + return container_of(link, struct netkit_link, link); +} + +static int netkit_link_prog_attach(struct bpf_link *link, u32 flags, + u32 id_or_fd, u64 revision) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev = nkl->dev; + int ret; + + ASSERT_RTNL(); + entry = netkit_entry_fetch(dev, true); + ret = bpf_mprog_attach(entry, &entry_new, link->prog, link, NULL, flags, + id_or_fd, revision); + if (!ret) { + if (entry != entry_new) { + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + } + bpf_mprog_commit(entry); + } + return ret; +} + +static void netkit_link_release(struct bpf_link *link) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = nkl->dev; + if (!dev) + goto out; + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_detach(entry, &entry_new, link->prog, link, 0, 0, 0); + if (!ret) { + if (!bpf_mprog_total(entry_new)) + entry_new = NULL; + netkit_entry_update(dev, entry_new); + netkit_entry_sync(); + bpf_mprog_commit(entry); + nkl->dev = NULL; + } +out: + WARN_ON_ONCE(ret); + rtnl_unlock(); +} + +static int netkit_link_update(struct bpf_link *link, struct bpf_prog *nprog, + struct bpf_prog *oprog) +{ + struct netkit_link *nkl = netkit_link(link); + struct bpf_mprog_entry *entry, *entry_new; + struct net_device *dev; + int ret = 0; + + rtnl_lock(); + dev = nkl->dev; + if (!dev) { + ret = -ENOLINK; + goto out; + } + if (oprog && link->prog != oprog) { + ret = -EPERM; + goto out; + } + oprog = link->prog; + if (oprog == nprog) { + bpf_prog_put(nprog); + goto out; + } + entry = netkit_entry_fetch(dev, false); + if (!entry) { + ret = -ENOENT; + goto out; + } + ret = bpf_mprog_attach(entry, &entry_new, nprog, link, oprog, + BPF_F_REPLACE | BPF_F_ID, + link->prog->aux->id, 0); + if (!ret) { + WARN_ON_ONCE(entry != entry_new); + oprog = xchg(&link->prog, nprog); + bpf_prog_put(oprog); + bpf_mprog_commit(entry); + } +out: + rtnl_unlock(); + return ret; +} + +static void netkit_link_dealloc(struct bpf_link *link) +{ + kfree(netkit_link(link)); +} + +static void netkit_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) +{ + const struct netkit_link *nkl = netkit_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (nkl->dev) + ifindex = nkl->dev->ifindex; + rtnl_unlock(); + + seq_printf(seq, "ifindex:\t%u\n", ifindex); + seq_printf(seq, "attach_type:\t%u (%s)\n", + nkl->location, + nkl->location == BPF_NETKIT_PRIMARY ? "primary" : "peer"); +} + +static int netkit_link_fill_info(const struct bpf_link *link, + struct bpf_link_info *info) +{ + const struct netkit_link *nkl = netkit_link(link); + u32 ifindex = 0; + + rtnl_lock(); + if (nkl->dev) + ifindex = nkl->dev->ifindex; + rtnl_unlock(); + + info->netkit.ifindex = ifindex; + info->netkit.attach_type = nkl->location; + return 0; +} + +static int netkit_link_detach(struct bpf_link *link) +{ + netkit_link_release(link); + return 0; +} + +static const struct bpf_link_ops netkit_link_lops = { + .release = netkit_link_release, + .detach = netkit_link_detach, + .dealloc = netkit_link_dealloc, + .update_prog = netkit_link_update, + .show_fdinfo = netkit_link_fdinfo, + .fill_link_info = netkit_link_fill_info, +}; + +static int netkit_link_init(struct netkit_link *nkl, + struct bpf_link_primer *link_primer, + const union bpf_attr *attr, + struct net_device *dev, + struct bpf_prog *prog) +{ + bpf_link_init(&nkl->link, BPF_LINK_TYPE_NETKIT, + &netkit_link_lops, prog); + nkl->location = attr->link_create.attach_type; + nkl->dev = dev; + return bpf_link_prime(&nkl->link, link_primer); +} + +int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog) +{ + struct bpf_link_primer link_primer; + struct netkit_link *nkl; + struct net_device *dev; + int ret; + + rtnl_lock(); + dev = netkit_dev_fetch(current->nsproxy->net_ns, + attr->link_create.target_ifindex, + attr->link_create.attach_type); + if (IS_ERR(dev)) { + ret = PTR_ERR(dev); + goto out; + } + nkl = kzalloc(sizeof(*nkl), GFP_KERNEL_ACCOUNT); + if (!nkl) { + ret = -ENOMEM; + goto out; + } + ret = netkit_link_init(nkl, &link_primer, attr, dev, prog); + if (ret) { + kfree(nkl); + goto out; + } + ret = netkit_link_prog_attach(&nkl->link, + attr->link_create.flags, + attr->link_create.netkit.relative_fd, + attr->link_create.netkit.expected_revision); + if (ret) { + nkl->dev = NULL; + bpf_link_cleanup(&link_primer); + goto out; + } + ret = bpf_link_settle(&link_primer); +out: + rtnl_unlock(); + return ret; +} + +static void netkit_release_all(struct net_device *dev) +{ + struct bpf_mprog_entry *entry; + struct bpf_tuple tuple = {}; + struct bpf_mprog_fp *fp; + struct bpf_mprog_cp *cp; + + entry = netkit_entry_fetch(dev, false); + if (!entry) + return; + netkit_entry_update(dev, NULL); + netkit_entry_sync(); + bpf_mprog_foreach_tuple(entry, fp, cp, tuple) { + if (tuple.link) + netkit_link(tuple.link)->dev = NULL; + else + bpf_prog_put(tuple.prog); + } +} + +static void netkit_uninit(struct net_device *dev) +{ + netkit_release_all(dev); +} + +static void netkit_del_link(struct net_device *dev, struct list_head *head) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + RCU_INIT_POINTER(nk->peer, NULL); + unregister_netdevice_queue(dev, head); + if (peer) { + nk = netkit_priv(peer); + RCU_INIT_POINTER(nk->peer, NULL); + unregister_netdevice_queue(peer, head); + } +} + +static int netkit_change_link(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + enum netkit_action policy; + struct nlattr *attr; + int err; + + if (!nk->primary) { + NL_SET_ERR_MSG(extack, + "netkit link settings can be changed only through the primary device"); + return -EACCES; + } + + if (data[IFLA_NETKIT_MODE]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_NETKIT_MODE], + "netkit link operating mode cannot be changed after device creation"); + return -EACCES; + } + + if (data[IFLA_NETKIT_POLICY]) { + attr = data[IFLA_NETKIT_POLICY]; + policy = nla_get_u32(attr); + err = netkit_check_policy(policy, attr, extack); + if (err) + return err; + WRITE_ONCE(nk->policy, policy); + } + + if (data[IFLA_NETKIT_PEER_POLICY]) { + err = -EOPNOTSUPP; + attr = data[IFLA_NETKIT_PEER_POLICY]; + policy = nla_get_u32(attr); + if (peer) + err = netkit_check_policy(policy, attr, extack); + if (err) + return err; + nk = netkit_priv(peer); + WRITE_ONCE(nk->policy, policy); + } + + return 0; +} + +static size_t netkit_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_POLICY */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_PEER_POLICY */ + nla_total_size(sizeof(u8)) + /* IFLA_NETKIT_PRIMARY */ + nla_total_size(sizeof(u32)) + /* IFLA_NETKIT_MODE */ + 0; +} + +static int netkit_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct netkit *nk = netkit_priv(dev); + struct net_device *peer = rtnl_dereference(nk->peer); + + if (nla_put_u8(skb, IFLA_NETKIT_PRIMARY, nk->primary)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_POLICY, nk->policy)) + return -EMSGSIZE; + if (nla_put_u32(skb, IFLA_NETKIT_MODE, nk->mode)) + return -EMSGSIZE; + + if (peer) { + nk = netkit_priv(peer); + if (nla_put_u32(skb, IFLA_NETKIT_PEER_POLICY, nk->policy)) + return -EMSGSIZE; + } + + return 0; +} + +static const struct nla_policy netkit_policy[IFLA_NETKIT_MAX + 1] = { + [IFLA_NETKIT_PEER_INFO] = { .len = sizeof(struct ifinfomsg) }, + [IFLA_NETKIT_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_MODE] = { .type = NLA_U32 }, + [IFLA_NETKIT_PEER_POLICY] = { .type = NLA_U32 }, + [IFLA_NETKIT_PRIMARY] = { .type = NLA_REJECT, + .reject_message = "Primary attribute is read-only" }, +}; + +static struct rtnl_link_ops netkit_link_ops = { + .kind = DRV_NAME, + .priv_size = sizeof(struct netkit), + .setup = netkit_setup, + .newlink = netkit_new_link, + .dellink = netkit_del_link, + .changelink = netkit_change_link, + .get_link_net = netkit_get_link_net, + .get_size = netkit_get_size, + .fill_info = netkit_fill_info, + .policy = netkit_policy, + .validate = netkit_validate, + .maxtype = IFLA_NETKIT_MAX, +}; + +static __init int netkit_init(void) +{ + BUILD_BUG_ON((int)NETKIT_NEXT != (int)TCX_NEXT || + (int)NETKIT_PASS != (int)TCX_PASS || + (int)NETKIT_DROP != (int)TCX_DROP || + (int)NETKIT_REDIRECT != (int)TCX_REDIRECT); + + return rtnl_link_register(&netkit_link_ops); +} + +static __exit void netkit_exit(void) +{ + rtnl_link_unregister(&netkit_link_ops); +} + +module_init(netkit_init); +module_exit(netkit_exit); + +MODULE_DESCRIPTION("BPF-programmable network device"); +MODULE_AUTHOR("Daniel Borkmann <[email protected]>"); +MODULE_AUTHOR("Nikolay Aleksandrov <[email protected]>"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_RTNL_LINK(DRV_NAME); diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c index 8478b081c058..97638ba7ae85 100644 --- a/drivers/net/phy/bcm7xxx.c +++ b/drivers/net/phy/bcm7xxx.c @@ -894,6 +894,9 @@ static int bcm7xxx_28nm_probe(struct phy_device *phydev) .name = _name, \ /* PHY_BASIC_FEATURES */ \ .flags = PHY_IS_INTERNAL, \ + .get_sset_count = bcm_phy_get_sset_count, \ + .get_strings = bcm_phy_get_strings, \ + .get_stats = bcm7xxx_28nm_get_phy_stats, \ .probe = bcm7xxx_28nm_probe, \ .config_init = bcm7xxx_16nm_ephy_config_init, \ .config_aneg = genphy_config_aneg, \ diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 927d3d54658e..08e3915001c3 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -1733,6 +1733,28 @@ static int ksz886x_config_aneg(struct phy_device *phydev) if (ret) return ret; + if (phydev->autoneg != AUTONEG_ENABLE) { + /* When autonegotation is disabled, we need to manually force + * the link state. If we don't do this, the PHY will keep + * sending Fast Link Pulses (FLPs) which are part of the + * autonegotiation process. This is not desired when + * autonegotiation is off. + */ + ret = phy_set_bits(phydev, MII_KSZPHY_CTRL, + KSZ886X_CTRL_FORCE_LINK); + if (ret) + return ret; + } else { + /* If we had previously forced the link state, we need to + * clear KSZ886X_CTRL_FORCE_LINK bit now. Otherwise, the PHY + * will not perform autonegotiation. + */ + ret = phy_clear_bits(phydev, MII_KSZPHY_CTRL, + KSZ886X_CTRL_FORCE_LINK); + if (ret) + return ret; + } + /* The MDI-X configuration is automatically changed by the PHY after * switching from autoneg off to on. So, take MDI-X configuration under * own control and set it after autoneg configuration was done. diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 89ab9efe522c..afa5497f7c35 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3073,10 +3073,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; - unsigned int ifindex, carrier; + unsigned int carrier; struct ifreq ifr; kuid_t owner; kgid_t group; + int ifindex; int sndbuf; int vnet_hdr_sz; int le; @@ -3132,7 +3133,9 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ret = -EFAULT; if (copy_from_user(&ifindex, argp, sizeof(ifindex))) goto unlock; - + ret = -EINVAL; + if (ifindex < 0) + goto unlock; ret = 0; tfile->ifindex = ifindex; goto unlock; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index 1231bf365796..2c5c1e91ded6 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -764,7 +764,7 @@ enum rtl_register_content { /* rtl8152 flags */ enum rtl8152_flags { - RTL8152_UNPLUG = 0, + RTL8152_INACCESSIBLE = 0, RTL8152_SET_RX_MODE, WORK_ENABLE, RTL8152_LINK_CHG, @@ -773,6 +773,9 @@ enum rtl8152_flags { SCHEDULE_TASKLET, GREEN_ETHERNET, RX_EPROTO, + IN_PRE_RESET, + PROBED_WITH_NO_ERRORS, + PROBE_SHOULD_RETRY, }; #define DEVICE_ID_LENOVO_USB_C_TRAVEL_HUB 0x721e @@ -953,6 +956,8 @@ struct r8152 { u8 version; u8 duplex; u8 autoneg; + + unsigned int reg_access_reset_count; }; /** @@ -1200,6 +1205,96 @@ static unsigned int agg_buf_sz = 16384; #define RTL_LIMITED_TSO_SIZE (size_to_mtu(agg_buf_sz) - sizeof(struct tx_desc)) +/* If register access fails then we block access and issue a reset. If this + * happens too many times in a row without a successful access then we stop + * trying to reset and just leave access blocked. + */ +#define REGISTER_ACCESS_MAX_RESETS 3 + +static void rtl_set_inaccessible(struct r8152 *tp) +{ + set_bit(RTL8152_INACCESSIBLE, &tp->flags); + smp_mb__after_atomic(); +} + +static void rtl_set_accessible(struct r8152 *tp) +{ + clear_bit(RTL8152_INACCESSIBLE, &tp->flags); + smp_mb__after_atomic(); +} + +static +int r8152_control_msg(struct r8152 *tp, unsigned int pipe, __u8 request, + __u8 requesttype, __u16 value, __u16 index, void *data, + __u16 size, const char *msg_tag) +{ + struct usb_device *udev = tp->udev; + int ret; + + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return -ENODEV; + + ret = usb_control_msg(udev, pipe, request, requesttype, + value, index, data, size, + USB_CTRL_GET_TIMEOUT); + + /* No need to issue a reset to report an error if the USB device got + * unplugged; just return immediately. + */ + if (ret == -ENODEV) + return ret; + + /* If the write was successful then we're done */ + if (ret >= 0) { + tp->reg_access_reset_count = 0; + return ret; + } + + dev_err(&udev->dev, + "Failed to %s %d bytes at %#06x/%#06x (%d)\n", + msg_tag, size, value, index, ret); + + /* Block all future register access until we reset. Much of the code + * in the driver doesn't check for errors. Notably, many parts of the + * driver do a read/modify/write of a register value without + * confirming that the read succeeded. Writing back modified garbage + * like this can fully wedge the adapter, requiring a power cycle. + */ + rtl_set_inaccessible(tp); + + /* If probe hasn't yet finished, then we'll request a retry of the + * whole probe routine if we get any control transfer errors. We + * never have to clear this bit since we free/reallocate the whole "tp" + * structure if we retry probe. + */ + if (!test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) { + set_bit(PROBE_SHOULD_RETRY, &tp->flags); + return ret; + } + + /* Failing to access registers in pre-reset is not surprising since we + * wouldn't be resetting if things were behaving normally. The register + * access we do in pre-reset isn't truly mandatory--we're just reusing + * the disable() function and trying to be nice by powering the + * adapter down before resetting it. Thus, if we're in pre-reset, + * we'll return right away and not try to queue up yet another reset. + * We know the post-reset is already coming. + */ + if (test_bit(IN_PRE_RESET, &tp->flags)) + return ret; + + if (tp->reg_access_reset_count < REGISTER_ACCESS_MAX_RESETS) { + usb_queue_reset_device(tp->intf); + tp->reg_access_reset_count++; + } else if (tp->reg_access_reset_count == REGISTER_ACCESS_MAX_RESETS) { + dev_err(&udev->dev, + "Tried to reset %d times; giving up.\n", + REGISTER_ACCESS_MAX_RESETS); + } + + return ret; +} + static int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) { @@ -1210,9 +1305,10 @@ int get_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) if (!tmp) return -ENOMEM; - ret = usb_control_msg(tp->udev, tp->pipe_ctrl_in, - RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, - value, index, tmp, size, 500); + ret = r8152_control_msg(tp, tp->pipe_ctrl_in, + RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, + value, index, tmp, size, "read"); + if (ret < 0) memset(data, 0xff, size); else @@ -1233,9 +1329,9 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) if (!tmp) return -ENOMEM; - ret = usb_control_msg(tp->udev, tp->pipe_ctrl_out, - RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE, - value, index, tmp, size, 500); + ret = r8152_control_msg(tp, tp->pipe_ctrl_out, + RTL8152_REQ_SET_REGS, RTL8152_REQT_WRITE, + value, index, tmp, size, "write"); kfree(tmp); @@ -1244,10 +1340,8 @@ int set_registers(struct r8152 *tp, u16 value, u16 index, u16 size, void *data) static void rtl_set_unplug(struct r8152 *tp) { - if (tp->udev->state == USB_STATE_NOTATTACHED) { - set_bit(RTL8152_UNPLUG, &tp->flags); - smp_mb__after_atomic(); - } + if (tp->udev->state == USB_STATE_NOTATTACHED) + rtl_set_inaccessible(tp); } static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size, @@ -1256,7 +1350,7 @@ static int generic_ocp_read(struct r8152 *tp, u16 index, u16 size, u16 limit = 64; int ret = 0; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; /* both size and indix must be 4 bytes align */ @@ -1300,7 +1394,7 @@ static int generic_ocp_write(struct r8152 *tp, u16 index, u16 byteen, u16 byteen_start, byteen_end, byen; u16 limit = 512; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; /* both size and indix must be 4 bytes align */ @@ -1537,7 +1631,7 @@ static int read_mii_word(struct net_device *netdev, int phy_id, int reg) struct r8152 *tp = netdev_priv(netdev); int ret; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; if (phy_id != R8152_PHY_ID) @@ -1553,7 +1647,7 @@ void write_mii_word(struct net_device *netdev, int phy_id, int reg, int val) { struct r8152 *tp = netdev_priv(netdev); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; if (phy_id != R8152_PHY_ID) @@ -1758,7 +1852,7 @@ static void read_bulk_callback(struct urb *urb) if (!tp) return; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; if (!test_bit(WORK_ENABLE, &tp->flags)) @@ -1850,7 +1944,7 @@ static void write_bulk_callback(struct urb *urb) if (!test_bit(WORK_ENABLE, &tp->flags)) return; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; if (!skb_queue_empty(&tp->tx_queue)) @@ -1871,7 +1965,7 @@ static void intr_callback(struct urb *urb) if (!test_bit(WORK_ENABLE, &tp->flags)) return; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; switch (status) { @@ -2656,7 +2750,7 @@ static void bottom_half(struct tasklet_struct *t) { struct r8152 *tp = from_tasklet(tp, t, tx_tl); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; if (!test_bit(WORK_ENABLE, &tp->flags)) @@ -2699,7 +2793,7 @@ int r8152_submit_rx(struct r8152 *tp, struct rx_agg *agg, gfp_t mem_flags) int ret; /* The rx would be stopped, so skip submitting */ - if (test_bit(RTL8152_UNPLUG, &tp->flags) || + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags) || !test_bit(WORK_ENABLE, &tp->flags) || !netif_carrier_ok(tp->netdev)) return 0; @@ -3099,7 +3193,7 @@ static int rtl_enable(struct r8152 *tp) static int rtl8152_enable(struct r8152 *tp) { - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; set_tx_qlen(tp); @@ -3186,7 +3280,7 @@ static int rtl8153_enable(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; set_tx_qlen(tp); @@ -3218,7 +3312,7 @@ static void rtl_disable(struct r8152 *tp) u32 ocp_data; int i; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) { rtl_drop_queued_tx(tp); return; } @@ -3672,7 +3766,7 @@ static u16 r8153_phy_status(struct r8152 *tp, u16 desired) } msleep(20); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) break; } @@ -3704,6 +3798,8 @@ static void r8153b_ups_en(struct r8152 *tp, bool enable) int i; for (i = 0; i < 500; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return; if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; @@ -3744,6 +3840,8 @@ static void r8153c_ups_en(struct r8152 *tp, bool enable) int i; for (i = 0; i < 500; i++) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return; if (ocp_read_word(tp, MCU_TYPE_PLA, PLA_BOOT_CTRL) & AUTOLOAD_DONE) break; @@ -4087,6 +4185,9 @@ static int rtl_phy_patch_request(struct r8152 *tp, bool request, bool wait) for (i = 0; wait && i < 5000; i++) { u32 ocp_data; + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) + return -ENODEV; + usleep_range(1000, 2000); ocp_data = ocp_reg_read(tp, OCP_PHY_PATCH_STAT); if ((ocp_data & PATCH_READY) ^ check) @@ -6043,7 +6144,7 @@ static int rtl8156_enable(struct r8152 *tp) u32 ocp_data; u16 speed; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; r8156_fc_parameter(tp); @@ -6101,7 +6202,7 @@ static int rtl8156b_enable(struct r8152 *tp) u32 ocp_data; u16 speed; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; set_tx_qlen(tp); @@ -6287,7 +6388,7 @@ out: static void rtl8152_up(struct r8152 *tp) { - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8152_aldps_en(tp, false); @@ -6297,7 +6398,7 @@ static void rtl8152_up(struct r8152 *tp) static void rtl8152_down(struct r8152 *tp) { - if (test_bit(RTL8152_UNPLUG, &tp->flags)) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) { rtl_drop_queued_tx(tp); return; } @@ -6312,7 +6413,7 @@ static void rtl8153_up(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153_u1u2en(tp, false); @@ -6352,7 +6453,7 @@ static void rtl8153_down(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) { rtl_drop_queued_tx(tp); return; } @@ -6373,7 +6474,7 @@ static void rtl8153b_up(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153b_u1u2en(tp, false); @@ -6397,7 +6498,7 @@ static void rtl8153b_down(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) { rtl_drop_queued_tx(tp); return; } @@ -6434,7 +6535,7 @@ static void rtl8153c_up(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153b_u1u2en(tp, false); @@ -6515,7 +6616,7 @@ static void rtl8156_up(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153b_u1u2en(tp, false); @@ -6588,7 +6689,7 @@ static void rtl8156_down(struct r8152 *tp) { u32 ocp_data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) { + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) { rtl_drop_queued_tx(tp); return; } @@ -6726,7 +6827,7 @@ static void rtl_work_func_t(struct work_struct *work) /* If the device is unplugged or !netif_running(), the workqueue * doesn't need to wake the device, and could return directly. */ - if (test_bit(RTL8152_UNPLUG, &tp->flags) || !netif_running(tp->netdev)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags) || !netif_running(tp->netdev)) return; if (usb_autopm_get_interface(tp->intf) < 0) @@ -6765,7 +6866,7 @@ static void rtl_hw_phy_work_func_t(struct work_struct *work) { struct r8152 *tp = container_of(work, struct r8152, hw_phy_work.work); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; if (usb_autopm_get_interface(tp->intf) < 0) @@ -6892,7 +6993,7 @@ static int rtl8152_close(struct net_device *netdev) netif_stop_queue(netdev); res = usb_autopm_get_interface(tp->intf); - if (res < 0 || test_bit(RTL8152_UNPLUG, &tp->flags)) { + if (res < 0 || test_bit(RTL8152_INACCESSIBLE, &tp->flags)) { rtl_drop_queued_tx(tp); rtl_stop_rx(tp); } else { @@ -6925,7 +7026,7 @@ static void r8152b_init(struct r8152 *tp) u32 ocp_data; u16 data; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; data = r8152_mdio_read(tp, MII_BMCR); @@ -6969,7 +7070,7 @@ static void r8153_init(struct r8152 *tp) u16 data; int i; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153_u1u2en(tp, false); @@ -6980,7 +7081,7 @@ static void r8153_init(struct r8152 *tp) break; msleep(20); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) break; } @@ -7109,7 +7210,7 @@ static void r8153b_init(struct r8152 *tp) u16 data; int i; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153b_u1u2en(tp, false); @@ -7120,7 +7221,7 @@ static void r8153b_init(struct r8152 *tp) break; msleep(20); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) break; } @@ -7191,7 +7292,7 @@ static void r8153c_init(struct r8152 *tp) u16 data; int i; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153b_u1u2en(tp, false); @@ -7211,7 +7312,7 @@ static void r8153c_init(struct r8152 *tp) break; msleep(20); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; } @@ -8040,7 +8141,7 @@ static void r8156_init(struct r8152 *tp) u16 data; int i; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_ECM_OP); @@ -8061,7 +8162,7 @@ static void r8156_init(struct r8152 *tp) break; msleep(20); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; } @@ -8136,7 +8237,7 @@ static void r8156b_init(struct r8152 *tp) u16 data; int i; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; ocp_data = ocp_read_byte(tp, MCU_TYPE_USB, USB_ECM_OP); @@ -8170,7 +8271,7 @@ static void r8156b_init(struct r8152 *tp) break; msleep(20); - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; } @@ -8296,7 +8397,7 @@ static int rtl8152_pre_reset(struct usb_interface *intf) struct r8152 *tp = usb_get_intfdata(intf); struct net_device *netdev; - if (!tp) + if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) return 0; netdev = tp->netdev; @@ -8311,7 +8412,9 @@ static int rtl8152_pre_reset(struct usb_interface *intf) napi_disable(&tp->napi); if (netif_carrier_ok(netdev)) { mutex_lock(&tp->control); + set_bit(IN_PRE_RESET, &tp->flags); tp->rtl_ops.disable(tp); + clear_bit(IN_PRE_RESET, &tp->flags); mutex_unlock(&tp->control); } @@ -8324,9 +8427,11 @@ static int rtl8152_post_reset(struct usb_interface *intf) struct net_device *netdev; struct sockaddr sa; - if (!tp) + if (!tp || !test_bit(PROBED_WITH_NO_ERRORS, &tp->flags)) return 0; + rtl_set_accessible(tp); + /* reset the MAC address in case of policy change */ if (determine_ethernet_addr(tp, &sa) >= 0) { rtnl_lock(); @@ -9199,7 +9304,7 @@ static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) struct mii_ioctl_data *data = if_mii(rq); int res; - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return -ENODEV; res = usb_autopm_get_interface(tp->intf); @@ -9301,7 +9406,7 @@ static const struct net_device_ops rtl8152_netdev_ops = { static void rtl8152_unload(struct r8152 *tp) { - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; if (tp->version != RTL_VER_01) @@ -9310,7 +9415,7 @@ static void rtl8152_unload(struct r8152 *tp) static void rtl8153_unload(struct r8152 *tp) { - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153_power_cut_en(tp, false); @@ -9318,7 +9423,7 @@ static void rtl8153_unload(struct r8152 *tp) static void rtl8153b_unload(struct r8152 *tp) { - if (test_bit(RTL8152_UNPLUG, &tp->flags)) + if (test_bit(RTL8152_INACCESSIBLE, &tp->flags)) return; r8153b_power_cut_en(tp, false); @@ -9528,16 +9633,29 @@ static u8 __rtl_get_hw_ver(struct usb_device *udev) __le32 *tmp; u8 version; int ret; + int i; tmp = kmalloc(sizeof(*tmp), GFP_KERNEL); if (!tmp) return 0; - ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), - RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, - PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp), 500); - if (ret > 0) - ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK; + /* Retry up to 3 times in case there is a transitory error. We do this + * since retrying a read of the version is always safe and this + * function doesn't take advantage of r8152_control_msg(). + */ + for (i = 0; i < 3; i++) { + ret = usb_control_msg(udev, usb_rcvctrlpipe(udev, 0), + RTL8152_REQ_GET_REGS, RTL8152_REQT_READ, + PLA_TCR0, MCU_TYPE_PLA, tmp, sizeof(*tmp), + USB_CTRL_GET_TIMEOUT); + if (ret > 0) { + ocp_data = (__le32_to_cpu(*tmp) >> 16) & VERSION_MASK; + break; + } + } + + if (i != 0 && ret > 0) + dev_warn(&udev->dev, "Needed %d retries to read version\n", i); kfree(tmp); @@ -9636,25 +9754,14 @@ static bool rtl8152_supports_lenovo_macpassthru(struct usb_device *udev) return 0; } -static int rtl8152_probe(struct usb_interface *intf, - const struct usb_device_id *id) +static int rtl8152_probe_once(struct usb_interface *intf, + const struct usb_device_id *id, u8 version) { struct usb_device *udev = interface_to_usbdev(intf); struct r8152 *tp; struct net_device *netdev; - u8 version; int ret; - if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC) - return -ENODEV; - - if (!rtl_check_vendor_ok(intf)) - return -ENODEV; - - version = rtl8152_get_version(intf); - if (version == RTL_VER_UNKNOWN) - return -ENODEV; - usb_reset_device(udev); netdev = alloc_etherdev(sizeof(struct r8152)); if (!netdev) { @@ -9817,18 +9924,68 @@ static int rtl8152_probe(struct usb_interface *intf, else device_set_wakeup_enable(&udev->dev, false); + /* If we saw a control transfer error while probing then we may + * want to try probe() again. Consider this an error. + */ + if (test_bit(PROBE_SHOULD_RETRY, &tp->flags)) + goto out2; + + set_bit(PROBED_WITH_NO_ERRORS, &tp->flags); netif_info(tp, probe, netdev, "%s\n", DRIVER_VERSION); return 0; +out2: + unregister_netdev(netdev); + out1: tasklet_kill(&tp->tx_tl); + cancel_delayed_work_sync(&tp->hw_phy_work); + if (tp->rtl_ops.unload) + tp->rtl_ops.unload(tp); + rtl8152_release_firmware(tp); usb_set_intfdata(intf, NULL); out: + if (test_bit(PROBE_SHOULD_RETRY, &tp->flags)) + ret = -EAGAIN; + free_netdev(netdev); return ret; } +#define RTL8152_PROBE_TRIES 3 + +static int rtl8152_probe(struct usb_interface *intf, + const struct usb_device_id *id) +{ + u8 version; + int ret; + int i; + + if (intf->cur_altsetting->desc.bInterfaceClass != USB_CLASS_VENDOR_SPEC) + return -ENODEV; + + if (!rtl_check_vendor_ok(intf)) + return -ENODEV; + + version = rtl8152_get_version(intf); + if (version == RTL_VER_UNKNOWN) + return -ENODEV; + + for (i = 0; i < RTL8152_PROBE_TRIES; i++) { + ret = rtl8152_probe_once(intf, id, version); + if (ret != -EAGAIN) + break; + } + if (ret == -EAGAIN) { + dev_err(&intf->dev, + "r8152 failed probe after %d tries; giving up\n", i); + return -ENODEV; + } + + return ret; +} + static void rtl8152_disconnect(struct usb_interface *intf) { struct r8152 *tp = usb_get_intfdata(intf); diff --git a/drivers/net/usb/smsc95xx.c b/drivers/net/usb/smsc95xx.c index 563ecd27b93e..a530f20ee257 100644 --- a/drivers/net/usb/smsc95xx.c +++ b/drivers/net/usb/smsc95xx.c @@ -95,7 +95,9 @@ static int __must_check smsc95xx_read_reg(struct usbnet *dev, u32 index, ret = fn(dev, USB_VENDOR_REQUEST_READ_REGISTER, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, 0, index, &buf, 4); - if (ret < 0) { + if (ret < 4) { + ret = ret < 0 ? ret : -ENODATA; + if (ret != -ENODEV) netdev_warn(dev->net, "Failed to read reg index 0x%08x: %d\n", index, ret); @@ -897,7 +899,7 @@ static int smsc95xx_reset(struct usbnet *dev) if (timeout >= 100) { netdev_warn(dev->net, "timeout waiting for completion of Lite Reset\n"); - return ret; + return -ETIMEDOUT; } ret = smsc95xx_set_mac_address(dev); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 0deefd1573cf..9980517ed8b0 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -737,10 +737,11 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, if (skb_shared(skb) || skb_head_is_locked(skb) || skb_shinfo(skb)->nr_frags || skb_headroom(skb) < XDP_PACKET_HEADROOM) { - u32 size, len, max_head_size, off; + u32 size, len, max_head_size, off, truesize, page_offset; struct sk_buff *nskb; struct page *page; int i, head_off; + void *va; /* We need a private copy of the skb and data buffers since * the ebpf program can modify it. We segment the original skb @@ -753,14 +754,17 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, if (skb->len > PAGE_SIZE * MAX_SKB_FRAGS + max_head_size) goto drop; + size = min_t(u32, skb->len, max_head_size); + truesize = SKB_HEAD_ALIGN(size) + VETH_XDP_HEADROOM; + /* Allocate skb head */ - page = page_pool_dev_alloc_pages(rq->page_pool); - if (!page) + va = page_pool_dev_alloc_va(rq->page_pool, &truesize); + if (!va) goto drop; - nskb = napi_build_skb(page_address(page), PAGE_SIZE); + nskb = napi_build_skb(va, truesize); if (!nskb) { - page_pool_put_full_page(rq->page_pool, page, true); + page_pool_free_va(rq->page_pool, va, true); goto drop; } @@ -768,7 +772,6 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, skb_copy_header(nskb, skb); skb_mark_for_recycle(nskb); - size = min_t(u32, skb->len, max_head_size); if (skb_copy_bits(skb, 0, nskb->data, size)) { consume_skb(nskb); goto drop; @@ -783,14 +786,18 @@ static int veth_convert_skb_to_xdp_buff(struct veth_rq *rq, len = skb->len - off; for (i = 0; i < MAX_SKB_FRAGS && off < skb->len; i++) { - page = page_pool_dev_alloc_pages(rq->page_pool); + size = min_t(u32, len, PAGE_SIZE); + truesize = size; + + page = page_pool_dev_alloc(rq->page_pool, &page_offset, + &truesize); if (!page) { consume_skb(nskb); goto drop; } - size = min_t(u32, len, PAGE_SIZE); - skb_add_rx_frag(nskb, i, page, 0, size, PAGE_SIZE); + skb_add_rx_frag(nskb, i, page, page_offset, size, + truesize); if (skb_copy_bits(skb, off, page_address(page), size)) { consume_skb(nskb); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index a52fd743504a..62962216b80c 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -607,16 +607,16 @@ static void virtnet_rq_unmap(struct receive_queue *rq, void *buf, u32 len) --dma->ref; - if (dma->ref) { - if (dma->need_sync && len) { - offset = buf - (head + sizeof(*dma)); + if (dma->need_sync && len) { + offset = buf - (head + sizeof(*dma)); - virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, offset, - len, DMA_FROM_DEVICE); - } + virtqueue_dma_sync_single_range_for_cpu(rq->vq, dma->addr, + offset, len, + DMA_FROM_DEVICE); + } + if (dma->ref) return; - } virtqueue_dma_unmap_single_attrs(rq->vq, dma->addr, dma->len, DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c index 6f7d45e3cfa2..7b526ae16ed0 100644 --- a/drivers/net/vxlan/vxlan_core.c +++ b/drivers/net/vxlan/vxlan_core.c @@ -2215,63 +2215,6 @@ static int vxlan_build_skb(struct sk_buff *skb, struct dst_entry *dst, return 0; } -#if IS_ENABLED(CONFIG_IPV6) -static struct dst_entry *vxlan6_get_route(struct vxlan_dev *vxlan, - struct net_device *dev, - struct vxlan_sock *sock6, - struct sk_buff *skb, int oif, u8 tos, - __be32 label, - const struct in6_addr *daddr, - struct in6_addr *saddr, - __be16 dport, __be16 sport, - struct dst_cache *dst_cache, - const struct ip_tunnel_info *info) -{ - bool use_cache = ip_tunnel_dst_cache_usable(skb, info); - struct dst_entry *ndst; - struct flowi6 fl6; - - if (!sock6) - return ERR_PTR(-EIO); - - if (tos && !info) - use_cache = false; - if (use_cache) { - ndst = dst_cache_get_ip6(dst_cache, saddr); - if (ndst) - return ndst; - } - - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_oif = oif; - fl6.daddr = *daddr; - fl6.saddr = *saddr; - fl6.flowlabel = ip6_make_flowinfo(tos, label); - fl6.flowi6_mark = skb->mark; - fl6.flowi6_proto = IPPROTO_UDP; - fl6.fl6_dport = dport; - fl6.fl6_sport = sport; - - ndst = ipv6_stub->ipv6_dst_lookup_flow(vxlan->net, sock6->sock->sk, - &fl6, NULL); - if (IS_ERR(ndst)) { - netdev_dbg(dev, "no route to %pI6\n", daddr); - return ERR_PTR(-ENETUNREACH); - } - - if (unlikely(ndst->dev == dev)) { - netdev_dbg(dev, "circular route to %pI6\n", daddr); - dst_release(ndst); - return ERR_PTR(-ELOOP); - } - - *saddr = fl6.saddr; - if (use_cache) - dst_cache_set_ip6(dst_cache, ndst, saddr); - return ndst; -} -#endif - /* Bypass encapsulation if the destination is local */ static void vxlan_encap_bypass(struct sk_buff *skb, struct vxlan_dev *src_vxlan, struct vxlan_dev *dst_vxlan, __be32 vni, @@ -2325,7 +2268,7 @@ drop: static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, struct vxlan_dev *vxlan, - union vxlan_addr *daddr, + int addr_family, __be16 dst_port, int dst_ifindex, __be32 vni, struct dst_entry *dst, u32 rt_flags) @@ -2345,7 +2288,7 @@ static int encap_bypass_if_local(struct sk_buff *skb, struct net_device *dev, dst_release(dst); dst_vxlan = vxlan_find_vni(vxlan->net, dst_ifindex, vni, - daddr->sa.sa_family, dst_port, + addr_family, dst_port, vxlan->cfg.flags); if (!dst_vxlan) { dev->stats.tx_errors++; @@ -2371,13 +2314,12 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, struct ip_tunnel_key key; struct vxlan_dev *vxlan = netdev_priv(dev); const struct iphdr *old_iph = ip_hdr(skb); - union vxlan_addr *dst; - union vxlan_addr remote_ip; struct vxlan_metadata _md; struct vxlan_metadata *md = &_md; unsigned int pkt_len = skb->len; __be16 src_port = 0, dst_port; struct dst_entry *ndst = NULL; + int addr_family; __u8 tos, ttl; int ifindex; int err; @@ -2386,20 +2328,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, bool udp_sum = false; bool xnet = !net_eq(vxlan->net, dev_net(vxlan->dev)); __be32 vni = 0; -#if IS_ENABLED(CONFIG_IPV6) - union vxlan_addr local_ip; - __be32 label; -#endif info = skb_tunnel_info(skb); use_cache = ip_tunnel_dst_cache_usable(skb, info); if (rdst) { - dst = &rdst->remote_ip; memset(&key, 0, sizeof(key)); pkey = &key; - if (vxlan_addr_any(dst)) { + if (vxlan_addr_any(&rdst->remote_ip)) { if (did_rsc) { /* short-circuited back to local bridge */ vxlan_encap_bypass(skb, vxlan, vxlan, @@ -2409,11 +2346,12 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto drop; } + addr_family = vxlan->cfg.saddr.sa.sa_family; dst_port = rdst->remote_port ? rdst->remote_port : vxlan->cfg.dst_port; vni = (rdst->remote_vni) ? : default_vni; ifindex = rdst->remote_ifindex; - if (dst->sa.sa_family == AF_INET) { + if (addr_family == AF_INET) { key.u.ipv4.src = vxlan->cfg.saddr.sin.sin_addr.s_addr; key.u.ipv4.dst = rdst->remote_ip.sin.sin_addr.s_addr; } else { @@ -2427,23 +2365,21 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, ttl = ip_tunnel_get_ttl(old_iph, skb); } else { ttl = vxlan->cfg.ttl; - if (!ttl && vxlan_addr_multicast(dst)) + if (!ttl && vxlan_addr_multicast(&rdst->remote_ip)) ttl = 1; } - tos = vxlan->cfg.tos; if (tos == 1) tos = ip_tunnel_get_dsfield(old_iph, skb); if (tos && !info) use_cache = false; - if (dst->sa.sa_family == AF_INET) + if (addr_family == AF_INET) udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM_TX); else udp_sum = !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX); #if IS_ENABLED(CONFIG_IPV6) - local_ip = vxlan->cfg.saddr; - label = vxlan->cfg.label; + key.label = vxlan->cfg.label; #endif } else { if (!info) { @@ -2451,17 +2387,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, dev->name); goto drop; } - remote_ip.sa.sa_family = ip_tunnel_info_af(info); - if (remote_ip.sa.sa_family == AF_INET) { - remote_ip.sin.sin_addr.s_addr = info->key.u.ipv4.dst; - } else { - remote_ip.sin6.sin6_addr = info->key.u.ipv6.dst; -#if IS_ENABLED(CONFIG_IPV6) - local_ip.sin6.sin6_addr = info->key.u.ipv6.src; -#endif - } - dst = &remote_ip; pkey = &info->key; + addr_family = ip_tunnel_info_af(info); dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port; vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; @@ -2473,16 +2400,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } ttl = info->key.ttl; tos = info->key.tos; -#if IS_ENABLED(CONFIG_IPV6) - label = info->key.label; -#endif udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM); } src_port = udp_flow_src_port(dev_net(dev), skb, vxlan->cfg.port_min, vxlan->cfg.port_max, true); rcu_read_lock(); - if (dst->sa.sa_family == AF_INET) { + if (addr_family == AF_INET) { struct vxlan_sock *sock4 = rcu_dereference(vxlan->vn4_sock); struct rtable *rt; __be16 df = 0; @@ -2501,7 +2425,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (!info) { /* Bypass encapsulation if the destination is local */ - err = encap_bypass_if_local(skb, dev, vxlan, dst, + err = encap_bypass_if_local(skb, dev, vxlan, AF_INET, dst_port, ifindex, vni, &rt->dst, rt->rt_flags); if (err) @@ -2555,15 +2479,15 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, #if IS_ENABLED(CONFIG_IPV6) } else { struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); + struct in6_addr saddr; if (!ifindex) ifindex = sock6->sock->sk->sk_bound_dev_if; - ndst = vxlan6_get_route(vxlan, dev, sock6, skb, ifindex, tos, - label, &dst->sin6.sin6_addr, - &local_ip.sin6.sin6_addr, - dst_port, src_port, - dst_cache, info); + ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, + ifindex, &saddr, pkey, + src_port, dst_port, tos, + use_cache ? dst_cache : NULL); if (IS_ERR(ndst)) { err = PTR_ERR(ndst); ndst = NULL; @@ -2573,7 +2497,7 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, if (!info) { u32 rt6i_flags = ((struct rt6_info *)ndst)->rt6i_flags; - err = encap_bypass_if_local(skb, dev, vxlan, dst, + err = encap_bypass_if_local(skb, dev, vxlan, AF_INET6, dst_port, ifindex, vni, ndst, rt6i_flags); if (err) @@ -2588,16 +2512,13 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, } else if (err) { if (info) { struct ip_tunnel_info *unclone; - struct in6_addr src, dst; unclone = skb_tunnel_info_unclone(skb); if (unlikely(!unclone)) goto tx_error; - src = remote_ip.sin6.sin6_addr; - dst = local_ip.sin6.sin6_addr; - unclone->key.u.ipv6.src = src; - unclone->key.u.ipv6.dst = dst; + unclone->key.u.ipv6.src = pkey->u.ipv6.dst; + unclone->key.u.ipv6.dst = saddr; } vxlan_encap_bypass(skb, vxlan, vxlan, vni, false); @@ -2614,9 +2535,8 @@ void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, goto tx_error; udp_tunnel6_xmit_skb(ndst, sock6->sock->sk, skb, dev, - &local_ip.sin6.sin6_addr, - &dst->sin6.sin6_addr, tos, ttl, - label, src_port, dst_port, !udp_sum); + &saddr, &pkey->u.ipv6.dst, tos, ttl, + pkey->label, src_port, dst_port, !udp_sum); #endif } vxlan_vnifilter_count(vxlan, vni, NULL, VXLAN_VNI_STATS_TX, pkt_len); @@ -3267,10 +3187,14 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) struct vxlan_sock *sock6 = rcu_dereference(vxlan->vn6_sock); struct dst_entry *ndst; - ndst = vxlan6_get_route(vxlan, dev, sock6, skb, 0, info->key.tos, - info->key.label, &info->key.u.ipv6.dst, - &info->key.u.ipv6.src, dport, sport, - &info->dst_cache, info); + if (!sock6) + return -EIO; + + ndst = udp_tunnel6_dst_lookup(skb, dev, vxlan->net, sock6->sock, + 0, &info->key.u.ipv6.src, + &info->key, + sport, dport, info->key.tos, + &info->dst_cache); if (IS_ERR(ndst)) return PTR_ERR(ndst); dst_release(ndst); diff --git a/drivers/net/vxlan/vxlan_mdb.c b/drivers/net/vxlan/vxlan_mdb.c index 5e041622261a..3a21389658ce 100644 --- a/drivers/net/vxlan/vxlan_mdb.c +++ b/drivers/net/vxlan/vxlan_mdb.c @@ -311,7 +311,7 @@ vxlan_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(vxlan_mdbe_src_list_entry_pol), }; -static struct netlink_range_validation vni_range = { +static const struct netlink_range_validation vni_range = { .max = VXLAN_N_VID - 1, }; diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index cb76053973aa..51a767121b0d 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -570,7 +570,7 @@ int mt76_create_page_pool(struct mt76_dev *dev, struct mt76_queue *q) { struct page_pool_params pp_params = { .order = 0, - .flags = PP_FLAG_PAGE_FRAG, + .flags = 0, .nid = NUMA_NO_NODE, .dev = dev->dma_dev, }; diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c index 4bfb4188de72..3d75165e48be 100644 --- a/drivers/net/wireless/realtek/rtw89/core.c +++ b/drivers/net/wireless/realtek/rtw89/core.c @@ -2005,7 +2005,7 @@ static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev, struct napi_struct *napi = &rtwdev->napi; /* In low power mode, napi isn't scheduled. Receive it to netif. */ - if (unlikely(!test_bit(NAPI_STATE_SCHED, &napi->state))) + if (unlikely(!napi_is_scheduled(napi))) napi = NULL; rtw89_core_hw_to_sband_rate(rx_status); diff --git a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h index e77084e76718..fdc211bbeda7 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h +++ b/drivers/net/wwan/iosm/iosm_ipc_chnl_cfg.h @@ -51,7 +51,7 @@ struct ipc_chnl_cfg { /** * ipc_chnl_cfg_get - Get pipe configuration. * @chnl_cfg: Array of ipc_chnl_cfg struct - * @index: Channel index (upto MAX_CHANNELS) + * @index: Channel index (up to MAX_CHANNELS) * * Return: 0 on success and failure value on error */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.c b/drivers/net/wwan/iosm/iosm_ipc_imem.c index 635301d677e1..829515a601b3 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.c +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.c @@ -4,7 +4,6 @@ */ #include <linux/delay.h> -#include <linux/pm_runtime.h> #include "iosm_ipc_chnl_cfg.h" #include "iosm_ipc_devlink.h" @@ -632,11 +631,6 @@ static void ipc_imem_run_state_worker(struct work_struct *instance) /* Complete all memory stores after setting bit */ smp_mb__after_atomic(); - if (ipc_imem->pcie->pci->device == INTEL_CP_DEVICE_7560_ID) { - pm_runtime_mark_last_busy(ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_imem->dev); - } - return; err_ipc_mux_deinit: @@ -1240,7 +1234,6 @@ void ipc_imem_cleanup(struct iosm_imem *ipc_imem) /* forward MDM_NOT_READY to listeners */ ipc_uevent_send(ipc_imem->dev, UEVENT_MDM_NOT_READY); - pm_runtime_get_sync(ipc_imem->dev); hrtimer_cancel(&ipc_imem->td_alloc_timer); hrtimer_cancel(&ipc_imem->tdupdate_timer); @@ -1426,16 +1419,6 @@ struct iosm_imem *ipc_imem_init(struct iosm_pcie *pcie, unsigned int device_id, set_bit(IOSM_DEVLINK_INIT, &ipc_imem->flag); } - - if (!pm_runtime_enabled(ipc_imem->dev)) - pm_runtime_enable(ipc_imem->dev); - - pm_runtime_set_autosuspend_delay(ipc_imem->dev, - IPC_MEM_AUTO_SUSPEND_DELAY_MS); - pm_runtime_use_autosuspend(ipc_imem->dev); - pm_runtime_allow(ipc_imem->dev); - pm_runtime_mark_last_busy(ipc_imem->dev); - return ipc_imem; devlink_channel_fail: ipc_devlink_deinit(ipc_imem->ipc_devlink); diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h index 0144b45e2afb..5664ac507c90 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h @@ -103,8 +103,6 @@ struct ipc_chnl_cfg; #define FULLY_FUNCTIONAL 0 #define IOSM_DEVLINK_INIT 1 -#define IPC_MEM_AUTO_SUSPEND_DELAY_MS 5000 - /* List of the supported UL/DL pipes. */ enum ipc_mem_pipes { IPC_MEM_PIPE_0 = 0, diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h index 026c5bd0f999..6bd0290e8be7 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h +++ b/drivers/net/wwan/iosm/iosm_ipc_imem_ops.h @@ -36,8 +36,8 @@ /** * ipc_imem_sys_port_open - Open a port link to CP. * @ipc_imem: Imem instance. - * @chl_id: Channel Indentifier. - * @hp_id: HP Indentifier. + * @chl_id: Channel Identifier. + * @hp_id: HP Identifier. * * Return: channel instance on success, NULL for failure */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_mux.h b/drivers/net/wwan/iosm/iosm_ipc_mux.h index 17ca8d1f9397..db5f1f9ebf26 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_mux.h +++ b/drivers/net/wwan/iosm/iosm_ipc_mux.h @@ -432,7 +432,7 @@ int ipc_mux_open_session(struct iosm_mux *ipc_mux, int session_nr); int ipc_mux_close_session(struct iosm_mux *ipc_mux, int session_nr); /** - * ipc_mux_get_max_sessions - Retuns the maximum sessions supported on the + * ipc_mux_get_max_sessions - Returns the maximum sessions supported on the * provided MUX instance.. * @ipc_mux: Pointer to MUX data-struct * diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 3a259c9abefd..04517bd3325a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -6,7 +6,6 @@ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/module.h> -#include <linux/pm_runtime.h> #include <net/rtnetlink.h> #include "iosm_ipc_imem.h" @@ -438,8 +437,7 @@ static int __maybe_unused ipc_pcie_resume_cb(struct device *dev) return 0; } -static DEFINE_RUNTIME_DEV_PM_OPS(iosm_ipc_pm, ipc_pcie_suspend_cb, - ipc_pcie_resume_cb, NULL); +static SIMPLE_DEV_PM_OPS(iosm_ipc_pm, ipc_pcie_suspend_cb, ipc_pcie_resume_cb); static struct pci_driver iosm_ipc_driver = { .name = KBUILD_MODNAME, diff --git a/drivers/net/wwan/iosm/iosm_ipc_pm.h b/drivers/net/wwan/iosm/iosm_ipc_pm.h index e7c00f388cb0..5f14d7932af9 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pm.h +++ b/drivers/net/wwan/iosm/iosm_ipc_pm.h @@ -172,7 +172,7 @@ bool ipc_pm_prepare_host_sleep(struct iosm_pm *ipc_pm); bool ipc_pm_prepare_host_active(struct iosm_pm *ipc_pm); /** - * ipc_pm_wait_for_device_active - Wait upto IPC_PM_ACTIVE_TIMEOUT_MS ms + * ipc_pm_wait_for_device_active - Wait up to IPC_PM_ACTIVE_TIMEOUT_MS ms * for the device to reach active state * @ipc_pm: Pointer to power management component * diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.c b/drivers/net/wwan/iosm/iosm_ipc_port.c index 2ba1ddca3945..5d5b4183e14a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_port.c +++ b/drivers/net/wwan/iosm/iosm_ipc_port.c @@ -3,8 +3,6 @@ * Copyright (C) 2020-21 Intel Corporation. */ -#include <linux/pm_runtime.h> - #include "iosm_ipc_chnl_cfg.h" #include "iosm_ipc_imem_ops.h" #include "iosm_ipc_port.h" @@ -15,16 +13,12 @@ static int ipc_port_ctrl_start(struct wwan_port *port) struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port); int ret = 0; - pm_runtime_get_sync(ipc_port->ipc_imem->dev); ipc_port->channel = ipc_imem_sys_port_open(ipc_port->ipc_imem, ipc_port->chl_id, IPC_HP_CDEV_OPEN); if (!ipc_port->channel) ret = -EIO; - pm_runtime_mark_last_busy(ipc_port->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_port->ipc_imem->dev); - return ret; } @@ -33,24 +27,15 @@ static void ipc_port_ctrl_stop(struct wwan_port *port) { struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port); - pm_runtime_get_sync(ipc_port->ipc_imem->dev); ipc_imem_sys_port_close(ipc_port->ipc_imem, ipc_port->channel); - pm_runtime_mark_last_busy(ipc_port->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_port->ipc_imem->dev); } /* transfer control data to modem */ static int ipc_port_ctrl_tx(struct wwan_port *port, struct sk_buff *skb) { struct iosm_cdev *ipc_port = wwan_port_get_drvdata(port); - int ret; - pm_runtime_get_sync(ipc_port->ipc_imem->dev); - ret = ipc_imem_sys_cdev_write(ipc_port, skb); - pm_runtime_mark_last_busy(ipc_port->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_port->ipc_imem->dev); - - return ret; + return ipc_imem_sys_cdev_write(ipc_port, skb); } static const struct wwan_port_ops ipc_wwan_ctrl_ops = { diff --git a/drivers/net/wwan/iosm/iosm_ipc_port.h b/drivers/net/wwan/iosm/iosm_ipc_port.h index 11bc8ed21616..d33c52aebf66 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_port.h +++ b/drivers/net/wwan/iosm/iosm_ipc_port.h @@ -18,7 +18,7 @@ * @pcie: PCIe component * @port_type: WWAN port type * @channel: Channel instance - * @chl_id: Channel Indentifier + * @chl_id: Channel Identifier */ struct iosm_cdev { struct wwan_port *iosm_port; diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.c b/drivers/net/wwan/iosm/iosm_ipc_trace.c index 4368373797b6..eeecfa3d10c5 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.c +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.c @@ -3,9 +3,7 @@ * Copyright (C) 2020-2021 Intel Corporation. */ -#include <linux/pm_runtime.h> #include <linux/wwan.h> - #include "iosm_ipc_trace.h" /* sub buffer size and number of sub buffer */ @@ -99,8 +97,6 @@ static ssize_t ipc_trace_ctrl_file_write(struct file *filp, if (ret) return ret; - pm_runtime_get_sync(ipc_trace->ipc_imem->dev); - mutex_lock(&ipc_trace->trc_mutex); if (val == TRACE_ENABLE && ipc_trace->mode != TRACE_ENABLE) { ipc_trace->channel = ipc_imem_sys_port_open(ipc_trace->ipc_imem, @@ -121,10 +117,6 @@ static ssize_t ipc_trace_ctrl_file_write(struct file *filp, ret = count; unlock: mutex_unlock(&ipc_trace->trc_mutex); - - pm_runtime_mark_last_busy(ipc_trace->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_trace->ipc_imem->dev); - return ret; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.h b/drivers/net/wwan/iosm/iosm_ipc_trace.h index 5ebe7790585c..3e7c7f163e1d 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_trace.h +++ b/drivers/net/wwan/iosm/iosm_ipc_trace.h @@ -29,7 +29,7 @@ enum trace_ctrl_mode { * @ipc_imem: Imem instance * @dev: Pointer to device struct * @channel: Channel instance - * @chl_id: Channel Indentifier + * @chl_id: Channel Identifier * @trc_mutex: Mutex used for read and write mode * @mode: Mode for enable and disable trace */ diff --git a/drivers/net/wwan/iosm/iosm_ipc_wwan.c b/drivers/net/wwan/iosm/iosm_ipc_wwan.c index 93d17de08786..ff747fc79aaf 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_wwan.c +++ b/drivers/net/wwan/iosm/iosm_ipc_wwan.c @@ -6,7 +6,6 @@ #include <linux/etherdevice.h> #include <linux/if_arp.h> #include <linux/if_link.h> -#include <linux/pm_runtime.h> #include <linux/rtnetlink.h> #include <linux/wwan.h> #include <net/pkt_sched.h> @@ -52,13 +51,11 @@ static int ipc_wwan_link_open(struct net_device *netdev) struct iosm_netdev_priv *priv = wwan_netdev_drvpriv(netdev); struct iosm_wwan *ipc_wwan = priv->ipc_wwan; int if_id = priv->if_id; - int ret = 0; if (if_id < IP_MUX_SESSION_START || if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) return -EINVAL; - pm_runtime_get_sync(ipc_wwan->ipc_imem->dev); /* get channel id */ priv->ch_id = ipc_imem_sys_wwan_open(ipc_wwan->ipc_imem, if_id); @@ -66,8 +63,7 @@ static int ipc_wwan_link_open(struct net_device *netdev) dev_err(ipc_wwan->dev, "cannot connect wwan0 & id %d to the IPC mem layer", if_id); - ret = -ENODEV; - goto err_out; + return -ENODEV; } /* enable tx path, DL data may follow */ @@ -76,11 +72,7 @@ static int ipc_wwan_link_open(struct net_device *netdev) dev_dbg(ipc_wwan->dev, "Channel id %d allocated to if_id %d", priv->ch_id, priv->if_id); -err_out: - pm_runtime_mark_last_busy(ipc_wwan->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_wwan->ipc_imem->dev); - - return ret; + return 0; } /* Bring-down the wwan net link */ @@ -90,12 +82,9 @@ static int ipc_wwan_link_stop(struct net_device *netdev) netif_stop_queue(netdev); - pm_runtime_get_sync(priv->ipc_wwan->ipc_imem->dev); ipc_imem_sys_wwan_close(priv->ipc_wwan->ipc_imem, priv->if_id, priv->ch_id); priv->ch_id = -1; - pm_runtime_mark_last_busy(priv->ipc_wwan->ipc_imem->dev); - pm_runtime_put_autosuspend(priv->ipc_wwan->ipc_imem->dev); return 0; } @@ -117,7 +106,6 @@ static netdev_tx_t ipc_wwan_link_transmit(struct sk_buff *skb, if_id >= ARRAY_SIZE(ipc_wwan->sub_netlist)) return -EINVAL; - pm_runtime_get(ipc_wwan->ipc_imem->dev); /* Send the SKB to device for transmission */ ret = ipc_imem_sys_wwan_transmit(ipc_wwan->ipc_imem, if_id, priv->ch_id, skb); @@ -131,14 +119,9 @@ static netdev_tx_t ipc_wwan_link_transmit(struct sk_buff *skb, ret = NETDEV_TX_BUSY; dev_err(ipc_wwan->dev, "unable to push packets"); } else { - pm_runtime_mark_last_busy(ipc_wwan->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_wwan->ipc_imem->dev); goto exit; } - pm_runtime_mark_last_busy(ipc_wwan->ipc_imem->dev); - pm_runtime_put_autosuspend(ipc_wwan->ipc_imem->dev); - return ret; exit: diff --git a/drivers/net/wwan/rpmsg_wwan_ctrl.c b/drivers/net/wwan/rpmsg_wwan_ctrl.c index 86b60aadfa11..26756ff0e44d 100644 --- a/drivers/net/wwan/rpmsg_wwan_ctrl.c +++ b/drivers/net/wwan/rpmsg_wwan_ctrl.c @@ -37,7 +37,7 @@ static int rpmsg_wwan_ctrl_start(struct wwan_port *port) .dst = RPMSG_ADDR_ANY, }; - strncpy(chinfo.name, rpwwan->rpdev->id.name, RPMSG_NAME_SIZE); + strscpy(chinfo.name, rpwwan->rpdev->id.name, sizeof(chinfo.name)); rpwwan->ept = rpmsg_create_ept(rpwwan->rpdev, rpmsg_wwan_ctrl_callback, rpwwan, chinfo); if (!rpwwan->ept) diff --git a/drivers/nvme/host/auth.c b/drivers/nvme/host/auth.c index daf5d144a8ea..064592a5d546 100644 --- a/drivers/nvme/host/auth.c +++ b/drivers/nvme/host/auth.c @@ -341,7 +341,7 @@ static int nvme_auth_process_dhchap_success1(struct nvme_ctrl *ctrl, struct nvmf_auth_dhchap_success1_data *data = chap->buf; size_t size = sizeof(*data); - if (chap->ctrl_key) + if (chap->s2) size += chap->hash_len; if (size > CHAP_BUF_SIZE) { @@ -825,7 +825,7 @@ static void nvme_queue_auth_work(struct work_struct *work) goto fail2; } - if (chap->ctrl_key) { + if (chap->s2) { /* DH-HMAC-CHAP Step 5: send success2 */ dev_dbg(ctrl->device, "%s: qid %d send success2\n", __func__, chap->qid); diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index d8ff796fd5f2..747c879e8982 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -108,9 +108,13 @@ static void *nvme_add_user_metadata(struct request *req, void __user *ubuf, if (!buf) goto out; - ret = -EFAULT; - if ((req_op(req) == REQ_OP_DRV_OUT) && copy_from_user(buf, ubuf, len)) - goto out_free_meta; + if (req_op(req) == REQ_OP_DRV_OUT) { + ret = -EFAULT; + if (copy_from_user(buf, ubuf, len)) + goto out_free_meta; + } else { + memset(buf, 0, len); + } bip = bio_integrity_alloc(bio, GFP_KERNEL, 1); if (IS_ERR(bip)) { diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 347cb5daebc3..3f0c9ee09a12 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -3329,7 +3329,8 @@ static const struct pci_device_id nvme_id_table[] = { { PCI_VDEVICE(INTEL, 0x0a54), /* Intel P4500/P4600 */ .driver_data = NVME_QUIRK_STRIPE_SIZE | NVME_QUIRK_DEALLOCATE_ZEROES | - NVME_QUIRK_IGNORE_DEV_SUBNQN, }, + NVME_QUIRK_IGNORE_DEV_SUBNQN | + NVME_QUIRK_BOGUS_NID, }, { PCI_VDEVICE(INTEL, 0x0a55), /* Dell Express Flash P4600 */ .driver_data = NVME_QUIRK_STRIPE_SIZE | NVME_QUIRK_DEALLOCATE_ZEROES, }, diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index 337a624a537c..a7fea4cbacd7 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -638,6 +638,9 @@ static void __nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) static void nvme_rdma_stop_queue(struct nvme_rdma_queue *queue) { + if (!test_bit(NVME_RDMA_Q_ALLOCATED, &queue->flags)) + return; + mutex_lock(&queue->queue_lock); if (test_and_clear_bit(NVME_RDMA_Q_LIVE, &queue->flags)) __nvme_rdma_stop_queue(queue); diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c index 586458f765f1..1d9854484e2e 100644 --- a/drivers/nvme/target/fabrics-cmd-auth.c +++ b/drivers/nvme/target/fabrics-cmd-auth.c @@ -333,19 +333,21 @@ done: __func__, ctrl->cntlid, req->sq->qid, status, req->error_loc); req->cqe->result.u64 = 0; - nvmet_req_complete(req, status); if (req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2 && req->sq->dhchap_step != NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) { unsigned long auth_expire_secs = ctrl->kato ? ctrl->kato : 120; mod_delayed_work(system_wq, &req->sq->auth_expired_work, auth_expire_secs * HZ); - return; + goto complete; } /* Final states, clear up variables */ nvmet_auth_sq_free(req->sq); if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE2) nvmet_ctrl_fatal_error(ctrl); + +complete: + nvmet_req_complete(req, status); } static int nvmet_auth_challenge(struct nvmet_req *req, void *d, int al) @@ -514,11 +516,12 @@ void nvmet_execute_auth_receive(struct nvmet_req *req) kfree(d); done: req->cqe->result.u64 = 0; - nvmet_req_complete(req, status); + if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_SUCCESS2) nvmet_auth_sq_free(req->sq); else if (req->sq->dhchap_step == NVME_AUTH_DHCHAP_MESSAGE_FAILURE1) { nvmet_auth_sq_free(req->sq); nvmet_ctrl_fatal_error(ctrl); } + nvmet_req_complete(req, status); } diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index cd92d7ddf5ed..197fc2ecb164 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -372,6 +372,7 @@ static void nvmet_tcp_fatal_error(struct nvmet_tcp_queue *queue) static void nvmet_tcp_socket_error(struct nvmet_tcp_queue *queue, int status) { + queue->rcv_state = NVMET_TCP_RECV_ERR; if (status == -EPIPE || status == -ECONNRESET) kernel_sock_shutdown(queue->sock, SHUT_RDWR); else @@ -910,15 +911,11 @@ static int nvmet_tcp_handle_icreq(struct nvmet_tcp_queue *queue) iov.iov_len = sizeof(*icresp); ret = kernel_sendmsg(queue->sock, &msg, &iov, 1, iov.iov_len); if (ret < 0) - goto free_crypto; + return ret; /* queue removal will cleanup */ queue->state = NVMET_TCP_Q_LIVE; nvmet_prepare_receive_pdu(queue); return 0; -free_crypto: - if (queue->hdr_digest || queue->data_digest) - nvmet_tcp_free_crypto(queue); - return ret; } static void nvmet_tcp_handle_req_failure(struct nvmet_tcp_queue *queue, diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index 1f9a35f724f5..0dda70e1ef90 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -23,7 +23,8 @@ static bool riscv_perf_user_access(struct perf_event *event) return ((event->attr.type == PERF_TYPE_HARDWARE) || (event->attr.type == PERF_TYPE_HW_CACHE) || (event->attr.type == PERF_TYPE_RAW)) && - !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT); + !!(event->hw.flags & PERF_EVENT_FLAG_USER_READ_CNT) && + (event->hw.idx != -1); } void arch_perf_update_userpage(struct perf_event *event, diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c index 9a51053b1f99..96c7f670c8f0 100644 --- a/drivers/perf/riscv_pmu_sbi.c +++ b/drivers/perf/riscv_pmu_sbi.c @@ -510,16 +510,18 @@ static void pmu_sbi_set_scounteren(void *arg) { struct perf_event *event = (struct perf_event *)arg; - csr_write(CSR_SCOUNTEREN, - csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event))); + if (event->hw.idx != -1) + csr_write(CSR_SCOUNTEREN, + csr_read(CSR_SCOUNTEREN) | (1 << pmu_sbi_csr_index(event))); } static void pmu_sbi_reset_scounteren(void *arg) { struct perf_event *event = (struct perf_event *)arg; - csr_write(CSR_SCOUNTEREN, - csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event))); + if (event->hw.idx != -1) + csr_write(CSR_SCOUNTEREN, + csr_read(CSR_SCOUNTEREN) & ~(1 << pmu_sbi_csr_index(event))); } static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) @@ -541,7 +543,8 @@ static void pmu_sbi_ctr_start(struct perf_event *event, u64 ival) if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) && (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) - pmu_sbi_set_scounteren((void *)event); + on_each_cpu_mask(mm_cpumask(event->owner->mm), + pmu_sbi_set_scounteren, (void *)event, 1); } static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag) @@ -551,7 +554,8 @@ static void pmu_sbi_ctr_stop(struct perf_event *event, unsigned long flag) if ((hwc->flags & PERF_EVENT_FLAG_USER_ACCESS) && (hwc->flags & PERF_EVENT_FLAG_USER_READ_CNT)) - pmu_sbi_reset_scounteren((void *)event); + on_each_cpu_mask(mm_cpumask(event->owner->mm), + pmu_sbi_reset_scounteren, (void *)event, 1); ret = sbi_ecall(SBI_EXT_PMU, SBI_EXT_PMU_COUNTER_STOP, hwc->idx, 1, flag, 0, 0, 0); if (ret.error && (ret.error != SBI_ERR_ALREADY_STOPPED) && diff --git a/drivers/phy/motorola/phy-mapphone-mdm6600.c b/drivers/phy/motorola/phy-mapphone-mdm6600.c index 1d567604b650..376d023a0aa9 100644 --- a/drivers/phy/motorola/phy-mapphone-mdm6600.c +++ b/drivers/phy/motorola/phy-mapphone-mdm6600.c @@ -122,16 +122,10 @@ static int phy_mdm6600_power_on(struct phy *x) { struct phy_mdm6600 *ddata = phy_get_drvdata(x); struct gpio_desc *enable_gpio = ddata->ctrl_gpios[PHY_MDM6600_ENABLE]; - int error; if (!ddata->enabled) return -ENODEV; - error = pinctrl_pm_select_default_state(ddata->dev); - if (error) - dev_warn(ddata->dev, "%s: error with default_state: %i\n", - __func__, error); - gpiod_set_value_cansleep(enable_gpio, 1); /* Allow aggressive PM for USB, it's only needed for n_gsm port */ @@ -160,11 +154,6 @@ static int phy_mdm6600_power_off(struct phy *x) gpiod_set_value_cansleep(enable_gpio, 0); - error = pinctrl_pm_select_sleep_state(ddata->dev); - if (error) - dev_warn(ddata->dev, "%s: error with sleep_state: %i\n", - __func__, error); - return 0; } @@ -456,6 +445,7 @@ static void phy_mdm6600_device_power_off(struct phy_mdm6600 *ddata) { struct gpio_desc *reset_gpio = ddata->ctrl_gpios[PHY_MDM6600_RESET]; + int error; ddata->enabled = false; phy_mdm6600_cmd(ddata, PHY_MDM6600_CMD_BP_SHUTDOWN_REQ); @@ -471,6 +461,17 @@ static void phy_mdm6600_device_power_off(struct phy_mdm6600 *ddata) } else { dev_err(ddata->dev, "Timed out powering down\n"); } + + /* + * Keep reset gpio high with padconf internal pull-up resistor to + * prevent modem from waking up during deeper SoC idle states. The + * gpio bank lines can have glitches if not in the always-on wkup + * domain. + */ + error = pinctrl_pm_select_sleep_state(ddata->dev); + if (error) + dev_warn(ddata->dev, "%s: error with sleep_state: %i\n", + __func__, error); } static void phy_mdm6600_deferred_power_on(struct work_struct *work) @@ -571,12 +572,6 @@ static int phy_mdm6600_probe(struct platform_device *pdev) ddata->dev = &pdev->dev; platform_set_drvdata(pdev, ddata); - /* Active state selected in phy_mdm6600_power_on() */ - error = pinctrl_pm_select_sleep_state(ddata->dev); - if (error) - dev_warn(ddata->dev, "%s: error with sleep_state: %i\n", - __func__, error); - error = phy_mdm6600_init_lines(ddata); if (error) return error; @@ -627,10 +622,12 @@ idle: pm_runtime_put_autosuspend(ddata->dev); cleanup: - if (error < 0) + if (error < 0) { phy_mdm6600_device_power_off(ddata); - pm_runtime_disable(ddata->dev); - pm_runtime_dont_use_autosuspend(ddata->dev); + pm_runtime_disable(ddata->dev); + pm_runtime_dont_use_autosuspend(ddata->dev); + } + return error; } @@ -639,6 +636,7 @@ static void phy_mdm6600_remove(struct platform_device *pdev) struct phy_mdm6600 *ddata = platform_get_drvdata(pdev); struct gpio_desc *reset_gpio = ddata->ctrl_gpios[PHY_MDM6600_RESET]; + pm_runtime_get_noresume(ddata->dev); pm_runtime_dont_use_autosuspend(ddata->dev); pm_runtime_put_sync(ddata->dev); pm_runtime_disable(ddata->dev); diff --git a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c index 8814f4322adf..3642a5d4f2f3 100644 --- a/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c +++ b/drivers/phy/qualcomm/phy-qcom-apq8064-sata.c @@ -152,7 +152,7 @@ static int qcom_apq8064_sata_phy_init(struct phy *generic_phy) return ret; } - /* SATA phy calibrated succesfully, power up to functional mode */ + /* SATA phy calibrated successfully, power up to functional mode */ writel_relaxed(0x3E, base + SATA_PHY_POW_DWN_CTRL1); writel_relaxed(0x01, base + SATA_PHY_RX_IMCAL0); writel_relaxed(0x01, base + SATA_PHY_TX_IMCAL0); diff --git a/drivers/phy/qualcomm/phy-qcom-m31.c b/drivers/phy/qualcomm/phy-qcom-m31.c index ed08072ca032..5cb7e79b99b3 100644 --- a/drivers/phy/qualcomm/phy-qcom-m31.c +++ b/drivers/phy/qualcomm/phy-qcom-m31.c @@ -82,7 +82,7 @@ struct m31_priv_data { unsigned int nregs; }; -struct m31_phy_regs m31_ipq5332_regs[] = { +static struct m31_phy_regs m31_ipq5332_regs[] = { { USB_PHY_CFG0, UTMI_PHY_OVERRIDE_EN, @@ -172,8 +172,7 @@ static int m31usb_phy_init(struct phy *phy) ret = clk_prepare_enable(qphy->clk); if (ret) { - if (qphy->vreg) - regulator_disable(qphy->vreg); + regulator_disable(qphy->vreg); dev_err(&phy->dev, "failed to enable cfg ahb clock, %d\n", ret); return ret; } @@ -256,7 +255,7 @@ static int m31usb_phy_probe(struct platform_device *pdev) qphy->vreg = devm_regulator_get(dev, "vdda-phy"); if (IS_ERR(qphy->vreg)) - return dev_err_probe(dev, PTR_ERR(qphy->phy), + return dev_err_probe(dev, PTR_ERR(qphy->vreg), "failed to get vreg\n"); phy_set_drvdata(qphy->phy, qphy); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c index cbb28afce135..5e6fc8103e9d 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-combo.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-combo.c @@ -859,10 +859,10 @@ static const struct qmp_phy_init_tbl sm8550_usb3_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_PCS_TX_RX_CONFIG, 0x0c), QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_EQ_CONFIG1, 0x4b), QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_EQ_CONFIG5, 0x10), - QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_USB3_POWER_STATE_CONFIG1, 0x68), }; static const struct qmp_phy_init_tbl sm8550_usb3_pcs_usb_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_USB3_POWER_STATE_CONFIG1, 0x68), QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), QMP_PHY_INIT_CFG(QPHY_USB_V6_PCS_USB3_RCVR_DTCT_DLY_U3_L, 0x40), @@ -2555,6 +2555,7 @@ static int qmp_combo_usb_power_on(struct phy *phy) void __iomem *tx2 = qmp->tx2; void __iomem *rx2 = qmp->rx2; void __iomem *pcs = qmp->pcs; + void __iomem *pcs_usb = qmp->pcs_usb; void __iomem *status; unsigned int val; int ret; @@ -2576,6 +2577,9 @@ static int qmp_combo_usb_power_on(struct phy *phy) qmp_combo_configure(pcs, cfg->pcs_tbl, cfg->pcs_tbl_num); + if (pcs_usb) + qmp_combo_configure(pcs_usb, cfg->pcs_usb_tbl, cfg->pcs_usb_tbl_num); + if (cfg->has_pwrdn_delay) usleep_range(10, 20); diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v6.h index 9510e63ba9d8..c38530d6776b 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v6.h +++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-usb-v6.h @@ -12,7 +12,7 @@ #define QPHY_USB_V6_PCS_LOCK_DETECT_CONFIG3 0xcc #define QPHY_USB_V6_PCS_LOCK_DETECT_CONFIG6 0xd8 #define QPHY_USB_V6_PCS_REFGEN_REQ_CONFIG1 0xdc -#define QPHY_USB_V6_PCS_USB3_POWER_STATE_CONFIG1 0x90 +#define QPHY_USB_V6_PCS_POWER_STATE_CONFIG1 0x90 #define QPHY_USB_V6_PCS_RX_SIGDET_LVL 0x188 #define QPHY_USB_V6_PCS_RCVR_DTCT_DLY_P1U2_L 0x190 #define QPHY_USB_V6_PCS_RCVR_DTCT_DLY_P1U2_H 0x194 @@ -23,6 +23,7 @@ #define QPHY_USB_V6_PCS_EQ_CONFIG1 0x1dc #define QPHY_USB_V6_PCS_EQ_CONFIG5 0x1ec +#define QPHY_USB_V6_PCS_USB3_POWER_STATE_CONFIG1 0x00 #define QPHY_USB_V6_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL 0x18 #define QPHY_USB_V6_PCS_USB3_RXEQTRAINING_DFE_TIME_S2 0x3c #define QPHY_USB_V6_PCS_USB3_RCVR_DTCT_DLY_U3_L 0x40 diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c index 0130bb8e809a..c69577601ae0 100644 --- a/drivers/phy/qualcomm/phy-qcom-qmp-usb.c +++ b/drivers/phy/qualcomm/phy-qcom-qmp-usb.c @@ -1112,8 +1112,6 @@ static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), QMP_PHY_INIT_CFG(QPHY_V5_PCS_RX_SIGDET_LVL, 0xaa), QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCS_TX_RX_CONFIG, 0x0c), - QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), - QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), QMP_PHY_INIT_CFG(QPHY_V5_PCS_CDR_RESET_TIME, 0x0a), QMP_PHY_INIT_CFG(QPHY_V5_PCS_ALIGN_DETECT_CONFIG1, 0x88), QMP_PHY_INIT_CFG(QPHY_V5_PCS_ALIGN_DETECT_CONFIG2, 0x13), @@ -1122,6 +1120,11 @@ static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_REFGEN_REQ_CONFIG1, 0x21), }; +static const struct qmp_phy_init_tbl sc8280xp_usb3_uniphy_pcs_usb_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), + QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), +}; + static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_LOCK_DETECT_CONFIG1, 0xc4), QMP_PHY_INIT_CFG(QPHY_V5_PCS_LOCK_DETECT_CONFIG2, 0x89), @@ -1131,9 +1134,6 @@ static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_RCVR_DTCT_DLY_P1U2_H, 0x03), QMP_PHY_INIT_CFG(QPHY_V5_PCS_RX_SIGDET_LVL, 0xaa), QMP_PHY_INIT_CFG(QPHY_V5_PCS_PCS_TX_RX_CONFIG, 0x0c), - QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), - QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), - QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_POWER_STATE_CONFIG1, 0x6f), QMP_PHY_INIT_CFG(QPHY_V5_PCS_CDR_RESET_TIME, 0x0a), QMP_PHY_INIT_CFG(QPHY_V5_PCS_ALIGN_DETECT_CONFIG1, 0x88), QMP_PHY_INIT_CFG(QPHY_V5_PCS_ALIGN_DETECT_CONFIG2, 0x13), @@ -1142,6 +1142,12 @@ static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_tbl[] = { QMP_PHY_INIT_CFG(QPHY_V5_PCS_REFGEN_REQ_CONFIG1, 0x21), }; +static const struct qmp_phy_init_tbl sa8775p_usb3_uniphy_pcs_usb_tbl[] = { + QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_RXEQTRAINING_DFE_TIME_S2, 0x07), + QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_LFPS_DET_HIGH_COUNT_VAL, 0xf8), + QMP_PHY_INIT_CFG(QPHY_V5_PCS_USB3_POWER_STATE_CONFIG1, 0x6f), +}; + struct qmp_usb_offsets { u16 serdes; u16 pcs; @@ -1383,6 +1389,8 @@ static const struct qmp_phy_cfg sa8775p_usb3_uniphy_cfg = { .rx_tbl_num = ARRAY_SIZE(sc8280xp_usb3_uniphy_rx_tbl), .pcs_tbl = sa8775p_usb3_uniphy_pcs_tbl, .pcs_tbl_num = ARRAY_SIZE(sa8775p_usb3_uniphy_pcs_tbl), + .pcs_usb_tbl = sa8775p_usb3_uniphy_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(sa8775p_usb3_uniphy_pcs_usb_tbl), .clk_list = qmp_v4_phy_clk_l, .num_clks = ARRAY_SIZE(qmp_v4_phy_clk_l), .reset_list = qcm2290_usb3phy_reset_l, @@ -1405,6 +1413,8 @@ static const struct qmp_phy_cfg sc8280xp_usb3_uniphy_cfg = { .rx_tbl_num = ARRAY_SIZE(sc8280xp_usb3_uniphy_rx_tbl), .pcs_tbl = sc8280xp_usb3_uniphy_pcs_tbl, .pcs_tbl_num = ARRAY_SIZE(sc8280xp_usb3_uniphy_pcs_tbl), + .pcs_usb_tbl = sc8280xp_usb3_uniphy_pcs_usb_tbl, + .pcs_usb_tbl_num = ARRAY_SIZE(sc8280xp_usb3_uniphy_pcs_usb_tbl), .clk_list = qmp_v4_phy_clk_l, .num_clks = ARRAY_SIZE(qmp_v4_phy_clk_l), .reset_list = qcm2290_usb3phy_reset_l, @@ -1703,6 +1713,7 @@ static int qmp_usb_power_on(struct phy *phy) void __iomem *tx = qmp->tx; void __iomem *rx = qmp->rx; void __iomem *pcs = qmp->pcs; + void __iomem *pcs_usb = qmp->pcs_usb; void __iomem *status; unsigned int val; int ret; @@ -1726,6 +1737,9 @@ static int qmp_usb_power_on(struct phy *phy) qmp_usb_configure(pcs, cfg->pcs_tbl, cfg->pcs_tbl_num); + if (pcs_usb) + qmp_usb_configure(pcs_usb, cfg->pcs_usb_tbl, cfg->pcs_usb_tbl_num); + if (cfg->has_pwrdn_delay) usleep_range(10, 20); diff --git a/drivers/phy/realtek/Kconfig b/drivers/phy/realtek/Kconfig index 650e20ed69af..75ac7e7c31ae 100644 --- a/drivers/phy/realtek/Kconfig +++ b/drivers/phy/realtek/Kconfig @@ -2,6 +2,9 @@ # # Phy drivers for Realtek platforms # + +if ARCH_REALTEK || COMPILE_TEST + config PHY_RTK_RTD_USB2PHY tristate "Realtek RTD USB2 PHY Transceiver Driver" depends on USB_SUPPORT @@ -25,3 +28,5 @@ config PHY_RTK_RTD_USB3PHY The DHC (digital home center) RTD series SoCs used the Synopsys DWC3 USB IP. This driver will do the PHY initialization of the parameters. + +endif # ARCH_REALTEK || COMPILE_TEST diff --git a/drivers/phy/realtek/phy-rtk-usb2.c b/drivers/phy/realtek/phy-rtk-usb2.c index 5e7ee060b404..aedc78bd37f7 100644 --- a/drivers/phy/realtek/phy-rtk-usb2.c +++ b/drivers/phy/realtek/phy-rtk-usb2.c @@ -853,17 +853,11 @@ static inline void create_debug_files(struct rtk_phy *rtk_phy) rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev), phy_debug_root); - if (!rtk_phy->debug_dir) - return; - if (!debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy, - &rtk_usb2_parameter_fops)) - goto file_error; + debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy, + &rtk_usb2_parameter_fops); return; - -file_error: - debugfs_remove_recursive(rtk_phy->debug_dir); } static inline void remove_debug_files(struct rtk_phy *rtk_phy) diff --git a/drivers/phy/realtek/phy-rtk-usb3.c b/drivers/phy/realtek/phy-rtk-usb3.c index 7881f908aade..dfb3122f3f11 100644 --- a/drivers/phy/realtek/phy-rtk-usb3.c +++ b/drivers/phy/realtek/phy-rtk-usb3.c @@ -416,17 +416,11 @@ static inline void create_debug_files(struct rtk_phy *rtk_phy) return; rtk_phy->debug_dir = debugfs_create_dir(dev_name(rtk_phy->dev), phy_debug_root); - if (!rtk_phy->debug_dir) - return; - if (!debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy, - &rtk_usb3_parameter_fops)) - goto file_error; + debugfs_create_file("parameter", 0444, rtk_phy->debug_dir, rtk_phy, + &rtk_usb3_parameter_fops); return; - -file_error: - debugfs_remove_recursive(rtk_phy->debug_dir); } static inline void remove_debug_files(struct rtk_phy *rtk_phy) diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c index e2f7519bef04..e9dc9638120a 100644 --- a/drivers/pinctrl/core.c +++ b/drivers/pinctrl/core.c @@ -1022,20 +1022,17 @@ static int add_setting(struct pinctrl *p, struct pinctrl_dev *pctldev, static struct pinctrl *find_pinctrl(struct device *dev) { - struct pinctrl *entry, *p = NULL; + struct pinctrl *p; mutex_lock(&pinctrl_list_mutex); - - list_for_each_entry(entry, &pinctrl_list, node) { - if (entry->dev == dev) { - p = entry; - kref_get(&p->users); - break; + list_for_each_entry(p, &pinctrl_list, node) + if (p->dev == dev) { + mutex_unlock(&pinctrl_list_mutex); + return p; } - } mutex_unlock(&pinctrl_list_mutex); - return p; + return NULL; } static void pinctrl_free(struct pinctrl *p, bool inlist); @@ -1143,6 +1140,7 @@ struct pinctrl *pinctrl_get(struct device *dev) p = find_pinctrl(dev); if (p) { dev_dbg(dev, "obtain a copy of previously claimed pinctrl\n"); + kref_get(&p->users); return p; } diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c index e5a418026ba3..0b2839d27fd6 100644 --- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c +++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c @@ -32,7 +32,8 @@ struct lpi_pinctrl { char __iomem *tlmm_base; char __iomem *slew_base; struct clk_bulk_data clks[MAX_LPI_NUM_CLKS]; - struct mutex slew_access_lock; + /* Protects from concurrent register updates */ + struct mutex lock; DECLARE_BITMAP(ever_gpio, MAX_NR_GPIO); const struct lpi_pinctrl_variant_data *data; }; @@ -103,6 +104,7 @@ static int lpi_gpio_set_mux(struct pinctrl_dev *pctldev, unsigned int function, if (WARN_ON(i == g->nfuncs)) return -EINVAL; + mutex_lock(&pctrl->lock); val = lpi_gpio_read(pctrl, pin, LPI_GPIO_CFG_REG); /* @@ -128,6 +130,7 @@ static int lpi_gpio_set_mux(struct pinctrl_dev *pctldev, unsigned int function, u32p_replace_bits(&val, i, LPI_GPIO_FUNCTION_MASK); lpi_gpio_write(pctrl, pin, LPI_GPIO_CFG_REG, val); + mutex_unlock(&pctrl->lock); return 0; } @@ -233,14 +236,14 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, if (slew_offset == LPI_NO_SLEW) break; - mutex_lock(&pctrl->slew_access_lock); + mutex_lock(&pctrl->lock); sval = ioread32(pctrl->slew_base + LPI_SLEW_RATE_CTL_REG); sval &= ~(LPI_SLEW_RATE_MASK << slew_offset); sval |= arg << slew_offset; iowrite32(sval, pctrl->slew_base + LPI_SLEW_RATE_CTL_REG); - mutex_unlock(&pctrl->slew_access_lock); + mutex_unlock(&pctrl->lock); break; default: return -EINVAL; @@ -256,6 +259,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, lpi_gpio_write(pctrl, group, LPI_GPIO_VALUE_REG, val); } + mutex_lock(&pctrl->lock); val = lpi_gpio_read(pctrl, group, LPI_GPIO_CFG_REG); u32p_replace_bits(&val, pullup, LPI_GPIO_PULL_MASK); @@ -264,6 +268,7 @@ static int lpi_config_set(struct pinctrl_dev *pctldev, unsigned int group, u32p_replace_bits(&val, output_enabled, LPI_GPIO_OE_MASK); lpi_gpio_write(pctrl, group, LPI_GPIO_CFG_REG, val); + mutex_unlock(&pctrl->lock); return 0; } @@ -461,7 +466,7 @@ int lpi_pinctrl_probe(struct platform_device *pdev) pctrl->chip.label = dev_name(dev); pctrl->chip.can_sleep = false; - mutex_init(&pctrl->slew_access_lock); + mutex_init(&pctrl->lock); pctrl->ctrl = devm_pinctrl_register(dev, &pctrl->desc, pctrl); if (IS_ERR(pctrl->ctrl)) { @@ -483,7 +488,7 @@ int lpi_pinctrl_probe(struct platform_device *pdev) return 0; err_pinctrl: - mutex_destroy(&pctrl->slew_access_lock); + mutex_destroy(&pctrl->lock); clk_bulk_disable_unprepare(MAX_LPI_NUM_CLKS, pctrl->clks); return ret; @@ -495,7 +500,7 @@ int lpi_pinctrl_remove(struct platform_device *pdev) struct lpi_pinctrl *pctrl = platform_get_drvdata(pdev); int i; - mutex_destroy(&pctrl->slew_access_lock); + mutex_destroy(&pctrl->lock); clk_bulk_disable_unprepare(MAX_LPI_NUM_CLKS, pctrl->clks); for (i = 0; i < pctrl->data->npins; i++) diff --git a/drivers/platform/mellanox/mlxbf-tmfifo.c b/drivers/platform/mellanox/mlxbf-tmfifo.c index fd38d8c8371e..ab7d7a1235b8 100644 --- a/drivers/platform/mellanox/mlxbf-tmfifo.c +++ b/drivers/platform/mellanox/mlxbf-tmfifo.c @@ -609,24 +609,25 @@ static void mlxbf_tmfifo_rxtx_word(struct mlxbf_tmfifo_vring *vring, if (vring->cur_len + sizeof(u64) <= len) { /* The whole word. */ - if (!IS_VRING_DROP(vring)) { - if (is_rx) + if (is_rx) { + if (!IS_VRING_DROP(vring)) memcpy(addr + vring->cur_len, &data, sizeof(u64)); - else - memcpy(&data, addr + vring->cur_len, - sizeof(u64)); + } else { + memcpy(&data, addr + vring->cur_len, + sizeof(u64)); } vring->cur_len += sizeof(u64); } else { /* Leftover bytes. */ - if (!IS_VRING_DROP(vring)) { - if (is_rx) + if (is_rx) { + if (!IS_VRING_DROP(vring)) memcpy(addr + vring->cur_len, &data, len - vring->cur_len); - else - memcpy(&data, addr + vring->cur_len, - len - vring->cur_len); + } else { + data = 0; + memcpy(&data, addr + vring->cur_len, + len - vring->cur_len); } vring->cur_len = len; } diff --git a/drivers/platform/surface/surface_platform_profile.c b/drivers/platform/surface/surface_platform_profile.c index f433a13c3689..a5a3941b3f43 100644 --- a/drivers/platform/surface/surface_platform_profile.c +++ b/drivers/platform/surface/surface_platform_profile.c @@ -159,8 +159,7 @@ static int surface_platform_profile_probe(struct ssam_device *sdev) set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, tpd->handler.choices); set_bit(PLATFORM_PROFILE_PERFORMANCE, tpd->handler.choices); - platform_profile_register(&tpd->handler); - return 0; + return platform_profile_register(&tpd->handler); } static void surface_platform_profile_remove(struct ssam_device *sdev) diff --git a/drivers/platform/x86/apple-gmux.c b/drivers/platform/x86/apple-gmux.c index cadbb557a108..1417e230edbd 100644 --- a/drivers/platform/x86/apple-gmux.c +++ b/drivers/platform/x86/apple-gmux.c @@ -105,6 +105,8 @@ struct apple_gmux_config { #define GMUX_BRIGHTNESS_MASK 0x00ffffff #define GMUX_MAX_BRIGHTNESS GMUX_BRIGHTNESS_MASK +# define MMIO_GMUX_MAX_BRIGHTNESS 0xffff + static u8 gmux_pio_read8(struct apple_gmux_data *gmux_data, int port) { return inb(gmux_data->iostart + port); @@ -857,7 +859,17 @@ get_version: memset(&props, 0, sizeof(props)); props.type = BACKLIGHT_PLATFORM; - props.max_brightness = gmux_read32(gmux_data, GMUX_PORT_MAX_BRIGHTNESS); + + /* + * All MMIO gmux's have 0xffff as max brightness, but some iMacs incorrectly + * report 0x03ff, despite the firmware being happy to set 0xffff as the brightness + * at boot. Force 0xffff for all MMIO gmux's so they all have the correct brightness + * range. + */ + if (type == APPLE_GMUX_TYPE_MMIO) + props.max_brightness = MMIO_GMUX_MAX_BRIGHTNESS; + else + props.max_brightness = gmux_read32(gmux_data, GMUX_PORT_MAX_BRIGHTNESS); #if IS_REACHABLE(CONFIG_ACPI_VIDEO) register_bdev = acpi_video_get_backlight_type() == acpi_backlight_apple_gmux; diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c index d85d895fee89..df1db54d4e18 100644 --- a/drivers/platform/x86/asus-nb-wmi.c +++ b/drivers/platform/x86/asus-nb-wmi.c @@ -531,6 +531,9 @@ static void asus_nb_wmi_quirks(struct asus_wmi_driver *driver) static const struct key_entry asus_nb_wmi_keymap[] = { { KE_KEY, ASUS_WMI_BRN_DOWN, { KEY_BRIGHTNESSDOWN } }, { KE_KEY, ASUS_WMI_BRN_UP, { KEY_BRIGHTNESSUP } }, + { KE_KEY, 0x2a, { KEY_SELECTIVE_SCREENSHOT } }, + { KE_IGNORE, 0x2b, }, /* PrintScreen (also send via PS/2) on newer models */ + { KE_IGNORE, 0x2c, }, /* CapsLock (also send via PS/2) on newer models */ { KE_KEY, 0x30, { KEY_VOLUMEUP } }, { KE_KEY, 0x31, { KEY_VOLUMEDOWN } }, { KE_KEY, 0x32, { KEY_MUTE } }, diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index 9f8cea5f9615..19bfd30861aa 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -3826,7 +3826,6 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) { unsigned int key_value = 1; bool autorelease = 1; - int orig_code = code; if (asus->driver->key_filter) { asus->driver->key_filter(asus->driver, &code, &key_value, @@ -3835,16 +3834,10 @@ static void asus_wmi_handle_event_code(int code, struct asus_wmi *asus) return; } - if (code >= NOTIFY_BRNUP_MIN && code <= NOTIFY_BRNUP_MAX) - code = ASUS_WMI_BRN_UP; - else if (code >= NOTIFY_BRNDOWN_MIN && code <= NOTIFY_BRNDOWN_MAX) - code = ASUS_WMI_BRN_DOWN; - - if (code == ASUS_WMI_BRN_DOWN || code == ASUS_WMI_BRN_UP) { - if (acpi_video_get_backlight_type() == acpi_backlight_vendor) { - asus_wmi_backlight_notify(asus, orig_code); - return; - } + if (acpi_video_get_backlight_type() == acpi_backlight_vendor && + code >= NOTIFY_BRNUP_MIN && code <= NOTIFY_BRNDOWN_MAX) { + asus_wmi_backlight_notify(asus, code); + return; } if (code == NOTIFY_KBD_BRTUP) { diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h index a478ebfd34df..fc41d1b1bb7f 100644 --- a/drivers/platform/x86/asus-wmi.h +++ b/drivers/platform/x86/asus-wmi.h @@ -18,7 +18,7 @@ #include <linux/i8042.h> #define ASUS_WMI_KEY_IGNORE (-1) -#define ASUS_WMI_BRN_DOWN 0x20 +#define ASUS_WMI_BRN_DOWN 0x2e #define ASUS_WMI_BRN_UP 0x2f struct module; diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c index 1152deaa0078..33ab207493e3 100644 --- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c +++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-common.c @@ -176,7 +176,7 @@ show_uncore_data(initial_max_freq_khz); static int create_attr_group(struct uncore_data *data, char *name) { - int ret, index = 0; + int ret, freq, index = 0; init_attribute_rw(max_freq_khz); init_attribute_rw(min_freq_khz); @@ -197,7 +197,11 @@ static int create_attr_group(struct uncore_data *data, char *name) data->uncore_attrs[index++] = &data->min_freq_khz_dev_attr.attr; data->uncore_attrs[index++] = &data->initial_min_freq_khz_dev_attr.attr; data->uncore_attrs[index++] = &data->initial_max_freq_khz_dev_attr.attr; - data->uncore_attrs[index++] = &data->current_freq_khz_dev_attr.attr; + + ret = uncore_read_freq(data, &freq); + if (!ret) + data->uncore_attrs[index++] = &data->current_freq_khz_dev_attr.attr; + data->uncore_attrs[index] = NULL; data->uncore_attr_group.name = name; diff --git a/drivers/platform/x86/mlx-platform.c b/drivers/platform/x86/mlx-platform.c index 3d96dbf79a72..a2ffe4157df1 100644 --- a/drivers/platform/x86/mlx-platform.c +++ b/drivers/platform/x86/mlx-platform.c @@ -6514,6 +6514,7 @@ static int mlxplat_i2c_main_init(struct mlxplat_priv *priv) return 0; fail_mlxplat_i2c_mux_topology_init: + platform_device_unregister(priv->pdev_i2c); fail_platform_i2c_register: fail_mlxplat_mlxcpld_verify_bus_topology: return err; @@ -6521,6 +6522,7 @@ fail_mlxplat_mlxcpld_verify_bus_topology: static void mlxplat_i2c_main_exit(struct mlxplat_priv *priv) { + mlxplat_pre_exit(priv); mlxplat_i2c_mux_topology_exit(priv); if (priv->pdev_i2c) platform_device_unregister(priv->pdev_i2c); @@ -6597,7 +6599,7 @@ static int mlxplat_probe(struct platform_device *pdev) fail_register_reboot_notifier: fail_regcache_sync: - mlxplat_pre_exit(priv); + mlxplat_i2c_main_exit(priv); fail_mlxplat_i2c_main_init: fail_regmap_write: fail_alloc: @@ -6614,7 +6616,6 @@ static int mlxplat_remove(struct platform_device *pdev) pm_power_off = NULL; if (mlxplat_reboot_nb) unregister_reboot_notifier(mlxplat_reboot_nb); - mlxplat_pre_exit(priv); mlxplat_i2c_main_exit(priv); mlxplat_post_exit(); return 0; diff --git a/drivers/platform/x86/msi-ec.c b/drivers/platform/x86/msi-ec.c index f26a3121092f..492eb383ee7a 100644 --- a/drivers/platform/x86/msi-ec.c +++ b/drivers/platform/x86/msi-ec.c @@ -276,14 +276,13 @@ static struct msi_ec_conf CONF2 __initdata = { static const char * const ALLOWED_FW_3[] __initconst = { "1592EMS1.111", - "E1592IMS.10C", NULL }; static struct msi_ec_conf CONF3 __initdata = { .allowed_fw = ALLOWED_FW_3, .charge_control = { - .address = 0xef, + .address = 0xd7, .offset_start = 0x8a, .offset_end = 0x80, .range_min = 0x8a, diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c index de77df97b3a4..ec163d1bcd18 100644 --- a/drivers/power/supply/qcom_battmgr.c +++ b/drivers/power/supply/qcom_battmgr.c @@ -105,7 +105,7 @@ struct qcom_battmgr_property_request { struct qcom_battmgr_update_request { struct pmic_glink_hdr hdr; - u32 battery_id; + __le32 battery_id; }; struct qcom_battmgr_charge_time_request { @@ -1282,9 +1282,9 @@ static void qcom_battmgr_enable_worker(struct work_struct *work) { struct qcom_battmgr *battmgr = container_of(work, struct qcom_battmgr, enable_work); struct qcom_battmgr_enable_request req = { - .hdr.owner = PMIC_GLINK_OWNER_BATTMGR, - .hdr.type = PMIC_GLINK_NOTIFY, - .hdr.opcode = BATTMGR_REQUEST_NOTIFICATION, + .hdr.owner = cpu_to_le32(PMIC_GLINK_OWNER_BATTMGR), + .hdr.type = cpu_to_le32(PMIC_GLINK_NOTIFY), + .hdr.opcode = cpu_to_le32(BATTMGR_REQUEST_NOTIFICATION), }; int ret; diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index 2e801cd33220..3d1b0a97301c 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -220,7 +220,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, struct ptp_clock *ptp; struct timestamp_event_queue *queue = NULL; int err = 0, index, major = MAJOR(ptp_devt); - char debugfsname[8]; + char debugfsname[16]; size_t size; if (info->n_alarm > PTP_MAX_ALARMS) @@ -343,7 +343,7 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, } /* Debugfs initialization */ - sprintf(debugfsname, "ptp%d", ptp->index); + snprintf(debugfsname, sizeof(debugfsname), "ptp%d", ptp->index); ptp->debugfs_root = debugfs_create_dir(debugfsname, NULL); return ptp; diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c index 3ef636935a54..3ff46fc694f8 100644 --- a/drivers/s390/cio/css.c +++ b/drivers/s390/cio/css.c @@ -233,17 +233,19 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid, */ ret = dma_set_coherent_mask(&sch->dev, DMA_BIT_MASK(31)); if (ret) - goto err; + goto err_lock; /* * But we don't have such restrictions imposed on the stuff that * is handled by the streaming API. */ ret = dma_set_mask(&sch->dev, DMA_BIT_MASK(64)); if (ret) - goto err; + goto err_lock; return sch; +err_lock: + kfree(sch->lock); err: kfree(sch); return ERR_PTR(ret); diff --git a/drivers/s390/net/ctcm_main.c b/drivers/s390/net/ctcm_main.c index 6faf27136024..ac15d7c2b200 100644 --- a/drivers/s390/net/ctcm_main.c +++ b/drivers/s390/net/ctcm_main.c @@ -200,13 +200,13 @@ static void channel_free(struct channel *ch) static void channel_remove(struct channel *ch) { struct channel **c = &channels; - char chid[CTCM_ID_SIZE+1]; + char chid[CTCM_ID_SIZE]; int ok = 0; if (ch == NULL) return; else - strncpy(chid, ch->id, CTCM_ID_SIZE); + strscpy(chid, ch->id, sizeof(chid)); channel_free(ch); while (*c) { diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index cd783290bde5..6af2511e070c 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -6226,7 +6226,7 @@ static int qeth_add_dbf_entry(struct qeth_card *card, char *name) new_entry = kzalloc(sizeof(struct qeth_dbf_entry), GFP_KERNEL); if (!new_entry) goto err_dbg; - strncpy(new_entry->dbf_name, name, DBF_NAME_LEN); + strscpy(new_entry->dbf_name, name, sizeof(new_entry->dbf_name)); new_entry->dbf_info = card->debug; mutex_lock(&qeth_dbf_list_mutex); list_add(&new_entry->dbf_list, &qeth_dbf_list); diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c index c3c1f466fe01..605013d3ee83 100644 --- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c +++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c @@ -12913,8 +12913,10 @@ _mpt3sas_init(void) mpt3sas_ctl_init(hbas_to_enumerate); error = pci_register_driver(&mpt3sas_driver); - if (error) + if (error) { + mpt3sas_ctl_exit(hbas_to_enumerate); scsih_exit(); + } return error; } diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 50db08265c51..dcae09a37d49 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -4953,7 +4953,7 @@ qla2x00_mem_free(struct qla_hw_data *ha) ha->gid_list = NULL; ha->gid_list_dma = 0; - if (!list_empty(&ha->base_qpair->dsd_list)) { + if (ha->base_qpair && !list_empty(&ha->base_qpair->dsd_list)) { struct dsd_dma *dsd_ptr, *tdsd_ptr; /* clean up allocated prev pool */ diff --git a/drivers/soundwire/Makefile b/drivers/soundwire/Makefile index c3d3ab3262d3..657f5888a77b 100644 --- a/drivers/soundwire/Makefile +++ b/drivers/soundwire/Makefile @@ -15,6 +15,10 @@ ifdef CONFIG_DEBUG_FS soundwire-bus-y += debugfs.o endif +ifdef CONFIG_IRQ_DOMAIN +soundwire-bus-y += irq.o +endif + #AMD driver soundwire-amd-y := amd_manager.o obj-$(CONFIG_SOUNDWIRE_AMD) += soundwire-amd.o diff --git a/drivers/soundwire/bus.c b/drivers/soundwire/bus.c index 1720031f35a3..0e7bc3c40f9d 100644 --- a/drivers/soundwire/bus.c +++ b/drivers/soundwire/bus.c @@ -3,13 +3,13 @@ #include <linux/acpi.h> #include <linux/delay.h> -#include <linux/irq.h> #include <linux/mod_devicetable.h> #include <linux/pm_runtime.h> #include <linux/soundwire/sdw_registers.h> #include <linux/soundwire/sdw.h> #include <linux/soundwire/sdw_type.h> #include "bus.h" +#include "irq.h" #include "sysfs_local.h" static DEFINE_IDA(sdw_bus_ida); @@ -25,23 +25,6 @@ static int sdw_get_id(struct sdw_bus *bus) return 0; } -static int sdw_irq_map(struct irq_domain *h, unsigned int virq, - irq_hw_number_t hw) -{ - struct sdw_bus *bus = h->host_data; - - irq_set_chip_data(virq, bus); - irq_set_chip(virq, &bus->irq_chip); - irq_set_nested_thread(virq, 1); - irq_set_noprobe(virq); - - return 0; -} - -static const struct irq_domain_ops sdw_domain_ops = { - .map = sdw_irq_map, -}; - /** * sdw_bus_master_add() - add a bus Master instance * @bus: bus instance @@ -168,13 +151,9 @@ int sdw_bus_master_add(struct sdw_bus *bus, struct device *parent, bus->params.curr_bank = SDW_BANK0; bus->params.next_bank = SDW_BANK1; - bus->irq_chip.name = dev_name(bus->dev); - bus->domain = irq_domain_create_linear(fwnode, SDW_MAX_DEVICES, - &sdw_domain_ops, bus); - if (!bus->domain) { - dev_err(bus->dev, "Failed to add IRQ domain\n"); - return -EINVAL; - } + ret = sdw_irq_create(bus, fwnode); + if (ret) + return ret; return 0; } @@ -213,7 +192,7 @@ void sdw_bus_master_delete(struct sdw_bus *bus) { device_for_each_child(bus->dev, NULL, sdw_delete_slave); - irq_domain_remove(bus->domain); + sdw_irq_delete(bus); sdw_master_device_del(bus); diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c index fafbc284e82d..9fa93bb923d7 100644 --- a/drivers/soundwire/bus_type.c +++ b/drivers/soundwire/bus_type.c @@ -7,6 +7,7 @@ #include <linux/soundwire/sdw.h> #include <linux/soundwire/sdw_type.h> #include "bus.h" +#include "irq.h" #include "sysfs_local.h" /** @@ -122,11 +123,8 @@ static int sdw_drv_probe(struct device *dev) if (drv->ops && drv->ops->read_prop) drv->ops->read_prop(slave); - if (slave->prop.use_domain_irq) { - slave->irq = irq_create_mapping(slave->bus->domain, slave->dev_num); - if (!slave->irq) - dev_warn(dev, "Failed to map IRQ\n"); - } + if (slave->prop.use_domain_irq) + sdw_irq_create_mapping(slave); /* init the sysfs as we have properties now */ ret = sdw_slave_sysfs_init(slave); @@ -176,8 +174,7 @@ static int sdw_drv_remove(struct device *dev) slave->probed = false; if (slave->prop.use_domain_irq) - irq_dispose_mapping(irq_find_mapping(slave->bus->domain, - slave->dev_num)); + sdw_irq_dispose_mapping(slave); mutex_unlock(&slave->sdw_dev_lock); diff --git a/drivers/soundwire/irq.c b/drivers/soundwire/irq.c new file mode 100644 index 000000000000..0c08cebb1235 --- /dev/null +++ b/drivers/soundwire/irq.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2023 Cirrus Logic, Inc. and +// Cirrus Logic International Semiconductor Ltd. + +#include <linux/device.h> +#include <linux/fwnode.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/soundwire/sdw.h> +#include "irq.h" + +static int sdw_irq_map(struct irq_domain *h, unsigned int virq, + irq_hw_number_t hw) +{ + struct sdw_bus *bus = h->host_data; + + irq_set_chip_data(virq, bus); + irq_set_chip(virq, &bus->irq_chip); + irq_set_nested_thread(virq, 1); + irq_set_noprobe(virq); + + return 0; +} + +static const struct irq_domain_ops sdw_domain_ops = { + .map = sdw_irq_map, +}; + +int sdw_irq_create(struct sdw_bus *bus, + struct fwnode_handle *fwnode) +{ + bus->irq_chip.name = dev_name(bus->dev); + + bus->domain = irq_domain_create_linear(fwnode, SDW_MAX_DEVICES, + &sdw_domain_ops, bus); + if (!bus->domain) { + dev_err(bus->dev, "Failed to add IRQ domain\n"); + return -EINVAL; + } + + return 0; +} + +void sdw_irq_delete(struct sdw_bus *bus) +{ + irq_domain_remove(bus->domain); +} + +void sdw_irq_create_mapping(struct sdw_slave *slave) +{ + slave->irq = irq_create_mapping(slave->bus->domain, slave->dev_num); + if (!slave->irq) + dev_warn(&slave->dev, "Failed to map IRQ\n"); +} + +void sdw_irq_dispose_mapping(struct sdw_slave *slave) +{ + irq_dispose_mapping(irq_find_mapping(slave->bus->domain, slave->dev_num)); +} diff --git a/drivers/soundwire/irq.h b/drivers/soundwire/irq.h new file mode 100644 index 000000000000..58a58046d92b --- /dev/null +++ b/drivers/soundwire/irq.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2023 Cirrus Logic, Inc. and + * Cirrus Logic International Semiconductor Ltd. + */ + +#ifndef __SDW_IRQ_H +#define __SDW_IRQ_H + +#include <linux/soundwire/sdw.h> +#include <linux/fwnode.h> + +#if IS_ENABLED(CONFIG_IRQ_DOMAIN) + +int sdw_irq_create(struct sdw_bus *bus, + struct fwnode_handle *fwnode); +void sdw_irq_delete(struct sdw_bus *bus); +void sdw_irq_create_mapping(struct sdw_slave *slave); +void sdw_irq_dispose_mapping(struct sdw_slave *slave); + +#else /* CONFIG_IRQ_DOMAIN */ + +static inline int sdw_irq_create(struct sdw_bus *bus, + struct fwnode_handle *fwnode) +{ + return 0; +} + +static inline void sdw_irq_delete(struct sdw_bus *bus) +{ +} + +static inline void sdw_irq_create_mapping(struct sdw_slave *slave) +{ +} + +static inline void sdw_irq_dispose_mapping(struct sdw_slave *slave) +{ +} + +#endif /* CONFIG_IRQ_DOMAIN */ + +#endif /* __SDW_IRQ_H */ diff --git a/drivers/spi/spi-npcm-fiu.c b/drivers/spi/spi-npcm-fiu.c index 0ca21ff0e9cc..e42248519688 100644 --- a/drivers/spi/spi-npcm-fiu.c +++ b/drivers/spi/spi-npcm-fiu.c @@ -353,8 +353,9 @@ static int npcm_fiu_uma_read(struct spi_mem *mem, uma_cfg |= ilog2(op->cmd.buswidth); uma_cfg |= ilog2(op->addr.buswidth) << NPCM_FIU_UMA_CFG_ADBPCK_SHIFT; - uma_cfg |= ilog2(op->dummy.buswidth) - << NPCM_FIU_UMA_CFG_DBPCK_SHIFT; + if (op->dummy.nbytes) + uma_cfg |= ilog2(op->dummy.buswidth) + << NPCM_FIU_UMA_CFG_DBPCK_SHIFT; uma_cfg |= ilog2(op->data.buswidth) << NPCM_FIU_UMA_CFG_RDBPCK_SHIFT; uma_cfg |= op->dummy.nbytes << NPCM_FIU_UMA_CFG_DBSIZ_SHIFT; diff --git a/drivers/staging/qlge/qlge_devlink.c b/drivers/staging/qlge/qlge_devlink.c index 0ab02d6d3817..0b19363ca2e9 100644 --- a/drivers/staging/qlge/qlge_devlink.c +++ b/drivers/staging/qlge/qlge_devlink.c @@ -2,51 +2,29 @@ #include "qlge.h" #include "qlge_devlink.h" -static int qlge_fill_seg_(struct devlink_fmsg *fmsg, - struct mpi_coredump_segment_header *seg_header, - u32 *reg_data) +static void qlge_fill_seg_(struct devlink_fmsg *fmsg, + struct mpi_coredump_segment_header *seg_header, + u32 *reg_data) { int regs_num = (seg_header->seg_size - sizeof(struct mpi_coredump_segment_header)) / sizeof(u32); - int err; int i; - err = devlink_fmsg_pair_nest_start(fmsg, seg_header->description); - if (err) - return err; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - return err; - err = devlink_fmsg_u32_pair_put(fmsg, "segment", seg_header->seg_num); - if (err) - return err; - err = devlink_fmsg_arr_pair_nest_start(fmsg, "values"); - if (err) - return err; + devlink_fmsg_pair_nest_start(fmsg, seg_header->description); + devlink_fmsg_obj_nest_start(fmsg); + devlink_fmsg_u32_pair_put(fmsg, "segment", seg_header->seg_num); + devlink_fmsg_arr_pair_nest_start(fmsg, "values"); for (i = 0; i < regs_num; i++) { - err = devlink_fmsg_u32_put(fmsg, *reg_data); - if (err) - return err; + devlink_fmsg_u32_put(fmsg, *reg_data); reg_data++; } - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - return err; - err = devlink_fmsg_arr_pair_nest_end(fmsg); - if (err) - return err; - err = devlink_fmsg_pair_nest_end(fmsg); - return err; + devlink_fmsg_obj_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_pair_nest_end(fmsg); } -#define FILL_SEG(seg_hdr, seg_regs) \ - do { \ - err = qlge_fill_seg_(fmsg, &dump->seg_hdr, dump->seg_regs); \ - if (err) { \ - kvfree(dump); \ - return err; \ - } \ - } while (0) +#define FILL_SEG(seg_hdr, seg_regs) \ + qlge_fill_seg_(fmsg, &dump->seg_hdr, dump->seg_regs) static int qlge_reporter_coredump(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg, void *priv_ctx, @@ -114,14 +92,8 @@ static int qlge_reporter_coredump(struct devlink_health_reporter *reporter, FILL_SEG(xfi_hss_tx_hdr, serdes_xfi_hss_tx); FILL_SEG(xfi_hss_rx_hdr, serdes_xfi_hss_rx); FILL_SEG(xfi_hss_pll_hdr, serdes_xfi_hss_pll); - - err = qlge_fill_seg_(fmsg, &dump->misc_nic_seg_hdr, - (u32 *)&dump->misc_nic_info); - if (err) { - kvfree(dump); - return err; - } - + qlge_fill_seg_(fmsg, &dump->misc_nic_seg_hdr, + (u32 *)&dump->misc_nic_info); FILL_SEG(intr_states_seg_hdr, intr_states); FILL_SEG(cam_entries_seg_hdr, cam_entries); FILL_SEG(nic_routing_words_seg_hdr, nic_routing_words); @@ -140,7 +112,7 @@ static int qlge_reporter_coredump(struct devlink_health_reporter *reporter, FILL_SEG(sem_regs_seg_hdr, sem_regs); kvfree(dump); - return err; + return 0; } static const struct devlink_health_reporter_ops qlge_reporter_ops = { diff --git a/drivers/thunderbolt/icm.c b/drivers/thunderbolt/icm.c index dbdcad8d73bf..d8b9c734abd3 100644 --- a/drivers/thunderbolt/icm.c +++ b/drivers/thunderbolt/icm.c @@ -41,6 +41,7 @@ #define PHY_PORT_CS1_LINK_STATE_SHIFT 26 #define ICM_TIMEOUT 5000 /* ms */ +#define ICM_RETRIES 3 #define ICM_APPROVE_TIMEOUT 10000 /* ms */ #define ICM_MAX_LINK 4 @@ -296,10 +297,9 @@ static bool icm_copy(struct tb_cfg_request *req, const struct ctl_pkg *pkg) static int icm_request(struct tb *tb, const void *request, size_t request_size, void *response, size_t response_size, size_t npackets, - unsigned int timeout_msec) + int retries, unsigned int timeout_msec) { struct icm *icm = tb_priv(tb); - int retries = 3; do { struct tb_cfg_request *req; @@ -410,7 +410,7 @@ static int icm_fr_get_route(struct tb *tb, u8 link, u8 depth, u64 *route) return -ENOMEM; ret = icm_request(tb, &request, sizeof(request), switches, - sizeof(*switches), npackets, ICM_TIMEOUT); + sizeof(*switches), npackets, ICM_RETRIES, ICM_TIMEOUT); if (ret) goto err_free; @@ -463,7 +463,7 @@ icm_fr_driver_ready(struct tb *tb, enum tb_security_level *security_level, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -488,7 +488,7 @@ static int icm_fr_approve_switch(struct tb *tb, struct tb_switch *sw) memset(&reply, 0, sizeof(reply)); /* Use larger timeout as establishing tunnels can take some time */ ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_APPROVE_TIMEOUT); + 1, ICM_RETRIES, ICM_APPROVE_TIMEOUT); if (ret) return ret; @@ -515,7 +515,7 @@ static int icm_fr_add_switch_key(struct tb *tb, struct tb_switch *sw) memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -543,7 +543,7 @@ static int icm_fr_challenge_switch_key(struct tb *tb, struct tb_switch *sw, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -577,7 +577,7 @@ static int icm_fr_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1020,7 +1020,7 @@ icm_tr_driver_ready(struct tb *tb, enum tb_security_level *security_level, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, 20000); + 1, 10, 2000); if (ret) return ret; @@ -1053,7 +1053,7 @@ static int icm_tr_approve_switch(struct tb *tb, struct tb_switch *sw) memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_APPROVE_TIMEOUT); + 1, ICM_RETRIES, ICM_APPROVE_TIMEOUT); if (ret) return ret; @@ -1081,7 +1081,7 @@ static int icm_tr_add_switch_key(struct tb *tb, struct tb_switch *sw) memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1110,7 +1110,7 @@ static int icm_tr_challenge_switch_key(struct tb *tb, struct tb_switch *sw, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1144,7 +1144,7 @@ static int icm_tr_approve_xdomain_paths(struct tb *tb, struct tb_xdomain *xd, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1170,7 +1170,7 @@ static int icm_tr_xdomain_tear_down(struct tb *tb, struct tb_xdomain *xd, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1496,7 +1496,7 @@ icm_ar_driver_ready(struct tb *tb, enum tb_security_level *security_level, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1522,7 +1522,7 @@ static int icm_ar_get_route(struct tb *tb, u8 link, u8 depth, u64 *route) memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1543,7 +1543,7 @@ static int icm_ar_get_boot_acl(struct tb *tb, uuid_t *uuids, size_t nuuids) memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1604,7 +1604,7 @@ static int icm_ar_set_boot_acl(struct tb *tb, const uuid_t *uuids, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; @@ -1626,7 +1626,7 @@ icm_icl_driver_ready(struct tb *tb, enum tb_security_level *security_level, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, 20000); + 1, ICM_RETRIES, 20000); if (ret) return ret; @@ -2298,7 +2298,7 @@ static int icm_usb4_switch_op(struct tb_switch *sw, u16 opcode, u32 *metadata, memset(&reply, 0, sizeof(reply)); ret = icm_request(tb, &request, sizeof(request), &reply, sizeof(reply), - 1, ICM_TIMEOUT); + 1, ICM_RETRIES, ICM_TIMEOUT); if (ret) return ret; diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c index 43171cc1cc2d..bd5815f8f23b 100644 --- a/drivers/thunderbolt/switch.c +++ b/drivers/thunderbolt/switch.c @@ -2725,6 +2725,13 @@ int tb_switch_lane_bonding_enable(struct tb_switch *sw) !tb_port_is_width_supported(down, TB_LINK_WIDTH_DUAL)) return 0; + /* + * Both lanes need to be in CL0. Here we assume lane 0 already be in + * CL0 and check just for lane 1. + */ + if (tb_wait_for_port(down->dual_link_port, false) <= 0) + return -ENOTCONN; + ret = tb_port_lane_bonding_enable(up); if (ret) { tb_port_warn(up, "failed to enable lane bonding\n"); diff --git a/drivers/thunderbolt/tb.c b/drivers/thunderbolt/tb.c index dd0a1ef8cf12..27bd6ca6f99e 100644 --- a/drivers/thunderbolt/tb.c +++ b/drivers/thunderbolt/tb.c @@ -1907,14 +1907,14 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work) in = &sw->ports[ev->port]; if (!tb_port_is_dpin(in)) { tb_port_warn(in, "bandwidth request to non-DP IN adapter\n"); - goto unlock; + goto put_sw; } tb_port_dbg(in, "handling bandwidth allocation request\n"); if (!usb4_dp_port_bandwidth_mode_enabled(in)) { tb_port_warn(in, "bandwidth allocation mode not enabled\n"); - goto unlock; + goto put_sw; } ret = usb4_dp_port_requested_bandwidth(in); @@ -1923,7 +1923,7 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work) tb_port_dbg(in, "no bandwidth request active\n"); else tb_port_warn(in, "failed to read requested bandwidth\n"); - goto unlock; + goto put_sw; } requested_bw = ret; @@ -1932,7 +1932,7 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work) tunnel = tb_find_tunnel(tb, TB_TUNNEL_DP, in, NULL); if (!tunnel) { tb_port_warn(in, "failed to find tunnel\n"); - goto unlock; + goto put_sw; } out = tunnel->dst_port; @@ -1959,6 +1959,8 @@ static void tb_handle_dp_bandwidth_request(struct work_struct *work) tb_recalc_estimated_bandwidth(tb); } +put_sw: + tb_switch_put(sw); unlock: mutex_unlock(&tb->lock); diff --git a/drivers/thunderbolt/tmu.c b/drivers/thunderbolt/tmu.c index 747f88703d5c..11f2aec2a5d3 100644 --- a/drivers/thunderbolt/tmu.c +++ b/drivers/thunderbolt/tmu.c @@ -382,7 +382,7 @@ static int tmu_mode_init(struct tb_switch *sw) } else if (ucap && tb_port_tmu_is_unidirectional(up)) { if (tmu_rates[TB_SWITCH_TMU_MODE_LOWRES] == rate) sw->tmu.mode = TB_SWITCH_TMU_MODE_LOWRES; - else if (tmu_rates[TB_SWITCH_TMU_MODE_LOWRES] == rate) + else if (tmu_rates[TB_SWITCH_TMU_MODE_HIFI_UNI] == rate) sw->tmu.mode = TB_SWITCH_TMU_MODE_HIFI_UNI; } else if (rate) { sw->tmu.mode = TB_SWITCH_TMU_MODE_HIFI_BI; diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c index 5b5566862318..9803f0bbf20d 100644 --- a/drivers/thunderbolt/xdomain.c +++ b/drivers/thunderbolt/xdomain.c @@ -703,6 +703,27 @@ out_unlock: mutex_unlock(&xdomain_lock); } +static void start_handshake(struct tb_xdomain *xd) +{ + xd->state = XDOMAIN_STATE_INIT; + queue_delayed_work(xd->tb->wq, &xd->state_work, + msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); +} + +/* Can be called from state_work */ +static void __stop_handshake(struct tb_xdomain *xd) +{ + cancel_delayed_work_sync(&xd->properties_changed_work); + xd->properties_changed_retries = 0; + xd->state_retries = 0; +} + +static void stop_handshake(struct tb_xdomain *xd) +{ + cancel_delayed_work_sync(&xd->state_work); + __stop_handshake(xd); +} + static void tb_xdp_handle_request(struct work_struct *work) { struct xdomain_request_work *xw = container_of(work, typeof(*xw), work); @@ -765,6 +786,15 @@ static void tb_xdp_handle_request(struct work_struct *work) case UUID_REQUEST: tb_dbg(tb, "%llx: received XDomain UUID request\n", route); ret = tb_xdp_uuid_response(ctl, route, sequence, uuid); + /* + * If we've stopped the discovery with an error such as + * timing out, we will restart the handshake now that we + * received UUID request from the remote host. + */ + if (!ret && xd && xd->state == XDOMAIN_STATE_ERROR) { + dev_dbg(&xd->dev, "restarting handshake\n"); + start_handshake(xd); + } break; case LINK_STATE_STATUS_REQUEST: @@ -1521,6 +1551,13 @@ static void tb_xdomain_queue_properties_changed(struct tb_xdomain *xd) msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); } +static void tb_xdomain_failed(struct tb_xdomain *xd) +{ + xd->state = XDOMAIN_STATE_ERROR; + queue_delayed_work(xd->tb->wq, &xd->state_work, + msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT)); +} + static void tb_xdomain_state_work(struct work_struct *work) { struct tb_xdomain *xd = container_of(work, typeof(*xd), state_work.work); @@ -1547,7 +1584,7 @@ static void tb_xdomain_state_work(struct work_struct *work) if (ret) { if (ret == -EAGAIN) goto retry_state; - xd->state = XDOMAIN_STATE_ERROR; + tb_xdomain_failed(xd); } else { tb_xdomain_queue_properties_changed(xd); if (xd->bonding_possible) @@ -1612,7 +1649,7 @@ static void tb_xdomain_state_work(struct work_struct *work) if (ret) { if (ret == -EAGAIN) goto retry_state; - xd->state = XDOMAIN_STATE_ERROR; + tb_xdomain_failed(xd); } else { xd->state = XDOMAIN_STATE_ENUMERATED; } @@ -1623,6 +1660,8 @@ static void tb_xdomain_state_work(struct work_struct *work) break; case XDOMAIN_STATE_ERROR: + dev_dbg(&xd->dev, "discovery failed, stopping handshake\n"); + __stop_handshake(xd); break; default: @@ -1833,21 +1872,6 @@ static void tb_xdomain_release(struct device *dev) kfree(xd); } -static void start_handshake(struct tb_xdomain *xd) -{ - xd->state = XDOMAIN_STATE_INIT; - queue_delayed_work(xd->tb->wq, &xd->state_work, - msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT)); -} - -static void stop_handshake(struct tb_xdomain *xd) -{ - cancel_delayed_work_sync(&xd->properties_changed_work); - cancel_delayed_work_sync(&xd->state_work); - xd->properties_changed_retries = 0; - xd->state_retries = 0; -} - static int __maybe_unused tb_xdomain_suspend(struct device *dev) { stop_handshake(tb_to_xdomain(dev)); diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index 26dd089d8e82..ca972fd37725 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -1617,7 +1617,7 @@ static int omap8250_suspend(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); struct uart_8250_port *up = serial8250_get_port(priv->line); - int err; + int err = 0; serial8250_suspend_port(priv->line); @@ -1627,7 +1627,8 @@ static int omap8250_suspend(struct device *dev) if (!device_may_wakeup(dev)) priv->wer = 0; serial_out(up, UART_OMAP_WER, priv->wer); - err = pm_runtime_force_suspend(dev); + if (uart_console(&up->port) && console_suspend_enabled) + err = pm_runtime_force_suspend(dev); flush_work(&priv->qos_work); return err; @@ -1636,11 +1637,15 @@ static int omap8250_suspend(struct device *dev) static int omap8250_resume(struct device *dev) { struct omap8250_priv *priv = dev_get_drvdata(dev); + struct uart_8250_port *up = serial8250_get_port(priv->line); int err; - err = pm_runtime_force_resume(dev); - if (err) - return err; + if (uart_console(&up->port) && console_suspend_enabled) { + err = pm_runtime_force_resume(dev); + if (err) + return err; + } + serial8250_resume_port(priv->line); /* Paired with pm_runtime_resume_and_get() in omap8250_suspend() */ pm_runtime_mark_last_busy(dev); @@ -1717,16 +1722,6 @@ static int omap8250_runtime_suspend(struct device *dev) if (priv->line >= 0) up = serial8250_get_port(priv->line); - /* - * When using 'no_console_suspend', the console UART must not be - * suspended. Since driver suspend is managed by runtime suspend, - * preventing runtime suspend (by returning error) will keep device - * active during suspend. - */ - if (priv->is_suspending && !console_suspend_enabled) { - if (up && uart_console(&up->port)) - return -EBUSY; - } if (priv->habit & UART_ERRATA_CLOCK_DISABLE) { int ret; diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index 7bdc21d5e13b..d5ba6e90bd95 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -156,7 +156,7 @@ static void __uart_start(struct uart_state *state) * enabled, serial_port_runtime_resume() calls start_tx() again * after enabling the device. */ - if (pm_runtime_active(&port_dev->dev)) + if (!pm_runtime_enabled(port->dev) || pm_runtime_active(port->dev)) port->ops->start_tx(port); pm_runtime_mark_last_busy(&port_dev->dev); pm_runtime_put_autosuspend(&port_dev->dev); @@ -1404,12 +1404,18 @@ static void uart_set_rs485_termination(struct uart_port *port, static int uart_rs485_config(struct uart_port *port) { struct serial_rs485 *rs485 = &port->rs485; + unsigned long flags; int ret; + if (!(rs485->flags & SER_RS485_ENABLED)) + return 0; + uart_sanitize_serial_rs485(port, rs485); uart_set_rs485_termination(port, rs485); + spin_lock_irqsave(&port->lock, flags); ret = port->rs485_config(port, NULL, rs485); + spin_unlock_irqrestore(&port->lock, flags); if (ret) memset(rs485, 0, sizeof(*rs485)); @@ -2474,11 +2480,10 @@ int uart_resume_port(struct uart_driver *drv, struct uart_port *uport) if (ret == 0) { if (tty) uart_change_line_settings(tty, state, NULL); + uart_rs485_config(uport); spin_lock_irq(&uport->lock); if (!(uport->rs485.flags & SER_RS485_ENABLED)) ops->set_mctrl(uport, uport->mctrl); - else - uart_rs485_config(uport); ops->start_tx(uport); spin_unlock_irq(&uport->lock); tty_port_set_initialized(port, true); @@ -2587,10 +2592,10 @@ uart_configure_port(struct uart_driver *drv, struct uart_state *state, port->mctrl &= TIOCM_DTR; if (!(port->rs485.flags & SER_RS485_ENABLED)) port->ops->set_mctrl(port, port->mctrl); - else - uart_rs485_config(port); spin_unlock_irqrestore(&port->lock, flags); + uart_rs485_config(port); + /* * If this driver supports console, and it hasn't been * successfully registered yet, try to re-register it. diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index c2df07545f96..8382e8cfa414 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -6895,7 +6895,7 @@ static int ufshcd_clear_tm_cmd(struct ufs_hba *hba, int tag) mask, 0, 1000, 1000); dev_err(hba->dev, "Clearing task management function with tag %d %s\n", - tag, err ? "succeeded" : "failed"); + tag, err < 0 ? "failed" : "succeeded"); out: return err; diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index fff9ec9c391f..4b67749edb99 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -1125,6 +1125,9 @@ static int cdnsp_gadget_ep_dequeue(struct usb_ep *ep, unsigned long flags; int ret; + if (request->status != -EINPROGRESS) + return 0; + if (!pep->endpoint.desc) { dev_err(pdev->dev, "%s: can't dequeue to disabled endpoint\n", diff --git a/drivers/usb/cdns3/core.h b/drivers/usb/cdns3/core.h index 4a4dbc2c1561..81a9c9d6be08 100644 --- a/drivers/usb/cdns3/core.h +++ b/drivers/usb/cdns3/core.h @@ -131,8 +131,7 @@ void cdns_set_active(struct cdns *cdns, u8 set_active); #else /* CONFIG_PM_SLEEP */ static inline int cdns_resume(struct cdns *cdns) { return 0; } -static inline int cdns_set_active(struct cdns *cdns, u8 set_active) -{ return 0; } +static inline void cdns_set_active(struct cdns *cdns, u8 set_active) { } static inline int cdns_suspend(struct cdns *cdns) { return 0; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c index 3c54b218301c..0ff47eeffb49 100644 --- a/drivers/usb/core/hub.c +++ b/drivers/usb/core/hub.c @@ -151,6 +151,10 @@ int usb_device_supports_lpm(struct usb_device *udev) if (udev->quirks & USB_QUIRK_NO_LPM) return 0; + /* Skip if the device BOS descriptor couldn't be read */ + if (!udev->bos) + return 0; + /* USB 2.1 (and greater) devices indicate LPM support through * their USB 2.0 Extended Capabilities BOS descriptor. */ @@ -327,6 +331,10 @@ static void usb_set_lpm_parameters(struct usb_device *udev) if (!udev->lpm_capable || udev->speed < USB_SPEED_SUPER) return; + /* Skip if the device BOS descriptor couldn't be read */ + if (!udev->bos) + return; + hub = usb_hub_to_struct_hub(udev->parent); /* It doesn't take time to transition the roothub into U0, since it * doesn't have an upstream link. @@ -2704,13 +2712,17 @@ out_authorized: static enum usb_ssp_rate get_port_ssp_rate(struct usb_device *hdev, u32 ext_portstatus) { - struct usb_ssp_cap_descriptor *ssp_cap = hdev->bos->ssp_cap; + struct usb_ssp_cap_descriptor *ssp_cap; u32 attr; u8 speed_id; u8 ssac; u8 lanes; int i; + if (!hdev->bos) + goto out; + + ssp_cap = hdev->bos->ssp_cap; if (!ssp_cap) goto out; @@ -4215,8 +4227,15 @@ static void usb_enable_link_state(struct usb_hcd *hcd, struct usb_device *udev, enum usb3_link_state state) { int timeout; - __u8 u1_mel = udev->bos->ss_cap->bU1devExitLat; - __le16 u2_mel = udev->bos->ss_cap->bU2DevExitLat; + __u8 u1_mel; + __le16 u2_mel; + + /* Skip if the device BOS descriptor couldn't be read */ + if (!udev->bos) + return; + + u1_mel = udev->bos->ss_cap->bU1devExitLat; + u2_mel = udev->bos->ss_cap->bU2DevExitLat; /* If the device says it doesn't have *any* exit latency to come out of * U1 or U2, it's probably lying. Assume it doesn't implement that link diff --git a/drivers/usb/core/hub.h b/drivers/usb/core/hub.h index 37897afd1b64..d44dd7f6623e 100644 --- a/drivers/usb/core/hub.h +++ b/drivers/usb/core/hub.h @@ -153,7 +153,7 @@ static inline int hub_is_superspeedplus(struct usb_device *hdev) { return (hdev->descriptor.bDeviceProtocol == USB_HUB_PR_SS && le16_to_cpu(hdev->descriptor.bcdUSB) >= 0x0310 && - hdev->bos->ssp_cap); + hdev->bos && hdev->bos->ssp_cap); } static inline unsigned hub_power_on_good_delay(struct usb_hub *hub) diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c index 9c6bf054f15d..343d2570189f 100644 --- a/drivers/usb/dwc3/core.c +++ b/drivers/usb/dwc3/core.c @@ -279,9 +279,46 @@ int dwc3_core_soft_reset(struct dwc3 *dwc) * XHCI driver will reset the host block. If dwc3 was configured for * host-only mode or current role is host, then we can return early. */ - if (dwc->dr_mode == USB_DR_MODE_HOST || dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST) + if (dwc->current_dr_role == DWC3_GCTL_PRTCAP_HOST) return 0; + /* + * If the dr_mode is host and the dwc->current_dr_role is not the + * corresponding DWC3_GCTL_PRTCAP_HOST, then the dwc3_core_init_mode + * isn't executed yet. Ensure the phy is ready before the controller + * updates the GCTL.PRTCAPDIR or other settings by soft-resetting + * the phy. + * + * Note: GUSB3PIPECTL[n] and GUSB2PHYCFG[n] are port settings where n + * is port index. If this is a multiport host, then we need to reset + * all active ports. + */ + if (dwc->dr_mode == USB_DR_MODE_HOST) { + u32 usb3_port; + u32 usb2_port; + + usb3_port = dwc3_readl(dwc->regs, DWC3_GUSB3PIPECTL(0)); + usb3_port |= DWC3_GUSB3PIPECTL_PHYSOFTRST; + dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port); + + usb2_port = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0)); + usb2_port |= DWC3_GUSB2PHYCFG_PHYSOFTRST; + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port); + + /* Small delay for phy reset assertion */ + usleep_range(1000, 2000); + + usb3_port &= ~DWC3_GUSB3PIPECTL_PHYSOFTRST; + dwc3_writel(dwc->regs, DWC3_GUSB3PIPECTL(0), usb3_port); + + usb2_port &= ~DWC3_GUSB2PHYCFG_PHYSOFTRST; + dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), usb2_port); + + /* Wait for clock synchronization */ + msleep(50); + return 0; + } + reg = dwc3_readl(dwc->regs, DWC3_DCTL); reg |= DWC3_DCTL_CSFTRST; reg &= ~DWC3_DCTL_RUN_STOP; diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c index feccf4c8cc4f..e6ab8cc225ff 100644 --- a/drivers/usb/gadget/function/f_ncm.c +++ b/drivers/usb/gadget/function/f_ncm.c @@ -1156,7 +1156,8 @@ static int ncm_unwrap_ntb(struct gether *port, struct sk_buff_head *list) { struct f_ncm *ncm = func_to_ncm(&port->func); - __le16 *tmp = (void *) skb->data; + unsigned char *ntb_ptr = skb->data; + __le16 *tmp; unsigned index, index2; int ndp_index; unsigned dg_len, dg_len2; @@ -1169,6 +1170,10 @@ static int ncm_unwrap_ntb(struct gether *port, const struct ndp_parser_opts *opts = ncm->parser_opts; unsigned crc_len = ncm->is_crc ? sizeof(uint32_t) : 0; int dgram_counter; + int to_process = skb->len; + +parse_ntb: + tmp = (__le16 *)ntb_ptr; /* dwSignature */ if (get_unaligned_le32(tmp) != opts->nth_sign) { @@ -1215,7 +1220,7 @@ static int ncm_unwrap_ntb(struct gether *port, * walk through NDP * dwSignature */ - tmp = (void *)(skb->data + ndp_index); + tmp = (__le16 *)(ntb_ptr + ndp_index); if (get_unaligned_le32(tmp) != ncm->ndp_sign) { INFO(port->func.config->cdev, "Wrong NDP SIGN\n"); goto err; @@ -1272,11 +1277,11 @@ static int ncm_unwrap_ntb(struct gether *port, if (ncm->is_crc) { uint32_t crc, crc2; - crc = get_unaligned_le32(skb->data + + crc = get_unaligned_le32(ntb_ptr + index + dg_len - crc_len); crc2 = ~crc32_le(~0, - skb->data + index, + ntb_ptr + index, dg_len - crc_len); if (crc != crc2) { INFO(port->func.config->cdev, @@ -1303,7 +1308,7 @@ static int ncm_unwrap_ntb(struct gether *port, dg_len - crc_len); if (skb2 == NULL) goto err; - skb_put_data(skb2, skb->data + index, + skb_put_data(skb2, ntb_ptr + index, dg_len - crc_len); skb_queue_tail(list, skb2); @@ -1316,10 +1321,17 @@ static int ncm_unwrap_ntb(struct gether *port, } while (ndp_len > 2 * (opts->dgram_item_len * 2)); } while (ndp_index); - dev_consume_skb_any(skb); - VDBG(port->func.config->cdev, "Parsed NTB with %d frames\n", dgram_counter); + + to_process -= block_len; + if (to_process != 0) { + ntb_ptr = (unsigned char *)(ntb_ptr + block_len); + goto parse_ntb; + } + + dev_consume_skb_any(skb); + return 0; err: skb_queue_purge(list); diff --git a/drivers/usb/gadget/udc/udc-xilinx.c b/drivers/usb/gadget/udc/udc-xilinx.c index 56b8286a8009..74590f93ea61 100644 --- a/drivers/usb/gadget/udc/udc-xilinx.c +++ b/drivers/usb/gadget/udc/udc-xilinx.c @@ -497,11 +497,13 @@ static int xudc_eptxrx(struct xusb_ep *ep, struct xusb_req *req, /* Get the Buffer address and copy the transmit data.*/ eprambase = (u32 __force *)(udc->addr + ep->rambase); if (ep->is_in) { - memcpy(eprambase, bufferptr, bytestosend); + memcpy_toio((void __iomem *)eprambase, bufferptr, + bytestosend); udc->write_fn(udc->addr, ep->offset + XUSB_EP_BUF0COUNT_OFFSET, bufferlen); } else { - memcpy(bufferptr, eprambase, bytestosend); + memcpy_toio((void __iomem *)bufferptr, eprambase, + bytestosend); } /* * Enable the buffer for transmission. @@ -515,11 +517,13 @@ static int xudc_eptxrx(struct xusb_ep *ep, struct xusb_req *req, eprambase = (u32 __force *)(udc->addr + ep->rambase + ep->ep_usb.maxpacket); if (ep->is_in) { - memcpy(eprambase, bufferptr, bytestosend); + memcpy_toio((void __iomem *)eprambase, bufferptr, + bytestosend); udc->write_fn(udc->addr, ep->offset + XUSB_EP_BUF1COUNT_OFFSET, bufferlen); } else { - memcpy(bufferptr, eprambase, bytestosend); + memcpy_toio((void __iomem *)bufferptr, eprambase, + bytestosend); } /* * Enable the buffer for transmission. @@ -1021,7 +1025,7 @@ static int __xudc_ep0_queue(struct xusb_ep *ep0, struct xusb_req *req) udc->addr); length = req->usb_req.actual = min_t(u32, length, EP0_MAX_PACKET); - memcpy(corebuf, req->usb_req.buf, length); + memcpy_toio((void __iomem *)corebuf, req->usb_req.buf, length); udc->write_fn(udc->addr, XUSB_EP_BUF0COUNT_OFFSET, length); udc->write_fn(udc->addr, XUSB_BUFFREADY_OFFSET, 1); } else { @@ -1752,7 +1756,7 @@ static void xudc_handle_setup(struct xusb_udc *udc) /* Load up the chapter 9 command buffer.*/ ep0rambase = (u32 __force *) (udc->addr + XUSB_SETUP_PKT_ADDR_OFFSET); - memcpy(&setup, ep0rambase, 8); + memcpy_toio((void __iomem *)&setup, ep0rambase, 8); udc->setup = setup; udc->setup.wValue = cpu_to_le16((u16 __force)setup.wValue); @@ -1839,7 +1843,7 @@ static void xudc_ep0_out(struct xusb_udc *udc) (ep0->rambase << 2)); buffer = req->usb_req.buf + req->usb_req.actual; req->usb_req.actual = req->usb_req.actual + bytes_to_rx; - memcpy(buffer, ep0rambase, bytes_to_rx); + memcpy_toio((void __iomem *)buffer, ep0rambase, bytes_to_rx); if (req->usb_req.length == req->usb_req.actual) { /* Data transfer completed get ready for Status stage */ @@ -1915,7 +1919,7 @@ static void xudc_ep0_in(struct xusb_udc *udc) (ep0->rambase << 2)); buffer = req->usb_req.buf + req->usb_req.actual; req->usb_req.actual = req->usb_req.actual + length; - memcpy(ep0rambase, buffer, length); + memcpy_toio((void __iomem *)ep0rambase, buffer, length); } udc->write_fn(udc->addr, XUSB_EP_BUF0COUNT_OFFSET, count); udc->write_fn(udc->addr, XUSB_BUFFREADY_OFFSET, 1); diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c index 0054d02239e2..0df5d807a77e 100644 --- a/drivers/usb/host/xhci-hub.c +++ b/drivers/usb/host/xhci-hub.c @@ -1062,19 +1062,19 @@ static void xhci_get_usb3_port_status(struct xhci_port *port, u32 *status, *status |= USB_PORT_STAT_C_CONFIG_ERROR << 16; /* USB3 specific wPortStatus bits */ - if (portsc & PORT_POWER) { + if (portsc & PORT_POWER) *status |= USB_SS_PORT_STAT_POWER; - /* link state handling */ - if (link_state == XDEV_U0) - bus_state->suspended_ports &= ~(1 << portnum); - } - /* remote wake resume signaling complete */ - if (bus_state->port_remote_wakeup & (1 << portnum) && + /* no longer suspended or resuming */ + if (link_state != XDEV_U3 && link_state != XDEV_RESUME && link_state != XDEV_RECOVERY) { - bus_state->port_remote_wakeup &= ~(1 << portnum); - usb_hcd_end_port_resume(&hcd->self, portnum); + /* remote wake resume signaling complete */ + if (bus_state->port_remote_wakeup & (1 << portnum)) { + bus_state->port_remote_wakeup &= ~(1 << portnum); + usb_hcd_end_port_resume(&hcd->self, portnum); + } + bus_state->suspended_ports &= ~(1 << portnum); } xhci_hub_report_usb3_link_state(xhci, status, portsc); @@ -1131,6 +1131,7 @@ static void xhci_get_usb2_port_status(struct xhci_port *port, u32 *status, usb_hcd_end_port_resume(&port->rhub->hcd->self, portnum); } port->rexit_active = 0; + bus_state->suspended_ports &= ~(1 << portnum); } } diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 8714ab5bf04d..0a37f0d511cf 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -2285,8 +2285,8 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir, writel(erst_size, &ir->ir_set->erst_size); erst_base = xhci_read_64(xhci, &ir->ir_set->erst_base); - erst_base &= ERST_PTR_MASK; - erst_base |= (ir->erst.erst_dma_addr & (u64) ~ERST_PTR_MASK); + erst_base &= ERST_BASE_RSVDP; + erst_base |= ir->erst.erst_dma_addr & ~ERST_BASE_RSVDP; xhci_write_64(xhci, erst_base, &ir->ir_set->erst_base); /* Set the event ring dequeue address of this interrupter */ diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c index 1dde53f6eb31..3e5dc0723a8f 100644 --- a/drivers/usb/host/xhci-ring.c +++ b/drivers/usb/host/xhci-ring.c @@ -798,7 +798,7 @@ static void xhci_giveback_urb_in_irq(struct xhci_hcd *xhci, static void xhci_unmap_td_bounce_buffer(struct xhci_hcd *xhci, struct xhci_ring *ring, struct xhci_td *td) { - struct device *dev = xhci_to_hcd(xhci)->self.controller; + struct device *dev = xhci_to_hcd(xhci)->self.sysdev; struct xhci_segment *seg = td->bounce_seg; struct urb *urb = td->urb; size_t len; @@ -2996,7 +2996,8 @@ static int xhci_handle_event(struct xhci_hcd *xhci, struct xhci_interrupter *ir) */ static void xhci_update_erst_dequeue(struct xhci_hcd *xhci, struct xhci_interrupter *ir, - union xhci_trb *event_ring_deq) + union xhci_trb *event_ring_deq, + bool clear_ehb) { u64 temp_64; dma_addr_t deq; @@ -3017,12 +3018,13 @@ static void xhci_update_erst_dequeue(struct xhci_hcd *xhci, return; /* Update HC event ring dequeue pointer */ - temp_64 &= ERST_PTR_MASK; + temp_64 &= ERST_DESI_MASK; temp_64 |= ((u64) deq & (u64) ~ERST_PTR_MASK); } /* Clear the event handler busy flag (RW1C) */ - temp_64 |= ERST_EHB; + if (clear_ehb) + temp_64 |= ERST_EHB; xhci_write_64(xhci, temp_64, &ir->ir_set->erst_dequeue); } @@ -3103,7 +3105,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) while (xhci_handle_event(xhci, ir) > 0) { if (event_loop++ < TRBS_PER_SEGMENT / 2) continue; - xhci_update_erst_dequeue(xhci, ir, event_ring_deq); + xhci_update_erst_dequeue(xhci, ir, event_ring_deq, false); event_ring_deq = ir->event_ring->dequeue; /* ring is half-full, force isoc trbs to interrupt more often */ @@ -3113,7 +3115,7 @@ irqreturn_t xhci_irq(struct usb_hcd *hcd) event_loop = 0; } - xhci_update_erst_dequeue(xhci, ir, event_ring_deq); + xhci_update_erst_dequeue(xhci, ir, event_ring_deq, true); ret = IRQ_HANDLED; out: @@ -3469,7 +3471,7 @@ static u32 xhci_td_remainder(struct xhci_hcd *xhci, int transferred, static int xhci_align_td(struct xhci_hcd *xhci, struct urb *urb, u32 enqd_len, u32 *trb_buff_len, struct xhci_segment *seg) { - struct device *dev = xhci_to_hcd(xhci)->self.controller; + struct device *dev = xhci_to_hcd(xhci)->self.sysdev; unsigned int unalign; unsigned int max_pkt; u32 new_buff_len; diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h index 7e282b4522c0..5df370482521 100644 --- a/drivers/usb/host/xhci.h +++ b/drivers/usb/host/xhci.h @@ -514,7 +514,7 @@ struct xhci_intr_reg { #define ERST_SIZE_MASK (0xffff << 16) /* erst_base bitmasks */ -#define ERST_BASE_RSVDP (0x3f) +#define ERST_BASE_RSVDP (GENMASK_ULL(5, 0)) /* erst_dequeue bitmasks */ /* Dequeue ERST Segment Index (DESI) - Segment number (or alias) diff --git a/drivers/usb/misc/onboard_usb_hub.c b/drivers/usb/misc/onboard_usb_hub.c index 3da1a4659c5f..57bbe1309094 100644 --- a/drivers/usb/misc/onboard_usb_hub.c +++ b/drivers/usb/misc/onboard_usb_hub.c @@ -434,6 +434,7 @@ static const struct usb_device_id onboard_hub_id_table[] = { { USB_DEVICE(VENDOR_ID_GENESYS, 0x0608) }, /* Genesys Logic GL850G USB 2.0 */ { USB_DEVICE(VENDOR_ID_GENESYS, 0x0610) }, /* Genesys Logic GL852G USB 2.0 */ { USB_DEVICE(VENDOR_ID_GENESYS, 0x0620) }, /* Genesys Logic GL3523 USB 3.1 */ + { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2412) }, /* USB2412 USB 2.0 */ { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2514) }, /* USB2514B USB 2.0 */ { USB_DEVICE(VENDOR_ID_MICROCHIP, 0x2517) }, /* USB2517 USB 2.0 */ { USB_DEVICE(VENDOR_ID_REALTEK, 0x0411) }, /* RTS5411 USB 3.1 */ diff --git a/drivers/usb/misc/onboard_usb_hub.h b/drivers/usb/misc/onboard_usb_hub.h index 4026ba64c592..2a4ab5ac0ebe 100644 --- a/drivers/usb/misc/onboard_usb_hub.h +++ b/drivers/usb/misc/onboard_usb_hub.h @@ -47,6 +47,7 @@ static const struct onboard_hub_pdata vialab_vl817_data = { }; static const struct of_device_id onboard_hub_match[] = { + { .compatible = "usb424,2412", .data = µchip_usb424_data, }, { .compatible = "usb424,2514", .data = µchip_usb424_data, }, { .compatible = "usb424,2517", .data = µchip_usb424_data, }, { .compatible = "usb451,8140", .data = &ti_tusb8041_data, }, diff --git a/drivers/usb/musb/musb_debugfs.c b/drivers/usb/musb/musb_debugfs.c index 78c726a71b17..2d623284edf6 100644 --- a/drivers/usb/musb/musb_debugfs.c +++ b/drivers/usb/musb/musb_debugfs.c @@ -39,7 +39,7 @@ static const struct musb_register_map musb_regmap[] = { { "IntrUsbE", MUSB_INTRUSBE, 8 }, { "DevCtl", MUSB_DEVCTL, 8 }, { "VControl", 0x68, 32 }, - { "HWVers", 0x69, 16 }, + { "HWVers", MUSB_HWVERS, 16 }, { "LinkInfo", MUSB_LINKINFO, 8 }, { "VPLen", MUSB_VPLEN, 8 }, { "HS_EOF1", MUSB_HS_EOF1, 8 }, diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index a02c29216955..bc4507781167 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -321,10 +321,16 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb, musb_giveback(musb, urb, status); qh->is_ready = ready; + /* + * musb->lock had been unlocked in musb_giveback, so qh may + * be freed, need to get it again + */ + qh = musb_ep_get_qh(hw_ep, is_in); + /* reclaim resources (and bandwidth) ASAP; deschedule it, and * invalidate qh as soon as list_empty(&hep->urb_list) */ - if (list_empty(&qh->hep->urb_list)) { + if (qh && list_empty(&qh->hep->urb_list)) { struct list_head *head; struct dma_controller *dma = musb->dma_controller; @@ -2398,6 +2404,7 @@ static int musb_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status) * and its URB list has emptied, recycle this qh. */ if (ready && list_empty(&qh->hep->urb_list)) { + musb_ep_set_qh(qh->hw_ep, is_in, NULL); qh->hep->hcpriv = NULL; list_del(&qh->ring); kfree(qh); diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index 7994a4549a6c..45dcfaadaf98 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -203,6 +203,9 @@ static void option_instat_callback(struct urb *urb); #define DELL_PRODUCT_5829E_ESIM 0x81e4 #define DELL_PRODUCT_5829E 0x81e6 +#define DELL_PRODUCT_FM101R 0x8213 +#define DELL_PRODUCT_FM101R_ESIM 0x8215 + #define KYOCERA_VENDOR_ID 0x0c88 #define KYOCERA_PRODUCT_KPC650 0x17da #define KYOCERA_PRODUCT_KPC680 0x180a @@ -1108,6 +1111,8 @@ static const struct usb_device_id option_ids[] = { .driver_info = RSVD(0) | RSVD(6) }, { USB_DEVICE(DELL_VENDOR_ID, DELL_PRODUCT_5829E_ESIM), .driver_info = RSVD(0) | RSVD(6) }, + { USB_DEVICE_INTERFACE_CLASS(DELL_VENDOR_ID, DELL_PRODUCT_FM101R, 0xff) }, + { USB_DEVICE_INTERFACE_CLASS(DELL_VENDOR_ID, DELL_PRODUCT_FM101R_ESIM, 0xff) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_E100A) }, /* ADU-E100, ADU-310 */ { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_500A) }, { USB_DEVICE(ANYDATA_VENDOR_ID, ANYDATA_PRODUCT_ADU_620UW) }, @@ -1290,6 +1295,7 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff), /* Telit LE910C1-EUX (ECM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1035, 0xff) }, /* Telit LE910C4-WWX (ECM) */ { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1), @@ -2262,6 +2268,7 @@ static const struct usb_device_id option_ids[] = { { USB_DEVICE_INTERFACE_CLASS(0x305a, 0x1406, 0xff) }, /* GosunCn GM500 ECM/NCM */ { USB_DEVICE_AND_INTERFACE_INFO(OPPO_VENDOR_ID, OPPO_PRODUCT_R11, 0xff, 0xff, 0x30) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x30) }, + { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0xff, 0x40) }, { USB_DEVICE_AND_INTERFACE_INFO(SIERRA_VENDOR_ID, SIERRA_PRODUCT_EM9191, 0xff, 0, 0) }, { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) }, { } /* Terminating entry */ diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c index 426c88a516e5..59e0218a8bc5 100644 --- a/drivers/usb/typec/altmodes/displayport.c +++ b/drivers/usb/typec/altmodes/displayport.c @@ -304,6 +304,11 @@ static int dp_altmode_vdm(struct typec_altmode *alt, typec_altmode_update_active(alt, false); dp->data.status = 0; dp->data.conf = 0; + if (dp->hpd) { + drm_connector_oob_hotplug_event(dp->connector_fwnode); + dp->hpd = false; + sysfs_notify(&dp->alt->dev.kobj, "displayport", "hpd"); + } break; case DP_CMD_STATUS_UPDATE: dp->data.status = *vdo; diff --git a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c index bb0b8479d80f..52c81378e36e 100644 --- a/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c +++ b/drivers/usb/typec/tcpm/qcom/qcom_pmic_typec_pdphy.c @@ -381,10 +381,6 @@ static int qcom_pmic_typec_pdphy_enable(struct pmic_typec_pdphy *pmic_typec_pdph struct device *dev = pmic_typec_pdphy->dev; int ret; - ret = regulator_enable(pmic_typec_pdphy->vdd_pdphy); - if (ret) - return ret; - /* PD 2.0, DR=TYPEC_DEVICE, PR=TYPEC_SINK */ ret = regmap_update_bits(pmic_typec_pdphy->regmap, pmic_typec_pdphy->base + USB_PDPHY_MSG_CONFIG_REG, @@ -422,8 +418,6 @@ static int qcom_pmic_typec_pdphy_disable(struct pmic_typec_pdphy *pmic_typec_pdp ret = regmap_write(pmic_typec_pdphy->regmap, pmic_typec_pdphy->base + USB_PDPHY_EN_CONTROL_REG, 0); - regulator_disable(pmic_typec_pdphy->vdd_pdphy); - return ret; } @@ -447,6 +441,10 @@ int qcom_pmic_typec_pdphy_start(struct pmic_typec_pdphy *pmic_typec_pdphy, int i; int ret; + ret = regulator_enable(pmic_typec_pdphy->vdd_pdphy); + if (ret) + return ret; + pmic_typec_pdphy->tcpm_port = tcpm_port; ret = pmic_typec_pdphy_reset(pmic_typec_pdphy); @@ -467,6 +465,8 @@ void qcom_pmic_typec_pdphy_stop(struct pmic_typec_pdphy *pmic_typec_pdphy) disable_irq(pmic_typec_pdphy->irq_data[i].irq); qcom_pmic_typec_pdphy_reset_on(pmic_typec_pdphy); + + regulator_disable(pmic_typec_pdphy->vdd_pdphy); } struct pmic_typec_pdphy *qcom_pmic_typec_pdphy_alloc(struct device *dev) diff --git a/drivers/usb/typec/ucsi/psy.c b/drivers/usb/typec/ucsi/psy.c index 384b42267f1f..b35c6e07911e 100644 --- a/drivers/usb/typec/ucsi/psy.c +++ b/drivers/usb/typec/ucsi/psy.c @@ -37,6 +37,15 @@ static int ucsi_psy_get_scope(struct ucsi_connector *con, struct device *dev = con->ucsi->dev; device_property_read_u8(dev, "scope", &scope); + if (scope == POWER_SUPPLY_SCOPE_UNKNOWN) { + u32 mask = UCSI_CAP_ATTR_POWER_AC_SUPPLY | + UCSI_CAP_ATTR_BATTERY_CHARGING; + + if (con->ucsi->cap.attributes & mask) + scope = POWER_SUPPLY_SCOPE_SYSTEM; + else + scope = POWER_SUPPLY_SCOPE_DEVICE; + } val->intval = scope; return 0; } diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c index c6dfe3dff346..61b64558f96c 100644 --- a/drivers/usb/typec/ucsi/ucsi.c +++ b/drivers/usb/typec/ucsi/ucsi.c @@ -787,6 +787,7 @@ static void ucsi_unregister_partner(struct ucsi_connector *con) typec_set_mode(con->port, TYPEC_STATE_SAFE); + typec_partner_set_usb_power_delivery(con->partner, NULL); ucsi_unregister_partner_pdos(con); ucsi_unregister_altmodes(con, UCSI_RECIPIENT_SOP); typec_unregister_partner(con->partner); @@ -884,6 +885,7 @@ static void ucsi_handle_connector_change(struct work_struct *work) if (ret < 0) { dev_err(ucsi->dev, "%s: GET_CONNECTOR_STATUS failed (%d)\n", __func__, ret); + clear_bit(EVENT_PENDING, &con->ucsi->flags); goto out_unlock; } diff --git a/drivers/vdpa/mlx5/net/debug.c b/drivers/vdpa/mlx5/net/debug.c index 60d6ac68cdc4..9c85162c19fc 100644 --- a/drivers/vdpa/mlx5/net/debug.c +++ b/drivers/vdpa/mlx5/net/debug.c @@ -146,7 +146,8 @@ void mlx5_vdpa_add_debugfs(struct mlx5_vdpa_net *ndev) ndev->rx_dent = debugfs_create_dir("rx", ndev->debugfs); } -void mlx5_vdpa_remove_debugfs(struct dentry *dbg) +void mlx5_vdpa_remove_debugfs(struct mlx5_vdpa_net *ndev) { - debugfs_remove_recursive(dbg); + debugfs_remove_recursive(ndev->debugfs); + ndev->debugfs = NULL; } diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c b/drivers/vdpa/mlx5/net/mlx5_vnet.c index 40a03b08d7cf..946488b8989f 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.c +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c @@ -625,30 +625,70 @@ static void cq_destroy(struct mlx5_vdpa_net *ndev, u16 idx) mlx5_db_free(ndev->mvdev.mdev, &vcq->db); } +static int read_umem_params(struct mlx5_vdpa_net *ndev) +{ + u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {}; + u16 opmod = (MLX5_CAP_VDPA_EMULATION << 1) | (HCA_CAP_OPMOD_GET_CUR & 0x01); + struct mlx5_core_dev *mdev = ndev->mvdev.mdev; + int out_size; + void *caps; + void *out; + int err; + + out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out); + out = kzalloc(out_size, GFP_KERNEL); + if (!out) + return -ENOMEM; + + MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); + MLX5_SET(query_hca_cap_in, in, op_mod, opmod); + err = mlx5_cmd_exec_inout(mdev, query_hca_cap, in, out); + if (err) { + mlx5_vdpa_warn(&ndev->mvdev, + "Failed reading vdpa umem capabilities with err %d\n", err); + goto out; + } + + caps = MLX5_ADDR_OF(query_hca_cap_out, out, capability); + + ndev->umem_1_buffer_param_a = MLX5_GET(virtio_emulation_cap, caps, umem_1_buffer_param_a); + ndev->umem_1_buffer_param_b = MLX5_GET(virtio_emulation_cap, caps, umem_1_buffer_param_b); + + ndev->umem_2_buffer_param_a = MLX5_GET(virtio_emulation_cap, caps, umem_2_buffer_param_a); + ndev->umem_2_buffer_param_b = MLX5_GET(virtio_emulation_cap, caps, umem_2_buffer_param_b); + + ndev->umem_3_buffer_param_a = MLX5_GET(virtio_emulation_cap, caps, umem_3_buffer_param_a); + ndev->umem_3_buffer_param_b = MLX5_GET(virtio_emulation_cap, caps, umem_3_buffer_param_b); + +out: + kfree(out); + return 0; +} + static void set_umem_size(struct mlx5_vdpa_net *ndev, struct mlx5_vdpa_virtqueue *mvq, int num, struct mlx5_vdpa_umem **umemp) { - struct mlx5_core_dev *mdev = ndev->mvdev.mdev; - int p_a; - int p_b; + u32 p_a; + u32 p_b; switch (num) { case 1: - p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_1_buffer_param_a); - p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_1_buffer_param_b); + p_a = ndev->umem_1_buffer_param_a; + p_b = ndev->umem_1_buffer_param_b; *umemp = &mvq->umem1; break; case 2: - p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_2_buffer_param_a); - p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_2_buffer_param_b); + p_a = ndev->umem_2_buffer_param_a; + p_b = ndev->umem_2_buffer_param_b; *umemp = &mvq->umem2; break; case 3: - p_a = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_3_buffer_param_a); - p_b = MLX5_CAP_DEV_VDPA_EMULATION(mdev, umem_3_buffer_param_b); + p_a = ndev->umem_3_buffer_param_a; + p_b = ndev->umem_3_buffer_param_b; *umemp = &mvq->umem3; break; } + (*umemp)->size = p_a * mvq->num_ent + p_b; } @@ -2679,6 +2719,11 @@ static int setup_driver(struct mlx5_vdpa_dev *mvdev) goto out; } mlx5_vdpa_add_debugfs(ndev); + + err = read_umem_params(ndev); + if (err) + goto err_setup; + err = setup_virtqueues(mvdev); if (err) { mlx5_vdpa_warn(mvdev, "setup_virtqueues\n"); @@ -2713,7 +2758,7 @@ err_tir: err_rqt: teardown_virtqueues(ndev); err_setup: - mlx5_vdpa_remove_debugfs(ndev->debugfs); + mlx5_vdpa_remove_debugfs(ndev); out: return err; } @@ -2727,8 +2772,7 @@ static void teardown_driver(struct mlx5_vdpa_net *ndev) if (!ndev->setup) return; - mlx5_vdpa_remove_debugfs(ndev->debugfs); - ndev->debugfs = NULL; + mlx5_vdpa_remove_debugfs(ndev); teardown_steering(ndev); destroy_tir(ndev); destroy_rqt(ndev); @@ -3489,8 +3533,6 @@ static void mlx5_vdpa_dev_del(struct vdpa_mgmt_dev *v_mdev, struct vdpa_device * struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev); struct workqueue_struct *wq; - mlx5_vdpa_remove_debugfs(ndev->debugfs); - ndev->debugfs = NULL; unregister_link_notifier(ndev); _vdpa_unregister_device(dev); wq = mvdev->wq; diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.h b/drivers/vdpa/mlx5/net/mlx5_vnet.h index 36c44d9fdd16..90b556a57971 100644 --- a/drivers/vdpa/mlx5/net/mlx5_vnet.h +++ b/drivers/vdpa/mlx5/net/mlx5_vnet.h @@ -65,6 +65,15 @@ struct mlx5_vdpa_net { struct hlist_head macvlan_hash[MLX5V_MACVLAN_SIZE]; struct mlx5_vdpa_irq_pool irqp; struct dentry *debugfs; + + u32 umem_1_buffer_param_a; + u32 umem_1_buffer_param_b; + + u32 umem_2_buffer_param_a; + u32 umem_2_buffer_param_b; + + u32 umem_3_buffer_param_a; + u32 umem_3_buffer_param_b; }; struct mlx5_vdpa_counter { @@ -88,7 +97,7 @@ struct macvlan_node { }; void mlx5_vdpa_add_debugfs(struct mlx5_vdpa_net *ndev); -void mlx5_vdpa_remove_debugfs(struct dentry *dbg); +void mlx5_vdpa_remove_debugfs(struct mlx5_vdpa_net *ndev); void mlx5_vdpa_add_rx_flow_table(struct mlx5_vdpa_net *ndev); void mlx5_vdpa_remove_rx_flow_table(struct mlx5_vdpa_net *ndev); void mlx5_vdpa_add_tirn(struct mlx5_vdpa_net *ndev); diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c index 00d7d72713be..b3a3cb165795 100644 --- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c +++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c @@ -499,12 +499,13 @@ static int __init vdpasim_blk_init(void) GFP_KERNEL); if (!shared_buffer) { ret = -ENOMEM; - goto parent_err; + goto mgmt_dev_err; } } return 0; - +mgmt_dev_err: + vdpa_mgmtdev_unregister(&mgmt_dev); parent_err: device_unregister(&vdpasim_blk_mgmtdev); return ret; diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index c71d573f1c94..e0c181ad17e3 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -1458,9 +1458,7 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev, goto done; } - if ((msg.type == VHOST_IOTLB_UPDATE || - msg.type == VHOST_IOTLB_INVALIDATE) && - msg.size == 0) { + if (msg.type == VHOST_IOTLB_UPDATE && msg.size == 0) { ret = -EINVAL; goto done; } diff --git a/drivers/video/fbdev/aty/atyfb_base.c b/drivers/video/fbdev/aty/atyfb_base.c index 5c87817a4f4c..3dcf83f5e7b4 100644 --- a/drivers/video/fbdev/aty/atyfb_base.c +++ b/drivers/video/fbdev/aty/atyfb_base.c @@ -3440,11 +3440,15 @@ static int atyfb_setup_generic(struct pci_dev *pdev, struct fb_info *info, } info->fix.mmio_start = raddr; +#if defined(__i386__) || defined(__ia64__) /* * By using strong UC we force the MTRR to never have an * effect on the MMIO region on both non-PAT and PAT systems. */ par->ati_regbase = ioremap_uc(info->fix.mmio_start, 0x1000); +#else + par->ati_regbase = ioremap(info->fix.mmio_start, 0x1000); +#endif if (par->ati_regbase == NULL) return -ENOMEM; diff --git a/drivers/video/fbdev/core/cfbcopyarea.c b/drivers/video/fbdev/core/cfbcopyarea.c index 6d4bfeecee35..5b80bf3dae50 100644 --- a/drivers/video/fbdev/core/cfbcopyarea.c +++ b/drivers/video/fbdev/core/cfbcopyarea.c @@ -382,7 +382,7 @@ void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area) { u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy; u32 height = area->height, width = area->width; - unsigned long const bits_per_line = p->fix.line_length*8u; + unsigned int const bits_per_line = p->fix.line_length * 8u; unsigned long __iomem *base = NULL; int bits = BITS_PER_LONG, bytes = bits >> 3; unsigned dst_idx = 0, src_idx = 0, rev_copy = 0; diff --git a/drivers/video/fbdev/core/syscopyarea.c b/drivers/video/fbdev/core/syscopyarea.c index c1eda3190968..7b8bd3a2bedc 100644 --- a/drivers/video/fbdev/core/syscopyarea.c +++ b/drivers/video/fbdev/core/syscopyarea.c @@ -316,7 +316,7 @@ void sys_copyarea(struct fb_info *p, const struct fb_copyarea *area) { u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy; u32 height = area->height, width = area->width; - unsigned long const bits_per_line = p->fix.line_length*8u; + unsigned int const bits_per_line = p->fix.line_length * 8u; unsigned long *base = NULL; int bits = BITS_PER_LONG, bytes = bits >> 3; unsigned dst_idx = 0, src_idx = 0, rev_copy = 0; diff --git a/drivers/video/fbdev/mmp/hw/mmp_ctrl.h b/drivers/video/fbdev/mmp/hw/mmp_ctrl.h index 167585a889d3..719b99a9bc77 100644 --- a/drivers/video/fbdev/mmp/hw/mmp_ctrl.h +++ b/drivers/video/fbdev/mmp/hw/mmp_ctrl.h @@ -1406,7 +1406,7 @@ struct mmphw_ctrl { /*pathes*/ int path_num; - struct mmphw_path_plat path_plats[]; + struct mmphw_path_plat path_plats[] __counted_by(path_num); }; static inline int overlay_is_vid(struct mmp_overlay *overlay) diff --git a/drivers/video/fbdev/omap/omapfb_main.c b/drivers/video/fbdev/omap/omapfb_main.c index f28cb90947a3..42c96f1cfc93 100644 --- a/drivers/video/fbdev/omap/omapfb_main.c +++ b/drivers/video/fbdev/omap/omapfb_main.c @@ -1645,13 +1645,13 @@ static int omapfb_do_probe(struct platform_device *pdev, } fbdev->int_irq = platform_get_irq(pdev, 0); if (fbdev->int_irq < 0) { - r = ENXIO; + r = -ENXIO; goto cleanup; } fbdev->ext_irq = platform_get_irq(pdev, 1); if (fbdev->ext_irq < 0) { - r = ENXIO; + r = -ENXIO; goto cleanup; } diff --git a/drivers/video/fbdev/sa1100fb.c b/drivers/video/fbdev/sa1100fb.c index 3d76ce111488..cf0f706762b4 100644 --- a/drivers/video/fbdev/sa1100fb.c +++ b/drivers/video/fbdev/sa1100fb.c @@ -1214,7 +1214,7 @@ static struct platform_driver sa1100fb_driver = { }, }; -int __init sa1100fb_init(void) +static int __init sa1100fb_init(void) { if (fb_get_options("sa1100fb", NULL)) return -ENODEV; diff --git a/drivers/video/fbdev/uvesafb.c b/drivers/video/fbdev/uvesafb.c index a1a67830fbbc..e1f421e91b4f 100644 --- a/drivers/video/fbdev/uvesafb.c +++ b/drivers/video/fbdev/uvesafb.c @@ -1928,10 +1928,10 @@ static void uvesafb_exit(void) } } - cn_del_callback(&uvesafb_cn_id); driver_remove_file(&uvesafb_driver.driver, &driver_attr_v86d); platform_device_unregister(uvesafb_device); platform_driver_unregister(&uvesafb_driver); + cn_del_callback(&uvesafb_cn_id); } module_exit(uvesafb_exit); diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index 5b15936a5214..2d5d252ef419 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -395,7 +395,11 @@ static inline s64 towards_target(struct virtio_balloon *vb) virtio_cread_le(vb->vdev, struct virtio_balloon_config, num_pages, &num_pages); - target = num_pages; + /* + * Aligned up to guest page size to avoid inflating and deflating + * balloon endlessly. + */ + target = ALIGN(num_pages, VIRTIO_BALLOON_PAGES_PER_PAGE); return target - vb->num_pages; } diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c index 97760f611295..59892a31cf76 100644 --- a/drivers/virtio/virtio_mmio.c +++ b/drivers/virtio/virtio_mmio.c @@ -631,14 +631,17 @@ static int virtio_mmio_probe(struct platform_device *pdev) spin_lock_init(&vm_dev->lock); vm_dev->base = devm_platform_ioremap_resource(pdev, 0); - if (IS_ERR(vm_dev->base)) - return PTR_ERR(vm_dev->base); + if (IS_ERR(vm_dev->base)) { + rc = PTR_ERR(vm_dev->base); + goto free_vm_dev; + } /* Check magic value */ magic = readl(vm_dev->base + VIRTIO_MMIO_MAGIC_VALUE); if (magic != ('v' | 'i' << 8 | 'r' << 16 | 't' << 24)) { dev_warn(&pdev->dev, "Wrong magic value 0x%08lx!\n", magic); - return -ENODEV; + rc = -ENODEV; + goto free_vm_dev; } /* Check device version */ @@ -646,7 +649,8 @@ static int virtio_mmio_probe(struct platform_device *pdev) if (vm_dev->version < 1 || vm_dev->version > 2) { dev_err(&pdev->dev, "Version %ld not supported!\n", vm_dev->version); - return -ENXIO; + rc = -ENXIO; + goto free_vm_dev; } vm_dev->vdev.id.device = readl(vm_dev->base + VIRTIO_MMIO_DEVICE_ID); @@ -655,7 +659,8 @@ static int virtio_mmio_probe(struct platform_device *pdev) * virtio-mmio device with an ID 0 is a (dummy) placeholder * with no function. End probing now with no error reported. */ - return -ENODEV; + rc = -ENODEV; + goto free_vm_dev; } vm_dev->vdev.id.vendor = readl(vm_dev->base + VIRTIO_MMIO_VENDOR_ID); @@ -685,6 +690,10 @@ static int virtio_mmio_probe(struct platform_device *pdev) put_device(&vm_dev->vdev.dev); return rc; + +free_vm_dev: + kfree(vm_dev); + return rc; } static int virtio_mmio_remove(struct platform_device *pdev) diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c index aad7d9296e77..9cb601e16688 100644 --- a/drivers/virtio/virtio_pci_modern_dev.c +++ b/drivers/virtio/virtio_pci_modern_dev.c @@ -291,7 +291,7 @@ int vp_modern_probe(struct virtio_pci_modern_device *mdev) err = -EINVAL; mdev->common = vp_modern_map_capability(mdev, common, sizeof(struct virtio_pci_common_cfg), 4, - 0, sizeof(struct virtio_pci_common_cfg), + 0, sizeof(struct virtio_pci_modern_common_cfg), NULL, NULL); if (!mdev->common) goto err_map_common; diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c index b7d54efb4728..a4a809efc92f 100644 --- a/fs/btrfs/backref.c +++ b/fs/btrfs/backref.c @@ -3196,12 +3196,14 @@ static int handle_direct_tree_backref(struct btrfs_backref_cache *cache, * We still need to do a tree search to find out the parents. This is for * TREE_BLOCK_REF backref (keyed or inlined). * + * @trans: Transaction handle. * @ref_key: The same as @ref_key in handle_direct_tree_backref() * @tree_key: The first key of this tree block. * @path: A clean (released) path, to avoid allocating path every time * the function get called. */ -static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, +static int handle_indirect_tree_backref(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_key *ref_key, struct btrfs_key *tree_key, @@ -3315,7 +3317,7 @@ static int handle_indirect_tree_backref(struct btrfs_backref_cache *cache, * If we know the block isn't shared we can avoid * checking its backrefs. */ - if (btrfs_block_can_be_shared(root, eb)) + if (btrfs_block_can_be_shared(trans, root, eb)) upper->checked = 0; else upper->checked = 1; @@ -3363,11 +3365,13 @@ out: * links aren't yet bi-directional. Needs to finish such links. * Use btrfs_backref_finish_upper_links() to finish such linkage. * + * @trans: Transaction handle. * @path: Released path for indirect tree backref lookup * @iter: Released backref iter for extent tree search * @node_key: The first key of the tree block */ -int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, +int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, @@ -3467,8 +3471,8 @@ int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, * offset means the root objectid. We need to search * the tree to get its parent bytenr. */ - ret = handle_indirect_tree_backref(cache, path, &key, node_key, - cur); + ret = handle_indirect_tree_backref(trans, cache, path, + &key, node_key, cur); if (ret < 0) goto out; } diff --git a/fs/btrfs/backref.h b/fs/btrfs/backref.h index 1616e3e3f1e4..71d535e03dca 100644 --- a/fs/btrfs/backref.h +++ b/fs/btrfs/backref.h @@ -540,7 +540,8 @@ static inline void btrfs_backref_panic(struct btrfs_fs_info *fs_info, bytenr); } -int btrfs_backref_add_tree_node(struct btrfs_backref_cache *cache, +int btrfs_backref_add_tree_node(struct btrfs_trans_handle *trans, + struct btrfs_backref_cache *cache, struct btrfs_path *path, struct btrfs_backref_iter *iter, struct btrfs_key *node_key, diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c index da519c1b6ad0..617d4827eec2 100644 --- a/fs/btrfs/ctree.c +++ b/fs/btrfs/ctree.c @@ -367,7 +367,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, /* * check if the tree block can be shared by multiple trees */ -int btrfs_block_can_be_shared(struct btrfs_root *root, +int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf) { /* @@ -376,11 +377,21 @@ int btrfs_block_can_be_shared(struct btrfs_root *root, * not allocated by tree relocation, we know the block is not shared. */ if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) && - buf != root->node && buf != root->commit_root && + buf != root->node && (btrfs_header_generation(buf) <= btrfs_root_last_snapshot(&root->root_item) || - btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) - return 1; + btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC))) { + if (buf != root->commit_root) + return 1; + /* + * An extent buffer that used to be the commit root may still be + * shared because the tree height may have increased and it + * became a child of a higher level root. This can happen when + * snapshotting a subvolume created in the current transaction. + */ + if (btrfs_header_generation(buf) == trans->transid) + return 1; + } return 0; } @@ -415,7 +426,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans, * are only allowed for blocks use full backrefs. */ - if (btrfs_block_can_be_shared(root, buf)) { + if (btrfs_block_can_be_shared(trans, root, buf)) { ret = btrfs_lookup_extent_info(trans, fs_info, buf->start, btrfs_header_level(buf), 1, &refs, &flags); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9419f4e37a58..ff40acd63a37 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -540,7 +540,8 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *buf, struct extent_buffer **cow_ret, u64 new_root_objectid); -int btrfs_block_can_be_shared(struct btrfs_root *root, +int btrfs_block_can_be_shared(struct btrfs_trans_handle *trans, + struct btrfs_root *root, struct extent_buffer *buf); int btrfs_del_ptr(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct btrfs_path *path, int level, int slot); diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index 9951a0caf5bb..c6d4bb8cbe29 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -466,6 +466,7 @@ static bool handle_useless_nodes(struct reloc_control *rc, * cached. */ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( + struct btrfs_trans_handle *trans, struct reloc_control *rc, struct btrfs_key *node_key, int level, u64 bytenr) { @@ -499,8 +500,8 @@ static noinline_for_stack struct btrfs_backref_node *build_backref_tree( /* Breadth-first search to build backref cache */ do { - ret = btrfs_backref_add_tree_node(cache, path, iter, node_key, - cur); + ret = btrfs_backref_add_tree_node(trans, cache, path, iter, + node_key, cur); if (ret < 0) { err = ret; goto out; @@ -2803,7 +2804,7 @@ int relocate_tree_blocks(struct btrfs_trans_handle *trans, /* Do tree relocation */ rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) { - node = build_backref_tree(rc, &block->key, + node = build_backref_tree(trans, rc, &block->key, block->level, block->bytenr); if (IS_ERR(node)) { err = PTR_ERR(node); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5a5a8d488a7b..b9ef6f54635c 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5109,7 +5109,7 @@ static void init_alloc_chunk_ctl_policy_regular( ASSERT(space_info); ctl->max_chunk_size = READ_ONCE(space_info->chunk_size); - ctl->max_stripe_size = ctl->max_chunk_size; + ctl->max_stripe_size = min_t(u64, ctl->max_chunk_size, SZ_1G); if (ctl->type & BTRFS_BLOCK_GROUP_SYSTEM) ctl->devs_max = min_t(int, ctl->devs_max, BTRFS_MAX_DEVS_SYS_CHUNK); diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c index e1f31b86fd48..5b5112c78462 100644 --- a/fs/ceph/crypto.c +++ b/fs/ceph/crypto.c @@ -460,7 +460,7 @@ int ceph_fname_to_usr(const struct ceph_fname *fname, struct fscrypt_str *tname, out: fscrypt_fname_free_buffer(&_tname); out_inode: - if ((dir != fname->dir) && !IS_ERR(dir)) { + if (dir != fname->dir) { if ((dir->i_state & I_NEW)) discard_new_inode(dir); else diff --git a/fs/ceph/file.c b/fs/ceph/file.c index b1da02f5dbe3..b5f8038065d7 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -2969,7 +2969,7 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off, ret = do_splice_direct(src_file, &src_off, dst_file, &dst_off, src_objlen, flags); /* Abort on short copies or on error */ - if (ret < src_objlen) { + if (ret < (long)src_objlen) { dout("Failed partial copy (%zd)\n", ret); goto out; } diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 800ab7920513..b79100f720b3 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -769,9 +769,7 @@ int ceph_fill_file_size(struct inode *inode, int issued, ci->i_truncate_seq = truncate_seq; /* the MDS should have revoked these caps */ - WARN_ON_ONCE(issued & (CEPH_CAP_FILE_EXCL | - CEPH_CAP_FILE_RD | - CEPH_CAP_FILE_WR | + WARN_ON_ONCE(issued & (CEPH_CAP_FILE_RD | CEPH_CAP_FILE_LAZYIO)); /* * If we hold relevant caps, or in the case where we're diff --git a/fs/fs_context.c b/fs/fs_context.c index a0ad7a0c4680..98589aae5208 100644 --- a/fs/fs_context.c +++ b/fs/fs_context.c @@ -192,17 +192,19 @@ int vfs_parse_fs_string(struct fs_context *fc, const char *key, EXPORT_SYMBOL(vfs_parse_fs_string); /** - * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data + * vfs_parse_monolithic_sep - Parse key[=val][,key[=val]]* mount data * @fc: The superblock configuration to fill in. * @data: The data to parse + * @sep: callback for separating next option * - * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be - * called from the ->monolithic_mount_data() fs_context operation. + * Parse a blob of data that's in key[=val][,key[=val]]* form with a custom + * option separator callback. * * Returns 0 on success or the error returned by the ->parse_option() fs_context * operation on failure. */ -int generic_parse_monolithic(struct fs_context *fc, void *data) +int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, + char *(*sep)(char **)) { char *options = data, *key; int ret = 0; @@ -214,7 +216,7 @@ int generic_parse_monolithic(struct fs_context *fc, void *data) if (ret) return ret; - while ((key = strsep(&options, ",")) != NULL) { + while ((key = sep(&options)) != NULL) { if (*key) { size_t v_len = 0; char *value = strchr(key, '='); @@ -233,6 +235,28 @@ int generic_parse_monolithic(struct fs_context *fc, void *data) return ret; } +EXPORT_SYMBOL(vfs_parse_monolithic_sep); + +static char *vfs_parse_comma_sep(char **s) +{ + return strsep(s, ","); +} + +/** + * generic_parse_monolithic - Parse key[=val][,key[=val]]* mount data + * @fc: The superblock configuration to fill in. + * @data: The data to parse + * + * Parse a blob of data that's in key[=val][,key[=val]]* form. This can be + * called from the ->monolithic_mount_data() fs_context operation. + * + * Returns 0 on success or the error returned by the ->parse_option() fs_context + * operation on failure. + */ +int generic_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, vfs_parse_comma_sep); +} EXPORT_SYMBOL(generic_parse_monolithic); /** diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 5db54ca29a35..2bc0aa23fde3 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -881,8 +881,10 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) size_t bytes; /* Bytes to write to folio */ size_t copied; /* Bytes copied from user */ + bytes = iov_iter_count(i); +retry: offset = pos & (chunk - 1); - bytes = min(chunk - offset, iov_iter_count(i)); + bytes = min(chunk - offset, bytes); status = balance_dirty_pages_ratelimited_flags(mapping, bdp_flags); if (unlikely(status)) @@ -933,10 +935,12 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i) * halfway through, might be a race with munmap, * might be severe memory pressure. */ - if (copied) - bytes = copied; if (chunk > PAGE_SIZE) chunk /= 2; + if (copied) { + bytes = copied; + goto retry; + } } else { pos += status; written += status; diff --git a/fs/namei.c b/fs/namei.c index 567ee547492b..94565bd7e73f 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -188,7 +188,7 @@ getname_flags(const char __user *filename, int flags, int *empty) } } - result->refcnt = 1; + atomic_set(&result->refcnt, 1); /* The empty path is special. */ if (unlikely(!len)) { if (empty) @@ -249,7 +249,7 @@ getname_kernel(const char * filename) memcpy((char *)result->name, filename, len); result->uptr = NULL; result->aname = NULL; - result->refcnt = 1; + atomic_set(&result->refcnt, 1); audit_getname(result); return result; @@ -261,9 +261,10 @@ void putname(struct filename *name) if (IS_ERR(name)) return; - BUG_ON(name->refcnt <= 0); + if (WARN_ON_ONCE(!atomic_read(&name->refcnt))) + return; - if (--name->refcnt > 0) + if (!atomic_dec_and_test(&name->refcnt)) return; if (name->name != name->iname) { diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index a1dc33864906..ef817a0475ff 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -2520,9 +2520,9 @@ ff_layout_mirror_prepare_stats(struct pnfs_layout_hdr *lo, return i; } -static int -ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) +static int ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) { + struct pnfs_layout_hdr *lo; struct nfs4_flexfile_layout *ff_layout; const int dev_count = PNFS_LAYOUTSTATS_MAXDEV; @@ -2533,11 +2533,14 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args) return -ENOMEM; spin_lock(&args->inode->i_lock); - ff_layout = FF_LAYOUT_FROM_HDR(NFS_I(args->inode)->layout); - args->num_dev = ff_layout_mirror_prepare_stats(&ff_layout->generic_hdr, - &args->devinfo[0], - dev_count, - NFS4_FF_OP_LAYOUTSTATS); + lo = NFS_I(args->inode)->layout; + if (lo && pnfs_layout_is_valid(lo)) { + ff_layout = FF_LAYOUT_FROM_HDR(lo); + args->num_dev = ff_layout_mirror_prepare_stats( + &ff_layout->generic_hdr, &args->devinfo[0], dev_count, + NFS4_FF_OP_LAYOUTSTATS); + } else + args->num_dev = 0; spin_unlock(&args->inode->i_lock); if (!args->num_dev) { kfree(args->devinfo); diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 063e00aff87e..28704f924612 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -81,7 +81,8 @@ static int _nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, if (status == 0) { if (nfs_should_remove_suid(inode)) { spin_lock(&inode->i_lock); - nfs_set_cache_invalid(inode, NFS_INO_INVALID_MODE); + nfs_set_cache_invalid(inode, + NFS_INO_REVAL_FORCED | NFS_INO_INVALID_MODE); spin_unlock(&inode->i_lock); } status = nfs_post_op_update_inode_force_wcc(inode, diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 7016eaadf555..5ee283eb9660 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -8870,8 +8870,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, const struct cred *cre /* Save the EXCHANGE_ID verifier session trunk tests */ memcpy(clp->cl_confirm.data, argp->verifier.data, sizeof(clp->cl_confirm.data)); - if (resp->flags & EXCHGID4_FLAG_USE_PNFS_DS) - set_bit(NFS_CS_DS, &clp->cl_flags); out: trace_nfs4_exchange_id(clp, status); rpc_put_task(task); diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index 306cba0b9e69..84343aefbbd6 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -2634,31 +2634,44 @@ pnfs_should_return_unused_layout(struct pnfs_layout_hdr *lo, return mode == 0; } -static int -pnfs_layout_return_unused_byserver(struct nfs_server *server, void *data) +static int pnfs_layout_return_unused_byserver(struct nfs_server *server, + void *data) { const struct pnfs_layout_range *range = data; + const struct cred *cred; struct pnfs_layout_hdr *lo; struct inode *inode; + nfs4_stateid stateid; + enum pnfs_iomode iomode; + restart: rcu_read_lock(); list_for_each_entry_rcu(lo, &server->layouts, plh_layouts) { - if (!pnfs_layout_can_be_returned(lo) || + inode = lo->plh_inode; + if (!inode || !pnfs_layout_can_be_returned(lo) || test_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags)) continue; - inode = lo->plh_inode; spin_lock(&inode->i_lock); - if (!pnfs_should_return_unused_layout(lo, range)) { + if (!lo->plh_inode || + !pnfs_should_return_unused_layout(lo, range)) { spin_unlock(&inode->i_lock); continue; } + pnfs_get_layout_hdr(lo); + pnfs_set_plh_return_info(lo, range->iomode, 0); + if (pnfs_mark_matching_lsegs_return(lo, &lo->plh_return_segs, + range, 0) != 0 || + !pnfs_prepare_layoutreturn(lo, &stateid, &cred, &iomode)) { + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + pnfs_put_layout_hdr(lo); + cond_resched(); + goto restart; + } spin_unlock(&inode->i_lock); - inode = pnfs_grab_inode_layout_hdr(lo); - if (!inode) - continue; rcu_read_unlock(); - pnfs_mark_layout_for_return(inode, range); - iput(inode); + pnfs_send_layoutreturn(lo, &stateid, &cred, iomode, false); + pnfs_put_layout_hdr(lo); cond_resched(); goto restart; } diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 7720b5e43014..9d82d50ce0b1 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -788,6 +788,8 @@ static void nfs_inode_add_request(struct nfs_page *req) */ static void nfs_inode_remove_request(struct nfs_page *req) { + struct nfs_inode *nfsi = NFS_I(nfs_page_to_inode(req)); + if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) { struct folio *folio = nfs_page_to_folio(req->wb_head); struct address_space *mapping = folio_file_mapping(folio); @@ -802,7 +804,7 @@ static void nfs_inode_remove_request(struct nfs_page *req) } if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags)) { - atomic_long_dec(&NFS_I(nfs_page_to_inode(req))->nrequests); + atomic_long_dec(&nfsi->nrequests); nfs_release_request(req); } } diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 48260cf68fde..02f5fcaad03f 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1788,6 +1788,12 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen, if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen)) goto out; + err = (rqstp->rq_vers == 2) ? nfserr_acces : nfserr_xdev; + if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) + goto out; + if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) + goto out; + retry: host_err = fh_want_write(ffhp); if (host_err) { @@ -1823,12 +1829,6 @@ retry: if (ndentry == trap) goto out_dput_new; - host_err = -EXDEV; - if (ffhp->fh_export->ex_path.mnt != tfhp->fh_export->ex_path.mnt) - goto out_dput_new; - if (ffhp->fh_export->ex_path.dentry != tfhp->fh_export->ex_path.dentry) - goto out_dput_new; - if ((ndentry->d_sb->s_export_op->flags & EXPORT_OP_CLOSE_BEFORE_UNLINK) && nfsd_has_cached_files(ndentry)) { close_cached = true; diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index f69c451018e3..62fe0b679e58 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -1585,16 +1585,25 @@ static int fanotify_test_fsid(struct dentry *dentry, __kernel_fsid_t *fsid) } /* Check if filesystem can encode a unique fid */ -static int fanotify_test_fid(struct dentry *dentry) +static int fanotify_test_fid(struct dentry *dentry, unsigned int flags) { + unsigned int mark_type = flags & FANOTIFY_MARK_TYPE_BITS; + const struct export_operations *nop = dentry->d_sb->s_export_op; + + /* + * We need to make sure that the filesystem supports encoding of + * file handles so user can use name_to_handle_at() to compare fids + * reported with events to the file handle of watched objects. + */ + if (!nop) + return -EOPNOTSUPP; + /* - * We need to make sure that the file system supports at least - * encoding a file handle so user can use name_to_handle_at() to - * compare fid returned with event to the file handle of watched - * objects. However, even the relaxed AT_HANDLE_FID flag requires - * at least empty export_operations for ecoding unique file ids. + * For sb/mount mark, we also need to make sure that the filesystem + * supports decoding file handles, so user has a way to map back the + * reported fids to filesystem objects. */ - if (!dentry->d_sb->s_export_op) + if (mark_type != FAN_MARK_INODE && !nop->fh_to_dentry) return -EOPNOTSUPP; return 0; @@ -1812,7 +1821,7 @@ static int do_fanotify_mark(int fanotify_fd, unsigned int flags, __u64 mask, if (ret) goto path_put_and_out; - ret = fanotify_test_fid(path.dentry); + ret = fanotify_test_fid(path.dentry, flags); if (ret) goto path_put_and_out; diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c index a9d82bbb4729..63f70259edc0 100644 --- a/fs/ntfs3/attrib.c +++ b/fs/ntfs3/attrib.c @@ -1106,10 +1106,10 @@ repack: } } - /* + /* * The code below may require additional cluster (to extend attribute list) - * and / or one MFT record - * It is too complex to undo operations if -ENOSPC occurs deep inside + * and / or one MFT record + * It is too complex to undo operations if -ENOSPC occurs deep inside * in 'ni_insert_nonresident'. * Return in advance -ENOSPC here if there are no free cluster and no free MFT. */ @@ -1736,10 +1736,8 @@ repack: le_b = NULL; attr_b = ni_find_attr(ni, NULL, &le_b, ATTR_DATA, NULL, 0, NULL, &mi_b); - if (!attr_b) { - err = -ENOENT; - goto out; - } + if (!attr_b) + return -ENOENT; attr = attr_b; le = le_b; diff --git a/fs/ntfs3/attrlist.c b/fs/ntfs3/attrlist.c index 42631b31adf1..7c01735d1219 100644 --- a/fs/ntfs3/attrlist.c +++ b/fs/ntfs3/attrlist.c @@ -52,7 +52,8 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (!attr->non_res) { lsize = le32_to_cpu(attr->res.data_size); - le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); + /* attr is resident: lsize < record_size (1K or 4K) */ + le = kvmalloc(al_aligned(lsize), GFP_KERNEL); if (!le) { err = -ENOMEM; goto out; @@ -80,7 +81,17 @@ int ntfs_load_attr_list(struct ntfs_inode *ni, struct ATTRIB *attr) if (err < 0) goto out; - le = kmalloc(al_aligned(lsize), GFP_NOFS | __GFP_NOWARN); + /* attr is nonresident. + * The worst case: + * 1T (2^40) extremely fragmented file. + * cluster = 4K (2^12) => 2^28 fragments + * 2^9 fragments per one record => 2^19 records + * 2^5 bytes of ATTR_LIST_ENTRY per one record => 2^24 bytes. + * + * the result is 16M bytes per attribute list. + * Use kvmalloc to allocate in range [several Kbytes - dozen Mbytes] + */ + le = kvmalloc(al_aligned(lsize), GFP_KERNEL); if (!le) { err = -ENOMEM; goto out; diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c index 107e808e06ea..63f14a0232f6 100644 --- a/fs/ntfs3/bitmap.c +++ b/fs/ntfs3/bitmap.c @@ -125,6 +125,7 @@ void wnd_close(struct wnd_bitmap *wnd) struct rb_node *node, *next; kfree(wnd->free_bits); + wnd->free_bits = NULL; run_close(&wnd->run); node = rb_first(&wnd->start_tree); @@ -659,7 +660,8 @@ int wnd_init(struct wnd_bitmap *wnd, struct super_block *sb, size_t nbits) wnd->bits_last = wbits; wnd->free_bits = - kcalloc(wnd->nwnd, sizeof(u16), GFP_NOFS | __GFP_NOWARN); + kvmalloc_array(wnd->nwnd, sizeof(u16), GFP_KERNEL | __GFP_ZERO); + if (!wnd->free_bits) return -ENOMEM; diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c index 063a6654199b..ec0566b322d5 100644 --- a/fs/ntfs3/dir.c +++ b/fs/ntfs3/dir.c @@ -309,7 +309,11 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni, return 0; } - dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; + /* NTFS: symlinks are "dir + reparse" or "file + reparse" */ + if (fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) + dt_type = DT_LNK; + else + dt_type = (fname->dup.fa & FILE_ATTRIBUTE_DIRECTORY) ? DT_DIR : DT_REG; return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type); } diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c index 962f12ce6c0a..1f7a194983c5 100644 --- a/fs/ntfs3/file.c +++ b/fs/ntfs3/file.c @@ -745,8 +745,8 @@ static ssize_t ntfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) } static ssize_t ntfs_file_splice_read(struct file *in, loff_t *ppos, - struct pipe_inode_info *pipe, - size_t len, unsigned int flags) + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) { struct inode *inode = in->f_mapping->host; struct ntfs_inode *ni = ntfs_i(inode); diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c index 2b85cb10f0be..dad976a68985 100644 --- a/fs/ntfs3/frecord.c +++ b/fs/ntfs3/frecord.c @@ -2148,7 +2148,7 @@ out1: for (i = 0; i < pages_per_frame; i++) { pg = pages[i]; - if (i == idx) + if (i == idx || !pg) continue; unlock_page(pg); put_page(pg); @@ -3208,6 +3208,12 @@ static bool ni_update_parent(struct ntfs_inode *ni, struct NTFS_DUP_INFO *dup, if (!fname || !memcmp(&fname->dup, dup, sizeof(fname->dup))) continue; + /* Check simple case when parent inode equals current inode. */ + if (ino_get(&fname->home) == ni->vfs_inode.i_ino) { + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + continue; + } + /* ntfs_iget5 may sleep. */ dir = ntfs_iget5(sb, &fname->home, NULL); if (IS_ERR(dir)) { diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c index 12f28cdf5c83..98ccb6650858 100644 --- a/fs/ntfs3/fslog.c +++ b/fs/ntfs3/fslog.c @@ -2168,8 +2168,10 @@ file_is_valid: if (!page) { page = kmalloc(log->page_size, GFP_NOFS); - if (!page) - return -ENOMEM; + if (!page) { + err = -ENOMEM; + goto out; + } } /* diff --git a/fs/ntfs3/fsntfs.c b/fs/ntfs3/fsntfs.c index 33afee0f5559..fbfe21dbb425 100644 --- a/fs/ntfs3/fsntfs.c +++ b/fs/ntfs3/fsntfs.c @@ -983,18 +983,11 @@ out: if (err) return err; - mark_inode_dirty(&ni->vfs_inode); + mark_inode_dirty_sync(&ni->vfs_inode); /* verify(!ntfs_update_mftmirr()); */ - /* - * If we used wait=1, sync_inode_metadata waits for the io for the - * inode to finish. It hangs when media is removed. - * So wait=0 is sent down to sync_inode_metadata - * and filemap_fdatawrite is used for the data blocks. - */ - err = sync_inode_metadata(&ni->vfs_inode, 0); - if (!err) - err = filemap_fdatawrite(ni->vfs_inode.i_mapping); + /* write mft record on disk. */ + err = _ni_write_inode(&ni->vfs_inode, 1); return err; } @@ -2461,10 +2454,12 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) { CLST end, i, zone_len, zlen; struct wnd_bitmap *wnd = &sbi->used.bitmap; + bool dirty = false; down_write_nested(&wnd->rw_lock, BITMAP_MUTEX_CLUSTERS); if (!wnd_is_used(wnd, lcn, len)) { - ntfs_set_state(sbi, NTFS_DIRTY_ERROR); + /* mark volume as dirty out of wnd->rw_lock */ + dirty = true; end = lcn + len; len = 0; @@ -2518,6 +2513,8 @@ void mark_as_free_ex(struct ntfs_sb_info *sbi, CLST lcn, CLST len, bool trim) out: up_write(&wnd->rw_lock); + if (dirty) + ntfs_set_state(sbi, NTFS_DIRTY_ERROR); } /* diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c index 124c6e822623..cf92b2433f7a 100644 --- a/fs/ntfs3/index.c +++ b/fs/ntfs3/index.c @@ -729,6 +729,9 @@ static struct NTFS_DE *hdr_find_e(const struct ntfs_index *indx, u32 total = le32_to_cpu(hdr->total); u16 offs[128]; + if (unlikely(!cmp)) + return NULL; + fill_table: if (end > total) return NULL; diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c index eb2ed0701495..d6d021e19aaa 100644 --- a/fs/ntfs3/inode.c +++ b/fs/ntfs3/inode.c @@ -170,8 +170,8 @@ next_attr: nt2kernel(std5->cr_time, &ni->i_crtime); #endif nt2kernel(std5->a_time, &inode->i_atime); - ctime = inode_get_ctime(inode); nt2kernel(std5->c_time, &ctime); + inode_set_ctime_to_ts(inode, ctime); nt2kernel(std5->m_time, &inode->i_mtime); ni->std_fa = std5->fa; @@ -1660,7 +1660,8 @@ struct inode *ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir, d_instantiate(dentry, inode); /* Set original time. inode times (i_ctime) may be changed in ntfs_init_acl. */ - inode->i_atime = inode->i_mtime = inode_set_ctime_to_ts(inode, ni->i_crtime); + inode->i_atime = inode->i_mtime = + inode_set_ctime_to_ts(inode, ni->i_crtime); dir->i_mtime = inode_set_ctime_to_ts(dir, ni->i_crtime); mark_inode_dirty(dir); diff --git a/fs/ntfs3/namei.c b/fs/ntfs3/namei.c index ad430d50bd79..eedacf94edd8 100644 --- a/fs/ntfs3/namei.c +++ b/fs/ntfs3/namei.c @@ -156,8 +156,8 @@ static int ntfs_link(struct dentry *ode, struct inode *dir, struct dentry *de) err = ntfs_link_inode(inode, de); if (!err) { - dir->i_mtime = inode_set_ctime_to_ts(inode, - inode_set_ctime_current(dir)); + dir->i_mtime = inode_set_ctime_to_ts( + inode, inode_set_ctime_current(dir)); mark_inode_dirty(inode); mark_inode_dirty(dir); d_instantiate(de, inode); @@ -373,7 +373,7 @@ static int ntfs_atomic_open(struct inode *dir, struct dentry *dentry, #ifdef CONFIG_NTFS3_FS_POSIX_ACL if (IS_POSIXACL(dir)) { - /* + /* * Load in cache current acl to avoid ni_lock(dir): * ntfs_create_inode -> ntfs_init_acl -> posix_acl_create -> * ntfs_get_acl -> ntfs_get_acl_ex -> ni_lock diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h index 98b76d1b09e7..86aecbb01a92 100644 --- a/fs/ntfs3/ntfs.h +++ b/fs/ntfs3/ntfs.h @@ -847,7 +847,7 @@ struct OBJECT_ID { // Birth Volume Id is the Object Id of the Volume on. // which the Object Id was allocated. It never changes. struct GUID BirthVolumeId; //0x10: - + // Birth Object Id is the first Object Id that was // ever assigned to this MFT Record. I.e. If the Object Id // is changed for some reason, this field will reflect the diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h index 629403ede6e5..0e6a2777870c 100644 --- a/fs/ntfs3/ntfs_fs.h +++ b/fs/ntfs3/ntfs_fs.h @@ -42,9 +42,11 @@ enum utf16_endian; #define MINUS_ONE_T ((size_t)(-1)) /* Biggest MFT / smallest cluster */ #define MAXIMUM_BYTES_PER_MFT 4096 +#define MAXIMUM_SHIFT_BYTES_PER_MFT 12 #define NTFS_BLOCKS_PER_MFT_RECORD (MAXIMUM_BYTES_PER_MFT / 512) #define MAXIMUM_BYTES_PER_INDEX 4096 +#define MAXIMUM_SHIFT_BYTES_PER_INDEX 12 #define NTFS_BLOCKS_PER_INODE (MAXIMUM_BYTES_PER_INDEX / 512) /* NTFS specific error code when fixup failed. */ @@ -495,8 +497,6 @@ int ntfs_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, u32 flags); int ntfs3_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); -void ntfs_sparse_cluster(struct inode *inode, struct page *page0, CLST vcn, - CLST len); int ntfs_file_open(struct inode *inode, struct file *file); int ntfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len); diff --git a/fs/ntfs3/record.c b/fs/ntfs3/record.c index c12ebffc94da..53629b1f65e9 100644 --- a/fs/ntfs3/record.c +++ b/fs/ntfs3/record.c @@ -189,12 +189,19 @@ out: return err; } +/* + * mi_enum_attr - start/continue attributes enumeration in record. + * + * NOTE: mi->mrec - memory of size sbi->record_size + * here we sure that mi->mrec->total == sbi->record_size (see mi_read) + */ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) { const struct MFT_REC *rec = mi->mrec; u32 used = le32_to_cpu(rec->used); - u32 t32, off, asize; + u32 t32, off, asize, prev_type; u16 t16; + u64 data_size, alloc_size, tot_size; if (!attr) { u32 total = le32_to_cpu(rec->total); @@ -213,6 +220,7 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) if (!is_rec_inuse(rec)) return NULL; + prev_type = 0; attr = Add2Ptr(rec, off); } else { /* Check if input attr inside record. */ @@ -226,11 +234,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return NULL; } - if (off + asize < off) { - /* Overflow check. */ + /* Overflow check. */ + if (off + asize < off) return NULL; - } + prev_type = le32_to_cpu(attr->type); attr = Add2Ptr(attr, asize); off += asize; } @@ -250,7 +258,11 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* 0x100 is last known attribute for now. */ t32 = le32_to_cpu(attr->type); - if ((t32 & 0xf) || (t32 > 0x100)) + if (!t32 || (t32 & 0xf) || (t32 > 0x100)) + return NULL; + + /* attributes in record must be ordered by type */ + if (t32 < prev_type) return NULL; /* Check overflow and boundary. */ @@ -259,16 +271,15 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) /* Check size of attribute. */ if (!attr->non_res) { + /* Check resident fields. */ if (asize < SIZEOF_RESIDENT) return NULL; t16 = le16_to_cpu(attr->res.data_off); - if (t16 > asize) return NULL; - t32 = le32_to_cpu(attr->res.data_size); - if (t16 + t32 > asize) + if (t16 + le32_to_cpu(attr->res.data_size) > asize) return NULL; t32 = sizeof(short) * attr->name_len; @@ -278,21 +289,52 @@ struct ATTRIB *mi_enum_attr(struct mft_inode *mi, struct ATTRIB *attr) return attr; } - /* Check some nonresident fields. */ - if (attr->name_len && - le16_to_cpu(attr->name_off) + sizeof(short) * attr->name_len > - le16_to_cpu(attr->nres.run_off)) { + /* Check nonresident fields. */ + if (attr->non_res != 1) + return NULL; + + t16 = le16_to_cpu(attr->nres.run_off); + if (t16 > asize) + return NULL; + + t32 = sizeof(short) * attr->name_len; + if (t32 && le16_to_cpu(attr->name_off) + t32 > t16) + return NULL; + + /* Check start/end vcn. */ + if (le64_to_cpu(attr->nres.svcn) > le64_to_cpu(attr->nres.evcn) + 1) return NULL; - } - if (attr->nres.svcn || !is_attr_ext(attr)) { + data_size = le64_to_cpu(attr->nres.data_size); + if (le64_to_cpu(attr->nres.valid_size) > data_size) + return NULL; + + alloc_size = le64_to_cpu(attr->nres.alloc_size); + if (data_size > alloc_size) + return NULL; + + t32 = mi->sbi->cluster_mask; + if (alloc_size & t32) + return NULL; + + if (!attr->nres.svcn && is_attr_ext(attr)) { + /* First segment of sparse/compressed attribute */ + if (asize + 8 < SIZEOF_NONRESIDENT_EX) + return NULL; + + tot_size = le64_to_cpu(attr->nres.total_size); + if (tot_size & t32) + return NULL; + + if (tot_size > alloc_size) + return NULL; + } else { if (asize + 8 < SIZEOF_NONRESIDENT) return NULL; if (attr->nres.c_unit) return NULL; - } else if (asize + 8 < SIZEOF_NONRESIDENT_EX) - return NULL; + } return attr; } diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c index 5661a363005e..f763e3256ccc 100644 --- a/fs/ntfs3/super.c +++ b/fs/ntfs3/super.c @@ -453,15 +453,23 @@ static struct proc_dir_entry *proc_info_root; * ntfs3.1 * cluster size * number of clusters + * total number of mft records + * number of used mft records ~= number of files + folders + * real state of ntfs "dirty"/"clean" + * current state of ntfs "dirty"/"clean" */ static int ntfs3_volinfo(struct seq_file *m, void *o) { struct super_block *sb = m->private; struct ntfs_sb_info *sbi = sb->s_fs_info; - seq_printf(m, "ntfs%d.%d\n%u\n%zu\n", sbi->volume.major_ver, - sbi->volume.minor_ver, sbi->cluster_size, - sbi->used.bitmap.nbits); + seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n", + sbi->volume.major_ver, sbi->volume.minor_ver, + sbi->cluster_size, sbi->used.bitmap.nbits, + sbi->mft.bitmap.nbits, + sbi->mft.bitmap.nbits - wnd_zeroes(&sbi->mft.bitmap), + sbi->volume.real_dirty ? "dirty" : "clean", + (sbi->volume.flags & VOLUME_FLAG_DIRTY) ? "dirty" : "clean"); return 0; } @@ -488,9 +496,13 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, { int err; struct super_block *sb = pde_data(file_inode(file)); - struct ntfs_sb_info *sbi = sb->s_fs_info; ssize_t ret = count; - u8 *label = kmalloc(count, GFP_NOFS); + u8 *label; + + if (sb_rdonly(sb)) + return -EROFS; + + label = kmalloc(count, GFP_NOFS); if (!label) return -ENOMEM; @@ -502,7 +514,7 @@ static ssize_t ntfs3_label_write(struct file *file, const char __user *buffer, while (ret > 0 && label[ret - 1] == '\n') ret -= 1; - err = ntfs_set_label(sbi, label, ret); + err = ntfs_set_label(sb->s_fs_info, label, ret); if (err < 0) { ntfs_err(sb, "failed (%d) to write label", err); @@ -576,20 +588,30 @@ static noinline void ntfs3_put_sbi(struct ntfs_sb_info *sbi) wnd_close(&sbi->mft.bitmap); wnd_close(&sbi->used.bitmap); - if (sbi->mft.ni) + if (sbi->mft.ni) { iput(&sbi->mft.ni->vfs_inode); + sbi->mft.ni = NULL; + } - if (sbi->security.ni) + if (sbi->security.ni) { iput(&sbi->security.ni->vfs_inode); + sbi->security.ni = NULL; + } - if (sbi->reparse.ni) + if (sbi->reparse.ni) { iput(&sbi->reparse.ni->vfs_inode); + sbi->reparse.ni = NULL; + } - if (sbi->objid.ni) + if (sbi->objid.ni) { iput(&sbi->objid.ni->vfs_inode); + sbi->objid.ni = NULL; + } - if (sbi->volume.ni) + if (sbi->volume.ni) { iput(&sbi->volume.ni->vfs_inode); + sbi->volume.ni = NULL; + } ntfs_update_mftmirr(sbi, 0); @@ -836,7 +858,7 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, struct ntfs_sb_info *sbi = sb->s_fs_info; int err; u32 mb, gb, boot_sector_size, sct_per_clst, record_size; - u64 sectors, clusters, mlcn, mlcn2; + u64 sectors, clusters, mlcn, mlcn2, dev_size0; struct NTFS_BOOT *boot; struct buffer_head *bh; struct MFT_REC *rec; @@ -845,6 +867,9 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, u32 boot_off = 0; const char *hint = "Primary boot"; + /* Save original dev_size. Used with alternative boot. */ + dev_size0 = dev_size; + sbi->volume.blocks = dev_size >> PAGE_SHIFT; bh = ntfs_bread(sb, 0); @@ -853,6 +878,11 @@ static int ntfs_init_from_boot(struct super_block *sb, u32 sector_size, check_boot: err = -EINVAL; + + /* Corrupted image; do not read OOB */ + if (bh->b_size - sizeof(*boot) < boot_off) + goto out; + boot = (struct NTFS_BOOT *)Add2Ptr(bh->b_data, boot_off); if (memcmp(boot->system_id, "NTFS ", sizeof("NTFS ") - 1)) { @@ -899,9 +929,17 @@ check_boot: goto out; } - sbi->record_size = record_size = - boot->record_size < 0 ? 1 << (-boot->record_size) : - (u32)boot->record_size << cluster_bits; + if (boot->record_size >= 0) { + record_size = (u32)boot->record_size << cluster_bits; + } else if (-boot->record_size <= MAXIMUM_SHIFT_BYTES_PER_MFT) { + record_size = 1u << (-boot->record_size); + } else { + ntfs_err(sb, "%s: invalid record size %d.", hint, + boot->record_size); + goto out; + } + + sbi->record_size = record_size; sbi->record_bits = blksize_bits(record_size); sbi->attr_size_tr = (5 * record_size >> 4); // ~320 bytes @@ -918,9 +956,15 @@ check_boot: goto out; } - sbi->index_size = boot->index_size < 0 ? - 1u << (-boot->index_size) : - (u32)boot->index_size << cluster_bits; + if (boot->index_size >= 0) { + sbi->index_size = (u32)boot->index_size << cluster_bits; + } else if (-boot->index_size <= MAXIMUM_SHIFT_BYTES_PER_INDEX) { + sbi->index_size = 1u << (-boot->index_size); + } else { + ntfs_err(sb, "%s: invalid index size %d.", hint, + boot->index_size); + goto out; + } /* Check index record size. */ if (sbi->index_size < SECTOR_SIZE || !is_power_of_2(sbi->index_size)) { @@ -1055,17 +1099,17 @@ check_boot: if (bh->b_blocknr && !sb_rdonly(sb)) { /* - * Alternative boot is ok but primary is not ok. - * Do not update primary boot here 'cause it may be faked boot. - * Let ntfs to be mounted and update boot later. - */ + * Alternative boot is ok but primary is not ok. + * Do not update primary boot here 'cause it may be faked boot. + * Let ntfs to be mounted and update boot later. + */ *boot2 = kmemdup(boot, sizeof(*boot), GFP_NOFS | __GFP_NOWARN); } out: - if (err == -EINVAL && !bh->b_blocknr && dev_size > PAGE_SHIFT) { + if (err == -EINVAL && !bh->b_blocknr && dev_size0 > PAGE_SHIFT) { u32 block_size = min_t(u32, sector_size, PAGE_SIZE); - u64 lbo = dev_size - sizeof(*boot); + u64 lbo = dev_size0 - sizeof(*boot); /* * Try alternative boot (last sector) @@ -1079,6 +1123,7 @@ out: boot_off = lbo & (block_size - 1); hint = "Alternative boot"; + dev_size = dev_size0; /* restore original size. */ goto check_boot; } brelse(bh); @@ -1367,7 +1412,7 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc) } bytes = inode->i_size; - sbi->def_table = t = kmalloc(bytes, GFP_NOFS | __GFP_NOWARN); + sbi->def_table = t = kvmalloc(bytes, GFP_KERNEL); if (!t) { err = -ENOMEM; goto put_inode_out; @@ -1521,9 +1566,9 @@ load_root: if (boot2) { /* - * Alternative boot is ok but primary is not ok. - * Volume is recognized as NTFS. Update primary boot. - */ + * Alternative boot is ok but primary is not ok. + * Volume is recognized as NTFS. Update primary boot. + */ struct buffer_head *bh0 = sb_getblk(sb, 0); if (bh0) { if (buffer_locked(bh0)) @@ -1564,6 +1609,7 @@ put_inode_out: out: ntfs3_put_sbi(sbi); kfree(boot2); + ntfs3_put_sbi(sbi); return err; } @@ -1757,7 +1803,6 @@ static int __init init_ntfs_fs(void) if (IS_ENABLED(CONFIG_NTFS3_LZX_XPRESS)) pr_info("ntfs3: Read-only LZX/Xpress compression included\n"); - #ifdef CONFIG_PROC_FS /* Create "/proc/fs/ntfs3" */ proc_info_root = proc_mkdir("fs/ntfs3", NULL); @@ -1799,7 +1844,6 @@ static void __exit exit_ntfs_fs(void) if (proc_info_root) remove_proc_entry("fs/ntfs3", NULL); #endif - } MODULE_LICENSE("GPL"); diff --git a/fs/ntfs3/xattr.c b/fs/ntfs3/xattr.c index 29fd391899e5..4920548192a0 100644 --- a/fs/ntfs3/xattr.c +++ b/fs/ntfs3/xattr.c @@ -211,7 +211,8 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, size = le32_to_cpu(info->size); /* Enumerate all xattrs. */ - for (ret = 0, off = 0; off < size; off += ea_size) { + ret = 0; + for (off = 0; off + sizeof(struct EA_FULL) < size; off += ea_size) { ea = Add2Ptr(ea_all, off); ea_size = unpacked_ea_size(ea); @@ -219,6 +220,10 @@ static ssize_t ntfs_list_ea(struct ntfs_inode *ni, char *buffer, break; if (buffer) { + /* Check if we can use field ea->name */ + if (off + ea_size > size) + break; + if (ret + ea->name_len + 1 > bytes_per_buffer) { err = -ERANGE; goto out; diff --git a/fs/overlayfs/params.c b/fs/overlayfs/params.c index 95b751507ac8..f6ff23fd101c 100644 --- a/fs/overlayfs/params.c +++ b/fs/overlayfs/params.c @@ -157,6 +157,34 @@ const struct fs_parameter_spec ovl_parameter_spec[] = { {} }; +static char *ovl_next_opt(char **s) +{ + char *sbegin = *s; + char *p; + + if (sbegin == NULL) + return NULL; + + for (p = sbegin; *p; p++) { + if (*p == '\\') { + p++; + if (!*p) + break; + } else if (*p == ',') { + *p = '\0'; + *s = p + 1; + return sbegin; + } + } + *s = NULL; + return sbegin; +} + +static int ovl_parse_monolithic(struct fs_context *fc, void *data) +{ + return vfs_parse_monolithic_sep(fc, data, ovl_next_opt); +} + static ssize_t ovl_parse_param_split_lowerdirs(char *str) { ssize_t nr_layers = 1, nr_colons = 0; @@ -164,7 +192,8 @@ static ssize_t ovl_parse_param_split_lowerdirs(char *str) for (s = d = str;; s++, d++) { if (*s == '\\') { - s++; + /* keep esc chars in split lowerdir */ + *d++ = *s++; } else if (*s == ':') { bool next_colon = (*(s + 1) == ':'); @@ -239,7 +268,7 @@ static void ovl_unescape(char *s) } } -static int ovl_mount_dir(const char *name, struct path *path) +static int ovl_mount_dir(const char *name, struct path *path, bool upper) { int err = -ENOMEM; char *tmp = kstrdup(name, GFP_KERNEL); @@ -248,7 +277,7 @@ static int ovl_mount_dir(const char *name, struct path *path) ovl_unescape(tmp); err = ovl_mount_dir_noesc(tmp, path); - if (!err && path->dentry->d_flags & DCACHE_OP_REAL) { + if (!err && upper && path->dentry->d_flags & DCACHE_OP_REAL) { pr_err("filesystem on '%s' not supported as upperdir\n", tmp); path_put_init(path); @@ -269,7 +298,7 @@ static int ovl_parse_param_upperdir(const char *name, struct fs_context *fc, struct path path; char *dup; - err = ovl_mount_dir(name, &path); + err = ovl_mount_dir(name, &path, true); if (err) return err; @@ -321,12 +350,6 @@ static void ovl_parse_param_drop_lowerdir(struct ovl_fs_context *ctx) * Set "/lower1", "/lower2", and "/lower3" as lower layers and * "/data1" and "/data2" as data lower layers. Any existing lower * layers are replaced. - * (2) lowerdir=:/lower4 - * Append "/lower4" to current stack of lower layers. This requires - * that there already is at least one lower layer configured. - * (3) lowerdir=::/lower5 - * Append data "/lower5" as data lower layer. This requires that - * there's at least one regular lower layer present. */ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) { @@ -348,49 +371,9 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) return 0; } - if (strncmp(name, "::", 2) == 0) { - /* - * This is a data layer. - * There must be at least one regular lower layer - * specified. - */ - if (ctx->nr == 0) { - pr_err("data lower layers without regular lower layers not allowed"); - return -EINVAL; - } - - /* Skip the leading "::". */ - name += 2; - data_layer = true; - /* - * A data layer is automatically an append as there - * must've been at least one regular lower layer. - */ - append = true; - } else if (*name == ':') { - /* - * This is a regular lower layer. - * If users want to append a layer enforce that they - * have already specified a first layer before. It's - * better to be strict. - */ - if (ctx->nr == 0) { - pr_err("cannot append layer if no previous layer has been specified"); - return -EINVAL; - } - - /* - * Once a sequence of data layers has started regular - * lower layers are forbidden. - */ - if (ctx->nr_data > 0) { - pr_err("regular lower layers cannot follow data lower layers"); - return -EINVAL; - } - - /* Skip the leading ":". */ - name++; - append = true; + if (*name == ':') { + pr_err("cannot append lower layer"); + return -EINVAL; } dup = kstrdup(name, GFP_KERNEL); @@ -472,7 +455,7 @@ static int ovl_parse_param_lowerdir(const char *name, struct fs_context *fc) l = &ctx->lower[nr]; memset(l, 0, sizeof(*l)); - err = ovl_mount_dir_noesc(dup_iter, &l->path); + err = ovl_mount_dir(dup_iter, &l->path, false); if (err) goto out_put; @@ -682,6 +665,7 @@ static int ovl_reconfigure(struct fs_context *fc) } static const struct fs_context_operations ovl_context_ops = { + .parse_monolithic = ovl_parse_monolithic, .parse_param = ovl_parse_param, .get_tree = ovl_get_tree, .reconfigure = ovl_reconfigure, @@ -950,16 +934,23 @@ int ovl_show_options(struct seq_file *m, struct dentry *dentry) struct super_block *sb = dentry->d_sb; struct ovl_fs *ofs = OVL_FS(sb); size_t nr, nr_merged_lower = ofs->numlayer - ofs->numdatalayer; - char **lowerdatadirs = &ofs->config.lowerdirs[nr_merged_lower]; - - /* lowerdirs[] starts from offset 1 */ - seq_printf(m, ",lowerdir=%s", ofs->config.lowerdirs[1]); - /* dump regular lower layers */ - for (nr = 2; nr < nr_merged_lower; nr++) - seq_printf(m, ":%s", ofs->config.lowerdirs[nr]); - /* dump data lower layers */ - for (nr = 0; nr < ofs->numdatalayer; nr++) - seq_printf(m, "::%s", lowerdatadirs[nr]); + + /* + * lowerdirs[] starts from offset 1, then + * >= 0 regular lower layers prefixed with : and + * >= 0 data-only lower layers prefixed with :: + * + * we need to escase comma and space like seq_show_option() does and + * we also need to escape the colon separator from lowerdir paths. + */ + seq_puts(m, ",lowerdir="); + for (nr = 1; nr < ofs->numlayer; nr++) { + if (nr > 1) + seq_putc(m, ':'); + if (nr >= nr_merged_lower) + seq_putc(m, ':'); + seq_escape(m, ofs->config.lowerdirs[nr], ":, \t\n\\"); + } if (ofs->config.upperdir) { seq_show_option(m, "upperdir", ofs->config.upperdir); seq_show_option(m, "workdir", ofs->config.workdir); diff --git a/fs/smb/client/cached_dir.c b/fs/smb/client/cached_dir.c index e2be8aedb26e..fe1bf5b6e0cb 100644 --- a/fs/smb/client/cached_dir.c +++ b/fs/smb/client/cached_dir.c @@ -15,6 +15,7 @@ static struct cached_fid *init_cached_dir(const char *path); static void free_cached_dir(struct cached_fid *cfid); static void smb2_close_cached_fid(struct kref *ref); +static void cfids_laundromat_worker(struct work_struct *work); static struct cached_fid *find_or_create_cached_dir(struct cached_fids *cfids, const char *path, @@ -169,15 +170,18 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, return -ENOENT; } /* - * At this point we either have a lease already and we can just - * return it. If not we are guaranteed to be the only thread accessing - * this cfid. + * Return cached fid if it has a lease. Otherwise, it is either a new + * entry or laundromat worker removed it from @cfids->entries. Caller + * will put last reference if the latter. */ + spin_lock(&cfids->cfid_list_lock); if (cfid->has_lease) { + spin_unlock(&cfids->cfid_list_lock); *ret_cfid = cfid; kfree(utf16_path); return 0; } + spin_unlock(&cfids->cfid_list_lock); /* * Skip any prefix paths in @path as lookup_positive_unlocked() ends up @@ -294,9 +298,11 @@ int open_cached_dir(unsigned int xid, struct cifs_tcon *tcon, goto oshr_free; } } + spin_lock(&cfids->cfid_list_lock); cfid->dentry = dentry; cfid->time = jiffies; cfid->has_lease = true; + spin_unlock(&cfids->cfid_list_lock); oshr_free: kfree(utf16_path); @@ -305,24 +311,28 @@ oshr_free: free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base); free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base); spin_lock(&cfids->cfid_list_lock); - if (rc && !cfid->has_lease) { - if (cfid->on_list) { - list_del(&cfid->entry); - cfid->on_list = false; - cfids->num_entries--; + if (!cfid->has_lease) { + if (rc) { + if (cfid->on_list) { + list_del(&cfid->entry); + cfid->on_list = false; + cfids->num_entries--; + } + rc = -ENOENT; + } else { + /* + * We are guaranteed to have two references at this + * point. One for the caller and one for a potential + * lease. Release the Lease-ref so that the directory + * will be closed when the caller closes the cached + * handle. + */ + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); + goto out; } - rc = -ENOENT; } spin_unlock(&cfids->cfid_list_lock); - if (!rc && !cfid->has_lease) { - /* - * We are guaranteed to have two references at this point. - * One for the caller and one for a potential lease. - * Release the Lease-ref so that the directory will be closed - * when the caller closes the cached handle. - */ - kref_put(&cfid->refcount, smb2_close_cached_fid); - } if (rc) { if (cfid->is_open) SMB2_close(0, cfid->tcon, cfid->fid.persistent_fid, @@ -330,7 +340,7 @@ oshr_free: free_cached_dir(cfid); cfid = NULL; } - +out: if (rc == 0) { *ret_cfid = cfid; atomic_inc(&tcon->num_remote_opens); @@ -572,53 +582,51 @@ static void free_cached_dir(struct cached_fid *cfid) kfree(cfid); } -static int -cifs_cfids_laundromat_thread(void *p) +static void cfids_laundromat_worker(struct work_struct *work) { - struct cached_fids *cfids = p; + struct cached_fids *cfids; struct cached_fid *cfid, *q; - struct list_head entry; + LIST_HEAD(entry); - while (!kthread_should_stop()) { - ssleep(1); - INIT_LIST_HEAD(&entry); - if (kthread_should_stop()) - return 0; - spin_lock(&cfids->cfid_list_lock); - list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { - if (time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) { - list_del(&cfid->entry); - list_add(&cfid->entry, &entry); - cfids->num_entries--; - } - } - spin_unlock(&cfids->cfid_list_lock); + cfids = container_of(work, struct cached_fids, laundromat_work.work); - list_for_each_entry_safe(cfid, q, &entry, entry) { + spin_lock(&cfids->cfid_list_lock); + list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { + if (cfid->time && + time_after(jiffies, cfid->time + HZ * dir_cache_timeout)) { cfid->on_list = false; - list_del(&cfid->entry); + list_move(&cfid->entry, &entry); + cfids->num_entries--; + /* To prevent race with smb2_cached_lease_break() */ + kref_get(&cfid->refcount); + } + } + spin_unlock(&cfids->cfid_list_lock); + + list_for_each_entry_safe(cfid, q, &entry, entry) { + list_del(&cfid->entry); + /* + * Cancel and wait for the work to finish in case we are racing + * with it. + */ + cancel_work_sync(&cfid->lease_break); + if (cfid->has_lease) { /* - * Cancel, and wait for the work to finish in - * case we are racing with it. + * Our lease has not yet been cancelled from the server + * so we need to drop the reference. */ - cancel_work_sync(&cfid->lease_break); - if (cfid->has_lease) { - /* - * We lease has not yet been cancelled from - * the server so we need to drop the reference. - */ - spin_lock(&cfids->cfid_list_lock); - cfid->has_lease = false; - spin_unlock(&cfids->cfid_list_lock); - kref_put(&cfid->refcount, smb2_close_cached_fid); - } + spin_lock(&cfids->cfid_list_lock); + cfid->has_lease = false; + spin_unlock(&cfids->cfid_list_lock); + kref_put(&cfid->refcount, smb2_close_cached_fid); } + /* Drop the extra reference opened above */ + kref_put(&cfid->refcount, smb2_close_cached_fid); } - - return 0; + queue_delayed_work(cifsiod_wq, &cfids->laundromat_work, + dir_cache_timeout * HZ); } - struct cached_fids *init_cached_dirs(void) { struct cached_fids *cfids; @@ -629,19 +637,10 @@ struct cached_fids *init_cached_dirs(void) spin_lock_init(&cfids->cfid_list_lock); INIT_LIST_HEAD(&cfids->entries); - /* - * since we're in a cifs function already, we know that - * this will succeed. No need for try_module_get(). - */ - __module_get(THIS_MODULE); - cfids->laundromat = kthread_run(cifs_cfids_laundromat_thread, - cfids, "cifsd-cfid-laundromat"); - if (IS_ERR(cfids->laundromat)) { - cifs_dbg(VFS, "Failed to start cfids laundromat thread.\n"); - kfree(cfids); - module_put(THIS_MODULE); - return NULL; - } + INIT_DELAYED_WORK(&cfids->laundromat_work, cfids_laundromat_worker); + queue_delayed_work(cifsiod_wq, &cfids->laundromat_work, + dir_cache_timeout * HZ); + return cfids; } @@ -657,11 +656,7 @@ void free_cached_dirs(struct cached_fids *cfids) if (cfids == NULL) return; - if (cfids->laundromat) { - kthread_stop(cfids->laundromat); - cfids->laundromat = NULL; - module_put(THIS_MODULE); - } + cancel_delayed_work_sync(&cfids->laundromat_work); spin_lock(&cfids->cfid_list_lock); list_for_each_entry_safe(cfid, q, &cfids->entries, entry) { diff --git a/fs/smb/client/cached_dir.h b/fs/smb/client/cached_dir.h index a82ff2cea789..81ba0fd5cc16 100644 --- a/fs/smb/client/cached_dir.h +++ b/fs/smb/client/cached_dir.h @@ -57,7 +57,7 @@ struct cached_fids { spinlock_t cfid_list_lock; int num_entries; struct list_head entries; - struct task_struct *laundromat; + struct delayed_work laundromat_work; }; extern struct cached_fids *init_cached_dirs(void); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 898860adf929..93262ca3f58a 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -231,11 +231,12 @@ void set_smb2_rsp_status(struct ksmbd_work *work, __le32 err) { struct smb2_hdr *rsp_hdr; - if (work->next_smb2_rcv_hdr_off) - rsp_hdr = ksmbd_resp_buf_next(work); - else - rsp_hdr = smb2_get_msg(work->response_buf); + rsp_hdr = smb2_get_msg(work->response_buf); rsp_hdr->Status = err; + + work->iov_idx = 0; + work->iov_cnt = 0; + work->next_smb2_rcv_hdr_off = 0; smb2_set_err_rsp(work); } @@ -6151,12 +6152,12 @@ static noinline int smb2_read_pipe(struct ksmbd_work *work) memcpy(aux_payload_buf, rpc_resp->payload, rpc_resp->payload_sz); nbytes = rpc_resp->payload_sz; - kvfree(rpc_resp); err = ksmbd_iov_pin_rsp_read(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer), aux_payload_buf, nbytes); if (err) goto out; + kvfree(rpc_resp); } else { err = ksmbd_iov_pin_rsp(work, (void *)rsp, offsetof(struct smb2_read_rsp, Buffer)); diff --git a/fs/smb/server/vfs_cache.c b/fs/smb/server/vfs_cache.c index c4b80ab7df74..c91eac6514dd 100644 --- a/fs/smb/server/vfs_cache.c +++ b/fs/smb/server/vfs_cache.c @@ -106,7 +106,7 @@ int ksmbd_query_inode_status(struct inode *inode) ci = __ksmbd_inode_lookup(inode); if (ci) { ret = KSMBD_INODE_STATUS_OK; - if (ci->m_flags & S_DEL_PENDING) + if (ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)) ret = KSMBD_INODE_STATUS_PENDING_DELETE; atomic_dec(&ci->m_count); } @@ -116,7 +116,7 @@ int ksmbd_query_inode_status(struct inode *inode) bool ksmbd_inode_pending_delete(struct ksmbd_file *fp) { - return (fp->f_ci->m_flags & S_DEL_PENDING); + return (fp->f_ci->m_flags & (S_DEL_PENDING | S_DEL_ON_CLS)); } void ksmbd_set_inode_pending_delete(struct ksmbd_file *fp) @@ -603,6 +603,9 @@ err_out: void ksmbd_update_fstate(struct ksmbd_file_table *ft, struct ksmbd_file *fp, unsigned int state) { + if (!fp) + return; + write_lock(&ft->lock); fp->f_state = state; write_unlock(&ft->lock); diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index e9cc481b4ddf..f9f4d694640d 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -1001,6 +1001,12 @@ xfs_ag_shrink_space( error = -ENOSPC; goto resv_init_out; } + + /* Update perag geometry */ + pag->block_count -= delta; + __xfs_agino_range(pag->pag_mount, pag->block_count, &pag->agino_min, + &pag->agino_max); + xfs_ialloc_log_agi(*tpp, agibp, XFS_AGI_LENGTH); xfs_alloc_log_agf(*tpp, agfbp, XFS_AGF_LENGTH); return 0; diff --git a/fs/xfs/scrub/xfile.c b/fs/xfs/scrub/xfile.c index d98e8e77c684..090c3ead43fd 100644 --- a/fs/xfs/scrub/xfile.c +++ b/fs/xfs/scrub/xfile.c @@ -10,7 +10,6 @@ #include "xfs_log_format.h" #include "xfs_trans_resv.h" #include "xfs_mount.h" -#include "xfs_format.h" #include "scrub/xfile.h" #include "scrub/xfarray.h" #include "scrub/scrub.h" diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c index 746814815b1d..9ecfdcdc752f 100644 --- a/fs/xfs/xfs_extent_busy.c +++ b/fs/xfs/xfs_extent_busy.c @@ -62,7 +62,8 @@ xfs_extent_busy_insert_list( rb_link_node(&new->rb_node, parent, rbp); rb_insert_color(&new->rb_node, &pag->pagb_tree); - list_add(&new->list, busy_list); + /* always process discard lists in fifo order */ + list_add_tail(&new->list, busy_list); spin_unlock(&pag->pagb_lock); } diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c index 1c1e6171209d..2b3b05c28e9e 100644 --- a/fs/xfs/xfs_iops.c +++ b/fs/xfs/xfs_iops.c @@ -584,6 +584,11 @@ xfs_vn_getattr( } } + if ((request_mask & STATX_CHANGE_COOKIE) && IS_I_VERSION(inode)) { + stat->change_cookie = inode_query_iversion(inode); + stat->result_mask |= STATX_CHANGE_COOKIE; + } + /* * Note: If you add another clause to set an attribute flag, please * update attributes_mask below. diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c index 4a9bbd3fe120..a7daa522e00f 100644 --- a/fs/xfs/xfs_notify_failure.c +++ b/fs/xfs/xfs_notify_failure.c @@ -126,8 +126,8 @@ xfs_dax_notify_ddev_failure( struct xfs_rmap_irec ri_low = { }; struct xfs_rmap_irec ri_high; struct xfs_agf *agf; - xfs_agblock_t agend; struct xfs_perag *pag; + xfs_agblock_t range_agend; pag = xfs_perag_get(mp, agno); error = xfs_alloc_read_agf(pag, tp, 0, &agf_bp); @@ -148,10 +148,10 @@ xfs_dax_notify_ddev_failure( ri_high.rm_startblock = XFS_FSB_TO_AGBNO(mp, end_fsbno); agf = agf_bp->b_addr; - agend = min(be32_to_cpu(agf->agf_length), + range_agend = min(be32_to_cpu(agf->agf_length) - 1, ri_high.rm_startblock); notify.startblock = ri_low.rm_startblock; - notify.blockcount = agend - ri_low.rm_startblock; + notify.blockcount = range_agend + 1 - ri_low.rm_startblock; error = xfs_rmap_query_range(cur, &ri_low, &ri_high, xfs_dax_failure_fn, ¬ify); diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 94181fe9780a..3f34ebb27525 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -465,9 +465,4 @@ extern int acpi_processor_ffh_lpi_probe(unsigned int cpu); extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); #endif -#ifdef CONFIG_ACPI_HOTPLUG_CPU -extern int arch_register_cpu(int cpu); -extern void arch_unregister_cpu(int cpu); -#endif - #endif diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index f9544d9b670d..ac65f0626cfc 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -68,8 +68,7 @@ enum drm_sched_priority { DRM_SCHED_PRIORITY_HIGH, DRM_SCHED_PRIORITY_KERNEL, - DRM_SCHED_PRIORITY_COUNT, - DRM_SCHED_PRIORITY_UNSET = -2 + DRM_SCHED_PRIORITY_COUNT }; /* Used to chose between FIFO and RR jobs scheduling */ diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index bb3cb005873e..e748bc957d83 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -82,6 +82,8 @@ struct timer_map { struct arch_timer_context *emul_ptimer; }; +void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map); + struct arch_timer_cpu { struct arch_timer_context timers[NR_KVM_TIMERS]; @@ -145,4 +147,9 @@ u64 timer_get_cval(struct arch_timer_context *ctxt); void kvm_timer_cpu_up(void); void kvm_timer_cpu_down(void); +static inline bool has_cntpoff(void) +{ + return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); +} + #endif diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d3c51a507508..b4825d3cdb29 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2058,6 +2058,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); @@ -2478,6 +2479,9 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); + +bool dev_check_flush(void); +bool cpu_map_check_flush(void); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index d644bbb298af..bb1223b21308 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -11,6 +11,7 @@ struct bpf_mem_caches; struct bpf_mem_alloc { struct bpf_mem_caches __percpu *caches; struct bpf_mem_cache __percpu *cache; + bool percpu; struct work_struct work; }; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 94ec766432f5..24213a99cc79 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -373,10 +373,25 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + /* If this state was ever pointed-to by other state's loop_entry field + * this flag would be set to true. Used to avoid freeing such states + * while they are still in use. + */ + bool used_as_loop_entry; /* first and last insn idx of this verifier state */ u32 first_insn_idx; u32 last_insn_idx; + /* If this state is a part of states loop this field points to some + * parent of this state such that: + * - it is also a member of the same states loop; + * - DFS states traversal starting from initial state visits loop_entry + * state before this state. + * Used to compute topmost loop entry for state loops. + * State loops might appear because of open coded iterators logic. + * See get_loop_entry() for more information. + */ + struct bpf_verifier_state *loop_entry; /* jmp history recorded from first to last. * backtracking is using it to go from last to first. * For most states jmp_history_cnt is [0-3]. @@ -384,21 +399,21 @@ struct bpf_verifier_state { */ struct bpf_idx_pair *jmp_history; u32 jmp_history_cnt; + u32 dfs_depth; }; -#define bpf_get_spilled_reg(slot, frame) \ +#define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -#define bpf_for_each_spilled_reg(iter, frame, reg) \ - for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ +#define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ - iter++, reg = bpf_get_spilled_reg(iter, frame)) + iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) -/* Invoke __expr over regsiters in __vst, setting __state and __reg */ -#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ +#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ @@ -410,7 +425,7 @@ struct bpf_verifier_state { __reg = &___regs[___j]; \ (void)(__expr); \ } \ - bpf_for_each_spilled_reg(___j, __state, __reg) { \ + bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ @@ -418,6 +433,10 @@ struct bpf_verifier_state { } \ }) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; diff --git a/include/linux/btf.h b/include/linux/btf.h index 928113a80a95..c2231c64d60b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -74,6 +74,7 @@ #define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ +#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index f1b3151ac30b..265da00a1a8b 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -238,7 +238,7 @@ struct css_set { * Lists running through all tasks using this cgroup group. * mg_tasks lists tasks which belong to this cset but are in the * process of being migrated out or in. Protected by - * css_set_rwsem, but, during migration, once tasks are moved to + * css_set_lock, but, during migration, once tasks are moved to * mg_tasks, it can be read safely while holding cgroup_mutex. */ struct list_head tasks; diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b307013b9c6c..0ef0af66080e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -40,13 +40,11 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 -/* walk only threadgroup leaders */ -#define CSS_TASK_ITER_PROCS (1U << 0) -/* walk all threaded css_sets in the domain */ -#define CSS_TASK_ITER_THREADED (1U << 1) - -/* internal flags */ -#define CSS_TASK_ITER_SKIPPED (1U << 16) +enum { + CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ + CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ +}; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { diff --git a/include/linux/cpu.h b/include/linux/cpu.h index 0abd60a7987b..eb768a866fe3 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -80,6 +80,8 @@ extern __printf(4, 5) struct device *cpu_device_create(struct device *parent, void *drvdata, const struct attribute_group **groups, const char *fmt, ...); +extern int arch_register_cpu(int cpu); +extern void arch_unregister_cpu(int cpu); #ifdef CONFIG_HOTPLUG_CPU extern void unregister_cpu(struct cpu *cpu); extern ssize_t arch_cpu_probe(const char *, size_t); diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index 0d678e9a7b24..ebe78bd3d121 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -568,6 +568,25 @@ static inline void dma_fence_set_error(struct dma_fence *fence, fence->error = error; } +/** + * dma_fence_timestamp - helper to get the completion timestamp of a fence + * @fence: fence to get the timestamp from. + * + * After a fence is signaled the timestamp is updated with the signaling time, + * but setting the timestamp can race with tasks waiting for the signaling. This + * helper busy waits for the correct timestamp to appear. + */ +static inline ktime_t dma_fence_timestamp(struct dma_fence *fence) +{ + if (WARN_ON(!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))) + return ktime_get(); + + while (!test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags)) + cpu_relax(); + + return fence->timestamp; +} + signed long dma_fence_wait_timeout(struct dma_fence *, bool intr, signed long timeout); signed long dma_fence_wait_any_timeout(struct dma_fence **fences, diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index c177322f793d..b9dd35d4b8f5 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -28,7 +28,7 @@ /* Source and Destination MAC of follow-up meta frames. * Whereas the choice of SMAC only affects the unique identification of the * switch as sender of meta frames, the DMAC must be an address that is present - * in the DSA master port's multicast MAC filter. + * in the DSA conduit port's multicast MAC filter. * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588 * over L2 use this address for some purpose already. */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 62b61527bcc4..226a36ed5aa1 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -1052,4 +1052,23 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, * next string. */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); + +/* Link mode to forced speed capabilities maps */ +struct ethtool_forced_speed_map { + u32 speed; + __ETHTOOL_DECLARE_LINK_MODE_MASK(caps); + + const u32 *cap_arr; + u32 arr_size; +}; + +#define ETHTOOL_FORCED_SPEED_MAP(prefix, value) \ +{ \ + .speed = SPEED_##value, \ + .cap_arr = prefix##_##value, \ + .arr_size = ARRAY_SIZE(prefix##_##value), \ +} + +void +ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index b528f063e8ff..4a40823c3c67 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2403,7 +2403,7 @@ struct audit_names; struct filename { const char *name; /* pointer to actual string */ const __user char *uptr; /* original userland pointer */ - int refcnt; + atomic_t refcnt; struct audit_names *aname; const char iname[]; }; diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h index 96332db693d5..c13e99cbbf81 100644 --- a/include/linux/fs_context.h +++ b/include/linux/fs_context.h @@ -136,6 +136,8 @@ extern struct fs_context *vfs_dup_fs_context(struct fs_context *fc); extern int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param); extern int vfs_parse_fs_string(struct fs_context *fc, const char *key, const char *value, size_t v_size); +int vfs_parse_monolithic_sep(struct fs_context *fc, void *data, + char *(*sep)(char **)); extern int generic_parse_monolithic(struct fs_context *fc, void *data); extern int vfs_get_tree(struct fs_context *fc); extern void put_fs_context(struct fs_context *fc); diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index a30686e649f7..47d25a5e1933 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -60,6 +60,7 @@ struct resv_map { long adds_in_progress; struct list_head region_cache; long region_cache_count; + struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored @@ -138,7 +139,7 @@ struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma, void unmap_hugepage_range(struct vm_area_struct *, unsigned long, unsigned long, struct page *, zap_flags_t); -void __unmap_hugepage_range_final(struct mmu_gather *tlb, +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags); @@ -245,6 +246,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma, void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); +extern void __hugetlb_zap_begin(struct vm_area_struct *vma, + unsigned long *begin, unsigned long *end); +extern void __hugetlb_zap_end(struct vm_area_struct *vma, + struct zap_details *details); + +static inline void hugetlb_zap_begin(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + if (is_vm_hugetlb_page(vma)) + __hugetlb_zap_begin(vma, start, end); +} + +static inline void hugetlb_zap_end(struct vm_area_struct *vma, + struct zap_details *details) +{ + if (is_vm_hugetlb_page(vma)) + __hugetlb_zap_end(vma, details); +} + void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); @@ -296,6 +316,18 @@ static inline void adjust_range_if_pmd_sharing_possible( { } +static inline void hugetlb_zap_begin( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + +static inline void hugetlb_zap_end( + struct vm_area_struct *vma, + struct zap_details *details) +{ +} + static inline struct page *hugetlb_follow_page_mask( struct vm_area_struct *vma, unsigned long address, unsigned int flags, unsigned int *page_mask) @@ -441,7 +473,7 @@ static inline long hugetlb_change_protection( return 0; } -static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb, +static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct page *ref_page, zap_flags_t zap_flags) @@ -1233,6 +1265,11 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma) return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } +static inline bool __vma_private_lock(struct vm_area_struct *vma) +{ + return (!(vma->vm_flags & VM_MAYSHARE)) && vma->vm_private_data; +} + /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 045a776ee547..958771bac9c0 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4420,6 +4420,35 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr, } /** + * ieee80211_is_protected_dual_of_public_action - check if skb contains a + * protected dual of public action management frame + * @skb: the skb containing the frame, length will be checked + * + * Return: true if the skb contains a protected dual of public action + * management frame, false otherwise. + */ +static inline bool +ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb) +{ + u8 action; + + if (!ieee80211_is_public_action((void *)skb->data, skb->len) || + skb->len < IEEE80211_MIN_ACTION_SIZE + 1) + return false; + + action = *(u8 *)(skb->data + IEEE80211_MIN_ACTION_SIZE); + + return action != WLAN_PUB_ACTION_20_40_BSS_COEX && + action != WLAN_PUB_ACTION_DSE_REG_LOC_ANN && + action != WLAN_PUB_ACTION_MSMT_PILOT && + action != WLAN_PUB_ACTION_TDLS_DISCOVER_RES && + action != WLAN_PUB_ACTION_LOC_TRACK_NOTI && + action != WLAN_PUB_ACTION_FTM_REQUEST && + action != WLAN_PUB_ACTION_FTM_RESPONSE && + action != WLAN_PUB_ACTION_FILS_DISCOVERY; +} + +/** * _ieee80211_is_group_privacy_action - check if frame is a group addressed * privacy action frame * @hdr: the frame diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 9bc5b4d35494..72cb693b075b 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -468,10 +468,10 @@ static inline void kasan_free_module_shadow(const struct vm_struct *vm) {} #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */ -#ifdef CONFIG_KASAN_INLINE +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) void kasan_non_canonical_hook(unsigned long addr); -#else /* CONFIG_KASAN_INLINE */ +#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ static inline void kasan_non_canonical_hook(unsigned long addr) { } -#endif /* CONFIG_KASAN_INLINE */ +#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */ #endif /* LINUX_KASAN_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 15e0e0209da4..7303b4bc2ce0 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -43,15 +43,6 @@ static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) __set_bit(nr, addr); } -static inline void linkmode_set_bit_array(const int *array, int array_size, - unsigned long *addr) -{ - int i; - - for (i = 0; i < array_size; i++) - linkmode_set_bit(array[i], addr); -} - static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); @@ -71,6 +62,15 @@ static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) return test_bit(nr, addr); } +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + static inline int linkmode_equal(const unsigned long *src1, const unsigned long *src2) { diff --git a/include/linux/mcb.h b/include/linux/mcb.h index 1e5893138afe..0b971b24a804 100644 --- a/include/linux/mcb.h +++ b/include/linux/mcb.h @@ -63,7 +63,6 @@ static inline struct mcb_bus *to_mcb_bus(struct device *dev) struct mcb_device { struct device dev; struct mcb_bus *bus; - bool is_added; struct mcb_driver *driver; u16 id; int inst; diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 4e27ca7c49de..591bf5b5e8dc 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -64,6 +64,10 @@ #define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) #define KSZ886X_BMCR_DISABLE_LED BIT(0) +/* PHY Special Control/Status Register (Reg 31) */ #define KSZ886X_CTRL_MDIX_STAT BIT(4) +#define KSZ886X_CTRL_FORCE_LINK BIT(3) +#define KSZ886X_CTRL_PWRSAVE BIT(2) +#define KSZ886X_CTRL_REMOTE_LOOPBACK BIT(1) #endif /* _MICREL_PHY_H */ diff --git a/include/linux/mtd/jedec.h b/include/linux/mtd/jedec.h index 0b6b59f7cfbd..56047a4e54c9 100644 --- a/include/linux/mtd/jedec.h +++ b/include/linux/mtd/jedec.h @@ -21,6 +21,9 @@ struct jedec_ecc_info { /* JEDEC features */ #define JEDEC_FEATURE_16_BIT_BUS (1 << 0) +/* JEDEC Optional Commands */ +#define JEDEC_OPT_CMD_READ_CACHE BIT(1) + struct nand_jedec_params { /* rev info and features block */ /* 'J' 'E' 'S' 'D' */ diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h index a7376f9beddf..55ab2e4d62f9 100644 --- a/include/linux/mtd/onfi.h +++ b/include/linux/mtd/onfi.h @@ -55,6 +55,7 @@ #define ONFI_SUBFEATURE_PARAM_LEN 4 /* ONFI optional commands SET/GET FEATURES supported? */ +#define ONFI_OPT_CMD_READ_CACHE BIT(1) #define ONFI_OPT_CMD_SET_GET_FEATURES BIT(2) struct nand_onfi_params { diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h index 90a141ba2a5a..c29ace15a053 100644 --- a/include/linux/mtd/rawnand.h +++ b/include/linux/mtd/rawnand.h @@ -225,6 +225,7 @@ struct gpio_desc; * struct nand_parameters - NAND generic parameters from the parameter page * @model: Model name * @supports_set_get_features: The NAND chip supports setting/getting features + * @supports_read_cache: The NAND chip supports read cache operations * @set_feature_list: Bitmap of features that can be set * @get_feature_list: Bitmap of features that can be get * @onfi: ONFI specific parameters @@ -233,6 +234,7 @@ struct nand_parameters { /* Generic parameters */ const char *model; bool supports_set_get_features; + bool supports_read_cache; DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER); DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1c7681263d30..b8bf669212cc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -482,6 +482,29 @@ static inline bool napi_prefer_busy_poll(struct napi_struct *n) return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); } +/** + * napi_is_scheduled - test if NAPI is scheduled + * @n: NAPI context + * + * This check is "best-effort". With no locking implemented, + * a NAPI can be scheduled or terminate right after this check + * and produce not precise results. + * + * NAPI_STATE_SCHED is an internal state, napi_is_scheduled + * should not be used normally and napi_schedule should be + * used instead. + * + * Use only if the driver really needs to check if a NAPI + * is scheduled for example in the context of delayed timer + * that can be skipped if a NAPI is already scheduled. + * + * Return True if NAPI is scheduled, False otherwise. + */ +static inline bool napi_is_scheduled(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_SCHED, &n->state); +} + bool napi_schedule_prep(struct napi_struct *n); /** diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d68644b7c299..80900d910992 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -22,6 +22,16 @@ static inline int NF_DROP_GETERR(int verdict) return -(verdict >> NF_VERDICT_QBITS); } +static __always_inline int +NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err) +{ + BUILD_BUG_ON(err > 0xffff); + + kfree_skb_reason(skb, reason); + + return ((err << 16) | NF_STOLEN); +} + static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 68fac2e7cbe6..8c677f185901 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -132,6 +132,7 @@ extern void __init setup_per_cpu_areas(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); +extern size_t pcpu_alloc_size(void __percpu *__pdata); DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e85cd1c0eaf3..7b5406e3288d 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -704,6 +704,7 @@ struct perf_event { /* The cumulative AND of all event_caps for events in this group. */ int group_caps; + unsigned int group_generation; struct perf_event *group_leader; /* * event->pmu will always point to pmu in which this event belongs. diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c0079a7574ae..0b4658a7eceb 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -303,7 +303,6 @@ struct plat_stmmacenet_data { unsigned int eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; - int ext_snapshot_num; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e15452df9804..6df715b6e51d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -152,6 +152,7 @@ struct tcp_request_sock { u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; + s8 req_usec_ts; #if IS_ENABLED(CONFIG_MPTCP) bool drop_req; #endif @@ -257,7 +258,8 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - unused:5; + tcp_usec_ts:1, /* TSval values in usec */ + unused:4; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ @@ -576,4 +578,9 @@ void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); int tcp_sock_set_user_timeout(struct sock *sk, int val); +static inline bool dst_tcp_usec_ts(const struct dst_entry *dst) +{ + return dst_feature(dst, RTAX_FEATURE_TCP_USEC_TS); +} + #endif /* _LINUX_TCP_H */ diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 7b4dd69555e4..27cc1d464321 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -3,8 +3,8 @@ #define _LINUX_VIRTIO_NET_H #include <linux/if_vlan.h> +#include <linux/udp.h> #include <uapi/linux/tcp.h> -#include <uapi/linux/udp.h> #include <uapi/linux/virtio_net.h> static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type) @@ -151,9 +151,22 @@ retry: unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); - /* UFO may not include transport header in gso_size. */ - if (gso_type & SKB_GSO_UDP) + switch (gso_type & ~SKB_GSO_TCP_ECN) { + case SKB_GSO_UDP: + /* UFO may not include transport header in gso_size. */ nh_off -= thlen; + break; + case SKB_GSO_UDP_L4: + if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM)) + return -EINVAL; + if (skb->csum_offset != offsetof(struct udphdr, check)) + return -EINVAL; + if (skb->len - p_off > gso_size * UDP_MAX_SEGMENTS) + return -EINVAL; + if (gso_type != SKB_GSO_UDP_L4) + return -EINVAL; + break; + } /* Kernel has a special handling for GSO_BY_FRAGS. */ if (gso_size == GSO_BY_FRAGS) diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 87d92accc26e..bdee5d649cc6 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -1,6 +1,7 @@ /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated + Copyright 2023 NXP Written 2000,2001 by Maxim Krasnyansky <[email protected]> @@ -673,6 +674,8 @@ enum { #define HCI_TX_POWER_INVALID 127 #define HCI_RSSI_INVALID 127 +#define HCI_SYNC_HANDLE_INVALID 0xffff + #define HCI_ROLE_MASTER 0x00 #define HCI_ROLE_SLAVE 0x01 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index c33348ba1657..20988623c5cc 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -350,6 +350,8 @@ struct hci_dev { struct list_head list; struct mutex lock; + struct ida unset_handle_ida; + const char *name; unsigned long flags; __u16 id; @@ -1290,8 +1292,8 @@ static inline struct hci_conn *hci_conn_hash_lookup_big(struct hci_dev *hdev, return NULL; } -static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev *hdev, - __u8 handle) +static inline struct hci_conn * +hci_conn_hash_lookup_pa_sync_big_handle(struct hci_dev *hdev, __u8 big) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; @@ -1299,22 +1301,22 @@ static inline struct hci_conn *hci_conn_hash_lookup_big_any_dst(struct hci_dev * rcu_read_lock(); list_for_each_entry_rcu(c, &h->list, list) { - if (c->type != ISO_LINK) + if (c->type != ISO_LINK || + !test_bit(HCI_CONN_PA_SYNC, &c->flags)) continue; - if (handle != BT_ISO_QOS_BIG_UNSET && handle == c->iso_qos.bcast.big) { + if (c->iso_qos.bcast.big == big) { rcu_read_unlock(); return c; } } - rcu_read_unlock(); return NULL; } static inline struct hci_conn * -hci_conn_hash_lookup_pa_sync(struct hci_dev *hdev, __u8 big) +hci_conn_hash_lookup_pa_sync_handle(struct hci_dev *hdev, __u16 sync_handle) { struct hci_conn_hash *h = &hdev->conn_hash; struct hci_conn *c; @@ -1326,7 +1328,7 @@ hci_conn_hash_lookup_pa_sync(struct hci_dev *hdev, __u8 big) !test_bit(HCI_CONN_PA_SYNC, &c->flags)) continue; - if (c->iso_qos.bcast.big == big) { + if (c->sync_handle == sync_handle) { rcu_read_unlock(); return c; } @@ -1377,6 +1379,26 @@ static inline void hci_conn_hash_list_state(struct hci_dev *hdev, rcu_read_unlock(); } +static inline void hci_conn_hash_list_flag(struct hci_dev *hdev, + hci_conn_func_t func, __u8 type, + __u8 flag, void *data) +{ + struct hci_conn_hash *h = &hdev->conn_hash; + struct hci_conn *c; + + if (!func) + return; + + rcu_read_lock(); + + list_for_each_entry_rcu(c, &h->list, list) { + if (c->type == type && test_bit(flag, &c->flags)) + func(c, data); + } + + rcu_read_unlock(); +} + static inline struct hci_conn *hci_lookup_le_connect(struct hci_dev *hdev) { struct hci_conn_hash *h = &hdev->conn_hash; @@ -1426,7 +1448,9 @@ int hci_le_create_cis_pending(struct hci_dev *hdev); int hci_conn_check_create_cis(struct hci_conn *conn); struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, - u8 role); + u8 role, u16 handle); +struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, + bdaddr_t *dst, u8 role); void hci_conn_del(struct hci_conn *conn); void hci_conn_hash_flush(struct hci_dev *hdev); void hci_conn_check_pending(struct hci_dev *hdev); diff --git a/include/net/bluetooth/hci_mon.h b/include/net/bluetooth/hci_mon.h index 2d5fcda1bcd0..082f89531b88 100644 --- a/include/net/bluetooth/hci_mon.h +++ b/include/net/bluetooth/hci_mon.h @@ -56,7 +56,7 @@ struct hci_mon_new_index { __u8 type; __u8 bus; bdaddr_t bdaddr; - char name[8]; + char name[8] __nonstring; } __packed; #define HCI_MON_NEW_INDEX_SIZE 16 diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h index 57eeb07aeb25..6efbc2152146 100644 --- a/include/net/bluetooth/hci_sync.h +++ b/include/net/bluetooth/hci_sync.h @@ -80,6 +80,8 @@ int hci_start_per_adv_sync(struct hci_dev *hdev, u8 instance, u8 data_len, u8 *data, u32 flags, u16 min_interval, u16 max_interval, u16 sync_interval); +int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance); + int hci_remove_advertising_sync(struct hci_dev *hdev, struct sock *sk, u8 instance, bool force); int hci_disable_advertising_sync(struct hci_dev *hdev); diff --git a/include/net/devlink.h b/include/net/devlink.h index fad8e36e3d98..9ac394bdfbe4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1854,36 +1854,36 @@ int devlink_info_version_running_put_ext(struct devlink_info_req *req, const char *version_value, enum devlink_info_version_type version_type); -int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg); -int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg); - -int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name); -int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg); - -int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name); -int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg); -int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name); -int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg); - -int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); -int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len); - -int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, - bool value); -int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, - u8 value); -int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, - u32 value); -int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, - u64 value); -int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, - const char *value); -int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u32 value_len); +void devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg); +void devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg); + +void devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name); +void devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg); + +void devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name); +void devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg); +void devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name); +void devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg); + +void devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); +void devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); +void devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len); + +void devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value); +void devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value); +void devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value); +void devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value); +void devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value); +void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u32 value_len); struct devlink_health_reporter * devl_port_health_reporter_create(struct devlink_port *port, diff --git a/include/net/dsa.h b/include/net/dsa.h index d98439ea6146..82135fbdb1e6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -102,11 +102,11 @@ struct dsa_device_ops { const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC - * address, in which case the DSA master would drop packets on ingress + * address, in which case the DSA conduit would drop packets on ingress * if what it understands out of the destination MAC address is not in * its RX filter. */ - bool promisc_on_master; + bool promisc_on_conduit; }; struct dsa_lag { @@ -236,12 +236,12 @@ struct dsa_bridge { }; struct dsa_port { - /* A CPU port is physically connected to a master device. - * A user port exposed to userspace has a slave device. + /* A CPU port is physically connected to a conduit device. A user port + * exposes a network device to user-space, called 'user' here. */ union { - struct net_device *master; - struct net_device *slave; + struct net_device *conduit; + struct net_device *user; }; /* Copy of the tagging protocol operations, for quicker access @@ -249,7 +249,7 @@ struct dsa_port { */ const struct dsa_device_ops *tag_ops; - /* Copies for faster access in master receive hot path */ + /* Copies for faster access in conduit receive hot path */ struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); @@ -281,9 +281,9 @@ struct dsa_port { u8 lag_tx_enabled:1; - /* Master state bits, valid only on CPU ports */ - u8 master_admin_up:1; - u8 master_oper_up:1; + /* conduit state bits, valid only on CPU ports */ + u8 conduit_admin_up:1; + u8 conduit_oper_up:1; /* Valid only on user ports */ u8 cpu_port_in_lag:1; @@ -303,7 +303,7 @@ struct dsa_port { struct list_head list; /* - * Original copy of the master netdev ethtool_ops + * Original copy of the conduit netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; @@ -452,10 +452,10 @@ struct dsa_switch { const struct dsa_switch_ops *ops; /* - * Slave mii_bus and devices for the individual ports. + * User mii_bus and devices for the individual ports. */ u32 phys_mii_mask; - struct mii_bus *slave_mii_bus; + struct mii_bus *user_mii_bus; /* Ageing Time limits in msecs */ unsigned int ageing_time_min; @@ -520,10 +520,10 @@ static inline bool dsa_port_is_unused(struct dsa_port *dp) return dp->type == DSA_PORT_TYPE_UNUSED; } -static inline bool dsa_port_master_is_operational(struct dsa_port *dp) +static inline bool dsa_port_conduit_is_operational(struct dsa_port *dp) { - return dsa_port_is_cpu(dp) && dp->master_admin_up && - dp->master_oper_up; + return dsa_port_is_cpu(dp) && dp->conduit_admin_up && + dp->conduit_oper_up; } static inline bool dsa_is_unused_port(struct dsa_switch *ds, int p) @@ -713,12 +713,12 @@ static inline bool dsa_port_offloads_lag(struct dsa_port *dp, return dsa_port_lag_dev_get(dp) == lag->dev; } -static inline struct net_device *dsa_port_to_master(const struct dsa_port *dp) +static inline struct net_device *dsa_port_to_conduit(const struct dsa_port *dp) { if (dp->cpu_port_in_lag) return dsa_port_lag_dev_get(dp->cpu_dp); - return dp->cpu_dp->master; + return dp->cpu_dp->conduit; } static inline @@ -732,7 +732,7 @@ struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) else if (dp->hsr_dev) return dp->hsr_dev; - return dp->slave; + return dp->user; } static inline struct net_device * @@ -834,9 +834,9 @@ struct dsa_switch_ops { int (*connect_tag_protocol)(struct dsa_switch *ds, enum dsa_tag_protocol proto); - int (*port_change_master)(struct dsa_switch *ds, int port, - struct net_device *master, - struct netlink_ext_ack *extack); + int (*port_change_conduit)(struct dsa_switch *ds, int port, + struct net_device *conduit, + struct netlink_ext_ack *extack); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); @@ -1233,11 +1233,11 @@ struct dsa_switch_ops { int (*tag_8021q_vlan_del)(struct dsa_switch *ds, int port, u16 vid); /* - * DSA master tracking operations + * DSA conduit tracking operations */ - void (*master_state_change)(struct dsa_switch *ds, - const struct net_device *master, - bool operational); + void (*conduit_state_change)(struct dsa_switch *ds, + const struct net_device *conduit, + bool operational); }; #define DSA_DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes) \ @@ -1374,9 +1374,9 @@ static inline int dsa_switch_resume(struct dsa_switch *ds) #endif /* CONFIG_PM_SLEEP */ #if IS_ENABLED(CONFIG_NET_DSA) -bool dsa_slave_dev_check(const struct net_device *dev); +bool dsa_user_dev_check(const struct net_device *dev); #else -static inline bool dsa_slave_dev_check(const struct net_device *dev) +static inline bool dsa_user_dev_check(const struct net_device *dev) { return false; } diff --git a/include/net/dsa_stubs.h b/include/net/dsa_stubs.h index 361811750a54..6f384897f287 100644 --- a/include/net/dsa_stubs.h +++ b/include/net/dsa_stubs.h @@ -13,14 +13,14 @@ extern const struct dsa_stubs *dsa_stubs; struct dsa_stubs { - int (*master_hwtstamp_validate)(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack); + int (*conduit_hwtstamp_validate)(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); }; -static inline int dsa_master_hwtstamp_validate(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +static inline int dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { if (!netdev_uses_dsa(dev)) return 0; @@ -29,18 +29,18 @@ static inline int dsa_master_hwtstamp_validate(struct net_device *dev, * netdev_uses_dsa() returns true, the dsa_core module is still * registered, and so, dsa_unregister_stubs() couldn't have run. * For netdev_uses_dsa() to start returning false, it would imply that - * dsa_master_teardown() has executed, which requires rtnl_lock(). + * dsa_conduit_teardown() has executed, which requires rtnl_lock(). */ ASSERT_RTNL(); - return dsa_stubs->master_hwtstamp_validate(dev, config, extack); + return dsa_stubs->conduit_hwtstamp_validate(dev, config, extack); } #else -static inline int dsa_master_hwtstamp_validate(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +static inline int dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { return 0; } diff --git a/include/net/dst.h b/include/net/dst.h index f8b8599a0600..f5dfc8fb7b37 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -222,13 +222,6 @@ static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metr return msecs_to_jiffies(dst_metric(dst, metric)); } -static inline u32 -dst_allfrag(const struct dst_entry *dst) -{ - int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG); - return ret; -} - static inline int dst_metric_locked(const struct dst_entry *dst, int metric) { diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 086d1193c9ef..d0a2f827d5f2 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -44,7 +44,6 @@ struct inet_connection_sock_af_ops { struct request_sock *req_unhash, bool *own_req); u16 net_header_len; - u16 net_frag_header_len; u16 sockaddr_len; int (*setsockopt)(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 98e11958cdff..74db6d97cae1 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -244,7 +244,6 @@ struct inet_sock { }; #define IPCORK_OPT 1 /* ip-options has been held in ipcork.opt */ -#define IPCORK_ALLFRAG 2 /* always fragment (for ipv6 for now) */ enum { INET_FLAGS_PKTINFO = 0, diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index 4a8e578405cb..b14999ff55db 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -67,7 +67,8 @@ struct inet_timewait_sock { /* And these are ours. */ unsigned int tw_transparent : 1, tw_flowlabel : 20, - tw_pad : 3, /* 3 bits hole */ + tw_usec_ts : 1, + tw_pad : 2, /* 2 bits hole */ tw_tos : 8; u32 tw_txhash; u32 tw_priority; diff --git a/include/net/ip.h b/include/net/ip.h index 6fbc0dcf4b97..1fc4c8d69e33 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -810,5 +810,6 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val); void ip_sock_set_pktinfo(struct sock *sk); void ip_sock_set_recverr(struct sock *sk); void ip_sock_set_tos(struct sock *sk, int val); +void __ip_sock_set_tos(struct sock *sk, int val); #endif /* _IP_H */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index b3444c8a6f74..78d38dd88aba 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1133,12 +1133,6 @@ struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, st struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); -struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, - struct net_device *dev, - struct net *net, struct socket *sock, - struct in6_addr *saddr, - const struct ip_tunnel_info *info, - u8 protocol, bool use_cache); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index eb6cd43b1746..13b3a4e29fdb 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -368,21 +368,30 @@ static inline void put_net_track(struct net *net, netns_tracker *tracker) typedef struct { #ifdef CONFIG_NET_NS - struct net *net; + struct net __rcu *net; #endif } possible_net_t; static inline void write_pnet(possible_net_t *pnet, struct net *net) { #ifdef CONFIG_NET_NS - pnet->net = net; + rcu_assign_pointer(pnet->net, net); #endif } static inline struct net *read_pnet(const possible_net_t *pnet) { #ifdef CONFIG_NET_NS - return pnet->net; + return rcu_dereference_protected(pnet->net, true); +#else + return &init_net; +#endif +} + +static inline struct net *read_pnet_rcu(possible_net_t *pnet) +{ +#ifdef CONFIG_NET_NS + return rcu_dereference(pnet->net); #else return &init_net; #endif diff --git a/include/net/netfilter/nf_conntrack_labels.h b/include/net/netfilter/nf_conntrack_labels.h index fcb19a4e8f2b..6903f72bcc15 100644 --- a/include/net/netfilter/nf_conntrack_labels.h +++ b/include/net/netfilter/nf_conntrack_labels.h @@ -39,7 +39,7 @@ static inline struct nf_conn_labels *nf_ct_labels_ext_add(struct nf_conn *ct) #ifdef CONFIG_NF_CONNTRACK_LABELS struct net *net = nf_ct_net(ct); - if (net->ct.labels_used == 0) + if (atomic_read(&net->ct.labels_used) == 0) return NULL; return nf_ct_ext_add(ct, NF_CT_EXT_LABELS, GFP_ATOMIC); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index d466e1a3b0b1..fe1507c1db82 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -53,6 +53,7 @@ struct nf_flowtable_type { struct list_head list; int family; int (*init)(struct nf_flowtable *ft); + bool (*gc)(const struct flow_offload *flow); int (*setup)(struct nf_flowtable *ft, struct net_device *dev, enum flow_block_command cmd); diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 9fb16485d08f..3bbd13ab1ecf 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -274,6 +274,9 @@ struct nft_userdata { unsigned char data[]; }; +/* placeholder structure for opaque set element backend representation. */ +struct nft_elem_priv { }; + /** * struct nft_set_elem - generic representation of set elements * @@ -294,9 +297,14 @@ struct nft_set_elem { u32 buf[NFT_DATA_VALUE_MAXLEN / sizeof(u32)]; struct nft_data val; } data; - void *priv; + struct nft_elem_priv *priv; }; +static inline void *nft_elem_priv_cast(const struct nft_elem_priv *priv) +{ + return (void *)priv; +} + struct nft_set; struct nft_set_iter { u8 genmask; @@ -306,7 +314,7 @@ struct nft_set_iter { int (*fn)(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem); + struct nft_elem_priv *elem_priv); }; /** @@ -430,7 +438,8 @@ struct nft_set_ops { const struct nft_set_ext **ext); bool (*update)(struct nft_set *set, const u32 *key, - void *(*new)(struct nft_set *, + struct nft_elem_priv * + (*new)(struct nft_set *, const struct nft_expr *, struct nft_regs *), const struct nft_expr *expr, @@ -442,27 +451,27 @@ struct nft_set_ops { int (*insert)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext); + struct nft_elem_priv **priv); void (*activate)(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem); - void * (*deactivate)(const struct net *net, + struct nft_elem_priv *elem_priv); + struct nft_elem_priv * (*deactivate)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem); - bool (*flush)(const struct net *net, + void (*flush)(const struct net *net, const struct nft_set *set, - void *priv); + struct nft_elem_priv *priv); void (*remove)(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem); + struct nft_elem_priv *elem_priv); void (*walk)(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_iter *iter); - void * (*get)(const struct net *net, + struct nft_elem_priv * (*get)(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, unsigned int flags); - void (*commit)(const struct nft_set *set); + void (*commit)(struct nft_set *set); void (*abort)(const struct nft_set *set); u64 (*privsize)(const struct nlattr * const nla[], const struct nft_set_desc *desc); @@ -796,9 +805,9 @@ static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, - void *elem) + const struct nft_elem_priv *elem_priv) { - return elem + set->ops->elemsize; + return (void *)elem_priv + set->ops->elemsize; } static inline struct nft_object **nft_set_ext_obj(const struct nft_set_ext *ext) @@ -810,16 +819,19 @@ struct nft_expr *nft_set_elem_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set, const struct nlattr *attr); -void *nft_set_elem_init(const struct nft_set *set, - const struct nft_set_ext_tmpl *tmpl, - const u32 *key, const u32 *key_end, const u32 *data, - u64 timeout, u64 expiration, gfp_t gfp); +struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, + const struct nft_set_ext_tmpl *tmpl, + const u32 *key, const u32 *key_end, + const u32 *data, + u64 timeout, u64 expiration, gfp_t gfp); int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, struct nft_expr *expr_array[]); -void nft_set_elem_destroy(const struct nft_set *set, void *elem, +void nft_set_elem_destroy(const struct nft_set *set, + const struct nft_elem_priv *elem_priv, bool destroy_expr); void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem); + const struct nft_set *set, + const struct nft_elem_priv *elem_priv); struct nft_expr_ops; /** @@ -1061,7 +1073,7 @@ struct nft_chain { int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem); + struct nft_elem_priv *elem_priv); int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set); int nf_tables_bind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); void nf_tables_unbind_chain(const struct nft_ctx *ctx, struct nft_chain *chain); @@ -1638,14 +1650,14 @@ struct nft_trans_table { struct nft_trans_elem { struct nft_set *set; - struct nft_set_elem elem; + struct nft_elem_priv *elem_priv; bool bound; }; #define nft_trans_elem_set(trans) \ (((struct nft_trans_elem *)trans->data)->set) -#define nft_trans_elem(trans) \ - (((struct nft_trans_elem *)trans->data)->elem) +#define nft_trans_elem_priv(trans) \ + (((struct nft_trans_elem *)trans->data)->elem_priv) #define nft_trans_elem_set_bound(trans) \ (((struct nft_trans_elem *)trans->data)->bound) @@ -1686,7 +1698,7 @@ struct nft_trans_gc { struct nft_set *set; u32 seq; u16 count; - void *priv[NFT_TRANS_GC_BATCHCOUNT]; + struct nft_elem_priv *priv[NFT_TRANS_GC_BATCHCOUNT]; struct rcu_head rcu; }; @@ -1709,7 +1721,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc); void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem); + struct nft_elem_priv *elem_priv); int __init nft_chain_filter_init(void); void nft_chain_filter_fini(void); diff --git a/include/net/netkit.h b/include/net/netkit.h new file mode 100644 index 000000000000..0ba2e6b847ca --- /dev/null +++ b/include/net/netkit.h @@ -0,0 +1,38 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2023 Isovalent */ +#ifndef __NET_NETKIT_H +#define __NET_NETKIT_H + +#include <linux/bpf.h> + +#ifdef CONFIG_NETKIT +int netkit_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int netkit_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); +int netkit_prog_detach(const union bpf_attr *attr, struct bpf_prog *prog); +int netkit_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); +#else +static inline int netkit_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int netkit_link_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int netkit_prog_detach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + return -EINVAL; +} + +static inline int netkit_prog_query(const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + return -EINVAL; +} +#endif /* CONFIG_NETKIT */ +#endif /* __NET_NETKIT_H */ diff --git a/include/net/netlink.h b/include/net/netlink.h index 8a7cd1170e1f..83bdf787aeee 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -128,6 +128,8 @@ * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: + * nla_get_uint(nla) get payload for a uint attribute + * nla_get_sint(nla) get payload for a sint attribute * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute @@ -183,6 +185,8 @@ enum { NLA_REJECT, NLA_BE16, NLA_BE32, + NLA_SINT, + NLA_UINT, __NLA_TYPE_MAX, }; @@ -229,6 +233,7 @@ enum nla_policy_validation { * nested header (or empty); len field is used if * nested_policy is also used, for the max attr * number in the nested policy. + * NLA_SINT, NLA_UINT, * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, @@ -260,12 +265,14 @@ enum nla_policy_validation { * while an array has the nested attributes at another * level down and the attribute types directly in the * nesting don't matter. + * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64, * NLA_BE16, * NLA_BE32, + * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, @@ -280,6 +287,7 @@ enum nla_policy_validation { * or NLA_POLICY_FULL_RANGE_SIGNED() macros instead. * Use the NLA_POLICY_MIN(), NLA_POLICY_MAX() and * NLA_POLICY_RANGE() macros. + * NLA_UINT, * NLA_U8, * NLA_U16, * NLA_U32, @@ -288,6 +296,7 @@ enum nla_policy_validation { * to a struct netlink_range_validation that indicates * the min/max values. * Use NLA_POLICY_FULL_RANGE(). + * NLA_SINT, * NLA_S8, * NLA_S16, * NLA_S32, @@ -351,8 +360,8 @@ struct nla_policy { const u32 mask; const char *reject_message; const struct nla_policy *nested_policy; - struct netlink_range_validation *range; - struct netlink_range_validation_signed *range_signed; + const struct netlink_range_validation *range; + const struct netlink_range_validation_signed *range_signed; struct { s16 min, max; }; @@ -377,9 +386,11 @@ struct nla_policy { #define __NLA_IS_UINT_TYPE(tp) \ (tp == NLA_U8 || tp == NLA_U16 || tp == NLA_U32 || \ - tp == NLA_U64 || tp == NLA_BE16 || tp == NLA_BE32) + tp == NLA_U64 || tp == NLA_UINT || \ + tp == NLA_BE16 || tp == NLA_BE32) #define __NLA_IS_SINT_TYPE(tp) \ - (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64) + (tp == NLA_S8 || tp == NLA_S16 || tp == NLA_S32 || tp == NLA_S64 || \ + tp == NLA_SINT) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_UINT_TYPE(tp) \ @@ -1358,6 +1369,22 @@ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) } /** + * nla_put_uint - Add a variable-size unsigned int to a socket buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @value: numeric value + */ +static inline int nla_put_uint(struct sk_buff *skb, int attrtype, u64 value) +{ + u64 tmp64 = value; + u32 tmp32 = value; + + if (tmp64 == tmp32) + return nla_put_u32(skb, attrtype, tmp32); + return nla_put(skb, attrtype, sizeof(u64), &tmp64); +} + +/** * nla_put_be32 - Add a __be32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type @@ -1512,6 +1539,22 @@ static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, } /** + * nla_put_sint - Add a variable-size signed int to a socket buffer + * @skb: socket buffer to add attribute to + * @attrtype: attribute type + * @value: numeric value + */ +static inline int nla_put_sint(struct sk_buff *skb, int attrtype, s64 value) +{ + s64 tmp64 = value; + s32 tmp32 = value; + + if (tmp64 == tmp32) + return nla_put_s32(skb, attrtype, tmp32); + return nla_put(skb, attrtype, sizeof(s64), &tmp64); +} + +/** * nla_put_string - Add a string netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type @@ -1668,6 +1711,17 @@ static inline u64 nla_get_u64(const struct nlattr *nla) } /** + * nla_get_uint - return payload of uint attribute + * @nla: uint netlink attribute + */ +static inline u64 nla_get_uint(const struct nlattr *nla) +{ + if (nla_len(nla) == sizeof(u32)) + return nla_get_u32(nla); + return nla_get_u64(nla); +} + +/** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ @@ -1730,6 +1784,17 @@ static inline s64 nla_get_s64(const struct nlattr *nla) } /** + * nla_get_sint - return payload of uint attribute + * @nla: uint netlink attribute + */ +static inline s64 nla_get_sint(const struct nlattr *nla) +{ + if (nla_len(nla) == sizeof(s32)) + return nla_get_s32(nla); + return nla_get_s64(nla); +} + +/** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index 1f463b3957c7..bae914815aa3 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -107,7 +107,7 @@ struct netns_ct { struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; struct nf_ip_net nf_ct_proto; #if defined(CONFIG_NF_CONNTRACK_LABELS) - unsigned int labels_used; + atomic_t labels_used; #endif }; #endif diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index bd7c3be4af5d..423b52eca908 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -50,6 +50,7 @@ struct netns_xfrm { struct list_head policy_all; struct hlist_head *policy_byidx; unsigned int policy_idx_hmask; + unsigned int idx_generator; struct hlist_head policy_inexact[XFRM_POLICY_MAX]; struct xfrm_policy_hash policy_bydst[XFRM_POLICY_MAX]; unsigned int policy_count[XFRM_POLICY_MAX * 2]; diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h index 8f64adf86f5b..4ebd544ae977 100644 --- a/include/net/page_pool/helpers.h +++ b/include/net/page_pool/helpers.h @@ -8,23 +8,46 @@ /** * DOC: page_pool allocator * - * The page_pool allocator is optimized for the XDP mode that - * uses one frame per-page, but it can fallback on the - * regular page allocator APIs. - * - * Basic use involves replacing alloc_pages() calls with the - * page_pool_alloc_pages() call. Drivers should use - * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). - * - * The API keeps track of in-flight pages, in order to let API users know - * when it is safe to free a page_pool object. Thus, API users - * must call page_pool_put_page() to free the page, or attach - * the page to a page_pool-aware object like skbs marked with + * The page_pool allocator is optimized for recycling page or page fragment used + * by skb packet and xdp frame. + * + * Basic use involves replacing and alloc_pages() calls with page_pool_alloc(), + * which allocate memory with or without page splitting depending on the + * requested memory size. + * + * If the driver knows that it always requires full pages or its allocations are + * always smaller than half a page, it can use one of the more specific API + * calls: + * + * 1. page_pool_alloc_pages(): allocate memory without page splitting when + * driver knows that the memory it need is always bigger than half of the page + * allocated from page pool. There is no cache line dirtying for 'struct page' + * when a page is recycled back to the page pool. + * + * 2. page_pool_alloc_frag(): allocate memory with page splitting when driver + * knows that the memory it need is always smaller than or equal to half of the + * page allocated from page pool. Page splitting enables memory saving and thus + * avoids TLB/cache miss for data access, but there also is some cost to + * implement page splitting, mainly some cache line dirtying/bouncing for + * 'struct page' and atomic operation for page->pp_frag_count. + * + * The API keeps track of in-flight pages, in order to let API users know when + * it is safe to free a page_pool object, the API users must call + * page_pool_put_page() or page_pool_free_va() to free the page_pool object, or + * attach the page_pool object to a page_pool-aware object like skbs marked with * skb_mark_for_recycle(). * - * API users must call page_pool_put_page() once on a page, as it - * will either recycle the page, or in case of refcnt > 1, it will - * release the DMA mapping and in-flight state accounting. + * page_pool_put_page() may be called multi times on the same page if a page is + * split into multi fragments. For the last fragment, it will either recycle the + * page, or in case of page->_refcount > 1, it will release the DMA mapping and + * in-flight state accounting. + * + * dma_sync_single_range_for_device() is only called for the last fragment when + * page_pool is created with PP_FLAG_DMA_SYNC_DEV flag, so it depends on the + * last freed fragment to do the sync_for_device operation for all fragments in + * the same page when a page is split, the API user must setup pool->p.max_len + * and pool->p.offset correctly and ensure that page_pool_put_page() is called + * with dma_sync_size being -1 for fragment API. */ #ifndef _NET_PAGE_POOL_HELPERS_H #define _NET_PAGE_POOL_HELPERS_H @@ -73,6 +96,17 @@ static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) return page_pool_alloc_pages(pool, gfp); } +/** + * page_pool_dev_alloc_frag() - allocate a page fragment. + * @pool: pool from which to allocate + * @offset: offset to the allocated page + * @size: requested size + * + * Get a page fragment from the page allocator or page_pool caches. + * + * Return: + * Return allocated page fragment, otherwise return NULL. + */ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, unsigned int *offset, unsigned int size) @@ -82,6 +116,91 @@ static inline struct page *page_pool_dev_alloc_frag(struct page_pool *pool, return page_pool_alloc_frag(pool, offset, size, gfp); } +static inline struct page *page_pool_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size, gfp_t gfp) +{ + unsigned int max_size = PAGE_SIZE << pool->p.order; + struct page *page; + + if ((*size << 1) > max_size) { + *size = max_size; + *offset = 0; + return page_pool_alloc_pages(pool, gfp); + } + + page = page_pool_alloc_frag(pool, offset, *size, gfp); + if (unlikely(!page)) + return NULL; + + /* There is very likely not enough space for another fragment, so append + * the remaining size to the current fragment to avoid truesize + * underestimate problem. + */ + if (pool->frag_offset + *size > max_size) { + *size = max_size - *offset; + pool->frag_offset = max_size; + } + + return page; +} + +/** + * page_pool_dev_alloc() - allocate a page or a page fragment. + * @pool: pool from which to allocate + * @offset: offset to the allocated page + * @size: in as the requested size, out as the allocated size + * + * Get a page or a page fragment from the page allocator or page_pool caches + * depending on the requested size in order to allocate memory with least memory + * utilization and performance penalty. + * + * Return: + * Return allocated page or page fragment, otherwise return NULL. + */ +static inline struct page *page_pool_dev_alloc(struct page_pool *pool, + unsigned int *offset, + unsigned int *size) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc(pool, offset, size, gfp); +} + +static inline void *page_pool_alloc_va(struct page_pool *pool, + unsigned int *size, gfp_t gfp) +{ + unsigned int offset; + struct page *page; + + /* Mask off __GFP_HIGHMEM to ensure we can use page_address() */ + page = page_pool_alloc(pool, &offset, size, gfp & ~__GFP_HIGHMEM); + if (unlikely(!page)) + return NULL; + + return page_address(page) + offset; +} + +/** + * page_pool_dev_alloc_va() - allocate a page or a page fragment and return its + * va. + * @pool: pool from which to allocate + * @size: in as the requested size, out as the allocated size + * + * This is just a thin wrapper around the page_pool_alloc() API, and + * it returns va of the allocated page or page fragment. + * + * Return: + * Return the va for the allocated page or page fragment, otherwise return NULL. + */ +static inline void *page_pool_dev_alloc_va(struct page_pool *pool, + unsigned int *size) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_va(pool, size, gfp); +} + /** * page_pool_get_dma_dir() - Retrieve the stored DMA direction. * @pool: pool from which page was allocated @@ -115,28 +234,49 @@ static inline long page_pool_defrag_page(struct page *page, long nr) long ret; /* If nr == pp_frag_count then we have cleared all remaining - * references to the page. No need to actually overwrite it, instead - * we can leave this to be overwritten by the calling function. + * references to the page: + * 1. 'n == 1': no need to actually overwrite it. + * 2. 'n != 1': overwrite it with one, which is the rare case + * for pp_frag_count draining. * - * The main advantage to doing this is that an atomic_read is - * generally a much cheaper operation than an atomic update, - * especially when dealing with a page that may be partitioned - * into only 2 or 3 pieces. + * The main advantage to doing this is that not only we avoid a atomic + * update, as an atomic_read is generally a much cheaper operation than + * an atomic update, especially when dealing with a page that may be + * partitioned into only 2 or 3 pieces; but also unify the pp_frag_count + * handling by ensuring all pages have partitioned into only 1 piece + * initially, and only overwrite it when the page is partitioned into + * more than one piece. */ - if (atomic_long_read(&page->pp_frag_count) == nr) + if (atomic_long_read(&page->pp_frag_count) == nr) { + /* As we have ensured nr is always one for constant case using + * the BUILD_BUG_ON(), only need to handle the non-constant case + * here for pp_frag_count draining, which is a rare case. + */ + BUILD_BUG_ON(__builtin_constant_p(nr) && nr != 1); + if (!__builtin_constant_p(nr)) + atomic_long_set(&page->pp_frag_count, 1); + return 0; + } ret = atomic_long_sub_return(nr, &page->pp_frag_count); WARN_ON(ret < 0); + + /* We are the last user here too, reset pp_frag_count back to 1 to + * ensure all pages have been partitioned into 1 piece initially, + * this should be the rare case when the last two fragment users call + * page_pool_defrag_page() currently. + */ + if (unlikely(!ret)) + atomic_long_set(&page->pp_frag_count, 1); + return ret; } -static inline bool page_pool_is_last_frag(struct page_pool *pool, - struct page *page) +static inline bool page_pool_is_last_frag(struct page *page) { - /* If fragments aren't enabled or count is 0 we were the last user */ - return !(pool->p.flags & PP_FLAG_PAGE_FRAG) || - (page_pool_defrag_page(page, 1) == 0); + /* If page_pool_defrag_page() returns 0, we were the last user */ + return page_pool_defrag_page(page, 1) == 0; } /** @@ -161,7 +301,7 @@ static inline void page_pool_put_page(struct page_pool *pool, * allow registering MEM_TYPE_PAGE_POOL, but shield linker. */ #ifdef CONFIG_PAGE_POOL - if (!page_pool_is_last_frag(pool, page)) + if (!page_pool_is_last_frag(page)) return; page_pool_put_defragged_page(pool, page, dma_sync_size, allow_direct); @@ -201,6 +341,20 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, (sizeof(dma_addr_t) > sizeof(unsigned long)) /** + * page_pool_free_va() - free a va into the page_pool + * @pool: pool from which va was allocated + * @va: va to be freed + * @allow_direct: freed by the consumer, allow lockless caching + * + * Free a va allocated from page_pool_allo_va(). + */ +static inline void page_pool_free_va(struct page_pool *pool, void *va, + bool allow_direct) +{ + page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct); +} + +/** * page_pool_get_dma_addr() - Retrieve the stored DMA address. * @page: page allocated from a page pool * diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h index 887e7946a597..6fc5134095ed 100644 --- a/include/net/page_pool/types.h +++ b/include/net/page_pool/types.h @@ -17,10 +17,8 @@ * Please note DMA-sync-for-CPU is still * device driver responsibility */ -#define PP_FLAG_PAGE_FRAG BIT(2) /* for page frag feature */ #define PP_FLAG_ALL (PP_FLAG_DMA_MAP |\ - PP_FLAG_DMA_SYNC_DEV |\ - PP_FLAG_PAGE_FRAG) + PP_FLAG_DMA_SYNC_DEV) /* * Fast allocation side cache array/stack @@ -45,7 +43,7 @@ struct pp_alloc_cache { /** * struct page_pool_params - page pool parameters - * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV, PP_FLAG_PAGE_FRAG + * @flags: PP_FLAG_DMA_MAP, PP_FLAG_DMA_SYNC_DEV * @order: 2^order pages on allocation * @pool_size: size of the ptr_ring * @nid: NUMA node id to allocate from pages from diff --git a/include/net/sock.h b/include/net/sock.h index 01f0005cb7d8..242590308d64 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -336,7 +336,7 @@ struct sk_filter; * @sk_cgrp_data: cgroup data for this cgroup * @sk_memcg: this socket's memory cgroup association * @sk_write_pending: a write to stream socket waits to start - * @sk_wait_pending: number of threads blocked on this socket + * @sk_disconnects: number of disconnect operations performed on this sock * @sk_state_change: callback to indicate change in the state of the sock * @sk_data_ready: callback to indicate there is data to be processed * @sk_write_space: callback to indicate there is bf sending space available @@ -429,7 +429,7 @@ struct sock { unsigned int sk_napi_id; #endif int sk_rcvbuf; - int sk_wait_pending; + int sk_disconnects; struct sk_filter __rcu *sk_filter; union { @@ -1189,8 +1189,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } #define sk_wait_event(__sk, __timeo, __condition, __wait) \ - ({ int __rc; \ - __sk->sk_wait_pending++; \ + ({ int __rc, __dis = __sk->sk_disconnects; \ release_sock(__sk); \ __rc = __condition; \ if (!__rc) { \ @@ -1200,8 +1199,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk) } \ sched_annotate_sleep(); \ lock_sock(__sk); \ - __sk->sk_wait_pending--; \ - __rc = __condition; \ + __rc = __dis == __sk->sk_disconnects ? __condition : -EPIPE; \ __rc; \ }) diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index b24ea2d9400b..8a6dbfb23336 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -22,6 +22,7 @@ struct tcf_ct_params { struct nf_nat_range2 range; bool ipv4_range; + bool put_labels; u16 ct_action; diff --git a/include/net/tcp.h b/include/net/tcp.h index 32146088a095..993b7fcd4e46 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -143,6 +143,9 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); #define TCP_RTO_MAX ((unsigned)(120*HZ)) #define TCP_RTO_MIN ((unsigned)(HZ/5)) #define TCP_TIMEOUT_MIN (2U) /* Min timeout for TCP timers in jiffies */ + +#define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */ + #define TCP_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ #define TCP_TIMEOUT_FALLBACK ((unsigned)(3*HZ)) /* RFC 1122 initial RTO value, now * used as a fallback RTO for the @@ -163,7 +166,12 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX); #define MAX_TCP_KEEPCNT 127 #define MAX_TCP_SYNCNT 127 -#define TCP_PAWS_24DAYS (60 * 60 * 24 * 24) +/* Ensure that TCP PAWS checks are relaxed after ~2147 seconds + * to avoid overflows. This assumes a clock smaller than 1 Mhz. + * Default clock is 1 Khz, tcp_usec_ts uses 1 Mhz. + */ +#define TCP_PAWS_WRAP (INT_MAX / USEC_PER_SEC) + #define TCP_PAWS_MSL 60 /* Per-host timestamps are invalidated * after this time. It should be equal * (or greater than) TCP_TIMEWAIT_LEN @@ -795,22 +803,31 @@ static inline u64 tcp_clock_us(void) return div_u64(tcp_clock_ns(), NSEC_PER_USEC); } -/* This should only be used in contexts where tp->tcp_mstamp is up to date */ -static inline u32 tcp_time_stamp(const struct tcp_sock *tp) +static inline u64 tcp_clock_ms(void) +{ + return div_u64(tcp_clock_ns(), NSEC_PER_MSEC); +} + +/* TCP Timestamp included in TS option (RFC 1323) can either use ms + * or usec resolution. Each socket carries a flag to select one or other + * resolution, as the route attribute could change anytime. + * Each flow must stick to initial resolution. + */ +static inline u32 tcp_clock_ts(bool usec_ts) { - return div_u64(tp->tcp_mstamp, USEC_PER_SEC / TCP_TS_HZ); + return usec_ts ? tcp_clock_us() : tcp_clock_ms(); } -/* Convert a nsec timestamp into TCP TSval timestamp (ms based currently) */ -static inline u32 tcp_ns_to_ts(u64 ns) +static inline u32 tcp_time_stamp_ms(const struct tcp_sock *tp) { - return div_u64(ns, NSEC_PER_SEC / TCP_TS_HZ); + return div_u64(tp->tcp_mstamp, USEC_PER_MSEC); } -/* Could use tcp_clock_us() / 1000, but this version uses a single divide */ -static inline u32 tcp_time_stamp_raw(void) +static inline u32 tcp_time_stamp_ts(const struct tcp_sock *tp) { - return tcp_ns_to_ts(tcp_clock_ns()); + if (tp->tcp_usec_ts) + return tp->tcp_mstamp; + return tcp_time_stamp_ms(tp); } void tcp_mstamp_refresh(struct tcp_sock *tp); @@ -820,17 +837,30 @@ static inline u32 tcp_stamp_us_delta(u64 t1, u64 t0) return max_t(s64, t1 - t0, 0); } -static inline u32 tcp_skb_timestamp(const struct sk_buff *skb) -{ - return tcp_ns_to_ts(skb->skb_mstamp_ns); -} - /* provide the departure time in us unit */ static inline u64 tcp_skb_timestamp_us(const struct sk_buff *skb) { return div_u64(skb->skb_mstamp_ns, NSEC_PER_USEC); } +/* Provide skb TSval in usec or ms unit */ +static inline u32 tcp_skb_timestamp_ts(bool usec_ts, const struct sk_buff *skb) +{ + if (usec_ts) + return tcp_skb_timestamp_us(skb); + + return div_u64(skb->skb_mstamp_ns, NSEC_PER_MSEC); +} + +static inline u32 tcp_tw_tsval(const struct tcp_timewait_sock *tcptw) +{ + return tcp_clock_ts(tcptw->tw_sk.tw_usec_ts) + tcptw->tw_ts_offset; +} + +static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) +{ + return tcp_clock_ts(treq->req_usec_ts) + treq->ts_off; +} #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) @@ -1459,13 +1489,15 @@ static inline int tcp_space_from_win(const struct sock *sk, int win) return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); } +/* Assume a conservative default of 1200 bytes of payload per 4K page. + * This may be adjusted later in tcp_measure_rcv_mss(). + */ +#define TCP_DEFAULT_SCALING_RATIO ((1200 << TCP_RMEM_TO_WIN_SCALE) / \ + SKB_TRUESIZE(4096)) + static inline void tcp_scaling_ratio_init(struct sock *sk) { - /* Assume a conservative default of 1200 bytes of payload per 4K page. - * This may be adjusted later in tcp_measure_rcv_mss(). - */ - tcp_sk(sk)->scaling_ratio = (1200 << TCP_RMEM_TO_WIN_SCALE) / - SKB_TRUESIZE(4096); + tcp_sk(sk)->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; } /* Note: caller must be prepared to deal with negative returns */ @@ -1596,7 +1628,7 @@ static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt, if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win) return true; if (unlikely(!time_before32(ktime_get_seconds(), - rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))) + rx_opt->ts_recent_stamp + TCP_PAWS_WRAP))) return true; /* * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0, diff --git a/include/net/tcx.h b/include/net/tcx.h index 264f147953ba..04be9377785d 100644 --- a/include/net/tcx.h +++ b/include/net/tcx.h @@ -38,16 +38,11 @@ static inline struct tcx_entry *tcx_entry(struct bpf_mprog_entry *entry) return container_of(bundle, struct tcx_entry, bundle); } -static inline struct tcx_link *tcx_link(struct bpf_link *link) +static inline struct tcx_link *tcx_link(const struct bpf_link *link) { return container_of(link, struct tcx_link, link); } -static inline const struct tcx_link *tcx_link_const(const struct bpf_link *link) -{ - return tcx_link((struct bpf_link *)link); -} - void tcx_inc(void); void tcx_dec(void); diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h index 4d0578fab01a..d716214fe03d 100644 --- a/include/net/udp_tunnel.h +++ b/include/net/udp_tunnel.h @@ -169,6 +169,14 @@ struct rtable *udp_tunnel_dst_lookup(struct sk_buff *skb, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 tos, struct dst_cache *dst_cache); +struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, + struct net_device *dev, + struct net *net, + struct socket *sock, int oif, + struct in6_addr *saddr, + const struct ip_tunnel_key *key, + __be16 sport, __be16 dport, u8 dsfield, + struct dst_cache *dst_cache); struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, __be16 flags, __be64 tunnel_id, diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 69b472604b86..f83128007fb0 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -63,6 +63,13 @@ struct xdp_sock { struct xsk_queue *tx ____cacheline_aligned_in_smp; struct list_head tx_list; + /* record the number of tx descriptors sent by this xsk and + * when it exceeds MAX_PER_SOCKET_BUDGET, an opportunity needs + * to be given to other xsks for sending tx descriptors, thereby + * preventing other XSKs from being starved. + */ + u32 tx_budget_spent; + /* Protects generic receive. */ spinlock_t rx_lock; @@ -109,4 +116,13 @@ static inline void __xsk_map_flush(void) #endif /* CONFIG_XDP_SOCKETS */ +#if defined(CONFIG_XDP_SOCKETS) && defined(CONFIG_DEBUG_NET) +bool xsk_map_check_flush(void); +#else +static inline bool xsk_map_check_flush(void) +{ + return false; +} +#endif + #endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h index d2faec9a323e..433543eb82b9 100644 --- a/include/sound/soc-dapm.h +++ b/include/sound/soc-dapm.h @@ -469,6 +469,7 @@ void snd_soc_dapm_connect_dai_link_widgets(struct snd_soc_card *card); int snd_soc_dapm_update_dai(struct snd_pcm_substream *substream, struct snd_pcm_hw_params *params, struct snd_soc_dai *dai); +int snd_soc_dapm_widget_name_cmp(struct snd_soc_dapm_widget *widget, const char *s); /* dapm path setup */ int snd_soc_dapm_new_widgets(struct snd_soc_card *card); diff --git a/include/trace/events/neigh.h b/include/trace/events/neigh.h index 5eaa1fa99171..833143d0992e 100644 --- a/include/trace/events/neigh.h +++ b/include/trace/events/neigh.h @@ -39,7 +39,6 @@ TRACE_EVENT(neigh_create, ), TP_fast_assign( - struct in6_addr *pin6; __be32 *p32; __entry->family = tbl->family; @@ -47,7 +46,6 @@ TRACE_EVENT(neigh_create, __entry->entries = atomic_read(&tbl->gc_entries); __entry->created = n != NULL; __entry->gc_exempt = exempt_from_gc; - pin6 = (struct in6_addr *)__entry->primary_key6; p32 = (__be32 *)__entry->primary_key4; if (tbl->family == AF_INET) @@ -57,6 +55,8 @@ TRACE_EVENT(neigh_create, #if IS_ENABLED(CONFIG_IPV6) if (tbl->family == AF_INET6) { + struct in6_addr *pin6; + pin6 = (struct in6_addr *)__entry->primary_key6; *pin6 = *(struct in6_addr *)pkey; } diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index eaf9f248619f..0bade1592f34 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -45,8 +45,8 @@ extern "C" { #define NOUVEAU_GETPARAM_HAS_BO_USAGE 15 #define NOUVEAU_GETPARAM_HAS_PAGEFLIP 16 -/** - * @NOUVEAU_GETPARAM_EXEC_PUSH_MAX +/* + * NOUVEAU_GETPARAM_EXEC_PUSH_MAX - query max pushes through getparam * * Query the maximum amount of IBs that can be pushed through a single * &drm_nouveau_exec structure and hence a single &DRM_IOCTL_NOUVEAU_EXEC diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 7ba61b75bc0e..0f6cdf52b1da 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1052,6 +1052,8 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_RECVMSG, BPF_CGROUP_UNIX_GETPEERNAME, BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_NETKIT_PRIMARY, + BPF_NETKIT_PEER, __MAX_BPF_ATTACH_TYPE }; @@ -1071,6 +1073,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, + BPF_LINK_TYPE_NETKIT = 13, MAX_BPF_LINK_TYPE, }; @@ -1656,6 +1659,13 @@ union bpf_attr { __u32 flags; __u32 pid; } uprobe_multi; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } netkit; }; } link_create; @@ -6576,6 +6586,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } tcx; + struct { + __u32 ifindex; + __u32 attach_type; + } netkit; }; } __attribute__((aligned(8))); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index cd4b82458d1b..b3c8383d342d 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -265,7 +265,7 @@ enum { * Documentation/networking/devlink/devlink-flash.rst * */ -enum { +enum devlink_flash_overwrite { DEVLINK_FLASH_OVERWRITE_SETTINGS_BIT, DEVLINK_FLASH_OVERWRITE_IDENTIFIERS_BIT, diff --git a/include/uapi/linux/gtp.h b/include/uapi/linux/gtp.h index 2f61298a7b77..3dcdb9e33cba 100644 --- a/include/uapi/linux/gtp.h +++ b/include/uapi/linux/gtp.h @@ -33,6 +33,6 @@ enum gtp_attrs { GTPA_PAD, __GTPA_MAX, }; -#define GTPA_MAX (__GTPA_MAX + 1) +#define GTPA_MAX (__GTPA_MAX - 1) #endif /* _UAPI_LINUX_GTP_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9f8a3da0f14f..29ff80da2775 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -758,6 +758,30 @@ struct tunnel_msg { __u32 ifindex; }; +/* netkit section */ +enum netkit_action { + NETKIT_NEXT = -1, + NETKIT_PASS = 0, + NETKIT_DROP = 2, + NETKIT_REDIRECT = 7, +}; + +enum netkit_mode { + NETKIT_L2, + NETKIT_L3, +}; + +enum { + IFLA_NETKIT_UNSPEC, + IFLA_NETKIT_PEER_INFO, + IFLA_NETKIT_PRIMARY, + IFLA_NETKIT_POLICY, + IFLA_NETKIT_PEER_POLICY, + IFLA_NETKIT_MODE, + __IFLA_NETKIT_MAX, +}; +#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) + /* VXLAN section */ /* include statistics in the dump */ @@ -1394,7 +1418,9 @@ enum { enum { IFLA_DSA_UNSPEC, - IFLA_DSA_MASTER, + IFLA_DSA_CONDUIT, + /* Deprecated, use IFLA_DSA_CONDUIT instead */ + IFLA_DSA_MASTER = IFLA_DSA_CONDUIT, __IFLA_DSA_MAX, }; diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index ee9c49f949a2..64ecc8a3f9f2 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -23,91 +23,24 @@ #define MPTCP_SUBFLOW_FLAG_CONNECTED _BITUL(7) #define MPTCP_SUBFLOW_FLAG_MAPVALID _BITUL(8) -enum { - MPTCP_SUBFLOW_ATTR_UNSPEC, - MPTCP_SUBFLOW_ATTR_TOKEN_REM, - MPTCP_SUBFLOW_ATTR_TOKEN_LOC, - MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ, - MPTCP_SUBFLOW_ATTR_MAP_SEQ, - MPTCP_SUBFLOW_ATTR_MAP_SFSEQ, - MPTCP_SUBFLOW_ATTR_SSN_OFFSET, - MPTCP_SUBFLOW_ATTR_MAP_DATALEN, - MPTCP_SUBFLOW_ATTR_FLAGS, - MPTCP_SUBFLOW_ATTR_ID_REM, - MPTCP_SUBFLOW_ATTR_ID_LOC, - MPTCP_SUBFLOW_ATTR_PAD, - __MPTCP_SUBFLOW_ATTR_MAX -}; - -#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1) - -/* netlink interface */ -#define MPTCP_PM_NAME "mptcp_pm" #define MPTCP_PM_CMD_GRP_NAME "mptcp_pm_cmds" #define MPTCP_PM_EV_GRP_NAME "mptcp_pm_events" -#define MPTCP_PM_VER 0x1 - -/* - * ATTR types defined for MPTCP - */ -enum { - MPTCP_PM_ATTR_UNSPEC, - - MPTCP_PM_ATTR_ADDR, /* nested address */ - MPTCP_PM_ATTR_RCV_ADD_ADDRS, /* u32 */ - MPTCP_PM_ATTR_SUBFLOWS, /* u32 */ - MPTCP_PM_ATTR_TOKEN, /* u32 */ - MPTCP_PM_ATTR_LOC_ID, /* u8 */ - MPTCP_PM_ATTR_ADDR_REMOTE, /* nested address */ - - __MPTCP_PM_ATTR_MAX -}; - -#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1) - -enum { - MPTCP_PM_ADDR_ATTR_UNSPEC, - - MPTCP_PM_ADDR_ATTR_FAMILY, /* u16 */ - MPTCP_PM_ADDR_ATTR_ID, /* u8 */ - MPTCP_PM_ADDR_ATTR_ADDR4, /* struct in_addr */ - MPTCP_PM_ADDR_ATTR_ADDR6, /* struct in6_addr */ - MPTCP_PM_ADDR_ATTR_PORT, /* u16 */ - MPTCP_PM_ADDR_ATTR_FLAGS, /* u32 */ - MPTCP_PM_ADDR_ATTR_IF_IDX, /* s32 */ - - __MPTCP_PM_ADDR_ATTR_MAX -}; - -#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1) - -#define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) -#define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) -#define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) -#define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) -#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4) -enum { - MPTCP_PM_CMD_UNSPEC, +#include <linux/mptcp_pm.h> - MPTCP_PM_CMD_ADD_ADDR, - MPTCP_PM_CMD_DEL_ADDR, - MPTCP_PM_CMD_GET_ADDR, - MPTCP_PM_CMD_FLUSH_ADDRS, - MPTCP_PM_CMD_SET_LIMITS, - MPTCP_PM_CMD_GET_LIMITS, - MPTCP_PM_CMD_SET_FLAGS, - MPTCP_PM_CMD_ANNOUNCE, - MPTCP_PM_CMD_REMOVE, - MPTCP_PM_CMD_SUBFLOW_CREATE, - MPTCP_PM_CMD_SUBFLOW_DESTROY, - - __MPTCP_PM_CMD_AFTER_LAST -}; +/* for backward compatibility */ +#define __MPTCP_PM_CMD_AFTER_LAST __MPTCP_PM_CMD_MAX +#define __MPTCP_ATTR_AFTER_LAST __MPTCP_ATTR_MAX #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) +#define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) +#define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) +#define MPTCP_PM_ADDR_FLAG_FULLMESH (1 << 3) +#define MPTCP_PM_ADDR_FLAG_IMPLICIT (1 << 4) + struct mptcp_info { __u8 mptcpi_subflows; __u8 mptcpi_add_addr_signal; @@ -130,93 +63,6 @@ struct mptcp_info { __u64 mptcpi_bytes_acked; }; -/* - * MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport - * A new MPTCP connection has been created. It is the good time to allocate - * memory and send ADD_ADDR if needed. Depending on the traffic-patterns - * it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. - * - * MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport - * A MPTCP connection is established (can start new subflows). - * - * MPTCP_EVENT_CLOSED: token - * A MPTCP connection has stopped. - * - * MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] - * A new address has been announced by the peer. - * - * MPTCP_EVENT_REMOVED: token, rem_id - * An address has been lost by the peer. - * - * MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, - * saddr4 | saddr6, daddr4 | daddr6, sport, - * dport, backup, if_idx [, error] - * A new subflow has been established. 'error' should not be set. - * - * MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx - * [, error] - * A subflow has been closed. An error (copy of sk_err) could be set if an - * error has been detected for this subflow. - * - * MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, - * daddr4 | daddr6, sport, dport, backup, if_idx - * [, error] - * The priority of a subflow has changed. 'error' should not be set. - * - * MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 - * A new PM listener is created. - * - * MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 - * A PM listener is closed. - */ -enum mptcp_event_type { - MPTCP_EVENT_UNSPEC = 0, - MPTCP_EVENT_CREATED = 1, - MPTCP_EVENT_ESTABLISHED = 2, - MPTCP_EVENT_CLOSED = 3, - - MPTCP_EVENT_ANNOUNCED = 6, - MPTCP_EVENT_REMOVED = 7, - - MPTCP_EVENT_SUB_ESTABLISHED = 10, - MPTCP_EVENT_SUB_CLOSED = 11, - - MPTCP_EVENT_SUB_PRIORITY = 13, - - MPTCP_EVENT_LISTENER_CREATED = 15, - MPTCP_EVENT_LISTENER_CLOSED = 16, -}; - -enum mptcp_event_attr { - MPTCP_ATTR_UNSPEC = 0, - - MPTCP_ATTR_TOKEN, /* u32 */ - MPTCP_ATTR_FAMILY, /* u16 */ - MPTCP_ATTR_LOC_ID, /* u8 */ - MPTCP_ATTR_REM_ID, /* u8 */ - MPTCP_ATTR_SADDR4, /* be32 */ - MPTCP_ATTR_SADDR6, /* struct in6_addr */ - MPTCP_ATTR_DADDR4, /* be32 */ - MPTCP_ATTR_DADDR6, /* struct in6_addr */ - MPTCP_ATTR_SPORT, /* be16 */ - MPTCP_ATTR_DPORT, /* be16 */ - MPTCP_ATTR_BACKUP, /* u8 */ - MPTCP_ATTR_ERROR, /* u8 */ - MPTCP_ATTR_FLAGS, /* u16 */ - MPTCP_ATTR_TIMEOUT, /* u32 */ - MPTCP_ATTR_IF_IDX, /* s32 */ - MPTCP_ATTR_RESET_REASON,/* u32 */ - MPTCP_ATTR_RESET_FLAGS, /* u32 */ - MPTCP_ATTR_SERVER_SIDE, /* u8 */ - - __MPTCP_ATTR_AFTER_LAST -}; - -#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1) - /* MPTCP Reset reason codes, rfc8684 */ #define MPTCP_RST_EUNSPEC 0 #define MPTCP_RST_EMPTCP 1 diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h new file mode 100644 index 000000000000..0ad598fe940b --- /dev/null +++ b/include/uapi/linux/mptcp_pm.h @@ -0,0 +1,150 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN uapi header */ + +#ifndef _UAPI_LINUX_MPTCP_PM_H +#define _UAPI_LINUX_MPTCP_PM_H + +#define MPTCP_PM_NAME "mptcp_pm" +#define MPTCP_PM_VER 1 + +/** + * enum mptcp_event_type + * @MPTCP_EVENT_UNSPEC: unused event + * @MPTCP_EVENT_CREATED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport A new MPTCP connection has been created. It is the good time + * to allocate memory and send ADD_ADDR if needed. Depending on the + * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED + * is sent. + * @MPTCP_EVENT_ESTABLISHED: token, family, saddr4 | saddr6, daddr4 | daddr6, + * sport, dport A MPTCP connection is established (can start new subflows). + * @MPTCP_EVENT_CLOSED: token A MPTCP connection has stopped. + * @MPTCP_EVENT_ANNOUNCED: token, rem_id, family, daddr4 | daddr6 [, dport] A + * new address has been announced by the peer. + * @MPTCP_EVENT_REMOVED: token, rem_id An address has been lost by the peer. + * @MPTCP_EVENT_SUB_ESTABLISHED: token, family, loc_id, rem_id, saddr4 | + * saddr6, daddr4 | daddr6, sport, dport, backup, if_idx [, error] A new + * subflow has been established. 'error' should not be set. + * @MPTCP_EVENT_SUB_CLOSED: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx [, error] A subflow has been + * closed. An error (copy of sk_err) could be set if an error has been + * detected for this subflow. + * @MPTCP_EVENT_SUB_PRIORITY: token, family, loc_id, rem_id, saddr4 | saddr6, + * daddr4 | daddr6, sport, dport, backup, if_idx [, error] The priority of a + * subflow has changed. 'error' should not be set. + * @MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 A new PM + * listener is created. + * @MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 A PM listener + * is closed. + */ +enum mptcp_event_type { + MPTCP_EVENT_UNSPEC, + MPTCP_EVENT_CREATED, + MPTCP_EVENT_ESTABLISHED, + MPTCP_EVENT_CLOSED, + MPTCP_EVENT_ANNOUNCED = 6, + MPTCP_EVENT_REMOVED, + MPTCP_EVENT_SUB_ESTABLISHED = 10, + MPTCP_EVENT_SUB_CLOSED, + MPTCP_EVENT_SUB_PRIORITY = 13, + MPTCP_EVENT_LISTENER_CREATED = 15, + MPTCP_EVENT_LISTENER_CLOSED, +}; + +enum { + MPTCP_PM_ADDR_ATTR_UNSPEC, + MPTCP_PM_ADDR_ATTR_FAMILY, + MPTCP_PM_ADDR_ATTR_ID, + MPTCP_PM_ADDR_ATTR_ADDR4, + MPTCP_PM_ADDR_ATTR_ADDR6, + MPTCP_PM_ADDR_ATTR_PORT, + MPTCP_PM_ADDR_ATTR_FLAGS, + MPTCP_PM_ADDR_ATTR_IF_IDX, + + __MPTCP_PM_ADDR_ATTR_MAX +}; +#define MPTCP_PM_ADDR_ATTR_MAX (__MPTCP_PM_ADDR_ATTR_MAX - 1) + +enum { + MPTCP_SUBFLOW_ATTR_UNSPEC, + MPTCP_SUBFLOW_ATTR_TOKEN_REM, + MPTCP_SUBFLOW_ATTR_TOKEN_LOC, + MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ, + MPTCP_SUBFLOW_ATTR_MAP_SEQ, + MPTCP_SUBFLOW_ATTR_MAP_SFSEQ, + MPTCP_SUBFLOW_ATTR_SSN_OFFSET, + MPTCP_SUBFLOW_ATTR_MAP_DATALEN, + MPTCP_SUBFLOW_ATTR_FLAGS, + MPTCP_SUBFLOW_ATTR_ID_REM, + MPTCP_SUBFLOW_ATTR_ID_LOC, + MPTCP_SUBFLOW_ATTR_PAD, + + __MPTCP_SUBFLOW_ATTR_MAX +}; +#define MPTCP_SUBFLOW_ATTR_MAX (__MPTCP_SUBFLOW_ATTR_MAX - 1) + +enum { + MPTCP_PM_ENDPOINT_ADDR = 1, + + __MPTCP_PM_ENDPOINT_MAX +}; +#define MPTCP_PM_ENDPOINT_MAX (__MPTCP_PM_ENDPOINT_MAX - 1) + +enum { + MPTCP_PM_ATTR_UNSPEC, + MPTCP_PM_ATTR_ADDR, + MPTCP_PM_ATTR_RCV_ADD_ADDRS, + MPTCP_PM_ATTR_SUBFLOWS, + MPTCP_PM_ATTR_TOKEN, + MPTCP_PM_ATTR_LOC_ID, + MPTCP_PM_ATTR_ADDR_REMOTE, + + __MPTCP_PM_ATTR_MAX +}; +#define MPTCP_PM_ATTR_MAX (__MPTCP_PM_ATTR_MAX - 1) + +enum mptcp_event_attr { + MPTCP_ATTR_UNSPEC, + MPTCP_ATTR_TOKEN, + MPTCP_ATTR_FAMILY, + MPTCP_ATTR_LOC_ID, + MPTCP_ATTR_REM_ID, + MPTCP_ATTR_SADDR4, + MPTCP_ATTR_SADDR6, + MPTCP_ATTR_DADDR4, + MPTCP_ATTR_DADDR6, + MPTCP_ATTR_SPORT, + MPTCP_ATTR_DPORT, + MPTCP_ATTR_BACKUP, + MPTCP_ATTR_ERROR, + MPTCP_ATTR_FLAGS, + MPTCP_ATTR_TIMEOUT, + MPTCP_ATTR_IF_IDX, + MPTCP_ATTR_RESET_REASON, + MPTCP_ATTR_RESET_FLAGS, + MPTCP_ATTR_SERVER_SIDE, + + __MPTCP_ATTR_MAX +}; +#define MPTCP_ATTR_MAX (__MPTCP_ATTR_MAX - 1) + +enum { + MPTCP_PM_CMD_UNSPEC, + MPTCP_PM_CMD_ADD_ADDR, + MPTCP_PM_CMD_DEL_ADDR, + MPTCP_PM_CMD_GET_ADDR, + MPTCP_PM_CMD_FLUSH_ADDRS, + MPTCP_PM_CMD_SET_LIMITS, + MPTCP_PM_CMD_GET_LIMITS, + MPTCP_PM_CMD_SET_FLAGS, + MPTCP_PM_CMD_ANNOUNCE, + MPTCP_PM_CMD_REMOVE, + MPTCP_PM_CMD_SUBFLOW_CREATE, + MPTCP_PM_CMD_SUBFLOW_DESTROY, + + __MPTCP_PM_CMD_MAX +}; +#define MPTCP_PM_CMD_MAX (__MPTCP_PM_CMD_MAX - 1) + +#endif /* _UAPI_LINUX_MPTCP_PM_H */ diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index e2ae82e3f9f7..f87aaf28a649 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -298,6 +298,8 @@ struct nla_bitfield32 { * entry has attributes again, the policy for those inner ones * and the corresponding maxtype may be specified. * @NL_ATTR_TYPE_BITFIELD32: &struct nla_bitfield32 attribute + * @NL_ATTR_TYPE_SINT: 32-bit or 64-bit signed attribute, aligned to 4B + * @NL_ATTR_TYPE_UINT: 32-bit or 64-bit unsigned attribute, aligned to 4B */ enum netlink_attribute_type { NL_ATTR_TYPE_INVALID, @@ -322,6 +324,9 @@ enum netlink_attribute_type { NL_ATTR_TYPE_NESTED_ARRAY, NL_ATTR_TYPE_BITFIELD32, + + NL_ATTR_TYPE_SINT, + NL_ATTR_TYPE_UINT, }; /** diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 51c13cf9c5ae..3b687d20c9ed 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -502,13 +502,17 @@ enum { #define RTAX_MAX (__RTAX_MAX - 1) -#define RTAX_FEATURE_ECN (1 << 0) -#define RTAX_FEATURE_SACK (1 << 1) -#define RTAX_FEATURE_TIMESTAMP (1 << 2) -#define RTAX_FEATURE_ALLFRAG (1 << 3) - -#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | RTAX_FEATURE_SACK | \ - RTAX_FEATURE_TIMESTAMP | RTAX_FEATURE_ALLFRAG) +#define RTAX_FEATURE_ECN (1 << 0) +#define RTAX_FEATURE_SACK (1 << 1) /* unused */ +#define RTAX_FEATURE_TIMESTAMP (1 << 2) /* unused */ +#define RTAX_FEATURE_ALLFRAG (1 << 3) /* unused */ +#define RTAX_FEATURE_TCP_USEC_TS (1 << 4) + +#define RTAX_FEATURE_MASK (RTAX_FEATURE_ECN | \ + RTAX_FEATURE_SACK | \ + RTAX_FEATURE_TIMESTAMP | \ + RTAX_FEATURE_ALLFRAG | \ + RTAX_FEATURE_TCP_USEC_TS) struct rta_session { __u8 proto; diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 26f33a4c253d..b2b72886cb6d 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -24,7 +24,7 @@ enum IPSTATS_MIB_INOCTETS, /* InOctets */ IPSTATS_MIB_INDELIVERS, /* InDelivers */ IPSTATS_MIB_OUTFORWDATAGRAMS, /* OutForwDatagrams */ - IPSTATS_MIB_OUTPKTS, /* OutRequests */ + IPSTATS_MIB_OUTREQUESTS, /* OutRequests */ IPSTATS_MIB_OUTOCTETS, /* OutOctets */ /* other fields */ IPSTATS_MIB_INHDRERRORS, /* InHdrErrors */ @@ -57,6 +57,7 @@ enum IPSTATS_MIB_ECT0PKTS, /* InECT0Pkts */ IPSTATS_MIB_CEPKTS, /* InCEPkts */ IPSTATS_MIB_REASM_OVERLAPS, /* ReasmOverlaps */ + IPSTATS_MIB_OUTPKTS, /* OutTransmits */ __IPSTATS_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index d1d08da6331a..8aa3916e14f6 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -170,6 +170,7 @@ enum tcp_fastopen_client_fail { #define TCPI_OPT_ECN 8 /* ECN was negociated at TCP session init */ #define TCPI_OPT_ECN_SEEN 16 /* we received at least one packet with ECT */ #define TCPI_OPT_SYN_DATA 32 /* SYN-ACK acked data in SYN sent or rcvd */ +#define TCPI_OPT_USEC_TS 64 /* usec timestamps */ /* * Sender's congestion state indicating normal or abnormal situations diff --git a/include/video/mmp_disp.h b/include/video/mmp_disp.h index 77252cb46361..a722dcbf5073 100644 --- a/include/video/mmp_disp.h +++ b/include/video/mmp_disp.h @@ -231,7 +231,7 @@ struct mmp_path { /* layers */ int overlay_num; - struct mmp_overlay overlays[]; + struct mmp_overlay overlays[] __counted_by(overlay_num); }; extern struct mmp_path *mmp_get_path(const char *name); diff --git a/include/video/uvesafb.h b/include/video/uvesafb.h index 8d2a3bfc8dac..47d96e75e8ef 100644 --- a/include/video/uvesafb.h +++ b/include/video/uvesafb.h @@ -109,8 +109,6 @@ struct uvesafb_ktask { u32 ack; }; -static int uvesafb_exec(struct uvesafb_ktask *tsk); - #define UVESAFB_EXACT_RES 1 #define UVESAFB_EXACT_DEPTH 2 diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index d839a80a6751..8d1bc6cdfe71 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2674,7 +2674,11 @@ static void io_pages_free(struct page ***pages, int npages) if (!pages) return; + page_array = *pages; + if (!page_array) + return; + for (i = 0; i < npages; i++) unpin_user_page(page_array[i]); kvfree(page_array); @@ -2758,7 +2762,9 @@ static void io_rings_free(struct io_ring_ctx *ctx) ctx->sq_sqes = NULL; } else { io_pages_free(&ctx->ring_pages, ctx->n_ring_pages); + ctx->n_ring_pages = 0; io_pages_free(&ctx->sqe_pages, ctx->n_sqe_pages); + ctx->n_sqe_pages = 0; } } diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 21d2fa815e78..6f0d6fb6523f 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -2212,7 +2212,7 @@ __audit_reusename(const __user char *uptr) if (!n->name) continue; if (n->name->uptr == uptr) { - n->name->refcnt++; + atomic_inc(&n->name->refcnt); return n->name; } } @@ -2241,7 +2241,7 @@ void __audit_getname(struct filename *name) n->name = name; n->name_len = AUDIT_NAME_FULL; name->aname = n; - name->refcnt++; + atomic_inc(&name->refcnt); } static inline int audit_copy_fcaps(struct audit_names *name, @@ -2373,7 +2373,7 @@ out_alloc: return; if (name) { n->name = name; - name->refcnt++; + atomic_inc(&name->refcnt); } out: @@ -2500,7 +2500,7 @@ void __audit_inode_child(struct inode *parent, if (found_parent) { found_child->name = found_parent->name; found_child->name_len = AUDIT_NAME_FULL; - found_child->name->refcnt++; + atomic_inc(&found_child->name->refcnt); } } diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 810378f04fbc..209e5135f9fb 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -294,3 +294,68 @@ static int __init bpf_cgroup_iter_init(void) } late_initcall(bpf_cgroup_iter_init); + +struct bpf_iter_css { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_kern { + struct cgroup_subsys_state *start; + struct cgroup_subsys_state *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css)); + + kit->start = NULL; + switch (flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + case BPF_CGROUP_ITER_DESCENDANTS_POST: + case BPF_CGROUP_ITER_ANCESTORS_UP: + break; + default: + return -EINVAL; + } + + kit->start = start; + kit->pos = NULL; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + if (!kit->start) + return NULL; + + switch (kit->flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + kit->pos = css_next_descendant_pre(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + kit->pos = css_next_descendant_post(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_ANCESTORS_UP: + kit->pos = kit->pos ? kit->pos->parent : kit->start; + } + + return kit->pos; +} + +__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it) +{ +} + +__diag_pop();
\ No newline at end of file diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index e42a1bdb7f53..8a0bb80fe48a 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -764,6 +764,16 @@ void __cpu_map_flush(void) } } +#ifdef CONFIG_DEBUG_NET +bool cpu_map_check_flush(void) +{ + if (list_empty(this_cpu_ptr(&cpu_map_flush_list))) + return false; + __cpu_map_flush(); + return true; +} +#endif + static int __init cpu_map_init(void) { int cpu; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 4d42f6ed6c11..a936c704d4e7 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -418,6 +418,16 @@ void __dev_flush(void) } } +#ifdef CONFIG_DEBUG_NET +bool dev_check_flush(void) +{ + if (list_empty(this_cpu_ptr(&dev_flush_list))) + return false; + __dev_flush(); + return true; +} +#endif + /* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or * by local_bh_disable() (from XDP calls inside NAPI). The * rcu_read_lock_bh_held() below makes lockdep accept both. diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index a8c7e1c5abfa..fd8d4b0addfc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -155,13 +155,15 @@ static inline int htab_lock_bucket(const struct bpf_htab *htab, hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); preempt_disable(); + local_irq_save(flags); if (unlikely(__this_cpu_inc_return(*(htab->map_locked[hash])) != 1)) { __this_cpu_dec(*(htab->map_locked[hash])); + local_irq_restore(flags); preempt_enable(); return -EBUSY; } - raw_spin_lock_irqsave(&b->raw_lock, flags); + raw_spin_lock(&b->raw_lock); *pflags = flags; return 0; @@ -172,8 +174,9 @@ static inline void htab_unlock_bucket(const struct bpf_htab *htab, unsigned long flags) { hash = hash & min_t(u32, HASHTAB_MAP_LOCK_MASK, htab->n_buckets - 1); - raw_spin_unlock_irqrestore(&b->raw_lock, flags); + raw_spin_unlock(&b->raw_lock); __this_cpu_dec(*(htab->map_locked[hash])); + local_irq_restore(flags); preempt_enable(); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 62a53ebfedf9..e46ac288a108 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1811,8 +1811,6 @@ bpf_base_func_proto(enum bpf_func_id func_id) } } -void __bpf_obj_drop_impl(void *p, const struct btf_record *rec); - void bpf_list_head_free(const struct btf_field *field, void *list_head, struct bpf_spin_lock *spin_lock) { @@ -1844,7 +1842,7 @@ unlock: * bpf_list_head which needs to be freed. */ migrate_disable(); - __bpf_obj_drop_impl(obj, field->graph_root.value_rec); + __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); migrate_enable(); } } @@ -1883,7 +1881,7 @@ void bpf_rb_root_free(const struct btf_field *field, void *rb_root, migrate_disable(); - __bpf_obj_drop_impl(obj, field->graph_root.value_rec); + __bpf_obj_drop_impl(obj, field->graph_root.value_rec, false); migrate_enable(); } } @@ -1915,8 +1913,10 @@ __bpf_kfunc void *bpf_percpu_obj_new_impl(u64 local_type_id__k, void *meta__ign) } /* Must be called under migrate_disable(), as required by bpf_mem_free */ -void __bpf_obj_drop_impl(void *p, const struct btf_record *rec) +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu) { + struct bpf_mem_alloc *ma; + if (rec && rec->refcount_off >= 0 && !refcount_dec_and_test((refcount_t *)(p + rec->refcount_off))) { /* Object is refcounted and refcount_dec didn't result in 0 @@ -1928,10 +1928,14 @@ void __bpf_obj_drop_impl(void *p, const struct btf_record *rec) if (rec) bpf_obj_free_fields(rec, p); + if (percpu) + ma = &bpf_global_percpu_ma; + else + ma = &bpf_global_ma; if (rec && rec->refcount_off >= 0) - bpf_mem_free_rcu(&bpf_global_ma, p); + bpf_mem_free_rcu(ma, p); else - bpf_mem_free(&bpf_global_ma, p); + bpf_mem_free(ma, p); } __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) @@ -1939,7 +1943,7 @@ __bpf_kfunc void bpf_obj_drop_impl(void *p__alloc, void *meta__ign) struct btf_struct_meta *meta = meta__ign; void *p = p__alloc; - __bpf_obj_drop_impl(p, meta ? meta->record : NULL); + __bpf_obj_drop_impl(p, meta ? meta->record : NULL, false); } __bpf_kfunc void bpf_percpu_obj_drop_impl(void *p__alloc, void *meta__ign) @@ -1983,7 +1987,7 @@ static int __bpf_list_add(struct bpf_list_node_kern *node, */ if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) { /* Only called from BPF prog, no need to migrate_disable */ - __bpf_obj_drop_impl((void *)n - off, rec); + __bpf_obj_drop_impl((void *)n - off, rec, false); return -EINVAL; } @@ -2082,7 +2086,7 @@ static int __bpf_rbtree_add(struct bpf_rb_root *root, */ if (cmpxchg(&node->owner, NULL, BPF_PTR_POISON)) { /* Only called from BPF prog, no need to migrate_disable */ - __bpf_obj_drop_impl((void *)n - off, rec); + __bpf_obj_drop_impl((void *)n - off, rec, false); return -EINVAL; } @@ -2215,7 +2219,12 @@ __bpf_kfunc struct cgroup *bpf_cgroup_from_id(u64 cgid) __bpf_kfunc long bpf_task_under_cgroup(struct task_struct *task, struct cgroup *ancestor) { - return task_under_cgroup_hierarchy(task, ancestor); + long ret; + + rcu_read_lock(); + ret = task_under_cgroup_hierarchy(task, ancestor); + rcu_read_unlock(); + return ret; } #endif /* CONFIG_CGROUPS */ @@ -2555,6 +2564,15 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU) BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) +BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c index 39ea316c55e7..63b909d277d4 100644 --- a/kernel/bpf/memalloc.c +++ b/kernel/bpf/memalloc.c @@ -340,6 +340,7 @@ static void free_bulk(struct bpf_mem_cache *c) int cnt; WARN_ON_ONCE(tgt->unit_size != c->unit_size); + WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); do { inc_active(c, &flags); @@ -365,6 +366,9 @@ static void __free_by_rcu(struct rcu_head *head) struct bpf_mem_cache *tgt = c->tgt; struct llist_node *llnode; + WARN_ON_ONCE(tgt->unit_size != c->unit_size); + WARN_ON_ONCE(tgt->percpu_size != c->percpu_size); + llnode = llist_del_all(&c->waiting_for_gp); if (!llnode) goto out; @@ -491,21 +495,17 @@ static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx) struct llist_node *first; unsigned int obj_size; - /* For per-cpu allocator, the size of free objects in free list doesn't - * match with unit_size and now there is no way to get the size of - * per-cpu pointer saved in free object, so just skip the checking. - */ - if (c->percpu_size) - return 0; - first = c->free_llist.first; if (!first) return 0; - obj_size = ksize(first); + if (c->percpu_size) + obj_size = pcpu_alloc_size(((void **)first)[1]); + else + obj_size = ksize(first); if (obj_size != c->unit_size) { - WARN_ONCE(1, "bpf_mem_cache[%u]: unexpected object size %u, expect %u\n", - idx, obj_size, c->unit_size); + WARN_ONCE(1, "bpf_mem_cache[%u]: percpu %d, unexpected object size %u, expect %u\n", + idx, c->percpu_size, obj_size, c->unit_size); return -EINVAL; } return 0; @@ -529,6 +529,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu) /* room for llist_node and per-cpu pointer */ if (percpu) percpu_size = LLIST_NODE_SZ + sizeof(void *); + ma->percpu = percpu; if (size) { pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL); @@ -878,6 +879,17 @@ void notrace *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size) return !ret ? NULL : ret + LLIST_NODE_SZ; } +static notrace int bpf_mem_free_idx(void *ptr, bool percpu) +{ + size_t size; + + if (percpu) + size = pcpu_alloc_size(*((void **)ptr)); + else + size = ksize(ptr - LLIST_NODE_SZ); + return bpf_mem_cache_idx(size); +} + void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) { int idx; @@ -885,7 +897,7 @@ void notrace bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr) if (!ptr) return; - idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ)); + idx = bpf_mem_free_idx(ptr, ma->percpu); if (idx < 0) return; @@ -899,7 +911,7 @@ void notrace bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr) if (!ptr) return; - idx = bpf_mem_cache_idx(ksize(ptr - LLIST_NODE_SZ)); + idx = bpf_mem_free_idx(ptr, ma->percpu); if (idx < 0) return; @@ -973,6 +985,12 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags) return !ret ? NULL : ret + LLIST_NODE_SZ; } +/* The alignment of dynamic per-cpu area is 8, so c->unit_size and the + * actual size of dynamic per-cpu area will always be matched and there is + * no need to adjust size_index for per-cpu allocation. However for the + * simplicity of the implementation, use an unified size_index for both + * kmalloc and per-cpu allocation. + */ static __init int bpf_mem_cache_adjust_size(void) { unsigned int size; diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index f045fde632e5..0ee653a936ea 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -770,8 +770,7 @@ schedule_work_return: /* Prevent the clearing of the busy-bit from being reordered before the * storing of any rb consumer or producer positions. */ - smp_mb__before_atomic(); - atomic_set(&rb->busy, 0); + atomic_set_release(&rb->busy, 0); if (flags & BPF_RB_FORCE_WAKEUP) irq_work_queue(&rb->work); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 341f8cb4405c..0ed286b8a0f0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -35,8 +35,9 @@ #include <linux/rcupdate_trace.h> #include <linux/memcontrol.h> #include <linux/trace_events.h> -#include <net/netfilter/nf_bpf_link.h> +#include <net/netfilter/nf_bpf_link.h> +#include <net/netkit.h> #include <net/tcx.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ @@ -626,8 +627,6 @@ void bpf_obj_free_timer(const struct btf_record *rec, void *obj) bpf_timer_cancel_and_free(obj + rec->timer_off); } -extern void __bpf_obj_drop_impl(void *p, const struct btf_record *rec); - void bpf_obj_free_fields(const struct btf_record *rec, void *obj) { const struct btf_field *fields; @@ -662,8 +661,8 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) field->kptr.btf_id); migrate_disable(); __bpf_obj_drop_impl(xchgd_field, pointee_struct_meta ? - pointee_struct_meta->record : - NULL); + pointee_struct_meta->record : NULL, + fields[i].type == BPF_KPTR_PERCPU); migrate_enable(); } else { field->kptr.dtor(xchgd_field); @@ -3732,6 +3731,8 @@ attach_type_to_prog_type(enum bpf_attach_type attach_type) return BPF_PROG_TYPE_LSM; case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: return BPF_PROG_TYPE_SCHED_CLS; default: return BPF_PROG_TYPE_UNSPEC; @@ -3783,7 +3784,9 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, return 0; case BPF_PROG_TYPE_SCHED_CLS: if (attach_type != BPF_TCX_INGRESS && - attach_type != BPF_TCX_EGRESS) + attach_type != BPF_TCX_EGRESS && + attach_type != BPF_NETKIT_PRIMARY && + attach_type != BPF_NETKIT_PEER) return -EINVAL; return 0; default: @@ -3866,7 +3869,11 @@ static int bpf_prog_attach(const union bpf_attr *attr) ret = cgroup_bpf_prog_attach(attr, ptype, prog); break; case BPF_PROG_TYPE_SCHED_CLS: - ret = tcx_prog_attach(attr, prog); + if (attr->attach_type == BPF_TCX_INGRESS || + attr->attach_type == BPF_TCX_EGRESS) + ret = tcx_prog_attach(attr, prog); + else + ret = netkit_prog_attach(attr, prog); break; default: ret = -EINVAL; @@ -3927,7 +3934,11 @@ static int bpf_prog_detach(const union bpf_attr *attr) ret = cgroup_bpf_prog_detach(attr, ptype); break; case BPF_PROG_TYPE_SCHED_CLS: - ret = tcx_prog_detach(attr, prog); + if (attr->attach_type == BPF_TCX_INGRESS || + attr->attach_type == BPF_TCX_EGRESS) + ret = tcx_prog_detach(attr, prog); + else + ret = netkit_prog_detach(attr, prog); break; default: ret = -EINVAL; @@ -3994,6 +4005,9 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_TCX_INGRESS: case BPF_TCX_EGRESS: return tcx_prog_query(attr, uattr); + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + return netkit_prog_query(attr, uattr); default: return -EINVAL; } @@ -4975,7 +4989,11 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr) ret = bpf_xdp_link_attach(attr, prog); break; case BPF_PROG_TYPE_SCHED_CLS: - ret = tcx_link_attach(attr, prog); + if (attr->link_create.attach_type == BPF_TCX_INGRESS || + attr->link_create.attach_type == BPF_TCX_EGRESS) + ret = tcx_link_attach(attr, prog); + else + ret = netkit_link_attach(attr, prog); break; case BPF_PROG_TYPE_NETFILTER: ret = bpf_nf_link_attach(attr, prog); diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index fef17628341f..59e747938bdb 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -894,6 +894,157 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __diag_pop(); +struct bpf_iter_css_task { + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_task_kern { + struct css_task_iter *css_it; +} __attribute__((aligned(8))); + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) != + __alignof__(struct bpf_iter_css_task)); + kit->css_it = NULL; + switch (flags) { + case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED: + case CSS_TASK_ITER_PROCS: + case 0: + break; + default: + return -EINVAL; + } + + kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter)); + if (!kit->css_it) + return -ENOMEM; + css_task_iter_start(css, flags, kit->css_it); + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return NULL; + return css_task_iter_next(kit->css_it); +} + +__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return; + css_task_iter_end(kit->css_it); + bpf_mem_free(&bpf_global_ma, kit->css_it); +} + +__diag_pop(); + +struct bpf_iter_task { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_task_kern { + struct task_struct *task; + struct task_struct *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +enum { + /* all process in the system */ + BPF_TASK_ITER_ALL_PROCS, + /* all threads in the system */ + BPF_TASK_ITER_ALL_THREADS, + /* all threads of a specific process */ + BPF_TASK_ITER_PROC_THREADS +}; + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task__nullable, unsigned int flags) +{ + struct bpf_iter_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != + __alignof__(struct bpf_iter_task)); + + kit->task = kit->pos = NULL; + switch (flags) { + case BPF_TASK_ITER_ALL_THREADS: + case BPF_TASK_ITER_ALL_PROCS: + break; + case BPF_TASK_ITER_PROC_THREADS: + if (!task__nullable) + return -EINVAL; + break; + default: + return -EINVAL; + } + + if (flags == BPF_TASK_ITER_PROC_THREADS) + kit->task = task__nullable; + else + kit->task = &init_task; + kit->pos = kit->task; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) +{ + struct bpf_iter_task_kern *kit = (void *)it; + struct task_struct *pos; + unsigned int flags; + + flags = kit->flags; + pos = kit->pos; + + if (!pos) + return pos; + + if (flags == BPF_TASK_ITER_ALL_PROCS) + goto get_next_task; + + kit->pos = next_thread(kit->pos); + if (kit->pos == kit->task) { + if (flags == BPF_TASK_ITER_PROC_THREADS) { + kit->pos = NULL; + return pos; + } + } else + return pos; + +get_next_task: + kit->pos = next_task(kit->pos); + kit->task = kit->pos; + if (kit->pos == &init_task) + kit->pos = NULL; + + return pos; +} + +__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it) +{ +} + +__diag_pop(); + DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); static void do_mmap_read_unlock(struct irq_work *entry) diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c index 1338a13a8b64..2e4885e7781f 100644 --- a/kernel/bpf/tcx.c +++ b/kernel/bpf/tcx.c @@ -250,7 +250,7 @@ static void tcx_link_dealloc(struct bpf_link *link) static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) { - const struct tcx_link *tcx = tcx_link_const(link); + const struct tcx_link *tcx = tcx_link(link); u32 ifindex = 0; rtnl_lock(); @@ -267,7 +267,7 @@ static void tcx_link_fdinfo(const struct bpf_link *link, struct seq_file *seq) static int tcx_link_fill_info(const struct bpf_link *link, struct bpf_link_info *info) { - const struct tcx_link *tcx = tcx_link_const(link); + const struct tcx_link *tcx = tcx_link(link); u32 ifindex = 0; rtnl_lock(); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bb58987e4844..857d76694517 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1173,7 +1173,12 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg static void __mark_reg_known_zero(struct bpf_reg_state *reg); +static bool in_rcu_cs(struct bpf_verifier_env *env); + +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta); + static int mark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *reg, int insn_idx, struct btf *btf, u32 btf_id, int nr_slots) { @@ -1194,6 +1199,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env, __mark_reg_known_zero(st); st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + if (is_kfunc_rcu_protected(meta)) { + if (in_rcu_cs(env)) + st->type |= MEM_RCU; + else + st->type |= PTR_UNTRUSTED; + } st->live |= REG_LIVE_WRITTEN; st->ref_obj_id = i == 0 ? id : 0; st->iter.btf = btf; @@ -1268,7 +1279,7 @@ static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, return true; } -static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, +static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = func(env, reg); @@ -1276,26 +1287,28 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_ spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) - return false; + return -EINVAL; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; + if (st->type & PTR_UNTRUSTED) + return -EPROTO; /* only main (first) slot has ref_obj_id set */ if (i == 0 && !st->ref_obj_id) - return false; + return -EINVAL; if (i != 0 && st->ref_obj_id) - return false; + return -EINVAL; if (st->iter.btf != btf || st->iter.btf_id != btf_id) - return false; + return -EINVAL; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] != STACK_ITER) - return false; + return -EINVAL; } - return true; + return 0; } /* Check if given stack slot is "special": @@ -1789,6 +1802,8 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->parent = src->parent; dst_state->first_insn_idx = src->first_insn_idx; dst_state->last_insn_idx = src->last_insn_idx; + dst_state->dfs_depth = src->dfs_depth; + dst_state->used_as_loop_entry = src->used_as_loop_entry; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -1804,11 +1819,203 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, return 0; } +static u32 state_htab_size(struct bpf_verifier_env *env) +{ + return env->prog->len; +} + +static struct bpf_verifier_state_list **explored_state(struct bpf_verifier_env *env, int idx) +{ + struct bpf_verifier_state *cur = env->cur_state; + struct bpf_func_state *state = cur->frame[cur->curframe]; + + return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; +} + +static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b) +{ + int fr; + + if (a->curframe != b->curframe) + return false; + + for (fr = a->curframe; fr >= 0; fr--) + if (a->frame[fr]->callsite != b->frame[fr]->callsite) + return false; + + return true; +} + +/* Open coded iterators allow back-edges in the state graph in order to + * check unbounded loops that iterators. + * + * In is_state_visited() it is necessary to know if explored states are + * part of some loops in order to decide whether non-exact states + * comparison could be used: + * - non-exact states comparison establishes sub-state relation and uses + * read and precision marks to do so, these marks are propagated from + * children states and thus are not guaranteed to be final in a loop; + * - exact states comparison just checks if current and explored states + * are identical (and thus form a back-edge). + * + * Paper "A New Algorithm for Identifying Loops in Decompilation" + * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient + * algorithm for loop structure detection and gives an overview of + * relevant terminology. It also has helpful illustrations. + * + * [1] https://api.semanticscholar.org/CorpusID:15784067 + * + * We use a similar algorithm but because loop nested structure is + * irrelevant for verifier ours is significantly simpler and resembles + * strongly connected components algorithm from Sedgewick's textbook. + * + * Define topmost loop entry as a first node of the loop traversed in a + * depth first search starting from initial state. The goal of the loop + * tracking algorithm is to associate topmost loop entries with states + * derived from these entries. + * + * For each step in the DFS states traversal algorithm needs to identify + * the following situations: + * + * initial initial initial + * | | | + * V V V + * ... ... .---------> hdr + * | | | | + * V V | V + * cur .-> succ | .------... + * | | | | | | + * V | V | V V + * succ '-- cur | ... ... + * | | | + * | V V + * | succ <- cur + * | | + * | V + * | ... + * | | + * '----' + * + * (A) successor state of cur (B) successor state of cur or it's entry + * not yet traversed are in current DFS path, thus cur and succ + * are members of the same outermost loop + * + * initial initial + * | | + * V V + * ... ... + * | | + * V V + * .------... .------... + * | | | | + * V V V V + * .-> hdr ... ... ... + * | | | | | + * | V V V V + * | succ <- cur succ <- cur + * | | | + * | V V + * | ... ... + * | | | + * '----' exit + * + * (C) successor state of cur is a part of some loop but this loop + * does not include cur or successor state is not in a loop at all. + * + * Algorithm could be described as the following python code: + * + * traversed = set() # Set of traversed nodes + * entries = {} # Mapping from node to loop entry + * depths = {} # Depth level assigned to graph node + * path = set() # Current DFS path + * + * # Find outermost loop entry known for n + * def get_loop_entry(n): + * h = entries.get(n, None) + * while h in entries and entries[h] != h: + * h = entries[h] + * return h + * + * # Update n's loop entry if h's outermost entry comes + * # before n's outermost entry in current DFS path. + * def update_loop_entry(n, h): + * n1 = get_loop_entry(n) or n + * h1 = get_loop_entry(h) or h + * if h1 in path and depths[h1] <= depths[n1]: + * entries[n] = h1 + * + * def dfs(n, depth): + * traversed.add(n) + * path.add(n) + * depths[n] = depth + * for succ in G.successors(n): + * if succ not in traversed: + * # Case A: explore succ and update cur's loop entry + * # only if succ's entry is in current DFS path. + * dfs(succ, depth + 1) + * h = get_loop_entry(succ) + * update_loop_entry(n, h) + * else: + * # Case B or C depending on `h1 in path` check in update_loop_entry(). + * update_loop_entry(n, succ) + * path.remove(n) + * + * To adapt this algorithm for use with verifier: + * - use st->branch == 0 as a signal that DFS of succ had been finished + * and cur's loop entry has to be updated (case A), handle this in + * update_branch_counts(); + * - use st->branch > 0 as a signal that st is in the current DFS path; + * - handle cases B and C in is_state_visited(); + * - update topmost loop entry for intermediate states in get_loop_entry(). + */ +static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_state *st) +{ + struct bpf_verifier_state *topmost = st->loop_entry, *old; + + while (topmost && topmost->loop_entry && topmost != topmost->loop_entry) + topmost = topmost->loop_entry; + /* Update loop entries for intermediate states to avoid this + * traversal in future get_loop_entry() calls. + */ + while (st && st->loop_entry != topmost) { + old = st->loop_entry; + st->loop_entry = topmost; + st = old; + } + return topmost; +} + +static void update_loop_entry(struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr) +{ + struct bpf_verifier_state *cur1, *hdr1; + + cur1 = get_loop_entry(cur) ?: cur; + hdr1 = get_loop_entry(hdr) ?: hdr; + /* The head1->branches check decides between cases B and C in + * comment for get_loop_entry(). If hdr1->branches == 0 then + * head's topmost loop entry is not in current DFS path, + * hence 'cur' and 'hdr' are not in the same loop and there is + * no need to update cur->loop_entry. + */ + if (hdr1->branches && hdr1->dfs_depth <= cur1->dfs_depth) { + cur->loop_entry = hdr; + hdr->used_as_loop_entry = true; + } +} + static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st) { while (st) { u32 br = --st->branches; + /* br == 0 signals that DFS exploration for 'st' is finished, + * thus it is necessary to update parent's loop entry if it + * turned out that st is a part of some loop. + * This is a part of 'case A' in get_loop_entry() comment. + */ + if (br == 0 && st->parent && st->loop_entry) + update_loop_entry(st->parent, st->loop_entry); + /* WARN_ON(br > 1) technically makes sense here, * but see comment in push_stack(), hence: */ @@ -7640,15 +7847,24 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id return err; } - err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots); + err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots); if (err) return err; } else { /* iter_next() or iter_destroy() expect initialized iter state*/ - if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) { + err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots); + switch (err) { + case 0: + break; + case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno); - return -EINVAL; + return err; + case -EPROTO: + verbose(env, "expected an RCU CS when using %s\n", meta->func_name); + return err; + default: + return err; } spi = iter_get_spi(env, reg, nr_slots); @@ -7674,6 +7890,81 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id return 0; } +/* Look for a previous loop entry at insn_idx: nearest parent state + * stopped at insn_idx with callsites matching those in cur->frame. + */ +static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env, + struct bpf_verifier_state *cur, + int insn_idx) +{ + struct bpf_verifier_state_list *sl; + struct bpf_verifier_state *st; + + /* Explored states are pushed in stack order, most recent states come first */ + sl = *explored_state(env, insn_idx); + for (; sl; sl = sl->next) { + /* If st->branches != 0 state is a part of current DFS verification path, + * hence cur & st for a loop. + */ + st = &sl->state; + if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) && + st->dfs_depth < cur->dfs_depth) + return st; + } + + return NULL; +} + +static void reset_idmap_scratch(struct bpf_verifier_env *env); +static bool regs_exact(const struct bpf_reg_state *rold, + const struct bpf_reg_state *rcur, + struct bpf_idmap *idmap); + +static void maybe_widen_reg(struct bpf_verifier_env *env, + struct bpf_reg_state *rold, struct bpf_reg_state *rcur, + struct bpf_idmap *idmap) +{ + if (rold->type != SCALAR_VALUE) + return; + if (rold->type != rcur->type) + return; + if (rold->precise || rcur->precise || regs_exact(rold, rcur, idmap)) + return; + __mark_reg_unknown(env, rcur); +} + +static int widen_imprecise_scalars(struct bpf_verifier_env *env, + struct bpf_verifier_state *old, + struct bpf_verifier_state *cur) +{ + struct bpf_func_state *fold, *fcur; + int i, fr; + + reset_idmap_scratch(env); + for (fr = old->curframe; fr >= 0; fr--) { + fold = old->frame[fr]; + fcur = cur->frame[fr]; + + for (i = 0; i < MAX_BPF_REG; i++) + maybe_widen_reg(env, + &fold->regs[i], + &fcur->regs[i], + &env->idmap_scratch); + + for (i = 0; i < fold->allocated_stack / BPF_REG_SIZE; i++) { + if (!is_spilled_reg(&fold->stack[i]) || + !is_spilled_reg(&fcur->stack[i])) + continue; + + maybe_widen_reg(env, + &fold->stack[i].spilled_ptr, + &fcur->stack[i].spilled_ptr, + &env->idmap_scratch); + } + } + return 0; +} + /* process_iter_next_call() is called when verifier gets to iterator's next * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer * to it as just "iter_next()" in comments below. @@ -7715,25 +8006,47 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id * is some statically known limit on number of iterations (e.g., if there is * an explicit `if n > 100 then break;` statement somewhere in the loop). * - * One very subtle but very important aspect is that we *always* simulate NULL - * condition first (as the current state) before we simulate non-NULL case. - * This has to do with intricacies of scalar precision tracking. By simulating - * "exit condition" of iter_next() returning NULL first, we make sure all the - * relevant precision marks *that will be set **after** we exit iterator loop* - * are propagated backwards to common parent state of NULL and non-NULL - * branches. Thanks to that, state equivalence checks done later in forked - * state, when reaching iter_next() for ACTIVE iterator, can assume that - * precision marks are finalized and won't change. Because simulating another - * ACTIVE iterator iteration won't change them (because given same input - * states we'll end up with exactly same output states which we are currently - * comparing; and verification after the loop already propagated back what - * needs to be **additionally** tracked as precise). It's subtle, grok - * precision tracking for more intuitive understanding. + * Iteration convergence logic in is_state_visited() relies on exact + * states comparison, which ignores read and precision marks. + * This is necessary because read and precision marks are not finalized + * while in the loop. Exact comparison might preclude convergence for + * simple programs like below: + * + * i = 0; + * while(iter_next(&it)) + * i++; + * + * At each iteration step i++ would produce a new distinct state and + * eventually instruction processing limit would be reached. + * + * To avoid such behavior speculatively forget (widen) range for + * imprecise scalar registers, if those registers were not precise at the + * end of the previous iteration and do not match exactly. + * + * This is a conservative heuristic that allows to verify wide range of programs, + * however it precludes verification of programs that conjure an + * imprecise value on the first loop iteration and use it as precise on a second. + * For example, the following safe program would fail to verify: + * + * struct bpf_num_iter it; + * int arr[10]; + * int i = 0, a = 0; + * bpf_iter_num_new(&it, 0, 10); + * while (bpf_iter_num_next(&it)) { + * if (a == 0) { + * a = 1; + * i = 7; // Because i changed verifier would forget + * // it's range on second loop entry. + * } else { + * arr[i] = 42; // This would fail to verify. + * } + * } + * bpf_iter_num_destroy(&it); */ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, struct bpf_kfunc_call_arg_meta *meta) { - struct bpf_verifier_state *cur_st = env->cur_state, *queued_st; + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr; struct bpf_reg_state *cur_iter, *queued_iter; int iter_frameno = meta->iter.frameno; @@ -7751,6 +8064,19 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, } if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) { + /* Because iter_next() call is a checkpoint is_state_visitied() + * should guarantee parent state with same call sites and insn_idx. + */ + if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx || + !same_callsites(cur_st->parent, cur_st)) { + verbose(env, "bug: bad parent state for iter next call"); + return -EFAULT; + } + /* Note cur_st->parent in the call below, it is necessary to skip + * checkpoint created for cur_st by is_state_visited() + * right at this instruction. + */ + prev_st = find_prev_entry(env, cur_st->parent, insn_idx); /* branch out active iter state */ queued_st = push_stack(env, insn_idx + 1, insn_idx, false); if (!queued_st) @@ -7759,6 +8085,8 @@ static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx, queued_iter = &queued_st->frame[iter_frameno]->stack[iter_spi].spilled_ptr; queued_iter->iter.state = BPF_ITER_STATE_ACTIVE; queued_iter->iter.depth++; + if (prev_st) + widen_imprecise_scalars(env, prev_st, queued_st); queued_fr = queued_st->frame[queued_st->curframe]; mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]); @@ -10231,6 +10559,11 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU; } +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RCU_PROTECTED; +} + static bool __kfunc_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix) @@ -10305,6 +10638,11 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr"); } +static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__nullable"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -10447,6 +10785,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CALLBACK, KF_ARG_PTR_TO_RB_ROOT, KF_ARG_PTR_TO_RB_NODE, + KF_ARG_PTR_TO_NULL, }; enum special_kfunc_type { @@ -10472,6 +10811,7 @@ enum special_kfunc_type { KF_bpf_percpu_obj_new_impl, KF_bpf_percpu_obj_drop_impl, KF_bpf_throw, + KF_bpf_iter_css_task_new, }; BTF_SET_START(special_kfunc_set) @@ -10495,6 +10835,7 @@ BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) +BTF_ID(func, bpf_iter_css_task_new) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -10520,6 +10861,7 @@ BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) +BTF_ID(func, bpf_iter_css_task_new) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -10600,6 +10942,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) return KF_ARG_PTR_TO_CALLBACK; + if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg)) + return KF_ARG_PTR_TO_NULL; if (argno + 1 < nargs && (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || @@ -11050,6 +11394,20 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, &meta->arg_rbtree_root.field); } +static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) +{ + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + + switch (prog_type) { + case BPF_PROG_TYPE_LSM: + return true; + case BPF_TRACE_ITER: + return env->prog->aux->sleepable; + default: + return false; + } +} + static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, int insn_idx) { @@ -11136,7 +11494,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ } if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && - (register_is_null(reg) || type_may_be_null(reg->type))) { + (register_is_null(reg) || type_may_be_null(reg->type)) && + !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); return -EACCES; } @@ -11161,6 +11520,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return kf_arg_type; switch (kf_arg_type) { + case KF_ARG_PTR_TO_NULL: + continue; case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) @@ -11300,6 +11661,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; } case KF_ARG_PTR_TO_ITER: + if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) { + if (!check_css_task_iter_allowlist(env)) { + verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n"); + return -EINVAL; + } + } ret = process_iter_arg(env, regno, insn_idx, meta); if (ret < 0) return ret; @@ -11559,6 +11926,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (env->cur_state->active_rcu_lock) { struct bpf_func_state *state; struct bpf_reg_state *reg; + u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); @@ -11569,7 +11937,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); return -EINVAL; } else if (rcu_unlock) { - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({ if (reg->type & MEM_RCU) { reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; @@ -13663,12 +14031,16 @@ static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode) return !!tnum_equals_const(subreg, val); else if (val < reg->u32_min_value || val > reg->u32_max_value) return 0; + else if (sval < reg->s32_min_value || sval > reg->s32_max_value) + return 0; break; case BPF_JNE: if (tnum_is_const(subreg)) return !tnum_equals_const(subreg, val); else if (val < reg->u32_min_value || val > reg->u32_max_value) return 1; + else if (sval < reg->s32_min_value || sval > reg->s32_max_value) + return 1; break; case BPF_JSET: if ((~subreg.mask & subreg.value) & val) @@ -13740,12 +14112,16 @@ static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode) return !!tnum_equals_const(reg->var_off, val); else if (val < reg->umin_value || val > reg->umax_value) return 0; + else if (sval < reg->smin_value || sval > reg->smax_value) + return 0; break; case BPF_JNE: if (tnum_is_const(reg->var_off)) return !tnum_equals_const(reg->var_off, val); else if (val < reg->umin_value || val > reg->umax_value) return 1; + else if (sval < reg->smin_value || sval > reg->smax_value) + return 1; break; case BPF_JSET: if ((~reg->var_off.mask & reg->var_off.value) & val) @@ -14958,21 +15334,6 @@ enum { BRANCH = 2, }; -static u32 state_htab_size(struct bpf_verifier_env *env) -{ - return env->prog->len; -} - -static struct bpf_verifier_state_list **explored_state( - struct bpf_verifier_env *env, - int idx) -{ - struct bpf_verifier_state *cur = env->cur_state; - struct bpf_func_state *state = cur->frame[cur->curframe]; - - return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)]; -} - static void mark_prune_point(struct bpf_verifier_env *env, int idx) { env->insn_aux_data[idx].prune_point = true; @@ -15849,18 +16210,14 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn, struct bpf_verifier_state *cur) { struct bpf_verifier_state_list *sl; - int i; sl = *explored_state(env, insn); while (sl) { if (sl->state.branches) goto next; if (sl->state.insn_idx != insn || - sl->state.curframe != cur->curframe) + !same_callsites(&sl->state, cur)) goto next; - for (i = 0; i <= cur->curframe; i++) - if (sl->state.frame[i]->callsite != cur->frame[i]->callsite) - goto next; clean_verifier_state(env, &sl->state); next: sl = sl->next; @@ -15878,8 +16235,11 @@ static bool regs_exact(const struct bpf_reg_state *rold, /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, - struct bpf_reg_state *rcur, struct bpf_idmap *idmap) + struct bpf_reg_state *rcur, struct bpf_idmap *idmap, bool exact) { + if (exact) + return regs_exact(rold, rcur, idmap); + if (!(rold->live & REG_LIVE_READ)) /* explored state didn't use this */ return true; @@ -15996,7 +16356,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, } static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur, struct bpf_idmap *idmap) + struct bpf_func_state *cur, struct bpf_idmap *idmap, bool exact) { int i, spi; @@ -16009,7 +16369,12 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, spi = i / BPF_REG_SIZE; - if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) { + if (exact && + old->stack[spi].slot_type[i % BPF_REG_SIZE] != + cur->stack[spi].slot_type[i % BPF_REG_SIZE]) + return false; + + if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) && !exact) { i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; @@ -16059,7 +16424,7 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, * return false to continue verification of this path */ if (!regsafe(env, &old->stack[spi].spilled_ptr, - &cur->stack[spi].spilled_ptr, idmap)) + &cur->stack[spi].spilled_ptr, idmap, exact)) return false; break; case STACK_DYNPTR: @@ -16141,16 +16506,16 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur, * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur) + struct bpf_func_state *cur, bool exact) { int i; for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], - &env->idmap_scratch)) + &env->idmap_scratch, exact)) return false; - if (!stacksafe(env, old, cur, &env->idmap_scratch)) + if (!stacksafe(env, old, cur, &env->idmap_scratch, exact)) return false; if (!refsafe(old, cur, &env->idmap_scratch)) @@ -16159,17 +16524,23 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat return true; } +static void reset_idmap_scratch(struct bpf_verifier_env *env) +{ + env->idmap_scratch.tmp_id_gen = env->id_gen; + memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map)); +} + static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, - struct bpf_verifier_state *cur) + struct bpf_verifier_state *cur, + bool exact) { int i; if (old->curframe != cur->curframe) return false; - env->idmap_scratch.tmp_id_gen = env->id_gen; - memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map)); + reset_idmap_scratch(env); /* Verification state from speculative execution simulation * must never prune a non-speculative execution one. @@ -16199,7 +16570,7 @@ static bool states_equal(struct bpf_verifier_env *env, for (i = 0; i <= old->curframe; i++) { if (old->frame[i]->callsite != cur->frame[i]->callsite) return false; - if (!func_states_equal(env, old->frame[i], cur->frame[i])) + if (!func_states_equal(env, old->frame[i], cur->frame[i], exact)) return false; } return true; @@ -16453,10 +16824,11 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl, **pprev; - struct bpf_verifier_state *cur = env->cur_state, *new; - int i, j, err, states_cnt = 0; + struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry; + int i, j, n, err, states_cnt = 0; bool force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx); bool add_new_state = force_new_state; + bool force_exact; /* bpf progs typically have pruning point every 4 instructions * http://vger.kernel.org/bpfconf2019.html#session-1 @@ -16509,9 +16881,33 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * It's safe to assume that iterator loop will finish, taking into * account iter_next() contract of eventually returning * sticky NULL result. + * + * Note, that states have to be compared exactly in this case because + * read and precision marks might not be finalized inside the loop. + * E.g. as in the program below: + * + * 1. r7 = -16 + * 2. r6 = bpf_get_prandom_u32() + * 3. while (bpf_iter_num_next(&fp[-8])) { + * 4. if (r6 != 42) { + * 5. r7 = -32 + * 6. r6 = bpf_get_prandom_u32() + * 7. continue + * 8. } + * 9. r0 = r10 + * 10. r0 += r7 + * 11. r8 = *(u64 *)(r0 + 0) + * 12. r6 = bpf_get_prandom_u32() + * 13. } + * + * Here verifier would first visit path 1-3, create a checkpoint at 3 + * with r7=-16, continue to 4-7,3. Existing checkpoint at 3 does + * not have read or precision mark for r7 yet, thus inexact states + * comparison would discard current state with r7=-32 + * => unsafe memory access at 11 would not be caught. */ if (is_iter_next_insn(env, insn_idx)) { - if (states_equal(env, &sl->state, cur)) { + if (states_equal(env, &sl->state, cur, true)) { struct bpf_func_state *cur_frame; struct bpf_reg_state *iter_state, *iter_reg; int spi; @@ -16527,17 +16923,23 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) */ spi = __get_spi(iter_reg->off + iter_reg->var_off.value); iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr; - if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) + if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) { + update_loop_entry(cur, &sl->state); goto hit; + } } goto skip_inf_loop_check; } /* attempt to detect infinite loop to avoid unnecessary doomed work */ if (states_maybe_looping(&sl->state, cur) && - states_equal(env, &sl->state, cur) && + states_equal(env, &sl->state, cur, false) && !iter_active_depths_differ(&sl->state, cur)) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); + verbose(env, "cur state:"); + print_verifier_state(env, cur->frame[cur->curframe], true); + verbose(env, "old state:"); + print_verifier_state(env, sl->state.frame[cur->curframe], true); return -EINVAL; } /* if the verifier is processing a loop, avoid adding new state @@ -16559,7 +16961,36 @@ skip_inf_loop_check: add_new_state = false; goto miss; } - if (states_equal(env, &sl->state, cur)) { + /* If sl->state is a part of a loop and this loop's entry is a part of + * current verification path then states have to be compared exactly. + * 'force_exact' is needed to catch the following case: + * + * initial Here state 'succ' was processed first, + * | it was eventually tracked to produce a + * V state identical to 'hdr'. + * .---------> hdr All branches from 'succ' had been explored + * | | and thus 'succ' has its .branches == 0. + * | V + * | .------... Suppose states 'cur' and 'succ' correspond + * | | | to the same instruction + callsites. + * | V V In such case it is necessary to check + * | ... ... if 'succ' and 'cur' are states_equal(). + * | | | If 'succ' and 'cur' are a part of the + * | V V same loop exact flag has to be set. + * | succ <- cur To check if that is the case, verify + * | | if loop entry of 'succ' is in current + * | V DFS path. + * | ... + * | | + * '----' + * + * Additional details are in the comment before get_loop_entry(). + */ + loop_entry = get_loop_entry(&sl->state); + force_exact = loop_entry && loop_entry->branches > 0; + if (states_equal(env, &sl->state, cur, force_exact)) { + if (force_exact) + update_loop_entry(cur, loop_entry); hit: sl->hit_cnt++; /* reached equivalent register/stack state, @@ -16598,13 +17029,18 @@ miss: * to keep checking from state equivalence point of view. * Higher numbers increase max_states_per_insn and verification time, * but do not meaningfully decrease insn_processed. + * 'n' controls how many times state could miss before eviction. + * Use bigger 'n' for checkpoints because evicting checkpoint states + * too early would hinder iterator convergence. */ - if (sl->miss_cnt > sl->hit_cnt * 3 + 3) { + n = is_force_checkpoint(env, insn_idx) && sl->state.branches > 0 ? 64 : 3; + if (sl->miss_cnt > sl->hit_cnt * n + n) { /* the state is unlikely to be useful. Remove it to * speed up verification */ *pprev = sl->next; - if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) { + if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE && + !sl->state.used_as_loop_entry) { u32 br = sl->state.branches; WARN_ONCE(br, @@ -16673,6 +17109,7 @@ next: cur->parent = new; cur->first_insn_idx = insn_idx; + cur->dfs_depth = new->dfs_depth + 1; clear_jmp_history(cur); new_sl->next = *explored_state(env, insn_idx); *explored_state(env, insn_idx) = new_sl; diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index c487ffef6652..76db6c67e39a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -360,10 +360,9 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, } css_task_iter_end(&it); length = n; - /* now sort & (if procs) strip out duplicates */ + /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ sort(array, length, sizeof(pid_t), cmppid, NULL); - if (type == CGROUP_FILE_PROCS) - length = pidlist_uniq(array, length); + length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1fb7f562289d..b6d64f3b8888 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4917,9 +4917,11 @@ repeat: void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { + unsigned long irqflags; + memset(it, 0, sizeof(*it)); - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); it->ss = css->ss; it->flags = flags; @@ -4933,7 +4935,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, css_task_iter_advance(it); - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); } /** @@ -4946,12 +4948,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { + unsigned long irqflags; + if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) @@ -4964,7 +4968,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) css_task_iter_advance(it); } - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); return it->cur_task; } @@ -4977,11 +4981,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) */ void css_task_iter_end(struct css_task_iter *it) { + unsigned long irqflags; + if (it->cur_cset) { - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); } if (it->cur_dcset) diff --git a/kernel/events/core.c b/kernel/events/core.c index 4c72a41f11af..d0663b9324e7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1954,6 +1954,7 @@ static void perf_group_attach(struct perf_event *event) list_add_tail(&event->sibling_list, &group_leader->sibling_list); group_leader->nr_siblings++; + group_leader->group_generation++; perf_event__header_size(group_leader); @@ -2144,6 +2145,7 @@ static void perf_group_detach(struct perf_event *event) if (leader != event) { list_del_init(&event->sibling_list); event->group_leader->nr_siblings--; + event->group_leader->group_generation++; goto out; } @@ -5440,7 +5442,7 @@ static int __perf_read_group_add(struct perf_event *leader, u64 read_format, u64 *values) { struct perf_event_context *ctx = leader->ctx; - struct perf_event *sub; + struct perf_event *sub, *parent; unsigned long flags; int n = 1; /* skip @nr */ int ret; @@ -5450,6 +5452,33 @@ static int __perf_read_group_add(struct perf_event *leader, return ret; raw_spin_lock_irqsave(&ctx->lock, flags); + /* + * Verify the grouping between the parent and child (inherited) + * events is still in tact. + * + * Specifically: + * - leader->ctx->lock pins leader->sibling_list + * - parent->child_mutex pins parent->child_list + * - parent->ctx->mutex pins parent->sibling_list + * + * Because parent->ctx != leader->ctx (and child_list nests inside + * ctx->mutex), group destruction is not atomic between children, also + * see perf_event_release_kernel(). Additionally, parent can grow the + * group. + * + * Therefore it is possible to have parent and child groups in a + * different configuration and summing over such a beast makes no sense + * what so ever. + * + * Reject this. + */ + parent = leader->parent; + if (parent && + (parent->group_generation != leader->group_generation || + parent->nr_siblings != leader->nr_siblings)) { + ret = -ECHILD; + goto unlock; + } /* * Since we co-schedule groups, {enabled,running} times of siblings @@ -5483,8 +5512,9 @@ static int __perf_read_group_add(struct perf_event *leader, values[n++] = atomic64_read(&sub->lost_samples); } +unlock: raw_spin_unlock_irqrestore(&ctx->lock, flags); - return 0; + return ret; } static int perf_read_group(struct perf_event *event, @@ -5503,10 +5533,6 @@ static int perf_read_group(struct perf_event *event, values[0] = 1 + leader->nr_siblings; - /* - * By locking the child_mutex of the leader we effectively - * lock the child list of all siblings.. XXX explain how. - */ mutex_lock(&leader->child_mutex); ret = __perf_read_group_add(leader, read_format, values); @@ -13346,6 +13372,7 @@ static int inherit_group(struct perf_event *parent_event, !perf_get_aux_event(child_ctr, leader)) return -EINVAL; } + leader->group_generation = parent_event->group_generation; return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ef7490c4b8b4..df348aa55d3c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -872,14 +872,16 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) * * Which allows an EDF like search on (sub)trees. */ -static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) +static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq) { struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node; struct sched_entity *curr = cfs_rq->curr; struct sched_entity *best = NULL; + struct sched_entity *best_left = NULL; if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr))) curr = NULL; + best = curr; /* * Once selected, run a task until it either becomes non-eligible or @@ -900,33 +902,75 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) } /* - * If this entity has an earlier deadline than the previous - * best, take this one. If it also has the earliest deadline - * of its subtree, we're done. + * Now we heap search eligible trees for the best (min_)deadline */ - if (!best || deadline_gt(deadline, best, se)) { + if (!best || deadline_gt(deadline, best, se)) best = se; - if (best->deadline == best->min_deadline) - break; - } /* - * If the earlest deadline in this subtree is in the fully - * eligible left half of our space, go there. + * Every se in a left branch is eligible, keep track of the + * branch with the best min_deadline */ + if (node->rb_left) { + struct sched_entity *left = __node_2_se(node->rb_left); + + if (!best_left || deadline_gt(min_deadline, best_left, left)) + best_left = left; + + /* + * min_deadline is in the left branch. rb_left and all + * descendants are eligible, so immediately switch to the second + * loop. + */ + if (left->min_deadline == se->min_deadline) + break; + } + + /* min_deadline is at this node, no need to look right */ + if (se->deadline == se->min_deadline) + break; + + /* else min_deadline is in the right branch. */ + node = node->rb_right; + } + + /* + * We ran into an eligible node which is itself the best. + * (Or nr_running == 0 and both are NULL) + */ + if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0) + return best; + + /* + * Now best_left and all of its children are eligible, and we are just + * looking for deadline == min_deadline + */ + node = &best_left->run_node; + while (node) { + struct sched_entity *se = __node_2_se(node); + + /* min_deadline is the current node */ + if (se->deadline == se->min_deadline) + return se; + + /* min_deadline is in the left branch */ if (node->rb_left && __node_2_se(node->rb_left)->min_deadline == se->min_deadline) { node = node->rb_left; continue; } + /* else min_deadline is in the right branch */ node = node->rb_right; } + return NULL; +} - if (!best || (curr && deadline_gt(deadline, best, curr))) - best = curr; +static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) +{ + struct sched_entity *se = __pick_eevdf(cfs_rq); - if (unlikely(!best)) { + if (!se) { struct sched_entity *left = __pick_first_entity(cfs_rq); if (left) { pr_err("EEVDF scheduling fail, picking leftmost\n"); @@ -934,7 +978,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) } } - return best; + return se; } #ifdef CONFIG_SCHED_DEBUG @@ -3613,6 +3657,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, */ deadline = div_s64(deadline * old_weight, weight); se->deadline = se->vruntime + deadline; + if (se != cfs_rq->curr) + min_deadline_cb_propagate(&se->run_node, NULL); } #ifdef CONFIG_SMP diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 3b21f4063258..881f90f0cbcf 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -189,7 +189,7 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) { int i, size; - if (num < 0) + if (num <= 0) return -EINVAL; if (!fp->exit_handler) { @@ -202,8 +202,8 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) size = fp->nr_maxactive; else size = num * num_possible_cpus() * 2; - if (size < 0) - return -E2BIG; + if (size <= 0) + return -EINVAL; fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler); if (!fp->rethook) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index 961a78ffd6d2..effcaede4759 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -705,6 +705,25 @@ static struct notifier_block trace_kprobe_module_nb = { .priority = 1 /* Invoked after kprobe module callback */ }; +static int count_symbols(void *data, unsigned long unused) +{ + unsigned int *count = data; + + (*count)++; + + return 0; +} + +static unsigned int number_of_same_symbols(char *func_name) +{ + unsigned int count; + + count = 0; + kallsyms_on_each_match_symbol(count_symbols, func_name, &count); + + return count; +} + static int __trace_kprobe_create(int argc, const char *argv[]) { /* @@ -836,6 +855,31 @@ static int __trace_kprobe_create(int argc, const char *argv[]) } } + if (symbol && !strchr(symbol, ':')) { + unsigned int count; + + count = number_of_same_symbols(symbol); + if (count > 1) { + /* + * Users should use ADDR to remove the ambiguity of + * using KSYM only. + */ + trace_probe_log_err(0, NON_UNIQ_SYMBOL); + ret = -EADDRNOTAVAIL; + + goto error; + } else if (count == 0) { + /* + * We can return ENOENT earlier than when register the + * kprobe. + */ + trace_probe_log_err(0, BAD_PROBE_ADDR); + ret = -ENOENT; + + goto error; + } + } + trace_probe_log_set_index(0); if (event) { ret = traceprobe_parse_event_name(&event, &group, gbuf, @@ -1703,6 +1747,7 @@ static int unregister_kprobe_event(struct trace_kprobe *tk) } #ifdef CONFIG_PERF_EVENTS + /* create a trace_kprobe, but don't add it to global lists */ struct trace_event_call * create_local_trace_kprobe(char *func, void *addr, unsigned long offs, @@ -1713,6 +1758,24 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs, int ret; char *event; + if (func) { + unsigned int count; + + count = number_of_same_symbols(func); + if (count > 1) + /* + * Users should use addr to remove the ambiguity of + * using func only. + */ + return ERR_PTR(-EADDRNOTAVAIL); + else if (count == 0) + /* + * We can return ENOENT earlier than when register the + * kprobe. + */ + return ERR_PTR(-ENOENT); + } + /* * local trace_kprobes are not added to dyn_event, so they are never * searched in find_trace_kprobe(). Therefore, there is no concern of diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index 02b432ae7513..850d9ecb6765 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -450,6 +450,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(BAD_MAXACT, "Invalid maxactive number"), \ C(MAXACT_TOO_BIG, "Maxactive is too big"), \ C(BAD_PROBE_ADDR, "Invalid probed address or symbol"), \ + C(NON_UNIQ_SYMBOL, "The symbol is not unique"), \ C(BAD_RETPROBE, "Retprobe address must be an function entry"), \ C(NO_TRACEPOINT, "Tracepoint is not found"), \ C(BAD_ADDR_SUFFIX, "Invalid probed address suffix"), \ diff --git a/kernel/workqueue.c b/kernel/workqueue.c index b9f053a5a5f0..a3522b70218d 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -2166,7 +2166,7 @@ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; - char id_buf[16]; + char id_buf[23]; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); @@ -4600,12 +4600,22 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) } cpus_read_unlock(); + /* for unbound pwq, flush the pwq_release_worker ensures that the + * pwq_release_workfn() completes before calling kfree(wq). + */ + if (ret) + kthread_flush_worker(pwq_release_worker); + return ret; enomem: if (wq->cpu_pwq) { - for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(wq->cpu_pwq, cpu)); + for_each_possible_cpu(cpu) { + struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); + + if (pwq) + kmem_cache_free(pwq_cache, pwq); + } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } @@ -5782,9 +5792,13 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND)) continue; + /* creating multiple pwqs breaks ordering guarantee */ - if (wq->flags & __WQ_ORDERED) - continue; + if (!list_empty(&wq->pwqs)) { + if (wq->flags & __WQ_ORDERED_EXPLICIT) + continue; + wq->flags &= ~__WQ_ORDERED; + } ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { diff --git a/lib/maple_tree.c b/lib/maple_tree.c index 0e00a84e8e8f..bb24d84a4922 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -5627,7 +5627,7 @@ int mas_expected_entries(struct ma_state *mas, unsigned long nr_entries) /* Internal nodes */ nr_nodes += DIV_ROUND_UP(nr_nodes, nonleaf_cap); /* Add working room for split (2 nodes) + new parents */ - mas_node_count(mas, nr_nodes + 3); + mas_node_count_gfp(mas, nr_nodes + 3, GFP_KERNEL); /* Detect if allocations run out */ mas->mas_flags |= MA_STATE_PREALLOC; diff --git a/lib/nlattr.c b/lib/nlattr.c index 7a2b6c38fd59..dc15e7888fc1 100644 --- a/lib/nlattr.c +++ b/lib/nlattr.c @@ -134,6 +134,7 @@ void nla_get_range_unsigned(const struct nla_policy *pt, range->max = U32_MAX; break; case NLA_U64: + case NLA_UINT: case NLA_MSECS: range->max = U64_MAX; break; @@ -183,6 +184,9 @@ static int nla_validate_range_unsigned(const struct nla_policy *pt, case NLA_U64: value = nla_get_u64(nla); break; + case NLA_UINT: + value = nla_get_uint(nla); + break; case NLA_MSECS: value = nla_get_u64(nla); break; @@ -248,6 +252,7 @@ void nla_get_range_signed(const struct nla_policy *pt, range->max = S32_MAX; break; case NLA_S64: + case NLA_SINT: range->min = S64_MIN; range->max = S64_MAX; break; @@ -295,6 +300,9 @@ static int nla_validate_int_range_signed(const struct nla_policy *pt, case NLA_S64: value = nla_get_s64(nla); break; + case NLA_SINT: + value = nla_get_sint(nla); + break; default: return -EINVAL; } @@ -320,6 +328,7 @@ static int nla_validate_int_range(const struct nla_policy *pt, case NLA_U16: case NLA_U32: case NLA_U64: + case NLA_UINT: case NLA_MSECS: case NLA_BINARY: case NLA_BE16: @@ -329,6 +338,7 @@ static int nla_validate_int_range(const struct nla_policy *pt, case NLA_S16: case NLA_S32: case NLA_S64: + case NLA_SINT: return nla_validate_int_range_signed(pt, nla, extack); default: WARN_ON(1); @@ -355,6 +365,9 @@ static int nla_validate_mask(const struct nla_policy *pt, case NLA_U64: value = nla_get_u64(nla); break; + case NLA_UINT: + value = nla_get_uint(nla); + break; case NLA_BE16: value = ntohs(nla_get_be16(nla)); break; @@ -433,6 +446,15 @@ static int validate_nla(const struct nlattr *nla, int maxtype, goto out_err; break; + case NLA_SINT: + case NLA_UINT: + if (attrlen != sizeof(u32) && attrlen != sizeof(u64)) { + NL_SET_ERR_MSG_ATTR_POL(extack, nla, pt, + "invalid attribute length"); + return -EINVAL; + } + break; + case NLA_BITFIELD32: if (attrlen != sizeof(struct nla_bitfield32)) goto out_err; diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 06959165e2f9..464eeb90d5ad 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -9,6 +9,7 @@ #include <linux/maple_tree.h> #include <linux/module.h> +#include <linux/rwsem.h> #define MTREE_ALLOC_MAX 0x2000000000000Ul #define CONFIG_MAPLE_SEARCH @@ -1841,17 +1842,21 @@ static noinline void __init check_forking(struct maple_tree *mt) void *val; MA_STATE(mas, mt, 0, 0); MA_STATE(newmas, mt, 0, 0); + struct rw_semaphore newmt_lock; + + init_rwsem(&newmt_lock); for (i = 0; i <= nr_entries; i++) mtree_store_range(mt, i*10, i*10 + 5, xa_mk_value(i), GFP_KERNEL); mt_set_non_kernel(99999); - mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE); + mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&newmt, &newmt_lock); newmas.tree = &newmt; mas_reset(&newmas); mas_reset(&mas); - mas_lock(&newmas); + down_write(&newmt_lock); mas.index = 0; mas.last = 0; if (mas_expected_entries(&newmas, nr_entries)) { @@ -1866,10 +1871,10 @@ static noinline void __init check_forking(struct maple_tree *mt) } rcu_read_unlock(); mas_destroy(&newmas); - mas_unlock(&newmas); mt_validate(&newmt); mt_set_non_kernel(0); - mtree_destroy(&newmt); + __mt_destroy(&newmt); + up_write(&newmt_lock); } static noinline void __init check_iteration(struct maple_tree *mt) @@ -1980,6 +1985,10 @@ static noinline void __init bench_forking(struct maple_tree *mt) void *val; MA_STATE(mas, mt, 0, 0); MA_STATE(newmas, mt, 0, 0); + struct rw_semaphore newmt_lock; + + init_rwsem(&newmt_lock); + mt_set_external_lock(&newmt, &newmt_lock); for (i = 0; i <= nr_entries; i++) mtree_store_range(mt, i*10, i*10 + 5, @@ -1994,7 +2003,7 @@ static noinline void __init bench_forking(struct maple_tree *mt) mas.index = 0; mas.last = 0; rcu_read_lock(); - mas_lock(&newmas); + down_write(&newmt_lock); if (mas_expected_entries(&newmas, nr_entries)) { printk("OOM!"); BUG_ON(1); @@ -2005,11 +2014,11 @@ static noinline void __init bench_forking(struct maple_tree *mt) mas_store(&newmas, val); } mas_destroy(&newmas); - mas_unlock(&newmas); rcu_read_unlock(); mt_validate(&newmt); mt_set_non_kernel(0); - mtree_destroy(&newmt); + __mt_destroy(&newmt); + up_write(&newmt_lock); } } #endif @@ -2616,6 +2625,10 @@ static noinline void __init check_dup_gaps(struct maple_tree *mt, void *tmp; MA_STATE(mas, mt, 0, 0); MA_STATE(newmas, &newmt, 0, 0); + struct rw_semaphore newmt_lock; + + init_rwsem(&newmt_lock); + mt_set_external_lock(&newmt, &newmt_lock); if (!zero_start) i = 1; @@ -2625,9 +2638,9 @@ static noinline void __init check_dup_gaps(struct maple_tree *mt, mtree_store_range(mt, i*10, (i+1)*10 - gap, xa_mk_value(i), GFP_KERNEL); - mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE); + mt_init_flags(&newmt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN); mt_set_non_kernel(99999); - mas_lock(&newmas); + down_write(&newmt_lock); ret = mas_expected_entries(&newmas, nr_entries); mt_set_non_kernel(0); MT_BUG_ON(mt, ret != 0); @@ -2640,9 +2653,9 @@ static noinline void __init check_dup_gaps(struct maple_tree *mt, } rcu_read_unlock(); mas_destroy(&newmas); - mas_unlock(&newmas); - mtree_destroy(&newmt); + __mt_destroy(&newmt); + up_write(&newmt_lock); } /* Duplicate many sizes of trees. Mainly to test expected entry values */ diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index b86ba7b0a921..f60e56150feb 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1208,6 +1208,8 @@ static int damon_sysfs_set_targets(struct damon_ctx *ctx, return 0; } +static bool damon_sysfs_schemes_regions_updating; + static void damon_sysfs_before_terminate(struct damon_ctx *ctx) { struct damon_target *t, *next; @@ -1219,8 +1221,10 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx) cmd = damon_sysfs_cmd_request.cmd; if (kdamond && ctx == kdamond->damon_ctx && (cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_REGIONS || - cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES)) { + cmd == DAMON_SYSFS_CMD_UPDATE_SCHEMES_TRIED_BYTES) && + damon_sysfs_schemes_regions_updating) { damon_sysfs_schemes_update_regions_stop(ctx); + damon_sysfs_schemes_regions_updating = false; mutex_unlock(&damon_sysfs_lock); } @@ -1340,7 +1344,6 @@ static int damon_sysfs_commit_input(struct damon_sysfs_kdamond *kdamond) static int damon_sysfs_cmd_request_callback(struct damon_ctx *c) { struct damon_sysfs_kdamond *kdamond; - static bool damon_sysfs_schemes_regions_updating; bool total_bytes_only = false; int err = 0; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 52d26072dfda..1301ba7b2c9a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -97,6 +97,7 @@ static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, unsigned long end); +static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static inline bool subpool_is_free(struct hugepage_subpool *spool) { @@ -267,6 +268,10 @@ void hugetlb_vma_lock_read(struct vm_area_struct *vma) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_read(&vma_lock->rw_sema); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + down_read(&resv_map->rw_sema); } } @@ -276,6 +281,10 @@ void hugetlb_vma_unlock_read(struct vm_area_struct *vma) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_read(&vma_lock->rw_sema); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + up_read(&resv_map->rw_sema); } } @@ -285,6 +294,10 @@ void hugetlb_vma_lock_write(struct vm_area_struct *vma) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; down_write(&vma_lock->rw_sema); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + down_write(&resv_map->rw_sema); } } @@ -294,17 +307,27 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; up_write(&vma_lock->rw_sema); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + up_write(&resv_map->rw_sema); } } int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { - struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; - if (!__vma_shareable_lock(vma)) - return 1; + if (__vma_shareable_lock(vma)) { + struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; - return down_write_trylock(&vma_lock->rw_sema); + return down_write_trylock(&vma_lock->rw_sema); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + return down_write_trylock(&resv_map->rw_sema); + } + + return 1; } void hugetlb_vma_assert_locked(struct vm_area_struct *vma) @@ -313,6 +336,10 @@ void hugetlb_vma_assert_locked(struct vm_area_struct *vma) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; lockdep_assert_held(&vma_lock->rw_sema); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + lockdep_assert_held(&resv_map->rw_sema); } } @@ -345,6 +372,11 @@ static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; __hugetlb_vma_unlock_write_put(vma_lock); + } else if (__vma_private_lock(vma)) { + struct resv_map *resv_map = vma_resv_map(vma); + + /* no free for anon vmas, but still need to unlock */ + up_write(&resv_map->rw_sema); } } @@ -1068,6 +1100,7 @@ struct resv_map *resv_map_alloc(void) kref_init(&resv_map->refs); spin_lock_init(&resv_map->lock); INIT_LIST_HEAD(&resv_map->regions); + init_rwsem(&resv_map->rw_sema); resv_map->adds_in_progress = 0; /* @@ -1138,8 +1171,7 @@ static void set_vma_resv_map(struct vm_area_struct *vma, struct resv_map *map) VM_BUG_ON_VMA(!is_vm_hugetlb_page(vma), vma); VM_BUG_ON_VMA(vma->vm_flags & VM_MAYSHARE, vma); - set_vma_private_data(vma, (get_vma_private_data(vma) & - HPAGE_RESV_MASK) | (unsigned long)map); + set_vma_private_data(vma, (unsigned long)map); } static void set_vma_resv_flags(struct vm_area_struct *vma, unsigned long flags) @@ -5274,9 +5306,9 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma, return len + old_addr - old_end; } -static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, - unsigned long start, unsigned long end, - struct page *ref_page, zap_flags_t zap_flags) +void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long start, unsigned long end, + struct page *ref_page, zap_flags_t zap_flags) { struct mm_struct *mm = vma->vm_mm; unsigned long address; @@ -5405,16 +5437,25 @@ static void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct tlb_flush_mmu_tlbonly(tlb); } -void __unmap_hugepage_range_final(struct mmu_gather *tlb, - struct vm_area_struct *vma, unsigned long start, - unsigned long end, struct page *ref_page, - zap_flags_t zap_flags) +void __hugetlb_zap_begin(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) { + if (!vma->vm_file) /* hugetlbfs_file_mmap error */ + return; + + adjust_range_if_pmd_sharing_possible(vma, start, end); hugetlb_vma_lock_write(vma); - i_mmap_lock_write(vma->vm_file->f_mapping); + if (vma->vm_file) + i_mmap_lock_write(vma->vm_file->f_mapping); +} - /* mmu notification performed in caller */ - __unmap_hugepage_range(tlb, vma, start, end, ref_page, zap_flags); +void __hugetlb_zap_end(struct vm_area_struct *vma, + struct zap_details *details) +{ + zap_flags_t zap_flags = details ? details->zap_flags : 0; + + if (!vma->vm_file) /* hugetlbfs_file_mmap error */ + return; if (zap_flags & ZAP_FLAG_UNMAP) { /* final unmap */ /* @@ -5427,11 +5468,12 @@ void __unmap_hugepage_range_final(struct mmu_gather *tlb, * someone else. */ __hugetlb_vma_unlock_write_free(vma); - i_mmap_unlock_write(vma->vm_file->f_mapping); } else { - i_mmap_unlock_write(vma->vm_file->f_mapping); hugetlb_vma_unlock_write(vma); } + + if (vma->vm_file) + i_mmap_unlock_write(vma->vm_file->f_mapping); } void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, @@ -6811,8 +6853,10 @@ out_err: */ if (chg >= 0 && add < 0) region_abort(resv_map, from, to, regions_needed); - if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) + if (vma && is_vma_resv_set(vma, HPAGE_RESV_OWNER)) { kref_put(&resv_map->refs, resv_map_release); + set_vma_resv_map(vma, NULL); + } return false; } diff --git a/mm/kasan/report.c b/mm/kasan/report.c index ca4b6ff080a6..6e3cb118d20e 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -621,7 +621,7 @@ void kasan_report_async(void) } #endif /* CONFIG_KASAN_HW_TAGS */ -#ifdef CONFIG_KASAN_INLINE +#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) /* * With CONFIG_KASAN_INLINE, accesses to bogus pointers (outside the high * canonical half of the address space) cause out-of-bounds shadow memory reads diff --git a/mm/memory.c b/mm/memory.c index 6c264d2f969c..517221f01303 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1683,7 +1683,7 @@ static void unmap_single_vma(struct mmu_gather *tlb, if (vma->vm_file) { zap_flags_t zap_flags = details ? details->zap_flags : 0; - __unmap_hugepage_range_final(tlb, vma, start, end, + __unmap_hugepage_range(tlb, vma, start, end, NULL, zap_flags); } } else @@ -1728,8 +1728,12 @@ void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas, start_addr, end_addr); mmu_notifier_invalidate_range_start(&range); do { - unmap_single_vma(tlb, vma, start_addr, end_addr, &details, + unsigned long start = start_addr; + unsigned long end = end_addr; + hugetlb_zap_begin(vma, &start, &end); + unmap_single_vma(tlb, vma, start, end, &details, mm_wr_locked); + hugetlb_zap_end(vma, &details); } while ((vma = mas_find(mas, tree_end - 1)) != NULL); mmu_notifier_invalidate_range_end(&range); } @@ -1753,9 +1757,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, lru_add_drain(); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address, end); - if (is_vm_hugetlb_page(vma)) - adjust_range_if_pmd_sharing_possible(vma, &range.start, - &range.end); + hugetlb_zap_begin(vma, &range.start, &range.end); tlb_gather_mmu(&tlb, vma->vm_mm); update_hiwater_rss(vma->vm_mm); mmu_notifier_invalidate_range_start(&range); @@ -1766,6 +1768,7 @@ void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, unmap_single_vma(&tlb, vma, address, end, details, false); mmu_notifier_invalidate_range_end(&range); tlb_finish_mmu(&tlb); + hugetlb_zap_end(vma, details); } /** diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f1b00d6ac7ee..29ebf1e7898c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1543,8 +1543,10 @@ SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, le * the home node for vmas we already updated before. */ old = vma_policy(vma); - if (!old) + if (!old) { + prev = vma; continue; + } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; diff --git a/mm/migrate.c b/mm/migrate.c index 2053b54556ca..06086dc9da28 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2162,6 +2162,7 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, const int __user *nodes, int __user *status, int flags) { + compat_uptr_t __user *compat_pages = (void __user *)pages; int current_node = NUMA_NO_NODE; LIST_HEAD(pagelist); int start, i; @@ -2174,8 +2175,17 @@ static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, int node; err = -EFAULT; - if (get_user(p, pages + i)) - goto out_flush; + if (in_compat_syscall()) { + compat_uptr_t cp; + + if (get_user(cp, compat_pages + i)) + goto out_flush; + + p = compat_ptr(cp); + } else { + if (get_user(p, pages + i)) + goto out_flush; + } if (get_user(node, nodes + i)) goto out_flush; diff --git a/mm/mmap.c b/mm/mmap.c index b56a7f0c9f85..9e018d8dd7d6 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -583,11 +583,12 @@ again: * dup_anon_vma() - Helper function to duplicate anon_vma * @dst: The destination VMA * @src: The source VMA + * @dup: Pointer to the destination VMA when successful. * * Returns: 0 on success. */ static inline int dup_anon_vma(struct vm_area_struct *dst, - struct vm_area_struct *src) + struct vm_area_struct *src, struct vm_area_struct **dup) { /* * Easily overlooked: when mprotect shifts the boundary, make sure the @@ -595,9 +596,15 @@ static inline int dup_anon_vma(struct vm_area_struct *dst, * anon pages imported. */ if (src->anon_vma && !dst->anon_vma) { + int ret; + vma_assert_write_locked(dst); dst->anon_vma = src->anon_vma; - return anon_vma_clone(dst, src); + ret = anon_vma_clone(dst, src); + if (ret) + return ret; + + *dup = dst; } return 0; @@ -624,6 +631,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *next) { + struct vm_area_struct *anon_dup = NULL; bool remove_next = false; struct vma_prepare vp; @@ -633,7 +641,7 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, remove_next = true; vma_start_write(next); - ret = dup_anon_vma(vma, next); + ret = dup_anon_vma(vma, next, &anon_dup); if (ret) return ret; } @@ -661,6 +669,8 @@ int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma, return 0; nomem: + if (anon_dup) + unlink_anon_vmas(anon_dup); return -ENOMEM; } @@ -860,6 +870,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, { struct vm_area_struct *curr, *next, *res; struct vm_area_struct *vma, *adjust, *remove, *remove2; + struct vm_area_struct *anon_dup = NULL; struct vma_prepare vp; pgoff_t vma_pgoff; int err = 0; @@ -927,18 +938,18 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_start_write(next); remove = next; /* case 1 */ vma_end = next->vm_end; - err = dup_anon_vma(prev, next); + err = dup_anon_vma(prev, next, &anon_dup); if (curr) { /* case 6 */ vma_start_write(curr); remove = curr; remove2 = next; if (!next->anon_vma) - err = dup_anon_vma(prev, curr); + err = dup_anon_vma(prev, curr, &anon_dup); } } else if (merge_prev) { /* case 2 */ if (curr) { vma_start_write(curr); - err = dup_anon_vma(prev, curr); + err = dup_anon_vma(prev, curr, &anon_dup); if (end == curr->vm_end) { /* case 7 */ remove = curr; } else { /* case 5 */ @@ -954,7 +965,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_end = addr; adjust = next; adj_start = -(prev->vm_end - addr); - err = dup_anon_vma(next, prev); + err = dup_anon_vma(next, prev, &anon_dup); } else { /* * Note that cases 3 and 8 are the ONLY ones where prev @@ -968,14 +979,14 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_pgoff = curr->vm_pgoff; vma_start_write(curr); remove = curr; - err = dup_anon_vma(next, curr); + err = dup_anon_vma(next, curr, &anon_dup); } } } /* Error in anon_vma clone. */ if (err) - return NULL; + goto anon_vma_fail; if (vma_start < vma->vm_start || vma_end > vma->vm_end) vma_expanded = true; @@ -988,7 +999,7 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, } if (vma_iter_prealloc(vmi, vma)) - return NULL; + goto prealloc_fail; init_multi_vma_prep(&vp, vma, adjust, remove, remove2); VM_WARN_ON(vp.anon_vma && adjust && adjust->anon_vma && @@ -1016,6 +1027,15 @@ struct vm_area_struct *vma_merge(struct vma_iterator *vmi, struct mm_struct *mm, vma_complete(&vp, vmi, mm); khugepaged_enter_vma(res, vm_flags); return res; + +prealloc_fail: + if (anon_dup) + unlink_anon_vmas(anon_dup); + +anon_vma_fail: + vma_iter_set(vmi, addr); + vma_iter_load(vmi); + return NULL; } /* @@ -3143,13 +3163,13 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags) if (!len) return 0; - if (mmap_write_lock_killable(mm)) - return -EINTR; - /* Until we need other flags, refuse anything except VM_EXEC. */ if ((flags & (~VM_EXEC)) != 0) return -EINVAL; + if (mmap_write_lock_killable(mm)) + return -EINTR; + ret = check_brk_limits(addr, len); if (ret) goto limits_failed; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 95546f376302..85741403948f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6475,6 +6475,7 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page, next_page = page; current_buddy = page + size; } + page = next_page; if (set_page_guard(zone, current_buddy, high, migratetype)) continue; @@ -6482,7 +6483,6 @@ static void break_down_buddy_pages(struct zone *zone, struct page *page, if (current_buddy != target) { add_to_free_list(current_buddy, zone, high, migratetype); set_buddy_order(current_buddy, high); - page = next_page; } } } diff --git a/mm/percpu.c b/mm/percpu.c index a7665de8485f..60ed078e4cd0 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2245,6 +2245,37 @@ static void pcpu_balance_workfn(struct work_struct *work) } /** + * pcpu_alloc_size - the size of the dynamic percpu area + * @ptr: pointer to the dynamic percpu area + * + * Returns the size of the @ptr allocation. This is undefined for statically + * defined percpu variables as there is no corresponding chunk->bound_map. + * + * RETURNS: + * The size of the dynamic percpu area. + * + * CONTEXT: + * Can be called from atomic context. + */ +size_t pcpu_alloc_size(void __percpu *ptr) +{ + struct pcpu_chunk *chunk; + unsigned long bit_off, end; + void *addr; + + if (!ptr) + return 0; + + addr = __pcpu_ptr_to_addr(ptr); + /* No pcpu_lock here: ptr has not been freed, so chunk is still alive */ + chunk = pcpu_chunk_addr_search(addr); + bit_off = (addr - chunk->base_addr) / PCPU_MIN_ALLOC_SIZE; + end = find_next_bit(chunk->bound_map, pcpu_chunk_map_bits(chunk), + bit_off + 1); + return (end - bit_off) * PCPU_MIN_ALLOC_SIZE; +} + +/** * free_percpu - free percpu area * @ptr: pointer to area to free * @@ -2267,12 +2298,10 @@ void free_percpu(void __percpu *ptr) kmemleak_free_percpu(ptr); addr = __pcpu_ptr_to_addr(ptr); - - spin_lock_irqsave(&pcpu_lock, flags); - chunk = pcpu_chunk_addr_search(addr); off = addr - chunk->base_addr; + spin_lock_irqsave(&pcpu_lock, flags); size = pcpu_free_area(chunk, off); pcpu_memcg_free_hook(chunk, off, size); diff --git a/mm/slab_common.c b/mm/slab_common.c index 8fda308e400d..9bbffe82d65a 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -895,10 +895,13 @@ void __init setup_kmalloc_cache_index_table(void) static unsigned int __kmalloc_minalign(void) { + unsigned int minalign = dma_get_cache_alignment(); + if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && is_swiotlb_allocated()) - return ARCH_KMALLOC_MINALIGN; - return dma_get_cache_alignment(); + minalign = ARCH_KMALLOC_MINALIGN; + + return max(minalign, arch_slab_minalign()); } void __init diff --git a/mm/zswap.c b/mm/zswap.c index 083c693602b8..37d2b1cb2ecb 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1383,8 +1383,8 @@ reject: shrink: pool = zswap_pool_last_get(); - if (pool) - queue_work(shrink_wq, &pool->shrink_work); + if (pool && !queue_work(shrink_wq, &pool->shrink_work)) + zswap_pool_put(pool); goto reject; } diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c index 466353b3dde4..54e7fb1a4ee5 100644 --- a/net/atm/atm_sysfs.c +++ b/net/atm/atm_sysfs.c @@ -116,8 +116,6 @@ static int atm_uevent(const struct device *cdev, struct kobj_uevent_env *env) return -ENODEV; adev = to_atm_dev(cdev); - if (!adev) - return -ENODEV; if (add_uevent_var(env, "NAME=%s%d", adev->type, adev->number)) return -ENOMEM; diff --git a/net/bluetooth/amp.c b/net/bluetooth/amp.c index 2134f92bd7ac..5d698f19868c 100644 --- a/net/bluetooth/amp.c +++ b/net/bluetooth/amp.c @@ -109,7 +109,7 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, struct hci_conn *hcon; u8 role = out ? HCI_ROLE_MASTER : HCI_ROLE_SLAVE; - hcon = hci_conn_add(hdev, AMP_LINK, dst, role); + hcon = hci_conn_add(hdev, AMP_LINK, dst, role, __next_handle(mgr)); if (!hcon) return NULL; @@ -117,7 +117,6 @@ struct hci_conn *phylink_add(struct hci_dev *hdev, struct amp_mgr *mgr, hcon->state = BT_CONNECT; hcon->attempt++; - hcon->handle = __next_handle(mgr); hcon->remote_id = remote_id; hcon->amp_mgr = amp_mgr_get(mgr); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 7a6f20338db8..2cee330188ce 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -153,6 +153,9 @@ static void hci_conn_cleanup(struct hci_conn *conn) hci_conn_hash_del(hdev, conn); + if (HCI_CONN_HANDLE_UNSET(conn->handle)) + ida_free(&hdev->unset_handle_ida, conn->handle); + if (conn->cleanup) conn->cleanup(conn); @@ -169,13 +172,11 @@ static void hci_conn_cleanup(struct hci_conn *conn) hdev->notify(hdev, HCI_NOTIFY_CONN_DEL); } - hci_conn_del_sysfs(conn); - debugfs_remove_recursive(conn->debugfs); - hci_dev_put(hdev); + hci_conn_del_sysfs(conn); - hci_conn_put(conn); + hci_dev_put(hdev); } static void hci_acl_create_connection(struct hci_conn *conn) @@ -759,6 +760,7 @@ static int terminate_big_sync(struct hci_dev *hdev, void *data) bt_dev_dbg(hdev, "big 0x%2.2x bis 0x%2.2x", d->big, d->bis); + hci_disable_per_advertising_sync(hdev, d->bis); hci_remove_ext_adv_instance_sync(hdev, d->bis, NULL); /* Only terminate BIG if it has been created */ @@ -814,6 +816,17 @@ static int big_terminate_sync(struct hci_dev *hdev, void *data) return 0; } +static void find_bis(struct hci_conn *conn, void *data) +{ + struct iso_list_data *d = data; + + /* Ignore if BIG doesn't match */ + if (d->big != conn->iso_qos.bcast.big) + return; + + d->count++; +} + static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *conn) { struct iso_list_data *d; @@ -825,10 +838,27 @@ static int hci_le_big_terminate(struct hci_dev *hdev, u8 big, struct hci_conn *c if (!d) return -ENOMEM; + memset(d, 0, sizeof(*d)); d->big = big; d->sync_handle = conn->sync_handle; - d->pa_sync_term = test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags); - d->big_sync_term = test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags); + + if (test_and_clear_bit(HCI_CONN_PA_SYNC, &conn->flags)) { + hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK, + HCI_CONN_PA_SYNC, d); + + if (!d->count) + d->pa_sync_term = true; + + d->count = 0; + } + + if (test_and_clear_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { + hci_conn_hash_list_flag(hdev, find_bis, ISO_LINK, + HCI_CONN_BIG_SYNC, d); + + if (!d->count) + d->big_sync_term = true; + } ret = hci_cmd_sync_queue(hdev, big_terminate_sync, d, terminate_big_destroy); @@ -864,12 +894,6 @@ static void bis_cleanup(struct hci_conn *conn) hci_le_terminate_big(hdev, conn); } else { - bis = hci_conn_hash_lookup_big_any_dst(hdev, - conn->iso_qos.bcast.big); - - if (bis) - return; - hci_le_big_terminate(hdev, conn->iso_qos.bcast.big, conn); } @@ -928,31 +952,18 @@ static void cis_cleanup(struct hci_conn *conn) hci_le_remove_cig(hdev, conn->iso_qos.ucast.cig); } -static u16 hci_conn_hash_alloc_unset(struct hci_dev *hdev) +static int hci_conn_hash_alloc_unset(struct hci_dev *hdev) { - struct hci_conn_hash *h = &hdev->conn_hash; - struct hci_conn *c; - u16 handle = HCI_CONN_HANDLE_MAX + 1; - - rcu_read_lock(); - - list_for_each_entry_rcu(c, &h->list, list) { - /* Find the first unused handle */ - if (handle == 0xffff || c->handle != handle) - break; - handle++; - } - rcu_read_unlock(); - - return handle; + return ida_alloc_range(&hdev->unset_handle_ida, HCI_CONN_HANDLE_MAX + 1, + U16_MAX, GFP_ATOMIC); } struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, - u8 role) + u8 role, u16 handle) { struct hci_conn *conn; - BT_DBG("%s dst %pMR", hdev->name, dst); + bt_dev_dbg(hdev, "dst %pMR handle 0x%4.4x", dst, handle); conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -960,7 +971,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, bacpy(&conn->dst, dst); bacpy(&conn->src, &hdev->bdaddr); - conn->handle = hci_conn_hash_alloc_unset(hdev); + conn->handle = handle; conn->hdev = hdev; conn->type = type; conn->role = role; @@ -973,6 +984,7 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, conn->rssi = HCI_RSSI_INVALID; conn->tx_power = HCI_TX_POWER_INVALID; conn->max_tx_power = HCI_TX_POWER_INVALID; + conn->sync_handle = HCI_SYNC_HANDLE_INVALID; set_bit(HCI_CONN_POWER_SAVE, &conn->flags); conn->disc_timeout = HCI_DISCONN_TIMEOUT; @@ -1044,6 +1056,20 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +struct hci_conn *hci_conn_add_unset(struct hci_dev *hdev, int type, + bdaddr_t *dst, u8 role) +{ + int handle; + + bt_dev_dbg(hdev, "dst %pMR", dst); + + handle = hci_conn_hash_alloc_unset(hdev); + if (unlikely(handle < 0)) + return NULL; + + return hci_conn_add(hdev, type, dst, role, handle); +} + static void hci_conn_cleanup_child(struct hci_conn *conn, u8 reason) { if (!reason) @@ -1247,6 +1273,12 @@ void hci_conn_failed(struct hci_conn *conn, u8 status) break; } + /* In case of BIG/PA sync failed, clear conn flags so that + * the conns will be correctly cleaned up by ISO layer + */ + test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags); + test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags); + conn->state = BT_CLOSED; hci_connect_cfm(conn, status); hci_conn_del(conn); @@ -1274,6 +1306,9 @@ u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle) if (conn->abort_reason) return conn->abort_reason; + if (HCI_CONN_HANDLE_UNSET(conn->handle)) + ida_free(&hdev->unset_handle_ida, conn->handle); + conn->handle = handle; return 0; @@ -1381,7 +1416,7 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, if (conn) { bacpy(&conn->dst, dst); } else { - conn = hci_conn_add(hdev, LE_LINK, dst, role); + conn = hci_conn_add_unset(hdev, LE_LINK, dst, role); if (!conn) return ERR_PTR(-ENOMEM); hci_conn_hold(conn); @@ -1486,6 +1521,18 @@ static int qos_set_bis(struct hci_dev *hdev, struct bt_iso_qos *qos) /* Allocate BIS if not set */ if (qos->bcast.bis == BT_ISO_QOS_BIS_UNSET) { + if (qos->bcast.big != BT_ISO_QOS_BIG_UNSET) { + conn = hci_conn_hash_lookup_big(hdev, qos->bcast.big); + + if (conn) { + /* If the BIG handle is already matched to an advertising + * handle, do not allocate a new one. + */ + qos->bcast.bis = conn->iso_qos.bcast.bis; + return 0; + } + } + /* Find an unused adv set to advertise BIS, skip instance 0x00 * since it is reserved as general purpose set. */ @@ -1546,7 +1593,7 @@ static struct hci_conn *hci_add_bis(struct hci_dev *hdev, bdaddr_t *dst, memcmp(conn->le_per_adv_data, base, base_len))) return ERR_PTR(-EADDRINUSE); - conn = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); + conn = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (!conn) return ERR_PTR(-ENOMEM); @@ -1590,7 +1637,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, BT_DBG("requesting refresh of dst_addr"); - conn = hci_conn_add(hdev, LE_LINK, dst, HCI_ROLE_MASTER); + conn = hci_conn_add_unset(hdev, LE_LINK, dst, HCI_ROLE_MASTER); if (!conn) return ERR_PTR(-ENOMEM); @@ -1627,9 +1674,18 @@ struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, return ERR_PTR(-EOPNOTSUPP); } + /* Reject outgoing connection to device with same BD ADDR against + * CVE-2020-26555 + */ + if (!bacmp(&hdev->bdaddr, dst)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + dst); + return ERR_PTR(-ECONNREFUSED); + } + acl = hci_conn_hash_lookup_ba(hdev, ACL_LINK, dst); if (!acl) { - acl = hci_conn_add(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); + acl = hci_conn_add_unset(hdev, ACL_LINK, dst, HCI_ROLE_MASTER); if (!acl) return ERR_PTR(-ENOMEM); } @@ -1689,7 +1745,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, sco = hci_conn_hash_lookup_ba(hdev, type, dst); if (!sco) { - sco = hci_conn_add(hdev, type, dst, HCI_ROLE_MASTER); + sco = hci_conn_add_unset(hdev, type, dst, HCI_ROLE_MASTER); if (!sco) { hci_conn_drop(acl); return ERR_PTR(-ENOMEM); @@ -1881,7 +1937,7 @@ struct hci_conn *hci_bind_cis(struct hci_dev *hdev, bdaddr_t *dst, cis = hci_conn_hash_lookup_cis(hdev, dst, dst_type, qos->ucast.cig, qos->ucast.cis); if (!cis) { - cis = hci_conn_add(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); + cis = hci_conn_add_unset(hdev, ISO_LINK, dst, HCI_ROLE_MASTER); if (!cis) return ERR_PTR(-ENOMEM); cis->cleanup = cis_cleanup; @@ -2130,7 +2186,7 @@ int hci_le_big_create_sync(struct hci_dev *hdev, struct hci_conn *hcon, } pdu; int err; - if (num_bis > sizeof(pdu.bis)) + if (num_bis < 0x01 || num_bis > sizeof(pdu.bis)) return -EINVAL; err = qos_set_big(hdev, qos); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 195aea2198a9..65601aa52e0d 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2535,6 +2535,8 @@ struct hci_dev *hci_alloc_dev_priv(int sizeof_priv) mutex_init(&hdev->lock); mutex_init(&hdev->req_lock); + ida_init(&hdev->unset_handle_ida); + INIT_LIST_HEAD(&hdev->mesh_pending); INIT_LIST_HEAD(&hdev->mgmt_pending); INIT_LIST_HEAD(&hdev->reject_list); @@ -2789,6 +2791,7 @@ void hci_release_dev(struct hci_dev *hdev) hci_codec_list_clear(&hdev->local_codecs); hci_dev_unlock(hdev); + ida_destroy(&hdev->unset_handle_ida); ida_simple_remove(&hci_index_ida, hdev->id); kfree_skb(hdev->sent_cmd); kfree_skb(hdev->recv_event); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 31d02b54eea1..0849e0dafa95 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -26,6 +26,8 @@ /* Bluetooth HCI event handling. */ #include <asm/unaligned.h> +#include <linux/crypto.h> +#include <crypto/algapi.h> #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> @@ -2333,8 +2335,8 @@ static void hci_cs_create_conn(struct hci_dev *hdev, __u8 status) } } else { if (!conn) { - conn = hci_conn_add(hdev, ACL_LINK, &cp->bdaddr, - HCI_ROLE_MASTER); + conn = hci_conn_add_unset(hdev, ACL_LINK, &cp->bdaddr, + HCI_ROLE_MASTER); if (!conn) bt_dev_err(hdev, "no memory for new connection"); } @@ -3149,8 +3151,8 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, void *data, hci_bdaddr_list_lookup_with_flags(&hdev->accept_list, &ev->bdaddr, BDADDR_BREDR)) { - conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, - HCI_ROLE_SLAVE); + conn = hci_conn_add_unset(hdev, ev->link_type, + &ev->bdaddr, HCI_ROLE_SLAVE); if (!conn) { bt_dev_err(hdev, "no memory for new conn"); goto unlock; @@ -3268,6 +3270,16 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "bdaddr %pMR type 0x%x", &ev->bdaddr, ev->link_type); + /* Reject incoming connection from device with same BD ADDR against + * CVE-2020-26555 + */ + if (hdev && !bacmp(&hdev->bdaddr, &ev->bdaddr)) { + bt_dev_dbg(hdev, "Reject connection with same BD_ADDR %pMR\n", + &ev->bdaddr); + hci_reject_conn(hdev, &ev->bdaddr); + return; + } + mask |= hci_proto_connect_ind(hdev, &ev->bdaddr, ev->link_type, &flags); @@ -3305,8 +3317,8 @@ static void hci_conn_request_evt(struct hci_dev *hdev, void *data, conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr); if (!conn) { - conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr, - HCI_ROLE_SLAVE); + conn = hci_conn_add_unset(hdev, ev->link_type, &ev->bdaddr, + HCI_ROLE_SLAVE); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); goto unlock; @@ -4742,6 +4754,15 @@ static void hci_link_key_notify_evt(struct hci_dev *hdev, void *data, if (!conn) goto unlock; + /* Ignore NULL link key against CVE-2020-26555 */ + if (!crypto_memneq(ev->link_key, ZERO_KEY, HCI_LINK_KEY_SIZE)) { + bt_dev_dbg(hdev, "Ignore NULL link key (ZERO KEY) for %pMR", + &ev->bdaddr); + hci_disconnect(conn, HCI_ERROR_AUTH_FAILURE); + hci_conn_drop(conn); + goto unlock; + } + hci_conn_hold(conn); conn->disc_timeout = HCI_DISCONN_TIMEOUT; hci_conn_drop(conn); @@ -5274,8 +5295,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * available, then do not declare that OOB data is * present. */ - if (!memcmp(data->rand256, ZERO_KEY, 16) || - !memcmp(data->hash256, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand256, ZERO_KEY, 16) || + !crypto_memneq(data->hash256, ZERO_KEY, 16)) return 0x00; return 0x02; @@ -5285,8 +5306,8 @@ static u8 bredr_oob_data_present(struct hci_conn *conn) * not supported by the hardware, then check that if * P-192 data values are present. */ - if (!memcmp(data->rand192, ZERO_KEY, 16) || - !memcmp(data->hash192, ZERO_KEY, 16)) + if (!crypto_memneq(data->rand192, ZERO_KEY, 16) || + !crypto_memneq(data->hash192, ZERO_KEY, 16)) return 0x00; return 0x01; @@ -5303,7 +5324,7 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; hci_conn_hold(conn); @@ -5550,7 +5571,7 @@ static void hci_simple_pair_complete_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn) + if (!conn || !hci_conn_ssp_enabled(conn)) goto unlock; /* Reset the authentication requirement to unknown */ @@ -5869,7 +5890,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; - conn = hci_conn_add(hdev, LE_LINK, bdaddr, role); + conn = hci_conn_add_unset(hdev, LE_LINK, bdaddr, role); if (!conn) { bt_dev_err(hdev, "no memory for new connection"); goto unlock; @@ -5931,17 +5952,11 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, conn->dst_type = ev_bdaddr_type(hdev, conn->dst_type, NULL); - if (handle > HCI_CONN_HANDLE_MAX) { - bt_dev_err(hdev, "Invalid handle: 0x%4.4x > 0x%4.4x", handle, - HCI_CONN_HANDLE_MAX); - status = HCI_ERROR_INVALID_PARAMETERS; - } - /* All connection failure handling is taken care of by the * hci_conn_failed function which is triggered by the HCI * request completion callbacks used for connecting. */ - if (status) + if (status || hci_conn_set_handle(conn, handle)) goto unlock; /* Drop the connection if it has been aborted */ @@ -5965,7 +5980,6 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, mgmt_device_connected(hdev, conn, NULL, 0); conn->sec_level = BT_SECURITY_LOW; - conn->handle = handle; conn->state = BT_CONFIG; /* Store current advertising instance as connection advertising instance @@ -6582,7 +6596,7 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data, struct hci_ev_le_pa_sync_established *ev = data; int mask = hdev->link_mode; __u8 flags = 0; - struct hci_conn *bis; + struct hci_conn *pa_sync; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6599,20 +6613,19 @@ static void hci_le_pa_sync_estabilished_evt(struct hci_dev *hdev, void *data, if (!(flags & HCI_PROTO_DEFER)) goto unlock; - /* Add connection to indicate the PA sync event */ - bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, - HCI_ROLE_SLAVE); + if (ev->status) { + /* Add connection to indicate the failed PA sync event */ + pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); - if (!bis) - goto unlock; + if (!pa_sync) + goto unlock; - if (ev->status) - set_bit(HCI_CONN_PA_SYNC_FAILED, &bis->flags); - else - set_bit(HCI_CONN_PA_SYNC, &bis->flags); + set_bit(HCI_CONN_PA_SYNC_FAILED, &pa_sync->flags); - /* Notify connection to iso layer */ - hci_connect_cfm(bis, ev->status); + /* Notify iso layer */ + hci_connect_cfm(pa_sync, ev->status); + } unlock: hci_dev_unlock(hdev); @@ -6999,12 +7012,12 @@ static void hci_le_cis_req_evt(struct hci_dev *hdev, void *data, cis = hci_conn_hash_lookup_handle(hdev, cis_handle); if (!cis) { - cis = hci_conn_add(hdev, ISO_LINK, &acl->dst, HCI_ROLE_SLAVE); + cis = hci_conn_add(hdev, ISO_LINK, &acl->dst, HCI_ROLE_SLAVE, + cis_handle); if (!cis) { hci_le_reject_cis(hdev, ev->cis_handle); goto unlock; } - cis->handle = cis_handle; } cis->iso_qos.ucast.cig = ev->cig_id; @@ -7021,6 +7034,14 @@ unlock: hci_dev_unlock(hdev); } +static int hci_iso_term_big_sync(struct hci_dev *hdev, void *data) +{ + u8 handle = PTR_UINT(data); + + return hci_le_terminate_big_sync(hdev, handle, + HCI_ERROR_LOCAL_HOST_TERM); +} + static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, struct sk_buff *skb) { @@ -7065,16 +7086,17 @@ static void hci_le_create_big_complete_evt(struct hci_dev *hdev, void *data, rcu_read_lock(); } + rcu_read_unlock(); + if (!ev->status && !i) /* If no BISes have been connected for the BIG, * terminate. This is in case all bound connections * have been closed before the BIG creation * has completed. */ - hci_le_terminate_big_sync(hdev, ev->handle, - HCI_ERROR_LOCAL_HOST_TERM); + hci_cmd_sync_queue(hdev, hci_iso_term_big_sync, + UINT_PTR(ev->handle), NULL); - rcu_read_unlock(); hci_dev_unlock(hdev); } @@ -7083,7 +7105,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_big_sync_estabilished *ev = data; struct hci_conn *bis; - struct hci_conn *pa_sync; int i; bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -7094,15 +7115,6 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, hci_dev_lock(hdev); - if (!ev->status) { - pa_sync = hci_conn_hash_lookup_pa_sync(hdev, ev->handle); - if (pa_sync) - /* Also mark the BIG sync established event on the - * associated PA sync hcon - */ - set_bit(HCI_CONN_BIG_SYNC, &pa_sync->flags); - } - for (i = 0; i < ev->num_bis; i++) { u16 handle = le16_to_cpu(ev->bis[i]); __le32 interval; @@ -7110,10 +7122,9 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis = hci_conn_hash_lookup_handle(hdev, handle); if (!bis) { bis = hci_conn_add(hdev, ISO_LINK, BDADDR_ANY, - HCI_ROLE_SLAVE); + HCI_ROLE_SLAVE, handle); if (!bis) continue; - bis->handle = handle; } if (ev->status != 0x42) @@ -7156,15 +7167,42 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data, struct hci_evt_le_big_info_adv_report *ev = data; int mask = hdev->link_mode; __u8 flags = 0; + struct hci_conn *pa_sync; bt_dev_dbg(hdev, "sync_handle 0x%4.4x", le16_to_cpu(ev->sync_handle)); hci_dev_lock(hdev); mask |= hci_proto_connect_ind(hdev, BDADDR_ANY, ISO_LINK, &flags); - if (!(mask & HCI_LM_ACCEPT)) + if (!(mask & HCI_LM_ACCEPT)) { hci_le_pa_term_sync(hdev, ev->sync_handle); + goto unlock; + } + if (!(flags & HCI_PROTO_DEFER)) + goto unlock; + + pa_sync = hci_conn_hash_lookup_pa_sync_handle + (hdev, + le16_to_cpu(ev->sync_handle)); + + if (pa_sync) + goto unlock; + + /* Add connection to indicate the PA sync event */ + pa_sync = hci_conn_add_unset(hdev, ISO_LINK, BDADDR_ANY, + HCI_ROLE_SLAVE); + + if (!pa_sync) + goto unlock; + + pa_sync->sync_handle = le16_to_cpu(ev->sync_handle); + set_bit(HCI_CONN_PA_SYNC, &pa_sync->flags); + + /* Notify iso layer */ + hci_connect_cfm(pa_sync, 0x00); + +unlock: hci_dev_unlock(hdev); } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 5e4f718073b7..3e7cd330d731 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -488,7 +488,8 @@ static struct sk_buff *create_monitor_event(struct hci_dev *hdev, int event) ni->type = hdev->dev_type; ni->bus = hdev->bus; bacpy(&ni->bdaddr, &hdev->bdaddr); - memcpy(ni->name, hdev->name, 8); + memcpy_and_pad(ni->name, sizeof(ni->name), hdev->name, + strnlen(hdev->name, sizeof(ni->name)), '\0'); opcode = cpu_to_le16(HCI_MON_NEW_INDEX); break; diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index d06e07a0ea5a..d85a7091a116 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -152,7 +152,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, struct sk_buff *skb; int err = 0; - bt_dev_dbg(hdev, "Opcode 0x%4x", opcode); + bt_dev_dbg(hdev, "Opcode 0x%4.4x", opcode); hci_req_init(&req, hdev); @@ -248,7 +248,7 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { if (!event) - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + bt_dev_err(hdev, "Opcode 0x%4.4x failed: %ld", opcode, PTR_ERR(skb)); return PTR_ERR(skb); } @@ -1312,7 +1312,7 @@ int hci_start_ext_adv_sync(struct hci_dev *hdev, u8 instance) return hci_enable_ext_advertising_sync(hdev, instance); } -static int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) +int hci_disable_per_advertising_sync(struct hci_dev *hdev, u8 instance) { struct hci_cp_le_set_per_adv_enable cp; struct adv_info *adv = NULL; @@ -4264,12 +4264,12 @@ static int hci_le_set_host_feature_sync(struct hci_dev *hdev) { struct hci_cp_le_set_host_feature cp; - if (!iso_capable(hdev)) + if (!cis_capable(hdev)) return 0; memset(&cp, 0, sizeof(cp)); - /* Isochronous Channels (Host Support) */ + /* Connected Isochronous Channels (Host Support) */ cp.bit_number = 32; cp.bit_value = 1; @@ -5232,6 +5232,17 @@ static int hci_disconnect_sync(struct hci_dev *hdev, struct hci_conn *conn, if (conn->type == AMP_LINK) return hci_disconnect_phy_link_sync(hdev, conn->handle, reason); + if (test_bit(HCI_CONN_BIG_CREATED, &conn->flags)) { + /* This is a BIS connection, hci_conn_del will + * do the necessary cleanup. + */ + hci_dev_lock(hdev); + hci_conn_failed(conn, reason); + hci_dev_unlock(hdev); + + return 0; + } + memset(&cp, 0, sizeof(cp)); cp.handle = cpu_to_le16(conn->handle); cp.reason = reason; @@ -5369,6 +5380,7 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) { int err = 0; u16 handle = conn->handle; + bool disconnect = false; struct hci_conn *c; switch (conn->state) { @@ -5383,40 +5395,16 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) err = hci_reject_conn_sync(hdev, conn, reason); break; case BT_OPEN: - hci_dev_lock(hdev); - - /* Cleanup bis or pa sync connections */ - if (test_and_clear_bit(HCI_CONN_BIG_SYNC_FAILED, &conn->flags) || - test_and_clear_bit(HCI_CONN_PA_SYNC_FAILED, &conn->flags)) { - hci_conn_failed(conn, reason); - } else if (test_bit(HCI_CONN_PA_SYNC, &conn->flags) || - test_bit(HCI_CONN_BIG_SYNC, &conn->flags)) { - conn->state = BT_CLOSED; - hci_disconn_cfm(conn, reason); - hci_conn_del(conn); - } - - hci_dev_unlock(hdev); - return 0; case BT_BOUND: - hci_dev_lock(hdev); - hci_conn_failed(conn, reason); - hci_dev_unlock(hdev); - return 0; + break; default: - hci_dev_lock(hdev); - conn->state = BT_CLOSED; - hci_disconn_cfm(conn, reason); - hci_conn_del(conn); - hci_dev_unlock(hdev); - return 0; + disconnect = true; + break; } hci_dev_lock(hdev); - /* Check if the connection hasn't been cleanup while waiting - * commands to complete. - */ + /* Check if the connection has been cleaned up concurrently */ c = hci_conn_hash_lookup_handle(hdev, handle); if (!c || c != conn) { err = 0; @@ -5428,7 +5416,13 @@ int hci_abort_conn_sync(struct hci_dev *hdev, struct hci_conn *conn, u8 reason) * or in case of LE it was still scanning so it can be cleanup * safely. */ - hci_conn_failed(conn, reason); + if (disconnect) { + conn->state = BT_CLOSED; + hci_disconn_cfm(conn, reason); + hci_conn_del(conn); + } else { + hci_conn_failed(conn, reason); + } unlock: hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 15b33579007c..367e32fe30eb 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -35,7 +35,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); conn->dev.type = &bt_link; conn->dev.class = &bt_class; @@ -48,27 +48,30 @@ void hci_conn_add_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - BT_DBG("conn %p", conn); + bt_dev_dbg(hdev, "conn %p", conn); if (device_is_registered(&conn->dev)) return; dev_set_name(&conn->dev, "%s:%d", hdev->name, conn->handle); - if (device_add(&conn->dev) < 0) { + if (device_add(&conn->dev) < 0) bt_dev_err(hdev, "failed to register connection device"); - return; - } - - hci_dev_hold(hdev); } void hci_conn_del_sysfs(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; - if (!device_is_registered(&conn->dev)) + bt_dev_dbg(hdev, "conn %p", conn); + + if (!device_is_registered(&conn->dev)) { + /* If device_add() has *not* succeeded, use *only* put_device() + * to drop the reference count. + */ + put_device(&conn->dev); return; + } while (1) { struct device *dev; @@ -80,9 +83,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn) put_device(dev); } - device_del(&conn->dev); - - hci_dev_put(hdev); + device_unregister(&conn->dev); } static void bt_host_release(struct device *dev) diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 71248163ce9a..07b80e97aead 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -14,6 +14,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/iso.h> +#include "eir.h" static const struct proto_ops iso_sock_ops; @@ -47,6 +48,7 @@ static void iso_sock_kill(struct sock *sk); #define EIR_SERVICE_DATA_LENGTH 4 #define BASE_MAX_LENGTH (HCI_MAX_PER_AD_LENGTH - EIR_SERVICE_DATA_LENGTH) +#define EIR_BAA_SERVICE_UUID 0x1851 /* iso_pinfo flags values */ enum { @@ -77,6 +79,7 @@ static struct bt_iso_qos default_qos; static bool check_ucast_qos(struct bt_iso_qos *qos); static bool check_bcast_qos(struct bt_iso_qos *qos); static bool iso_match_sid(struct sock *sk, void *data); +static bool iso_match_sync_handle(struct sock *sk, void *data); static void iso_sock_disconn(struct sock *sk); /* ---- ISO timers ---- */ @@ -789,8 +792,7 @@ static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr, BT_DBG("sk %p bc_sid %u bc_num_bis %u", sk, sa->iso_bc->bc_sid, sa->iso_bc->bc_num_bis); - if (addr_len > sizeof(*sa) + sizeof(*sa->iso_bc) || - sa->iso_bc->bc_num_bis < 0x01 || sa->iso_bc->bc_num_bis > 0x1f) + if (addr_len > sizeof(*sa) + sizeof(*sa->iso_bc)) return -EINVAL; bacpy(&iso_pi(sk)->dst, &sa->iso_bc->bc_bdaddr); @@ -1202,7 +1204,6 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, test_bit(HCI_CONN_PA_SYNC, &pi->conn->hcon->flags)) { iso_conn_big_sync(sk); sk->sk_state = BT_LISTEN; - set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } else { iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; @@ -1461,6 +1462,8 @@ static int iso_sock_getsockopt(struct socket *sock, int level, int optname, len = min_t(unsigned int, len, base_len); if (copy_to_user(optval, base, len)) err = -EFAULT; + if (put_user(len, optlen)) + err = -EFAULT; break; @@ -1579,6 +1582,7 @@ static void iso_conn_ready(struct iso_conn *conn) struct sock *sk = conn->sk; struct hci_ev_le_big_sync_estabilished *ev = NULL; struct hci_ev_le_pa_sync_established *ev2 = NULL; + struct hci_evt_le_big_info_adv_report *ev3 = NULL; struct hci_conn *hcon; BT_DBG("conn %p", conn); @@ -1603,14 +1607,20 @@ static void iso_conn_ready(struct iso_conn *conn) parent = iso_get_sock_listen(&hcon->src, &hcon->dst, iso_match_big, ev); - } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags) || - test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { + } else if (test_bit(HCI_CONN_PA_SYNC_FAILED, &hcon->flags)) { ev2 = hci_recv_event_data(hcon->hdev, HCI_EV_LE_PA_SYNC_ESTABLISHED); if (ev2) parent = iso_get_sock_listen(&hcon->src, &hcon->dst, iso_match_sid, ev2); + } else if (test_bit(HCI_CONN_PA_SYNC, &hcon->flags)) { + ev3 = hci_recv_event_data(hcon->hdev, + HCI_EVT_LE_BIG_INFO_ADV_REPORT); + if (ev3) + parent = iso_get_sock_listen(&hcon->src, + &hcon->dst, + iso_match_sync_handle, ev3); } if (!parent) @@ -1650,11 +1660,13 @@ static void iso_conn_ready(struct iso_conn *conn) hcon->sync_handle = iso_pi(parent)->sync_handle; } - if (ev2 && !ev2->status) { - iso_pi(sk)->sync_handle = iso_pi(parent)->sync_handle; + if (ev3) { iso_pi(sk)->qos = iso_pi(parent)->qos; + iso_pi(sk)->qos.bcast.encryption = ev3->encryption; + hcon->iso_qos = iso_pi(sk)->qos; iso_pi(sk)->bc_num_bis = iso_pi(parent)->bc_num_bis; memcpy(iso_pi(sk)->bc_bis, iso_pi(parent)->bc_bis, ISO_MAX_NUM_BIS); + set_bit(BT_SK_PA_SYNC, &iso_pi(sk)->flags); } bacpy(&iso_pi(sk)->dst, &hcon->dst); @@ -1774,12 +1786,16 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) ev3 = hci_recv_event_data(hdev, HCI_EV_LE_PER_ADV_REPORT); if (ev3) { + size_t base_len = ev3->length; + u8 *base; + sk = iso_get_sock_listen(&hdev->bdaddr, bdaddr, iso_match_sync_handle_pa_report, ev3); - - if (sk) { - memcpy(iso_pi(sk)->base, ev3->data, ev3->length); - iso_pi(sk)->base_len = ev3->length; + base = eir_get_service_data(ev3->data, ev3->length, + EIR_BAA_SERVICE_UUID, &base_len); + if (base && sk && base_len <= sizeof(iso_pi(sk)->base)) { + memcpy(iso_pi(sk)->base, base, base_len); + iso_pi(sk)->base_len = base_len; } } else { sk = iso_get_sock_listen(&hdev->bdaddr, BDADDR_ANY, NULL, NULL); diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c index abbafa6194ca..630e3023273b 100644 --- a/net/bluetooth/msft.c +++ b/net/bluetooth/msft.c @@ -150,10 +150,7 @@ static bool read_supported_features(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { - if (!skb) - skb = ERR_PTR(-EIO); - + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to read MSFT supported features (%ld)", PTR_ERR(skb)); return false; @@ -353,7 +350,7 @@ static void msft_remove_addr_filters_sync(struct hci_dev *hdev, u8 handle) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { kfree(address_filter); continue; } @@ -442,11 +439,8 @@ static int msft_remove_monitor_sync(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { - if (!skb) - return -EIO; + if (IS_ERR(skb)) return PTR_ERR(skb); - } return msft_le_cancel_monitor_advertisement_cb(hdev, hdev->msft_opcode, monitor, skb); @@ -559,7 +553,7 @@ static int msft_add_monitor_sync(struct hci_dev *hdev, skb = __hci_cmd_sync(hdev, hdev->msft_opcode, total_size, cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { err = PTR_ERR(skb); goto out_free; } @@ -740,10 +734,10 @@ static int msft_cancel_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, sizeof(cp), &cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { bt_dev_err(hdev, "MSFT: Failed to cancel address (%pMR) filter", &address_filter->bdaddr); - err = -EIO; + err = PTR_ERR(skb); goto done; } kfree_skb(skb); @@ -893,7 +887,7 @@ static int msft_add_address_filter_sync(struct hci_dev *hdev, void *data) skb = __hci_cmd_sync(hdev, hdev->msft_opcode, size, cp, HCI_CMD_TIMEOUT); - if (IS_ERR_OR_NULL(skb)) { + if (IS_ERR(skb)) { bt_dev_err(hdev, "Failed to enable address %pMR filter", &address_filter->bdaddr); skb = NULL; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 033034d68f1f..6adcb45bca75 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -486,11 +486,11 @@ static unsigned int br_nf_pre_routing(void *priv, struct brnf_net *brnet; if (unlikely(!pskb_may_pull(skb, len))) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0); p = br_port_get_rcu(state->in); if (p == NULL) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); br = p->br; brnet = net_generic(state->net, brnf_net_id); @@ -501,7 +501,7 @@ static unsigned int br_nf_pre_routing(void *priv, return NF_ACCEPT; if (!ipv6_mod_enabled()) { pr_warn_once("Module ipv6 is disabled, so call_ip6tables is not supported."); - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IPV6DISABLED, 0); } nf_bridge_pull_encap_header_rcsum(skb); @@ -518,12 +518,12 @@ static unsigned int br_nf_pre_routing(void *priv, nf_bridge_pull_encap_header_rcsum(skb); if (br_validate_ipv4(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); if (!nf_bridge_alloc(skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); if (!setup_pre_routing(skb, state->net)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge = nf_bridge_info_get(skb); nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; @@ -570,18 +570,12 @@ static int br_nf_forward_finish(struct net *net, struct sock *sk, struct sk_buff } -/* This is the 'purely bridged' case. For IP, we pass the packet to - * netfilter with indev and outdev set to the bridge device, - * but we are still able to filter on the 'real' indev/outdev - * because of the physdev module. For ARP, indev and outdev are the - * bridge ports. */ -static unsigned int br_nf_forward_ip(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) +static unsigned int br_nf_forward_ip(struct sk_buff *skb, + const struct nf_hook_state *state, + u8 pf) { struct nf_bridge_info *nf_bridge; struct net_device *parent; - u_int8_t pf; nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) @@ -590,24 +584,15 @@ static unsigned int br_nf_forward_ip(void *priv, /* Need exclusive nf_bridge_info since we might have multiple * different physoutdevs. */ if (!nf_bridge_unshare(skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); nf_bridge = nf_bridge_info_get(skb); if (!nf_bridge) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); parent = bridge_parent(state->out); if (!parent) - return NF_DROP; - - if (IS_IP(skb) || is_vlan_ip(skb, state->net) || - is_pppoe_ip(skb, state->net)) - pf = NFPROTO_IPV4; - else if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || - is_pppoe_ipv6(skb, state->net)) - pf = NFPROTO_IPV6; - else - return NF_ACCEPT; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge_pull_encap_header(skb); @@ -618,21 +603,20 @@ static unsigned int br_nf_forward_ip(void *priv, if (pf == NFPROTO_IPV4) { if (br_validate_ipv4(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); IPCB(skb)->frag_max_size = nf_bridge->frag_max_size; - } - - if (pf == NFPROTO_IPV6) { + skb->protocol = htons(ETH_P_IP); + } else if (pf == NFPROTO_IPV6) { if (br_validate_ipv6(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size; + skb->protocol = htons(ETH_P_IPV6); + } else { + WARN_ON_ONCE(1); + return NF_DROP; } nf_bridge->physoutdev = skb->dev; - if (pf == NFPROTO_IPV4) - skb->protocol = htons(ETH_P_IP); - else - skb->protocol = htons(ETH_P_IPV6); NF_HOOK(pf, NF_INET_FORWARD, state->net, NULL, skb, brnf_get_logical_dev(skb, state->in, state->net), @@ -641,8 +625,7 @@ static unsigned int br_nf_forward_ip(void *priv, return NF_STOLEN; } -static unsigned int br_nf_forward_arp(void *priv, - struct sk_buff *skb, +static unsigned int br_nf_forward_arp(struct sk_buff *skb, const struct nf_hook_state *state) { struct net_bridge_port *p; @@ -659,14 +642,11 @@ static unsigned int br_nf_forward_arp(void *priv, if (!brnet->call_arptables && !br_opt_get(br, BROPT_NF_CALL_ARPTABLES)) return NF_ACCEPT; - if (!IS_ARP(skb)) { - if (!is_vlan_arp(skb, state->net)) - return NF_ACCEPT; + if (is_vlan_arp(skb, state->net)) nf_bridge_pull_encap_header(skb); - } if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_PKT_TOO_SMALL, 0); if (arp_hdr(skb)->ar_pln != 4) { if (is_vlan_arp(skb, state->net)) @@ -680,6 +660,28 @@ static unsigned int br_nf_forward_arp(void *priv, return NF_STOLEN; } +/* This is the 'purely bridged' case. For IP, we pass the packet to + * netfilter with indev and outdev set to the bridge device, + * but we are still able to filter on the 'real' indev/outdev + * because of the physdev module. For ARP, indev and outdev are the + * bridge ports. + */ +static unsigned int br_nf_forward(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + if (IS_IP(skb) || is_vlan_ip(skb, state->net) || + is_pppoe_ip(skb, state->net)) + return br_nf_forward_ip(skb, state, NFPROTO_IPV4); + if (IS_IPV6(skb) || is_vlan_ipv6(skb, state->net) || + is_pppoe_ipv6(skb, state->net)) + return br_nf_forward_ip(skb, state, NFPROTO_IPV6); + if (IS_ARP(skb) || is_vlan_arp(skb, state->net)) + return br_nf_forward_arp(skb, state); + + return NF_ACCEPT; +} + static int br_nf_push_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) { struct brnf_frag_data *data; @@ -831,7 +833,7 @@ static unsigned int br_nf_post_routing(void *priv, return NF_ACCEPT; if (!realoutdev) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); if (IS_IP(skb) || is_vlan_ip(skb, state->net) || is_pppoe_ip(skb, state->net)) @@ -937,13 +939,7 @@ static const struct nf_hook_ops br_nf_ops[] = { .priority = NF_BR_PRI_BRNF, }, { - .hook = br_nf_forward_ip, - .pf = NFPROTO_BRIDGE, - .hooknum = NF_BR_FORWARD, - .priority = NF_BR_PRI_BRNF - 1, - }, - { - .hook = br_nf_forward_arp, + .hook = br_nf_forward, .pf = NFPROTO_BRIDGE, .hooknum = NF_BR_FORWARD, .priority = NF_BR_PRI_BRNF, diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c index 550039dfc31a..2e24a743f917 100644 --- a/net/bridge/br_netfilter_ipv6.c +++ b/net/bridge/br_netfilter_ipv6.c @@ -161,13 +161,13 @@ unsigned int br_nf_pre_routing_ipv6(void *priv, struct nf_bridge_info *nf_bridge; if (br_validate_ipv6(state->net, skb)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_IP_INHDR, 0); nf_bridge = nf_bridge_alloc(skb); if (!nf_bridge) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_NOMEM, 0); if (!setup_pre_routing(skb, state->net)) - return NF_DROP; + return NF_DROP_REASON(skb, SKB_DROP_REASON_DEV_READY, 0); nf_bridge = nf_bridge_info_get(skb); nf_bridge->ipv6_daddr = ipv6_hdr(skb)->daddr; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 10a41cd9c523..3c8b78d9c4d1 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -459,8 +459,8 @@ int ceph_tcp_connect(struct ceph_connection *con) set_sock_callbacks(sock, con); con_sock_state_connecting(con); - ret = sock->ops->connect(sock, (struct sockaddr *)&ss, sizeof(ss), - O_NONBLOCK); + ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss), + O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", ceph_pr_addr(&con->peer_addr), diff --git a/net/core/dev.c b/net/core/dev.c index 97e7b9833db9..0d548431f3fa 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -345,7 +345,6 @@ int netdev_name_node_alt_create(struct net_device *dev, const char *name) static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) { list_del(&name_node->list); - netdev_name_node_del(name_node); kfree(name_node->name); netdev_name_node_free(name_node); } @@ -364,6 +363,8 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) if (name_node == dev->name_node || name_node->dev != dev) return -EINVAL; + netdev_name_node_del(name_node); + synchronize_rcu(); __netdev_name_node_alt_destroy(name_node); return 0; @@ -380,6 +381,7 @@ static void netdev_name_node_alt_flush(struct net_device *dev) /* Device list insertion */ static void list_netdevice(struct net_device *dev) { + struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); @@ -390,6 +392,10 @@ static void list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock(&dev_base_lock); + + netdev_for_each_altname(dev, name_node) + netdev_name_node_add(net, name_node); + /* We reserved the ifindex, this can't fail */ WARN_ON(xa_store(&net->dev_by_index, dev->ifindex, dev, GFP_KERNEL)); @@ -401,12 +407,16 @@ static void list_netdevice(struct net_device *dev) */ static void unlist_netdevice(struct net_device *dev, bool lock) { + struct netdev_name_node *name_node; struct net *net = dev_net(dev); ASSERT_RTNL(); xa_erase(&net->dev_by_index, dev->ifindex); + netdev_for_each_altname(dev, name_node) + netdev_name_node_del(name_node); + /* Unlink dev from the device chain */ if (lock) write_lock(&dev_base_lock); @@ -1047,7 +1057,7 @@ EXPORT_SYMBOL(dev_valid_name); * __dev_alloc_name - allocate a name for a device * @net: network namespace to allocate the device name in * @name: name format string - * @buf: scratch buffer and result name string + * @res: result name string * * Passed a format string - eg "lt%d" it will try and find a suitable * id. It scans list of devices to build up a free map, then chooses @@ -1058,83 +1068,77 @@ EXPORT_SYMBOL(dev_valid_name); * Returns the number of the unit assigned or a negative errno code. */ -static int __dev_alloc_name(struct net *net, const char *name, char *buf) +static int __dev_alloc_name(struct net *net, const char *name, char *res) { int i = 0; const char *p; const int max_netdevices = 8*PAGE_SIZE; unsigned long *inuse; struct net_device *d; + char buf[IFNAMSIZ]; - if (!dev_valid_name(name)) - return -EINVAL; - + /* Verify the string as this thing may have come from the user. + * There must be one "%d" and no other "%" characters. + */ p = strchr(name, '%'); - if (p) { - /* - * Verify the string as this thing may have come from - * the user. There must be either one "%d" and no other "%" - * characters. - */ - if (p[1] != 'd' || strchr(p + 2, '%')) - return -EINVAL; + if (!p || p[1] != 'd' || strchr(p + 2, '%')) + return -EINVAL; - /* Use one page as a bit array of possible slots */ - inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); - if (!inuse) - return -ENOMEM; + /* Use one page as a bit array of possible slots */ + inuse = bitmap_zalloc(max_netdevices, GFP_ATOMIC); + if (!inuse) + return -ENOMEM; - for_each_netdev(net, d) { - struct netdev_name_node *name_node; - list_for_each_entry(name_node, &d->name_node->list, list) { - if (!sscanf(name_node->name, name, &i)) - continue; - if (i < 0 || i >= max_netdevices) - continue; + for_each_netdev(net, d) { + struct netdev_name_node *name_node; - /* avoid cases where sscanf is not exact inverse of printf */ - snprintf(buf, IFNAMSIZ, name, i); - if (!strncmp(buf, name_node->name, IFNAMSIZ)) - __set_bit(i, inuse); - } - if (!sscanf(d->name, name, &i)) + netdev_for_each_altname(d, name_node) { + if (!sscanf(name_node->name, name, &i)) continue; if (i < 0 || i >= max_netdevices) continue; - /* avoid cases where sscanf is not exact inverse of printf */ + /* avoid cases where sscanf is not exact inverse of printf */ snprintf(buf, IFNAMSIZ, name, i); - if (!strncmp(buf, d->name, IFNAMSIZ)) + if (!strncmp(buf, name_node->name, IFNAMSIZ)) __set_bit(i, inuse); } + if (!sscanf(d->name, name, &i)) + continue; + if (i < 0 || i >= max_netdevices) + continue; - i = find_first_zero_bit(inuse, max_netdevices); - bitmap_free(inuse); + /* avoid cases where sscanf is not exact inverse of printf */ + snprintf(buf, IFNAMSIZ, name, i); + if (!strncmp(buf, d->name, IFNAMSIZ)) + __set_bit(i, inuse); } - snprintf(buf, IFNAMSIZ, name, i); - if (!netdev_name_in_use(net, buf)) - return i; + i = find_first_zero_bit(inuse, max_netdevices); + bitmap_free(inuse); + if (i == max_netdevices) + return -ENFILE; - /* It is possible to run out of possible slots - * when the name is long and there isn't enough space left - * for the digits, or if all bits are used. - */ - return -ENFILE; + snprintf(res, IFNAMSIZ, name, i); + return i; } -static int dev_alloc_name_ns(struct net *net, - struct net_device *dev, - const char *name) +/* Returns negative errno or allocated unit id (see __dev_alloc_name()) */ +static int dev_prep_valid_name(struct net *net, struct net_device *dev, + const char *want_name, char *out_name, + int dup_errno) { - char buf[IFNAMSIZ]; - int ret; + if (!dev_valid_name(want_name)) + return -EINVAL; - BUG_ON(!net); - ret = __dev_alloc_name(net, name, buf); - if (ret >= 0) - strscpy(dev->name, buf, IFNAMSIZ); - return ret; + if (strchr(want_name, '%')) + return __dev_alloc_name(net, want_name, out_name); + + if (netdev_name_in_use(net, want_name)) + return -dup_errno; + if (out_name != want_name) + strscpy(out_name, want_name, IFNAMSIZ); + return 0; } /** @@ -1153,26 +1157,17 @@ static int dev_alloc_name_ns(struct net *net, int dev_alloc_name(struct net_device *dev, const char *name) { - return dev_alloc_name_ns(dev_net(dev), dev, name); + return dev_prep_valid_name(dev_net(dev), dev, name, dev->name, ENFILE); } EXPORT_SYMBOL(dev_alloc_name); static int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { - BUG_ON(!net); - - if (!dev_valid_name(name)) - return -EINVAL; - - if (strchr(name, '%')) - return dev_alloc_name_ns(net, dev, name); - else if (netdev_name_in_use(net, name)) - return -EEXIST; - else if (dev->name != name) - strscpy(dev->name, name, IFNAMSIZ); + int ret; - return 0; + ret = dev_prep_valid_name(net, dev, name, dev->name, EEXIST); + return ret < 0 ? ret : 0; } /** @@ -6532,9 +6527,11 @@ static int __napi_poll(struct napi_struct *n, bool *repoll) * accidentally calling ->poll() when NAPI is not scheduled. */ work = 0; - if (test_bit(NAPI_STATE_SCHED, &n->state)) { + if (napi_is_scheduled(n)) { work = n->poll(n, weight); trace_napi_poll(n, work, weight); + + xdp_do_check_flushed(n); } if (unlikely(work > weight)) @@ -11081,7 +11078,9 @@ EXPORT_SYMBOL(unregister_netdev); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex) { + struct netdev_name_node *name_node; struct net *net_old = dev_net(dev); + char new_name[IFNAMSIZ] = {}; int err, new_nsid; ASSERT_RTNL(); @@ -11108,10 +11107,15 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, /* We get here if we can't use the current device name */ if (!pat) goto out; - err = dev_get_valid_name(net, dev, pat); + err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST); if (err < 0) goto out; } + /* Check that none of the altnames conflicts. */ + err = -EEXIST; + netdev_for_each_altname(dev, name_node) + if (netdev_name_in_use(net, name_node->name)) + goto out; /* Check that new_ifindex isn't used yet. */ if (new_ifindex) { @@ -11179,6 +11183,9 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, kobject_uevent(&dev->dev.kobj, KOBJ_ADD); netdev_adjacent_add_links(dev); + if (new_name[0]) /* Rename the netdev to prepared name */ + strscpy(dev->name, new_name, IFNAMSIZ); + /* Fixup kobjects */ err = device_rename(&dev->dev, dev->name); WARN_ON(err); diff --git a/net/core/dev.h b/net/core/dev.h index e075e198092c..5aa45f0fd4ae 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -62,6 +62,9 @@ struct netdev_name_node { int netdev_get_name(struct net *net, char *name, int ifindex); int dev_change_name(struct net_device *dev, const char *newname); +#define netdev_for_each_altname(dev, namenode) \ + list_for_each_entry((namenode), &(dev)->name_node->list, list) + int netdev_name_node_alt_create(struct net_device *dev, const char *name); int netdev_name_node_alt_destroy(struct net_device *dev, const char *name); @@ -136,4 +139,10 @@ static inline void netif_set_gro_ipv4_max_size(struct net_device *dev, } int rps_cpumask_housekeeping(struct cpumask *mask); + +#if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) +void xdp_do_check_flushed(struct napi_struct *napi); +#else +static inline void xdp_do_check_flushed(struct napi_struct *napi) { } +#endif #endif diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index b46aedc36939..feeddf95f450 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -382,7 +382,7 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr) if (err) return err; - err = dsa_master_hwtstamp_validate(dev, &kernel_cfg, &extack); + err = dsa_conduit_hwtstamp_validate(dev, &kernel_cfg, &extack); if (err) { if (extack._msg) netdev_err(dev, "%s\n", extack._msg); diff --git a/net/core/filter.c b/net/core/filter.c index cc2e4babc85f..21d75108c2e9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -83,6 +83,8 @@ #include <net/netfilter/nf_conntrack_bpf.h> #include <linux/un.h> +#include "dev.h" + static const struct bpf_func_proto * bpf_sk_base_func_proto(enum bpf_func_id func_id); @@ -4208,6 +4210,20 @@ void xdp_do_flush(void) } EXPORT_SYMBOL_GPL(xdp_do_flush); +#if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL) +void xdp_do_check_flushed(struct napi_struct *napi) +{ + bool ret; + + ret = dev_check_flush(); + ret |= cpu_map_check_flush(); + ret |= xsk_map_check_flush(); + + WARN_ONCE(ret, "Missing xdp_do_flush() invocation after NAPI by %ps\n", + napi->poll); +} +#endif + void bpf_clear_redirect_map(struct bpf_map *map) { struct bpf_redirect_info *ri; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9c09f091cbff..df81c1f0a570 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -251,7 +251,8 @@ bool neigh_remove_one(struct neighbour *ndel, struct neigh_table *tbl) static int neigh_forced_gc(struct neigh_table *tbl) { - int max_clean = atomic_read(&tbl->gc_entries) - tbl->gc_thresh2; + int max_clean = atomic_read(&tbl->gc_entries) - + READ_ONCE(tbl->gc_thresh2); unsigned long tref = jiffies - 5 * HZ; struct neighbour *n, *tmp; int shrunk = 0; @@ -280,7 +281,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) } } - tbl->last_flush = jiffies; + WRITE_ONCE(tbl->last_flush, jiffies); write_unlock_bh(&tbl->lock); @@ -464,17 +465,17 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl, { struct neighbour *n = NULL; unsigned long now = jiffies; - int entries; + int entries, gc_thresh3; if (exempt_from_gc) goto do_alloc; entries = atomic_inc_return(&tbl->gc_entries) - 1; - if (entries >= tbl->gc_thresh3 || - (entries >= tbl->gc_thresh2 && - time_after(now, tbl->last_flush + 5 * HZ))) { - if (!neigh_forced_gc(tbl) && - entries >= tbl->gc_thresh3) { + gc_thresh3 = READ_ONCE(tbl->gc_thresh3); + if (entries >= gc_thresh3 || + (entries >= READ_ONCE(tbl->gc_thresh2) && + time_after(now, READ_ONCE(tbl->last_flush) + 5 * HZ))) { + if (!neigh_forced_gc(tbl) && entries >= gc_thresh3) { net_info_ratelimited("%s: neighbor table overflow!\n", tbl->id); NEIGH_CACHE_STAT_INC(tbl, table_fulls); @@ -955,13 +956,14 @@ static void neigh_periodic_work(struct work_struct *work) if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; - tbl->last_rand = jiffies; + + WRITE_ONCE(tbl->last_rand, jiffies); list_for_each_entry(p, &tbl->parms_list, list) p->reachable_time = neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); } - if (atomic_read(&tbl->entries) < tbl->gc_thresh1) + if (atomic_read(&tbl->entries) < READ_ONCE(tbl->gc_thresh1)) goto out; for (i = 0 ; i < (1 << nht->hash_shift); i++) { @@ -2167,15 +2169,16 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, ndtmsg->ndtm_pad2 = 0; if (nla_put_string(skb, NDTA_NAME, tbl->id) || - nla_put_msecs(skb, NDTA_GC_INTERVAL, tbl->gc_interval, NDTA_PAD) || - nla_put_u32(skb, NDTA_THRESH1, tbl->gc_thresh1) || - nla_put_u32(skb, NDTA_THRESH2, tbl->gc_thresh2) || - nla_put_u32(skb, NDTA_THRESH3, tbl->gc_thresh3)) + nla_put_msecs(skb, NDTA_GC_INTERVAL, READ_ONCE(tbl->gc_interval), + NDTA_PAD) || + nla_put_u32(skb, NDTA_THRESH1, READ_ONCE(tbl->gc_thresh1)) || + nla_put_u32(skb, NDTA_THRESH2, READ_ONCE(tbl->gc_thresh2)) || + nla_put_u32(skb, NDTA_THRESH3, READ_ONCE(tbl->gc_thresh3))) goto nla_put_failure; { unsigned long now = jiffies; - long flush_delta = now - tbl->last_flush; - long rand_delta = now - tbl->last_rand; + long flush_delta = now - READ_ONCE(tbl->last_flush); + long rand_delta = now - READ_ONCE(tbl->last_rand); struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, @@ -2183,7 +2186,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), - .ndtc_proxy_qlen = tbl->proxy_queue.qlen, + .ndtc_proxy_qlen = READ_ONCE(tbl->proxy_queue.qlen), }; rcu_read_lock(); @@ -2206,17 +2209,17 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, struct neigh_statistics *st; st = per_cpu_ptr(tbl->stats, cpu); - ndst.ndts_allocs += st->allocs; - ndst.ndts_destroys += st->destroys; - ndst.ndts_hash_grows += st->hash_grows; - ndst.ndts_res_failed += st->res_failed; - ndst.ndts_lookups += st->lookups; - ndst.ndts_hits += st->hits; - ndst.ndts_rcv_probes_mcast += st->rcv_probes_mcast; - ndst.ndts_rcv_probes_ucast += st->rcv_probes_ucast; - ndst.ndts_periodic_gc_runs += st->periodic_gc_runs; - ndst.ndts_forced_gc_runs += st->forced_gc_runs; - ndst.ndts_table_fulls += st->table_fulls; + ndst.ndts_allocs += READ_ONCE(st->allocs); + ndst.ndts_destroys += READ_ONCE(st->destroys); + ndst.ndts_hash_grows += READ_ONCE(st->hash_grows); + ndst.ndts_res_failed += READ_ONCE(st->res_failed); + ndst.ndts_lookups += READ_ONCE(st->lookups); + ndst.ndts_hits += READ_ONCE(st->hits); + ndst.ndts_rcv_probes_mcast += READ_ONCE(st->rcv_probes_mcast); + ndst.ndts_rcv_probes_ucast += READ_ONCE(st->rcv_probes_ucast); + ndst.ndts_periodic_gc_runs += READ_ONCE(st->periodic_gc_runs); + ndst.ndts_forced_gc_runs += READ_ONCE(st->forced_gc_runs); + ndst.ndts_table_fulls += READ_ONCE(st->table_fulls); } if (nla_put_64bit(skb, NDTA_STATS, sizeof(ndst), &ndst, @@ -2445,16 +2448,16 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout_tbl_lock; if (tb[NDTA_THRESH1]) - tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); + WRITE_ONCE(tbl->gc_thresh1, nla_get_u32(tb[NDTA_THRESH1])); if (tb[NDTA_THRESH2]) - tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); + WRITE_ONCE(tbl->gc_thresh2, nla_get_u32(tb[NDTA_THRESH2])); if (tb[NDTA_THRESH3]) - tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); + WRITE_ONCE(tbl->gc_thresh3, nla_get_u32(tb[NDTA_THRESH3])); if (tb[NDTA_GC_INTERVAL]) - tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); + WRITE_ONCE(tbl->gc_interval, nla_get_msecs(tb[NDTA_GC_INTERVAL])); err = 0; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 8a9868ea5067..5e409b98aba0 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -376,6 +376,14 @@ static void page_pool_set_pp_info(struct page_pool *pool, { page->pp = pool; page->pp_magic |= PP_SIGNATURE; + + /* Ensuring all pages have been split into one fragment initially: + * page_pool_set_pp_info() is only called once for every page when it + * is allocated from the page allocator and page_pool_fragment_page() + * is dirtying the same cache line as the page->pp_magic above, so + * the overhead is negligible. + */ + page_pool_fragment_page(page, 1); if (pool->p.init_callback) pool->p.init_callback(page, pool->p.init_arg); } @@ -672,7 +680,7 @@ void page_pool_put_page_bulk(struct page_pool *pool, void **data, struct page *page = virt_to_head_page(data[i]); /* It is not the last user for the page frag case */ - if (!page_pool_is_last_frag(pool, page)) + if (!page_pool_is_last_frag(page)) continue; page = __page_pool_put_page(pool, page, -1, false); @@ -748,8 +756,7 @@ struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int max_size = PAGE_SIZE << pool->p.order; struct page *page = pool->frag_page; - if (WARN_ON(!(pool->p.flags & PP_FLAG_PAGE_FRAG) || - size > max_size)) + if (WARN_ON(size > max_size)) return NULL; size = ALIGN(size, dma_get_cache_alignment()); @@ -802,7 +809,7 @@ static void page_pool_empty_ring(struct page_pool *pool) } } -static void page_pool_free(struct page_pool *pool) +static void __page_pool_destroy(struct page_pool *pool) { if (pool->disconnect) pool->disconnect(pool); @@ -853,7 +860,7 @@ static int page_pool_release(struct page_pool *pool) page_pool_scrub(pool); inflight = page_pool_inflight(pool); if (!inflight) - page_pool_free(pool); + __page_pool_destroy(pool); return inflight; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 5e865af82e5b..8afcfadf8d5a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -670,19 +670,19 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_puts(seq, " Flags: "); for (i = 0; i < NR_PKT_FLAGS; i++) { - if (i == F_FLOW_SEQ) + if (i == FLOW_SEQ_SHIFT) if (!pkt_dev->cflows) continue; - if (pkt_dev->flags & (1 << i)) + if (pkt_dev->flags & (1 << i)) { seq_printf(seq, "%s ", pkt_flag_names[i]); - else if (i == F_FLOW_SEQ) - seq_puts(seq, "FLOW_RND "); - #ifdef CONFIG_XFRM - if (i == F_IPSEC && pkt_dev->spi) - seq_printf(seq, "spi:%u", pkt_dev->spi); + if (i == IPSEC_SHIFT && pkt_dev->spi) + seq_printf(seq, "spi:%u ", pkt_dev->spi); #endif + } else if (i == FLOW_SEQ_SHIFT) { + seq_puts(seq, "FLOW_RND "); + } } seq_puts(seq, "\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eef7f7788996..f2753fd58881 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -5532,13 +5532,11 @@ static unsigned int rtnl_offload_xstats_get_size_hw_s_info_one(const struct net_device *dev, enum netdev_offload_xstats_type type) { - bool enabled = netdev_offload_xstats_enabled(dev, type); - return nla_total_size(0) + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST */ nla_total_size(sizeof(u8)) + /* IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED */ - (enabled ? nla_total_size(sizeof(u8)) : 0) + + nla_total_size(sizeof(u8)) + 0; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 0401f40973a5..c52ddd6891d9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4267,6 +4267,7 @@ static void skb_ts_finish(struct ts_config *conf, struct ts_state *state) unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config) { + unsigned int patlen = config->ops->get_pattern_len(config); struct ts_state state; unsigned int ret; @@ -4278,7 +4279,7 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, skb_prepare_seq_read(skb, from, to, TS_SKB_CB(&state)); ret = textsearch_find(config, &state); - return (ret <= to - from ? ret : UINT_MAX); + return (ret + patlen <= to - from ? ret : UINT_MAX); } EXPORT_SYMBOL(skb_find_text); @@ -5764,7 +5765,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, /* In general, avoid mixing page_pool and non-page_pool allocated * pages within the same SKB. Additionally avoid dealing with clones * with page_pool pages, in case the SKB is using page_pool fragment - * references (PP_FLAG_PAGE_FRAG). Since we only take full page + * references (page_pool_alloc_frag()). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. * In theory we could take full references if @from is cloned and diff --git a/net/core/sock.c b/net/core/sock.c index 290165954379..1d28e3e87970 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3035,21 +3035,29 @@ EXPORT_SYMBOL(sk_wait_data); * @amt: pages to allocate * @kind: allocation type * - * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc + * Similar to __sk_mem_schedule(), but does not update sk_forward_alloc. + * + * Unlike the globally shared limits among the sockets under same protocol, + * consuming the budget of a memcg won't have direct effect on other ones. + * So be optimistic about memcg's tolerance, and leave the callers to decide + * whether or not to raise allocated through sk_under_memory_pressure() or + * its variants. */ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { - bool memcg_charge = mem_cgroup_sockets_enabled && sk->sk_memcg; + struct mem_cgroup *memcg = mem_cgroup_sockets_enabled ? sk->sk_memcg : NULL; struct proto *prot = sk->sk_prot; - bool charged = true; + bool charged = false; long allocated; sk_memory_allocated_add(sk, amt); allocated = sk_memory_allocated(sk); - if (memcg_charge && - !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt, - gfp_memcg_charge()))) - goto suppress_allocation; + + if (memcg) { + if (!mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge())) + goto suppress_allocation; + charged = true; + } /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { @@ -3065,7 +3073,14 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) if (allocated > sk_prot_mem_limits(sk, 2)) goto suppress_allocation; - /* guarantee minimum buffer size under pressure */ + /* Guarantee minimum buffer size under pressure (either global + * or memcg) to make sure features described in RFC 7323 (TCP + * Extensions for High Performance) work properly. + * + * This rule does NOT stand when exceeds global or memcg's hard + * limit, or else a DoS attack can be taken place by spawning + * lots of sockets whose usage are under minimum buffer size. + */ if (kind == SK_MEM_RECV) { if (atomic_read(&sk->sk_rmem_alloc) < sk_get_rmem0(sk, prot)) return 1; @@ -3084,8 +3099,17 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) if (sk_has_memory_pressure(sk)) { u64 alloc; - if (!sk_under_memory_pressure(sk)) + /* The following 'average' heuristic is within the + * scope of global accounting, so it only makes + * sense for global memory pressure. + */ + if (!sk_under_global_memory_pressure(sk)) return 1; + + /* Try to be fair among all the sockets under global + * pressure by allowing the ones that below average + * usage to raise. + */ alloc = sk_sockets_allocated_read_positive(sk); if (sk_prot_mem_limits(sk, 2) > alloc * sk_mem_pages(sk->sk_wmem_queued + @@ -3104,8 +3128,8 @@ suppress_allocation: */ if (sk->sk_wmem_queued + size >= sk->sk_sndbuf) { /* Force charge with __GFP_NOFAIL */ - if (memcg_charge && !charged) { - mem_cgroup_charge_skmem(sk->sk_memcg, amt, + if (memcg && !charged) { + mem_cgroup_charge_skmem(memcg, amt, gfp_memcg_charge() | __GFP_NOFAIL); } return 1; @@ -3117,8 +3141,8 @@ suppress_allocation: sk_memory_allocated_sub(sk, amt); - if (memcg_charge && charged) - mem_cgroup_uncharge_skmem(sk->sk_memcg, amt); + if (charged) + mem_cgroup_uncharge_skmem(memcg, amt); return 0; } diff --git a/net/core/stream.c b/net/core/stream.c index f5c4e47df165..96fbcb9bbb30 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -117,7 +117,7 @@ EXPORT_SYMBOL(sk_stream_wait_close); */ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) { - int err = 0; + int ret, err = 0; long vm_wait = 0; long current_timeo = *timeo_p; DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -142,11 +142,13 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || - (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || - (sk_stream_memory_free(sk) && - !vm_wait), &wait); + ret = sk_wait_event(sk, ¤t_timeo, READ_ONCE(sk->sk_err) || + (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN) || + (sk_stream_memory_free(sk) && !vm_wait), + &wait); sk->sk_write_pending--; + if (ret < 0) + goto do_error; if (vm_wait) { vm_wait -= current_timeo; diff --git a/net/devlink/core.c b/net/devlink/core.c index bcbbb952569f..6984877e9f10 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -168,6 +168,20 @@ int devlink_rel_nested_in_add(u32 *rel_index, u32 devlink_index, return 0; } +/** + * devlink_rel_nested_in_notify - Notify the object this devlink + * instance is nested in. + * @devlink: devlink + * + * This is called upon network namespace change of devlink instance. + * In case this devlink instance is nested in another devlink object, + * a notification of a change of this object should be sent + * over netlink. The parent devlink instance lock needs to be + * taken during the notification preparation. + * However, since the devlink lock of nested instance is held here, + * we would end with wrong devlink instance lock ordering and + * deadlock. Therefore the work is utilized to avoid that. + */ void devlink_rel_nested_in_notify(struct devlink *devlink) { struct devlink_rel *rel = devlink->rel; @@ -183,9 +197,8 @@ static struct devlink_rel *devlink_rel_find(unsigned long rel_index) DEVLINK_REL_IN_USE); } -static struct devlink *devlink_rel_devlink_get_lock(u32 rel_index) +static struct devlink *devlink_rel_devlink_get(u32 rel_index) { - struct devlink *devlink; struct devlink_rel *rel; u32 devlink_index; @@ -198,16 +211,7 @@ static struct devlink *devlink_rel_devlink_get_lock(u32 rel_index) xa_unlock(&devlink_rels); if (!rel) return NULL; - devlink = devlinks_xa_get(devlink_index); - if (!devlink) - return NULL; - devl_lock(devlink); - if (!devl_is_registered(devlink)) { - devl_unlock(devlink); - devlink_put(devlink); - return NULL; - } - return devlink; + return devlinks_xa_get(devlink_index); } int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink, @@ -218,11 +222,10 @@ int devlink_rel_devlink_handle_put(struct sk_buff *msg, struct devlink *devlink, struct devlink *rel_devlink; int err; - rel_devlink = devlink_rel_devlink_get_lock(rel_index); + rel_devlink = devlink_rel_devlink_get(rel_index); if (!rel_devlink) return 0; err = devlink_nl_put_nested_handle(msg, net, rel_devlink, attrtype); - devl_unlock(rel_devlink); devlink_put(rel_devlink); if (!err && msg_updated) *msg_updated = true; @@ -310,6 +313,7 @@ static void devlink_release(struct work_struct *work) mutex_destroy(&devlink->lock); lockdep_unregister_key(&devlink->lock_key); + put_device(devlink->dev); kfree(devlink); } @@ -425,7 +429,7 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, if (ret < 0) goto err_xa_alloc; - devlink->dev = dev; + devlink->dev = get_device(dev); devlink->ops = ops; xa_init_flags(&devlink->ports, XA_FLAGS_ALLOC); xa_init_flags(&devlink->params, XA_FLAGS_ALLOC); diff --git a/net/devlink/dev.c b/net/devlink/dev.c index dc8039ca2b38..4fc7adb32663 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -492,7 +492,7 @@ free_msg: return -EMSGSIZE; } -int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; enum devlink_reload_action action; @@ -658,7 +658,7 @@ nla_put_failure: return err; } -int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct sk_buff *msg; @@ -679,7 +679,7 @@ int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) return genlmsg_reply(msg, info); } -int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -1108,7 +1108,7 @@ static int devlink_flash_component_get(struct devlink *devlink, return 0; } -int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *nla_overwrite_mask, *nla_file_name; struct devlink_flash_update_params params = {}; @@ -1351,7 +1351,7 @@ static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG }, }; -int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *tb[DEVLINK_ATTR_SELFTEST_ID_MAX + 1]; struct devlink *devlink = info->user_ptr[0]; diff --git a/net/devlink/devl_internal.h b/net/devlink/devl_internal.h index 741d1bf1bec8..183dbe3807ab 100644 --- a/net/devlink/devl_internal.h +++ b/net/devlink/devl_internal.h @@ -227,67 +227,3 @@ int devlink_rate_nodes_check(struct devlink *devlink, u16 mode, /* Linecards */ unsigned int devlink_linecard_index(struct devlink_linecard *linecard); - -/* Devlink nl cmds */ -int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_selftests_run(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb); -int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, - struct netlink_callback *cb); -int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, - struct netlink_callback *cb); -int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, - struct genl_info *info); -int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info); -int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, - struct genl_info *info); diff --git a/net/devlink/dpipe.c b/net/devlink/dpipe.c index 431227c412e5..a72a9292efc5 100644 --- a/net/devlink/dpipe.c +++ b/net/devlink/dpipe.c @@ -289,7 +289,7 @@ err_table_put: return err; } -int devlink_nl_cmd_dpipe_table_get(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name = NULL; @@ -562,8 +562,8 @@ send_done: return genlmsg_reply(dump_ctx.skb, info); } -int devlink_nl_cmd_dpipe_entries_get(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_dpipe_table *table; @@ -712,8 +712,8 @@ err_table_put: return err; } -int devlink_nl_cmd_dpipe_headers_get(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -746,8 +746,8 @@ static int devlink_dpipe_table_counters_set(struct devlink *devlink, return 0; } -int devlink_nl_cmd_dpipe_table_counters_set(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const char *table_name; diff --git a/net/devlink/health.c b/net/devlink/health.c index 51e6e81e31bb..695df61f8ac2 100644 --- a/net/devlink/health.c +++ b/net/devlink/health.c @@ -19,6 +19,7 @@ struct devlink_fmsg_item { struct devlink_fmsg { struct list_head item_list; + int err; /* first error encountered on some devlink_fmsg_XXX() call */ bool putting_binary; /* This flag forces enclosing of binary data * in an array brackets. It forces using * of designated API: @@ -451,8 +452,8 @@ int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, devlink_nl_health_reporter_get_dump_one); } -int devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -562,21 +563,18 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, return 0; reporter->dump_fmsg = devlink_fmsg_alloc(); - if (!reporter->dump_fmsg) { - err = -ENOMEM; - return err; - } + if (!reporter->dump_fmsg) + return -ENOMEM; - err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg); - if (err) - goto dump_err; + devlink_fmsg_obj_nest_start(reporter->dump_fmsg); err = reporter->ops->dump(reporter, reporter->dump_fmsg, priv_ctx, extack); if (err) goto dump_err; - err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + err = reporter->dump_fmsg->err; if (err) goto dump_err; @@ -657,8 +655,8 @@ devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, } EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); -int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -670,373 +668,258 @@ int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, return devlink_health_reporter_recover(reporter, NULL, info->extack); } -static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, - int attrtype) +static void devlink_fmsg_err_if_binary(struct devlink_fmsg *fmsg) +{ + if (!fmsg->err && fmsg->putting_binary) + fmsg->err = -EINVAL; +} + +static void devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, int attrtype) { struct devlink_fmsg_item *item; + if (fmsg->err) + return; + item = kzalloc(sizeof(*item), GFP_KERNEL); - if (!item) - return -ENOMEM; + if (!item) { + fmsg->err = -ENOMEM; + return; + } item->attrtype = attrtype; list_add_tail(&item->list, &fmsg->item_list); - - return 0; } -int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) +void devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); -static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) +static void devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); } -int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_end(fmsg); + devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); #define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) -static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) +static void devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) { struct devlink_fmsg_item *item; - if (fmsg->putting_binary) - return -EINVAL; + devlink_fmsg_err_if_binary(fmsg); + if (fmsg->err) + return; - if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) - return -EMSGSIZE; + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) { + fmsg->err = -EMSGSIZE; + return; + } item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); - if (!item) - return -ENOMEM; + if (!item) { + fmsg->err = -ENOMEM; + return; + } item->nla_type = NLA_NUL_STRING; item->len = strlen(name) + 1; item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; memcpy(&item->value, name, item->len); list_add_tail(&item->list, &fmsg->item_list); - - return 0; } -int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) +void devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) { - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); - if (err) - return err; - - err = devlink_fmsg_put_name(fmsg, name); - if (err) - return err; - - return 0; + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); + devlink_fmsg_put_name(fmsg, name); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); -int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_nest_end(fmsg); + devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); -int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) +void devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) { - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); -int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) { - int err; - - if (fmsg->putting_binary) - return -EINVAL; - - err = devlink_fmsg_nest_end(fmsg); - if (err) - return err; - - err = devlink_fmsg_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_nest_end(fmsg); + devlink_fmsg_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); -int devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, - const char *name) +void devlink_fmsg_binary_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) { - int err; - - err = devlink_fmsg_arr_pair_nest_start(fmsg, name); - if (err) - return err; - + devlink_fmsg_arr_pair_nest_start(fmsg, name); fmsg->putting_binary = true; - return err; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_start); -int devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) +void devlink_fmsg_binary_pair_nest_end(struct devlink_fmsg *fmsg) { + if (fmsg->err) + return; + if (!fmsg->putting_binary) - return -EINVAL; + fmsg->err = -EINVAL; fmsg->putting_binary = false; - return devlink_fmsg_arr_pair_nest_end(fmsg); + devlink_fmsg_arr_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_nest_end); -static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, - const void *value, u16 value_len, - u8 value_nla_type) +static void devlink_fmsg_put_value(struct devlink_fmsg *fmsg, + const void *value, u16 value_len, + u8 value_nla_type) { struct devlink_fmsg_item *item; - if (value_len > DEVLINK_FMSG_MAX_SIZE) - return -EMSGSIZE; + if (fmsg->err) + return; + + if (value_len > DEVLINK_FMSG_MAX_SIZE) { + fmsg->err = -EMSGSIZE; + return; + } item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); - if (!item) - return -ENOMEM; + if (!item) { + fmsg->err = -ENOMEM; + return; + } item->nla_type = value_nla_type; item->len = value_len; item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; memcpy(&item->value, value, item->len); list_add_tail(&item->list, &fmsg->item_list); - - return 0; } -static int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +static void devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } -static int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +static void devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } -int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) +void devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); -static int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +static void devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } -int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) +void devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { - if (fmsg->putting_binary) - return -EINVAL; - - return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, - NLA_NUL_STRING); + devlink_fmsg_err_if_binary(fmsg); + devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, NLA_NUL_STRING); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +void devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { - if (!fmsg->putting_binary) - return -EINVAL; + if (!fmsg->err && !fmsg->putting_binary) + fmsg->err = -EINVAL; - return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); + devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); -int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, - bool value) +void devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_bool_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_bool_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); -int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, - u8 value) +void devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u8_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_u8_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); -int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, - u32 value) +void devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u32_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_u32_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); -int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, - u64 value) +void devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_u64_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_u64_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); -int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, - const char *value) +void devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value) { - int err; - - err = devlink_fmsg_pair_nest_start(fmsg, name); - if (err) - return err; - - err = devlink_fmsg_string_put(fmsg, value); - if (err) - return err; - - err = devlink_fmsg_pair_nest_end(fmsg); - if (err) - return err; - - return 0; + devlink_fmsg_pair_nest_start(fmsg, name); + devlink_fmsg_string_put(fmsg, value); + devlink_fmsg_pair_nest_end(fmsg); } EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); -int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u32 value_len) +void devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u32 value_len) { u32 data_size; - int end_err; u32 offset; - int err; - err = devlink_fmsg_binary_pair_nest_start(fmsg, name); - if (err) - return err; + devlink_fmsg_binary_pair_nest_start(fmsg, name); for (offset = 0; offset < value_len; offset += data_size) { data_size = value_len - offset; if (data_size > DEVLINK_FMSG_MAX_SIZE) data_size = DEVLINK_FMSG_MAX_SIZE; - err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); - if (err) - break; - /* Exit from loop with a break (instead of - * return) to make sure putting_binary is turned off in - * devlink_fmsg_binary_pair_nest_end - */ - } - end_err = devlink_fmsg_binary_pair_nest_end(fmsg); - if (end_err) - err = end_err; + devlink_fmsg_binary_put(fmsg, value + offset, data_size); + } - return err; + devlink_fmsg_binary_pair_nest_end(fmsg); + fmsg->putting_binary = false; } EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); @@ -1146,6 +1029,9 @@ static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, void *hdr; int err; + if (fmsg->err) + return fmsg->err; + while (!last) { int tmp_index = index; @@ -1199,6 +1085,9 @@ static int devlink_fmsg_dumpit(struct devlink_fmsg *fmsg, struct sk_buff *skb, void *hdr; int err; + if (fmsg->err) + return fmsg->err; + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, cmd); if (!hdr) { @@ -1219,8 +1108,8 @@ nla_put_failure: return err; } -int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -1238,17 +1127,13 @@ int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (!fmsg) return -ENOMEM; - err = devlink_fmsg_obj_nest_start(fmsg); - if (err) - goto out; + devlink_fmsg_obj_nest_start(fmsg); err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; - err = devlink_fmsg_obj_nest_end(fmsg); - if (err) - goto out; + devlink_fmsg_obj_nest_end(fmsg); err = devlink_fmsg_snd(fmsg, info, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); @@ -1278,8 +1163,8 @@ devlink_health_reporter_get_from_cb_lock(struct netlink_callback *cb) return reporter; } -int devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, - struct netlink_callback *cb) +int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) { struct devlink_nl_dump_state *state = devlink_dump_state(cb); struct devlink_health_reporter *reporter; @@ -1317,8 +1202,8 @@ unlock: return err; } -int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; @@ -1334,8 +1219,8 @@ int devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, return 0; } -int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_health_reporter *reporter; diff --git a/net/devlink/linecard.c b/net/devlink/linecard.c index 9ff1813f88c5..2f1c317b64cd 100644 --- a/net/devlink/linecard.c +++ b/net/devlink/linecard.c @@ -369,8 +369,7 @@ out: return err; } -int devlink_nl_cmd_linecard_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; diff --git a/net/devlink/netlink.c b/net/devlink/netlink.c index 499304d9de49..d0b90ebc8b15 100644 --- a/net/devlink/netlink.c +++ b/net/devlink/netlink.c @@ -13,91 +13,28 @@ static const struct genl_multicast_group devlink_nl_mcgrps[] = { [DEVLINK_MCGRP_CONFIG] = { .name = DEVLINK_GENL_MCGRP_CONFIG_NAME }, }; -static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { - [DEVLINK_ATTR_UNSPEC] = { .strict_start_type = - DEVLINK_ATTR_TRAP_POLICER_ID }, - [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, - DEVLINK_PORT_TYPE_IB), - [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_SB_POOL_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, - DEVLINK_ESWITCH_MODE_SWITCHDEV), - [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 }, - [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64}, - [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64}, - [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, - [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, - [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, - [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = - NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), - [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, - [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8 }, - [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32 }, - [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, - [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, - DEVLINK_RELOAD_ACTION_MAX), - [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), - [DEVLINK_ATTR_PORT_FLAVOUR] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16 }, - [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TYPE] = { .type = NLA_U16 }, - [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64 }, - [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, - [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, - [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, - [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, - [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG }, -}; - int devlink_nl_put_nested_handle(struct sk_buff *msg, struct net *net, struct devlink *devlink, int attrtype) { struct nlattr *nested_attr; + struct net *devl_net; nested_attr = nla_nest_start(msg, attrtype); if (!nested_attr) return -EMSGSIZE; if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; - if (!net_eq(net, devlink_net(devlink))) { - int id = peernet2id_alloc(net, devlink_net(devlink), - GFP_KERNEL); + rcu_read_lock(); + devl_net = read_pnet_rcu(&devlink->_net); + if (!net_eq(net, devl_net)) { + int id = peernet2id_alloc(net, devl_net, GFP_ATOMIC); + + rcu_read_unlock(); if (nla_put_s32(msg, DEVLINK_ATTR_NETNS_ID, id)) return -EMSGSIZE; + } else { + rcu_read_unlock(); } nla_nest_end(msg, nested_attr); @@ -185,7 +122,7 @@ unlock: int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info) { - return __devlink_nl_pre_doit(skb, info, ops->internal_flags); + return __devlink_nl_pre_doit(skb, info, 0); } int devlink_nl_pre_doit_port(const struct genl_split_ops *ops, @@ -281,269 +218,12 @@ int devlink_nl_dumpit(struct sk_buff *msg, struct netlink_callback *cb, return devlink_nl_inst_iter_dumpit(msg, cb, flags, dump_one); } -static const struct genl_small_ops devlink_nl_small_ops[40] = { - { - .cmd = DEVLINK_CMD_PORT_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_RATE_SET, - .doit = devlink_nl_cmd_rate_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RATE_NEW, - .doit = devlink_nl_cmd_rate_new_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RATE_DEL, - .doit = devlink_nl_cmd_rate_del_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_SPLIT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_split_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_PORT_UNSPLIT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_unsplit_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_PORT_NEW, - .doit = devlink_nl_cmd_port_new_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_DEL, - .doit = devlink_nl_cmd_port_del_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - - { - .cmd = DEVLINK_CMD_LINECARD_SET, - .doit = devlink_nl_cmd_linecard_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_POOL_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_pool_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_port_pool_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_tc_pool_bind_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_occ_snapshot_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_sb_occ_max_clear_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_ESWITCH_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_eswitch_get_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_ESWITCH_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_eswitch_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_table_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_entries_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_headers_get, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_dpipe_table_counters_set, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RESOURCE_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_resource_set, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_RESOURCE_DUMP, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_resource_dump, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_RELOAD, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_reload, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PARAM_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_param_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_PORT_PARAM_GET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_param_get_doit, - .dumpit = devlink_nl_cmd_port_param_get_dumpit, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - /* can be retrieved by unprivileged users */ - }, - { - .cmd = DEVLINK_CMD_PORT_PARAM_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_port_param_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, - }, - { - .cmd = DEVLINK_CMD_REGION_NEW, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_new, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_DEL, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_region_del, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_REGION_READ, - .validate = GENL_DONT_VALIDATE_STRICT | - GENL_DONT_VALIDATE_DUMP_STRICT, - .dumpit = devlink_nl_cmd_region_read_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_set_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_recover_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_diagnose_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, - .validate = GENL_DONT_VALIDATE_STRICT | - GENL_DONT_VALIDATE_DUMP_STRICT, - .dumpit = devlink_nl_cmd_health_reporter_dump_get_dumpit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_health_reporter_test_doit, - .flags = GENL_ADMIN_PERM, - .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT, - }, - { - .cmd = DEVLINK_CMD_FLASH_UPDATE, - .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .doit = devlink_nl_cmd_flash_update, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_SET, - .doit = devlink_nl_cmd_trap_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_GROUP_SET, - .doit = devlink_nl_cmd_trap_group_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_TRAP_POLICER_SET, - .doit = devlink_nl_cmd_trap_policer_set_doit, - .flags = GENL_ADMIN_PERM, - }, - { - .cmd = DEVLINK_CMD_SELFTESTS_RUN, - .doit = devlink_nl_cmd_selftests_run, - .flags = GENL_ADMIN_PERM, - }, - /* -- No new ops here! Use split ops going forward! -- */ -}; - struct genl_family devlink_nl_family __ro_after_init = { .name = DEVLINK_GENL_NAME, .version = DEVLINK_GENL_VERSION, - .maxattr = DEVLINK_ATTR_MAX, - .policy = devlink_nl_policy, .netnsok = true, .parallel_ops = true, - .pre_doit = devlink_nl_pre_doit, - .post_doit = devlink_nl_post_doit, .module = THIS_MODULE, - .small_ops = devlink_nl_small_ops, - .n_small_ops = ARRAY_SIZE(devlink_nl_small_ops), .split_ops = devlink_nl_ops, .n_split_ops = ARRAY_SIZE(devlink_nl_ops), .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 467b7a431de1..9cbae0169249 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -10,6 +10,18 @@ #include <uapi/linux/devlink.h> +/* Common nested types */ +const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1] = { + [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY, }, + [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_PORT_FN_ATTR_OPSTATE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_PORT_FN_ATTR_CAPS] = NLA_POLICY_BITFIELD32(3), +}; + +const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .type = NLA_FLAG, }, +}; + /* DEVLINK_CMD_GET - do */ static const struct nla_policy devlink_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -29,6 +41,48 @@ static const struct nla_policy devlink_port_get_dump_nl_policy[DEVLINK_ATTR_DEV_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_PORT_SET - do */ +static const struct nla_policy devlink_port_set_nl_policy[DEVLINK_ATTR_PORT_FUNCTION + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_MAX(NLA_U16, 3), + [DEVLINK_ATTR_PORT_FUNCTION] = NLA_POLICY_NESTED(devlink_dl_port_function_nl_policy), +}; + +/* DEVLINK_CMD_PORT_NEW - do */ +static const struct nla_policy devlink_port_new_nl_policy[DEVLINK_ATTR_PORT_PCI_SF_NUMBER + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_FLAVOUR] = NLA_POLICY_MAX(NLA_U16, 7), + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .type = NLA_U16, }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_DEL - do */ +static const struct nla_policy devlink_port_del_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_SPLIT - do */ +static const struct nla_policy devlink_port_split_nl_policy[DEVLINK_ATTR_PORT_SPLIT_COUNT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_UNSPLIT - do */ +static const struct nla_policy devlink_port_unsplit_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_SB_GET - do */ static const struct nla_policy devlink_sb_get_do_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -56,6 +110,16 @@ static const struct nla_policy devlink_sb_pool_get_dump_nl_policy[DEVLINK_ATTR_D [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SB_POOL_SET - do */ +static const struct nla_policy devlink_sb_pool_set_nl_policy[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_ATTR_SB_POOL_SIZE] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_SB_PORT_POOL_GET - do */ static const struct nla_policy devlink_sb_port_pool_get_do_nl_policy[DEVLINK_ATTR_SB_POOL_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -71,6 +135,16 @@ static const struct nla_policy devlink_sb_port_pool_get_dump_nl_policy[DEVLINK_A [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SB_PORT_POOL_SET - do */ +static const struct nla_policy devlink_sb_port_pool_set_nl_policy[DEVLINK_ATTR_SB_THRESHOLD + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ static const struct nla_policy devlink_sb_tc_pool_bind_get_do_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -87,6 +161,100 @@ static const struct nla_policy devlink_sb_tc_pool_bind_get_dump_nl_policy[DEVLIN [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */ +static const struct nla_policy devlink_sb_tc_pool_bind_set_nl_policy[DEVLINK_ATTR_SB_TC_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_POOL_TYPE] = NLA_POLICY_MAX(NLA_U8, 1), + [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16, }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */ +static const struct nla_policy devlink_sb_occ_snapshot_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */ +static const struct nla_policy devlink_sb_occ_max_clear_nl_policy[DEVLINK_ATTR_SB_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_ESWITCH_GET - do */ +static const struct nla_policy devlink_eswitch_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_ESWITCH_SET - do */ +static const struct nla_policy devlink_eswitch_set_nl_policy[DEVLINK_ATTR_ESWITCH_ENCAP_MODE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 1), + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U16, 3), + [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = NLA_POLICY_MAX(NLA_U8, 1), +}; + +/* DEVLINK_CMD_DPIPE_TABLE_GET - do */ +static const struct nla_policy devlink_dpipe_table_get_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */ +static const struct nla_policy devlink_dpipe_entries_get_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */ +static const struct nla_policy devlink_dpipe_headers_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */ +static const struct nla_policy devlink_dpipe_table_counters_set_nl_policy[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8, }, +}; + +/* DEVLINK_CMD_RESOURCE_SET - do */ +static const struct nla_policy devlink_resource_set_nl_policy[DEVLINK_ATTR_RESOURCE_SIZE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64, }, +}; + +/* DEVLINK_CMD_RESOURCE_DUMP - do */ +static const struct nla_policy devlink_resource_dump_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RELOAD - do */ +static const struct nla_policy devlink_reload_nl_policy[DEVLINK_ATTR_RELOAD_LIMITS + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, 1, 2), + [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(6), + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32, }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32, }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_PARAM_GET - do */ static const struct nla_policy devlink_param_get_do_nl_policy[DEVLINK_ATTR_PARAM_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -100,6 +268,15 @@ static const struct nla_policy devlink_param_get_dump_nl_policy[DEVLINK_ATTR_DEV [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_PARAM_SET - do */ +static const struct nla_policy devlink_param_set_nl_policy[DEVLINK_ATTR_PARAM_VALUE_CMODE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8, }, + [DEVLINK_ATTR_PARAM_VALUE_CMODE] = NLA_POLICY_MAX(NLA_U8, 2), +}; + /* DEVLINK_CMD_REGION_GET - do */ static const struct nla_policy devlink_region_get_do_nl_policy[DEVLINK_ATTR_REGION_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -114,6 +291,50 @@ static const struct nla_policy devlink_region_get_dump_nl_policy[DEVLINK_ATTR_DE [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_REGION_NEW - do */ +static const struct nla_policy devlink_region_new_nl_policy[DEVLINK_ATTR_REGION_SNAPSHOT_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_REGION_DEL - do */ +static const struct nla_policy devlink_region_del_nl_policy[DEVLINK_ATTR_REGION_SNAPSHOT_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_REGION_READ - dump */ +static const struct nla_policy devlink_region_read_nl_policy[DEVLINK_ATTR_REGION_DIRECT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32, }, + [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG, }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64, }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64, }, +}; + +/* DEVLINK_CMD_PORT_PARAM_GET - do */ +static const struct nla_policy devlink_port_param_get_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + +/* DEVLINK_CMD_PORT_PARAM_SET - do */ +static const struct nla_policy devlink_port_param_set_nl_policy[DEVLINK_ATTR_PORT_INDEX + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_INFO_GET - do */ static const struct nla_policy devlink_info_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -135,6 +356,58 @@ static const struct nla_policy devlink_health_reporter_get_dump_nl_policy[DEVLIN [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, }; +/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */ +static const struct nla_policy devlink_health_reporter_set_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64, }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8, }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .type = NLA_U8, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */ +static const struct nla_policy devlink_health_reporter_recover_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */ +static const struct nla_policy devlink_health_reporter_diagnose_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */ +static const struct nla_policy devlink_health_reporter_dump_get_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */ +static const struct nla_policy devlink_health_reporter_dump_clear_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_FLASH_UPDATE - do */ +static const struct nla_policy devlink_flash_update_nl_policy[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = NLA_POLICY_BITFIELD32(3), +}; + /* DEVLINK_CMD_TRAP_GET - do */ static const struct nla_policy devlink_trap_get_do_nl_policy[DEVLINK_ATTR_TRAP_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -148,6 +421,14 @@ static const struct nla_policy devlink_trap_get_dump_nl_policy[DEVLINK_ATTR_DEV_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_TRAP_SET - do */ +static const struct nla_policy devlink_trap_set_nl_policy[DEVLINK_ATTR_TRAP_ACTION + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_ACTION] = NLA_POLICY_MAX(NLA_U8, 2), +}; + /* DEVLINK_CMD_TRAP_GROUP_GET - do */ static const struct nla_policy devlink_trap_group_get_do_nl_policy[DEVLINK_ATTR_TRAP_GROUP_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -161,6 +442,15 @@ static const struct nla_policy devlink_trap_group_get_dump_nl_policy[DEVLINK_ATT [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_TRAP_GROUP_SET - do */ +static const struct nla_policy devlink_trap_group_set_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_ACTION] = NLA_POLICY_MAX(NLA_U8, 2), + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, }, +}; + /* DEVLINK_CMD_TRAP_POLICER_GET - do */ static const struct nla_policy devlink_trap_policer_get_do_nl_policy[DEVLINK_ATTR_TRAP_POLICER_ID + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -174,6 +464,23 @@ static const struct nla_policy devlink_trap_policer_get_dump_nl_policy[DEVLINK_A [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_TRAP_POLICER_SET - do */ +static const struct nla_policy devlink_trap_policer_set_nl_policy[DEVLINK_ATTR_TRAP_POLICER_BURST + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_TRAP_POLICER_ID] = { .type = NLA_U32, }, + [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64, }, + [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64, }, +}; + +/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */ +static const struct nla_policy devlink_health_reporter_test_nl_policy[DEVLINK_ATTR_HEALTH_REPORTER_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_RATE_GET - do */ static const struct nla_policy devlink_rate_get_do_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -188,6 +495,37 @@ static const struct nla_policy devlink_rate_get_dump_nl_policy[DEVLINK_ATTR_DEV_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_RATE_SET - do */ +static const struct nla_policy devlink_rate_set_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RATE_NEW - do */ +static const struct nla_policy devlink_rate_new_nl_policy[DEVLINK_ATTR_RATE_TX_WEIGHT + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .type = NLA_U64, }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32, }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + +/* DEVLINK_CMD_RATE_DEL - do */ +static const struct nla_policy devlink_rate_del_nl_policy[DEVLINK_ATTR_RATE_NODE_NAME + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_RATE_NODE_NAME] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_LINECARD_GET - do */ static const struct nla_policy devlink_linecard_get_do_nl_policy[DEVLINK_ATTR_LINECARD_INDEX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, @@ -201,14 +539,29 @@ static const struct nla_policy devlink_linecard_get_dump_nl_policy[DEVLINK_ATTR_ [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_LINECARD_SET - do */ +static const struct nla_policy devlink_linecard_set_nl_policy[DEVLINK_ATTR_LINECARD_TYPE + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32, }, + [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING, }, +}; + /* DEVLINK_CMD_SELFTESTS_GET - do */ static const struct nla_policy devlink_selftests_get_nl_policy[DEVLINK_ATTR_DEV_NAME + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, }; +/* DEVLINK_CMD_SELFTESTS_RUN - do */ +static const struct nla_policy devlink_selftests_run_nl_policy[DEVLINK_ATTR_SELFTESTS + 1] = { + [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, + [DEVLINK_ATTR_SELFTESTS] = NLA_POLICY_NESTED(devlink_dl_selftest_id_nl_policy), +}; + /* Ops table for devlink */ -const struct genl_split_ops devlink_nl_ops[32] = { +const struct genl_split_ops devlink_nl_ops[73] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT, @@ -243,6 +596,56 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_PORT_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_set_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_FUNCTION, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_NEW, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_port_new_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_new_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_PCI_SF_NUMBER, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_DEL, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_del_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_del_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_SPLIT, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_split_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_split_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_SPLIT_COUNT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_UNSPLIT, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_unsplit_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_unsplit_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SB_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -277,6 +680,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_SB_POOL_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_pool_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_pool_set_nl_policy, + .maxattr = DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SB_PORT_POOL_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit_port, @@ -294,6 +707,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_SB_PORT_POOL_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_sb_port_pool_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_port_pool_set_nl_policy, + .maxattr = DEVLINK_ATTR_SB_THRESHOLD, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit_port, @@ -311,6 +734,126 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_SB_TC_POOL_BIND_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_sb_tc_pool_bind_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_tc_pool_bind_set_nl_policy, + .maxattr = DEVLINK_ATTR_SB_TC_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_OCC_SNAPSHOT, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_occ_snapshot_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_occ_snapshot_nl_policy, + .maxattr = DEVLINK_ATTR_SB_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_SB_OCC_MAX_CLEAR, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_sb_occ_max_clear_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_sb_occ_max_clear_nl_policy, + .maxattr = DEVLINK_ATTR_SB_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_ESWITCH_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_eswitch_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_eswitch_get_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_ESWITCH_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_eswitch_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_eswitch_set_nl_policy, + .maxattr = DEVLINK_ATTR_ESWITCH_ENCAP_MODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_table_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_table_get_nl_policy, + .maxattr = DEVLINK_ATTR_DPIPE_TABLE_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_entries_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_entries_get_nl_policy, + .maxattr = DEVLINK_ATTR_DPIPE_TABLE_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_HEADERS_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_headers_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_headers_get_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_dpipe_table_counters_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_dpipe_table_counters_set_nl_policy, + .maxattr = DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RESOURCE_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_resource_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_resource_set_nl_policy, + .maxattr = DEVLINK_ATTR_RESOURCE_SIZE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RESOURCE_DUMP, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_resource_dump_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_resource_dump_nl_policy, + .maxattr = DEVLINK_ATTR_DEV_NAME, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RELOAD, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_reload_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_reload_nl_policy, + .maxattr = DEVLINK_ATTR_RELOAD_LIMITS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_PARAM_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -328,6 +871,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_PARAM_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_param_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_param_set_nl_policy, + .maxattr = DEVLINK_ATTR_PARAM_VALUE_CMODE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_REGION_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit_port_optional, @@ -345,6 +898,60 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_REGION_NEW, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_region_new_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_region_new_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_SNAPSHOT_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_REGION_DEL, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_region_del_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_region_del_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_SNAPSHOT_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_REGION_READ, + .validate = GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_region_read_dumpit, + .policy = devlink_region_read_nl_policy, + .maxattr = DEVLINK_ATTR_REGION_DIRECT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_param_get_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_param_get_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .validate = GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_port_param_get_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port, + .doit = devlink_nl_port_param_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_port_param_set_nl_policy, + .maxattr = DEVLINK_ATTR_PORT_INDEX, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_INFO_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -378,6 +985,64 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_set_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_recover_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_recover_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_diagnose_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_diagnose_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .validate = GENL_DONT_VALIDATE_DUMP_STRICT, + .dumpit = devlink_nl_health_reporter_dump_get_dumpit, + .policy = devlink_health_reporter_dump_get_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_dump_clear_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_dump_clear_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_FLASH_UPDATE, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_flash_update_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_flash_update_nl_policy, + .maxattr = DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_TRAP_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -395,6 +1060,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_TRAP_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_set_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_ACTION, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_TRAP_GROUP_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -412,6 +1087,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_TRAP_GROUP_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_group_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_group_set_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_POLICER_ID, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_TRAP_POLICER_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -429,6 +1114,26 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_TRAP_POLICER_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_trap_policer_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_trap_policer_set_nl_policy, + .maxattr = DEVLINK_ATTR_TRAP_POLICER_BURST, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit_port_optional, + .doit = devlink_nl_health_reporter_test_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_health_reporter_test_nl_policy, + .maxattr = DEVLINK_ATTR_HEALTH_REPORTER_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_RATE_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -446,6 +1151,36 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_RATE_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_set_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RATE_NEW, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_new_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_new_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_TX_WEIGHT, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { + .cmd = DEVLINK_CMD_RATE_DEL, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_rate_del_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_rate_del_nl_policy, + .maxattr = DEVLINK_ATTR_RATE_NODE_NAME, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_LINECARD_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -463,6 +1198,16 @@ const struct genl_split_ops devlink_nl_ops[32] = { .flags = GENL_CMD_CAP_DUMP, }, { + .cmd = DEVLINK_CMD_LINECARD_SET, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_linecard_set_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_linecard_set_nl_policy, + .maxattr = DEVLINK_ATTR_LINECARD_TYPE, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, + { .cmd = DEVLINK_CMD_SELFTESTS_GET, .validate = GENL_DONT_VALIDATE_STRICT, .pre_doit = devlink_nl_pre_doit, @@ -478,4 +1223,14 @@ const struct genl_split_ops devlink_nl_ops[32] = { .dumpit = devlink_nl_selftests_get_dumpit, .flags = GENL_CMD_CAP_DUMP, }, + { + .cmd = DEVLINK_CMD_SELFTESTS_RUN, + .validate = GENL_DONT_VALIDATE_STRICT, + .pre_doit = devlink_nl_pre_doit, + .doit = devlink_nl_selftests_run_doit, + .post_doit = devlink_nl_post_doit, + .policy = devlink_selftests_run_nl_policy, + .maxattr = DEVLINK_ATTR_SELFTESTS, + .flags = GENL_ADMIN_PERM | GENL_CMD_CAP_DO, + }, }; diff --git a/net/devlink/netlink_gen.h b/net/devlink/netlink_gen.h index f8bbc93e39be..0e9e89c31c31 100644 --- a/net/devlink/netlink_gen.h +++ b/net/devlink/netlink_gen.h @@ -11,8 +11,12 @@ #include <uapi/linux/devlink.h> +/* Common nested types */ +extern const struct nla_policy devlink_dl_port_function_nl_policy[DEVLINK_PORT_FN_ATTR_CAPS + 1]; +extern const struct nla_policy devlink_dl_selftest_id_nl_policy[DEVLINK_ATTR_SELFTEST_ID_FLASH + 1]; + /* Ops table for devlink */ -extern const struct genl_split_ops devlink_nl_ops[32]; +extern const struct genl_split_ops devlink_nl_ops[73]; int devlink_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb, struct genl_info *info); @@ -30,25 +34,61 @@ int devlink_nl_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int devlink_nl_port_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_port_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int devlink_nl_sb_pool_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_port_pool_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_port_pool_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb, + struct genl_info *info); int devlink_nl_sb_tc_pool_bind_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_sb_tc_pool_bind_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_dpipe_table_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_dpipe_entries_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_dpipe_headers_get_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_dpipe_table_counters_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_reload_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_param_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_param_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_region_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_region_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_region_read_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_port_param_get_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_port_param_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_port_param_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_info_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_info_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); @@ -56,24 +96,46 @@ int devlink_nl_health_reporter_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_health_reporter_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_dump_get_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int devlink_nl_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_flash_update_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_group_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_group_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_policer_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_trap_policer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_trap_policer_set_doit(struct sk_buff *skb, + struct genl_info *info); +int devlink_nl_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info); int devlink_nl_rate_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_rate_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info); +int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_linecard_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_linecard_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_linecard_set_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_selftests_get_doit(struct sk_buff *skb, struct genl_info *info); int devlink_nl_selftests_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb); +int devlink_nl_selftests_run_doit(struct sk_buff *skb, struct genl_info *info); #endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/net/devlink/param.c b/net/devlink/param.c index 31275f9d4cb7..d74df09311a9 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -581,7 +581,7 @@ static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, return 0; } -int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_param_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -589,22 +589,22 @@ int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, struct genl_info *info) info, DEVLINK_CMD_PARAM_NEW); } -int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, - struct netlink_callback *cb) +int devlink_nl_port_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) { NL_SET_ERR_MSG(cb->extack, "Port params are not supported"); return msg->len; } -int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_param_get_doit(struct sk_buff *skb, + struct genl_info *info) { NL_SET_ERR_MSG(info->extack, "Port params are not supported"); return -EINVAL; } -int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_param_set_doit(struct sk_buff *skb, + struct genl_info *info) { NL_SET_ERR_MSG(info->extack, "Port params are not supported"); return -EINVAL; diff --git a/net/devlink/port.c b/net/devlink/port.c index 4e9003242448..7634f187fa50 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -772,7 +772,7 @@ static int devlink_port_function_set(struct devlink_port *port, return err; } -int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; int err; @@ -798,7 +798,7 @@ int devlink_nl_cmd_port_set_doit(struct sk_buff *skb, struct genl_info *info) return 0; } -int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_split_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -829,8 +829,7 @@ int devlink_nl_cmd_port_split_doit(struct sk_buff *skb, struct genl_info *info) info->extack); } -int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_port_unsplit_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -840,7 +839,7 @@ int devlink_nl_cmd_port_unsplit_doit(struct sk_buff *skb, return devlink_port->ops->port_unsplit(devlink, devlink_port, info->extack); } -int devlink_nl_cmd_port_new_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_new_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink_port_new_attrs new_attrs = {}; @@ -904,7 +903,7 @@ err_out_port_del: return err; } -int devlink_nl_cmd_port_del_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_port_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct netlink_ext_ack *extack = info->extack; diff --git a/net/devlink/rate.c b/net/devlink/rate.c index dff1593b8406..94b289b93ff2 100644 --- a/net/devlink/rate.c +++ b/net/devlink/rate.c @@ -458,7 +458,7 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, return true; } -int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_rate_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_rate *devlink_rate; @@ -480,7 +480,7 @@ int devlink_nl_cmd_rate_set_doit(struct sk_buff *skb, struct genl_info *info) return err; } -int devlink_nl_cmd_rate_new_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_rate_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_rate *rate_node; @@ -536,7 +536,7 @@ err_strdup: return err; } -int devlink_nl_cmd_rate_del_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_rate_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_rate *rate_node; diff --git a/net/devlink/region.c b/net/devlink/region.c index d197cdb662db..0aab7b82d678 100644 --- a/net/devlink/region.c +++ b/net/devlink/region.c @@ -588,7 +588,7 @@ int devlink_nl_region_get_dumpit(struct sk_buff *skb, return devlink_nl_dumpit(skb, cb, devlink_nl_region_get_dump_one); } -int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_region_del_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; @@ -633,7 +633,7 @@ int devlink_nl_cmd_region_del(struct sk_buff *skb, struct genl_info *info) return 0; } -int devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_region_new_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; @@ -863,8 +863,8 @@ devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, curr_offset, chunk_size, chunk); } -int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, - struct netlink_callback *cb) +int devlink_nl_region_read_dumpit(struct sk_buff *skb, + struct netlink_callback *cb) { const struct genl_dumpit_info *info = genl_dumpit_info(cb); struct devlink_nl_dump_state *state = devlink_dump_state(cb); diff --git a/net/devlink/resource.c b/net/devlink/resource.c index c8b615e4c385..594c8aeb3bfa 100644 --- a/net/devlink/resource.c +++ b/net/devlink/resource.c @@ -105,7 +105,7 @@ devlink_resource_validate_size(struct devlink_resource *resource, u64 size, return err; } -int devlink_nl_cmd_resource_set(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_resource_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_resource *resource; @@ -285,7 +285,7 @@ err_resource_put: return err; } -int devlink_nl_cmd_resource_dump(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_resource_dump_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; diff --git a/net/devlink/sb.c b/net/devlink/sb.c index bd677fff5ec8..0a76bb32502b 100644 --- a/net/devlink/sb.c +++ b/net/devlink/sb.c @@ -413,7 +413,7 @@ static int devlink_sb_pool_set(struct devlink *devlink, unsigned int sb_index, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_sb_pool_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; enum devlink_sb_threshold_type threshold_type; @@ -621,8 +621,8 @@ static int devlink_sb_port_pool_set(struct devlink_port *devlink_port, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_port_pool_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_port_pool_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -861,8 +861,8 @@ static int devlink_sb_tc_pool_bind_set(struct devlink_port *devlink_port, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_tc_pool_bind_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_port *devlink_port = info->user_ptr[1]; struct devlink *devlink = info->user_ptr[0]; @@ -900,8 +900,7 @@ int devlink_nl_cmd_sb_tc_pool_bind_set_doit(struct sk_buff *skb, pool_index, threshold, info->extack); } -int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_occ_snapshot_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; @@ -916,8 +915,8 @@ int devlink_nl_cmd_sb_occ_snapshot_doit(struct sk_buff *skb, return -EOPNOTSUPP; } -int devlink_nl_cmd_sb_occ_max_clear_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_sb_occ_max_clear_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; const struct devlink_ops *ops = devlink->ops; diff --git a/net/devlink/trap.c b/net/devlink/trap.c index c26bf9b29bca..c26313e7ca08 100644 --- a/net/devlink/trap.c +++ b/net/devlink/trap.c @@ -414,7 +414,7 @@ static int devlink_trap_action_set(struct devlink *devlink, info->extack); } -int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, struct genl_info *info) +int devlink_nl_trap_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; @@ -684,8 +684,7 @@ static int devlink_trap_group_set(struct devlink *devlink, return 0; } -int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_group_set_doit(struct sk_buff *skb, struct genl_info *info) { struct netlink_ext_ack *extack = info->extack; struct devlink *devlink = info->user_ptr[0]; @@ -926,8 +925,8 @@ devlink_trap_policer_set(struct devlink *devlink, return 0; } -int devlink_nl_cmd_trap_policer_set_doit(struct sk_buff *skb, - struct genl_info *info) +int devlink_nl_trap_policer_set_doit(struct sk_buff *skb, + struct genl_info *info) { struct devlink_trap_policer_item *policer_item; struct netlink_ext_ack *extack = info->extack; diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 12e305824a96..8a1894a42552 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -8,16 +8,16 @@ endif # the core obj-$(CONFIG_NET_DSA) += dsa_core.o dsa_core-y += \ + conduit.o \ devlink.o \ dsa.o \ - master.o \ netlink.o \ port.o \ - slave.o \ switch.o \ tag.o \ tag_8021q.o \ - trace.o + trace.o \ + user.o # tagging formats obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o diff --git a/net/dsa/master.c b/net/dsa/conduit.c index 6be89ab0cc01..3dfdb3cb47dc 100644 --- a/net/dsa/master.c +++ b/net/dsa/conduit.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * Handling of a master device, switching frames via its switch fabric CPU port + * Handling of a conduit device, switching frames via its switch fabric CPU port * * Copyright (c) 2017 Savoir-faire Linux Inc. * Vivien Didelot <[email protected]> @@ -11,12 +11,12 @@ #include <linux/netlink.h> #include <net/dsa.h> +#include "conduit.h" #include "dsa.h" -#include "master.h" #include "port.h" #include "tag.h" -static int dsa_master_get_regs_len(struct net_device *dev) +static int dsa_conduit_get_regs_len(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -45,8 +45,8 @@ static int dsa_master_get_regs_len(struct net_device *dev) return ret; } -static void dsa_master_get_regs(struct net_device *dev, - struct ethtool_regs *regs, void *data) +static void dsa_conduit_get_regs(struct net_device *dev, + struct ethtool_regs *regs, void *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -80,9 +80,9 @@ static void dsa_master_get_regs(struct net_device *dev, } } -static void dsa_master_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) +static void dsa_conduit_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -99,9 +99,9 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, ds->ops->get_ethtool_stats(ds, port, data + count); } -static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) +static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -125,7 +125,7 @@ static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, ds->ops->get_ethtool_phy_stats(ds, port, data + count); } -static int dsa_master_get_sset_count(struct net_device *dev, int sset) +static int dsa_conduit_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -147,8 +147,8 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset) return count; } -static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, - uint8_t *data) +static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset, + uint8_t *data) { struct dsa_port *cpu_dp = dev->dsa_ptr; const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; @@ -195,12 +195,12 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, } } -/* Deny PTP operations on master if there is at least one switch in the tree +/* Deny PTP operations on conduit if there is at least one switch in the tree * that is PTP capable. */ -int __dsa_master_hwtstamp_validate(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack) +int __dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch *ds = cpu_dp->ds; @@ -212,7 +212,7 @@ int __dsa_master_hwtstamp_validate(struct net_device *dev, list_for_each_entry(dp, &dst->ports, list) { if (dsa_port_supports_hwtstamp(dp)) { NL_SET_ERR_MSG(extack, - "HW timestamping not allowed on DSA master when switch supports the operation"); + "HW timestamping not allowed on DSA conduit when switch supports the operation"); return -EBUSY; } } @@ -220,7 +220,7 @@ int __dsa_master_hwtstamp_validate(struct net_device *dev, return 0; } -static int dsa_master_ethtool_setup(struct net_device *dev) +static int dsa_conduit_ethtool_setup(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch *ds = cpu_dp->ds; @@ -237,19 +237,19 @@ static int dsa_master_ethtool_setup(struct net_device *dev) if (cpu_dp->orig_ethtool_ops) memcpy(ops, cpu_dp->orig_ethtool_ops, sizeof(*ops)); - ops->get_regs_len = dsa_master_get_regs_len; - ops->get_regs = dsa_master_get_regs; - ops->get_sset_count = dsa_master_get_sset_count; - ops->get_ethtool_stats = dsa_master_get_ethtool_stats; - ops->get_strings = dsa_master_get_strings; - ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats; + ops->get_regs_len = dsa_conduit_get_regs_len; + ops->get_regs = dsa_conduit_get_regs; + ops->get_sset_count = dsa_conduit_get_sset_count; + ops->get_ethtool_stats = dsa_conduit_get_ethtool_stats; + ops->get_strings = dsa_conduit_get_strings; + ops->get_ethtool_phy_stats = dsa_conduit_get_ethtool_phy_stats; dev->ethtool_ops = ops; return 0; } -static void dsa_master_ethtool_teardown(struct net_device *dev) +static void dsa_conduit_ethtool_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -260,16 +260,16 @@ static void dsa_master_ethtool_teardown(struct net_device *dev) cpu_dp->orig_ethtool_ops = NULL; } -/* Keep the master always promiscuous if the tagging protocol requires that +/* Keep the conduit always promiscuous if the tagging protocol requires that * (garbles MAC DA) or if it doesn't support unicast filtering, case in which * it would revert to promiscuous mode as soon as we call dev_uc_add() on it * anyway. */ -static void dsa_master_set_promiscuity(struct net_device *dev, int inc) +static void dsa_conduit_set_promiscuity(struct net_device *dev, int inc) { const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops; - if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_master) + if ((dev->priv_flags & IFF_UNICAST_FLT) && !ops->promisc_on_conduit) return; ASSERT_RTNL(); @@ -336,17 +336,17 @@ out: } static DEVICE_ATTR_RW(tagging); -static struct attribute *dsa_slave_attrs[] = { +static struct attribute *dsa_user_attrs[] = { &dev_attr_tagging.attr, NULL }; static const struct attribute_group dsa_group = { .name = "dsa", - .attrs = dsa_slave_attrs, + .attrs = dsa_user_attrs, }; -static void dsa_master_reset_mtu(struct net_device *dev) +static void dsa_conduit_reset_mtu(struct net_device *dev) { int err; @@ -356,7 +356,7 @@ static void dsa_master_reset_mtu(struct net_device *dev) "Unable to reset MTU to exclude DSA overheads\n"); } -int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) +int dsa_conduit_setup(struct net_device *dev, struct dsa_port *cpu_dp) { const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; @@ -365,7 +365,7 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); - /* The DSA master must use SET_NETDEV_DEV for this to work. */ + /* The DSA conduit must use SET_NETDEV_DEV for this to work. */ if (!netif_is_lag_master(dev)) { consumer_link = device_link_add(ds->dev, dev->dev.parent, DL_FLAG_AUTOREMOVE_CONSUMER); @@ -376,7 +376,7 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) } /* The switch driver may not implement ->port_change_mtu(), case in - * which dsa_slave_change_mtu() will not update the master MTU either, + * which dsa_user_change_mtu() will not update the conduit MTU either, * so we need to do that here. */ ret = dev_set_mtu(dev, mtu); @@ -392,9 +392,9 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) dev->dsa_ptr = cpu_dp; - dsa_master_set_promiscuity(dev, 1); + dsa_conduit_set_promiscuity(dev, 1); - ret = dsa_master_ethtool_setup(dev); + ret = dsa_conduit_ethtool_setup(dev); if (ret) goto out_err_reset_promisc; @@ -405,18 +405,18 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) return ret; out_err_ethtool_teardown: - dsa_master_ethtool_teardown(dev); + dsa_conduit_ethtool_teardown(dev); out_err_reset_promisc: - dsa_master_set_promiscuity(dev, -1); + dsa_conduit_set_promiscuity(dev, -1); return ret; } -void dsa_master_teardown(struct net_device *dev) +void dsa_conduit_teardown(struct net_device *dev) { sysfs_remove_group(&dev->dev.kobj, &dsa_group); - dsa_master_ethtool_teardown(dev); - dsa_master_reset_mtu(dev); - dsa_master_set_promiscuity(dev, -1); + dsa_conduit_ethtool_teardown(dev); + dsa_conduit_reset_mtu(dev); + dsa_conduit_set_promiscuity(dev, -1); dev->dsa_ptr = NULL; @@ -427,40 +427,40 @@ void dsa_master_teardown(struct net_device *dev) wmb(); } -int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack) +int dsa_conduit_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) { - bool master_setup = false; + bool conduit_setup = false; int err; if (!netdev_uses_dsa(lag_dev)) { - err = dsa_master_setup(lag_dev, cpu_dp); + err = dsa_conduit_setup(lag_dev, cpu_dp); if (err) return err; - master_setup = true; + conduit_setup = true; } err = dsa_port_lag_join(cpu_dp, lag_dev, uinfo, extack); if (err) { NL_SET_ERR_MSG_WEAK_MOD(extack, "CPU port failed to join LAG"); - goto out_master_teardown; + goto out_conduit_teardown; } return 0; -out_master_teardown: - if (master_setup) - dsa_master_teardown(lag_dev); +out_conduit_teardown: + if (conduit_setup) + dsa_conduit_teardown(lag_dev); return err; } -/* Tear down a master if there isn't any other user port on it, +/* Tear down a conduit if there isn't any other user port on it, * optionally also destroying LAG information. */ -void dsa_master_lag_teardown(struct net_device *lag_dev, - struct dsa_port *cpu_dp) +void dsa_conduit_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp) { struct net_device *upper; struct list_head *iter; @@ -468,8 +468,8 @@ void dsa_master_lag_teardown(struct net_device *lag_dev, dsa_port_lag_leave(cpu_dp, lag_dev); netdev_for_each_upper_dev_rcu(lag_dev, upper, iter) - if (dsa_slave_dev_check(upper)) + if (dsa_user_dev_check(upper)) return; - dsa_master_teardown(lag_dev); + dsa_conduit_teardown(lag_dev); } diff --git a/net/dsa/conduit.h b/net/dsa/conduit.h new file mode 100644 index 000000000000..31f8834f54bb --- /dev/null +++ b/net/dsa/conduit.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_CONDUIT_H +#define __DSA_CONDUIT_H + +struct dsa_port; +struct net_device; +struct netdev_lag_upper_info; +struct netlink_ext_ack; + +int dsa_conduit_setup(struct net_device *dev, struct dsa_port *cpu_dp); +void dsa_conduit_teardown(struct net_device *dev); +int dsa_conduit_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack); +void dsa_conduit_lag_teardown(struct net_device *lag_dev, + struct dsa_port *cpu_dp); +int __dsa_conduit_hwtstamp_validate(struct net_device *dev, + const struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); + +#endif diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c index ccbdb98109f8..ac7be864e80d 100644 --- a/net/dsa/dsa.c +++ b/net/dsa/dsa.c @@ -20,14 +20,14 @@ #include <net/dsa_stubs.h> #include <net/sch_generic.h> +#include "conduit.h" #include "devlink.h" #include "dsa.h" -#include "master.h" #include "netlink.h" #include "port.h" -#include "slave.h" #include "switch.h" #include "tag.h" +#include "user.h" #define DSA_MAX_NUM_OFFLOADING_BRIDGES BITS_PER_LONG @@ -365,18 +365,18 @@ static struct dsa_port *dsa_tree_find_first_cpu(struct dsa_switch_tree *dst) return NULL; } -struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst) +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst) { struct device_node *ethernet; - struct net_device *master; + struct net_device *conduit; struct dsa_port *cpu_dp; cpu_dp = dsa_tree_find_first_cpu(dst); ethernet = of_parse_phandle(cpu_dp->dn, "ethernet", 0); - master = of_find_net_device_by_node(ethernet); + conduit = of_find_net_device_by_node(ethernet); of_node_put(ethernet); - return master; + return conduit; } /* Assign the default CPU port (the first one in the tree) to all ports of the @@ -517,7 +517,7 @@ static int dsa_port_setup(struct dsa_port *dp) break; case DSA_PORT_TYPE_USER: of_get_mac_address(dp->dn, dp->mac); - err = dsa_slave_create(dp); + err = dsa_user_create(dp); break; } @@ -554,9 +554,9 @@ static void dsa_port_teardown(struct dsa_port *dp) dsa_shared_port_link_unregister_of(dp); break; case DSA_PORT_TYPE_USER: - if (dp->slave) { - dsa_slave_destroy(dp->slave); - dp->slave = NULL; + if (dp->user) { + dsa_user_destroy(dp->user); + dp->user = NULL; } break; } @@ -632,9 +632,9 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (ds->setup) return 0; - /* Initialize ds->phys_mii_mask before registering the slave MDIO bus + /* Initialize ds->phys_mii_mask before registering the user MDIO bus * driver and before ops->setup() has run, since the switch drivers and - * the slave MDIO bus driver rely on these values for probing PHY + * the user MDIO bus driver rely on these values for probing PHY * devices or not */ ds->phys_mii_mask |= dsa_user_ports(ds); @@ -657,21 +657,21 @@ static int dsa_switch_setup(struct dsa_switch *ds) if (err) goto teardown; - if (!ds->slave_mii_bus && ds->ops->phy_read) { - ds->slave_mii_bus = mdiobus_alloc(); - if (!ds->slave_mii_bus) { + if (!ds->user_mii_bus && ds->ops->phy_read) { + ds->user_mii_bus = mdiobus_alloc(); + if (!ds->user_mii_bus) { err = -ENOMEM; goto teardown; } - dsa_slave_mii_bus_init(ds); + dsa_user_mii_bus_init(ds); dn = of_get_child_by_name(ds->dev->of_node, "mdio"); - err = of_mdiobus_register(ds->slave_mii_bus, dn); + err = of_mdiobus_register(ds->user_mii_bus, dn); of_node_put(dn); if (err < 0) - goto free_slave_mii_bus; + goto free_user_mii_bus; } dsa_switch_devlink_register(ds); @@ -679,9 +679,9 @@ static int dsa_switch_setup(struct dsa_switch *ds) ds->setup = true; return 0; -free_slave_mii_bus: - if (ds->slave_mii_bus && ds->ops->phy_read) - mdiobus_free(ds->slave_mii_bus); +free_user_mii_bus: + if (ds->user_mii_bus && ds->ops->phy_read) + mdiobus_free(ds->user_mii_bus); teardown: if (ds->ops->teardown) ds->ops->teardown(ds); @@ -699,10 +699,10 @@ static void dsa_switch_teardown(struct dsa_switch *ds) dsa_switch_devlink_unregister(ds); - if (ds->slave_mii_bus && ds->ops->phy_read) { - mdiobus_unregister(ds->slave_mii_bus); - mdiobus_free(ds->slave_mii_bus); - ds->slave_mii_bus = NULL; + if (ds->user_mii_bus && ds->ops->phy_read) { + mdiobus_unregister(ds->user_mii_bus); + mdiobus_free(ds->user_mii_bus); + ds->user_mii_bus = NULL; } dsa_switch_teardown_tag_protocol(ds); @@ -793,7 +793,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) return err; } -static int dsa_tree_setup_master(struct dsa_switch_tree *dst) +static int dsa_tree_setup_conduit(struct dsa_switch_tree *dst) { struct dsa_port *cpu_dp; int err = 0; @@ -801,18 +801,18 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) rtnl_lock(); dsa_tree_for_each_cpu_port(cpu_dp, dst) { - struct net_device *master = cpu_dp->master; - bool admin_up = (master->flags & IFF_UP) && - !qdisc_tx_is_noop(master); + struct net_device *conduit = cpu_dp->conduit; + bool admin_up = (conduit->flags & IFF_UP) && + !qdisc_tx_is_noop(conduit); - err = dsa_master_setup(master, cpu_dp); + err = dsa_conduit_setup(conduit, cpu_dp); if (err) break; - /* Replay master state event */ - dsa_tree_master_admin_state_change(dst, master, admin_up); - dsa_tree_master_oper_state_change(dst, master, - netif_oper_up(master)); + /* Replay conduit state event */ + dsa_tree_conduit_admin_state_change(dst, conduit, admin_up); + dsa_tree_conduit_oper_state_change(dst, conduit, + netif_oper_up(conduit)); } rtnl_unlock(); @@ -820,22 +820,22 @@ static int dsa_tree_setup_master(struct dsa_switch_tree *dst) return err; } -static void dsa_tree_teardown_master(struct dsa_switch_tree *dst) +static void dsa_tree_teardown_conduit(struct dsa_switch_tree *dst) { struct dsa_port *cpu_dp; rtnl_lock(); dsa_tree_for_each_cpu_port(cpu_dp, dst) { - struct net_device *master = cpu_dp->master; + struct net_device *conduit = cpu_dp->conduit; /* Synthesizing an "admin down" state is sufficient for - * the switches to get a notification if the master is + * the switches to get a notification if the conduit is * currently up and running. */ - dsa_tree_master_admin_state_change(dst, master, false); + dsa_tree_conduit_admin_state_change(dst, conduit, false); - dsa_master_teardown(master); + dsa_conduit_teardown(conduit); } rtnl_unlock(); @@ -894,13 +894,13 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) if (err) goto teardown_switches; - err = dsa_tree_setup_master(dst); + err = dsa_tree_setup_conduit(dst); if (err) goto teardown_ports; err = dsa_tree_setup_lags(dst); if (err) - goto teardown_master; + goto teardown_conduit; dst->setup = true; @@ -908,8 +908,8 @@ static int dsa_tree_setup(struct dsa_switch_tree *dst) return 0; -teardown_master: - dsa_tree_teardown_master(dst); +teardown_conduit: + dsa_tree_teardown_conduit(dst); teardown_ports: dsa_tree_teardown_ports(dst); teardown_switches: @@ -929,7 +929,7 @@ static void dsa_tree_teardown(struct dsa_switch_tree *dst) dsa_tree_teardown_lags(dst); - dsa_tree_teardown_master(dst); + dsa_tree_teardown_conduit(dst); dsa_tree_teardown_ports(dst); @@ -978,7 +978,7 @@ out_disconnect: return err; } -/* Since the dsa/tagging sysfs device attribute is per master, the assumption +/* Since the dsa/tagging sysfs device attribute is per conduit, the assumption * is that all DSA switches within a tree share the same tagger, otherwise * they would have formed disjoint trees (different "dsa,member" values). */ @@ -999,10 +999,10 @@ int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, * restriction, there needs to be another mutex which serializes this. */ dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp)->flags & IFF_UP) + if (dsa_port_to_conduit(dp)->flags & IFF_UP) goto out_unlock; - if (dp->slave->flags & IFF_UP) + if (dp->user->flags & IFF_UP) goto out_unlock; } @@ -1028,62 +1028,62 @@ out_unlock: return err; } -static void dsa_tree_master_state_change(struct dsa_switch_tree *dst, - struct net_device *master) +static void dsa_tree_conduit_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit) { - struct dsa_notifier_master_state_info info; - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_notifier_conduit_state_info info; + struct dsa_port *cpu_dp = conduit->dsa_ptr; - info.master = master; - info.operational = dsa_port_master_is_operational(cpu_dp); + info.conduit = conduit; + info.operational = dsa_port_conduit_is_operational(cpu_dp); - dsa_tree_notify(dst, DSA_NOTIFIER_MASTER_STATE_CHANGE, &info); + dsa_tree_notify(dst, DSA_NOTIFIER_CONDUIT_STATE_CHANGE, &info); } -void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up) +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; bool notify = false; - /* Don't keep track of admin state on LAG DSA masters, - * but rather just of physical DSA masters + /* Don't keep track of admin state on LAG DSA conduits, + * but rather just of physical DSA conduits */ - if (netif_is_lag_master(master)) + if (netif_is_lag_master(conduit)) return; - if ((dsa_port_master_is_operational(cpu_dp)) != - (up && cpu_dp->master_oper_up)) + if ((dsa_port_conduit_is_operational(cpu_dp)) != + (up && cpu_dp->conduit_oper_up)) notify = true; - cpu_dp->master_admin_up = up; + cpu_dp->conduit_admin_up = up; if (notify) - dsa_tree_master_state_change(dst, master); + dsa_tree_conduit_state_change(dst, conduit); } -void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up) +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; bool notify = false; - /* Don't keep track of oper state on LAG DSA masters, - * but rather just of physical DSA masters + /* Don't keep track of oper state on LAG DSA conduits, + * but rather just of physical DSA conduits */ - if (netif_is_lag_master(master)) + if (netif_is_lag_master(conduit)) return; - if ((dsa_port_master_is_operational(cpu_dp)) != - (cpu_dp->master_admin_up && up)) + if ((dsa_port_conduit_is_operational(cpu_dp)) != + (cpu_dp->conduit_admin_up && up)) notify = true; - cpu_dp->master_oper_up = up; + cpu_dp->conduit_oper_up = up; if (notify) - dsa_tree_master_state_change(dst, master); + dsa_tree_conduit_state_change(dst, conduit); } static struct dsa_port *dsa_port_touch(struct dsa_switch *ds, int index) @@ -1129,7 +1129,7 @@ static int dsa_port_parse_dsa(struct dsa_port *dp) } static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, - struct net_device *master) + struct net_device *conduit) { enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; struct dsa_switch *mds, *ds = dp->ds; @@ -1140,21 +1140,21 @@ static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, * happens the switch driver may want to know if its tagging protocol * is going to work in such a configuration. */ - if (dsa_slave_dev_check(master)) { - mdp = dsa_slave_to_port(master); + if (dsa_user_dev_check(conduit)) { + mdp = dsa_user_to_port(conduit); mds = mdp->ds; mdp_upstream = dsa_upstream_port(mds, mdp->index); tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, DSA_TAG_PROTO_NONE); } - /* If the master device is not itself a DSA slave in a disjoint DSA + /* If the conduit device is not itself a DSA user in a disjoint DSA * tree, then return immediately. */ return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); } -static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, +static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *conduit, const char *user_protocol) { const struct dsa_device_ops *tag_ops = NULL; @@ -1163,7 +1163,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, enum dsa_tag_protocol default_proto; /* Find out which protocol the switch would prefer. */ - default_proto = dsa_get_tag_protocol(dp, master); + default_proto = dsa_get_tag_protocol(dp, conduit); if (dst->default_proto) { if (dst->default_proto != default_proto) { dev_err(ds->dev, @@ -1218,7 +1218,7 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master, dst->tag_ops = tag_ops; } - dp->master = master; + dp->conduit = conduit; dp->type = DSA_PORT_TYPE_CPU; dsa_port_set_tag_protocol(dp, dst->tag_ops); dp->dst = dst; @@ -1248,16 +1248,16 @@ static int dsa_port_parse_of(struct dsa_port *dp, struct device_node *dn) dp->dn = dn; if (ethernet) { - struct net_device *master; + struct net_device *conduit; const char *user_protocol; - master = of_find_net_device_by_node(ethernet); + conduit = of_find_net_device_by_node(ethernet); of_node_put(ethernet); - if (!master) + if (!conduit) return -EPROBE_DEFER; user_protocol = of_get_property(dn, "dsa-tag-protocol", NULL); - return dsa_port_parse_cpu(dp, master, user_protocol); + return dsa_port_parse_cpu(dp, conduit, user_protocol); } if (link) @@ -1412,15 +1412,15 @@ static int dsa_port_parse(struct dsa_port *dp, const char *name, struct device *dev) { if (!strcmp(name, "cpu")) { - struct net_device *master; + struct net_device *conduit; - master = dsa_dev_to_net_device(dev); - if (!master) + conduit = dsa_dev_to_net_device(dev); + if (!conduit) return -EPROBE_DEFER; - dev_put(master); + dev_put(conduit); - return dsa_port_parse_cpu(dp, master, NULL); + return dsa_port_parse_cpu(dp, conduit, NULL); } if (!strcmp(name, "dsa")) @@ -1566,14 +1566,14 @@ void dsa_unregister_switch(struct dsa_switch *ds) } EXPORT_SYMBOL_GPL(dsa_unregister_switch); -/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is +/* If the DSA conduit chooses to unregister its net_device on .shutdown, DSA is * blocking that operation from completion, due to the dev_hold taken inside - * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of - * the DSA master, so that the system can reboot successfully. + * netdev_upper_dev_link. Unlink the DSA user interfaces from being uppers of + * the DSA conduit, so that the system can reboot successfully. */ void dsa_switch_shutdown(struct dsa_switch *ds) { - struct net_device *master, *slave_dev; + struct net_device *conduit, *user_dev; struct dsa_port *dp; mutex_lock(&dsa2_mutex); @@ -1584,17 +1584,17 @@ void dsa_switch_shutdown(struct dsa_switch *ds) rtnl_lock(); dsa_switch_for_each_user_port(dp, ds) { - master = dsa_port_to_master(dp); - slave_dev = dp->slave; + conduit = dsa_port_to_conduit(dp); + user_dev = dp->user; - netdev_upper_dev_unlink(master, slave_dev); + netdev_upper_dev_unlink(conduit, user_dev); } - /* Disconnect from further netdevice notifiers on the master, + /* Disconnect from further netdevice notifiers on the conduit, * since netdev_uses_dsa() will now return false. */ dsa_switch_for_each_cpu_port(dp, ds) - dp->master->dsa_ptr = NULL; + dp->conduit->dsa_ptr = NULL; rtnl_unlock(); out: @@ -1605,7 +1605,7 @@ EXPORT_SYMBOL_GPL(dsa_switch_shutdown); #ifdef CONFIG_PM_SLEEP static bool dsa_port_is_initialized(const struct dsa_port *dp) { - return dp->type == DSA_PORT_TYPE_USER && dp->slave; + return dp->type == DSA_PORT_TYPE_USER && dp->user; } int dsa_switch_suspend(struct dsa_switch *ds) @@ -1613,12 +1613,12 @@ int dsa_switch_suspend(struct dsa_switch *ds) struct dsa_port *dp; int ret = 0; - /* Suspend slave network devices */ + /* Suspend user network devices */ dsa_switch_for_each_port(dp, ds) { if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_suspend(dp->slave); + ret = dsa_user_suspend(dp->user); if (ret) return ret; } @@ -1641,12 +1641,12 @@ int dsa_switch_resume(struct dsa_switch *ds) if (ret) return ret; - /* Resume slave network devices */ + /* Resume user network devices */ dsa_switch_for_each_port(dp, ds) { if (!dsa_port_is_initialized(dp)) continue; - ret = dsa_slave_resume(dp->slave); + ret = dsa_user_resume(dp->user); if (ret) return ret; } @@ -1658,10 +1658,10 @@ EXPORT_SYMBOL_GPL(dsa_switch_resume); struct dsa_port *dsa_port_from_netdev(struct net_device *netdev) { - if (!netdev || !dsa_slave_dev_check(netdev)) + if (!netdev || !dsa_user_dev_check(netdev)) return ERR_PTR(-ENODEV); - return dsa_slave_to_port(netdev); + return dsa_user_to_port(netdev); } EXPORT_SYMBOL_GPL(dsa_port_from_netdev); @@ -1726,7 +1726,7 @@ bool dsa_mdb_present_in_other_db(struct dsa_switch *ds, int port, EXPORT_SYMBOL_GPL(dsa_mdb_present_in_other_db); static const struct dsa_stubs __dsa_stubs = { - .master_hwtstamp_validate = __dsa_master_hwtstamp_validate, + .conduit_hwtstamp_validate = __dsa_conduit_hwtstamp_validate, }; static void dsa_register_stubs(void) @@ -1748,7 +1748,7 @@ static int __init dsa_init_module(void) if (!dsa_owq) return -ENOMEM; - rc = dsa_slave_register_notifier(); + rc = dsa_user_register_notifier(); if (rc) goto register_notifier_fail; @@ -1763,7 +1763,7 @@ static int __init dsa_init_module(void) return 0; netlink_register_fail: - dsa_slave_unregister_notifier(); + dsa_user_unregister_notifier(); dev_remove_pack(&dsa_pack_type); register_notifier_fail: destroy_workqueue(dsa_owq); @@ -1778,7 +1778,7 @@ static void __exit dsa_cleanup_module(void) rtnl_link_unregister(&dsa_link_ops); - dsa_slave_unregister_notifier(); + dsa_user_unregister_notifier(); dev_remove_pack(&dsa_pack_type); destroy_workqueue(dsa_owq); } diff --git a/net/dsa/dsa.h b/net/dsa/dsa.h index b7e17ae1094d..3cc7823e9ef3 100644 --- a/net/dsa/dsa.h +++ b/net/dsa/dsa.h @@ -21,16 +21,16 @@ void dsa_lag_map(struct dsa_switch_tree *dst, struct dsa_lag *lag); void dsa_lag_unmap(struct dsa_switch_tree *dst, struct dsa_lag *lag); struct dsa_lag *dsa_tree_lag_find(struct dsa_switch_tree *dst, const struct net_device *lag_dev); -struct net_device *dsa_tree_find_first_master(struct dsa_switch_tree *dst); +struct net_device *dsa_tree_find_first_conduit(struct dsa_switch_tree *dst); int dsa_tree_change_tag_proto(struct dsa_switch_tree *dst, const struct dsa_device_ops *tag_ops, const struct dsa_device_ops *old_tag_ops); -void dsa_tree_master_admin_state_change(struct dsa_switch_tree *dst, - struct net_device *master, +void dsa_tree_conduit_admin_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, + bool up); +void dsa_tree_conduit_oper_state_change(struct dsa_switch_tree *dst, + struct net_device *conduit, bool up); -void dsa_tree_master_oper_state_change(struct dsa_switch_tree *dst, - struct net_device *master, - bool up); unsigned int dsa_bridge_num_get(const struct net_device *bridge_dev, int max); void dsa_bridge_num_put(const struct net_device *bridge_dev, unsigned int bridge_num); diff --git a/net/dsa/master.h b/net/dsa/master.h deleted file mode 100644 index 76e39d3ec909..000000000000 --- a/net/dsa/master.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -#ifndef __DSA_MASTER_H -#define __DSA_MASTER_H - -struct dsa_port; -struct net_device; -struct netdev_lag_upper_info; -struct netlink_ext_ack; - -int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); -void dsa_master_teardown(struct net_device *dev); -int dsa_master_lag_setup(struct net_device *lag_dev, struct dsa_port *cpu_dp, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack); -void dsa_master_lag_teardown(struct net_device *lag_dev, - struct dsa_port *cpu_dp); -int __dsa_master_hwtstamp_validate(struct net_device *dev, - const struct kernel_hwtstamp_config *config, - struct netlink_ext_ack *extack); - -#endif diff --git a/net/dsa/netlink.c b/net/dsa/netlink.c index bd4bbaf851de..1332e56349e5 100644 --- a/net/dsa/netlink.c +++ b/net/dsa/netlink.c @@ -5,10 +5,10 @@ #include <net/rtnetlink.h> #include "netlink.h" -#include "slave.h" +#include "user.h" static const struct nla_policy dsa_policy[IFLA_DSA_MAX + 1] = { - [IFLA_DSA_MASTER] = { .type = NLA_U32 }, + [IFLA_DSA_CONDUIT] = { .type = NLA_U32 }, }; static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], @@ -20,15 +20,15 @@ static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], if (!data) return 0; - if (data[IFLA_DSA_MASTER]) { - u32 ifindex = nla_get_u32(data[IFLA_DSA_MASTER]); - struct net_device *master; + if (data[IFLA_DSA_CONDUIT]) { + u32 ifindex = nla_get_u32(data[IFLA_DSA_CONDUIT]); + struct net_device *conduit; - master = __dev_get_by_index(dev_net(dev), ifindex); - if (!master) + conduit = __dev_get_by_index(dev_net(dev), ifindex); + if (!conduit) return -EINVAL; - err = dsa_slave_change_master(dev, master, extack); + err = dsa_user_change_conduit(dev, conduit, extack); if (err) return err; } @@ -38,15 +38,15 @@ static int dsa_changelink(struct net_device *dev, struct nlattr *tb[], static size_t dsa_get_size(const struct net_device *dev) { - return nla_total_size(sizeof(u32)) + /* IFLA_DSA_MASTER */ + return nla_total_size(sizeof(u32)) + /* IFLA_DSA_CONDUIT */ 0; } static int dsa_fill_info(struct sk_buff *skb, const struct net_device *dev) { - struct net_device *master = dsa_slave_to_master(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); - if (nla_put_u32(skb, IFLA_DSA_MASTER, master->ifindex)) + if (nla_put_u32(skb, IFLA_DSA_CONDUIT, conduit->ifindex)) return -EMSGSIZE; return 0; diff --git a/net/dsa/port.c b/net/dsa/port.c index 6e0d000a97c4..c42dac87671b 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -14,9 +14,9 @@ #include "dsa.h" #include "port.h" -#include "slave.h" #include "switch.h" #include "tag_8021q.h" +#include "user.h" /** * dsa_port_notify - Notify the switching fabric of changes to a port @@ -289,7 +289,7 @@ static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, } /* If the bridge was vlan_filtering, the bridge core doesn't trigger an - * event for changing vlan_filtering setting upon slave ports leaving + * event for changing vlan_filtering setting upon user ports leaving * it. That is a good thing, because that lets us handle it and also * handle the case where the switch's vlan_filtering setting is global * (not per port). When that happens, the correct moment to trigger the @@ -489,7 +489,7 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, .dp = dp, .extack = extack, }; - struct net_device *dev = dp->slave; + struct net_device *dev = dp->user; struct net_device *brport_dev; int err; @@ -514,8 +514,8 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, dp->bridge->tx_fwd_offload = info.tx_fwd_offload; err = switchdev_bridge_port_offload(brport_dev, dev, dp, - &dsa_slave_switchdev_notifier, - &dsa_slave_switchdev_blocking_notifier, + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier, dp->bridge->tx_fwd_offload, extack); if (err) goto out_rollback_unbridge; @@ -528,8 +528,8 @@ int dsa_port_bridge_join(struct dsa_port *dp, struct net_device *br, out_rollback_unoffload: switchdev_bridge_port_unoffload(brport_dev, dp, - &dsa_slave_switchdev_notifier, - &dsa_slave_switchdev_blocking_notifier); + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier); dsa_flush_workqueue(); out_rollback_unbridge: dsa_broadcast(DSA_NOTIFIER_BRIDGE_LEAVE, &info); @@ -547,8 +547,8 @@ void dsa_port_pre_bridge_leave(struct dsa_port *dp, struct net_device *br) return; switchdev_bridge_port_unoffload(brport_dev, dp, - &dsa_slave_switchdev_notifier, - &dsa_slave_switchdev_blocking_notifier); + &dsa_user_switchdev_notifier, + &dsa_user_switchdev_blocking_notifier); dsa_flush_workqueue(); } @@ -741,10 +741,10 @@ static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp, */ if (vlan_filtering && dsa_port_is_user(dp)) { struct net_device *br = dsa_port_bridge_dev_get(dp); - struct net_device *upper_dev, *slave = dp->slave; + struct net_device *upper_dev, *user = dp->user; struct list_head *iter; - netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { struct bridge_vlan_info br_info; u16 vid; @@ -803,9 +803,9 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, if (!ds->ops->port_vlan_filtering) return -EOPNOTSUPP; - /* We are called from dsa_slave_switchdev_blocking_event(), + /* We are called from dsa_user_switchdev_blocking_event(), * which is not under rcu_read_lock(), unlike - * dsa_slave_switchdev_event(). + * dsa_user_switchdev_event(). */ rcu_read_lock(); apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering, extack); @@ -827,24 +827,24 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, ds->vlan_filtering = vlan_filtering; dsa_switch_for_each_user_port(other_dp, ds) { - struct net_device *slave = other_dp->slave; + struct net_device *user = other_dp->user; /* We might be called in the unbind path, so not - * all slave devices might still be registered. + * all user devices might still be registered. */ - if (!slave) + if (!user) continue; - err = dsa_slave_manage_vlan_filtering(slave, - vlan_filtering); + err = dsa_user_manage_vlan_filtering(user, + vlan_filtering); if (err) goto restore; } } else { dp->vlan_filtering = vlan_filtering; - err = dsa_slave_manage_vlan_filtering(dp->slave, - vlan_filtering); + err = dsa_user_manage_vlan_filtering(dp->user, + vlan_filtering); if (err) goto restore; } @@ -863,7 +863,7 @@ restore: } /* This enforces legacy behavior for switch drivers which assume they can't - * receive VLAN configuration when enslaved to a bridge with vlan_filtering=0 + * receive VLAN configuration when joining a bridge with vlan_filtering=0 */ bool dsa_port_skip_vlan_configuration(struct dsa_port *dp) { @@ -1047,7 +1047,7 @@ int dsa_port_standalone_host_fdb_add(struct dsa_port *dp, int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, const unsigned char *addr, u16 vid) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1057,12 +1057,12 @@ int dsa_port_bridge_host_fdb_add(struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - /* Avoid a call to __dev_set_promiscuity() on the master, which + /* Avoid a call to __dev_set_promiscuity() on the conduit, which * requires rtnl_lock(), since we can't guarantee that is held here, * and we can't take it either. */ - if (master->priv_flags & IFF_UNICAST_FLT) { - err = dev_uc_add(master, addr); + if (conduit->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_add(conduit, addr); if (err) return err; } @@ -1098,7 +1098,7 @@ int dsa_port_standalone_host_fdb_del(struct dsa_port *dp, int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, const unsigned char *addr, u16 vid) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1108,8 +1108,8 @@ int dsa_port_bridge_host_fdb_del(struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - if (master->priv_flags & IFF_UNICAST_FLT) { - err = dev_uc_del(master, addr); + if (conduit->priv_flags & IFF_UNICAST_FLT) { + err = dev_uc_del(conduit, addr); if (err) return err; } @@ -1229,7 +1229,7 @@ int dsa_port_standalone_host_mdb_add(const struct dsa_port *dp, int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1239,7 +1239,7 @@ int dsa_port_bridge_host_mdb_add(const struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - err = dev_mc_add(master, mdb->addr); + err = dev_mc_add(conduit, mdb->addr); if (err) return err; @@ -1273,7 +1273,7 @@ int dsa_port_standalone_host_mdb_del(const struct dsa_port *dp, int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, const struct switchdev_obj_port_mdb *mdb) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_db db = { .type = DSA_DB_BRIDGE, .bridge = *dp->bridge, @@ -1283,7 +1283,7 @@ int dsa_port_bridge_host_mdb_del(const struct dsa_port *dp, if (!dp->ds->fdb_isolation) db.bridge.num = 0; - err = dev_mc_del(master, mdb->addr); + err = dev_mc_del(conduit, mdb->addr); if (err) return err; @@ -1318,7 +1318,7 @@ int dsa_port_host_vlan_add(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan, struct netlink_ext_ack *extack) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_notifier_vlan_info info = { .dp = dp, .vlan = vlan, @@ -1330,7 +1330,7 @@ int dsa_port_host_vlan_add(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - vlan_vid_add(master, htons(ETH_P_8021Q), vlan->vid); + vlan_vid_add(conduit, htons(ETH_P_8021Q), vlan->vid); return err; } @@ -1338,7 +1338,7 @@ int dsa_port_host_vlan_add(struct dsa_port *dp, int dsa_port_host_vlan_del(struct dsa_port *dp, const struct switchdev_obj_port_vlan *vlan) { - struct net_device *master = dsa_port_to_master(dp); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_notifier_vlan_info info = { .dp = dp, .vlan = vlan, @@ -1349,7 +1349,7 @@ int dsa_port_host_vlan_del(struct dsa_port *dp, if (err && err != -EOPNOTSUPP) return err; - vlan_vid_del(master, htons(ETH_P_8021Q), vlan->vid); + vlan_vid_del(conduit, htons(ETH_P_8021Q), vlan->vid); return err; } @@ -1398,24 +1398,24 @@ int dsa_port_mrp_del_ring_role(const struct dsa_port *dp, return ds->ops->port_mrp_del_ring_role(ds, dp->index, mrp); } -static int dsa_port_assign_master(struct dsa_port *dp, - struct net_device *master, - struct netlink_ext_ack *extack, - bool fail_on_err) +static int dsa_port_assign_conduit(struct dsa_port *dp, + struct net_device *conduit, + struct netlink_ext_ack *extack, + bool fail_on_err) { struct dsa_switch *ds = dp->ds; int port = dp->index, err; - err = ds->ops->port_change_master(ds, port, master, extack); + err = ds->ops->port_change_conduit(ds, port, conduit, extack); if (err && !fail_on_err) - dev_err(ds->dev, "port %d failed to assign master %s: %pe\n", - port, master->name, ERR_PTR(err)); + dev_err(ds->dev, "port %d failed to assign conduit %s: %pe\n", + port, conduit->name, ERR_PTR(err)); if (err && fail_on_err) return err; - dp->cpu_dp = master->dsa_ptr; - dp->cpu_port_in_lag = netif_is_lag_master(master); + dp->cpu_dp = conduit->dsa_ptr; + dp->cpu_port_in_lag = netif_is_lag_master(conduit); return 0; } @@ -1428,12 +1428,12 @@ static int dsa_port_assign_master(struct dsa_port *dp, * the old CPU port before changing it, and restore it on errors during the * bringup of the new one. */ -int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, - struct netlink_ext_ack *extack) +int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, + struct netlink_ext_ack *extack) { struct net_device *bridge_dev = dsa_port_bridge_dev_get(dp); - struct net_device *old_master = dsa_port_to_master(dp); - struct net_device *dev = dp->slave; + struct net_device *old_conduit = dsa_port_to_conduit(dp); + struct net_device *dev = dp->user; struct dsa_switch *ds = dp->ds; bool vlan_filtering; int err, tmp; @@ -1454,7 +1454,7 @@ int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, */ vlan_filtering = dsa_port_is_vlan_filtering(dp); if (vlan_filtering) { - err = dsa_slave_manage_vlan_filtering(dev, false); + err = dsa_user_manage_vlan_filtering(dev, false); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to remove standalone VLANs"); @@ -1465,16 +1465,16 @@ int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, /* Standalone addresses, and addresses of upper interfaces like * VLAN, LAG, HSR need to be migrated. */ - dsa_slave_unsync_ha(dev); + dsa_user_unsync_ha(dev); - err = dsa_port_assign_master(dp, master, extack, true); + err = dsa_port_assign_conduit(dp, conduit, extack, true); if (err) goto rewind_old_addrs; - dsa_slave_sync_ha(dev); + dsa_user_sync_ha(dev); if (vlan_filtering) { - err = dsa_slave_manage_vlan_filtering(dev, true); + err = dsa_user_manage_vlan_filtering(dev, true); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed to restore standalone VLANs"); @@ -1495,19 +1495,19 @@ int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, rewind_new_vlan: if (vlan_filtering) - dsa_slave_manage_vlan_filtering(dev, false); + dsa_user_manage_vlan_filtering(dev, false); rewind_new_addrs: - dsa_slave_unsync_ha(dev); + dsa_user_unsync_ha(dev); - dsa_port_assign_master(dp, old_master, NULL, false); + dsa_port_assign_conduit(dp, old_conduit, NULL, false); /* Restore the objects on the old CPU port */ rewind_old_addrs: - dsa_slave_sync_ha(dev); + dsa_user_sync_ha(dev); if (vlan_filtering) { - tmp = dsa_slave_manage_vlan_filtering(dev, true); + tmp = dsa_user_manage_vlan_filtering(dev, true); if (tmp) { dev_err(ds->dev, "port %d failed to restore standalone VLANs: %pe\n", @@ -1620,7 +1620,7 @@ static void dsa_port_phylink_mac_link_down(struct phylink_config *config, struct dsa_switch *ds = dp->ds; if (dsa_port_is_user(dp)) - phydev = dp->slave->phydev; + phydev = dp->user->phydev; if (!ds->ops->phylink_mac_link_down) { if (ds->ops->adjust_link && phydev) @@ -1808,7 +1808,7 @@ err_phy_connect: * their type. * * User ports with no phy-handle or fixed-link are expected to connect to an - * internal PHY located on the ds->slave_mii_bus at an MDIO address equal to + * internal PHY located on the ds->user_mii_bus at an MDIO address equal to * the port number. This description is still actively supported. * * Shared (CPU and DSA) ports with no phy-handle or fixed-link are expected to @@ -1829,7 +1829,7 @@ err_phy_connect: * a fixed-link, a phy-handle, or a managed = "in-band-status" property. * It becomes the responsibility of the driver to ensure that these ports * operate at the maximum speed (whatever this means) and will interoperate - * with the DSA master or other cascade port, since phylink methods will not be + * with the DSA conduit or other cascade port, since phylink methods will not be * invoked for them. * * If you are considering expanding this table for newly introduced switches, diff --git a/net/dsa/port.h b/net/dsa/port.h index 334879964e2c..6bc3291573c0 100644 --- a/net/dsa/port.h +++ b/net/dsa/port.h @@ -109,7 +109,7 @@ void dsa_port_hsr_leave(struct dsa_port *dp, struct net_device *hsr); int dsa_port_tag_8021q_vlan_add(struct dsa_port *dp, u16 vid, bool broadcast); void dsa_port_tag_8021q_vlan_del(struct dsa_port *dp, u16 vid, bool broadcast); void dsa_port_set_host_flood(struct dsa_port *dp, bool uc, bool mc); -int dsa_port_change_master(struct dsa_port *dp, struct net_device *master, - struct netlink_ext_ack *extack); +int dsa_port_change_conduit(struct dsa_port *dp, struct net_device *conduit, + struct netlink_ext_ack *extack); #endif diff --git a/net/dsa/slave.h b/net/dsa/slave.h deleted file mode 100644 index d0abe609e00d..000000000000 --- a/net/dsa/slave.h +++ /dev/null @@ -1,69 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ - -#ifndef __DSA_SLAVE_H -#define __DSA_SLAVE_H - -#include <linux/if_bridge.h> -#include <linux/if_vlan.h> -#include <linux/list.h> -#include <linux/netpoll.h> -#include <linux/types.h> -#include <net/dsa.h> -#include <net/gro_cells.h> - -struct net_device; -struct netlink_ext_ack; - -extern struct notifier_block dsa_slave_switchdev_notifier; -extern struct notifier_block dsa_slave_switchdev_blocking_notifier; - -struct dsa_slave_priv { - /* Copy of CPU port xmit for faster access in slave transmit hot path */ - struct sk_buff * (*xmit)(struct sk_buff *skb, - struct net_device *dev); - - struct gro_cells gcells; - - /* DSA port data, such as switch, port index, etc. */ - struct dsa_port *dp; - -#ifdef CONFIG_NET_POLL_CONTROLLER - struct netpoll *netpoll; -#endif - - /* TC context */ - struct list_head mall_tc_list; -}; - -void dsa_slave_mii_bus_init(struct dsa_switch *ds); -int dsa_slave_create(struct dsa_port *dp); -void dsa_slave_destroy(struct net_device *slave_dev); -int dsa_slave_suspend(struct net_device *slave_dev); -int dsa_slave_resume(struct net_device *slave_dev); -int dsa_slave_register_notifier(void); -void dsa_slave_unregister_notifier(void); -void dsa_slave_sync_ha(struct net_device *dev); -void dsa_slave_unsync_ha(struct net_device *dev); -void dsa_slave_setup_tagger(struct net_device *slave); -int dsa_slave_change_mtu(struct net_device *dev, int new_mtu); -int dsa_slave_change_master(struct net_device *dev, struct net_device *master, - struct netlink_ext_ack *extack); -int dsa_slave_manage_vlan_filtering(struct net_device *dev, - bool vlan_filtering); - -static inline struct dsa_port *dsa_slave_to_port(const struct net_device *dev) -{ - struct dsa_slave_priv *p = netdev_priv(dev); - - return p->dp; -} - -static inline struct net_device * -dsa_slave_to_master(const struct net_device *dev) -{ - struct dsa_port *dp = dsa_slave_to_port(dev); - - return dsa_port_to_master(dp); -} - -#endif diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 1a42f9317334..3d2feeea897b 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -15,10 +15,10 @@ #include "dsa.h" #include "netlink.h" #include "port.h" -#include "slave.h" #include "switch.h" #include "tag_8021q.h" #include "trace.h" +#include "user.h" static unsigned int dsa_switch_fastest_ageing_time(struct dsa_switch *ds, unsigned int ageing_time) @@ -894,12 +894,12 @@ static int dsa_switch_change_tag_proto(struct dsa_switch *ds, * bits that depend on the tagger, such as the MTU. */ dsa_switch_for_each_user_port(dp, ds) { - struct net_device *slave = dp->slave; + struct net_device *user = dp->user; - dsa_slave_setup_tagger(slave); + dsa_user_setup_tagger(user); /* rtnl_mutex is held in dsa_tree_change_tag_proto */ - dsa_slave_change_mtu(slave, slave->mtu); + dsa_user_change_mtu(user, user->mtu); } return 0; @@ -960,13 +960,13 @@ dsa_switch_disconnect_tag_proto(struct dsa_switch *ds, } static int -dsa_switch_master_state_change(struct dsa_switch *ds, - struct dsa_notifier_master_state_info *info) +dsa_switch_conduit_state_change(struct dsa_switch *ds, + struct dsa_notifier_conduit_state_info *info) { - if (!ds->ops->master_state_change) + if (!ds->ops->conduit_state_change) return 0; - ds->ops->master_state_change(ds, info->master, info->operational); + ds->ops->conduit_state_change(ds, info->conduit, info->operational); return 0; } @@ -1056,8 +1056,8 @@ static int dsa_switch_event(struct notifier_block *nb, case DSA_NOTIFIER_TAG_8021Q_VLAN_DEL: err = dsa_switch_tag_8021q_vlan_del(ds, info); break; - case DSA_NOTIFIER_MASTER_STATE_CHANGE: - err = dsa_switch_master_state_change(ds, info); + case DSA_NOTIFIER_CONDUIT_STATE_CHANGE: + err = dsa_switch_conduit_state_change(ds, info); break; default: err = -EOPNOTSUPP; diff --git a/net/dsa/switch.h b/net/dsa/switch.h index ea034677da15..be0a2749cd97 100644 --- a/net/dsa/switch.h +++ b/net/dsa/switch.h @@ -34,7 +34,7 @@ enum { DSA_NOTIFIER_TAG_PROTO_DISCONNECT, DSA_NOTIFIER_TAG_8021Q_VLAN_ADD, DSA_NOTIFIER_TAG_8021Q_VLAN_DEL, - DSA_NOTIFIER_MASTER_STATE_CHANGE, + DSA_NOTIFIER_CONDUIT_STATE_CHANGE, }; /* DSA_NOTIFIER_AGEING_TIME */ @@ -105,9 +105,9 @@ struct dsa_notifier_tag_8021q_vlan_info { u16 vid; }; -/* DSA_NOTIFIER_MASTER_STATE_CHANGE */ -struct dsa_notifier_master_state_info { - const struct net_device *master; +/* DSA_NOTIFIER_CONDUIT_STATE_CHANGE */ +struct dsa_notifier_conduit_state_info { + const struct net_device *conduit; bool operational; }; diff --git a/net/dsa/tag.c b/net/dsa/tag.c index 5105a5ff58fa..6e402d49afd3 100644 --- a/net/dsa/tag.c +++ b/net/dsa/tag.c @@ -13,8 +13,8 @@ #include <net/dsa.h> #include <net/dst_metadata.h> -#include "slave.h" #include "tag.h" +#include "user.h" static LIST_HEAD(dsa_tag_drivers_list); static DEFINE_MUTEX(dsa_tag_drivers_lock); @@ -27,7 +27,7 @@ static DEFINE_MUTEX(dsa_tag_drivers_lock); * switch, the DSA driver owning the interface to which the packet is * delivered is never notified unless we do so here. */ -static bool dsa_skb_defer_rx_timestamp(struct dsa_slave_priv *p, +static bool dsa_skb_defer_rx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; @@ -57,7 +57,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, struct metadata_dst *md_dst = skb_metadata_dst(skb); struct dsa_port *cpu_dp = dev->dsa_ptr; struct sk_buff *nskb = NULL; - struct dsa_slave_priv *p; + struct dsa_user_priv *p; if (unlikely(!cpu_dp)) { kfree_skb(skb); @@ -75,7 +75,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb_has_extensions(skb)) skb->slow_gro = 0; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (likely(skb->dev)) { dsa_default_offload_fwd_mark(skb); nskb = skb; @@ -94,7 +94,7 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev, skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, skb->dev); - if (unlikely(!dsa_slave_dev_check(skb->dev))) { + if (unlikely(!dsa_user_dev_check(skb->dev))) { /* Packet is to be injected directly on an upper * device, e.g. a team/bond, so skip all DSA-port * specific actions. diff --git a/net/dsa/tag.h b/net/dsa/tag.h index 32d12f4a9d73..f6b9c73718df 100644 --- a/net/dsa/tag.h +++ b/net/dsa/tag.h @@ -9,7 +9,7 @@ #include <net/dsa.h> #include "port.h" -#include "slave.h" +#include "user.h" struct dsa_tag_driver { const struct dsa_device_ops *ops; @@ -29,7 +29,7 @@ static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) return ops->needed_headroom + ops->needed_tailroom; } -static inline struct net_device *dsa_master_find_slave(struct net_device *dev, +static inline struct net_device *dsa_conduit_find_user(struct net_device *dev, int device, int port) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -39,7 +39,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, list_for_each_entry(dp, &dst->ports, list) if (dp->ds->index == device && dp->index == port && dp->type == DSA_PORT_TYPE_USER) - return dp->slave; + return dp->user; return NULL; } @@ -49,7 +49,7 @@ static inline struct net_device *dsa_master_find_slave(struct net_device *dev, */ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct net_device *dev = skb->dev; struct net_device *upper_dev; @@ -107,12 +107,12 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb) * to support termination through the bridge. */ static inline struct net_device * -dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) +dsa_find_designated_bridge_port_by_vid(struct net_device *conduit, u16 vid) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct bridge_vlan_info vinfo; - struct net_device *slave; + struct net_device *user; struct dsa_port *dp; int err; @@ -134,13 +134,13 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) if (dp->cpu_dp != cpu_dp) continue; - slave = dp->slave; + user = dp->user; - err = br_vlan_get_info_rcu(slave, vid, &vinfo); + err = br_vlan_get_info_rcu(user, vid, &vinfo); if (err) continue; - return slave; + return user; } return NULL; @@ -155,7 +155,7 @@ dsa_find_designated_bridge_port_by_vid(struct net_device *master, u16 vid) */ static inline void dsa_default_offload_fwd_mark(struct sk_buff *skb) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); skb->offload_fwd_mark = !!(dp->bridge); } @@ -215,9 +215,9 @@ static inline void dsa_alloc_etype_header(struct sk_buff *skb, int len) memmove(skb->data, skb->data + len, 2 * ETH_ALEN); } -/* On RX, eth_type_trans() on the DSA master pulls ETH_HLEN bytes starting from +/* On RX, eth_type_trans() on the DSA conduit pulls ETH_HLEN bytes starting from * skb_mac_header(skb), which leaves skb->data pointing at the first byte after - * what the DSA master perceives as the EtherType (the beginning of the L3 + * what the DSA conduit perceives as the EtherType (the beginning of the L3 * protocol). Since DSA EtherType header taggers treat the EtherType as part of * the DSA tag itself, and the EtherType is 2 bytes in length, the DSA header * is located 2 bytes behind skb->data. Note that EtherType in this context diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index cbdfc392f7e0..71b26ae6db39 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -73,7 +73,7 @@ struct dsa_tag_8021q_vlan { struct dsa_8021q_context { struct dsa_switch *ds; struct list_head vlans; - /* EtherType of RX VID, used for filtering on master interface */ + /* EtherType of RX VID, used for filtering on conduit interface */ __be16 proto; }; @@ -338,7 +338,7 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); u16 vid = dsa_tag_8021q_standalone_vid(dp); - struct net_device *master; + struct net_device *conduit; int err; /* The CPU port is implicitly configured by @@ -347,7 +347,7 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) if (!dsa_port_is_user(dp)) return 0; - master = dsa_port_to_master(dp); + conduit = dsa_port_to_conduit(dp); err = dsa_port_tag_8021q_vlan_add(dp, vid, false); if (err) { @@ -357,8 +357,8 @@ static int dsa_tag_8021q_port_setup(struct dsa_switch *ds, int port) return err; } - /* Add the VLAN to the master's RX filter. */ - vlan_vid_add(master, ctx->proto, vid); + /* Add the VLAN to the conduit's RX filter. */ + vlan_vid_add(conduit, ctx->proto, vid); return err; } @@ -368,7 +368,7 @@ static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) struct dsa_8021q_context *ctx = ds->tag_8021q_ctx; struct dsa_port *dp = dsa_to_port(ds, port); u16 vid = dsa_tag_8021q_standalone_vid(dp); - struct net_device *master; + struct net_device *conduit; /* The CPU port is implicitly configured by * configuring the front-panel ports @@ -376,11 +376,11 @@ static void dsa_tag_8021q_port_teardown(struct dsa_switch *ds, int port) if (!dsa_port_is_user(dp)) return; - master = dsa_port_to_master(dp); + conduit = dsa_port_to_conduit(dp); dsa_port_tag_8021q_vlan_del(dp, vid, false); - vlan_vid_del(master, ctx->proto, vid); + vlan_vid_del(conduit, ctx->proto, vid); } static int dsa_tag_8021q_setup(struct dsa_switch *ds) @@ -468,10 +468,10 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, int vbid) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; @@ -490,7 +490,7 @@ struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, continue; if (dsa_port_bridge_num_get(dp) == vbid) - return dp->slave; + return dp->user; } return NULL; diff --git a/net/dsa/tag_8021q.h b/net/dsa/tag_8021q.h index b75cbaa028ef..41f7167ac520 100644 --- a/net/dsa/tag_8021q.h +++ b/net/dsa/tag_8021q.h @@ -16,7 +16,7 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, int *vbid); -struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *master, +struct net_device *dsa_tag_8021q_find_port_by_vbid(struct net_device *conduit, int vbid); int dsa_switch_tag_8021q_vlan_add(struct dsa_switch *ds, diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 7f3b7d730b85..92ce67b93a58 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -29,7 +29,7 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __le16 *phdr; u16 hdr; @@ -74,7 +74,7 @@ static struct sk_buff *ar9331_tag_rcv(struct sk_buff *skb, /* Get source port information */ port = FIELD_GET(AR9331_HDR_PORT_NUM_MASK, hdr); - skb->dev = dsa_master_find_slave(ndev, 0, port); + skb->dev = dsa_conduit_find_user(ndev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index cacdafb41200..83d283a5d27e 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -85,7 +85,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, struct net_device *dev, unsigned int offset) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u16 queue = skb_get_queue_mapping(skb); u8 *brcm_tag; @@ -96,7 +96,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, * (including FCS and tag) because the length verification is done after * the Broadcom tag is stripped off the ingress packet. * - * Let dsa_slave_xmit() free the SKB + * Let dsa_user_xmit() free the SKB */ if (__skb_put_padto(skb, ETH_ZLEN + BRCM_TAG_LEN, false)) return NULL; @@ -119,7 +119,7 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb, brcm_tag[2] = BRCM_IG_DSTMAP2_MASK; brcm_tag[3] = (1 << dp->index) & BRCM_IG_DSTMAP1_MASK; - /* Now tell the master network device about the desired output queue + /* Now tell the conduit network device about the desired output queue * as well */ skb_set_queue_mapping(skb, BRCM_TAG_SET_PORT_QUEUE(dp->index, queue)); @@ -164,7 +164,7 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Locate which port this is coming from */ source_port = brcm_tag[3] & BRCM_EG_PID_MASK; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; @@ -216,7 +216,7 @@ MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_BRCM, BRCM_NAME); static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *brcm_tag; /* The Ethernet switch we are interfaced with needs packets to be at @@ -226,7 +226,7 @@ static struct sk_buff *brcm_leg_tag_xmit(struct sk_buff *skb, * (including FCS and tag) because the length verification is done after * the Broadcom tag is stripped off the ingress packet. * - * Let dsa_slave_xmit() free the SKB + * Let dsa_user_xmit() free the SKB */ if (__skb_put_padto(skb, ETH_ZLEN + BRCM_LEG_TAG_LEN, false)) return NULL; @@ -264,7 +264,7 @@ static struct sk_buff *brcm_leg_tag_rcv(struct sk_buff *skb, source_port = brcm_tag[5] & BRCM_LEG_PORT_ID; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 1fd7fa26db64..8ed52dd663ab 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -129,7 +129,7 @@ enum dsa_code { static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev, u8 extra) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br_dev; u8 tag_dev, tag_port; enum dsa_cmd cmd; @@ -267,14 +267,14 @@ static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev, lag = dsa_lag_by_id(cpu_dp->dst, source_port + 1); skb->dev = lag ? lag->dev : NULL; } else { - skb->dev = dsa_master_find_slave(dev, source_device, + skb->dev = dsa_conduit_find_user(dev, source_device, source_port); } if (!skb->dev) return NULL; - /* When using LAG offload, skb->dev is not a DSA slave interface, + /* When using LAG offload, skb->dev is not a DSA user interface, * so we cannot call dsa_default_offload_fwd_mark and we need to * special-case it. */ diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index e279cd9057b0..3539141b5350 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -61,7 +61,7 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *gswip_tag; skb_push(skb, GSWIP_TX_HEADER_LEN); @@ -89,7 +89,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, /* Get source port information */ port = (gswip_tag[7] & GSWIP_RX_SPPID_MASK) >> GSWIP_RX_SPPID_SHIFT; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index 03a1fb9c87a9..6e233cd0aa38 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -20,7 +20,7 @@ static struct sk_buff *hellcreek_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *tag; /* Calculate checksums (if required) before adding the trailer tag to @@ -45,7 +45,7 @@ static struct sk_buff *hellcreek_rcv(struct sk_buff *skb, u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN; unsigned int port = tag[0] & 0x03; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) { netdev_warn_once(dev, "Failed to get source port: %d\n", port); return NULL; diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 3632e47dea9e..9be341fa88f0 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -87,7 +87,7 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, struct net_device *dev, unsigned int port, unsigned int len) { - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; @@ -119,7 +119,7 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct ethhdr *hdr; u8 *tag; @@ -256,7 +256,7 @@ static struct sk_buff *ksz_defer_xmit(struct dsa_port *dp, struct sk_buff *skb) return NULL; kthread_init_work(&xmit_work->work, xmit_work_fn); - /* Increase refcount so the kfree_skb in dsa_slave_xmit + /* Increase refcount so the kfree_skb in dsa_user_xmit * won't really free the packet. */ xmit_work->dp = dp; @@ -272,7 +272,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, { u16 queue_mapping = skb_get_queue_mapping(skb); u8 prio = netdev_txq_to_tc(dev, queue_mapping); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct ethhdr *hdr; __be16 *tag; u16 val; @@ -344,7 +344,7 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb, { u16 queue_mapping = skb_get_queue_mapping(skb); u8 prio = netdev_txq_to_tc(dev, queue_mapping); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct ethhdr *hdr; u8 *tag; @@ -410,7 +410,7 @@ static struct sk_buff *lan937x_xmit(struct sk_buff *skb, { u16 queue_mapping = skb_get_queue_mapping(skb); u8 prio = netdev_txq_to_tc(dev, queue_mapping); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); const struct ethhdr *hdr = eth_hdr(skb); __be16 *tag; u16 val; diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index c25f5536706b..1ed8ee24855d 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -56,7 +56,7 @@ static int lan9303_xmit_use_arl(struct dsa_port *dp, u8 *dest_addr) static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 *lan9303_tag; u16 tag; @@ -99,7 +99,7 @@ static struct sk_buff *lan9303_rcv(struct sk_buff *skb, struct net_device *dev) source_port = lan9303_tag1 & 0x3; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); return NULL; diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index 40af80452747..2483785f6ab1 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -23,7 +23,7 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 xmit_tpid; u8 *mtk_tag; @@ -85,7 +85,7 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev) /* Get source port information */ port = (hdr & MTK_HDR_RECV_SOURCE_PORT_MASK); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_none.c b/net/dsa/tag_none.c index d2fd179c4227..9a473624db50 100644 --- a/net/dsa/tag_none.c +++ b/net/dsa/tag_none.c @@ -12,8 +12,8 @@ #define NONE_NAME "none" -static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, - struct net_device *dev) +static struct sk_buff *dsa_user_notag_xmit(struct sk_buff *skb, + struct net_device *dev) { /* Just return the original SKB */ return skb; @@ -22,7 +22,7 @@ static struct sk_buff *dsa_slave_notag_xmit(struct sk_buff *skb, static const struct dsa_device_ops none_ops = { .name = NONE_NAME, .proto = DSA_TAG_PROTO_NONE, - .xmit = dsa_slave_notag_xmit, + .xmit = dsa_user_notag_xmit, }; module_dsa_tag_driver(none_ops); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 20bf7074d5a6..ef2f8fffb2c7 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -45,7 +45,7 @@ static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp, static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, __be32 ifh_prefix, void **ifh) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); struct dsa_switch *ds = dp->ds; u64 vlan_tci, tag_type; void *injection; @@ -79,7 +79,7 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev, static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); void *injection; ocelot_xmit_common(skb, netdev, cpu_to_be32(0x8880000a), &injection); @@ -91,7 +91,7 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, static struct sk_buff *seville_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); void *injection; ocelot_xmit_common(skb, netdev, cpu_to_be32(0x88800005), &injection); @@ -111,12 +111,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, u16 vlan_tpid; u64 rew_val; - /* Revert skb->data by the amount consumed by the DSA master, + /* Revert skb->data by the amount consumed by the DSA conduit, * so it points to the beginning of the frame. */ skb_push(skb, ETH_HLEN); /* We don't care about the short prefix, it is just for easy entrance - * into the DSA master's RX filter. Discard it now by moving it into + * into the DSA conduit's RX filter. Discard it now by moving it into * the headroom. */ skb_pull(skb, OCELOT_SHORT_PREFIX_LEN); @@ -141,12 +141,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, 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); + skb->dev = dsa_conduit_find_user(netdev, 0, src_port); if (!skb->dev) /* The switch will reflect back some frames sent through - * sockets opened on the bare DSA master. These will come back + * sockets opened on the bare DSA conduit. These will come back * with src_port equal to the index of the CPU port, for which - * there is no slave registered. So don't print any error + * there is no user registered. So don't print any error * message here (ignore and drop those frames). */ return NULL; @@ -170,7 +170,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, * equal to the pvid of the ingress port and should not be used for * processing. */ - dp = dsa_slave_to_port(skb->dev); + dp = dsa_user_to_port(skb->dev); vlan_tpid = tag_type ? ETH_P_8021AD : ETH_P_8021Q; if (dsa_port_is_vlan_filtering(dp) && @@ -192,7 +192,7 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .xmit = ocelot_xmit, .rcv = ocelot_rcv, .needed_headroom = OCELOT_TOTAL_TAG_LEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; DSA_TAG_DRIVER(ocelot_netdev_ops); @@ -204,7 +204,7 @@ static const struct dsa_device_ops seville_netdev_ops = { .xmit = seville_xmit, .rcv = ocelot_rcv, .needed_headroom = OCELOT_TOTAL_TAG_LEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; DSA_TAG_DRIVER(seville_netdev_ops); diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 1f0b8c20eba5..210039320888 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -37,8 +37,8 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, return NULL; /* PTP over IP packets need UDP checksumming. We may have inherited - * NETIF_F_HW_CSUM from the DSA master, but these packets are not sent - * through the DSA master, so calculate the checksum here. + * NETIF_F_HW_CSUM from the DSA conduit, but these packets are not sent + * through the DSA conduit, so calculate the checksum here. */ if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) return NULL; @@ -49,7 +49,7 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, /* Calls felix_port_deferred_xmit in felix.c */ kthread_init_work(&xmit_work->work, xmit_work_fn); - /* Increase refcount so the kfree_skb in dsa_slave_xmit + /* Increase refcount so the kfree_skb in dsa_user_xmit * won't really free the packet. */ xmit_work->dp = dp; @@ -63,7 +63,7 @@ static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); @@ -83,7 +83,7 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, dsa_8021q_rcv(skb, &src_port, &switch_id, NULL); - skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); + skb->dev = dsa_conduit_find_user(netdev, switch_id, src_port); if (!skb->dev) return NULL; @@ -130,7 +130,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .connect = ocelot_connect, .disconnect = ocelot_disconnect, .needed_headroom = VLAN_HLEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index e5ff7c34e577..6514aa7993ce 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -14,7 +14,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 *phdr; u16 hdr; @@ -78,7 +78,7 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev) /* Get source port information */ port = FIELD_GET(QCA_HDR_RECV_SOURCE_PORT, hdr); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; @@ -116,7 +116,7 @@ static const struct dsa_device_ops qca_netdev_ops = { .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, .needed_headroom = QCA_HDR_LEN, - .promisc_on_master = true, + .promisc_on_conduit = true, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index c327314b95e3..4da5bad1a7aa 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -36,7 +36,7 @@ static struct sk_buff *rtl4a_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 *p; u8 *tag; u16 out; @@ -97,9 +97,9 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb, } port = protport & 0xff; - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) { - netdev_dbg(dev, "could not find slave for port %d\n", port); + netdev_dbg(dev, "could not find user for port %d\n", port); return NULL; } diff --git a/net/dsa/tag_rtl8_4.c b/net/dsa/tag_rtl8_4.c index 4f67834fd121..07e857debabf 100644 --- a/net/dsa/tag_rtl8_4.c +++ b/net/dsa/tag_rtl8_4.c @@ -103,7 +103,7 @@ static void rtl8_4_write_tag(struct sk_buff *skb, struct net_device *dev, void *tag) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); __be16 tag16[RTL8_4_TAG_LEN / 2]; /* Set Realtek EtherType */ @@ -180,10 +180,10 @@ static int rtl8_4_read_tag(struct sk_buff *skb, struct net_device *dev, /* Parse TX (switch->CPU) */ port = FIELD_GET(RTL8_4_TX, ntohs(tag16[3])); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) { dev_warn_ratelimited(&dev->dev, - "could not find slave for port %d\n", + "could not find user for port %d\n", port); return -ENOENT; } diff --git a/net/dsa/tag_rzn1_a5psw.c b/net/dsa/tag_rzn1_a5psw.c index 437a6820ac42..2ce866b45615 100644 --- a/net/dsa/tag_rzn1_a5psw.c +++ b/net/dsa/tag_rzn1_a5psw.c @@ -39,7 +39,7 @@ struct a5psw_tag { static struct sk_buff *a5psw_tag_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct a5psw_tag *ptag; u32 data2_val; @@ -90,7 +90,7 @@ static struct sk_buff *a5psw_tag_rcv(struct sk_buff *skb, port = FIELD_GET(A5PSW_CTRL_DATA_PORT, ntohs(tag->ctrl_data)); - skb->dev = dsa_master_find_slave(dev, 0, port); + skb->dev = dsa_conduit_find_user(dev, 0, port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index ade3eeb2f3e6..1fffe8c2b589 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -157,7 +157,7 @@ static struct sk_buff *sja1105_defer_xmit(struct dsa_port *dp, return NULL; kthread_init_work(&xmit_work->work, xmit_work_fn); - /* Increase refcount so the kfree_skb in dsa_slave_xmit + /* Increase refcount so the kfree_skb in dsa_user_xmit * won't really free the packet. */ xmit_work->dp = dp; @@ -210,7 +210,7 @@ static u16 sja1105_xmit_tpid(struct dsa_port *dp) static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); unsigned int bridge_num = dsa_port_bridge_num_get(dp); struct net_device *br = dsa_port_bridge_dev_get(dp); u16 tx_vid; @@ -235,7 +235,7 @@ static struct sk_buff *sja1105_imprecise_xmit(struct sk_buff *skb, /* Transform untagged control packets into pvid-tagged control packets so that * all packets sent by this tagger are VLAN-tagged and we can configure the - * switch to drop untagged packets coming from the DSA master. + * switch to drop untagged packets coming from the DSA conduit. */ static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, struct sk_buff *skb, u8 pcp) @@ -266,7 +266,7 @@ static struct sk_buff *sja1105_pvid_tag_control_pkt(struct dsa_port *dp, static struct sk_buff *sja1105_xmit(struct sk_buff *skb, struct net_device *netdev) { - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); @@ -294,7 +294,7 @@ static struct sk_buff *sja1110_xmit(struct sk_buff *skb, struct net_device *netdev) { struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; - struct dsa_port *dp = dsa_slave_to_port(netdev); + struct dsa_port *dp = dsa_user_to_port(netdev); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); u16 tx_vid = dsa_tag_8021q_standalone_vid(dp); @@ -383,7 +383,7 @@ static struct sk_buff * Buffer it until we get its meta frame. */ if (is_link_local) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); struct sja1105_tagger_private *priv; struct dsa_switch *ds = dp->ds; @@ -396,7 +396,7 @@ static struct sk_buff if (priv->stampable_skb) { dev_err_ratelimited(ds->dev, "Expected meta frame, is %12llx " - "in the DSA master multicast filter?\n", + "in the DSA conduit multicast filter?\n", SJA1105_META_DMAC); kfree_skb(priv->stampable_skb); } @@ -417,7 +417,7 @@ static struct sk_buff * frame, which serves no further purpose). */ } else if (is_meta) { - struct dsa_port *dp = dsa_slave_to_port(skb->dev); + struct dsa_port *dp = dsa_user_to_port(skb->dev); struct sja1105_tagger_private *priv; struct dsa_switch *ds = dp->ds; struct sk_buff *stampable_skb; @@ -550,7 +550,7 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, } if (source_port != -1 && switch_id != -1) - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + skb->dev = dsa_conduit_find_user(netdev, switch_id, source_port); else if (vbid >= 1) skb->dev = dsa_tag_8021q_find_port_by_vbid(netdev, vbid); else @@ -573,16 +573,16 @@ static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); struct sja1105_tagger_data *tagger_data; - struct net_device *master = skb->dev; + struct net_device *conduit = skb->dev; struct dsa_port *cpu_dp; struct dsa_switch *ds; int i; - cpu_dp = master->dsa_ptr; + cpu_dp = conduit->dsa_ptr; ds = dsa_switch_find(cpu_dp->dst->index, switch_id); if (!ds) { net_err_ratelimited("%s: cannot find switch id %d\n", - master->name, switch_id); + conduit->name, switch_id); return NULL; } @@ -649,7 +649,7 @@ static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, /* skb->len counts from skb->data, while start_of_padding * counts from the destination MAC address. Right now skb->data - * is still as set by the DSA master, so to trim away the + * is still as set by the DSA conduit, so to trim away the * padding and trailer we need to account for the fact that * skb->data points to skb_mac_header(skb) + ETH_HLEN. */ @@ -698,7 +698,7 @@ static struct sk_buff *sja1110_rcv(struct sk_buff *skb, else if (source_port == -1 || switch_id == -1) skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); else - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + skb->dev = dsa_conduit_find_user(netdev, switch_id, source_port); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; @@ -778,7 +778,7 @@ static const struct dsa_device_ops sja1105_netdev_ops = { .disconnect = sja1105_disconnect, .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, - .promisc_on_master = true, + .promisc_on_conduit = true, }; DSA_TAG_DRIVER(sja1105_netdev_ops); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 7361b9106382..1ebb25a8b140 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -14,7 +14,7 @@ static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); u8 *trailer; trailer = skb_put(skb, 4); @@ -41,7 +41,7 @@ static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev) source_port = trailer[1] & 7; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index af19969f9bc4..c9c163598ef2 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -13,7 +13,7 @@ static struct sk_buff *xrs700x_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_port *partner, *dp = dsa_slave_to_port(dev); + struct dsa_port *partner, *dp = dsa_user_to_port(dev); u8 *trailer; trailer = skb_put(skb, 1); @@ -39,7 +39,7 @@ static struct sk_buff *xrs700x_rcv(struct sk_buff *skb, struct net_device *dev) if (source_port < 0) return NULL; - skb->dev = dsa_master_find_slave(dev, 0, source_port); + skb->dev = dsa_conduit_find_user(dev, 0, source_port); if (!skb->dev) return NULL; diff --git a/net/dsa/slave.c b/net/dsa/user.c index 4c3e502d7e16..d438884a4eb0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/user.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * net/dsa/slave.c - Slave device handling + * net/dsa/user.c - user device handling * Copyright (c) 2008-2009 Marvell Semiconductor */ @@ -23,13 +23,13 @@ #include <linux/netpoll.h> #include <linux/string.h> +#include "conduit.h" #include "dsa.h" -#include "port.h" -#include "master.h" #include "netlink.h" -#include "slave.h" +#include "port.h" #include "switch.h" #include "tag.h" +#include "user.h" struct dsa_switchdev_event_work { struct net_device *dev; @@ -79,13 +79,13 @@ static bool dsa_switch_supports_mc_filtering(struct dsa_switch *ds) !ds->needs_standalone_vlan_filtering; } -static void dsa_slave_standalone_event_work(struct work_struct *work) +static void dsa_user_standalone_event_work(struct work_struct *work) { struct dsa_standalone_event_work *standalone_work = container_of(work, struct dsa_standalone_event_work, work); const unsigned char *addr = standalone_work->addr; struct net_device *dev = standalone_work->dev; - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_mdb mdb; struct dsa_switch *ds = dp->ds; u16 vid = standalone_work->vid; @@ -140,10 +140,10 @@ static void dsa_slave_standalone_event_work(struct work_struct *work) kfree(standalone_work); } -static int dsa_slave_schedule_standalone_work(struct net_device *dev, - enum dsa_standalone_event event, - const unsigned char *addr, - u16 vid) +static int dsa_user_schedule_standalone_work(struct net_device *dev, + enum dsa_standalone_event event, + const unsigned char *addr, + u16 vid) { struct dsa_standalone_event_work *standalone_work; @@ -151,7 +151,7 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, if (!standalone_work) return -ENOMEM; - INIT_WORK(&standalone_work->work, dsa_slave_standalone_event_work); + INIT_WORK(&standalone_work->work, dsa_user_standalone_event_work); standalone_work->event = event; standalone_work->dev = dev; @@ -163,18 +163,18 @@ static int dsa_slave_schedule_standalone_work(struct net_device *dev, return 0; } -static int dsa_slave_host_vlan_rx_filtering(void *arg, int vid) +static int dsa_user_host_vlan_rx_filtering(void *arg, int vid) { struct dsa_host_vlan_rx_filtering_ctx *ctx = arg; - return dsa_slave_schedule_standalone_work(ctx->dev, ctx->event, + return dsa_user_schedule_standalone_work(ctx->dev, ctx->event, ctx->addr, vid); } -static int dsa_slave_vlan_for_each(struct net_device *dev, - int (*cb)(void *arg, int vid), void *arg) +static int dsa_user_vlan_for_each(struct net_device *dev, + int (*cb)(void *arg, int vid), void *arg) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_vlan *v; int err; @@ -193,99 +193,99 @@ static int dsa_slave_vlan_for_each(struct net_device *dev, return 0; } -static int dsa_slave_sync_uc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_sync_uc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_ADD, }; - dev_uc_add(master, addr); + dev_uc_add(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -static int dsa_slave_unsync_uc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_unsync_uc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_UC_DEL, }; - dev_uc_del(master, addr); + dev_uc_del(conduit, addr); if (!dsa_switch_supports_uc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -static int dsa_slave_sync_mc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_sync_mc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_ADD, }; - dev_mc_add(master, addr); + dev_mc_add(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -static int dsa_slave_unsync_mc(struct net_device *dev, - const unsigned char *addr) +static int dsa_user_unsync_mc(struct net_device *dev, + const unsigned char *addr) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_host_vlan_rx_filtering_ctx ctx = { .dev = dev, .addr = addr, .event = DSA_MC_DEL, }; - dev_mc_del(master, addr); + dev_mc_del(conduit, addr); if (!dsa_switch_supports_mc_filtering(dp->ds)) return 0; - return dsa_slave_vlan_for_each(dev, dsa_slave_host_vlan_rx_filtering, + return dsa_user_vlan_for_each(dev, dsa_user_host_vlan_rx_filtering, &ctx); } -void dsa_slave_sync_ha(struct net_device *dev) +void dsa_user_sync_ha(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_mc_addr(ha, dev) - dsa_slave_sync_mc(dev, ha->addr); + dsa_user_sync_mc(dev, ha->addr); netdev_for_each_synced_uc_addr(ha, dev) - dsa_slave_sync_uc(dev, ha->addr); + dsa_user_sync_uc(dev, ha->addr); netif_addr_unlock_bh(dev); @@ -294,19 +294,19 @@ void dsa_slave_sync_ha(struct net_device *dev) dsa_flush_workqueue(); } -void dsa_slave_unsync_ha(struct net_device *dev) +void dsa_user_unsync_ha(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct netdev_hw_addr *ha; netif_addr_lock_bh(dev); netdev_for_each_synced_uc_addr(ha, dev) - dsa_slave_unsync_uc(dev, ha->addr); + dsa_user_unsync_uc(dev, ha->addr); netdev_for_each_synced_mc_addr(ha, dev) - dsa_slave_unsync_mc(dev, ha->addr); + dsa_user_unsync_mc(dev, ha->addr); netif_addr_unlock_bh(dev); @@ -315,8 +315,8 @@ void dsa_slave_unsync_ha(struct net_device *dev) dsa_flush_workqueue(); } -/* slave mii_bus handling ***************************************************/ -static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) +/* user mii_bus handling ***************************************************/ +static int dsa_user_phy_read(struct mii_bus *bus, int addr, int reg) { struct dsa_switch *ds = bus->priv; @@ -326,7 +326,7 @@ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) return 0xffff; } -static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) +static int dsa_user_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) { struct dsa_switch *ds = bus->priv; @@ -336,35 +336,35 @@ static int dsa_slave_phy_write(struct mii_bus *bus, int addr, int reg, u16 val) return 0; } -void dsa_slave_mii_bus_init(struct dsa_switch *ds) +void dsa_user_mii_bus_init(struct dsa_switch *ds) { - ds->slave_mii_bus->priv = (void *)ds; - ds->slave_mii_bus->name = "dsa slave smi"; - ds->slave_mii_bus->read = dsa_slave_phy_read; - ds->slave_mii_bus->write = dsa_slave_phy_write; - snprintf(ds->slave_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", + ds->user_mii_bus->priv = (void *)ds; + ds->user_mii_bus->name = "dsa user smi"; + ds->user_mii_bus->read = dsa_user_phy_read; + ds->user_mii_bus->write = dsa_user_phy_write; + snprintf(ds->user_mii_bus->id, MII_BUS_ID_SIZE, "dsa-%d.%d", ds->dst->index, ds->index); - ds->slave_mii_bus->parent = ds->dev; - ds->slave_mii_bus->phy_mask = ~ds->phys_mii_mask; + ds->user_mii_bus->parent = ds->dev; + ds->user_mii_bus->phy_mask = ~ds->phys_mii_mask; } -/* slave device handling ****************************************************/ -static int dsa_slave_get_iflink(const struct net_device *dev) +/* user device handling ****************************************************/ +static int dsa_user_get_iflink(const struct net_device *dev) { - return dsa_slave_to_master(dev)->ifindex; + return dsa_user_to_conduit(dev)->ifindex; } -static int dsa_slave_open(struct net_device *dev) +static int dsa_user_open(struct net_device *dev) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err; - err = dev_open(master, NULL); + err = dev_open(conduit, NULL); if (err < 0) { - netdev_err(dev, "failed to open master %s\n", master->name); + netdev_err(dev, "failed to open conduit %s\n", conduit->name); goto out; } @@ -374,8 +374,8 @@ static int dsa_slave_open(struct net_device *dev) goto out; } - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) { - err = dev_uc_add(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) { + err = dev_uc_add(conduit, dev->dev_addr); if (err < 0) goto del_host_addr; } @@ -387,8 +387,8 @@ static int dsa_slave_open(struct net_device *dev) return 0; del_unicast: - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); del_host_addr: if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); @@ -396,16 +396,16 @@ out: return err; } -static int dsa_slave_close(struct net_device *dev) +static int dsa_user_close(struct net_device *dev) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; dsa_port_disable_rt(dp); - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); @@ -413,43 +413,43 @@ static int dsa_slave_close(struct net_device *dev) return 0; } -static void dsa_slave_manage_host_flood(struct net_device *dev) +static void dsa_user_manage_host_flood(struct net_device *dev) { bool mc = dev->flags & (IFF_PROMISC | IFF_ALLMULTI); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); bool uc = dev->flags & IFF_PROMISC; dsa_port_set_host_flood(dp, uc, mc); } -static void dsa_slave_change_rx_flags(struct net_device *dev, int change) +static void dsa_user_change_rx_flags(struct net_device *dev, int change) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (change & IFF_ALLMULTI) - dev_set_allmulti(master, + dev_set_allmulti(conduit, dev->flags & IFF_ALLMULTI ? 1 : -1); if (change & IFF_PROMISC) - dev_set_promiscuity(master, + dev_set_promiscuity(conduit, dev->flags & IFF_PROMISC ? 1 : -1); if (dsa_switch_supports_uc_filtering(ds) && dsa_switch_supports_mc_filtering(ds)) - dsa_slave_manage_host_flood(dev); + dsa_user_manage_host_flood(dev); } -static void dsa_slave_set_rx_mode(struct net_device *dev) +static void dsa_user_set_rx_mode(struct net_device *dev) { - __dev_mc_sync(dev, dsa_slave_sync_mc, dsa_slave_unsync_mc); - __dev_uc_sync(dev, dsa_slave_sync_uc, dsa_slave_unsync_uc); + __dev_mc_sync(dev, dsa_user_sync_mc, dsa_user_unsync_mc); + __dev_uc_sync(dev, dsa_user_sync_uc, dsa_user_unsync_uc); } -static int dsa_slave_set_mac_address(struct net_device *dev, void *a) +static int dsa_user_set_mac_address(struct net_device *dev, void *a) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct sockaddr *addr = a; int err; @@ -465,7 +465,7 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) } /* If the port is down, the address isn't synced yet to hardware or - * to the DSA master, so there is nothing to change. + * to the DSA conduit, so there is nothing to change. */ if (!(dev->flags & IFF_UP)) goto out_change_dev_addr; @@ -476,14 +476,14 @@ static int dsa_slave_set_mac_address(struct net_device *dev, void *a) return err; } - if (!ether_addr_equal(addr->sa_data, master->dev_addr)) { - err = dev_uc_add(master, addr->sa_data); + if (!ether_addr_equal(addr->sa_data, conduit->dev_addr)) { + err = dev_uc_add(conduit, addr->sa_data); if (err < 0) goto del_unicast; } - if (!ether_addr_equal(dev->dev_addr, master->dev_addr)) - dev_uc_del(master, dev->dev_addr); + if (!ether_addr_equal(dev->dev_addr, conduit->dev_addr)) + dev_uc_del(conduit, dev->dev_addr); if (dsa_switch_supports_uc_filtering(ds)) dsa_port_standalone_host_fdb_del(dp, dev->dev_addr, 0); @@ -500,7 +500,7 @@ del_unicast: return err; } -struct dsa_slave_dump_ctx { +struct dsa_user_dump_ctx { struct net_device *dev; struct sk_buff *skb; struct netlink_callback *cb; @@ -508,10 +508,10 @@ struct dsa_slave_dump_ctx { }; static int -dsa_slave_port_fdb_do_dump(const unsigned char *addr, u16 vid, - bool is_static, void *data) +dsa_user_port_fdb_do_dump(const unsigned char *addr, u16 vid, + bool is_static, void *data) { - struct dsa_slave_dump_ctx *dump = data; + struct dsa_user_dump_ctx *dump = data; u32 portid = NETLINK_CB(dump->cb->skb).portid; u32 seq = dump->cb->nlh->nlmsg_seq; struct nlmsghdr *nlh; @@ -552,12 +552,12 @@ nla_put_failure: } static int -dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, - struct net_device *dev, struct net_device *filter_dev, - int *idx) +dsa_user_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct net_device *dev, struct net_device *filter_dev, + int *idx) { - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_dump_ctx dump = { + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_dump_ctx dump = { .dev = dev, .skb = skb, .cb = cb, @@ -565,15 +565,15 @@ dsa_slave_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, }; int err; - err = dsa_port_fdb_dump(dp, dsa_slave_port_fdb_do_dump, &dump); + err = dsa_port_fdb_dump(dp, dsa_user_port_fdb_do_dump, &dump); *idx = dump.idx; return err; } -static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int dsa_user_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; int port = p->dp->index; @@ -592,11 +592,11 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } -static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, - const struct switchdev_attr *attr, - struct netlink_ext_ack *extack) +static int dsa_user_port_attr_set(struct net_device *dev, const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); int ret; if (ctx && ctx != dp) @@ -663,13 +663,13 @@ static int dsa_slave_port_attr_set(struct net_device *dev, const void *ctx, /* Must be called under rcu_read_lock() */ static int -dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, - const struct switchdev_obj_port_vlan *vlan) +dsa_user_vlan_check_for_8021q_uppers(struct net_device *user, + const struct switchdev_obj_port_vlan *vlan) { struct net_device *upper_dev; struct list_head *iter; - netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) { + netdev_for_each_upper_dev_rcu(user, upper_dev, iter) { u16 vid; if (!is_vlan_dev(upper_dev)) @@ -683,11 +683,11 @@ dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave, return 0; } -static int dsa_slave_vlan_add(struct net_device *dev, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int dsa_user_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; int err; @@ -703,7 +703,7 @@ static int dsa_slave_vlan_add(struct net_device *dev, */ if (br_vlan_enabled(dsa_port_bridge_dev_get(dp))) { rcu_read_lock(); - err = dsa_slave_vlan_check_for_8021q_uppers(dev, vlan); + err = dsa_user_vlan_check_for_8021q_uppers(dev, vlan); rcu_read_unlock(); if (err) { NL_SET_ERR_MSG_MOD(extack, @@ -718,11 +718,11 @@ static int dsa_slave_vlan_add(struct net_device *dev, /* Offload a VLAN installed on the bridge or on a foreign interface by * installing it as a VLAN towards the CPU port. */ -static int dsa_slave_host_vlan_add(struct net_device *dev, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int dsa_user_host_vlan_add(struct net_device *dev, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan; /* Do nothing if this is a software bridge */ @@ -744,11 +744,11 @@ static int dsa_slave_host_vlan_add(struct net_device *dev, return dsa_port_host_vlan_add(dp, &vlan, extack); } -static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, - const struct switchdev_obj *obj, - struct netlink_ext_ack *extack) +static int dsa_user_port_obj_add(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) @@ -769,9 +769,9 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) - err = dsa_slave_vlan_add(dev, obj, extack); + err = dsa_user_vlan_add(dev, obj, extack); else - err = dsa_slave_host_vlan_add(dev, obj, extack); + err = dsa_user_host_vlan_add(dev, obj, extack); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) @@ -794,10 +794,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, const void *ctx, return err; } -static int dsa_slave_vlan_del(struct net_device *dev, - const struct switchdev_obj *obj) +static int dsa_user_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; if (dsa_port_skip_vlan_configuration(dp)) @@ -808,10 +808,10 @@ static int dsa_slave_vlan_del(struct net_device *dev, return dsa_port_vlan_del(dp, vlan); } -static int dsa_slave_host_vlan_del(struct net_device *dev, - const struct switchdev_obj *obj) +static int dsa_user_host_vlan_del(struct net_device *dev, + const struct switchdev_obj *obj) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan *vlan; /* Do nothing if this is a software bridge */ @@ -826,10 +826,10 @@ static int dsa_slave_host_vlan_del(struct net_device *dev, return dsa_port_host_vlan_del(dp, vlan); } -static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, - const struct switchdev_obj *obj) +static int dsa_user_port_obj_del(struct net_device *dev, const void *ctx, + const struct switchdev_obj *obj) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); int err; if (ctx && ctx != dp) @@ -850,9 +850,9 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, break; case SWITCHDEV_OBJ_ID_PORT_VLAN: if (dsa_port_offloads_bridge_port(dp, obj->orig_dev)) - err = dsa_slave_vlan_del(dev, obj); + err = dsa_user_vlan_del(dev, obj); else - err = dsa_slave_host_vlan_del(dev, obj); + err = dsa_user_host_vlan_del(dev, obj); break; case SWITCHDEV_OBJ_ID_MRP: if (!dsa_port_offloads_bridge_dev(dp, obj->orig_dev)) @@ -875,11 +875,11 @@ static int dsa_slave_port_obj_del(struct net_device *dev, const void *ctx, return err; } -static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, - struct sk_buff *skb) +static inline netdev_tx_t dsa_user_netpoll_send_skb(struct net_device *dev, + struct sk_buff *skb) { #ifdef CONFIG_NET_POLL_CONTROLLER - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); return netpoll_send_skb(p->netpoll, skb); #else @@ -888,7 +888,7 @@ static inline netdev_tx_t dsa_slave_netpoll_send_skb(struct net_device *dev, #endif } -static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p, +static void dsa_skb_tx_timestamp(struct dsa_user_priv *p, struct sk_buff *skb) { struct dsa_switch *ds = p->dp->ds; @@ -908,12 +908,12 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev) * tag to be successfully transmitted */ if (unlikely(netpoll_tx_running(dev))) - return dsa_slave_netpoll_send_skb(dev, skb); + return dsa_user_netpoll_send_skb(dev, skb); /* Queue the SKB for transmission on the parent interface, but * do not modify its EtherType */ - skb->dev = dsa_slave_to_master(dev); + skb->dev = dsa_user_to_conduit(dev); dev_queue_xmit(skb); return NETDEV_TX_OK; @@ -927,7 +927,7 @@ static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) /* For tail taggers, we need to pad short frames ourselves, to ensure * that the tail tag does not fail at its role of being at the end of - * the packet, once the master interface pads the frame. Account for + * the packet, once the conduit interface pads the frame. Account for * that pad length here, and pad later. */ if (unlikely(needed_tailroom && skb->len < ETH_ZLEN)) @@ -944,9 +944,9 @@ static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev) GFP_ATOMIC); } -static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t dsa_user_xmit(struct sk_buff *skb, struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct sk_buff *nskb; dev_sw_netstats_tx_add(dev, 1, skb->len); @@ -981,17 +981,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev) /* ethtool operations *******************************************************/ -static void dsa_slave_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *drvinfo) +static void dsa_user_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *drvinfo) { strscpy(drvinfo->driver, "dsa", sizeof(drvinfo->driver)); strscpy(drvinfo->fw_version, "N/A", sizeof(drvinfo->fw_version)); strscpy(drvinfo->bus_info, "platform", sizeof(drvinfo->bus_info)); } -static int dsa_slave_get_regs_len(struct net_device *dev) +static int dsa_user_get_regs_len(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs_len) @@ -1001,25 +1001,25 @@ static int dsa_slave_get_regs_len(struct net_device *dev) } static void -dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) +dsa_user_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_regs) ds->ops->get_regs(ds, dp->index, regs, _p); } -static int dsa_slave_nway_reset(struct net_device *dev) +static int dsa_user_nway_reset(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_nway_reset(dp->pl); } -static int dsa_slave_get_eeprom_len(struct net_device *dev) +static int dsa_user_get_eeprom_len(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->cd && ds->cd->eeprom_len) @@ -1031,10 +1031,10 @@ static int dsa_slave_get_eeprom_len(struct net_device *dev) return 0; } -static int dsa_slave_get_eeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) +static int dsa_user_get_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eeprom) @@ -1043,10 +1043,10 @@ static int dsa_slave_get_eeprom(struct net_device *dev, return -EOPNOTSUPP; } -static int dsa_slave_set_eeprom(struct net_device *dev, - struct ethtool_eeprom *eeprom, u8 *data) +static int dsa_user_set_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->set_eeprom) @@ -1055,10 +1055,10 @@ static int dsa_slave_set_eeprom(struct net_device *dev, return -EOPNOTSUPP; } -static void dsa_slave_get_strings(struct net_device *dev, - uint32_t stringset, uint8_t *data) +static void dsa_user_get_strings(struct net_device *dev, + uint32_t stringset, uint8_t *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (stringset == ETH_SS_STATS) { @@ -1077,11 +1077,11 @@ static void dsa_slave_get_strings(struct net_device *dev, } -static void dsa_slave_get_ethtool_stats(struct net_device *dev, - struct ethtool_stats *stats, - uint64_t *data) +static void dsa_user_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct pcpu_sw_netstats *s; unsigned int start; @@ -1107,9 +1107,9 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev, ds->ops->get_ethtool_stats(ds, dp->index, data + 4); } -static int dsa_slave_get_sset_count(struct net_device *dev, int sset) +static int dsa_user_get_sset_count(struct net_device *dev, int sset) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (sset == ETH_SS_STATS) { @@ -1129,20 +1129,20 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) return -EOPNOTSUPP; } -static void dsa_slave_get_eth_phy_stats(struct net_device *dev, - struct ethtool_eth_phy_stats *phy_stats) +static void dsa_user_get_eth_phy_stats(struct net_device *dev, + struct ethtool_eth_phy_stats *phy_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_phy_stats) ds->ops->get_eth_phy_stats(ds, dp->index, phy_stats); } -static void dsa_slave_get_eth_mac_stats(struct net_device *dev, - struct ethtool_eth_mac_stats *mac_stats) +static void dsa_user_get_eth_mac_stats(struct net_device *dev, + struct ethtool_eth_mac_stats *mac_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_mac_stats) @@ -1150,10 +1150,10 @@ static void dsa_slave_get_eth_mac_stats(struct net_device *dev, } static void -dsa_slave_get_eth_ctrl_stats(struct net_device *dev, - struct ethtool_eth_ctrl_stats *ctrl_stats) +dsa_user_get_eth_ctrl_stats(struct net_device *dev, + struct ethtool_eth_ctrl_stats *ctrl_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_eth_ctrl_stats) @@ -1161,21 +1161,21 @@ dsa_slave_get_eth_ctrl_stats(struct net_device *dev, } static void -dsa_slave_get_rmon_stats(struct net_device *dev, - struct ethtool_rmon_stats *rmon_stats, - const struct ethtool_rmon_hist_range **ranges) +dsa_user_get_rmon_stats(struct net_device *dev, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_rmon_stats) ds->ops->get_rmon_stats(ds, dp->index, rmon_stats, ranges); } -static void dsa_slave_net_selftest(struct net_device *ndev, - struct ethtool_test *etest, u64 *buf) +static void dsa_user_net_selftest(struct net_device *ndev, + struct ethtool_test *etest, u64 *buf) { - struct dsa_port *dp = dsa_slave_to_port(ndev); + struct dsa_port *dp = dsa_user_to_port(ndev); struct dsa_switch *ds = dp->ds; if (ds->ops->self_test) { @@ -1186,10 +1186,10 @@ static void dsa_slave_net_selftest(struct net_device *ndev, net_selftest(ndev, etest, buf); } -static int dsa_slave_get_mm(struct net_device *dev, - struct ethtool_mm_state *state) +static int dsa_user_get_mm(struct net_device *dev, + struct ethtool_mm_state *state) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_mm) @@ -1198,10 +1198,10 @@ static int dsa_slave_get_mm(struct net_device *dev, return ds->ops->get_mm(ds, dp->index, state); } -static int dsa_slave_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, - struct netlink_ext_ack *extack) +static int dsa_user_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, + struct netlink_ext_ack *extack) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_mm) @@ -1210,19 +1210,19 @@ static int dsa_slave_set_mm(struct net_device *dev, struct ethtool_mm_cfg *cfg, return ds->ops->set_mm(ds, dp->index, cfg, extack); } -static void dsa_slave_get_mm_stats(struct net_device *dev, - struct ethtool_mm_stats *stats) +static void dsa_user_get_mm_stats(struct net_device *dev, + struct ethtool_mm_stats *stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_mm_stats) ds->ops->get_mm_stats(ds, dp->index, stats); } -static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) +static void dsa_user_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; phylink_ethtool_get_wol(dp->pl, w); @@ -1231,9 +1231,9 @@ static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) ds->ops->get_wol(ds, dp->index, w); } -static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) +static int dsa_user_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; @@ -1245,9 +1245,9 @@ static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) return ret; } -static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_set_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; @@ -1265,9 +1265,9 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) return phylink_ethtool_set_eee(dp->pl, e); } -static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) +static int dsa_user_get_eee(struct net_device *dev, struct ethtool_eee *e) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int ret; @@ -1285,54 +1285,54 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) return phylink_ethtool_get_eee(dp->pl, e); } -static int dsa_slave_get_link_ksettings(struct net_device *dev, - struct ethtool_link_ksettings *cmd) +static int dsa_user_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_get(dp->pl, cmd); } -static int dsa_slave_set_link_ksettings(struct net_device *dev, - const struct ethtool_link_ksettings *cmd) +static int dsa_user_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_ksettings_set(dp->pl, cmd); } -static void dsa_slave_get_pause_stats(struct net_device *dev, - struct ethtool_pause_stats *pause_stats) +static void dsa_user_get_pause_stats(struct net_device *dev, + struct ethtool_pause_stats *pause_stats) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_pause_stats) ds->ops->get_pause_stats(ds, dp->index, pause_stats); } -static void dsa_slave_get_pauseparam(struct net_device *dev, - struct ethtool_pauseparam *pause) +static void dsa_user_get_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); phylink_ethtool_get_pauseparam(dp->pl, pause); } -static int dsa_slave_set_pauseparam(struct net_device *dev, - struct ethtool_pauseparam *pause) +static int dsa_user_set_pauseparam(struct net_device *dev, + struct ethtool_pauseparam *pause) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); return phylink_ethtool_set_pauseparam(dp->pl, pause); } #ifdef CONFIG_NET_POLL_CONTROLLER -static int dsa_slave_netpoll_setup(struct net_device *dev, - struct netpoll_info *ni) +static int dsa_user_netpoll_setup(struct net_device *dev, + struct netpoll_info *ni) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_slave_priv *p = netdev_priv(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll; int err = 0; @@ -1340,7 +1340,7 @@ static int dsa_slave_netpoll_setup(struct net_device *dev, if (!netpoll) return -ENOMEM; - err = __netpoll_setup(netpoll, master); + err = __netpoll_setup(netpoll, conduit); if (err) { kfree(netpoll); goto out; @@ -1351,9 +1351,9 @@ out: return err; } -static void dsa_slave_netpoll_cleanup(struct net_device *dev) +static void dsa_user_netpoll_cleanup(struct net_device *dev) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct netpoll *netpoll = p->netpoll; if (!netpoll) @@ -1364,15 +1364,15 @@ static void dsa_slave_netpoll_cleanup(struct net_device *dev) __netpoll_free(netpoll); } -static void dsa_slave_poll_controller(struct net_device *dev) +static void dsa_user_poll_controller(struct net_device *dev) { } #endif static struct dsa_mall_tc_entry * -dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) +dsa_user_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_tc_entry *mall_tc_entry; list_for_each_entry(mall_tc_entry, &p->mall_tc_list, list) @@ -1383,13 +1383,13 @@ dsa_slave_mall_tc_entry_find(struct net_device *dev, unsigned long cookie) } static int -dsa_slave_add_cls_matchall_mirred(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +dsa_user_add_cls_matchall_mirred(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_mirror_tc_entry *mirror; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; @@ -1409,7 +1409,7 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, if (!act->dev) return -EINVAL; - if (!dsa_slave_dev_check(act->dev)) + if (!dsa_user_dev_check(act->dev)) return -EOPNOTSUPP; mall_tc_entry = kzalloc(sizeof(*mall_tc_entry), GFP_KERNEL); @@ -1420,7 +1420,7 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, mall_tc_entry->type = DSA_PORT_MALL_MIRROR; mirror = &mall_tc_entry->mirror; - to_dp = dsa_slave_to_port(act->dev); + to_dp = dsa_user_to_port(act->dev); mirror->to_local_port = to_dp->index; mirror->ingress = ingress; @@ -1437,13 +1437,13 @@ dsa_slave_add_cls_matchall_mirred(struct net_device *dev, } static int -dsa_slave_add_cls_matchall_police(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +dsa_user_add_cls_matchall_police(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { struct netlink_ext_ack *extack = cls->common.extack; - struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_port *dp = dsa_user_to_port(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_mall_policer_tc_entry *policer; struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; @@ -1497,31 +1497,31 @@ dsa_slave_add_cls_matchall_police(struct net_device *dev, return err; } -static int dsa_slave_add_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +static int dsa_user_add_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { int err = -EOPNOTSUPP; if (cls->common.protocol == htons(ETH_P_ALL) && flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_MIRRED) - err = dsa_slave_add_cls_matchall_mirred(dev, cls, ingress); + err = dsa_user_add_cls_matchall_mirred(dev, cls, ingress); else if (flow_offload_has_one_action(&cls->rule->action) && cls->rule->action.entries[0].id == FLOW_ACTION_POLICE) - err = dsa_slave_add_cls_matchall_police(dev, cls, ingress); + err = dsa_user_add_cls_matchall_police(dev, cls, ingress); return err; } -static void dsa_slave_del_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls) +static void dsa_user_del_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_mall_tc_entry *mall_tc_entry; struct dsa_switch *ds = dp->ds; - mall_tc_entry = dsa_slave_mall_tc_entry_find(dev, cls->cookie); + mall_tc_entry = dsa_user_mall_tc_entry_find(dev, cls->cookie); if (!mall_tc_entry) return; @@ -1544,29 +1544,29 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev, kfree(mall_tc_entry); } -static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev, - struct tc_cls_matchall_offload *cls, - bool ingress) +static int dsa_user_setup_tc_cls_matchall(struct net_device *dev, + struct tc_cls_matchall_offload *cls, + bool ingress) { if (cls->common.chain_index) return -EOPNOTSUPP; switch (cls->command) { case TC_CLSMATCHALL_REPLACE: - return dsa_slave_add_cls_matchall(dev, cls, ingress); + return dsa_user_add_cls_matchall(dev, cls, ingress); case TC_CLSMATCHALL_DESTROY: - dsa_slave_del_cls_matchall(dev, cls); + dsa_user_del_cls_matchall(dev, cls); return 0; default: return -EOPNOTSUPP; } } -static int dsa_slave_add_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_add_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -1576,11 +1576,11 @@ static int dsa_slave_add_cls_flower(struct net_device *dev, return ds->ops->cls_flower_add(ds, port, cls, ingress); } -static int dsa_slave_del_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_del_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -1590,11 +1590,11 @@ static int dsa_slave_del_cls_flower(struct net_device *dev, return ds->ops->cls_flower_del(ds, port, cls, ingress); } -static int dsa_slave_stats_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_stats_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; @@ -1604,24 +1604,24 @@ static int dsa_slave_stats_cls_flower(struct net_device *dev, return ds->ops->cls_flower_stats(ds, port, cls, ingress); } -static int dsa_slave_setup_tc_cls_flower(struct net_device *dev, - struct flow_cls_offload *cls, - bool ingress) +static int dsa_user_setup_tc_cls_flower(struct net_device *dev, + struct flow_cls_offload *cls, + bool ingress) { switch (cls->command) { case FLOW_CLS_REPLACE: - return dsa_slave_add_cls_flower(dev, cls, ingress); + return dsa_user_add_cls_flower(dev, cls, ingress); case FLOW_CLS_DESTROY: - return dsa_slave_del_cls_flower(dev, cls, ingress); + return dsa_user_del_cls_flower(dev, cls, ingress); case FLOW_CLS_STATS: - return dsa_slave_stats_cls_flower(dev, cls, ingress); + return dsa_user_stats_cls_flower(dev, cls, ingress); default: return -EOPNOTSUPP; } } -static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv, bool ingress) +static int dsa_user_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv, bool ingress) { struct net_device *dev = cb_priv; @@ -1630,46 +1630,46 @@ static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSMATCHALL: - return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress); + return dsa_user_setup_tc_cls_matchall(dev, type_data, ingress); case TC_SETUP_CLSFLOWER: - return dsa_slave_setup_tc_cls_flower(dev, type_data, ingress); + return dsa_user_setup_tc_cls_flower(dev, type_data, ingress); default: return -EOPNOTSUPP; } } -static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type, - void *type_data, void *cb_priv) +static int dsa_user_setup_tc_block_cb_ig(enum tc_setup_type type, + void *type_data, void *cb_priv) { - return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true); + return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, true); } -static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type, - void *type_data, void *cb_priv) +static int dsa_user_setup_tc_block_cb_eg(enum tc_setup_type type, + void *type_data, void *cb_priv) { - return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false); + return dsa_user_setup_tc_block_cb(type, type_data, cb_priv, false); } -static LIST_HEAD(dsa_slave_block_cb_list); +static LIST_HEAD(dsa_user_block_cb_list); -static int dsa_slave_setup_tc_block(struct net_device *dev, - struct flow_block_offload *f) +static int dsa_user_setup_tc_block(struct net_device *dev, + struct flow_block_offload *f) { struct flow_block_cb *block_cb; flow_setup_cb_t *cb; if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) - cb = dsa_slave_setup_tc_block_cb_ig; + cb = dsa_user_setup_tc_block_cb_ig; else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) - cb = dsa_slave_setup_tc_block_cb_eg; + cb = dsa_user_setup_tc_block_cb_eg; else return -EOPNOTSUPP; - f->driver_block_list = &dsa_slave_block_cb_list; + f->driver_block_list = &dsa_user_block_cb_list; switch (f->command) { case FLOW_BLOCK_BIND: - if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list)) + if (flow_block_cb_is_busy(cb, dev, &dsa_user_block_cb_list)) return -EBUSY; block_cb = flow_block_cb_alloc(cb, dev, dev, NULL); @@ -1677,7 +1677,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, return PTR_ERR(block_cb); flow_block_cb_add(block_cb, f); - list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list); + list_add_tail(&block_cb->driver_list, &dsa_user_block_cb_list); return 0; case FLOW_BLOCK_UNBIND: block_cb = flow_block_cb_lookup(f->block, cb, dev); @@ -1692,28 +1692,28 @@ static int dsa_slave_setup_tc_block(struct net_device *dev, } } -static int dsa_slave_setup_ft_block(struct dsa_switch *ds, int port, - void *type_data) +static int dsa_user_setup_ft_block(struct dsa_switch *ds, int port, + void *type_data) { - struct net_device *master = dsa_port_to_master(dsa_to_port(ds, port)); + struct net_device *conduit = dsa_port_to_conduit(dsa_to_port(ds, port)); - if (!master->netdev_ops->ndo_setup_tc) + if (!conduit->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; - return master->netdev_ops->ndo_setup_tc(master, TC_SETUP_FT, type_data); + return conduit->netdev_ops->ndo_setup_tc(conduit, TC_SETUP_FT, type_data); } -static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, - void *type_data) +static int dsa_user_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; switch (type) { case TC_SETUP_BLOCK: - return dsa_slave_setup_tc_block(dev, type_data); + return dsa_user_setup_tc_block(dev, type_data); case TC_SETUP_FT: - return dsa_slave_setup_ft_block(ds, dp->index, type_data); + return dsa_user_setup_ft_block(ds, dp->index, type_data); default: break; } @@ -1724,10 +1724,10 @@ static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type, return ds->ops->port_setup_tc(ds, dp->index, type, type_data); } -static int dsa_slave_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *nfc, u32 *rule_locs) +static int dsa_user_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *nfc, u32 *rule_locs) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->get_rxnfc) @@ -1736,10 +1736,10 @@ static int dsa_slave_get_rxnfc(struct net_device *dev, return ds->ops->get_rxnfc(ds, dp->index, nfc, rule_locs); } -static int dsa_slave_set_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *nfc) +static int dsa_user_set_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *nfc) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (!ds->ops->set_rxnfc) @@ -1748,10 +1748,10 @@ static int dsa_slave_set_rxnfc(struct net_device *dev, return ds->ops->set_rxnfc(ds, dp->index, nfc); } -static int dsa_slave_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *ts) +static int dsa_user_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *ts) { - struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_user_priv *p = netdev_priv(dev); struct dsa_switch *ds = p->dp->ds; if (!ds->ops->get_ts_info) @@ -1760,10 +1760,10 @@ static int dsa_slave_get_ts_info(struct net_device *dev, return ds->ops->get_ts_info(ds, p->dp->index, ts); } -static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, - u16 vid) +static int dsa_user_vlan_rx_add_vid(struct net_device *dev, __be16 proto, + u16 vid) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN, .vid = vid, @@ -1810,15 +1810,15 @@ static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto, if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_MC_ADD, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_MC_ADD, + ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_UC_ADD, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_UC_ADD, + ha->addr, vid); } } @@ -1835,10 +1835,10 @@ rollback: return ret; } -static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, - u16 vid) +static int dsa_user_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, + u16 vid) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct switchdev_obj_port_vlan vlan = { .vid = vid, /* This API only allows programming tagged, non-PVID VIDs */ @@ -1874,15 +1874,15 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, if (dsa_switch_supports_mc_filtering(ds)) { netdev_for_each_synced_mc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_MC_DEL, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_MC_DEL, + ha->addr, vid); } } if (dsa_switch_supports_uc_filtering(ds)) { netdev_for_each_synced_uc_addr(ha, dev) { - dsa_slave_schedule_standalone_work(dev, DSA_UC_DEL, - ha->addr, vid); + dsa_user_schedule_standalone_work(dev, DSA_UC_DEL, + ha->addr, vid); } } @@ -1893,18 +1893,18 @@ static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, return 0; } -static int dsa_slave_restore_vlan(struct net_device *vdev, int vid, void *arg) +static int dsa_user_restore_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); - return dsa_slave_vlan_rx_add_vid(arg, proto, vid); + return dsa_user_vlan_rx_add_vid(arg, proto, vid); } -static int dsa_slave_clear_vlan(struct net_device *vdev, int vid, void *arg) +static int dsa_user_clear_vlan(struct net_device *vdev, int vid, void *arg) { __be16 proto = vdev ? vlan_dev_vlan_proto(vdev) : htons(ETH_P_8021Q); - return dsa_slave_vlan_rx_kill_vid(arg, proto, vid); + return dsa_user_vlan_rx_kill_vid(arg, proto, vid); } /* Keep the VLAN RX filtering list in sync with the hardware only if VLAN @@ -1938,26 +1938,26 @@ static int dsa_slave_clear_vlan(struct net_device *vdev, int vid, void *arg) * - the bridge VLANs * - the 8021q upper VLANs */ -int dsa_slave_manage_vlan_filtering(struct net_device *slave, - bool vlan_filtering) +int dsa_user_manage_vlan_filtering(struct net_device *user, + bool vlan_filtering) { int err; if (vlan_filtering) { - slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; - err = vlan_for_each(slave, dsa_slave_restore_vlan, slave); + err = vlan_for_each(user, dsa_user_restore_vlan, user); if (err) { - vlan_for_each(slave, dsa_slave_clear_vlan, slave); - slave->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + vlan_for_each(user, dsa_user_clear_vlan, user); + user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; return err; } } else { - err = vlan_for_each(slave, dsa_slave_clear_vlan, slave); + err = vlan_for_each(user, dsa_user_clear_vlan, user); if (err) return err; - slave->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + user->features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; } return 0; @@ -2028,7 +2028,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) list_for_each_entry(dst, &dsa_tree_list, list) { list_for_each_entry(other_dp, &dst->ports, list) { struct dsa_hw_port *hw_port; - struct net_device *slave; + struct net_device *user; if (other_dp->type != DSA_PORT_TYPE_USER) continue; @@ -2039,17 +2039,17 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) if (!other_dp->ds->mtu_enforcement_ingress) continue; - slave = other_dp->slave; + user = other_dp->user; - if (min_mtu > slave->mtu) - min_mtu = slave->mtu; + if (min_mtu > user->mtu) + min_mtu = user->mtu; hw_port = kzalloc(sizeof(*hw_port), GFP_KERNEL); if (!hw_port) goto out; - hw_port->dev = slave; - hw_port->old_mtu = slave->mtu; + hw_port->dev = user; + hw_port->old_mtu = user->mtu; list_add(&hw_port->list, &hw_port_list); } @@ -2059,7 +2059,7 @@ static void dsa_bridge_mtu_normalization(struct dsa_port *dp) * interface's MTU first, regardless of whether the intention of the * user was to raise or lower it. */ - err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->slave->mtu); + err = dsa_hw_port_list_set_mtu(&hw_port_list, dp->user->mtu); if (!err) goto out; @@ -2073,16 +2073,16 @@ out: dsa_hw_port_list_free(&hw_port_list); } -int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) +int dsa_user_change_mtu(struct net_device *dev, int new_mtu) { - struct net_device *master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_port *cpu_dp = dp->cpu_dp; struct dsa_switch *ds = dp->ds; struct dsa_port *other_dp; int largest_mtu = 0; - int new_master_mtu; - int old_master_mtu; + int new_conduit_mtu; + int old_conduit_mtu; int mtu_limit; int overhead; int cpu_mtu; @@ -2092,44 +2092,44 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) return -EOPNOTSUPP; dsa_tree_for_each_user_port(other_dp, ds->dst) { - int slave_mtu; + int user_mtu; - /* During probe, this function will be called for each slave + /* During probe, this function will be called for each user * device, while not all of them have been allocated. That's * ok, it doesn't change what the maximum is, so ignore it. */ - if (!other_dp->slave) + if (!other_dp->user) continue; /* Pretend that we already applied the setting, which we * actually haven't (still haven't done all integrity checks) */ if (dp == other_dp) - slave_mtu = new_mtu; + user_mtu = new_mtu; else - slave_mtu = other_dp->slave->mtu; + user_mtu = other_dp->user->mtu; - if (largest_mtu < slave_mtu) - largest_mtu = slave_mtu; + if (largest_mtu < user_mtu) + largest_mtu = user_mtu; } overhead = dsa_tag_protocol_overhead(cpu_dp->tag_ops); - mtu_limit = min_t(int, master->max_mtu, dev->max_mtu + overhead); - old_master_mtu = master->mtu; - new_master_mtu = largest_mtu + overhead; - if (new_master_mtu > mtu_limit) + mtu_limit = min_t(int, conduit->max_mtu, dev->max_mtu + overhead); + old_conduit_mtu = conduit->mtu; + new_conduit_mtu = largest_mtu + overhead; + if (new_conduit_mtu > mtu_limit) return -ERANGE; - /* If the master MTU isn't over limit, there's no need to check the CPU + /* If the conduit MTU isn't over limit, there's no need to check the CPU * MTU, since that surely isn't either. */ cpu_mtu = largest_mtu; /* Start applying stuff */ - if (new_master_mtu != old_master_mtu) { - err = dev_set_mtu(master, new_master_mtu); + if (new_conduit_mtu != old_conduit_mtu) { + err = dev_set_mtu(conduit, new_conduit_mtu); if (err < 0) - goto out_master_failed; + goto out_conduit_failed; /* We only need to propagate the MTU of the CPU port to * upstream switches, so emit a notifier which updates them. @@ -2150,19 +2150,19 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) return 0; out_port_failed: - if (new_master_mtu != old_master_mtu) - dsa_port_mtu_change(cpu_dp, old_master_mtu - overhead); + if (new_conduit_mtu != old_conduit_mtu) + dsa_port_mtu_change(cpu_dp, old_conduit_mtu - overhead); out_cpu_failed: - if (new_master_mtu != old_master_mtu) - dev_set_mtu(master, old_master_mtu); -out_master_failed: + if (new_conduit_mtu != old_conduit_mtu) + dev_set_mtu(conduit, old_conduit_mtu); +out_conduit_failed: return err; } static int __maybe_unused -dsa_slave_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; @@ -2187,9 +2187,9 @@ dsa_slave_dcbnl_set_default_prio(struct net_device *dev, struct dcb_app *app) } static int __maybe_unused -dsa_slave_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; @@ -2220,29 +2220,29 @@ dsa_slave_dcbnl_add_dscp_prio(struct net_device *dev, struct dcb_app *app) return 0; } -static int __maybe_unused dsa_slave_dcbnl_ieee_setapp(struct net_device *dev, - struct dcb_app *app) +static int __maybe_unused dsa_user_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: - return dsa_slave_dcbnl_set_default_prio(dev, app); + return dsa_user_dcbnl_set_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: - return dsa_slave_dcbnl_add_dscp_prio(dev, app); + return dsa_user_dcbnl_add_dscp_prio(dev, app); default: return -EOPNOTSUPP; } } static int __maybe_unused -dsa_slave_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; unsigned long mask, new_prio; int err, port = dp->index; @@ -2267,9 +2267,9 @@ dsa_slave_dcbnl_del_default_prio(struct net_device *dev, struct dcb_app *app) } static int __maybe_unused -dsa_slave_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) +dsa_user_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int err, port = dp->index; u8 dscp = app->protocol; @@ -2290,20 +2290,20 @@ dsa_slave_dcbnl_del_dscp_prio(struct net_device *dev, struct dcb_app *app) return 0; } -static int __maybe_unused dsa_slave_dcbnl_ieee_delapp(struct net_device *dev, - struct dcb_app *app) +static int __maybe_unused dsa_user_dcbnl_ieee_delapp(struct net_device *dev, + struct dcb_app *app) { switch (app->selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: switch (app->protocol) { case 0: - return dsa_slave_dcbnl_del_default_prio(dev, app); + return dsa_user_dcbnl_del_default_prio(dev, app); default: return -EOPNOTSUPP; } break; case IEEE_8021QAZ_APP_SEL_DSCP: - return dsa_slave_dcbnl_del_dscp_prio(dev, app); + return dsa_user_dcbnl_del_dscp_prio(dev, app); default: return -EOPNOTSUPP; } @@ -2312,9 +2312,9 @@ static int __maybe_unused dsa_slave_dcbnl_ieee_delapp(struct net_device *dev, /* Pre-populate the DCB application priority table with the priorities * configured during switch setup, which we read from hardware here. */ -static int dsa_slave_dcbnl_init(struct net_device *dev) +static int dsa_user_dcbnl_init(struct net_device *dev) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; int port = dp->index; int err; @@ -2362,49 +2362,49 @@ static int dsa_slave_dcbnl_init(struct net_device *dev) return 0; } -static const struct ethtool_ops dsa_slave_ethtool_ops = { - .get_drvinfo = dsa_slave_get_drvinfo, - .get_regs_len = dsa_slave_get_regs_len, - .get_regs = dsa_slave_get_regs, - .nway_reset = dsa_slave_nway_reset, +static const struct ethtool_ops dsa_user_ethtool_ops = { + .get_drvinfo = dsa_user_get_drvinfo, + .get_regs_len = dsa_user_get_regs_len, + .get_regs = dsa_user_get_regs, + .nway_reset = dsa_user_nway_reset, .get_link = ethtool_op_get_link, - .get_eeprom_len = dsa_slave_get_eeprom_len, - .get_eeprom = dsa_slave_get_eeprom, - .set_eeprom = dsa_slave_set_eeprom, - .get_strings = dsa_slave_get_strings, - .get_ethtool_stats = dsa_slave_get_ethtool_stats, - .get_sset_count = dsa_slave_get_sset_count, - .get_eth_phy_stats = dsa_slave_get_eth_phy_stats, - .get_eth_mac_stats = dsa_slave_get_eth_mac_stats, - .get_eth_ctrl_stats = dsa_slave_get_eth_ctrl_stats, - .get_rmon_stats = dsa_slave_get_rmon_stats, - .set_wol = dsa_slave_set_wol, - .get_wol = dsa_slave_get_wol, - .set_eee = dsa_slave_set_eee, - .get_eee = dsa_slave_get_eee, - .get_link_ksettings = dsa_slave_get_link_ksettings, - .set_link_ksettings = dsa_slave_set_link_ksettings, - .get_pause_stats = dsa_slave_get_pause_stats, - .get_pauseparam = dsa_slave_get_pauseparam, - .set_pauseparam = dsa_slave_set_pauseparam, - .get_rxnfc = dsa_slave_get_rxnfc, - .set_rxnfc = dsa_slave_set_rxnfc, - .get_ts_info = dsa_slave_get_ts_info, - .self_test = dsa_slave_net_selftest, - .get_mm = dsa_slave_get_mm, - .set_mm = dsa_slave_set_mm, - .get_mm_stats = dsa_slave_get_mm_stats, + .get_eeprom_len = dsa_user_get_eeprom_len, + .get_eeprom = dsa_user_get_eeprom, + .set_eeprom = dsa_user_set_eeprom, + .get_strings = dsa_user_get_strings, + .get_ethtool_stats = dsa_user_get_ethtool_stats, + .get_sset_count = dsa_user_get_sset_count, + .get_eth_phy_stats = dsa_user_get_eth_phy_stats, + .get_eth_mac_stats = dsa_user_get_eth_mac_stats, + .get_eth_ctrl_stats = dsa_user_get_eth_ctrl_stats, + .get_rmon_stats = dsa_user_get_rmon_stats, + .set_wol = dsa_user_set_wol, + .get_wol = dsa_user_get_wol, + .set_eee = dsa_user_set_eee, + .get_eee = dsa_user_get_eee, + .get_link_ksettings = dsa_user_get_link_ksettings, + .set_link_ksettings = dsa_user_set_link_ksettings, + .get_pause_stats = dsa_user_get_pause_stats, + .get_pauseparam = dsa_user_get_pauseparam, + .set_pauseparam = dsa_user_set_pauseparam, + .get_rxnfc = dsa_user_get_rxnfc, + .set_rxnfc = dsa_user_set_rxnfc, + .get_ts_info = dsa_user_get_ts_info, + .self_test = dsa_user_net_selftest, + .get_mm = dsa_user_get_mm, + .set_mm = dsa_user_set_mm, + .get_mm_stats = dsa_user_get_mm_stats, }; -static const struct dcbnl_rtnl_ops __maybe_unused dsa_slave_dcbnl_ops = { - .ieee_setapp = dsa_slave_dcbnl_ieee_setapp, - .ieee_delapp = dsa_slave_dcbnl_ieee_delapp, +static const struct dcbnl_rtnl_ops __maybe_unused dsa_user_dcbnl_ops = { + .ieee_setapp = dsa_user_dcbnl_ieee_setapp, + .ieee_delapp = dsa_user_dcbnl_ieee_delapp, }; -static void dsa_slave_get_stats64(struct net_device *dev, - struct rtnl_link_stats64 *s) +static void dsa_user_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *s) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; if (ds->ops->get_stats64) @@ -2413,43 +2413,43 @@ static void dsa_slave_get_stats64(struct net_device *dev, dev_get_tstats64(dev, s); } -static int dsa_slave_fill_forward_path(struct net_device_path_ctx *ctx, - struct net_device_path *path) +static int dsa_user_fill_forward_path(struct net_device_path_ctx *ctx, + struct net_device_path *path) { - struct dsa_port *dp = dsa_slave_to_port(ctx->dev); - struct net_device *master = dsa_port_to_master(dp); + struct dsa_port *dp = dsa_user_to_port(ctx->dev); + struct net_device *conduit = dsa_port_to_conduit(dp); struct dsa_port *cpu_dp = dp->cpu_dp; path->dev = ctx->dev; path->type = DEV_PATH_DSA; path->dsa.proto = cpu_dp->tag_ops->proto; path->dsa.port = dp->index; - ctx->dev = master; + ctx->dev = conduit; return 0; } -static const struct net_device_ops dsa_slave_netdev_ops = { - .ndo_open = dsa_slave_open, - .ndo_stop = dsa_slave_close, - .ndo_start_xmit = dsa_slave_xmit, - .ndo_change_rx_flags = dsa_slave_change_rx_flags, - .ndo_set_rx_mode = dsa_slave_set_rx_mode, - .ndo_set_mac_address = dsa_slave_set_mac_address, - .ndo_fdb_dump = dsa_slave_fdb_dump, - .ndo_eth_ioctl = dsa_slave_ioctl, - .ndo_get_iflink = dsa_slave_get_iflink, +static const struct net_device_ops dsa_user_netdev_ops = { + .ndo_open = dsa_user_open, + .ndo_stop = dsa_user_close, + .ndo_start_xmit = dsa_user_xmit, + .ndo_change_rx_flags = dsa_user_change_rx_flags, + .ndo_set_rx_mode = dsa_user_set_rx_mode, + .ndo_set_mac_address = dsa_user_set_mac_address, + .ndo_fdb_dump = dsa_user_fdb_dump, + .ndo_eth_ioctl = dsa_user_ioctl, + .ndo_get_iflink = dsa_user_get_iflink, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_netpoll_setup = dsa_slave_netpoll_setup, - .ndo_netpoll_cleanup = dsa_slave_netpoll_cleanup, - .ndo_poll_controller = dsa_slave_poll_controller, + .ndo_netpoll_setup = dsa_user_netpoll_setup, + .ndo_netpoll_cleanup = dsa_user_netpoll_cleanup, + .ndo_poll_controller = dsa_user_poll_controller, #endif - .ndo_setup_tc = dsa_slave_setup_tc, - .ndo_get_stats64 = dsa_slave_get_stats64, - .ndo_vlan_rx_add_vid = dsa_slave_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = dsa_slave_vlan_rx_kill_vid, - .ndo_change_mtu = dsa_slave_change_mtu, - .ndo_fill_forward_path = dsa_slave_fill_forward_path, + .ndo_setup_tc = dsa_user_setup_tc, + .ndo_get_stats64 = dsa_user_get_stats64, + .ndo_vlan_rx_add_vid = dsa_user_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = dsa_user_vlan_rx_kill_vid, + .ndo_change_mtu = dsa_user_change_mtu, + .ndo_fill_forward_path = dsa_user_fill_forward_path, }; static struct device_type dsa_type = { @@ -2465,8 +2465,8 @@ void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) } EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); -static void dsa_slave_phylink_fixed_state(struct phylink_config *config, - struct phylink_link_state *state) +static void dsa_user_phylink_fixed_state(struct phylink_config *config, + struct phylink_link_state *state) { struct dsa_port *dp = container_of(config, struct dsa_port, pl_config); struct dsa_switch *ds = dp->ds; @@ -2477,33 +2477,33 @@ static void dsa_slave_phylink_fixed_state(struct phylink_config *config, ds->ops->phylink_fixed_state(ds, dp->index, state); } -/* slave device setup *******************************************************/ -static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr, - u32 flags) +/* user device setup *******************************************************/ +static int dsa_user_phy_connect(struct net_device *user_dev, int addr, + u32 flags) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); struct dsa_switch *ds = dp->ds; - slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); - if (!slave_dev->phydev) { - netdev_err(slave_dev, "no phy at %d\n", addr); + user_dev->phydev = mdiobus_get_phy(ds->user_mii_bus, addr); + if (!user_dev->phydev) { + netdev_err(user_dev, "no phy at %d\n", addr); return -ENODEV; } - slave_dev->phydev->dev_flags |= flags; + user_dev->phydev->dev_flags |= flags; - return phylink_connect_phy(dp->pl, slave_dev->phydev); + return phylink_connect_phy(dp->pl, user_dev->phydev); } -static int dsa_slave_phy_setup(struct net_device *slave_dev) +static int dsa_user_phy_setup(struct net_device *user_dev) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; u32 phy_flags = 0; int ret; - dp->pl_config.dev = &slave_dev->dev; + dp->pl_config.dev = &user_dev->dev; dp->pl_config.type = PHYLINK_NETDEV; /* The get_fixed_state callback takes precedence over polling the @@ -2511,7 +2511,7 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) * this if the switch provides such a callback. */ if (ds->ops->phylink_fixed_state) { - dp->pl_config.get_fixed_state = dsa_slave_phylink_fixed_state; + dp->pl_config.get_fixed_state = dsa_user_phylink_fixed_state; dp->pl_config.poll_fixed_state = true; } @@ -2523,14 +2523,14 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) phy_flags = ds->ops->get_phy_flags(ds, dp->index); ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); - if (ret == -ENODEV && ds->slave_mii_bus) { + if (ret == -ENODEV && ds->user_mii_bus) { /* We could not connect to a designated PHY or SFP, so try to * use the switch internal MDIO bus instead */ - ret = dsa_slave_phy_connect(slave_dev, dp->index, phy_flags); + ret = dsa_user_phy_connect(user_dev, dp->index, phy_flags); } if (ret) { - netdev_err(slave_dev, "failed to connect to PHY: %pe\n", + netdev_err(user_dev, "failed to connect to PHY: %pe\n", ERR_PTR(ret)); dsa_port_phylink_destroy(dp); } @@ -2538,42 +2538,42 @@ static int dsa_slave_phy_setup(struct net_device *slave_dev) return ret; } -void dsa_slave_setup_tagger(struct net_device *slave) +void dsa_user_setup_tagger(struct net_device *user) { - struct dsa_port *dp = dsa_slave_to_port(slave); - struct net_device *master = dsa_port_to_master(dp); - struct dsa_slave_priv *p = netdev_priv(slave); + struct dsa_port *dp = dsa_user_to_port(user); + struct net_device *conduit = dsa_port_to_conduit(dp); + struct dsa_user_priv *p = netdev_priv(user); const struct dsa_port *cpu_dp = dp->cpu_dp; const struct dsa_switch *ds = dp->ds; - slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; - slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; - /* Try to save one extra realloc later in the TX path (in the master) - * by also inheriting the master's needed headroom and tailroom. + user->needed_headroom = cpu_dp->tag_ops->needed_headroom; + user->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; + /* Try to save one extra realloc later in the TX path (in the conduit) + * by also inheriting the conduit's needed headroom and tailroom. * The 8021q driver also does this. */ - slave->needed_headroom += master->needed_headroom; - slave->needed_tailroom += master->needed_tailroom; + user->needed_headroom += conduit->needed_headroom; + user->needed_tailroom += conduit->needed_tailroom; p->xmit = cpu_dp->tag_ops->xmit; - slave->features = master->vlan_features | NETIF_F_HW_TC; - slave->hw_features |= NETIF_F_HW_TC; - slave->features |= NETIF_F_LLTX; - if (slave->needed_tailroom) - slave->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); + user->features = conduit->vlan_features | NETIF_F_HW_TC; + user->hw_features |= NETIF_F_HW_TC; + user->features |= NETIF_F_LLTX; + if (user->needed_tailroom) + user->features &= ~(NETIF_F_SG | NETIF_F_FRAGLIST); if (ds->needs_standalone_vlan_filtering) - slave->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + user->features |= NETIF_F_HW_VLAN_CTAG_FILTER; } -int dsa_slave_suspend(struct net_device *slave_dev) +int dsa_user_suspend(struct net_device *user_dev) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); - if (!netif_running(slave_dev)) + if (!netif_running(user_dev)) return 0; - netif_device_detach(slave_dev); + netif_device_detach(user_dev); rtnl_lock(); phylink_stop(dp->pl); @@ -2582,14 +2582,14 @@ int dsa_slave_suspend(struct net_device *slave_dev) return 0; } -int dsa_slave_resume(struct net_device *slave_dev) +int dsa_user_resume(struct net_device *user_dev) { - struct dsa_port *dp = dsa_slave_to_port(slave_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); - if (!netif_running(slave_dev)) + if (!netif_running(user_dev)) return 0; - netif_device_attach(slave_dev); + netif_device_attach(user_dev); rtnl_lock(); phylink_start(dp->pl); @@ -2598,12 +2598,12 @@ int dsa_slave_resume(struct net_device *slave_dev) return 0; } -int dsa_slave_create(struct dsa_port *port) +int dsa_user_create(struct dsa_port *port) { - struct net_device *master = dsa_port_to_master(port); + struct net_device *conduit = dsa_port_to_conduit(port); struct dsa_switch *ds = port->ds; - struct net_device *slave_dev; - struct dsa_slave_priv *p; + struct net_device *user_dev; + struct dsa_user_priv *p; const char *name; int assign_type; int ret; @@ -2619,55 +2619,55 @@ int dsa_slave_create(struct dsa_port *port) assign_type = NET_NAME_ENUM; } - slave_dev = alloc_netdev_mqs(sizeof(struct dsa_slave_priv), name, - assign_type, ether_setup, - ds->num_tx_queues, 1); - if (slave_dev == NULL) + user_dev = alloc_netdev_mqs(sizeof(struct dsa_user_priv), name, + assign_type, ether_setup, + ds->num_tx_queues, 1); + if (user_dev == NULL) return -ENOMEM; - slave_dev->rtnl_link_ops = &dsa_link_ops; - slave_dev->ethtool_ops = &dsa_slave_ethtool_ops; + user_dev->rtnl_link_ops = &dsa_link_ops; + user_dev->ethtool_ops = &dsa_user_ethtool_ops; #if IS_ENABLED(CONFIG_DCB) - slave_dev->dcbnl_ops = &dsa_slave_dcbnl_ops; + user_dev->dcbnl_ops = &dsa_user_dcbnl_ops; #endif if (!is_zero_ether_addr(port->mac)) - eth_hw_addr_set(slave_dev, port->mac); + eth_hw_addr_set(user_dev, port->mac); else - eth_hw_addr_inherit(slave_dev, master); - slave_dev->priv_flags |= IFF_NO_QUEUE; + eth_hw_addr_inherit(user_dev, conduit); + user_dev->priv_flags |= IFF_NO_QUEUE; if (dsa_switch_supports_uc_filtering(ds)) - slave_dev->priv_flags |= IFF_UNICAST_FLT; - slave_dev->netdev_ops = &dsa_slave_netdev_ops; + user_dev->priv_flags |= IFF_UNICAST_FLT; + user_dev->netdev_ops = &dsa_user_netdev_ops; if (ds->ops->port_max_mtu) - slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); - SET_NETDEV_DEVTYPE(slave_dev, &dsa_type); - - SET_NETDEV_DEV(slave_dev, port->ds->dev); - SET_NETDEV_DEVLINK_PORT(slave_dev, &port->devlink_port); - slave_dev->dev.of_node = port->dn; - slave_dev->vlan_features = master->vlan_features; - - p = netdev_priv(slave_dev); - slave_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); - if (!slave_dev->tstats) { - free_netdev(slave_dev); + user_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index); + SET_NETDEV_DEVTYPE(user_dev, &dsa_type); + + SET_NETDEV_DEV(user_dev, port->ds->dev); + SET_NETDEV_DEVLINK_PORT(user_dev, &port->devlink_port); + user_dev->dev.of_node = port->dn; + user_dev->vlan_features = conduit->vlan_features; + + p = netdev_priv(user_dev); + user_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!user_dev->tstats) { + free_netdev(user_dev); return -ENOMEM; } - ret = gro_cells_init(&p->gcells, slave_dev); + ret = gro_cells_init(&p->gcells, user_dev); if (ret) goto out_free; p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); - port->slave = slave_dev; - dsa_slave_setup_tagger(slave_dev); + port->user = user_dev; + dsa_user_setup_tagger(user_dev); - netif_carrier_off(slave_dev); + netif_carrier_off(user_dev); - ret = dsa_slave_phy_setup(slave_dev); + ret = dsa_user_phy_setup(user_dev); if (ret) { - netdev_err(slave_dev, + netdev_err(user_dev, "error %d setting up PHY for tree %d, switch %d, port %d\n", ret, ds->dst->index, ds->index, port->index); goto out_gcells; @@ -2675,23 +2675,23 @@ int dsa_slave_create(struct dsa_port *port) rtnl_lock(); - ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN); + ret = dsa_user_change_mtu(user_dev, ETH_DATA_LEN); if (ret && ret != -EOPNOTSUPP) dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n", ret, ETH_DATA_LEN, port->index); - ret = register_netdevice(slave_dev); + ret = register_netdevice(user_dev); if (ret) { - netdev_err(master, "error %d registering interface %s\n", - ret, slave_dev->name); + netdev_err(conduit, "error %d registering interface %s\n", + ret, user_dev->name); rtnl_unlock(); goto out_phy; } if (IS_ENABLED(CONFIG_DCB)) { - ret = dsa_slave_dcbnl_init(slave_dev); + ret = dsa_user_dcbnl_init(user_dev); if (ret) { - netdev_err(slave_dev, + netdev_err(user_dev, "failed to initialize DCB: %pe\n", ERR_PTR(ret)); rtnl_unlock(); @@ -2699,7 +2699,7 @@ int dsa_slave_create(struct dsa_port *port) } } - ret = netdev_upper_dev_link(master, slave_dev, NULL); + ret = netdev_upper_dev_link(conduit, user_dev, NULL); rtnl_unlock(); @@ -2709,7 +2709,7 @@ int dsa_slave_create(struct dsa_port *port) return 0; out_unregister: - unregister_netdev(slave_dev); + unregister_netdev(user_dev); out_phy: rtnl_lock(); phylink_disconnect_phy(p->dp->pl); @@ -2718,122 +2718,122 @@ out_phy: out_gcells: gro_cells_destroy(&p->gcells); out_free: - free_percpu(slave_dev->tstats); - free_netdev(slave_dev); - port->slave = NULL; + free_percpu(user_dev->tstats); + free_netdev(user_dev); + port->user = NULL; return ret; } -void dsa_slave_destroy(struct net_device *slave_dev) +void dsa_user_destroy(struct net_device *user_dev) { - struct net_device *master = dsa_slave_to_master(slave_dev); - struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct net_device *conduit = dsa_user_to_conduit(user_dev); + struct dsa_port *dp = dsa_user_to_port(user_dev); + struct dsa_user_priv *p = netdev_priv(user_dev); - netif_carrier_off(slave_dev); + netif_carrier_off(user_dev); rtnl_lock(); - netdev_upper_dev_unlink(master, slave_dev); - unregister_netdevice(slave_dev); + netdev_upper_dev_unlink(conduit, user_dev); + unregister_netdevice(user_dev); phylink_disconnect_phy(dp->pl); rtnl_unlock(); dsa_port_phylink_destroy(dp); gro_cells_destroy(&p->gcells); - free_percpu(slave_dev->tstats); - free_netdev(slave_dev); + free_percpu(user_dev->tstats); + free_netdev(user_dev); } -int dsa_slave_change_master(struct net_device *dev, struct net_device *master, +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, struct netlink_ext_ack *extack) { - struct net_device *old_master = dsa_slave_to_master(dev); - struct dsa_port *dp = dsa_slave_to_port(dev); + struct net_device *old_conduit = dsa_user_to_conduit(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch *ds = dp->ds; struct net_device *upper; struct list_head *iter; int err; - if (master == old_master) + if (conduit == old_conduit) return 0; - if (!ds->ops->port_change_master) { + if (!ds->ops->port_change_conduit) { NL_SET_ERR_MSG_MOD(extack, - "Driver does not support changing DSA master"); + "Driver does not support changing DSA conduit"); return -EOPNOTSUPP; } - if (!netdev_uses_dsa(master)) { + if (!netdev_uses_dsa(conduit)) { NL_SET_ERR_MSG_MOD(extack, - "Interface not eligible as DSA master"); + "Interface not eligible as DSA conduit"); return -EOPNOTSUPP; } - netdev_for_each_upper_dev_rcu(master, upper, iter) { - if (dsa_slave_dev_check(upper)) + netdev_for_each_upper_dev_rcu(conduit, upper, iter) { + if (dsa_user_dev_check(upper)) continue; if (netif_is_bridge_master(upper)) continue; - NL_SET_ERR_MSG_MOD(extack, "Cannot join master with unknown uppers"); + NL_SET_ERR_MSG_MOD(extack, "Cannot join conduit with unknown uppers"); return -EOPNOTSUPP; } - /* Since we allow live-changing the DSA master, plus we auto-open the - * DSA master when the user port opens => we need to ensure that the - * new DSA master is open too. + /* Since we allow live-changing the DSA conduit, plus we auto-open the + * DSA conduit when the user port opens => we need to ensure that the + * new DSA conduit is open too. */ if (dev->flags & IFF_UP) { - err = dev_open(master, extack); + err = dev_open(conduit, extack); if (err) return err; } - netdev_upper_dev_unlink(old_master, dev); + netdev_upper_dev_unlink(old_conduit, dev); - err = netdev_upper_dev_link(master, dev, extack); + err = netdev_upper_dev_link(conduit, dev, extack); if (err) - goto out_revert_old_master_unlink; + goto out_revert_old_conduit_unlink; - err = dsa_port_change_master(dp, master, extack); + err = dsa_port_change_conduit(dp, conduit, extack); if (err) - goto out_revert_master_link; + goto out_revert_conduit_link; /* Update the MTU of the new CPU port through cross-chip notifiers */ - err = dsa_slave_change_mtu(dev, dev->mtu); + err = dsa_user_change_mtu(dev, dev->mtu); if (err && err != -EOPNOTSUPP) { netdev_warn(dev, - "nonfatal error updating MTU with new master: %pe\n", + "nonfatal error updating MTU with new conduit: %pe\n", ERR_PTR(err)); } /* If the port doesn't have its own MAC address and relies on the DSA - * master's one, inherit it again from the new DSA master. + * conduit's one, inherit it again from the new DSA conduit. */ if (is_zero_ether_addr(dp->mac)) - eth_hw_addr_inherit(dev, master); + eth_hw_addr_inherit(dev, conduit); return 0; -out_revert_master_link: - netdev_upper_dev_unlink(master, dev); -out_revert_old_master_unlink: - netdev_upper_dev_link(old_master, dev, NULL); +out_revert_conduit_link: + netdev_upper_dev_unlink(conduit, dev); +out_revert_old_conduit_unlink: + netdev_upper_dev_link(old_conduit, dev, NULL); return err; } -bool dsa_slave_dev_check(const struct net_device *dev) +bool dsa_user_dev_check(const struct net_device *dev) { - return dev->netdev_ops == &dsa_slave_netdev_ops; + return dev->netdev_ops == &dsa_user_netdev_ops; } -EXPORT_SYMBOL_GPL(dsa_slave_dev_check); +EXPORT_SYMBOL_GPL(dsa_user_dev_check); -static int dsa_slave_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +static int dsa_user_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct netlink_ext_ack *extack; int err = NOTIFY_DONE; - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return err; extack = netdev_notifier_info_to_extack(&info->info); @@ -2885,28 +2885,28 @@ static int dsa_slave_changeupper(struct net_device *dev, return err; } -static int dsa_slave_prechangeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +static int dsa_user_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return NOTIFY_DONE; if (netif_is_bridge_master(info->upper_dev) && !info->linking) dsa_port_pre_bridge_leave(dp, info->upper_dev); else if (netif_is_lag_master(info->upper_dev) && !info->linking) dsa_port_pre_lag_leave(dp, info->upper_dev); - /* dsa_port_pre_hsr_leave is not yet necessary since hsr cannot be - * meaningfully enslaved to a bridge yet + /* dsa_port_pre_hsr_leave is not yet necessary since hsr devices cannot + * meaningfully placed under a bridge yet */ return NOTIFY_DONE; } static int -dsa_slave_lag_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_lag_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; @@ -2917,15 +2917,15 @@ dsa_slave_lag_changeupper(struct net_device *dev, return err; netdev_for_each_lower_dev(dev, lower, iter) { - if (!dsa_slave_dev_check(lower)) + if (!dsa_user_dev_check(lower)) continue; - dp = dsa_slave_to_port(lower); + dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; - err = dsa_slave_changeupper(lower, info); + err = dsa_user_changeupper(lower, info); if (notifier_to_errno(err)) break; } @@ -2933,12 +2933,12 @@ dsa_slave_lag_changeupper(struct net_device *dev, return err; } -/* Same as dsa_slave_lag_changeupper() except that it calls - * dsa_slave_prechangeupper() +/* Same as dsa_user_lag_changeupper() except that it calls + * dsa_user_prechangeupper() */ static int -dsa_slave_lag_prechangeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_lag_prechangeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct net_device *lower; struct list_head *iter; @@ -2949,15 +2949,15 @@ dsa_slave_lag_prechangeupper(struct net_device *dev, return err; netdev_for_each_lower_dev(dev, lower, iter) { - if (!dsa_slave_dev_check(lower)) + if (!dsa_user_dev_check(lower)) continue; - dp = dsa_slave_to_port(lower); + dp = dsa_user_to_port(lower); if (!dp->lag) /* Software LAG */ continue; - err = dsa_slave_prechangeupper(lower, info); + err = dsa_user_prechangeupper(lower, info); if (notifier_to_errno(err)) break; } @@ -2970,7 +2970,7 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *ext_ack; - struct net_device *slave, *br; + struct net_device *user, *br; struct dsa_port *dp; ext_ack = netdev_notifier_info_to_extack(&info->info); @@ -2978,11 +2978,11 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, if (!is_vlan_dev(dev)) return NOTIFY_DONE; - slave = vlan_dev_real_dev(dev); - if (!dsa_slave_dev_check(slave)) + user = vlan_dev_real_dev(dev); + if (!dsa_user_dev_check(user)) return NOTIFY_DONE; - dp = dsa_slave_to_port(slave); + dp = dsa_user_to_port(user); br = dsa_port_bridge_dev_get(dp); if (!br) return NOTIFY_DONE; @@ -2991,7 +2991,7 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, if (br_vlan_enabled(br) && netif_is_bridge_master(info->upper_dev) && info->linking) { NL_SET_ERR_MSG_MOD(ext_ack, - "Cannot enslave VLAN device into VLAN aware bridge"); + "Cannot make VLAN device join VLAN-aware bridge"); return notifier_from_errno(-EINVAL); } @@ -2999,10 +2999,10 @@ dsa_prevent_bridging_8021q_upper(struct net_device *dev, } static int -dsa_slave_check_8021q_upper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_check_8021q_upper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); struct net_device *br = dsa_port_bridge_dev_get(dp); struct bridge_vlan_info br_info; struct netlink_ext_ack *extack; @@ -3030,17 +3030,17 @@ dsa_slave_check_8021q_upper(struct net_device *dev, } static int -dsa_slave_prechangeupper_sanity_check(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_user_prechangeupper_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct dsa_switch *ds; struct dsa_port *dp; int err; - if (!dsa_slave_dev_check(dev)) + if (!dsa_user_dev_check(dev)) return dsa_prevent_bridging_8021q_upper(dev, info); - dp = dsa_slave_to_port(dev); + dp = dsa_user_to_port(dev); ds = dp->ds; if (ds->ops->port_prechangeupper) { @@ -3050,17 +3050,17 @@ dsa_slave_prechangeupper_sanity_check(struct net_device *dev, } if (is_vlan_dev(info->upper_dev)) - return dsa_slave_check_8021q_upper(dev, info); + return dsa_user_check_8021q_upper(dev, info); return NOTIFY_DONE; } -/* To be eligible as a DSA master, a LAG must have all lower interfaces be - * eligible DSA masters. Additionally, all LAG slaves must be DSA masters of +/* To be eligible as a DSA conduit, a LAG must have all lower interfaces be + * eligible DSA conduits. Additionally, all LAG slaves must be DSA conduits of * switches in the same switch tree. */ -static int dsa_lag_master_validate(struct net_device *lag_dev, - struct netlink_ext_ack *extack) +static int dsa_lag_conduit_validate(struct net_device *lag_dev, + struct netlink_ext_ack *extack) { struct net_device *lower1, *lower2; struct list_head *iter1, *iter2; @@ -3070,7 +3070,7 @@ static int dsa_lag_master_validate(struct net_device *lag_dev, if (!netdev_uses_dsa(lower1) || !netdev_uses_dsa(lower2)) { NL_SET_ERR_MSG_MOD(extack, - "All LAG ports must be eligible as DSA masters"); + "All LAG ports must be eligible as DSA conduits"); return notifier_from_errno(-EINVAL); } @@ -3080,7 +3080,7 @@ static int dsa_lag_master_validate(struct net_device *lag_dev, if (!dsa_port_tree_same(lower1->dsa_ptr, lower2->dsa_ptr)) { NL_SET_ERR_MSG_MOD(extack, - "LAG contains DSA masters of disjoint switch trees"); + "LAG contains DSA conduits of disjoint switch trees"); return notifier_from_errno(-EINVAL); } } @@ -3090,41 +3090,41 @@ static int dsa_lag_master_validate(struct net_device *lag_dev, } static int -dsa_master_prechangeupper_sanity_check(struct net_device *master, - struct netdev_notifier_changeupper_info *info) +dsa_conduit_prechangeupper_sanity_check(struct net_device *conduit, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); - if (!netdev_uses_dsa(master)) + if (!netdev_uses_dsa(conduit)) return NOTIFY_DONE; if (!info->linking) return NOTIFY_DONE; /* Allow DSA switch uppers */ - if (dsa_slave_dev_check(info->upper_dev)) + if (dsa_user_dev_check(info->upper_dev)) return NOTIFY_DONE; - /* Allow bridge uppers of DSA masters, subject to further + /* Allow bridge uppers of DSA conduits, subject to further * restrictions in dsa_bridge_prechangelower_sanity_check() */ if (netif_is_bridge_master(info->upper_dev)) return NOTIFY_DONE; /* Allow LAG uppers, subject to further restrictions in - * dsa_lag_master_prechangelower_sanity_check() + * dsa_lag_conduit_prechangelower_sanity_check() */ if (netif_is_lag_master(info->upper_dev)) - return dsa_lag_master_validate(info->upper_dev, extack); + return dsa_lag_conduit_validate(info->upper_dev, extack); NL_SET_ERR_MSG_MOD(extack, - "DSA master cannot join unknown upper interfaces"); + "DSA conduit cannot join unknown upper interfaces"); return notifier_from_errno(-EBUSY); } static int -dsa_lag_master_prechangelower_sanity_check(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +dsa_lag_conduit_prechangelower_sanity_check(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack = netdev_notifier_info_to_extack(&info->info); struct net_device *lag_dev = info->upper_dev; @@ -3139,14 +3139,14 @@ dsa_lag_master_prechangelower_sanity_check(struct net_device *dev, if (!netdev_uses_dsa(dev)) { NL_SET_ERR_MSG(extack, - "Only DSA masters can join a LAG DSA master"); + "Only DSA conduits can join a LAG DSA conduit"); return notifier_from_errno(-EINVAL); } netdev_for_each_lower_dev(lag_dev, lower, iter) { if (!dsa_port_tree_same(dev->dsa_ptr, lower->dsa_ptr)) { NL_SET_ERR_MSG(extack, - "Interface is DSA master for a different switch tree than this LAG"); + "Interface is DSA conduit for a different switch tree than this LAG"); return notifier_from_errno(-EINVAL); } @@ -3156,13 +3156,13 @@ dsa_lag_master_prechangelower_sanity_check(struct net_device *dev, return NOTIFY_DONE; } -/* Don't allow bridging of DSA masters, since the bridge layer rx_handler +/* Don't allow bridging of DSA conduits, since the bridge layer rx_handler * prevents the DSA fake ethertype handler to be invoked, so we don't get the * chance to strip off and parse the DSA switch tag protocol header (the bridge * layer just returns RX_HANDLER_CONSUMED, stopping RX processing for these * frames). * The only case where that would not be an issue is when bridging can already - * be offloaded, such as when the DSA master is itself a DSA or plain switchdev + * be offloaded, such as when the DSA conduit is itself a DSA or plain switchdev * port, and is bridged only with other ports from the same hardware device. */ static int @@ -3188,7 +3188,7 @@ dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, if (!netdev_port_same_parent_id(lower, new_lower)) { NL_SET_ERR_MSG(extack, - "Cannot do software bridging with a DSA master"); + "Cannot do software bridging with a DSA conduit"); return notifier_from_errno(-EINVAL); } } @@ -3196,45 +3196,45 @@ dsa_bridge_prechangelower_sanity_check(struct net_device *new_lower, return NOTIFY_DONE; } -static void dsa_tree_migrate_ports_from_lag_master(struct dsa_switch_tree *dst, - struct net_device *lag_dev) +static void dsa_tree_migrate_ports_from_lag_conduit(struct dsa_switch_tree *dst, + struct net_device *lag_dev) { - struct net_device *new_master = dsa_tree_find_first_master(dst); + struct net_device *new_conduit = dsa_tree_find_first_conduit(dst); struct dsa_port *dp; int err; dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp) != lag_dev) + if (dsa_port_to_conduit(dp) != lag_dev) continue; - err = dsa_slave_change_master(dp->slave, new_master, NULL); + err = dsa_user_change_conduit(dp->user, new_conduit, NULL); if (err) { - netdev_err(dp->slave, - "failed to restore master to %s: %pe\n", - new_master->name, ERR_PTR(err)); + netdev_err(dp->user, + "failed to restore conduit to %s: %pe\n", + new_conduit->name, ERR_PTR(err)); } } } -static int dsa_master_lag_join(struct net_device *master, - struct net_device *lag_dev, - struct netdev_lag_upper_info *uinfo, - struct netlink_ext_ack *extack) +static int dsa_conduit_lag_join(struct net_device *conduit, + struct net_device *lag_dev, + struct netdev_lag_upper_info *uinfo, + struct netlink_ext_ack *extack) { - struct dsa_port *cpu_dp = master->dsa_ptr; + struct dsa_port *cpu_dp = conduit->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; struct dsa_port *dp; int err; - err = dsa_master_lag_setup(lag_dev, cpu_dp, uinfo, extack); + err = dsa_conduit_lag_setup(lag_dev, cpu_dp, uinfo, extack); if (err) return err; dsa_tree_for_each_user_port(dp, dst) { - if (dsa_port_to_master(dp) != master) + if (dsa_port_to_conduit(dp) != conduit) continue; - err = dsa_slave_change_master(dp->slave, lag_dev, extack); + err = dsa_user_change_conduit(dp->user, lag_dev, extack); if (err) goto restore; } @@ -3243,24 +3243,24 @@ static int dsa_master_lag_join(struct net_device *master, restore: dsa_tree_for_each_user_port_continue_reverse(dp, dst) { - if (dsa_port_to_master(dp) != lag_dev) + if (dsa_port_to_conduit(dp) != lag_dev) continue; - err = dsa_slave_change_master(dp->slave, master, NULL); + err = dsa_user_change_conduit(dp->user, conduit, NULL); if (err) { - netdev_err(dp->slave, - "failed to restore master to %s: %pe\n", - master->name, ERR_PTR(err)); + netdev_err(dp->user, + "failed to restore conduit to %s: %pe\n", + conduit->name, ERR_PTR(err)); } } - dsa_master_lag_teardown(lag_dev, master->dsa_ptr); + dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); return err; } -static void dsa_master_lag_leave(struct net_device *master, - struct net_device *lag_dev) +static void dsa_conduit_lag_leave(struct net_device *conduit, + struct net_device *lag_dev) { struct dsa_port *dp, *cpu_dp = lag_dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->dst; @@ -3277,10 +3277,10 @@ static void dsa_master_lag_leave(struct net_device *master, if (new_cpu_dp) { /* Update the CPU port of the user ports still under the LAG - * so that dsa_port_to_master() continues to work properly + * so that dsa_port_to_conduit() continues to work properly */ dsa_tree_for_each_user_port(dp, dst) - if (dsa_port_to_master(dp) == lag_dev) + if (dsa_port_to_conduit(dp) == lag_dev) dp->cpu_dp = new_cpu_dp; /* Update the index of the virtual CPU port to match the lowest @@ -3289,20 +3289,20 @@ static void dsa_master_lag_leave(struct net_device *master, lag_dev->dsa_ptr = new_cpu_dp; wmb(); } else { - /* If the LAG DSA master has no ports left, migrate back all + /* If the LAG DSA conduit has no ports left, migrate back all * user ports to the first physical CPU port */ - dsa_tree_migrate_ports_from_lag_master(dst, lag_dev); + dsa_tree_migrate_ports_from_lag_conduit(dst, lag_dev); } - /* This DSA master has left its LAG in any case, so let + /* This DSA conduit has left its LAG in any case, so let * the CPU port leave the hardware LAG as well */ - dsa_master_lag_teardown(lag_dev, master->dsa_ptr); + dsa_conduit_lag_teardown(lag_dev, conduit->dsa_ptr); } -static int dsa_master_changeupper(struct net_device *dev, - struct netdev_notifier_changeupper_info *info) +static int dsa_conduit_changeupper(struct net_device *dev, + struct netdev_notifier_changeupper_info *info) { struct netlink_ext_ack *extack; int err = NOTIFY_DONE; @@ -3314,11 +3314,11 @@ static int dsa_master_changeupper(struct net_device *dev, if (netif_is_lag_master(info->upper_dev)) { if (info->linking) { - err = dsa_master_lag_join(dev, info->upper_dev, - info->upper_info, extack); + err = dsa_conduit_lag_join(dev, info->upper_dev, + info->upper_info, extack); err = notifier_from_errno(err); } else { - dsa_master_lag_leave(dev, info->upper_dev); + dsa_conduit_lag_leave(dev, info->upper_dev); err = NOTIFY_OK; } } @@ -3326,8 +3326,8 @@ static int dsa_master_changeupper(struct net_device *dev, return err; } -static int dsa_slave_netdevice_event(struct notifier_block *nb, - unsigned long event, void *ptr) +static int dsa_user_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); @@ -3336,15 +3336,15 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, struct netdev_notifier_changeupper_info *info = ptr; int err; - err = dsa_slave_prechangeupper_sanity_check(dev, info); + err = dsa_user_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; - err = dsa_master_prechangeupper_sanity_check(dev, info); + err = dsa_conduit_prechangeupper_sanity_check(dev, info); if (notifier_to_errno(err)) return err; - err = dsa_lag_master_prechangelower_sanity_check(dev, info); + err = dsa_lag_conduit_prechangelower_sanity_check(dev, info); if (notifier_to_errno(err)) return err; @@ -3352,11 +3352,11 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, if (notifier_to_errno(err)) return err; - err = dsa_slave_prechangeupper(dev, ptr); + err = dsa_user_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; - err = dsa_slave_lag_prechangeupper(dev, ptr); + err = dsa_user_lag_prechangeupper(dev, ptr); if (notifier_to_errno(err)) return err; @@ -3365,15 +3365,15 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, case NETDEV_CHANGEUPPER: { int err; - err = dsa_slave_changeupper(dev, ptr); + err = dsa_user_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; - err = dsa_slave_lag_changeupper(dev, ptr); + err = dsa_user_lag_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; - err = dsa_master_changeupper(dev, ptr); + err = dsa_conduit_changeupper(dev, ptr); if (notifier_to_errno(err)) return err; @@ -3384,13 +3384,13 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, struct dsa_port *dp; int err = 0; - if (dsa_slave_dev_check(dev)) { - dp = dsa_slave_to_port(dev); + if (dsa_user_dev_check(dev)) { + dp = dsa_user_to_port(dev); err = dsa_port_lag_change(dp, info->lower_state_info); } - /* Mirror LAG port events on DSA masters that are in + /* Mirror LAG port events on DSA conduits that are in * a LAG towards their respective switch CPU ports */ if (netdev_uses_dsa(dev)) { @@ -3403,28 +3403,28 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, } case NETDEV_CHANGE: case NETDEV_UP: { - /* Track state of master port. - * DSA driver may require the master port (and indirectly + /* Track state of conduit port. + * DSA driver may require the conduit port (and indirectly * the tagger) to be available for some special operation. */ if (netdev_uses_dsa(dev)) { struct dsa_port *cpu_dp = dev->dsa_ptr; struct dsa_switch_tree *dst = cpu_dp->ds->dst; - /* Track when the master port is UP */ - dsa_tree_master_oper_state_change(dst, dev, - netif_oper_up(dev)); + /* Track when the conduit port is UP */ + dsa_tree_conduit_oper_state_change(dst, dev, + netif_oper_up(dev)); - /* Track when the master port is ready and can accept + /* Track when the conduit port is ready and can accept * packet. * NETDEV_UP event is not enough to flag a port as ready. * We also have to wait for linkwatch_do_dev to dev_activate * and emit a NETDEV_CHANGE event. - * We check if a master port is ready by checking if the dev + * We check if a conduit port is ready by checking if the dev * have a qdisc assigned and is not noop. */ - dsa_tree_master_admin_state_change(dst, dev, - !qdisc_tx_is_noop(dev)); + dsa_tree_conduit_admin_state_change(dst, dev, + !qdisc_tx_is_noop(dev)); return NOTIFY_OK; } @@ -3442,7 +3442,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, cpu_dp = dev->dsa_ptr; dst = cpu_dp->ds->dst; - dsa_tree_master_admin_state_change(dst, dev, false); + dsa_tree_conduit_admin_state_change(dst, dev, false); list_for_each_entry(dp, &dst->ports, list) { if (!dsa_port_is_user(dp)) @@ -3451,7 +3451,7 @@ static int dsa_slave_netdevice_event(struct notifier_block *nb, if (dp->cpu_dp != cpu_dp) continue; - list_add(&dp->slave->close_list, &close_list); + list_add(&dp->user->close_list, &close_list); } dev_close_many(&close_list, true); @@ -3477,7 +3477,7 @@ dsa_fdb_offload_notify(struct dsa_switchdev_event_work *switchdev_work) switchdev_work->orig_dev, &info.info, NULL); } -static void dsa_slave_switchdev_event_work(struct work_struct *work) +static void dsa_user_switchdev_event_work(struct work_struct *work) { struct dsa_switchdev_event_work *switchdev_work = container_of(work, struct dsa_switchdev_event_work, work); @@ -3488,7 +3488,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) struct dsa_port *dp; int err; - dp = dsa_slave_to_port(dev); + dp = dsa_user_to_port(dev); ds = dp->ds; switch (switchdev_work->event) { @@ -3530,7 +3530,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) static bool dsa_foreign_dev_check(const struct net_device *dev, const struct net_device *foreign_dev) { - const struct dsa_port *dp = dsa_slave_to_port(dev); + const struct dsa_port *dp = dsa_user_to_port(dev); struct dsa_switch_tree *dst = dp->ds->dst; if (netif_is_bridge_master(foreign_dev)) @@ -3543,13 +3543,13 @@ static bool dsa_foreign_dev_check(const struct net_device *dev, return true; } -static int dsa_slave_fdb_event(struct net_device *dev, - struct net_device *orig_dev, - unsigned long event, const void *ctx, - const struct switchdev_notifier_fdb_info *fdb_info) +static int dsa_user_fdb_event(struct net_device *dev, + struct net_device *orig_dev, + unsigned long event, const void *ctx, + const struct switchdev_notifier_fdb_info *fdb_info) { struct dsa_switchdev_event_work *switchdev_work; - struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_port *dp = dsa_user_to_port(dev); bool host_addr = fdb_info->is_local; struct dsa_switch *ds = dp->ds; @@ -3598,7 +3598,7 @@ static int dsa_slave_fdb_event(struct net_device *dev, orig_dev->name, fdb_info->addr, fdb_info->vid, host_addr ? " as host address" : ""); - INIT_WORK(&switchdev_work->work, dsa_slave_switchdev_event_work); + INIT_WORK(&switchdev_work->work, dsa_user_switchdev_event_work); switchdev_work->event = event; switchdev_work->dev = dev; switchdev_work->orig_dev = orig_dev; @@ -3613,8 +3613,8 @@ static int dsa_slave_fdb_event(struct net_device *dev, } /* Called under rcu_read_lock() */ -static int dsa_slave_switchdev_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int dsa_user_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; @@ -3622,15 +3622,15 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_attr_set); + dsa_user_dev_check, + dsa_user_port_attr_set); return notifier_from_errno(err); case SWITCHDEV_FDB_ADD_TO_DEVICE: case SWITCHDEV_FDB_DEL_TO_DEVICE: err = switchdev_handle_fdb_event_to_device(dev, event, ptr, - dsa_slave_dev_check, + dsa_user_dev_check, dsa_foreign_dev_check, - dsa_slave_fdb_event); + dsa_user_fdb_event); return notifier_from_errno(err); default: return NOTIFY_DONE; @@ -3639,8 +3639,8 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, return NOTIFY_OK; } -static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, - unsigned long event, void *ptr) +static int dsa_user_switchdev_blocking_event(struct notifier_block *unused, + unsigned long event, void *ptr) { struct net_device *dev = switchdev_notifier_info_to_dev(ptr); int err; @@ -3648,52 +3648,52 @@ static int dsa_slave_switchdev_blocking_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_PORT_OBJ_ADD: err = switchdev_handle_port_obj_add_foreign(dev, ptr, - dsa_slave_dev_check, + dsa_user_dev_check, dsa_foreign_dev_check, - dsa_slave_port_obj_add); + dsa_user_port_obj_add); return notifier_from_errno(err); case SWITCHDEV_PORT_OBJ_DEL: err = switchdev_handle_port_obj_del_foreign(dev, ptr, - dsa_slave_dev_check, + dsa_user_dev_check, dsa_foreign_dev_check, - dsa_slave_port_obj_del); + dsa_user_port_obj_del); return notifier_from_errno(err); case SWITCHDEV_PORT_ATTR_SET: err = switchdev_handle_port_attr_set(dev, ptr, - dsa_slave_dev_check, - dsa_slave_port_attr_set); + dsa_user_dev_check, + dsa_user_port_attr_set); return notifier_from_errno(err); } return NOTIFY_DONE; } -static struct notifier_block dsa_slave_nb __read_mostly = { - .notifier_call = dsa_slave_netdevice_event, +static struct notifier_block dsa_user_nb __read_mostly = { + .notifier_call = dsa_user_netdevice_event, }; -struct notifier_block dsa_slave_switchdev_notifier = { - .notifier_call = dsa_slave_switchdev_event, +struct notifier_block dsa_user_switchdev_notifier = { + .notifier_call = dsa_user_switchdev_event, }; -struct notifier_block dsa_slave_switchdev_blocking_notifier = { - .notifier_call = dsa_slave_switchdev_blocking_event, +struct notifier_block dsa_user_switchdev_blocking_notifier = { + .notifier_call = dsa_user_switchdev_blocking_event, }; -int dsa_slave_register_notifier(void) +int dsa_user_register_notifier(void) { struct notifier_block *nb; int err; - err = register_netdevice_notifier(&dsa_slave_nb); + err = register_netdevice_notifier(&dsa_user_nb); if (err) return err; - err = register_switchdev_notifier(&dsa_slave_switchdev_notifier); + err = register_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) goto err_switchdev_nb; - nb = &dsa_slave_switchdev_blocking_notifier; + nb = &dsa_user_switchdev_blocking_notifier; err = register_switchdev_blocking_notifier(nb); if (err) goto err_switchdev_blocking_nb; @@ -3701,27 +3701,27 @@ int dsa_slave_register_notifier(void) return 0; err_switchdev_blocking_nb: - unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); + unregister_switchdev_notifier(&dsa_user_switchdev_notifier); err_switchdev_nb: - unregister_netdevice_notifier(&dsa_slave_nb); + unregister_netdevice_notifier(&dsa_user_nb); return err; } -void dsa_slave_unregister_notifier(void) +void dsa_user_unregister_notifier(void) { struct notifier_block *nb; int err; - nb = &dsa_slave_switchdev_blocking_notifier; + nb = &dsa_user_switchdev_blocking_notifier; err = unregister_switchdev_blocking_notifier(nb); if (err) pr_err("DSA: failed to unregister switchdev blocking notifier (%d)\n", err); - err = unregister_switchdev_notifier(&dsa_slave_switchdev_notifier); + err = unregister_switchdev_notifier(&dsa_user_switchdev_notifier); if (err) pr_err("DSA: failed to unregister switchdev notifier (%d)\n", err); - err = unregister_netdevice_notifier(&dsa_slave_nb); + err = unregister_netdevice_notifier(&dsa_user_nb); if (err) - pr_err("DSA: failed to unregister slave notifier (%d)\n", err); + pr_err("DSA: failed to unregister user notifier (%d)\n", err); } diff --git a/net/dsa/user.h b/net/dsa/user.h new file mode 100644 index 000000000000..996069130bea --- /dev/null +++ b/net/dsa/user.h @@ -0,0 +1,69 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __DSA_USER_H +#define __DSA_USER_H + +#include <linux/if_bridge.h> +#include <linux/if_vlan.h> +#include <linux/list.h> +#include <linux/netpoll.h> +#include <linux/types.h> +#include <net/dsa.h> +#include <net/gro_cells.h> + +struct net_device; +struct netlink_ext_ack; + +extern struct notifier_block dsa_user_switchdev_notifier; +extern struct notifier_block dsa_user_switchdev_blocking_notifier; + +struct dsa_user_priv { + /* Copy of CPU port xmit for faster access in user transmit hot path */ + struct sk_buff * (*xmit)(struct sk_buff *skb, + struct net_device *dev); + + struct gro_cells gcells; + + /* DSA port data, such as switch, port index, etc. */ + struct dsa_port *dp; + +#ifdef CONFIG_NET_POLL_CONTROLLER + struct netpoll *netpoll; +#endif + + /* TC context */ + struct list_head mall_tc_list; +}; + +void dsa_user_mii_bus_init(struct dsa_switch *ds); +int dsa_user_create(struct dsa_port *dp); +void dsa_user_destroy(struct net_device *user_dev); +int dsa_user_suspend(struct net_device *user_dev); +int dsa_user_resume(struct net_device *user_dev); +int dsa_user_register_notifier(void); +void dsa_user_unregister_notifier(void); +void dsa_user_sync_ha(struct net_device *dev); +void dsa_user_unsync_ha(struct net_device *dev); +void dsa_user_setup_tagger(struct net_device *user); +int dsa_user_change_mtu(struct net_device *dev, int new_mtu); +int dsa_user_change_conduit(struct net_device *dev, struct net_device *conduit, + struct netlink_ext_ack *extack); +int dsa_user_manage_vlan_filtering(struct net_device *dev, + bool vlan_filtering); + +static inline struct dsa_port *dsa_user_to_port(const struct net_device *dev) +{ + struct dsa_user_priv *p = netdev_priv(dev); + + return p->dp; +} + +static inline struct net_device * +dsa_user_to_conduit(const struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + + return dsa_port_to_conduit(dp); +} + +#endif diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 883ed9be81f9..0515d6604b3b 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -431,10 +431,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, ethnl_string_array_t names, struct netlink_ext_ack *extack, bool *mod) { - u32 *orig_bitmap, *saved_bitmap = NULL; struct nlattr *bit_attr; bool no_mask; - bool dummy; int rem; int ret; @@ -450,22 +448,8 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, } no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; - if (no_mask) { - unsigned int nwords = DIV_ROUND_UP(nbits, 32); - unsigned int nbytes = nwords * sizeof(u32); - - /* The bitmap size is only the size of the map part without - * its mask part. - */ - saved_bitmap = kcalloc(nwords, sizeof(u32), GFP_KERNEL); - if (!saved_bitmap) - return -ENOMEM; - memcpy(saved_bitmap, bitmap, nbytes); - ethnl_bitmap32_clear(bitmap, 0, nbits, &dummy); - orig_bitmap = saved_bitmap; - } else { - orig_bitmap = bitmap; - } + if (no_mask) + ethnl_bitmap32_clear(bitmap, 0, nbits, mod); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; @@ -474,14 +458,13 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, if (nla_type(bit_attr) != ETHTOOL_A_BITSET_BITS_BIT) { NL_SET_ERR_MSG_ATTR(extack, bit_attr, "only ETHTOOL_A_BITSET_BITS_BIT allowed in ETHTOOL_A_BITSET_BITS"); - ret = -EINVAL; - goto out; + return -EINVAL; } ret = ethnl_parse_bit(&idx, &new_val, nbits, bit_attr, no_mask, names, extack); if (ret < 0) - goto out; - old_val = orig_bitmap[idx / 32] & ((u32)1 << (idx % 32)); + return ret; + old_val = bitmap[idx / 32] & ((u32)1 << (idx % 32)); if (new_val != old_val) { if (new_val) bitmap[idx / 32] |= ((u32)1 << (idx % 32)); @@ -491,10 +474,7 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, } } - ret = 0; -out: - kfree(saved_bitmap); - return ret; + return 0; } static int ethnl_compact_sanity_checks(unsigned int nbits, diff --git a/net/ethtool/common.c b/net/ethtool/common.c index f5598c5f50de..b4419fb6df6a 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -685,3 +685,24 @@ ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings, link_ksettings->base.duplex = link_info->duplex; } EXPORT_SYMBOL_GPL(ethtool_params_from_link_mode); + +/** + * ethtool_forced_speed_maps_init + * @maps: Pointer to an array of Ethtool forced speed map + * @size: Array size + * + * Initialize an array of Ethtool forced speed map to Ethtool link modes. This + * should be called during driver module init. + */ +void +ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) +{ + for (u32 i = 0; i < size; i++) { + struct ethtool_forced_speed_map *map = &maps[i]; + + linkmode_set_bit_array(map->cap_arr, map->arr_size, map->caps); + map->cap_arr = NULL; + map->arr_size = 0; + } +} +EXPORT_SYMBOL_GPL(ethtool_forced_speed_maps_init); diff --git a/net/handshake/netlink.c b/net/handshake/netlink.c index 64a0046dd611..89637e732866 100644 --- a/net/handshake/netlink.c +++ b/net/handshake/netlink.c @@ -87,29 +87,6 @@ struct nlmsghdr *handshake_genl_put(struct sk_buff *msg, } EXPORT_SYMBOL(handshake_genl_put); -/* - * dup() a kernel socket for use as a user space file descriptor - * in the current process. The kernel socket must have an - * instatiated struct file. - * - * Implicit argument: "current()" - */ -static int handshake_dup(struct socket *sock) -{ - struct file *file; - int newfd; - - file = get_file(sock->file); - newfd = get_unused_fd_flags(O_CLOEXEC); - if (newfd < 0) { - fput(file); - return newfd; - } - - fd_install(newfd, file); - return newfd; -} - int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) { struct net *net = sock_net(skb->sk); @@ -133,17 +110,20 @@ int handshake_nl_accept_doit(struct sk_buff *skb, struct genl_info *info) goto out_status; sock = req->hr_sk->sk_socket; - fd = handshake_dup(sock); + fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) { err = fd; goto out_complete; } + err = req->hr_proto->hp_accept(req, info, fd); if (err) { - fput(sock->file); + put_unused_fd(fd); goto out_complete; } + fd_install(fd, get_file(sock->file)); + trace_handshake_cmd_accept(net, req, req->hr_sk, fd); return 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 5ce275b2d7ef..fb81de10d332 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -597,7 +597,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending += writebias; - sk->sk_wait_pending++; /* Basic assumption: if someone sets sk->sk_err, he _must_ * change state of the socket from TCP_SYN_*. @@ -613,7 +612,6 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) } remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending -= writebias; - sk->sk_wait_pending--; return timeo; } @@ -642,6 +640,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, return -EINVAL; if (uaddr->sa_family == AF_UNSPEC) { + sk->sk_disconnects++; err = sk->sk_prot->disconnect(sk, flags); sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED; goto out; @@ -696,6 +695,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, int writebias = (sk->sk_protocol == IPPROTO_TCP) && tcp_sk(sk)->fastopen_req && tcp_sk(sk)->fastopen_req->data ? 1 : 0; + int dis = sk->sk_disconnects; /* Error code is set above */ if (!timeo || !inet_wait_for_connect(sk, timeo, writebias)) @@ -704,6 +704,11 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, err = sock_intr_errno(timeo); if (signal_pending(current)) goto out; + + if (dis != sk->sk_disconnects) { + err = -EPIPE; + goto out; + } } /* Connection was closed by RST, timeout, ICMP error @@ -725,6 +730,7 @@ out: sock_error: err = sock_error(sk) ? : -ECONNABORTED; sock->state = SS_UNCONNECTED; + sk->sk_disconnects++; if (sk->sk_prot->disconnect(sk, flags)) sock->state = SS_DISCONNECTING; goto out; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 2be2d4922557..4ccfc104f13a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -732,7 +732,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -784,7 +786,7 @@ int esp_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 1ea82bc33ef1..5eb1b8d302bb 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1325,15 +1325,18 @@ __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope) { struct fib_nh *nh; + __be32 saddr; if (nhc->nhc_family != AF_INET) return inet_select_addr(nhc->nhc_dev, 0, scope); nh = container_of(nhc, struct fib_nh, nh_common); - nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid); + saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope); - return nh->nh_saddr; + WRITE_ONCE(nh->nh_saddr, saddr); + WRITE_ONCE(nh->nh_saddr_genid, atomic_read(&net->ipv4.dev_addr_genid)); + + return saddr; } __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) @@ -1347,8 +1350,9 @@ __be32 fib_result_prefsrc(struct net *net, struct fib_result *res) struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); - if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid)) - return nh->nh_saddr; + if (READ_ONCE(nh->nh_saddr_genid) == + atomic_read(&net->ipv4.dev_addr_genid)) + return READ_ONCE(nh->nh_saddr); } return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope); diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index aeebe8816689..394a498c2823 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1145,7 +1145,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, if (newsk) { struct inet_connection_sock *newicsk = inet_csk(newsk); - newsk->sk_wait_pending = 0; inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; newicsk->icsk_bind2_hash = NULL; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c32f5e28758b..598c1b114d2c 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -149,8 +149,14 @@ static bool inet_bind2_bucket_addr_match(const struct inet_bind2_bucket *tb2, const struct sock *sk) { #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb2->family) - return false; + if (sk->sk_family != tb2->family) { + if (sk->sk_family == AF_INET) + return ipv6_addr_v4mapped(&tb2->v6_rcv_saddr) && + tb2->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; + + return ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr) && + sk->sk_v6_rcv_saddr.s6_addr32[3] == tb2->rcv_saddr; + } if (sk->sk_family == AF_INET6) return ipv6_addr_equal(&tb2->v6_rcv_saddr, @@ -819,19 +825,7 @@ static bool inet_bind2_bucket_match(const struct inet_bind2_bucket *tb, tb->l3mdev != l3mdev) return false; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family != tb->family) { - if (sk->sk_family == AF_INET) - return ipv6_addr_v4mapped(&tb->v6_rcv_saddr) && - tb->v6_rcv_saddr.s6_addr32[3] == sk->sk_rcv_saddr; - - return false; - } - - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); -#endif - return tb->rcv_saddr == sk->sk_rcv_saddr; + return inet_bind2_bucket_addr_match(tb, sk); } bool inet_bind2_bucket_match_addr_any(const struct inet_bind2_bucket *tb, const struct net *net, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 89e62ed08dad..b06f678b03a1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -101,6 +101,8 @@ int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb) { struct iphdr *iph = ip_hdr(skb); + IP_INC_STATS(net, IPSTATS_MIB_OUTREQUESTS); + iph_set_totlen(iph, skb->len); ip_send_check(iph); diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 0b74ac49d6a6..9c68b6b74d9f 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -585,9 +585,9 @@ out: return err; } -void ip_sock_set_tos(struct sock *sk, int val) +void __ip_sock_set_tos(struct sock *sk, int val) { - u8 old_tos = READ_ONCE(inet_sk(sk)->tos); + u8 old_tos = inet_sk(sk)->tos; if (sk->sk_type == SOCK_STREAM) { val &= ~INET_ECN_MASK; @@ -599,6 +599,13 @@ void ip_sock_set_tos(struct sock *sk, int val) sk_dst_reset(sk); } } + +void ip_sock_set_tos(struct sock *sk, int val) +{ + lock_sock(sk); + __ip_sock_set_tos(sk, val); + release_sock(sk); +} EXPORT_SYMBOL(ip_sock_set_tos); void ip_sock_set_freebind(struct sock *sk) diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 3abb430af9e6..385d945d8ebe 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -36,12 +36,12 @@ static const struct xt_table packet_mangler = { static unsigned int ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; + unsigned int ret, verdict; const struct iphdr *iph; - u_int8_t tos; __be32 saddr, daddr; - u_int32_t mark; + u32 mark; int err; + u8 tos; /* Save things which could affect route */ mark = skb->mark; @@ -51,8 +51,9 @@ ipt_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *stat tos = iph->tos; ret = ipt_do_table(priv, skb, state); + verdict = ret & NF_VERDICT_MASK; /* Reroute for ANY change. */ - if (ret != NF_DROP && ret != NF_STOLEN) { + if (verdict != NF_DROP && verdict != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index eaf1d3113b62..a85b0aba3646 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -83,7 +83,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("InUnknownProtos", IPSTATS_MIB_INUNKNOWNPROTOS), SNMP_MIB_ITEM("InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("InDelivers", IPSTATS_MIB_INDELIVERS), - SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -93,6 +93,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = { SNMP_MIB_ITEM("FragOKs", IPSTATS_MIB_FRAGOKS), SNMP_MIB_ITEM("FragFails", IPSTATS_MIB_FRAGFAILS), SNMP_MIB_ITEM("FragCreates", IPSTATS_MIB_FRAGCREATES), + SNMP_MIB_ITEM("OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index dc478a0574cb..c64334363230 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -41,7 +41,6 @@ static siphash_aligned_key_t syncookie_secret[2]; * requested/supported by the syn/synack exchange. */ #define TSBITS 6 -#define TSMASK (((__u32)1 << TSBITS) - 1) static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, u32 count, int c) @@ -52,6 +51,14 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, count, &syncookie_secret[c]); } +/* Convert one nsec 64bit timestamp to ts (ms or usec resolution) */ +static u64 tcp_ns_to_ts(bool usec_ts, u64 val) +{ + if (usec_ts) + return div_u64(val, NSEC_PER_USEC); + + return div_u64(val, NSEC_PER_MSEC); +} /* * when syncookies are in effect and tcp timestamps are enabled we encode @@ -62,27 +69,24 @@ static u32 cookie_hash(__be32 saddr, __be32 daddr, __be16 sport, __be16 dport, */ u64 cookie_init_timestamp(struct request_sock *req, u64 now) { - struct inet_request_sock *ireq; - u32 ts, ts_now = tcp_ns_to_ts(now); + const struct inet_request_sock *ireq = inet_rsk(req); + u64 ts, ts_now = tcp_ns_to_ts(false, now); u32 options = 0; - ireq = inet_rsk(req); - options = ireq->wscale_ok ? ireq->snd_wscale : TS_OPT_WSCALE_MASK; if (ireq->sack_ok) options |= TS_OPT_SACK; if (ireq->ecn_ok) options |= TS_OPT_ECN; - ts = ts_now & ~TSMASK; + ts = (ts_now >> TSBITS) << TSBITS; ts |= options; - if (ts > ts_now) { - ts >>= TSBITS; - ts--; - ts <<= TSBITS; - ts |= options; - } - return (u64)ts * (NSEC_PER_SEC / TCP_TS_HZ); + if (ts > ts_now) + ts -= (1UL << TSBITS); + + if (tcp_rsk(req)->req_usec_ts) + return ts * NSEC_PER_USEC; + return ts * NSEC_PER_MSEC; } @@ -302,6 +306,8 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, treq->af_specific = af_ops; treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; + treq->req_usec_ts = -1; + #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); if (treq->is_mptcp) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index faabb5a4a378..156264531124 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -831,7 +831,9 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos, */ if (!skb_queue_empty(&sk->sk_receive_queue)) break; - sk_wait_data(sk, &timeo, NULL); + ret = sk_wait_data(sk, &timeo, NULL); + if (ret < 0) + break; if (signal_pending(current)) { ret = sock_intr_errno(timeo); break; @@ -925,10 +927,11 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -/* In some cases, both sendmsg() could have added an skb to the write queue, - * but failed adding payload on it. We need to remove it to consume less +/* In some cases, sendmsg() could have added an skb to the write queue, + * but failed adding payload on it. We need to remove it to consume less * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger - * epoll() users. + * epoll() users. Another reason is that tcp_write_xmit() does not like + * finding an empty skb in the write queue. */ void tcp_remove_empty_skb(struct sock *sk) { @@ -1287,6 +1290,7 @@ new_segment: wait_for_space: set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); + tcp_remove_empty_skb(sk); if (copied) tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH, size_goal); @@ -2442,7 +2446,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len, __sk_flush_backlog(sk); } else { tcp_cleanup_rbuf(sk, copied); - sk_wait_data(sk, &timeo, last); + err = sk_wait_data(sk, &timeo, last); + if (err < 0) { + err = copied ? : err; + goto out; + } } if ((flags & MSG_PEEK) && @@ -2966,12 +2974,6 @@ int tcp_disconnect(struct sock *sk, int flags) int old_state = sk->sk_state; u32 seq; - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -3629,10 +3631,16 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, tp->fastopen_no_cookie = val; break; case TCP_TIMESTAMP: - if (!tp->repair) + if (!tp->repair) { err = -EPERM; - else - WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); + break; + } + /* val is an opaque field, + * and low order bit contains usec_ts enable bit. + * Its a best effort, and we do not care if user makes an error. + */ + tp->tcp_usec_ts = val & 1; + WRITE_ONCE(tp->tsoffset, val - tcp_clock_ts(tp->tcp_usec_ts)); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); @@ -3754,6 +3762,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_options |= TCPI_OPT_ECN_SEEN; if (tp->syn_data_acked) info->tcpi_options |= TCPI_OPT_SYN_DATA; + if (tp->tcp_usec_ts) + info->tcpi_options |= TCPI_OPT_USEC_TS; info->tcpi_rto = jiffies_to_usecs(icsk->icsk_rto); info->tcpi_ato = jiffies_to_usecs(min_t(u32, icsk->icsk_ack.ato, @@ -3817,10 +3827,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_total_rto = tp->total_rto; info->tcpi_total_rto_recoveries = tp->total_rto_recoveries; info->tcpi_total_rto_time = tp->total_rto_time; - if (tp->rto_stamp) { - info->tcpi_total_rto_time += tcp_time_stamp_raw() - - tp->rto_stamp; - } + if (tp->rto_stamp) + info->tcpi_total_rto_time += tcp_clock_ms() - tp->rto_stamp; unlock_sock_fast(sk, slow); } @@ -4145,7 +4153,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); + val = tcp_clock_ts(tp->tcp_usec_ts) + READ_ONCE(tp->tsoffset); + if (tp->tcp_usec_ts) + val |= 1; + else + val &= ~1; break; case TCP_NOTSENT_LOWAT: val = READ_ONCE(tp->notsent_lowat); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 327268203001..53b0d62fd2c2 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -307,6 +307,10 @@ msg_bytes_ready: } data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + copied = data; + goto unlock; + } if (data && !sk_psock_queue_empty(psock)) goto msg_bytes_ready; copied = -EAGAIN; @@ -317,6 +321,8 @@ out: tcp_rcv_space_adjust(sk); if (copied > 0) __tcp_cleanup_rbuf(sk, copied); + +unlock: release_sock(sk); sk_psock_put(sk, psock); return copied; @@ -351,6 +357,10 @@ msg_bytes_ready: timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); data = tcp_msg_wait_data(sk, psock, timeo); + if (data < 0) { + ret = data; + goto unlock; + } if (data) { if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; @@ -361,6 +371,8 @@ msg_bytes_ready: copied = -EAGAIN; } ret = copied; + +unlock: release_sock(sk); sk_psock_put(sk, psock); return ret; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ab87f0285b72..00d04ab68958 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -693,6 +693,23 @@ new_measure: tp->rcv_rtt_est.time = tp->tcp_mstamp; } +static s32 tcp_rtt_tsopt_us(const struct tcp_sock *tp) +{ + u32 delta, delta_us; + + delta = tcp_time_stamp_ts(tp) - tp->rx_opt.rcv_tsecr; + if (tp->tcp_usec_ts) + return delta; + + if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; + delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); + return delta_us; + } + return -1; +} + static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb) { @@ -704,15 +721,10 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, if (TCP_SKB_CB(skb)->end_seq - TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) { - u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - u32 delta_us; - - if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { - if (!delta) - delta = 1; - delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - tcp_rcv_rtt_update(tp, delta_us, 0); - } + s32 delta = tcp_rtt_tsopt_us(tp); + + if (delta >= 0) + tcp_rcv_rtt_update(tp, delta, 0); } } @@ -2222,16 +2234,17 @@ void tcp_enter_loss(struct sock *sk) * restore sanity to the SACK scoreboard. If the apparent reneging * persists until this RTO then we'll clear the SACK scoreboard. */ -static bool tcp_check_sack_reneging(struct sock *sk, int flag) +static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag) { - if (flag & FLAG_SACK_RENEGING && - flag & FLAG_SND_UNA_ADVANCED) { + if (*ack_flag & FLAG_SACK_RENEGING && + *ack_flag & FLAG_SND_UNA_ADVANCED) { struct tcp_sock *tp = tcp_sk(sk); unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4), msecs_to_jiffies(10)); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, TCP_RTO_MAX); + *ack_flag &= ~FLAG_SET_XMIT_TIMER; return true; } return false; @@ -2442,7 +2455,7 @@ static bool tcp_skb_spurious_retrans(const struct tcp_sock *tp, const struct sk_buff *skb) { return (TCP_SKB_CB(skb)->sacked & TCPCB_RETRANS) && - tcp_tsopt_ecr_before(tp, tcp_skb_timestamp(skb)); + tcp_tsopt_ecr_before(tp, tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); } /* Nothing was retransmitted or returned timestamp is less @@ -2856,7 +2869,7 @@ void tcp_enter_recovery(struct sock *sk, bool ece_ack) static void tcp_update_rto_time(struct tcp_sock *tp) { if (tp->rto_stamp) { - tp->total_rto_time += tcp_time_stamp(tp) - tp->rto_stamp; + tp->total_rto_time += tcp_time_stamp_ms(tp) - tp->rto_stamp; tp->rto_stamp = 0; } } @@ -3009,7 +3022,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, tp->prior_ssthresh = 0; /* B. In all the states check for reneging SACKs. */ - if (tcp_check_sack_reneging(sk, flag)) + if (tcp_check_sack_reneging(sk, ack_flag)) return; /* C. Check consistency of the current state. */ @@ -3146,17 +3159,10 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, * left edge of the send window. * See draft-ietf-tcplw-high-performance-00, section 3.3. */ - if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && - flag & FLAG_ACKED) { - u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; - - if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { - if (!delta) - delta = 1; - seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); - ca_rtt_us = seq_rtt_us; - } - } + if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && + tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) + seq_rtt_us = ca_rtt_us = tcp_rtt_tsopt_us(tp); + rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */ if (seq_rtt_us < 0) return false; @@ -6293,7 +6299,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && !between(tp->rx_opt.rcv_tsecr, tp->retrans_stamp, - tcp_time_stamp(tp))) { + tcp_time_stamp_ts(tp))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSACTIVEREJECTED); goto reset_and_undo; @@ -7042,6 +7048,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, req->syncookie = want_cookie; tcp_rsk(req)->af_specific = af_ops; tcp_rsk(req)->ts_off = 0; + tcp_rsk(req)->req_usec_ts = -1; #if IS_ENABLED(CONFIG_MPTCP) tcp_rsk(req)->is_mptcp = 0; #endif diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 2519f530b114..7583d4e34c8c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -296,6 +296,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) rt = NULL; goto failure; } + tp->tcp_usec_ts = dst_tcp_usec_ts(&rt->dst); /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); @@ -954,7 +955,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp_raw() + tcptw->tw_ts_offset, + tcp_tw_tsval(tcptw), tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), @@ -988,7 +989,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, + tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), @@ -1870,6 +1871,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb, #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif + !mptcp_skb_can_collapse(tail, skb) || thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index ae36780977d2..52fe17167460 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -272,7 +272,7 @@ static void tcp_lp_pkts_acked(struct sock *sk, const struct ack_sample *sample) { struct tcp_sock *tp = tcp_sk(sk); struct lp *lp = inet_csk_ca(sk); - u32 now = tcp_time_stamp(tp); + u32 now = tcp_time_stamp_ts(tp); u32 delta; if (sample->rtt_us > 0) diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 3f87611077ef..ace806c5bd0c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -300,6 +300,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_ts_recent = tp->rx_opt.ts_recent; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; tcptw->tw_ts_offset = tp->tsoffset; + tw->tw_usec_ts = tp->tcp_usec_ts; tcptw->tw_last_oow_ack_time = 0; tcptw->tw_tx_delay = tp->tcp_tx_delay; tw->tw_txhash = sk->sk_txhash; @@ -554,21 +555,29 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { + newtp->tcp_usec_ts = treq->req_usec_ts; newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { + newtp->tcp_usec_ts = 0; newtp->rx_opt.ts_recent_stamp = 0; newtp->tcp_header_len = sizeof(struct tcphdr); } if (req->num_timeout) { - newtp->undo_marker = treq->snt_isn; - newtp->retrans_stamp = div_u64(treq->snt_synack, - USEC_PER_SEC / TCP_TS_HZ); newtp->total_rto = req->num_timeout; - newtp->total_rto_recoveries = 1; - newtp->total_rto_time = tcp_time_stamp_raw() - + newtp->undo_marker = treq->snt_isn; + if (newtp->tcp_usec_ts) { + newtp->retrans_stamp = treq->snt_synack; + newtp->total_rto_time = (u32)(tcp_clock_us() - + newtp->retrans_stamp) / USEC_PER_MSEC; + } else { + newtp->retrans_stamp = div_u64(treq->snt_synack, + USEC_PER_SEC / TCP_TS_HZ); + newtp->total_rto_time = tcp_clock_ms() - newtp->retrans_stamp; + } + newtp->total_rto_recoveries = 1; } newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e6ebf35ed58..ca4d7594efd4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -799,7 +799,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; + opts->tsval = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -884,7 +884,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, } if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; + opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) + + tcp_rsk(req)->ts_off; opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } @@ -943,7 +944,8 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb if (likely(tp->rx_opt.tstamp_ok)) { opts->options |= OPTION_TS; - opts->tsval = skb ? tcp_skb_timestamp(skb) + tp->tsoffset : 0; + opts->tsval = skb ? tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb) + + tp->tsoffset : 0; opts->tsecr = tp->rx_opt.ts_recent; size += TCPOLEN_TSTAMP_ALIGNED; } @@ -1696,14 +1698,6 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) */ mss_now = pmtu - icsk->icsk_af_ops->net_header_len - sizeof(struct tcphdr); - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mss_now -= icsk->icsk_af_ops->net_frag_header_len; - } - /* Clamp it (mss_clamp does not include tcp options) */ if (mss_now > tp->rx_opt.mss_clamp) mss_now = tp->rx_opt.mss_clamp; @@ -1731,21 +1725,11 @@ int tcp_mss_to_mtu(struct sock *sk, int mss) { const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - int mtu; - mtu = mss + + return mss + tp->tcp_header_len + icsk->icsk_ext_hdr_len + icsk->icsk_af_ops->net_header_len; - - /* IPv6 adds a frag_hdr in case RTAX_FEATURE_ALLFRAG is set */ - if (icsk->icsk_af_ops->net_frag_header_len) { - const struct dst_entry *dst = __sk_dst_get(sk); - - if (dst && dst_allfrag(dst)) - mtu += icsk->icsk_af_ops->net_frag_header_len; - } - return mtu; } EXPORT_SYMBOL(tcp_mss_to_mtu); @@ -2535,6 +2519,18 @@ static bool tcp_pacing_check(struct sock *sk) return true; } +static bool tcp_rtx_queue_empty_or_single_skb(const struct sock *sk) +{ + const struct rb_node *node = sk->tcp_rtx_queue.rb_node; + + /* No skb in the rtx queue. */ + if (!node) + return true; + + /* Only one skb in rtx queue. */ + return !node->rb_left && !node->rb_right; +} + /* TCP Small Queues : * Control number of packets in qdisc/devices to two packets / or ~1 ms. * (These limits are doubled for retransmits) @@ -2573,12 +2569,12 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit += extra_bytes; } if (refcount_read(&sk->sk_wmem_alloc) > limit) { - /* Always send skb if rtx queue is empty. + /* Always send skb if rtx queue is empty or has one skb. * No need to wait for TX completion to call us back, * after softirq/tasklet schedule. * This helps when TX completions are delayed too much. */ - if (tcp_rtx_queue_empty(sk)) + if (tcp_rtx_queue_empty_or_single_skb(sk)) return false; set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); @@ -2782,7 +2778,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - u32 timeout, rto_delta_us; + u32 timeout, timeout_us, rto_delta_us; int early_retrans; /* Don't do any loss probe on a Fast Open connection before 3WHS @@ -2806,11 +2802,12 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) * sample is available then probe after TCP_TIMEOUT_INIT. */ if (tp->srtt_us) { - timeout = usecs_to_jiffies(tp->srtt_us >> 2); + timeout_us = tp->srtt_us >> 2; if (tp->packets_out == 1) - timeout += TCP_RTO_MIN; + timeout_us += tcp_rto_min_us(sk); else - timeout += TCP_TIMEOUT_MIN; + timeout_us += TCP_TIMEOUT_MIN_US; + timeout = usecs_to_jiffies(timeout_us); } else { timeout = TCP_TIMEOUT_INIT; } @@ -3366,7 +3363,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) /* Save stamp of the first (attempted) retransmit. */ if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); + tp->retrans_stamp = tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb); if (tp->undo_retrans < 0) tp->undo_retrans = 0; @@ -3652,6 +3649,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, mss = tcp_mss_clamp(tp, dst_metric_advmss(dst)); memset(&opts, 0, sizeof(opts)); + if (tcp_rsk(req)->req_usec_ts < 0) + tcp_rsk(req)->req_usec_ts = dst_tcp_usec_ts(dst); now = tcp_clock_ns(); #ifdef CONFIG_SYN_COOKIES if (unlikely(synack_type == TCP_SYNACK_COOKIE && ireq->tstamp_ok)) @@ -3948,7 +3947,7 @@ int tcp_connect(struct sock *sk) tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN); tcp_mstamp_refresh(tp); - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); tcp_connect_queue_skb(sk, buff); tcp_ecn_send_syn(sk, buff); tcp_rbtree_insert(&sk->tcp_rtx_queue, buff); diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index acf4869c5d3b..bba10110fbbc 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -104,7 +104,7 @@ bool tcp_rack_mark_lost(struct sock *sk) tp->rack.advanced = 0; tcp_rack_detect_loss(sk, &timeout); if (timeout) { - timeout = usecs_to_jiffies(timeout) + TCP_TIMEOUT_MIN; + timeout = usecs_to_jiffies(timeout + TCP_TIMEOUT_MIN_US); inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT, timeout, inet_csk(sk)->icsk_rto); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 0862b73dd3b5..1f9f6c1c196b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -26,14 +26,18 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - u32 elapsed, start_ts, user_timeout; + const struct tcp_sock *tp = tcp_sk(sk); + u32 elapsed, user_timeout; s32 remaining; - start_ts = tcp_sk(sk)->retrans_stamp; user_timeout = READ_ONCE(icsk->icsk_user_timeout); if (!user_timeout) return icsk->icsk_rto; - elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; + + elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp; + if (tp->tcp_usec_ts) + elapsed /= USEC_PER_MSEC; + remaining = user_timeout - elapsed; if (remaining <= 0) return 1; /* user timeout has passed; fire ASAP */ @@ -212,12 +216,13 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - unsigned int start_ts; + struct tcp_sock *tp = tcp_sk(sk); + unsigned int start_ts, delta; if (!inet_csk(sk)->icsk_retransmits) return false; - start_ts = tcp_sk(sk)->retrans_stamp; + start_ts = tp->retrans_stamp; if (likely(timeout == 0)) { unsigned int rto_base = TCP_RTO_MIN; @@ -226,7 +231,12 @@ static bool retransmits_timed_out(struct sock *sk, timeout = tcp_model_timeout(sk, boundary, rto_base); } - return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; + if (tp->tcp_usec_ts) { + /* delta maybe off up to a jiffy due to timer granularity. */ + delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1); + return (s32)(delta - timeout * USEC_PER_MSEC) >= 0; + } + return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ @@ -422,7 +432,7 @@ static void tcp_update_rto_stats(struct sock *sk) if (!icsk->icsk_retransmits) { tp->total_rto_recoveries++; - tp->rto_stamp = tcp_time_stamp(tp); + tp->rto_stamp = tcp_time_stamp_ms(tp); } icsk->icsk_retransmits++; tp->total_rto++; @@ -462,26 +472,24 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_time_stamp(tp); + tp->retrans_stamp = tcp_time_stamp_ts(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, req->timeout << req->num_timeout, TCP_RTO_MAX); } static bool tcp_rtx_probe0_timed_out(const struct sock *sk, - const struct sk_buff *skb) + const struct sk_buff *skb, + u32 rtx_delta) { const struct tcp_sock *tp = tcp_sk(sk); const int timeout = TCP_RTO_MAX * 2; - u32 rcv_delta, rtx_delta; + u32 rcv_delta; rcv_delta = inet_csk(sk)->icsk_timeout - tp->rcv_tstamp; if (rcv_delta <= timeout) return false; - rtx_delta = (u32)msecs_to_jiffies(tcp_time_stamp(tp) - - (tp->retrans_stamp ?: tcp_skb_timestamp(skb))); - - return rtx_delta > timeout; + return msecs_to_jiffies(rtx_delta) > timeout; } /** @@ -534,7 +542,11 @@ void tcp_retransmit_timer(struct sock *sk) struct inet_sock *inet = inet_sk(sk); u32 rtx_delta; - rtx_delta = tcp_time_stamp(tp) - (tp->retrans_stamp ?: tcp_skb_timestamp(skb)); + rtx_delta = tcp_time_stamp_ts(tp) - (tp->retrans_stamp ?: + tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); + if (tp->tcp_usec_ts) + rtx_delta /= USEC_PER_MSEC; + if (sk->sk_family == AF_INET) { net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", &inet->inet_daddr, ntohs(inet->inet_dport), @@ -551,7 +563,7 @@ void tcp_retransmit_timer(struct sock *sk) rtx_delta); } #endif - if (tcp_rtx_probe0_timed_out(sk, skb)) { + if (tcp_rtx_probe0_timed_out(sk, skb, rtx_delta)) { tcp_write_err(sk); goto out; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c2d471ad7922..3aaea56b5166 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1399,6 +1399,7 @@ retry: idev->cnf.temp_valid_lft + age); cfg.preferred_lft = cnf_temp_preferred_lft + age - idev->desync_factor; cfg.preferred_lft = min_t(__u32, ifp->prefered_lft, cfg.preferred_lft); + cfg.preferred_lft = min_t(__u32, cfg.valid_lft, cfg.preferred_lft); cfg.plen = ifp->prefix_len; tmp_tstamp = ifp->tstamp; @@ -1406,15 +1407,23 @@ retry: write_unlock_bh(&idev->lock); - /* A temporary address is created only if this calculated Preferred - * Lifetime is greater than REGEN_ADVANCE time units. In particular, - * an implementation must not create a temporary address with a zero - * Preferred Lifetime. + /* From RFC 4941: + * + * A temporary address is created only if this calculated Preferred + * Lifetime is greater than REGEN_ADVANCE time units. In + * particular, an implementation must not create a temporary address + * with a zero Preferred Lifetime. + * + * Clamp the preferred lifetime to a minimum of regen_advance, unless + * that would exceed valid_lft. + * * Use age calculation as in addrconf_verify to avoid unnecessary * temporary addresses being generated. */ age = (now - tmp_tstamp + ADDRCONF_TIMER_FUZZ_MINUS) / HZ; - if (cfg.preferred_lft <= regen_advance + age) { + if (cfg.preferred_lft <= regen_advance + age) + cfg.preferred_lft = regen_advance + age + 1; + if (cfg.preferred_lft > cfg.valid_lft) { in6_ifa_put(ifp); in6_dev_put(idev); ret = -1; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index fddd0cbdede1..2cc1a45742d8 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -770,7 +770,9 @@ static inline int esp_remove_trailer(struct sk_buff *skb) skb->csum = csum_block_sub(skb->csum, csumdiff, skb->len - trimlen); } - pskb_trim(skb, skb->len - trimlen); + ret = pskb_trim(skb, skb->len - trimlen); + if (unlikely(ret)) + return ret; ret = nexthdr[1]; @@ -831,7 +833,7 @@ int esp6_input_done2(struct sk_buff *skb, int err) /* * 1) if the NAT-T peer's IP or port changed then - * advertize the change to the keying daemon. + * advertise the change to the keying daemon. * This is an inbound SA, so just compare * SRC ports. */ diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index f6f5b83dd954..7563f8c6aa87 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -46,7 +46,7 @@ struct ioam6_lwt { struct ioam6_lwt_encap tuninfo; }; -static struct netlink_range_validation freq_range = { +static const struct netlink_range_validation freq_range = { .min = IOAM6_IPTUNNEL_FREQ_MIN, .max = IOAM6_IPTUNNEL_FREQ_MAX, }; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a471c7e91761..a722a43dd668 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -117,6 +117,8 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff * return res; } + IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, daddr); neigh = __ipv6_neigh_lookup_noref(dev, nexthop); @@ -162,7 +164,13 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, int err; skb_mark_not_on_list(segs); - err = ip6_fragment(net, sk, segs, ip6_finish_output2); + /* Last GSO segment can be smaller than gso_size (and MTU). + * Adding a fragment header would produce an "atomic fragment", + * which is considered harmful (RFC-8021). Avoid that. + */ + err = segs->len > mtu ? + ip6_fragment(net, sk, segs, ip6_finish_output2) : + ip6_finish_output2(net, sk, segs); if (err && ret == 0) ret = err; } @@ -170,6 +178,16 @@ ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk, return ret; } +static int ip6_finish_output_gso(struct net *net, struct sock *sk, + struct sk_buff *skb, unsigned int mtu) +{ + if (!(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && + !skb_gso_validate_network_len(skb, mtu)) + return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); + + return ip6_finish_output2(net, sk, skb); +} + static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned int mtu; @@ -183,17 +201,14 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff #endif mtu = ip6_skb_dst_mtu(skb); - if (skb_is_gso(skb) && - !(IP6CB(skb)->flags & IP6SKB_FAKEJUMBO) && - !skb_gso_validate_network_len(skb, mtu)) - return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu); + if (skb_is_gso(skb)) + return ip6_finish_output_gso(net, sk, skb, mtu); - if ((skb->len > mtu && !skb_is_gso(skb)) || - dst_allfrag(skb_dst(skb)) || + if (skb->len > mtu || (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size)) return ip6_fragment(net, sk, skb, ip6_finish_output2); - else - return ip6_finish_output2(net, sk, skb); + + return ip6_finish_output2(net, sk, skb); } static int ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -328,7 +343,7 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, mtu = dst_mtu(dst); if ((skb->len <= mtu) || skb->ignore_df || skb_is_gso(skb)) { - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing @@ -1015,9 +1030,6 @@ slow_path: return err; fail_toobig: - if (skb->sk && dst_allfrag(skb_dst(skb))) - sk_gso_disable(skb->sk); - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); err = -EMSGSIZE; @@ -1281,74 +1293,6 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, } EXPORT_SYMBOL_GPL(ip6_sk_dst_lookup_flow); -/** - * ip6_dst_lookup_tunnel - perform route lookup on tunnel - * @skb: Packet for which lookup is done - * @dev: Tunnel device - * @net: Network namespace of tunnel device - * @sock: Socket which provides route info - * @saddr: Memory to store the src ip address - * @info: Tunnel information - * @protocol: IP protocol - * @use_cache: Flag to enable cache usage - * This function performs a route lookup on a tunnel - * - * It returns a valid dst pointer and stores src address to be used in - * tunnel in param saddr on success, else a pointer encoded error code. - */ - -struct dst_entry *ip6_dst_lookup_tunnel(struct sk_buff *skb, - struct net_device *dev, - struct net *net, - struct socket *sock, - struct in6_addr *saddr, - const struct ip_tunnel_info *info, - u8 protocol, - bool use_cache) -{ - struct dst_entry *dst = NULL; -#ifdef CONFIG_DST_CACHE - struct dst_cache *dst_cache; -#endif - struct flowi6 fl6; - __u8 prio; - -#ifdef CONFIG_DST_CACHE - dst_cache = (struct dst_cache *)&info->dst_cache; - if (use_cache) { - dst = dst_cache_get_ip6(dst_cache, saddr); - if (dst) - return dst; - } -#endif - memset(&fl6, 0, sizeof(fl6)); - fl6.flowi6_mark = skb->mark; - fl6.flowi6_proto = protocol; - fl6.daddr = info->key.u.ipv6.dst; - fl6.saddr = info->key.u.ipv6.src; - prio = info->key.tos; - fl6.flowlabel = ip6_make_flowinfo(prio, info->key.label); - - dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, - NULL); - if (IS_ERR(dst)) { - netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); - return ERR_PTR(-ENETUNREACH); - } - if (dst->dev == dev) { /* is this necessary? */ - netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); - dst_release(dst); - return ERR_PTR(-ELOOP); - } -#ifdef CONFIG_DST_CACHE - if (use_cache) - dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); -#endif - *saddr = fl6.saddr; - return dst; -} -EXPORT_SYMBOL_GPL(ip6_dst_lookup_tunnel); - static inline struct ipv6_opt_hdr *ip6_opt_dup(struct ipv6_opt_hdr *src, gfp_t gfp) { @@ -1450,10 +1394,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, cork->base.mark = ipc6->sockc.mark; sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags); - if (dst_allfrag(xfrm_dst_path(&rt->dst))) - cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; - cork->base.transmit_time = ipc6->sockc.transmit_time; return 0; @@ -1510,8 +1451,6 @@ static int __ip6_append_data(struct sock *sk, headersize = sizeof(struct ipv6hdr) + (opt ? opt->opt_flen + opt->opt_nflen : 0) + - (dst_allfrag(&rt->dst) ? - sizeof(struct frag_hdr) : 0) + rt->rt6i_nfheader_len; if (mtu <= fragheaderlen || @@ -1621,7 +1560,7 @@ emsgsize: while (length > 0) { /* Check if the remaining data fits into current packet. */ - copy = (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - skb->len; + copy = (cork->length <= mtu ? mtu : maxfraglen) - skb->len; if (copy < length) copy = maxfraglen - skb->len; @@ -1652,7 +1591,7 @@ alloc_new_skb: */ datalen = length + fraggap; - if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) + if (datalen > (cork->length <= mtu ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; fraglen = datalen + fragheaderlen; pagedlen = 0; @@ -1901,7 +1840,6 @@ static void ip6_cork_steal_dst(struct sk_buff *skb, struct inet_cork_full *cork) struct dst_entry *dst = cork->base.dst; cork->base.dst = NULL; - cork->base.flags &= ~IPCORK_ALLFRAG; skb_dst_set(skb, dst); } @@ -1922,7 +1860,6 @@ static void ip6_cork_release(struct inet_cork_full *cork, if (cork->base.dst) { dst_release(cork->base.dst); cork->base.dst = NULL; - cork->base.flags &= ~IPCORK_ALLFRAG; } } @@ -1987,7 +1924,7 @@ struct sk_buff *__ip6_make_skb(struct sock *sk, skb->tstamp = cork->base.transmit_time; ip6_cork_steal_dst(skb, cork); - IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); if (proto == IPPROTO_ICMPV6) { struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb)); u8 icmp6_type; diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 70d38705c92f..a7bf0327b380 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -1,3 +1,4 @@ + // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> @@ -112,4 +113,73 @@ int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); +/** + * udp_tunnel6_dst_lookup - perform route lookup on UDP tunnel + * @skb: Packet for which lookup is done + * @dev: Tunnel device + * @net: Network namespace of tunnel device + * @sock: Socket which provides route info + * @oif: Index of the output interface + * @saddr: Memory to store the src ip address + * @key: Tunnel information + * @sport: UDP source port + * @dport: UDP destination port + * @dsfield: The traffic class field + * @dst_cache: The dst cache to use for lookup + * This function performs a route lookup on a UDP tunnel + * + * It returns a valid dst pointer and stores src address to be used in + * tunnel in param saddr on success, else a pointer encoded error code. + */ + +struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, + struct net_device *dev, + struct net *net, + struct socket *sock, + int oif, + struct in6_addr *saddr, + const struct ip_tunnel_key *key, + __be16 sport, __be16 dport, u8 dsfield, + struct dst_cache *dst_cache) +{ + struct dst_entry *dst = NULL; + struct flowi6 fl6; + +#ifdef CONFIG_DST_CACHE + if (dst_cache) { + dst = dst_cache_get_ip6(dst_cache, saddr); + if (dst) + return dst; + } +#endif + memset(&fl6, 0, sizeof(fl6)); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = IPPROTO_UDP; + fl6.flowi6_oif = oif; + fl6.daddr = key->u.ipv6.dst; + fl6.saddr = key->u.ipv6.src; + fl6.fl6_sport = sport; + fl6.fl6_dport = dport; + fl6.flowlabel = ip6_make_flowinfo(dsfield, key->label); + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, sock->sk, &fl6, + NULL); + if (IS_ERR(dst)) { + netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } +#ifdef CONFIG_DST_CACHE + if (dst_cache) + dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); +#endif + *saddr = fl6.saddr; + return dst; +} +EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); + MODULE_LICENSE("GPL"); diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 99e28b444a4c..b75d3c9d41bb 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1789,7 +1789,7 @@ static void mld_sendpack(struct sk_buff *skb) rcu_read_lock(); idev = __in6_dev_get(skb->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); payload_len = (skb_tail_pointer(skb) - skb_network_header(skb)) - sizeof(*pip6); @@ -2147,8 +2147,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) full_len = sizeof(struct ipv6hdr) + payload_len; rcu_read_lock(); - IP6_UPD_PO_STATS(net, __in6_dev_get(dev), - IPSTATS_MIB_OUT, full_len); + IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_OUTREQUESTS); rcu_read_unlock(); skb = sock_alloc_send_skb(sk, hlen + tlen + full_len, 1, &err); diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 679443d7ecb5..a19999b30bc0 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -504,7 +504,7 @@ void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr, rcu_read_lock(); idev = __in6_dev_get(dst->dev); - IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, dst->dev, diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index a88b2ce4a3cb..8dd4cd0c47bd 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -31,10 +31,10 @@ static const struct xt_table packet_mangler = { static unsigned int ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; struct in6_addr saddr, daddr; - u_int8_t hop_limit; - u_int32_t flowlabel, mark; + unsigned int ret, verdict; + u32 flowlabel, mark; + u8 hop_limit; int err; /* save source/dest address, mark, hoplimit, flowlabel, priority, */ @@ -47,8 +47,9 @@ ip6t_mangle_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *sta flowlabel = *((u_int32_t *)ipv6_hdr(skb)); ret = ip6t_do_table(priv, skb, state); + verdict = ret & NF_VERDICT_MASK; - if (ret != NF_DROP && ret != NF_STOLEN && + if (verdict != NF_DROP && verdict != NF_STOLEN && (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) || !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) || skb->mark != mark || diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c index e20b3705c2d2..6d1d9221649d 100644 --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -61,7 +61,7 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InDiscards", IPSTATS_MIB_INDISCARDS), SNMP_MIB_ITEM("Ip6InDelivers", IPSTATS_MIB_INDELIVERS), SNMP_MIB_ITEM("Ip6OutForwDatagrams", IPSTATS_MIB_OUTFORWDATAGRAMS), - SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTPKTS), + SNMP_MIB_ITEM("Ip6OutRequests", IPSTATS_MIB_OUTREQUESTS), SNMP_MIB_ITEM("Ip6OutDiscards", IPSTATS_MIB_OUTDISCARDS), SNMP_MIB_ITEM("Ip6OutNoRoutes", IPSTATS_MIB_OUTNOROUTES), SNMP_MIB_ITEM("Ip6ReasmTimeout", IPSTATS_MIB_REASMTIMEOUT), @@ -84,6 +84,7 @@ static const struct snmp_mib snmp6_ipstats_list[] = { SNMP_MIB_ITEM("Ip6InECT1Pkts", IPSTATS_MIB_ECT1PKTS), SNMP_MIB_ITEM("Ip6InECT0Pkts", IPSTATS_MIB_ECT0PKTS), SNMP_MIB_ITEM("Ip6InCEPkts", IPSTATS_MIB_CEPKTS), + SNMP_MIB_ITEM("Ip6OutTransmits", IPSTATS_MIB_OUTPKTS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index a2aa54a2baae..dd0a4e73e602 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -651,7 +651,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, * have been queued for deletion. */ rcu_read_lock(); - IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); + IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d410703bb5a1..dc27988512a6 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -286,6 +286,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, goto failure; } + tp->tcp_usec_ts = dst_tcp_usec_ts(dst); tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (!saddr) { @@ -1096,7 +1097,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, - tcp_time_stamp_raw() + tcptw->tw_ts_offset, + tcp_tw_tsval(tcptw), tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority, tw->tw_txhash); @@ -1123,7 +1124,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, - tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, + tcp_rsk_tsval(tcp_rsk(req)), READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, @@ -1894,7 +1895,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = { .conn_request = tcp_v6_conn_request, .syn_recv_sock = tcp_v6_syn_recv_sock, .net_header_len = sizeof(struct ipv6hdr), - .net_frag_header_len = sizeof(struct frag_hdr), .setsockopt = ipv6_setsockopt, .getsockopt = ipv6_getsockopt, .addr2sockaddr = inet6_csk_addr2sockaddr, diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index ad07904642ca..5f7b1fdbffe6 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -95,7 +95,7 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb) return -EMSGSIZE; } - if (toobig || dst_allfrag(skb_dst(skb))) + if (toobig) return ip6_fragment(net, sk, skb, __xfrm6_output_finish); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 41a680c76d2e..42fb6996b077 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -117,10 +117,10 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; - if (likely(xdst->u.rt6.rt6i_idev)) - in6_dev_put(xdst->u.rt6.rt6i_idev); dst_destroy_metrics_generic(dst); rt6_uncached_list_del(&xdst->u.rt6); + if (likely(xdst->u.rt6.rt6i_idev)) + in6_dev_put(xdst->u.rt6.rt6i_idev); xfrm_dst_destroy(xdst); } diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 6f679d2c0409..64352e4e6d00 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2469,8 +2469,7 @@ ieee80211_drop_unencrypted_mgmt(struct ieee80211_rx_data *rx) /* drop unicast public action frames when using MPF */ if (is_unicast_ether_addr(mgmt->da) && - ieee80211_is_public_action((void *)rx->skb->data, - rx->skb->len)) + ieee80211_is_protected_dual_of_public_action(rx->skb)) return RX_DROP_U_UNPROT_UNICAST_PUB_ACTION; } diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile index 84e531f86b82..bcf1dbf3a432 100644 --- a/net/mptcp/Makefile +++ b/net/mptcp/Makefile @@ -2,7 +2,8 @@ obj-$(CONFIG_MPTCP) += mptcp.o mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \ - mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o + mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o \ + mptcp_pm_gen.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index e72b518c5d02..13fe0748dde8 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -27,6 +27,7 @@ struct mptcp_pernet { #endif unsigned int add_addr_timeout; + unsigned int close_timeout; unsigned int stale_loss_cnt; u8 mptcp_enabled; u8 checksum_enabled; @@ -65,6 +66,13 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net) return mptcp_get_pernet(net)->stale_loss_cnt; } +unsigned int mptcp_close_timeout(const struct sock *sk) +{ + if (sock_flag(sk, SOCK_DEAD)) + return TCP_TIMEWAIT_LEN; + return mptcp_get_pernet(sock_net(sk))->close_timeout; +} + int mptcp_get_pm_type(const struct net *net) { return mptcp_get_pernet(net)->pm_type; @@ -79,6 +87,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet) { pernet->mptcp_enabled = 1; pernet->add_addr_timeout = TCP_RTO_MAX; + pernet->close_timeout = TCP_TIMEWAIT_LEN; pernet->checksum_enabled = 0; pernet->allow_join_initial_addr_port = 1; pernet->stale_loss_cnt = 4; @@ -141,6 +150,12 @@ static struct ctl_table mptcp_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dostring, }, + { + .procname = "close_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, {} }; @@ -163,6 +178,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet) table[4].data = &pernet->stale_loss_cnt; table[5].data = &pernet->pm_type; table[6].data = &pernet->scheduler; + table[7].data = &pernet->close_timeout; hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table, ARRAY_SIZE(mptcp_sysctl_table)); diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index bceaab8dd8e4..74698582a285 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -52,6 +52,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf mptcp_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); + mptcp_sk(sk)->bytes_received += skb->len; sk->sk_data_ready(sk); diff --git a/net/mptcp/mptcp_pm_gen.c b/net/mptcp/mptcp_pm_gen.c new file mode 100644 index 000000000000..a2325e70ddab --- /dev/null +++ b/net/mptcp/mptcp_pm_gen.c @@ -0,0 +1,179 @@ +// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN kernel source */ + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include "mptcp_pm_gen.h" + +#include <uapi/linux/mptcp_pm.h> + +/* Common nested types */ +const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1] = { + [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, + [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_ADDR6] = NLA_POLICY_EXACT_LEN(16), + [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16, }, + [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32, }, + [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32, }, +}; + +/* MPTCP_PM_CMD_ADD_ADDR - do */ +const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_DEL_ADDR - do */ +const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_GET_ADDR - do */ +const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_FLUSH_ADDRS - do */ +const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1] = { + [MPTCP_PM_ENDPOINT_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SET_LIMITS - do */ +const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_GET_LIMITS - do */ +const struct nla_policy mptcp_pm_get_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1] = { + [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_SET_FLAGS - do */ +const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_ANNOUNCE - do */ +const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, +}; + +/* MPTCP_PM_CMD_REMOVE - do */ +const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1] = { + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, +}; + +/* MPTCP_PM_CMD_SUBFLOW_CREATE - do */ +const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* MPTCP_PM_CMD_SUBFLOW_DESTROY - do */ +const struct nla_policy mptcp_pm_subflow_destroy_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1] = { + [MPTCP_PM_ATTR_ADDR] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), + [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, + [MPTCP_PM_ATTR_ADDR_REMOTE] = NLA_POLICY_NESTED(mptcp_pm_address_nl_policy), +}; + +/* Ops table for mptcp_pm */ +const struct genl_ops mptcp_pm_nl_ops[11] = { + { + .cmd = MPTCP_PM_CMD_ADD_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_add_addr_doit, + .policy = mptcp_pm_add_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_DEL_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_del_addr_doit, + .policy = mptcp_pm_del_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_GET_ADDR, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_get_addr_doit, + .dumpit = mptcp_pm_nl_get_addr_dumpit, + .policy = mptcp_pm_get_addr_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_flush_addrs_doit, + .policy = mptcp_pm_flush_addrs_nl_policy, + .maxattr = MPTCP_PM_ENDPOINT_ADDR, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_set_limits_doit, + .policy = mptcp_pm_set_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_GET_LIMITS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_get_limits_doit, + .policy = mptcp_pm_get_limits_nl_policy, + .maxattr = MPTCP_PM_ATTR_SUBFLOWS, + }, + { + .cmd = MPTCP_PM_CMD_SET_FLAGS, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_set_flags_doit, + .policy = mptcp_pm_set_flags_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_ANNOUNCE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_announce_doit, + .policy = mptcp_pm_announce_nl_policy, + .maxattr = MPTCP_PM_ATTR_TOKEN, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_REMOVE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_remove_doit, + .policy = mptcp_pm_remove_nl_policy, + .maxattr = MPTCP_PM_ATTR_LOC_ID, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_subflow_create_doit, + .policy = mptcp_pm_subflow_create_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, + { + .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, + .validate = GENL_DONT_VALIDATE_STRICT, + .doit = mptcp_pm_nl_subflow_destroy_doit, + .policy = mptcp_pm_subflow_destroy_nl_policy, + .maxattr = MPTCP_PM_ATTR_ADDR_REMOTE, + .flags = GENL_UNS_ADMIN_PERM, + }, +}; diff --git a/net/mptcp/mptcp_pm_gen.h b/net/mptcp/mptcp_pm_gen.h new file mode 100644 index 000000000000..10579d184587 --- /dev/null +++ b/net/mptcp/mptcp_pm_gen.h @@ -0,0 +1,58 @@ +/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */ +/* Do not edit directly, auto-generated from: */ +/* Documentation/netlink/specs/mptcp.yaml */ +/* YNL-GEN kernel header */ + +#ifndef _LINUX_MPTCP_PM_GEN_H +#define _LINUX_MPTCP_PM_GEN_H + +#include <net/netlink.h> +#include <net/genetlink.h> + +#include <uapi/linux/mptcp_pm.h> + +/* Common nested types */ +extern const struct nla_policy mptcp_pm_address_nl_policy[MPTCP_PM_ADDR_ATTR_IF_IDX + 1]; + +extern const struct nla_policy mptcp_pm_add_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_del_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_get_addr_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_flush_addrs_nl_policy[MPTCP_PM_ENDPOINT_ADDR + 1]; + +extern const struct nla_policy mptcp_pm_set_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1]; + +extern const struct nla_policy mptcp_pm_get_limits_nl_policy[MPTCP_PM_ATTR_SUBFLOWS + 1]; + +extern const struct nla_policy mptcp_pm_set_flags_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +extern const struct nla_policy mptcp_pm_announce_nl_policy[MPTCP_PM_ATTR_TOKEN + 1]; + +extern const struct nla_policy mptcp_pm_remove_nl_policy[MPTCP_PM_ATTR_LOC_ID + 1]; + +extern const struct nla_policy mptcp_pm_subflow_create_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +extern const struct nla_policy mptcp_pm_subflow_destroy_nl_policy[MPTCP_PM_ATTR_ADDR_REMOTE + 1]; + +/* Ops table for mptcp_pm */ +extern const struct genl_ops mptcp_pm_nl_ops[11]; + +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *skb, + struct netlink_callback *cb); +int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info); +int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, + struct genl_info *info); +int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, + struct genl_info *info); + +#endif /* _LINUX_MPTCP_PM_GEN_H */ diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 9661f3812682..1529ec358815 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1104,29 +1104,6 @@ static const struct genl_multicast_group mptcp_pm_mcgrps[] = { }, }; -static const struct nla_policy -mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = { - [MPTCP_PM_ADDR_ATTR_FAMILY] = { .type = NLA_U16, }, - [MPTCP_PM_ADDR_ATTR_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ADDR_ATTR_ADDR4] = { .type = NLA_U32, }, - [MPTCP_PM_ADDR_ATTR_ADDR6] = - NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), - [MPTCP_PM_ADDR_ATTR_PORT] = { .type = NLA_U16 }, - [MPTCP_PM_ADDR_ATTR_FLAGS] = { .type = NLA_U32 }, - [MPTCP_PM_ADDR_ATTR_IF_IDX] = { .type = NLA_S32 }, -}; - -static const struct nla_policy mptcp_pm_policy[MPTCP_PM_ATTR_MAX + 1] = { - [MPTCP_PM_ATTR_ADDR] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), - [MPTCP_PM_ATTR_RCV_ADD_ADDRS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_SUBFLOWS] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_TOKEN] = { .type = NLA_U32, }, - [MPTCP_PM_ATTR_LOC_ID] = { .type = NLA_U8, }, - [MPTCP_PM_ATTR_ADDR_REMOTE] = - NLA_POLICY_NESTED(mptcp_pm_addr_policy), -}; - void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk); @@ -1188,7 +1165,7 @@ static int mptcp_pm_parse_pm_addr_attr(struct nlattr *tb[], /* no validation needed - was already done via nested policy */ err = nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, - mptcp_pm_addr_policy, info->extack); + mptcp_pm_address_nl_policy, info->extack); if (err) return err; @@ -1303,9 +1280,9 @@ next: return 0; } -static int mptcp_nl_cmd_add_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; int ret; @@ -1484,9 +1461,9 @@ next: return 0; } -static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; unsigned int addr_max; @@ -1619,7 +1596,7 @@ static void __reset_counters(struct pm_nl_pernet *pernet) pernet->addrs = 0; } -static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); LIST_HEAD(free_list); @@ -1675,9 +1652,9 @@ nla_put_failure: return -EMSGSIZE; } -static int mptcp_nl_cmd_get_addr(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info) { - struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; + struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct sk_buff *msg; @@ -1725,8 +1702,8 @@ fail: return ret; } -static int mptcp_nl_cmd_dump_addrs(struct sk_buff *msg, - struct netlink_callback *cb) +int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; @@ -1783,8 +1760,7 @@ static int parse_limit(struct genl_info *info, int id, unsigned int *limit) return 0; } -static int -mptcp_nl_cmd_set_limits(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); unsigned int rcv_addrs, subflows; @@ -1809,8 +1785,7 @@ unlock: return ret; } -static int -mptcp_nl_cmd_get_limits(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct sk_buff *msg; @@ -1919,7 +1894,7 @@ int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 return 0; } -static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; @@ -2283,72 +2258,13 @@ nla_put_failure: nlmsg_free(skb); } -static const struct genl_small_ops mptcp_pm_ops[] = { - { - .cmd = MPTCP_PM_CMD_ADD_ADDR, - .doit = mptcp_nl_cmd_add_addr, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_DEL_ADDR, - .doit = mptcp_nl_cmd_del_addr, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_FLUSH_ADDRS, - .doit = mptcp_nl_cmd_flush_addrs, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_GET_ADDR, - .doit = mptcp_nl_cmd_get_addr, - .dumpit = mptcp_nl_cmd_dump_addrs, - }, - { - .cmd = MPTCP_PM_CMD_SET_LIMITS, - .doit = mptcp_nl_cmd_set_limits, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_GET_LIMITS, - .doit = mptcp_nl_cmd_get_limits, - }, - { - .cmd = MPTCP_PM_CMD_SET_FLAGS, - .doit = mptcp_nl_cmd_set_flags, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_ANNOUNCE, - .doit = mptcp_nl_cmd_announce, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_REMOVE, - .doit = mptcp_nl_cmd_remove, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_SUBFLOW_CREATE, - .doit = mptcp_nl_cmd_sf_create, - .flags = GENL_UNS_ADMIN_PERM, - }, - { - .cmd = MPTCP_PM_CMD_SUBFLOW_DESTROY, - .doit = mptcp_nl_cmd_sf_destroy, - .flags = GENL_UNS_ADMIN_PERM, - }, -}; - static struct genl_family mptcp_genl_family __ro_after_init = { .name = MPTCP_PM_NAME, .version = MPTCP_PM_VER, - .maxattr = MPTCP_PM_ATTR_MAX, - .policy = mptcp_pm_policy, .netnsok = true, .module = THIS_MODULE, - .small_ops = mptcp_pm_ops, - .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), + .ops = mptcp_pm_nl_ops, + .n_ops = ARRAY_SIZE(mptcp_pm_nl_ops), .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index d042d32beb4d..0f92e5b13a8a 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -145,7 +145,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); } -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *addr = info->attrs[MPTCP_PM_ATTR_ADDR]; @@ -208,7 +208,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) return err; } -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID]; @@ -270,7 +270,7 @@ int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info) return err; } -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; @@ -394,7 +394,7 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, return NULL; } -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) +int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c3b83cb390d9..1dacc072dcca 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -121,8 +121,6 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) ret = __mptcp_socket_create(msk); if (ret) return ERR_PTR(ret); - - mptcp_sockopt_sync(msk, msk->first); } return msk->first; @@ -863,9 +861,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk)) + if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk)) sk->sk_data_ready(sk); - mptcp_data_unlock(sk); } @@ -893,6 +890,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); mptcp_stop_tout_timer(sk); + __mptcp_propagate_sndbuf(sk, ssk); return true; } @@ -1079,15 +1077,16 @@ static void mptcp_enter_memory_pressure(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(sk); bool first = true; - sk_stream_moderate_sndbuf(sk); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (first) tcp_enter_memory_pressure(ssk); sk_stream_moderate_sndbuf(ssk); + first = false; } + __mptcp_sync_sndbuf(sk); } /* ensure we get enough memory for the frag hdr, beyond some minimal amount of @@ -1298,7 +1297,7 @@ alloc_skb: if (copy == 0) { u64 snd_una = READ_ONCE(msk->snd_una); - if (snd_una != msk->snd_nxt) { + if (snd_una != msk->snd_nxt || tcp_write_queue_tail(ssk)) { tcp_remove_empty_skb(ssk); return 0; } @@ -1306,11 +1305,6 @@ alloc_skb: zero_window_probe = true; data_seq = snd_una - 1; copy = 1; - - /* all mptcp-level data is acked, no skbs should be present into the - * ssk write queue - */ - WARN_ON_ONCE(reuse_skb); } copy = min_t(size_t, copy, info->limit - info->sent); @@ -1339,7 +1333,6 @@ alloc_skb: if (reuse_skb) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; mpext->data_len += copy; - WARN_ON_ONCE(zero_window_probe); goto out; } @@ -1767,6 +1760,18 @@ static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, return ret; } +static int do_copy_data_nocache(struct sock *sk, int copy, + struct iov_iter *from, char *to) +{ + if (sk->sk_route_caps & NETIF_F_NOCACHE_COPY) { + if (!copy_from_iter_full_nocache(to, copy, from)) + return -EFAULT; + } else if (!copy_from_iter_full(to, copy, from)) { + return -EFAULT; + } + return 0; +} + static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1840,11 +1845,10 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!sk_wmem_schedule(sk, total_ts)) goto wait_for_memory; - if (copy_page_from_iter(dfrag->page, offset, psize, - &msg->msg_iter) != psize) { - ret = -EFAULT; + ret = do_copy_data_nocache(sk, psize, &msg->msg_iter, + page_address(dfrag->page) + offset); + if (ret) goto do_error; - } /* data successfully copied into the write queue */ sk_forward_alloc_add(sk, -total_ts); @@ -1928,6 +1932,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, if (!(flags & MSG_PEEK)) { MPTCP_SKB_CB(skb)->offset += count; MPTCP_SKB_CB(skb)->map_seq += count; + msk->bytes_consumed += count; } break; } @@ -1938,6 +1943,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); __skb_unlink(skb, &msk->receive_queue); __kfree_skb(skb); + msk->bytes_consumed += count; } if (copied >= len) @@ -2354,6 +2360,26 @@ bool __mptcp_retransmit_pending_data(struct sock *sk) #define MPTCP_CF_PUSH BIT(1) #define MPTCP_CF_FASTCLOSE BIT(2) +/* be sure to send a reset only if the caller asked for it, also + * clean completely the subflow status when the subflow reaches + * TCP_CLOSE state + */ +static void __mptcp_subflow_disconnect(struct sock *ssk, + struct mptcp_subflow_context *subflow, + unsigned int flags) +{ + if (((1 << ssk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + (flags & MPTCP_CF_FASTCLOSE)) { + /* The MPTCP code never wait on the subflow sockets, TCP-level + * disconnect should never fail + */ + WARN_ON_ONCE(tcp_disconnect(ssk, 0)); + mptcp_subflow_ctx_reset(subflow); + } else { + tcp_shutdown(ssk, SEND_SHUTDOWN); + } +} + /* subflow sockets can be either outgoing (connect) or incoming * (accept). * @@ -2377,8 +2403,8 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, if (msk->in_accept_queue && msk->first == ssk && (sock_flag(sk, SOCK_DEAD) || sock_flag(ssk, SOCK_DEAD))) { /* ensure later check in mptcp_worker() will dispose the msk */ - mptcp_set_close_tout(sk, tcp_jiffies32 - (TCP_TIMEWAIT_LEN + 1)); sock_set_flag(sk, SOCK_DEAD); + mptcp_set_close_tout(sk, tcp_jiffies32 - (mptcp_close_timeout(sk) + 1)); lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); mptcp_subflow_drop_ctx(ssk); goto out_release; @@ -2391,7 +2417,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); if ((flags & MPTCP_CF_FASTCLOSE) && !__mptcp_check_fallback(msk)) { - /* be sure to force the tcp_disconnect() path, + /* be sure to force the tcp_close path * to generate the egress reset */ ssk->sk_lingertime = 0; @@ -2401,11 +2427,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, need_push = (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(sk); if (!dispose_it) { - /* The MPTCP code never wait on the subflow sockets, TCP-level - * disconnect should never fail - */ - WARN_ON_ONCE(tcp_disconnect(ssk, 0)); - mptcp_subflow_ctx_reset(subflow); + __mptcp_subflow_disconnect(ssk, subflow, flags); release_sock(ssk); goto out; @@ -2438,6 +2460,7 @@ out_release: WRITE_ONCE(msk->first, NULL); out: + __mptcp_sync_sndbuf(sk); if (need_push) __mptcp_push_pending(sk, 0); @@ -2506,7 +2529,7 @@ static bool mptcp_close_tout_expired(const struct sock *sk) return false; return time_after32(tcp_jiffies32, - inet_csk(sk)->icsk_mtup.probe_timestamp + TCP_TIMEWAIT_LEN); + inet_csk(sk)->icsk_mtup.probe_timestamp + mptcp_close_timeout(sk)); } static void mptcp_check_fastclose(struct mptcp_sock *msk) @@ -2649,7 +2672,7 @@ void mptcp_reset_tout_timer(struct mptcp_sock *msk, unsigned long fail_tout) return; close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + - TCP_TIMEWAIT_LEN; + mptcp_close_timeout(sk); /* the close timeout takes precedence on the fail one, and here at least one of * them is active @@ -2745,6 +2768,7 @@ static void __mptcp_init_sock(struct sock *sk) msk->rmem_fwd_alloc = 0; WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; + msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; WRITE_ONCE(msk->first, NULL); inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss; @@ -2954,16 +2978,9 @@ void __mptcp_unaccepted_force_close(struct sock *sk) __mptcp_destroy_sock(sk); } -static __poll_t mptcp_check_readable(struct mptcp_sock *msk) +static __poll_t mptcp_check_readable(struct sock *sk) { - /* Concurrent splices from sk_receive_queue into receive_queue will - * always show at least one non-empty queue when checked in this order. - */ - if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && - skb_queue_empty_lockless(&msk->receive_queue)) - return 0; - - return EPOLLIN | EPOLLRDNORM; + return mptcp_epollin_ready(sk) ? EPOLLIN | EPOLLRDNORM : 0; } static void mptcp_check_listen_stop(struct sock *sk) @@ -3001,7 +3018,7 @@ bool __mptcp_close(struct sock *sk, long timeout) goto cleanup; } - if (mptcp_check_readable(msk) || timeout < 0) { + if (mptcp_data_avail(msk) || timeout < 0) { /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ @@ -3098,12 +3115,6 @@ static int mptcp_disconnect(struct sock *sk, int flags) { struct mptcp_sock *msk = mptcp_sk(sk); - /* Deny disconnect if other threads are blocked in sk_wait_event() - * or inet_wait_for_connect(). - */ - if (sk->sk_wait_pending) - return -EBUSY; - /* We are on the fastopen error path. We can't call straight into the * subflows cleanup code due to lock nesting (we are already under * msk->firstsocket lock). @@ -3134,6 +3145,7 @@ static int mptcp_disconnect(struct sock *sk, int flags) msk->snd_data_fin_enable = false; msk->rcv_fastclose = false; msk->use_64bit_ack = false; + msk->bytes_consumed = 0; WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); @@ -3173,7 +3185,6 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, inet_sk(nsk)->pinet6 = mptcp_inet6_sk(nsk); #endif - nsk->sk_wait_pending = 0; __mptcp_init_sock(nsk); msk = mptcp_sk(nsk); @@ -3216,7 +3227,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, * uses the correct data */ mptcp_copy_inaddrs(nsk, ssk); - mptcp_propagate_sndbuf(nsk, ssk); + __mptcp_propagate_sndbuf(nsk, ssk); mptcp_rcv_space_init(msk, ssk); bh_unlock_sock(nsk); @@ -3394,6 +3405,8 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_set_connected(sk); if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags)) __mptcp_error_report(sk); + if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags)) + __mptcp_sync_sndbuf(sk); } __mptcp_update_rmem(sk); @@ -3438,6 +3451,14 @@ void mptcp_subflow_process_delegated(struct sock *ssk, long status) __set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } + if (status & BIT(MPTCP_DELEGATE_SNDBUF)) { + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_sync_sndbuf(sk); + else + __set_bit(MPTCP_SYNC_SNDBUF, &mptcp_sk(sk)->cb_flags); + mptcp_data_unlock(sk); + } if (status & BIT(MPTCP_DELEGATE_ACK)) schedule_3rdack_retransmission(ssk); } @@ -3522,6 +3543,7 @@ bool mptcp_finish_join(struct sock *ssk) /* active subflow, already present inside the conn_list */ if (!list_empty(&subflow->node)) { mptcp_subflow_joined(msk, ssk); + mptcp_propagate_sndbuf(parent, ssk); return true; } @@ -3906,7 +3928,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock, mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP; if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) { - mask |= mptcp_check_readable(msk); + mask |= mptcp_check_readable(sk); if (shutdown & SEND_SHUTDOWN) mask |= EPOLLOUT | EPOLLWRNORM; else @@ -3944,6 +3966,7 @@ static const struct proto_ops mptcp_stream_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct inet_protosw mptcp_protosw = { @@ -4045,6 +4068,7 @@ static const struct proto_ops mptcp_v6_stream_ops = { #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif + .set_rcvlowat = mptcp_set_rcvlowat, }; static struct proto mptcp_v6_prot; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3612545fa62e..9092fcf18798 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -13,6 +13,8 @@ #include <uapi/linux/mptcp.h> #include <net/genetlink.h> +#include "mptcp_pm_gen.h" + #define MPTCP_SUPPORTED_VERSION 1 /* MPTCP option bits */ @@ -123,6 +125,7 @@ #define MPTCP_RETRANSMIT 4 #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_CONNECTED 6 +#define MPTCP_SYNC_SNDBUF 7 struct mptcp_skb_cb { u64 map_seq; @@ -267,6 +270,7 @@ struct mptcp_sock { atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; u64 bytes_retrans; + u64 bytes_consumed; int rmem_fwd_alloc; int snd_burst; int old_wspace; @@ -432,11 +436,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) return (struct mptcp_subflow_request_sock *)rsk; } -enum mptcp_data_avail { - MPTCP_SUBFLOW_NODATA, - MPTCP_SUBFLOW_DATA_AVAIL, -}; - struct mptcp_delegated_action { struct napi_struct napi; struct list_head head; @@ -447,6 +446,7 @@ DECLARE_PER_CPU(struct mptcp_delegated_action, mptcp_delegated_actions); #define MPTCP_DELEGATE_SCHEDULED 0 #define MPTCP_DELEGATE_SEND 1 #define MPTCP_DELEGATE_ACK 2 +#define MPTCP_DELEGATE_SNDBUF 3 #define MPTCP_DELEGATE_ACTIONS_MASK (~BIT(MPTCP_DELEGATE_SCHEDULED)) /* MPTCP subflow context */ @@ -492,7 +492,7 @@ struct mptcp_subflow_context { valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ __unused : 9; - enum mptcp_data_avail data_avail; + bool data_avail; bool scheduled; u32 remote_nonce; u64 thmac; @@ -520,6 +520,9 @@ struct mptcp_subflow_context { u32 setsockopt_seq; u32 stale_rcv_tstamp; + int cached_sndbuf; /* sndbuf size when last synced with the msk sndbuf, + * protected by the msk socket lock + */ struct sock *tcp_sock; /* tcp sk backpointer */ struct sock *conn; /* parent mptcp_sock */ @@ -613,6 +616,7 @@ unsigned int mptcp_get_add_addr_timeout(const struct net *net); int mptcp_is_checksum_enabled(const struct net *net); int mptcp_allow_join_id0(const struct net *net); unsigned int mptcp_stale_loss_cnt(const struct net *net); +unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, @@ -661,6 +665,24 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk); int mptcp_sched_get_send(struct mptcp_sock *msk); int mptcp_sched_get_retrans(struct mptcp_sock *msk); +static inline u64 mptcp_data_avail(const struct mptcp_sock *msk) +{ + return READ_ONCE(msk->bytes_received) - READ_ONCE(msk->bytes_consumed); +} + +static inline bool mptcp_epollin_ready(const struct sock *sk) +{ + /* mptcp doesn't have to deal with small skbs in the receive queue, + * at it can always coalesce them + */ + return (mptcp_data_avail(mptcp_sk(sk)) >= sk->sk_rcvlowat) || + (mem_cgroup_sockets_enabled && sk->sk_memcg && + mem_cgroup_under_socket_pressure(sk->sk_memcg)) || + READ_ONCE(tcp_memory_pressure); +} + +int mptcp_set_rcvlowat(struct sock *sk, int val); + static inline bool __tcp_can_send(const struct sock *ssk) { /* only send if our side has not closed yet */ @@ -735,6 +757,7 @@ static inline bool mptcp_is_fully_established(struct sock *sk) return inet_sk_state_load(sk) == TCP_ESTABLISHED && READ_ONCE(mptcp_sk(sk)->fully_established); } + void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk); void mptcp_data_ready(struct sock *sk, struct sock *ssk); bool mptcp_finish_join(struct sock *sk); @@ -762,13 +785,52 @@ static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk) READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt); } -static inline bool mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +static inline void __mptcp_sync_sndbuf(struct sock *sk) { - if ((sk->sk_userlocks & SOCK_SNDBUF_LOCK) || ssk->sk_sndbuf <= READ_ONCE(sk->sk_sndbuf)) - return false; + struct mptcp_subflow_context *subflow; + int ssk_sndbuf, new_sndbuf; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + new_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[0]; + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + ssk_sndbuf = READ_ONCE(mptcp_subflow_tcp_sock(subflow)->sk_sndbuf); + + subflow->cached_sndbuf = ssk_sndbuf; + new_sndbuf += ssk_sndbuf; + } + + /* the msk max wmem limit is <nr_subflows> * tcp wmem[2] */ + WRITE_ONCE(sk->sk_sndbuf, new_sndbuf); +} + +/* The called held both the msk socket and the subflow socket locks, + * possibly under BH + */ +static inline void __mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (READ_ONCE(ssk->sk_sndbuf) != subflow->cached_sndbuf) + __mptcp_sync_sndbuf(sk); +} + +/* the caller held only the subflow socket lock, either in process or + * BH context. Additionally this can be called under the msk data lock, + * so we can't acquire such lock here: let the delegate action acquires + * the needed locks in suitable order. + */ +static inline void mptcp_propagate_sndbuf(struct sock *sk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + + if (likely(READ_ONCE(ssk->sk_sndbuf) == subflow->cached_sndbuf)) + return; - WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf); - return true; + local_bh_disable(); + mptcp_subflow_delegate(subflow, MPTCP_DELEGATE_SNDBUF); + local_bh_enable(); } static inline void mptcp_write_space(struct sock *sk) @@ -877,10 +939,6 @@ void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list); void mptcp_free_local_addr_list(struct mptcp_sock *msk); -int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_remove(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_create(struct sk_buff *skb, struct genl_info *info); -int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info); void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 18ce624bfde2..574e221bb765 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -95,6 +95,7 @@ static void mptcp_sol_socket_sync_intval(struct mptcp_sock *msk, int optname, in case SO_SNDBUFFORCE: ssk->sk_userlocks |= SOCK_SNDBUF_LOCK; WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; break; case SO_RCVBUF: case SO_RCVBUFFORCE: @@ -738,7 +739,7 @@ static int mptcp_setsockopt_v4_set_tos(struct mptcp_sock *msk, int optname, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - ip_sock_set_tos(ssk, val); + __ip_sock_set_tos(ssk, val); } release_sock(sk); @@ -1411,12 +1412,14 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) ssk->sk_bound_dev_if = sk->sk_bound_dev_if; ssk->sk_incoming_cpu = sk->sk_incoming_cpu; ssk->sk_ipv6only = sk->sk_ipv6only; - ip_sock_set_tos(ssk, inet_sk(sk)->tos); + __ip_sock_set_tos(ssk, inet_sk(sk)->tos); if (sk->sk_userlocks & tx_rx_locks) { ssk->sk_userlocks |= sk->sk_userlocks & tx_rx_locks; - if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) { WRITE_ONCE(ssk->sk_sndbuf, sk->sk_sndbuf); + mptcp_subflow_ctx(ssk)->cached_sndbuf = sk->sk_sndbuf; + } if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) WRITE_ONCE(ssk->sk_rcvbuf, sk->sk_rcvbuf); } @@ -1444,37 +1447,63 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) inet_assign_bit(FREEBIND, ssk, inet_test_bit(FREEBIND, sk)); } -static void __mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) -{ - bool slow = lock_sock_fast(ssk); - - sync_socket_options(msk, ssk); - - unlock_sock_fast(ssk, slow); -} - -void mptcp_sockopt_sync(struct mptcp_sock *msk, struct sock *ssk) +void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); msk_owned_by_me(msk); + ssk->sk_rcvlowat = 0; + + /* subflows must ignore any latency-related settings: will not affect + * the user-space - only the msk is relevant - but will foul the + * mptcp scheduler + */ + tcp_sk(ssk)->notsent_lowat = UINT_MAX; + if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { - __mptcp_sockopt_sync(msk, ssk); + sync_socket_options(msk, ssk); subflow->setsockopt_seq = msk->setsockopt_seq; } } -void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) +/* unfortunately this is different enough from the tcp version so + * that we can't factor it out + */ +int mptcp_set_rcvlowat(struct sock *sk, int val) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct mptcp_subflow_context *subflow; + int space, cap; - msk_owned_by_me(msk); + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + cap = sk->sk_rcvbuf >> 1; + else + cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; + val = min(val, cap); + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); - if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { - sync_socket_options(msk, ssk); + /* Check if we need to signal EPOLLIN right now */ + if (mptcp_epollin_ready(sk)) + sk->sk_data_ready(sk); - subflow->setsockopt_seq = msk->setsockopt_seq; + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + space = __tcp_space_from_win(mptcp_sk(sk)->scaling_ratio, val); + if (space <= sk->sk_rcvbuf) + return 0; + + /* propagate the rcvbuf changes to all the subflows */ + WRITE_ONCE(sk->sk_rcvbuf, space); + mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + bool slow; + + slow = lock_sock_fast(ssk); + WRITE_ONCE(ssk->sk_rcvbuf, space); + tcp_sk(ssk)->window_clamp = val; + unlock_sock_fast(ssk, slow); } + return 0; } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 9c1f8d1d63d2..e120e9616454 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,6 +421,7 @@ static bool subflow_use_different_dport(struct mptcp_sock *msk, const struct soc void __mptcp_set_connected(struct sock *sk) { + __mptcp_propagate_sndbuf(sk, mptcp_sk(sk)->first); if (sk->sk_state == TCP_SYN_SENT) { inet_sk_state_store(sk, TCP_ESTABLISHED); sk->sk_state_change(sk); @@ -472,7 +473,6 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) return; msk = mptcp_sk(parent); - mptcp_propagate_sndbuf(parent, sk); subflow->rel_write_seq = 1; subflow->conn_finished = 1; subflow->ssn_offset = TCP_SKB_CB(skb)->seq; @@ -1237,7 +1237,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); if (subflow->data_avail) return true; @@ -1271,7 +1271,7 @@ static bool subflow_check_data_avail(struct sock *ssk) continue; } - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); break; } return true; @@ -1293,7 +1293,7 @@ fallback: goto reset; } mptcp_subflow_fail(msk, ssk); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1310,7 +1310,7 @@ reset: while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); return false; } @@ -1322,7 +1322,7 @@ reset: subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + WRITE_ONCE(subflow->data_avail, true); return true; } @@ -1334,7 +1334,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + WRITE_ONCE(subflow->data_avail, false); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1405,10 +1405,18 @@ static void subflow_data_ready(struct sock *sk) WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && !subflow->mp_join && !(state & TCPF_CLOSE)); - if (mptcp_subflow_data_available(sk)) + if (mptcp_subflow_data_available(sk)) { mptcp_data_ready(parent, sk); - else if (unlikely(sk->sk_err)) + + /* subflow-level lowat test are not relevant. + * respect the msk-level threshold eventually mandating an immediate ack + */ + if (mptcp_data_avail(msk) < parent->sk_rcvlowat && + (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } else if (unlikely(sk->sk_err)) { subflow_error_report(sk); + } } static void subflow_write_space(struct sock *ssk) @@ -1525,8 +1533,6 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, if (addr.ss_family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif - mptcp_sockopt_sync(msk, ssk); - ssk->sk_bound_dev_if = ifindex; err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); if (err) @@ -1637,7 +1643,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, err = security_mptcp_add_subflow(sk, sf->sk); if (err) - goto release_ssk; + goto err_free; /* the newly created socket has to be in the same cgroup as its parent */ mptcp_attach_cgroup(sk, sf->sk); @@ -1651,15 +1657,12 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family, get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL); sock_inuse_add(net, 1); err = tcp_set_ulp(sf->sk, "mptcp"); + if (err) + goto err_free; -release_ssk: + mptcp_sockopt_sync_locked(mptcp_sk(sk), sf->sk); release_sock(sf->sk); - if (err) { - sock_release(sf); - return err; - } - /* the newly created socket really belongs to the owning MPTCP master * socket, even if for additional subflows the allocation is performed * by a kernel workqueue. Adjust inode references, so that the @@ -1679,6 +1682,11 @@ release_ssk: mptcp_subflow_ops_override(sf->sk); return 0; + +err_free: + release_sock(sf->sk); + sock_release(sf); + return err; } static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, @@ -1728,7 +1736,6 @@ static void subflow_state_change(struct sock *sk) msk = mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { - mptcp_propagate_sndbuf(parent, sk); mptcp_do_fallback(sk); mptcp_rcv_space_init(msk, sk); pr_fallback(msk); @@ -2044,7 +2051,6 @@ void __init mptcp_subflow_init(void) subflow_v6m_specific.send_check = ipv4_specific.send_check; subflow_v6m_specific.net_header_len = ipv4_specific.net_header_len; subflow_v6m_specific.mtu_reduced = ipv4_specific.mtu_reduced; - subflow_v6m_specific.net_frag_header_len = 0; subflow_v6m_specific.rebuild_header = subflow_rebuild_header; tcpv6_prot_override = tcpv6_prot; diff --git a/net/netfilter/core.c b/net/netfilter/core.c index ef4e76e5aef9..3126911f5042 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -639,10 +639,10 @@ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, if (ret == 1) continue; return ret; + case NF_STOLEN: + return NF_DROP_GETERR(verdict); default: - /* Implicit handling for NF_STOLEN, as well as any other - * non conventional verdicts. - */ + WARN_ON_ONCE(1); return 0; } } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 124136b5a79a..2e5f3864d353 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2169,11 +2169,11 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); if (dataoff <= 0) - return -1; + return NF_DROP; if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, l4num, net, &tuple)) - return -1; + return NF_DROP; if (ct->status & IPS_SRC_NAT) { memcpy(tuple.src.u3.all, @@ -2193,7 +2193,7 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, h = nf_conntrack_find_get(net, nf_ct_zone(ct), &tuple); if (!h) - return 0; + return NF_ACCEPT; /* Store status bits of the conntrack that is clashing to re-do NAT * mangling according to what it has been done already to this packet. @@ -2206,19 +2206,25 @@ static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, nat_hook = rcu_dereference(nf_nat_hook); if (!nat_hook) - return 0; + return NF_ACCEPT; - if (status & IPS_SRC_NAT && - nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_SRC, - IP_CT_DIR_ORIGINAL) == NF_DROP) - return -1; + if (status & IPS_SRC_NAT) { + unsigned int verdict = nat_hook->manip_pkt(skb, ct, + NF_NAT_MANIP_SRC, + IP_CT_DIR_ORIGINAL); + if (verdict != NF_ACCEPT) + return verdict; + } - if (status & IPS_DST_NAT && - nat_hook->manip_pkt(skb, ct, NF_NAT_MANIP_DST, - IP_CT_DIR_ORIGINAL) == NF_DROP) - return -1; + if (status & IPS_DST_NAT) { + unsigned int verdict = nat_hook->manip_pkt(skb, ct, + NF_NAT_MANIP_DST, + IP_CT_DIR_ORIGINAL); + if (verdict != NF_ACCEPT) + return verdict; + } - return 0; + return NF_ACCEPT; } /* This packet is coming from userspace via nf_queue, complete the packet @@ -2233,14 +2239,14 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, help = nfct_help(ct); if (!help) - return 0; + return NF_ACCEPT; helper = rcu_dereference(help->helper); if (!helper) - return 0; + return NF_ACCEPT; if (!(helper->flags & NF_CT_HELPER_F_USERSPACE)) - return 0; + return NF_ACCEPT; switch (nf_ct_l3num(ct)) { case NFPROTO_IPV4: @@ -2255,42 +2261,44 @@ static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) - return 0; + return NF_ACCEPT; break; } #endif default: - return 0; + return NF_ACCEPT; } if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && !nf_is_loopback_packet(skb)) { if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return -1; + return NF_DROP; } } /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0; + return nf_conntrack_confirm(skb); } static int nf_conntrack_update(struct net *net, struct sk_buff *skb) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; - int err; ct = nf_ct_get(skb, &ctinfo); if (!ct) - return 0; + return NF_ACCEPT; if (!nf_ct_is_confirmed(ct)) { - err = __nf_conntrack_update(net, skb, ct, ctinfo); - if (err < 0) - return err; + int ret = __nf_conntrack_update(net, skb, ct, ctinfo); + + if (ret != NF_ACCEPT) + return ret; ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return NF_ACCEPT; } return nf_confirm_cthelper(skb, ct, ctinfo); diff --git a/net/netfilter/nf_conntrack_labels.c b/net/netfilter/nf_conntrack_labels.c index 6e70e137a0a6..6c46aad23313 100644 --- a/net/netfilter/nf_conntrack_labels.c +++ b/net/netfilter/nf_conntrack_labels.c @@ -11,8 +11,6 @@ #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_labels.h> -static DEFINE_SPINLOCK(nf_connlabels_lock); - static int replace_u32(u32 *address, u32 mask, u32 new) { u32 old, tmp; @@ -60,23 +58,24 @@ EXPORT_SYMBOL_GPL(nf_connlabels_replace); int nf_connlabels_get(struct net *net, unsigned int bits) { + int v; + if (BIT_WORD(bits) >= NF_CT_LABELS_MAX_SIZE / sizeof(long)) return -ERANGE; - spin_lock(&nf_connlabels_lock); - net->ct.labels_used++; - spin_unlock(&nf_connlabels_lock); - BUILD_BUG_ON(NF_CT_LABELS_MAX_SIZE / sizeof(long) >= U8_MAX); + v = atomic_inc_return_relaxed(&net->ct.labels_used); + WARN_ON_ONCE(v <= 0); + return 0; } EXPORT_SYMBOL_GPL(nf_connlabels_get); void nf_connlabels_put(struct net *net) { - spin_lock(&nf_connlabels_lock); - net->ct.labels_used--; - spin_unlock(&nf_connlabels_lock); + int v = atomic_dec_return_relaxed(&net->ct.labels_used); + + WARN_ON_ONCE(v < 0); } EXPORT_SYMBOL_GPL(nf_connlabels_put); diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 1d34d700bd09..920a5a29ae1d 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -316,12 +316,6 @@ void flow_offload_refresh(struct nf_flowtable *flow_table, } EXPORT_SYMBOL_GPL(flow_offload_refresh); -static bool nf_flow_is_outdated(const struct flow_offload *flow) -{ - return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && - !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); -} - static inline bool nf_flow_has_expired(const struct flow_offload *flow) { return nf_flow_timeout_delta(flow->timeout) <= 0; @@ -407,12 +401,18 @@ nf_flow_table_iterate(struct nf_flowtable *flow_table, return err; } +static bool nf_flow_custom_gc(struct nf_flowtable *flow_table, + const struct flow_offload *flow) +{ + return flow_table->type->gc && flow_table->type->gc(flow); +} + static void nf_flow_offload_gc_step(struct nf_flowtable *flow_table, struct flow_offload *flow, void *data) { if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - nf_flow_is_outdated(flow)) + nf_flow_custom_gc(flow_table, flow)) flow_offload_teardown(flow); if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 5a049740758f..6d969468c779 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -999,11 +999,12 @@ static unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - unsigned int ret; + unsigned int ret, verdict; struct in6_addr daddr = ipv6_hdr(skb)->daddr; ret = nf_nat_ipv6_fn(priv, skb, state); - if (ret != NF_DROP && ret != NF_STOLEN && + verdict = ret & NF_VERDICT_MASK; + if (verdict != NF_DROP && verdict != NF_STOLEN && ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr)) skb_dst_drop(skb); diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 16915f8eef2b..467671f2d42f 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -153,7 +153,7 @@ void synproxy_init_timestamp_cookie(const struct nf_synproxy_info *info, struct synproxy_options *opts) { opts->tsecr = opts->tsval; - opts->tsval = tcp_time_stamp_raw() & ~0x3f; + opts->tsval = tcp_clock_ms() & ~0x3f; if (opts->options & NF_SYNPROXY_OPT_WSCALE) { opts->tsval |= opts->wscale; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 68321345bb6d..3c1fd8283bf4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -591,9 +591,9 @@ static int nft_trans_set_add(const struct nft_ctx *ctx, int msg_type, static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - nft_setelem_data_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem_priv); return 0; } @@ -601,7 +601,7 @@ static int nft_mapelem_deactivate(const struct nft_ctx *ctx, struct nft_set_elem_catchall { struct list_head list; struct rcu_head rcu; - void *elem; + struct nft_elem_priv *elem; }; static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, @@ -609,7 +609,6 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { @@ -617,8 +616,7 @@ static void nft_map_catchall_deactivate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - nft_setelem_data_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, catchall->elem); break; } } @@ -3166,7 +3164,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, if (err < 0) return err; - if (!tb[NFTA_EXPR_DATA]) + if (!tb[NFTA_EXPR_DATA] || !tb[NFTA_EXPR_NAME]) return -EINVAL; type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); @@ -3551,6 +3549,23 @@ done: return skb->len; } +static int nf_tables_dumpreset_rules(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk)); + int ret; + + /* Mutex is held is to prevent that two concurrent dump-and-reset calls + * do not underrun counters and quotas. The commit_mutex is used for + * the lack a better lock, this is not transaction path. + */ + mutex_lock(&nft_net->commit_mutex); + ret = nf_tables_dump_rules(skb, cb); + mutex_unlock(&nft_net->commit_mutex); + + return ret; +} + static int nf_tables_dump_rules_start(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; @@ -3570,12 +3585,18 @@ static int nf_tables_dump_rules_start(struct netlink_callback *cb) return -ENOMEM; } } - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) - ctx->reset = true; - return 0; } +static int nf_tables_dumpreset_rules_start(struct netlink_callback *cb) +{ + struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + + return nf_tables_dump_rules_start(cb); +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = (void *)cb->ctx; @@ -3586,8 +3607,9 @@ static int nf_tables_dump_rules_done(struct netlink_callback *cb) } /* called with rcu_read_lock held */ -static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getrule_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); @@ -3597,60 +3619,110 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; - bool reset = false; int err; - if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start= nf_tables_dump_rules_start, - .dump = nf_tables_dump_rules, - .done = nf_tables_dump_rules_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); } chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask); if (IS_ERR(chain)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); - return PTR_ERR(chain); + return ERR_CAST(chain); } rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); if (IS_ERR(rule)) { NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); - return PTR_ERR(rule); + return ERR_CAST(rule); } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; - - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) - reset = true; + return ERR_PTR(-ENOMEM); - err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, + err = nf_tables_fill_rule_info(skb2, net, portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, family, table, chain, rule, 0, reset); - if (err < 0) - goto err_fill_rule_info; + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } - if (reset) - audit_log_rule_reset(table, nft_pernet(net)->base_seq, 1); + return skb2; +} - return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); +static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; -err_fill_rule_info: - kfree_skb(skb2); - return err; + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, + .dump = nf_tables_dump_rules, + .done = nf_tables_dump_rules_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + skb2 = nf_tables_getrule_single(portid, info, nla, false); + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + return nfnetlink_unicast(skb2, net, portid); +} + +static int nf_tables_getrule_reset(struct sk_buff *skb, + const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start= nf_tables_dumpreset_rules_start, + .dump = nf_tables_dumpreset_rules, + .done = nf_tables_dump_rules_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + } + + if (!try_module_get(THIS_MODULE)) + return -EINVAL; + rcu_read_unlock(); + mutex_lock(&nft_net->commit_mutex); + skb2 = nf_tables_getrule_single(portid, info, nla, true); + mutex_unlock(&nft_net->commit_mutex); + rcu_read_lock(); + module_put(THIS_MODULE); + + if (IS_ERR(skb2)) + return PTR_ERR(skb2); + + buf = kasprintf(GFP_ATOMIC, "%.*s:%u", + nla_len(nla[NFTA_RULE_TABLE]), + (char *)nla_data(nla[NFTA_RULE_TABLE]), + nft_net->base_seq); + audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1, + AUDIT_NFT_OP_RULE_RESET, GFP_ATOMIC); + kfree(buf); + + return nfnetlink_unicast(skb2, net, portid); } void nf_tables_rule_destroy(const struct nft_ctx *ctx, struct nft_rule *rule) @@ -3733,9 +3805,9 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) int nft_setelem_validate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -3765,7 +3837,6 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -3774,8 +3845,7 @@ int nft_set_catchall_validate(const struct nft_ctx *ctx, struct nft_set *set) if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - ret = nft_setelem_validate(ctx, set, NULL, &elem); + ret = nft_setelem_validate(ctx, set, NULL, catchall->elem); if (ret < 0) return ret; } @@ -5227,9 +5297,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, static int nft_setelem_data_validate(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); enum nft_registers dreg; dreg = nft_type_to_reg(set->dtype); @@ -5242,9 +5312,9 @@ static int nft_setelem_data_validate(const struct nft_ctx *ctx, static int nf_tables_bind_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - return nft_setelem_data_validate(ctx, set, elem); + return nft_setelem_data_validate(ctx, set, elem_priv); } static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, @@ -5252,7 +5322,6 @@ static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -5261,8 +5330,7 @@ static int nft_set_catchall_bind_check(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - ret = nft_setelem_data_validate(ctx, set, &elem); + ret = nft_setelem_data_validate(ctx, set, catchall->elem); if (ret < 0) break; } @@ -5329,14 +5397,14 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem); + struct nft_elem_priv *elem_priv); static int nft_mapelem_activate(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - nft_setelem_data_activate(ctx->net, set, elem); + nft_setelem_data_activate(ctx->net, set, elem_priv); return 0; } @@ -5346,7 +5414,6 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; list_for_each_entry(catchall, &set->catchall_list, list) { @@ -5354,8 +5421,7 @@ static void nft_map_catchall_activate(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - nft_setelem_data_activate(ctx->net, set, &elem); + nft_setelem_data_activate(ctx->net, set, catchall->elem); break; } } @@ -5534,13 +5600,12 @@ nla_put_failure: static int nf_tables_fill_setelem(struct sk_buff *skb, const struct nft_set *set, - const struct nft_set_elem *elem, + const struct nft_elem_priv *elem_priv, bool reset) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; - u64 timeout = 0; nest = nla_nest_start_noflag(skb, NFTA_LIST_ELEM); if (nest == NULL) @@ -5576,15 +5641,11 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, htonl(*nft_set_ext_flags(ext)))) goto nla_put_failure; - if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) { - timeout = *nft_set_ext_timeout(ext); - if (nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - nf_jiffies64_to_msecs(timeout), - NFTA_SET_ELEM_PAD)) - goto nla_put_failure; - } else if (set->flags & NFT_SET_TIMEOUT) { - timeout = READ_ONCE(set->timeout); - } + if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && + nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, + nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), + NFTA_SET_ELEM_PAD)) + goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { u64 expires, now = get_jiffies_64(); @@ -5599,9 +5660,6 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; - - if (reset) - *nft_set_ext_expiration(ext) = now + timeout; } if (nft_set_ext_exists(ext, NFT_SET_EXT_USERDATA)) { @@ -5631,16 +5689,16 @@ struct nft_set_dump_args { static int nf_tables_dump_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_set_dump_args *args; if (nft_set_elem_expired(ext)) return 0; args = container_of(iter, struct nft_set_dump_args, iter); - return nf_tables_fill_setelem(args->skb, set, elem, args->reset); + return nf_tables_fill_setelem(args->skb, set, elem_priv, args->reset); } static void audit_log_nft_set_reset(const struct nft_table *table, @@ -5657,6 +5715,7 @@ static void audit_log_nft_set_reset(const struct nft_table *table, struct nft_set_dump_ctx { const struct nft_set *set; struct nft_ctx ctx; + bool reset; }; static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, @@ -5665,7 +5724,6 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_cur(net); - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -5675,8 +5733,7 @@ static int nft_set_catchall_dump(struct net *net, struct sk_buff *skb, nft_set_elem_expired(ext)) continue; - elem.priv = catchall->elem; - ret = nf_tables_fill_setelem(skb, set, &elem, reset); + ret = nf_tables_fill_setelem(skb, set, catchall->elem, reset); if (reset && !ret) audit_log_nft_set_reset(set->table, base_seq, 1); break; @@ -5696,7 +5753,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) bool set_found = false; struct nlmsghdr *nlh; struct nlattr *nest; - bool reset = false; u32 portid, seq; int event; @@ -5744,12 +5800,9 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto nla_put_failure; - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) - reset = true; - args.cb = cb; args.skb = skb; - args.reset = reset; + args.reset = dump_ctx->reset; args.iter.genmask = nft_genmask_cur(net); args.iter.skip = cb->args[0]; args.iter.count = 0; @@ -5759,11 +5812,11 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (!args.iter.err && args.iter.count == cb->args[0]) args.iter.err = nft_set_catchall_dump(net, skb, set, - reset, cb->seq); + dump_ctx->reset, cb->seq); nla_nest_end(skb, nest); nlmsg_end(skb, nlh); - if (reset && args.iter.count > args.iter.skip) + if (dump_ctx->reset && args.iter.count > args.iter.skip) audit_log_nft_set_reset(table, cb->seq, args.iter.count - args.iter.skip); @@ -5801,7 +5854,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, const struct nft_ctx *ctx, u32 seq, u32 portid, int event, u16 flags, const struct nft_set *set, - const struct nft_set_elem *elem, + const struct nft_elem_priv *elem_priv, bool reset) { struct nlmsghdr *nlh; @@ -5823,7 +5876,7 @@ static int nf_tables_fill_setelem_info(struct sk_buff *skb, if (nest == NULL) goto nla_put_failure; - err = nf_tables_fill_setelem(skb, set, elem, reset); + err = nf_tables_fill_setelem(skb, set, elem_priv, reset); if (err < 0) goto nla_put_failure; @@ -5973,7 +6026,7 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = nf_tables_fill_setelem_info(skb, ctx, ctx->seq, ctx->portid, - NFT_MSG_NEWSETELEM, 0, set, &elem, + NFT_MSG_NEWSETELEM, 0, set, elem.priv, reset); if (err < 0) goto err_fill_setelem; @@ -6016,6 +6069,9 @@ static int nf_tables_getsetelem(struct sk_buff *skb, nft_ctx_init(&ctx, net, skb, info->nlh, family, table, NULL, nla); + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) + reset = true; + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { .start = nf_tables_dump_set_start, @@ -6026,6 +6082,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb, struct nft_set_dump_ctx dump_ctx = { .set = set, .ctx = ctx, + .reset = reset, }; c.data = &dump_ctx; @@ -6035,9 +6092,6 @@ static int nf_tables_getsetelem(struct sk_buff *skb, if (!nla[NFTA_SET_ELEM_LIST_ELEMENTS]) return -EINVAL; - if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETSETELEM_RESET) - reset = true; - nla_for_each_nested(attr, nla[NFTA_SET_ELEM_LIST_ELEMENTS], rem) { err = nft_get_set_elem(&ctx, set, attr, reset); if (err < 0) { @@ -6056,7 +6110,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb, static void nf_tables_setelem_notify(const struct nft_ctx *ctx, const struct nft_set *set, - const struct nft_set_elem *elem, + const struct nft_elem_priv *elem_priv, int event) { struct nftables_pernet *nft_net; @@ -6077,7 +6131,7 @@ static void nf_tables_setelem_notify(const struct nft_ctx *ctx, flags |= ctx->flags & (NLM_F_CREATE | NLM_F_EXCL); err = nf_tables_fill_setelem_info(skb, ctx, 0, portid, event, flags, - set, elem, false); + set, elem_priv, false); if (err < 0) { kfree_skb(skb); goto err; @@ -6152,10 +6206,11 @@ static int nft_set_ext_memcpy(const struct nft_set_ext_tmpl *tmpl, u8 id, return 0; } -void *nft_set_elem_init(const struct nft_set *set, - const struct nft_set_ext_tmpl *tmpl, - const u32 *key, const u32 *key_end, - const u32 *data, u64 timeout, u64 expiration, gfp_t gfp) +struct nft_elem_priv *nft_set_elem_init(const struct nft_set *set, + const struct nft_set_ext_tmpl *tmpl, + const u32 *key, const u32 *key_end, + const u32 *data, + u64 timeout, u64 expiration, gfp_t gfp) { struct nft_set_ext *ext; void *elem; @@ -6220,10 +6275,11 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx, } /* Drop references and destroy. Called from gc, dynset and abort path. */ -void nft_set_elem_destroy(const struct nft_set *set, void *elem, +void nft_set_elem_destroy(const struct nft_set *set, + const struct nft_elem_priv *elem_priv, bool destroy_expr) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); struct nft_ctx ctx = { .net = read_pnet(&set->net), .family = set->table->family, @@ -6234,10 +6290,10 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem, nft_data_release(nft_set_ext_data(ext), set->dtype); if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext)); - if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF)) nft_use_dec(&(*nft_set_ext_obj(ext))->use); - kfree(elem); + + kfree(elem_priv); } EXPORT_SYMBOL_GPL(nft_set_elem_destroy); @@ -6245,14 +6301,15 @@ EXPORT_SYMBOL_GPL(nft_set_elem_destroy); * path via nft_setelem_data_deactivate(). */ void nf_tables_set_elem_destroy(const struct nft_ctx *ctx, - const struct nft_set *set, void *elem) + const struct nft_set *set, + const struct nft_elem_priv *elem_priv) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS)) nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext)); - kfree(elem); + kfree(elem_priv); } int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set, @@ -6347,7 +6404,7 @@ EXPORT_SYMBOL_GPL(nft_set_catchall_lookup); static int nft_setelem_catchall_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **pext) + struct nft_elem_priv **priv) { struct nft_set_elem_catchall *catchall; u8 genmask = nft_genmask_next(net); @@ -6356,7 +6413,7 @@ static int nft_setelem_catchall_insert(const struct net *net, list_for_each_entry(catchall, &set->catchall_list, list) { ext = nft_set_elem_ext(set, catchall->elem); if (nft_set_elem_active(ext, genmask)) { - *pext = ext; + *priv = catchall->elem; return -EEXIST; } } @@ -6374,22 +6431,23 @@ static int nft_setelem_catchall_insert(const struct net *net, static int nft_setelem_insert(const struct net *net, struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext, unsigned int flags) + struct nft_elem_priv **elem_priv, + unsigned int flags) { int ret; if (flags & NFT_SET_ELEM_CATCHALL) - ret = nft_setelem_catchall_insert(net, set, elem, ext); + ret = nft_setelem_catchall_insert(net, set, elem, elem_priv); else - ret = set->ops->insert(net, set, elem, ext); + ret = set->ops->insert(net, set, elem, elem_priv); return ret; } static bool nft_setelem_is_catchall(const struct nft_set *set, - const struct nft_set_elem *elem) + const struct nft_elem_priv *elem_priv) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_CATCHALL) @@ -6399,14 +6457,14 @@ static bool nft_setelem_is_catchall(const struct nft_set *set, } static void nft_setelem_activate(struct net *net, struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); - if (nft_setelem_is_catchall(set, elem)) { + if (nft_setelem_is_catchall(set, elem_priv)) { nft_set_elem_change_active(net, set, ext); } else { - set->ops->activate(net, set, elem); + set->ops->activate(net, set, elem_priv); } } @@ -6464,12 +6522,12 @@ static int nft_setelem_deactivate(const struct net *net, static void nft_setelem_catchall_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_set_elem_catchall *catchall, *next; list_for_each_entry_safe(catchall, next, &set->catchall_list, list) { - if (catchall->elem == elem->priv) { + if (catchall->elem == elem_priv) { list_del_rcu(&catchall->list); kfree_rcu(catchall, rcu); break; @@ -6479,12 +6537,12 @@ static void nft_setelem_catchall_remove(const struct net *net, static void nft_setelem_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - if (nft_setelem_is_catchall(set, elem)) - nft_setelem_catchall_remove(net, set, elem); + if (nft_setelem_is_catchall(set, elem_priv)) + nft_setelem_catchall_remove(net, set, elem_priv); else - set->ops->remove(net, set, elem); + set->ops->remove(net, set, elem_priv); } static bool nft_setelem_valid_key_end(const struct nft_set *set, @@ -6517,13 +6575,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, struct nft_set_ext *ext, *ext2; struct nft_set_elem elem; struct nft_set_binding *binding; + struct nft_elem_priv *elem_priv; struct nft_object *obj = NULL; struct nft_userdata *udata; struct nft_data_desc desc; enum nft_registers dreg; struct nft_trans *trans; - u64 timeout; u64 expiration; + u64 timeout; int err, i; u8 ulen; @@ -6816,9 +6875,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ext->genmask = nft_genmask_cur(ctx->net); - err = nft_setelem_insert(ctx->net, set, &elem, &ext2, flags); + err = nft_setelem_insert(ctx->net, set, &elem, &elem_priv, flags); if (err) { if (err == -EEXIST) { + ext2 = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) ^ nft_set_ext_exists(ext2, NFT_SET_EXT_DATA) || nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) ^ @@ -6852,12 +6912,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, } } - nft_trans_elem(trans) = elem; + nft_trans_elem_priv(trans) = elem.priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; err_set_full: - nft_setelem_remove(ctx->net, set, &elem); + nft_setelem_remove(ctx->net, set, elem.priv); err_element_clash: kfree(trans); err_elem_free: @@ -6958,9 +7018,9 @@ void nft_data_hold(const struct nft_data *data, enum nft_data_types type) static void nft_setelem_data_activate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_hold(nft_set_ext_data(ext), set->dtype); @@ -6970,9 +7030,9 @@ static void nft_setelem_data_activate(const struct net *net, void nft_setelem_data_deactivate(const struct net *net, const struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA)) nft_data_release(nft_set_ext_data(ext), set->dtype); @@ -7057,9 +7117,9 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto fail_ops; - nft_setelem_data_deactivate(ctx->net, set, &elem); + nft_setelem_data_deactivate(ctx->net, set, elem.priv); - nft_trans_elem(trans) = elem; + nft_trans_elem_priv(trans) = elem.priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7077,36 +7137,29 @@ fail_elem: static int nft_setelem_flush(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_trans *trans; - int err; trans = nft_trans_alloc_gfp(ctx, NFT_MSG_DELSETELEM, sizeof(struct nft_trans_elem), GFP_ATOMIC); if (!trans) return -ENOMEM; - if (!set->ops->flush(ctx->net, set, elem->priv)) { - err = -ENOENT; - goto err1; - } + set->ops->flush(ctx->net, set, elem_priv); set->ndeact++; - nft_setelem_data_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; - nft_trans_elem(trans) = *elem; + nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; -err1: - kfree(trans); - return err; } static int __nft_set_catchall_flush(const struct nft_ctx *ctx, struct nft_set *set, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_trans *trans; @@ -7115,9 +7168,9 @@ static int __nft_set_catchall_flush(const struct nft_ctx *ctx, if (!trans) return -ENOMEM; - nft_setelem_data_deactivate(ctx->net, set, elem); + nft_setelem_data_deactivate(ctx->net, set, elem_priv); nft_trans_elem_set(trans) = set; - nft_trans_elem(trans) = *elem; + nft_trans_elem_priv(trans) = elem_priv; nft_trans_commit_list_add_tail(ctx->net, trans); return 0; @@ -7128,7 +7181,6 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, { u8 genmask = nft_genmask_next(ctx->net); struct nft_set_elem_catchall *catchall; - struct nft_set_elem elem; struct nft_set_ext *ext; int ret = 0; @@ -7137,8 +7189,7 @@ static int nft_set_catchall_flush(const struct nft_ctx *ctx, if (!nft_set_elem_active(ext, genmask)) continue; - elem.priv = catchall->elem; - ret = __nft_set_catchall_flush(ctx, set, &elem); + ret = __nft_set_catchall_flush(ctx, set, catchall->elem); if (ret < 0) break; nft_set_elem_change_active(ctx->net, set, ext); @@ -7605,25 +7656,35 @@ nla_put_failure: return -1; } -struct nft_obj_filter { +static void audit_log_obj_reset(const struct nft_table *table, + unsigned int base_seq, unsigned int nentries) +{ + char *buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, base_seq); + + audit_log_nfcfg(buf, table->family, nentries, + AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); + kfree(buf); +} + +struct nft_obj_dump_ctx { + unsigned int s_idx; char *table; u32 type; + bool reset; }; static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - const struct nft_table *table; - unsigned int idx = 0, s_idx = cb->args[0]; - struct nft_obj_filter *filter = cb->data; + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; + const struct nft_table *table; + unsigned int entries = 0; struct nft_object *obj; - bool reset = false; - - if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) - reset = true; + unsigned int idx = 0; + int rc = 0; rcu_read_lock(); nft_net = nft_pernet(net); @@ -7633,89 +7694,71 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) if (family != NFPROTO_UNSPEC && family != table->family) continue; + entries = 0; list_for_each_entry_rcu(obj, &table->objects, list) { if (!nft_is_active(net, obj)) goto cont; - if (idx < s_idx) + if (idx < ctx->s_idx) goto cont; - if (idx > s_idx) - memset(&cb->args[1], 0, - sizeof(cb->args) - sizeof(cb->args[0])); - if (filter && filter->table && - strcmp(filter->table, table->name)) + if (ctx->table && strcmp(ctx->table, table->name)) goto cont; - if (filter && - filter->type != NFT_OBJECT_UNSPEC && - obj->ops->type->type != filter->type) + if (ctx->type != NFT_OBJECT_UNSPEC && + obj->ops->type->type != ctx->type) goto cont; - if (reset) { - char *buf = kasprintf(GFP_ATOMIC, - "%s:%u", - table->name, - nft_net->base_seq); - - audit_log_nfcfg(buf, - family, - obj->handle, - AUDIT_NFT_OP_OBJ_RESET, - GFP_ATOMIC); - kfree(buf); - } - if (nf_tables_fill_obj_info(skb, net, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NFT_MSG_NEWOBJ, - NLM_F_MULTI | NLM_F_APPEND, - table->family, table, - obj, reset) < 0) - goto done; + rc = nf_tables_fill_obj_info(skb, net, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NFT_MSG_NEWOBJ, + NLM_F_MULTI | NLM_F_APPEND, + table->family, table, + obj, ctx->reset); + if (rc < 0) + break; + entries++; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } + if (ctx->reset && entries) + audit_log_obj_reset(table, nft_net->base_seq, entries); + if (rc < 0) + break; } -done: rcu_read_unlock(); - cb->args[0] = idx; + ctx->s_idx = idx; return skb->len; } static int nf_tables_dump_obj_start(struct netlink_callback *cb) { + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; - struct nft_obj_filter *filter = NULL; - if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx)); + + if (nla[NFTA_OBJ_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!ctx->table) return -ENOMEM; + } - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return -ENOMEM; - } - } + if (nla[NFTA_OBJ_TYPE]) + ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - } + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) + ctx->reset = true; - cb->data = filter; return 0; } static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; - if (filter) { - kfree(filter->table); - kfree(filter); - } + kfree(ctx->table); return 0; } @@ -7780,7 +7823,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, audit_log_nfcfg(buf, family, - obj->handle, + 1, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf); @@ -8974,7 +9017,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_rule_policy, }, [NFT_MSG_GETRULE_RESET] = { - .call = nf_tables_getrule, + .call = nf_tables_getrule_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, @@ -9224,7 +9267,7 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DESTROYSETELEM: nf_tables_set_elem_destroy(&trans->ctx, nft_trans_elem_set(trans), - nft_trans_elem(trans).priv); + nft_trans_elem_priv(trans)); break; case NFT_MSG_DELOBJ: case NFT_MSG_DESTROYOBJ: @@ -9453,16 +9496,12 @@ void nft_chain_del(struct nft_chain *chain) static void nft_trans_gc_setelem_remove(struct nft_ctx *ctx, struct nft_trans_gc *trans) { - void **priv = trans->priv; + struct nft_elem_priv **priv = trans->priv; unsigned int i; for (i = 0; i < trans->count; i++) { - struct nft_set_elem elem = { - .priv = priv[i], - }; - - nft_setelem_data_deactivate(ctx->net, trans->set, &elem); - nft_setelem_remove(ctx->net, trans->set, &elem); + nft_setelem_data_deactivate(ctx->net, trans->set, priv[i]); + nft_setelem_remove(ctx->net, trans->set, priv[i]); } } @@ -9475,7 +9514,7 @@ void nft_trans_gc_destroy(struct nft_trans_gc *trans) static void nft_trans_gc_trans_free(struct rcu_head *rcu) { - struct nft_set_elem elem = {}; + struct nft_elem_priv *elem_priv; struct nft_trans_gc *trans; struct nft_ctx ctx = {}; unsigned int i; @@ -9484,11 +9523,11 @@ static void nft_trans_gc_trans_free(struct rcu_head *rcu) ctx.net = read_pnet(&trans->set->net); for (i = 0; i < trans->count; i++) { - elem.priv = trans->priv[i]; - if (!nft_setelem_is_catchall(trans->set, &elem)) + elem_priv = trans->priv[i]; + if (!nft_setelem_is_catchall(trans->set, elem_priv)) atomic_dec(&trans->set->nelems); - nf_tables_set_elem_destroy(&ctx, trans->set, elem.priv); + nf_tables_set_elem_destroy(&ctx, trans->set, elem_priv); } nft_trans_gc_destroy(trans); @@ -10056,9 +10095,9 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) case NFT_MSG_NEWSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_activate(net, te->set, &te->elem); + nft_setelem_activate(net, te->set, te->elem_priv); nf_tables_setelem_notify(&trans->ctx, te->set, - &te->elem, + te->elem_priv, NFT_MSG_NEWSETELEM); if (te->set->ops->commit && list_empty(&te->set->pending_update)) { @@ -10072,10 +10111,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) te = (struct nft_trans_elem *)trans->data; nf_tables_setelem_notify(&trans->ctx, te->set, - &te->elem, + te->elem_priv, trans->msg_type); - nft_setelem_remove(net, te->set, &te->elem); - if (!nft_setelem_is_catchall(te->set, &te->elem)) { + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) { atomic_dec(&te->set->nelems); te->set->ndeact--; } @@ -10195,7 +10234,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) break; case NFT_MSG_NEWSETELEM: nft_set_elem_destroy(nft_trans_elem_set(trans), - nft_trans_elem(trans).priv, true); + nft_trans_elem_priv(trans), true); break; case NFT_MSG_NEWOBJ: nft_obj_destroy(&trans->ctx, nft_trans_obj(trans)); @@ -10342,8 +10381,8 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) break; } te = (struct nft_trans_elem *)trans->data; - nft_setelem_remove(net, te->set, &te->elem); - if (!nft_setelem_is_catchall(te->set, &te->elem)) + nft_setelem_remove(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) atomic_dec(&te->set->nelems); if (te->set->ops->abort && @@ -10356,9 +10395,9 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) case NFT_MSG_DESTROYSETELEM: te = (struct nft_trans_elem *)trans->data; - nft_setelem_data_activate(net, te->set, &te->elem); - nft_setelem_activate(net, te->set, &te->elem); - if (!nft_setelem_is_catchall(te->set, &te->elem)) + nft_setelem_data_activate(net, te->set, te->elem_priv); + nft_setelem_activate(net, te->set, te->elem_priv); + if (!nft_setelem_is_catchall(te->set, te->elem_priv)) te->set->ndeact--; if (te->set->ops->abort && @@ -10534,9 +10573,9 @@ static int nft_check_loops(const struct nft_ctx *ctx, static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx, struct nft_set *set, const struct nft_set_iter *iter, - struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + const struct nft_set_ext *ext = nft_set_elem_ext(set, elem_priv); if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 4d0ce12221f6..8b536d7ef6c2 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -115,7 +115,7 @@ static noinline void __nft_trace_verdict(const struct nft_pktinfo *pkt, { enum nft_trace_types type; - switch (regs->verdict.code) { + switch (regs->verdict.code & NF_VERDICT_MASK) { case NFT_CONTINUE: case NFT_RETURN: type = NFT_TRACETYPE_RETURN; @@ -308,10 +308,11 @@ next_rule: switch (regs.verdict.code & NF_VERDICT_MASK) { case NF_ACCEPT: - case NF_DROP: case NF_QUEUE: case NF_STOLEN: return regs.verdict.code; + case NF_DROP: + return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); } switch (regs.verdict.code) { @@ -342,6 +343,9 @@ next_rule: if (static_branch_unlikely(&nft_counters_enabled)) nft_update_chain_stats(basechain, pkt); + if (nft_base_chain(basechain)->policy == NF_DROP) + return NF_DROP_REASON(pkt->skb, SKB_DROP_REASON_NETFILTER_DROP, EPERM); + return nft_base_chain(basechain)->policy; } EXPORT_SYMBOL_GPL(nft_do_chain); diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 6d41c0bd3d78..a83637e3f455 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -258,17 +258,21 @@ void nft_trace_notify(const struct nft_pktinfo *pkt, case __NFT_TRACETYPE_MAX: break; case NFT_TRACETYPE_RETURN: - case NFT_TRACETYPE_RULE: + case NFT_TRACETYPE_RULE: { + unsigned int v; + if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, verdict)) goto nla_put_failure; /* pkt->skb undefined iff NF_STOLEN, disable dump */ - if (verdict->code == NF_STOLEN) + v = verdict->code & NF_VERDICT_MASK; + if (v == NF_STOLEN) info->packet_dumped = true; else mark = pkt->skb->mark; break; + } case NFT_TRACETYPE_POLICY: mark = pkt->skb->mark; diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 53c9e76473ba..f03f4d4d7d88 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -698,8 +698,8 @@ nfulnl_log_packet(struct net *net, unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; + enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; - enum ip_conntrack_info ctinfo; if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 556bc902af00..171d1f52d3dd 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -228,19 +228,22 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) static void nfqnl_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_ct_hook *ct_hook; - int err; if (verdict == NF_ACCEPT || verdict == NF_REPEAT || verdict == NF_STOP) { rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); - if (ct_hook) { - err = ct_hook->update(entry->state.net, entry->skb); - if (err < 0) - verdict = NF_DROP; - } + if (ct_hook) + verdict = ct_hook->update(entry->state.net, entry->skb); rcu_read_unlock(); + + switch (verdict & NF_VERDICT_MASK) { + case NF_STOLEN: + nf_queue_entry_free(entry); + return; + } + } nf_reinject(entry, verdict); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 5c5cc01c73c5..b18a79039125 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -44,33 +44,34 @@ static int nft_dynset_expr_setup(const struct nft_dynset *priv, return 0; } -static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, - struct nft_regs *regs) +static struct nft_elem_priv *nft_dynset_new(struct nft_set *set, + const struct nft_expr *expr, + struct nft_regs *regs) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set_ext *ext; + void *elem_priv; u64 timeout; - void *elem; if (!atomic_add_unless(&set->nelems, 1, set->size)) return NULL; timeout = priv->timeout ? : set->timeout; - elem = nft_set_elem_init(set, &priv->tmpl, - ®s->data[priv->sreg_key], NULL, - ®s->data[priv->sreg_data], - timeout, 0, GFP_ATOMIC); - if (IS_ERR(elem)) + elem_priv = nft_set_elem_init(set, &priv->tmpl, + ®s->data[priv->sreg_key], NULL, + ®s->data[priv->sreg_data], + timeout, 0, GFP_ATOMIC); + if (IS_ERR(elem_priv)) goto err1; - ext = nft_set_elem_ext(set, elem); + ext = nft_set_elem_ext(set, elem_priv); if (priv->num_exprs && nft_dynset_expr_setup(priv, ext) < 0) goto err2; - return elem; + return elem_priv; err2: - nft_set_elem_destroy(set, elem, false); + nft_set_elem_destroy(set, elem_priv, false); err1: if (set->size) atomic_dec(&set->nelems); diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 28e2873ba24e..928312d01eb1 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -298,6 +298,7 @@ static int nft_inner_init(const struct nft_ctx *ctx, int err; if (!tb[NFTA_INNER_FLAGS] || + !tb[NFTA_INNER_NUM] || !tb[NFTA_INNER_HDRSIZE] || !tb[NFTA_INNER_TYPE] || !tb[NFTA_INNER_EXPR]) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 120f6d395b98..0a689c8e0295 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -179,7 +179,7 @@ void nft_payload_eval(const struct nft_expr *expr, switch (priv->base) { case NFT_PAYLOAD_LL_HEADER: - if (!skb_mac_header_was_set(skb)) + if (!skb_mac_header_was_set(skb) || skb_mac_header_len(skb) == 0) goto err; if (skb_vlan_tag_present(skb) && diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 1e5e7a181e0b..32df7a16835d 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -13,6 +13,7 @@ #include <net/netfilter/nf_tables_core.h> struct nft_bitmap_elem { + struct nft_elem_priv priv; struct list_head head; struct nft_set_ext ext; }; @@ -104,8 +105,9 @@ nft_bitmap_elem_find(const struct nft_set *set, struct nft_bitmap_elem *this, return NULL; } -static void *nft_bitmap_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_bitmap_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { const struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -116,23 +118,23 @@ static void *nft_bitmap_get(const struct net *net, const struct nft_set *set, !nft_set_elem_active(&be->ext, genmask)) continue; - return be; + return &be->priv; } return ERR_PTR(-ENOENT); } static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { + struct nft_bitmap_elem *new = nft_elem_priv_cast(elem->priv), *be; struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *new = elem->priv, *be; u8 genmask = nft_genmask_next(net); u32 idx, off; be = nft_bitmap_elem_find(set, new, genmask); if (be) { - *ext = &be->ext; + *elem_priv = &be->priv; return -EEXIST; } @@ -144,12 +146,11 @@ static int nft_bitmap_insert(const struct net *net, const struct nft_set *set, return 0; } -static void nft_bitmap_remove(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_bitmap_remove(const struct net *net, const struct nft_set *set, + struct nft_elem_priv *elem_priv) { + struct nft_bitmap_elem *be = nft_elem_priv_cast(elem_priv); struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *be = elem->priv; u8 genmask = nft_genmask_next(net); u32 idx, off; @@ -161,10 +162,10 @@ static void nft_bitmap_remove(const struct net *net, static void nft_bitmap_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { + struct nft_bitmap_elem *be = nft_elem_priv_cast(elem_priv); struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *be = elem->priv; u8 genmask = nft_genmask_next(net); u32 idx, off; @@ -174,28 +175,27 @@ static void nft_bitmap_activate(const struct net *net, nft_set_elem_change_active(net, set, &be->ext); } -static bool nft_bitmap_flush(const struct net *net, - const struct nft_set *set, void *_be) +static void nft_bitmap_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { + struct nft_bitmap_elem *be = nft_elem_priv_cast(elem_priv); struct nft_bitmap *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); - struct nft_bitmap_elem *be = _be; u32 idx, off; nft_bitmap_location(set, nft_set_ext_key(&be->ext), &idx, &off); /* Enter 10 state, similar to deactivation. */ priv->bitmap[idx] &= ~(genmask << off); nft_set_elem_change_active(net, set, &be->ext); - - return true; } -static void *nft_bitmap_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_bitmap_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_bitmap_elem *this = nft_elem_priv_cast(elem->priv), *be; struct nft_bitmap *priv = nft_set_priv(set); - struct nft_bitmap_elem *this = elem->priv, *be; u8 genmask = nft_genmask_next(net); u32 idx, off; @@ -209,7 +209,7 @@ static void *nft_bitmap_deactivate(const struct net *net, priv->bitmap[idx] &= ~(genmask << off); nft_set_elem_change_active(net, set, &be->ext); - return be; + return &be->priv; } static void nft_bitmap_walk(const struct nft_ctx *ctx, @@ -218,7 +218,6 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, { const struct nft_bitmap *priv = nft_set_priv(set); struct nft_bitmap_elem *be; - struct nft_set_elem elem; list_for_each_entry_rcu(be, &priv->list, head) { if (iter->count < iter->skip) @@ -226,9 +225,7 @@ static void nft_bitmap_walk(const struct nft_ctx *ctx, if (!nft_set_elem_active(&be->ext, iter->genmask)) goto cont; - elem.priv = be; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &be->priv); if (iter->err < 0) return; @@ -265,6 +262,8 @@ static int nft_bitmap_init(const struct nft_set *set, { struct nft_bitmap *priv = nft_set_priv(set); + BUILD_BUG_ON(offsetof(struct nft_bitmap_elem, priv) != 0); + INIT_LIST_HEAD(&priv->list); priv->bitmap_size = nft_bitmap_size(set->klen); @@ -278,7 +277,7 @@ static void nft_bitmap_destroy(const struct nft_ctx *ctx, struct nft_bitmap_elem *be, *n; list_for_each_entry_safe(be, n, &priv->list, head) - nf_tables_set_elem_destroy(ctx, set, be); + nf_tables_set_elem_destroy(ctx, set, &be->priv); } static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 2013de934cef..6c2061bfdae6 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -27,6 +27,7 @@ struct nft_rhash { }; struct nft_rhash_elem { + struct nft_elem_priv priv; struct rhash_head node; struct nft_set_ext ext; }; @@ -95,8 +96,9 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set, return !!he; } -static void *nft_rhash_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_rhash_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he; @@ -108,13 +110,14 @@ static void *nft_rhash_get(const struct net *net, const struct nft_set *set, he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params); if (he != NULL) - return he; + return &he->priv; return ERR_PTR(-ENOENT); } static bool nft_rhash_update(struct nft_set *set, const u32 *key, - void *(*new)(struct nft_set *, + struct nft_elem_priv * + (*new)(struct nft_set *, const struct nft_expr *, struct nft_regs *regs), const struct nft_expr *expr, @@ -123,6 +126,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he, *prev; + struct nft_elem_priv *elem_priv; struct nft_rhash_cmp_arg arg = { .genmask = NFT_GENMASK_ANY, .set = set, @@ -133,10 +137,11 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, if (he != NULL) goto out; - he = new(set, expr, regs); - if (he == NULL) + elem_priv = new(set, expr, regs); + if (!elem_priv) goto err1; + he = nft_elem_priv_cast(elem_priv); prev = rhashtable_lookup_get_insert_key(&priv->ht, &arg, &he->node, nft_rhash_params); if (IS_ERR(prev)) @@ -144,7 +149,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, /* Another cpu may race to insert the element with the same key */ if (prev) { - nft_set_elem_destroy(set, he, true); + nft_set_elem_destroy(set, &he->priv, true); atomic_dec(&set->nelems); he = prev; } @@ -154,7 +159,7 @@ out: return true; err2: - nft_set_elem_destroy(set, he, true); + nft_set_elem_destroy(set, &he->priv, true); atomic_dec(&set->nelems); err1: return false; @@ -162,10 +167,10 @@ err1: static int nft_rhash_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { + struct nft_rhash_elem *he = nft_elem_priv_cast(elem->priv); struct nft_rhash *priv = nft_set_priv(set); - struct nft_rhash_elem *he = elem->priv; struct nft_rhash_cmp_arg arg = { .genmask = nft_genmask_next(net), .set = set, @@ -178,33 +183,32 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set, if (IS_ERR(prev)) return PTR_ERR(prev); if (prev) { - *ext = &prev->ext; + *elem_priv = &prev->priv; return -EEXIST; } return 0; } static void nft_rhash_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_rhash_elem *he = elem->priv; + struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); } -static bool nft_rhash_flush(const struct net *net, - const struct nft_set *set, void *priv) +static void nft_rhash_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_rhash_elem *he = priv; + struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); - - return true; } -static void *nft_rhash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_rhash_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he; @@ -221,15 +225,15 @@ static void *nft_rhash_deactivate(const struct net *net, rcu_read_unlock(); - return he; + return &he->priv; } static void nft_rhash_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { + struct nft_rhash_elem *he = nft_elem_priv_cast(elem_priv); struct nft_rhash *priv = nft_set_priv(set); - struct nft_rhash_elem *he = elem->priv; rhashtable_remove_fast(&priv->ht, &he->node, nft_rhash_params); } @@ -260,7 +264,6 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, struct nft_rhash *priv = nft_set_priv(set); struct nft_rhash_elem *he; struct rhashtable_iter hti; - struct nft_set_elem elem; rhashtable_walk_enter(&priv->ht, &hti); rhashtable_walk_start(&hti); @@ -280,9 +283,7 @@ static void nft_rhash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; - elem.priv = he; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) break; @@ -406,6 +407,8 @@ static int nft_rhash_init(const struct nft_set *set, struct rhashtable_params params = nft_rhash_params; int err; + BUILD_BUG_ON(offsetof(struct nft_rhash_elem, priv) != 0); + params.nelem_hint = desc->size ?: NFT_RHASH_ELEMENT_HINT; params.key_len = set->klen; @@ -428,8 +431,9 @@ struct nft_rhash_ctx { static void nft_rhash_elem_destroy(void *ptr, void *arg) { struct nft_rhash_ctx *rhash_ctx = arg; + struct nft_rhash_elem *he = ptr; - nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, ptr); + nf_tables_set_elem_destroy(&rhash_ctx->ctx, rhash_ctx->set, &he->priv); } static void nft_rhash_destroy(const struct nft_ctx *ctx, @@ -476,6 +480,7 @@ struct nft_hash { }; struct nft_hash_elem { + struct nft_elem_priv priv; struct hlist_node node; struct nft_set_ext ext; }; @@ -501,8 +506,9 @@ bool nft_hash_lookup(const struct net *net, const struct nft_set *set, return false; } -static void *nft_hash_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_hash_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_cur(net); @@ -514,7 +520,7 @@ static void *nft_hash_get(const struct net *net, const struct nft_set *set, hlist_for_each_entry_rcu(he, &priv->table[hash], node) { if (!memcmp(nft_set_ext_key(&he->ext), elem->key.val.data, set->klen) && nft_set_elem_active(&he->ext, genmask)) - return he; + return &he->priv; } return ERR_PTR(-ENOENT); } @@ -562,9 +568,9 @@ static u32 nft_jhash(const struct nft_set *set, const struct nft_hash *priv, static int nft_hash_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { - struct nft_hash_elem *this = elem->priv, *he; + struct nft_hash_elem *this = nft_elem_priv_cast(elem->priv), *he; struct nft_hash *priv = nft_set_priv(set); u8 genmask = nft_genmask_next(net); u32 hash; @@ -574,7 +580,7 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, if (!memcmp(nft_set_ext_key(&this->ext), nft_set_ext_key(&he->ext), set->klen) && nft_set_elem_active(&he->ext, genmask)) { - *ext = &he->ext; + *elem_priv = &he->priv; return -EEXIST; } } @@ -583,28 +589,28 @@ static int nft_hash_insert(const struct net *net, const struct nft_set *set, } static void nft_hash_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_hash_elem *he = elem->priv; + struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); } -static bool nft_hash_flush(const struct net *net, - const struct nft_set *set, void *priv) +static void nft_hash_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_hash_elem *he = priv; + struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &he->ext); - return true; } -static void *nft_hash_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_hash_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_hash_elem *this = nft_elem_priv_cast(elem->priv), *he; struct nft_hash *priv = nft_set_priv(set); - struct nft_hash_elem *this = elem->priv, *he; u8 genmask = nft_genmask_next(net); u32 hash; @@ -614,7 +620,7 @@ static void *nft_hash_deactivate(const struct net *net, set->klen) && nft_set_elem_active(&he->ext, genmask)) { nft_set_elem_change_active(net, set, &he->ext); - return he; + return &he->priv; } } return NULL; @@ -622,9 +628,9 @@ static void *nft_hash_deactivate(const struct net *net, static void nft_hash_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_hash_elem *he = elem->priv; + struct nft_hash_elem *he = nft_elem_priv_cast(elem_priv); hlist_del_rcu(&he->node); } @@ -634,7 +640,6 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, { struct nft_hash *priv = nft_set_priv(set); struct nft_hash_elem *he; - struct nft_set_elem elem; int i; for (i = 0; i < priv->buckets; i++) { @@ -644,9 +649,7 @@ static void nft_hash_walk(const struct nft_ctx *ctx, struct nft_set *set, if (!nft_set_elem_active(&he->ext, iter->genmask)) goto cont; - elem.priv = he; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &he->priv); if (iter->err < 0) return; cont: @@ -685,7 +688,7 @@ static void nft_hash_destroy(const struct nft_ctx *ctx, for (i = 0; i < priv->buckets; i++) { hlist_for_each_entry_safe(he, next, &priv->table[i], node) { hlist_del_rcu(&he->node); - nf_tables_set_elem_destroy(ctx, set, he); + nf_tables_set_elem_destroy(ctx, set, &he->priv); } } } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index c0dcc40de358..701977af3ee8 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -599,11 +599,18 @@ out: * @elem: nftables API element representation containing key data * @flags: Unused */ -static void *nft_pipapo_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_pipapo_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { - return pipapo_get(net, set, (const u8 *)elem->key.val.data, - nft_genmask_cur(net)); + static struct nft_pipapo_elem *e; + + e = pipapo_get(net, set, (const u8 *)elem->key.val.data, + nft_genmask_cur(net)); + if (IS_ERR(e)) + return ERR_CAST(e); + + return &e->priv; } /** @@ -1151,21 +1158,21 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, * @net: Network namespace * @set: nftables API set representation * @elem: nftables API element representation containing key data - * @ext2: Filled with pointer to &struct nft_set_ext in inserted element + * @elem_priv: Filled with pointer to &struct nft_set_ext in inserted element * * Return: 0 on success, error pointer on failure. */ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext2) + struct nft_elem_priv **elem_priv) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); union nft_pipapo_map_bucket rulemap[NFT_PIPAPO_MAX_FIELDS]; const u8 *start = (const u8 *)elem->key.val.data, *end; - struct nft_pipapo_elem *e = elem->priv, *dup; struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; u8 genmask = nft_genmask_next(net); + struct nft_pipapo_elem *e, *dup; struct nft_pipapo_field *f; const u8 *start_p, *end_p; int i, bsize_max, err = 0; @@ -1188,7 +1195,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (!memcmp(start, dup_key->data, sizeof(*dup_key->data)) && !memcmp(end, dup_end->data, sizeof(*dup_end->data))) { - *ext2 = &dup->ext; + *elem_priv = &dup->priv; return -EEXIST; } @@ -1203,7 +1210,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, if (PTR_ERR(dup) != -ENOENT) { if (IS_ERR(dup)) return PTR_ERR(dup); - *ext2 = &dup->ext; + *elem_priv = &dup->priv; return -ENOTEMPTY; } @@ -1263,7 +1270,8 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set, put_cpu_ptr(m->scratch); } - *ext2 = &e->ext; + e = nft_elem_priv_cast(elem->priv); + *elem_priv = &e->priv; pipapo_map(m, rulemap, e); @@ -1540,21 +1548,16 @@ static void nft_pipapo_gc_deactivate(struct net *net, struct nft_set *set, struct nft_pipapo_elem *e) { - struct nft_set_elem elem = { - .priv = e, - }; - - nft_setelem_data_deactivate(net, set, &elem); + nft_setelem_data_deactivate(net, set, &e->priv); } /** * pipapo_gc() - Drop expired entries from set, destroy start and end elements - * @_set: nftables API set representation + * @set: nftables API set representation * @m: Matching data */ -static void pipapo_gc(const struct nft_set *_set, struct nft_pipapo_match *m) +static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m) { - struct nft_set *set = (struct nft_set *) _set; struct nft_pipapo *priv = nft_set_priv(set); struct net *net = read_pnet(&set->net); int rules_f0, first_rule = 0; @@ -1672,7 +1675,7 @@ static void pipapo_reclaim_match(struct rcu_head *rcu) * We also need to create a new working copy for subsequent insertions and * deletions. */ -static void nft_pipapo_commit(const struct nft_set *set) +static void nft_pipapo_commit(struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *new_clone, *old; @@ -1732,7 +1735,7 @@ static void nft_pipapo_abort(const struct nft_set *set) * nft_pipapo_activate() - Mark element reference as active given key, commit * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @elem_priv: nftables API element representation containing key data * * On insertion, elements are added to a copy of the matching data currently * in use for lookups, and not directly inserted into current lookup data. Both @@ -1741,9 +1744,9 @@ static void nft_pipapo_abort(const struct nft_set *set) */ static void nft_pipapo_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_pipapo_elem *e = elem->priv; + struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &e->ext); } @@ -1783,9 +1786,9 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set, * * Return: deactivated element if found, NULL otherwise. */ -static void *nft_pipapo_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_pipapo_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); @@ -1796,7 +1799,7 @@ static void *nft_pipapo_deactivate(const struct net *net, * nft_pipapo_flush() - Call pipapo_deactivate() to make element inactive * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @elem_priv: nftables API element representation containing key data * * This is functionally the same as nft_pipapo_deactivate(), with a slightly * different interface, and it's also called once for each element in a set @@ -1810,13 +1813,12 @@ static void *nft_pipapo_deactivate(const struct net *net, * * Return: true if element was found and deactivated. */ -static bool nft_pipapo_flush(const struct net *net, const struct nft_set *set, - void *elem) +static void nft_pipapo_flush(const struct net *net, const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_pipapo_elem *e = elem; + struct nft_pipapo_elem *e = nft_elem_priv_cast(elem_priv); - return pipapo_deactivate(net, set, (const u8 *)nft_set_ext_key(&e->ext), - &e->ext); + nft_set_elem_change_active(net, set, &e->ext); } /** @@ -1939,7 +1941,7 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, * nft_pipapo_remove() - Remove element given key, commit * @net: Network namespace * @set: nftables API set representation - * @elem: nftables API element representation containing key data + * @elem_priv: nftables API element representation containing key data * * Similarly to nft_pipapo_activate(), this is used as commit operation by the * API, but it's called once per element in the pending transaction, so we can't @@ -1947,14 +1949,15 @@ static bool pipapo_match_field(struct nft_pipapo_field *f, * the matched element here, if any, and commit the updated matching data. */ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m = priv->clone; - struct nft_pipapo_elem *e = elem->priv; int rules_f0, first_rule = 0; + struct nft_pipapo_elem *e; const u8 *data; + e = nft_elem_priv_cast(elem_priv); data = (const u8 *)nft_set_ext_key(&e->ext); while ((rules_f0 = pipapo_rules_same_key(m->f, first_rule))) { @@ -2031,7 +2034,6 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, for (r = 0; r < f->rules; r++) { struct nft_pipapo_elem *e; - struct nft_set_elem elem; if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) continue; @@ -2041,9 +2043,7 @@ static void nft_pipapo_walk(const struct nft_ctx *ctx, struct nft_set *set, e = f->mt[r].e; - elem.priv = e; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &e->priv); if (iter->err < 0) goto out; @@ -2115,6 +2115,8 @@ static int nft_pipapo_init(const struct nft_set *set, struct nft_pipapo_field *f; int err, i, field_count; + BUILD_BUG_ON(offsetof(struct nft_pipapo_elem, priv) != 0); + field_count = desc->field_count ? : 1; if (field_count > NFT_PIPAPO_MAX_FIELDS) @@ -2209,7 +2211,7 @@ static void nft_set_pipapo_match_destroy(const struct nft_ctx *ctx, e = f->mt[r].e; - nf_tables_set_elem_destroy(ctx, set, e); + nf_tables_set_elem_destroy(ctx, set, &e->priv); } } diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index 25a75591583e..1040223da5fa 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -147,7 +147,7 @@ struct nft_pipapo_match { unsigned long * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; - struct nft_pipapo_field f[]; + struct nft_pipapo_field f[] __counted_by(field_count); }; /** @@ -170,10 +170,12 @@ struct nft_pipapo_elem; /** * struct nft_pipapo_elem - API-facing representation of single set element + * @priv: element placeholder * @ext: nftables API extensions */ struct nft_pipapo_elem { - struct nft_set_ext ext; + struct nft_elem_priv priv; + struct nft_set_ext ext; }; int pipapo_refill(unsigned long *map, int len, int rules, unsigned long *dst, diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 2660ceab3759..6f1186abd47b 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -19,10 +19,11 @@ struct nft_rbtree { struct rb_root root; rwlock_t lock; seqcount_rwlock_t count; - struct delayed_work gc_work; + unsigned long last_gc; }; struct nft_rbtree_elem { + struct nft_elem_priv priv; struct rb_node node; struct nft_set_ext ext; }; @@ -48,8 +49,7 @@ static int nft_rbtree_cmp(const struct nft_set *set, static bool nft_rbtree_elem_expired(const struct nft_rbtree_elem *rbe) { - return nft_set_elem_expired(&rbe->ext) || - nft_set_elem_is_dead(&rbe->ext); + return nft_set_elem_expired(&rbe->ext); } static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set, @@ -197,8 +197,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, return false; } -static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem, unsigned int flags) +static struct nft_elem_priv * +nft_rbtree_get(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem, unsigned int flags) { struct nft_rbtree *priv = nft_set_priv(set); unsigned int seq = read_seqcount_begin(&priv->count); @@ -209,27 +210,25 @@ static void *nft_rbtree_get(const struct net *net, const struct nft_set *set, ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); if (ret || !read_seqcount_retry(&priv->count, seq)) - return rbe; + return &rbe->priv; read_lock_bh(&priv->lock); seq = read_seqcount_begin(&priv->count); ret = __nft_rbtree_get(net, set, key, &rbe, seq, flags, genmask); - if (!ret) - rbe = ERR_PTR(-ENOENT); read_unlock_bh(&priv->lock); - return rbe; + if (!ret) + return ERR_PTR(-ENOENT); + + return &rbe->priv; } -static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, - struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe) +static void nft_rbtree_gc_elem_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) { - struct nft_set_elem elem = { - .priv = rbe, - }; - - nft_setelem_data_deactivate(net, set, &elem); + lockdep_assert_held_write(&priv->lock); + nft_setelem_data_deactivate(net, set, &rbe->priv); rb_erase(&rbe->node, &priv->root); } @@ -263,7 +262,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, rbe_prev = NULL; if (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); - nft_rbtree_gc_remove(net, set, priv, rbe_prev); + nft_rbtree_gc_elem_remove(net, set, priv, rbe_prev); /* There is always room in this trans gc for this element, * memory allocation never actually happens, hence, the warning @@ -277,7 +276,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, nft_trans_gc_elem_add(gc, rbe_prev); } - nft_rbtree_gc_remove(net, set, priv, rbe); + nft_rbtree_gc_elem_remove(net, set, priv, rbe); gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC); if (WARN_ON_ONCE(!gc)) return ERR_PTR(-ENOMEM); @@ -307,7 +306,7 @@ static bool nft_rbtree_update_first(const struct nft_set *set, static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, struct nft_rbtree_elem *new, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { struct nft_rbtree_elem *rbe, *rbe_le = NULL, *rbe_ge = NULL; struct rb_node *node, *next, *parent, **p, *first = NULL; @@ -424,7 +423,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (rbe_ge && !nft_rbtree_cmp(set, new, rbe_ge) && nft_rbtree_interval_start(rbe_ge) == nft_rbtree_interval_start(new)) { - *ext = &rbe_ge->ext; + *elem_priv = &rbe_ge->priv; return -EEXIST; } @@ -433,7 +432,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, */ if (rbe_le && !nft_rbtree_cmp(set, new, rbe_le) && nft_rbtree_interval_end(rbe_le) == nft_rbtree_interval_end(new)) { - *ext = &rbe_le->ext; + *elem_priv = &rbe_le->priv; return -EEXIST; } @@ -485,10 +484,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, const struct nft_set_elem *elem, - struct nft_set_ext **ext) + struct nft_elem_priv **elem_priv) { + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem->priv); struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe = elem->priv; int err; do { @@ -499,7 +498,7 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); - err = __nft_rbtree_insert(net, set, rbe, ext); + err = __nft_rbtree_insert(net, set, rbe, elem_priv); write_seqcount_end(&priv->count); write_unlock_bh(&priv->lock); } while (err == -EAGAIN); @@ -507,13 +506,8 @@ static int nft_rbtree_insert(const struct net *net, const struct nft_set *set, return err; } -static void nft_rbtree_remove(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static void nft_rbtree_erase(struct nft_rbtree *priv, struct nft_rbtree_elem *rbe) { - struct nft_rbtree *priv = nft_set_priv(set); - struct nft_rbtree_elem *rbe = elem->priv; - write_lock_bh(&priv->lock); write_seqcount_begin(&priv->count); rb_erase(&rbe->node, &priv->root); @@ -521,32 +515,41 @@ static void nft_rbtree_remove(const struct net *net, write_unlock_bh(&priv->lock); } +static void nft_rbtree_remove(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) +{ + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); + struct nft_rbtree *priv = nft_set_priv(set); + + nft_rbtree_erase(priv, rbe); +} + static void nft_rbtree_activate(const struct net *net, const struct nft_set *set, - const struct nft_set_elem *elem) + struct nft_elem_priv *elem_priv) { - struct nft_rbtree_elem *rbe = elem->priv; + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); } -static bool nft_rbtree_flush(const struct net *net, - const struct nft_set *set, void *priv) +static void nft_rbtree_flush(const struct net *net, + const struct nft_set *set, + struct nft_elem_priv *elem_priv) { - struct nft_rbtree_elem *rbe = priv; + struct nft_rbtree_elem *rbe = nft_elem_priv_cast(elem_priv); nft_set_elem_change_active(net, set, &rbe->ext); - - return true; } -static void *nft_rbtree_deactivate(const struct net *net, - const struct nft_set *set, - const struct nft_set_elem *elem) +static struct nft_elem_priv * +nft_rbtree_deactivate(const struct net *net, const struct nft_set *set, + const struct nft_set_elem *elem) { + struct nft_rbtree_elem *rbe, *this = nft_elem_priv_cast(elem->priv); const struct nft_rbtree *priv = nft_set_priv(set); const struct rb_node *parent = priv->root.rb_node; - struct nft_rbtree_elem *rbe, *this = elem->priv; u8 genmask = nft_genmask_next(net); int d; @@ -568,12 +571,14 @@ static void *nft_rbtree_deactivate(const struct net *net, nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; + } else if (nft_set_elem_expired(&rbe->ext)) { + break; } else if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = parent->rb_left; continue; } - nft_rbtree_flush(net, set, rbe); - return rbe; + nft_rbtree_flush(net, set, &rbe->priv); + return &rbe->priv; } } return NULL; @@ -585,7 +590,6 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, { struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe; - struct nft_set_elem elem; struct rb_node *node; read_lock_bh(&priv->lock); @@ -597,9 +601,7 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; - elem.priv = rbe; - - iter->err = iter->fn(ctx, set, iter, &elem); + iter->err = iter->fn(ctx, set, iter, &rbe->priv); if (iter->err < 0) { read_unlock_bh(&priv->lock); return; @@ -610,45 +612,36 @@ cont: read_unlock_bh(&priv->lock); } -static void nft_rbtree_gc(struct work_struct *work) +static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, + struct nft_rbtree *priv, + struct nft_rbtree_elem *rbe) { + nft_setelem_data_deactivate(net, set, &rbe->priv); + nft_rbtree_erase(priv, rbe); +} + +static void nft_rbtree_gc(struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); struct nft_rbtree_elem *rbe, *rbe_end = NULL; struct nftables_pernet *nft_net; - struct nft_rbtree *priv; + struct rb_node *node, *next; struct nft_trans_gc *gc; - struct rb_node *node; - struct nft_set *set; - unsigned int gc_seq; struct net *net; - priv = container_of(work, struct nft_rbtree, gc_work.work); set = nft_set_container_of(priv); net = read_pnet(&set->net); nft_net = nft_pernet(net); - gc_seq = READ_ONCE(nft_net->gc_seq); - if (nft_set_gc_is_pending(set)) - goto done; - - gc = nft_trans_gc_alloc(set, gc_seq, GFP_KERNEL); + gc = nft_trans_gc_alloc(set, 0, GFP_KERNEL); if (!gc) - goto done; - - read_lock_bh(&priv->lock); - for (node = rb_first(&priv->root); node != NULL; node = rb_next(node)) { + return; - /* Ruleset has been updated, try later. */ - if (READ_ONCE(nft_net->gc_seq) != gc_seq) { - nft_trans_gc_destroy(gc); - gc = NULL; - goto try_later; - } + for (node = rb_first(&priv->root); node ; node = next) { + next = rb_next(node); rbe = rb_entry(node, struct nft_rbtree_elem, node); - if (nft_set_elem_is_dead(&rbe->ext)) - goto dead_elem; - /* elements are reversed in the rbtree for historical reasons, * from highest to lowest value, that is why end element is * always visited before the start element. @@ -660,37 +653,34 @@ static void nft_rbtree_gc(struct work_struct *work) if (!nft_set_elem_expired(&rbe->ext)) continue; - nft_set_elem_dead(&rbe->ext); - - if (!rbe_end) - continue; - - nft_set_elem_dead(&rbe_end->ext); - - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; - nft_trans_gc_elem_add(gc, rbe_end); - rbe_end = NULL; -dead_elem: - gc = nft_trans_gc_queue_async(gc, gc_seq, GFP_ATOMIC); + /* end element needs to be removed first, it has + * no timeout extension. + */ + if (rbe_end) { + nft_rbtree_gc_remove(net, set, priv, rbe_end); + nft_trans_gc_elem_add(gc, rbe_end); + rbe_end = NULL; + } + + gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL); if (!gc) goto try_later; + nft_rbtree_gc_remove(net, set, priv, rbe); nft_trans_gc_elem_add(gc, rbe); } - gc = nft_trans_gc_catchall_async(gc, gc_seq); - try_later: - read_unlock_bh(&priv->lock); - if (gc) - nft_trans_gc_queue_async_done(gc); -done: - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); + if (gc) { + gc = nft_trans_gc_catchall_sync(gc); + nft_trans_gc_queue_sync_done(gc); + priv->last_gc = jiffies; + } } static u64 nft_rbtree_privsize(const struct nlattr * const nla[], @@ -705,15 +695,12 @@ static int nft_rbtree_init(const struct nft_set *set, { struct nft_rbtree *priv = nft_set_priv(set); + BUILD_BUG_ON(offsetof(struct nft_rbtree_elem, priv) != 0); + rwlock_init(&priv->lock); seqcount_rwlock_init(&priv->count, &priv->lock); priv->root = RB_ROOT; - INIT_DEFERRABLE_WORK(&priv->gc_work, nft_rbtree_gc); - if (set->flags & NFT_SET_TIMEOUT) - queue_delayed_work(system_power_efficient_wq, &priv->gc_work, - nft_set_gc_interval(set)); - return 0; } @@ -724,12 +711,10 @@ static void nft_rbtree_destroy(const struct nft_ctx *ctx, struct nft_rbtree_elem *rbe; struct rb_node *node; - cancel_delayed_work_sync(&priv->gc_work); - rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); - nf_tables_set_elem_destroy(ctx, set, rbe); + nf_tables_set_elem_destroy(ctx, set, &rbe->priv); } } @@ -751,6 +736,21 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } +static void nft_rbtree_commit(struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + + if (time_after_eq(jiffies, priv->last_gc + nft_set_gc_interval(set))) + nft_rbtree_gc(set); +} + +static void nft_rbtree_gc_init(const struct nft_set *set) +{ + struct nft_rbtree *priv = nft_set_priv(set); + + priv->last_gc = jiffies; +} + const struct nft_set_type nft_set_rbtree_type = { .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { @@ -764,6 +764,8 @@ const struct nft_set_type nft_set_rbtree_type = { .deactivate = nft_rbtree_deactivate, .flush = nft_rbtree_flush, .activate = nft_rbtree_activate, + .commit = nft_rbtree_commit, + .gc_init = nft_rbtree_gc_init, .lookup = nft_rbtree_lookup, .walk = nft_rbtree_walk, .get = nft_rbtree_get, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 8315d31b53db..92ef5ed2e7b0 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -225,7 +225,8 @@ static void genl_op_from_split(struct genl_op_iter *iter) } if (i + cnt < family->n_split_ops && - family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP) { + family->split_ops[i + cnt].flags & GENL_CMD_CAP_DUMP && + (!cnt || family->split_ops[i + cnt].cmd == iter->doit.cmd)) { iter->dumpit = family->split_ops[i + cnt]; genl_op_fill_in_reject_policy_split(family, &iter->dumpit); cnt++; diff --git a/net/netlink/policy.c b/net/netlink/policy.c index e2f111edf66c..1f8909c16f14 100644 --- a/net/netlink/policy.c +++ b/net/netlink/policy.c @@ -230,6 +230,8 @@ int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt) case NLA_S16: case NLA_S32: case NLA_S64: + case NLA_SINT: + case NLA_UINT: /* maximum is common, u64 min/max with padding */ return common + 2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64))); @@ -288,6 +290,7 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, case NLA_U16: case NLA_U32: case NLA_U64: + case NLA_UINT: case NLA_MSECS: { struct netlink_range_validation range; @@ -297,8 +300,10 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, type = NL_ATTR_TYPE_U16; else if (pt->type == NLA_U32) type = NL_ATTR_TYPE_U32; - else + else if (pt->type == NLA_U64) type = NL_ATTR_TYPE_U64; + else + type = NL_ATTR_TYPE_UINT; if (pt->validation_type == NLA_VALIDATE_MASK) { if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MASK, @@ -320,7 +325,8 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, case NLA_S8: case NLA_S16: case NLA_S32: - case NLA_S64: { + case NLA_S64: + case NLA_SINT: { struct netlink_range_validation_signed range; if (pt->type == NLA_S8) @@ -329,8 +335,10 @@ __netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state, type = NL_ATTR_TYPE_S16; else if (pt->type == NLA_S32) type = NL_ATTR_TYPE_S32; - else + else if (pt->type == NLA_S64) type = NL_ATTR_TYPE_S64; + else + type = NL_ATTR_TYPE_SINT; nla_get_range_signed(pt, &range); diff --git a/net/nfc/nci/spi.c b/net/nfc/nci/spi.c index 0935527d1d12..b68150c971d0 100644 --- a/net/nfc/nci/spi.c +++ b/net/nfc/nci/spi.c @@ -151,6 +151,8 @@ static int send_acknowledge(struct nci_spi *nspi, u8 acknowledge) int ret; skb = nci_skb_alloc(nspi->ndev, 0, GFP_KERNEL); + if (!skb) + return -ENOMEM; /* add the NCI SPI header to the start of the buffer */ hdr = skb_push(skb, NCI_SPI_HDR_LEN); diff --git a/net/rfkill/core.c b/net/rfkill/core.c index 08630896b6c8..14cc8fe8584b 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1180,7 +1180,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) init_waitqueue_head(&data->read_wait); mutex_lock(&rfkill_global_mutex); - mutex_lock(&data->mtx); /* * start getting events from elsewhere but hold mtx to get * startup events added first @@ -1192,10 +1191,11 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) goto free; rfkill_sync(rfkill); rfkill_fill_event(&ev->ev, rfkill, RFKILL_OP_ADD); + mutex_lock(&data->mtx); list_add_tail(&ev->list, &data->events); + mutex_unlock(&data->mtx); } list_add(&data->list, &rfkill_fds); - mutex_unlock(&data->mtx); mutex_unlock(&rfkill_global_mutex); file->private_data = data; @@ -1203,7 +1203,6 @@ static int rfkill_fop_open(struct inode *inode, struct file *file) return stream_open(inode, file); free: - mutex_unlock(&data->mtx); mutex_unlock(&rfkill_global_mutex); mutex_destroy(&data->mtx); list_for_each_entry_safe(ev, tmp, &data->events, list) diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c index e9d1b2f2ff0a..5a81505fba9a 100644 --- a/net/rfkill/rfkill-gpio.c +++ b/net/rfkill/rfkill-gpio.c @@ -108,13 +108,13 @@ static int rfkill_gpio_probe(struct platform_device *pdev) rfkill->clk = devm_clk_get(&pdev->dev, NULL); - gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "reset", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); rfkill->reset_gpio = gpio; - gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_OUT_LOW); + gpio = devm_gpiod_get_optional(&pdev->dev, "shutdown", GPIOD_ASIS); if (IS_ERR(gpio)) return PTR_ERR(gpio); diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 7c652d14528b..9583645e86c2 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -278,7 +278,16 @@ err_nat: return err; } +static bool tcf_ct_flow_is_outdated(const struct flow_offload *flow) +{ + return test_bit(IPS_SEEN_REPLY_BIT, &flow->ct->status) && + test_bit(IPS_HW_OFFLOAD_BIT, &flow->ct->status) && + !test_bit(NF_FLOW_HW_PENDING, &flow->flags) && + !test_bit(NF_FLOW_HW_ESTABLISHED, &flow->flags); +} + static struct nf_flowtable_type flowtable_ct = { + .gc = tcf_ct_flow_is_outdated, .action = tcf_ct_flow_table_fill_actions, .owner = THIS_MODULE, }; @@ -690,7 +699,6 @@ static struct tc_action_ops act_ct_ops; struct tc_ct_action_net { struct tc_action_net tn; /* Must be first */ - bool labels; }; /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ @@ -829,8 +837,13 @@ static void tcf_ct_params_free(struct tcf_ct_params *params) } if (params->ct_ft) tcf_ct_flow_table_put(params->ct_ft); - if (params->tmpl) + if (params->tmpl) { + if (params->put_labels) + nf_connlabels_put(nf_ct_net(params->tmpl)); + nf_ct_put(params->tmpl); + } + kfree(params); } @@ -1154,9 +1167,9 @@ static int tcf_ct_fill_params(struct net *net, struct nlattr **tb, struct netlink_ext_ack *extack) { - struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); struct nf_conntrack_zone zone; int err, family, proto, len; + bool put_labels = false; struct nf_conn *tmpl; char *name; @@ -1186,15 +1199,20 @@ static int tcf_ct_fill_params(struct net *net, } if (tb[TCA_CT_LABELS]) { + unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; + if (!IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS)) { NL_SET_ERR_MSG_MOD(extack, "Conntrack labels isn't enabled."); return -EOPNOTSUPP; } - if (!tn->labels) { + if (nf_connlabels_get(net, n_bits - 1)) { NL_SET_ERR_MSG_MOD(extack, "Failed to set connlabel length"); return -EOPNOTSUPP; + } else { + put_labels = true; } + tcf_ct_set_key_val(tb, p->labels, TCA_CT_LABELS, p->labels_mask, TCA_CT_LABELS_MASK, @@ -1238,10 +1256,15 @@ static int tcf_ct_fill_params(struct net *net, } } + p->put_labels = put_labels; + if (p->ct_action & TCA_CT_ACT_COMMIT) __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; err: + if (put_labels) + nf_connlabels_put(net); + nf_ct_put(p->tmpl); p->tmpl = NULL; return err; @@ -1542,32 +1565,13 @@ static struct tc_action_ops act_ct_ops = { static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = sizeof_field(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); - if (nf_connlabels_get(net, n_bits - 1)) { - tn->labels = false; - pr_err("act_ct: Failed to set connlabels length"); - } else { - tn->labels = true; - } - return tc_action_net_init(net, &tn->tn, &act_ct_ops); } static void __net_exit ct_exit_net(struct list_head *net_list) { - struct net *net; - - rtnl_lock(); - list_for_each_entry(net, net_list, exit_list) { - struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); - - if (tn->labels) - nf_connlabels_put(net); - } - rtnl_unlock(); - tc_action_net_exit(net_list, act_ct_ops.net_id); } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 8eacdb54e72f..0fd18c344ab5 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -383,6 +383,10 @@ static struct fq_flow *fq_classify(struct Qdisc *sch, struct sk_buff *skb, if (fq_fastpath_check(sch, skb, now)) { q->internal.stat_fastpath_packets++; + if (skb->sk == sk && q->rate_enable && + READ_ONCE(sk->sk_pacing_status) != SK_PACING_FQ) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); return &q->internal; } @@ -651,7 +655,7 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch) begin: head = fq_pband_head_select(pband); if (!head) { - while (++retry < FQ_BANDS) { + while (++retry <= FQ_BANDS) { if (++q->band_nr == FQ_BANDS) q->band_nr = 0; pband = &q->band_flows[q->band_nr]; @@ -893,7 +897,7 @@ static int fq_resize(struct Qdisc *sch, u32 log) return 0; } -static struct netlink_range_validation iq_range = { +static const struct netlink_range_validation iq_range = { .max = INT_MAX, }; diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 68e6acd0f130..5b595773e59b 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -202,7 +202,7 @@ out: return NET_XMIT_CN; } -static struct netlink_range_validation fq_pie_q_range = { +static const struct netlink_range_validation fq_pie_q_range = { .min = 1, .max = 1 << 20, }; diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 3554085bc2be..880c5f16b29c 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -902,6 +902,14 @@ hfsc_change_usc(struct hfsc_class *cl, struct tc_service_curve *usc, cl->cl_flags |= HFSC_USC; } +static void +hfsc_upgrade_rt(struct hfsc_class *cl) +{ + cl->cl_fsc = cl->cl_rsc; + rtsc_init(&cl->cl_virtual, &cl->cl_fsc, cl->cl_vt, cl->cl_total); + cl->cl_flags |= HFSC_FSC; +} + static const struct nla_policy hfsc_policy[TCA_HFSC_MAX + 1] = { [TCA_HFSC_RSC] = { .len = sizeof(struct tc_service_curve) }, [TCA_HFSC_FSC] = { .len = sizeof(struct tc_service_curve) }, @@ -1011,10 +1019,6 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, if (parent == NULL) return -ENOENT; } - if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { - NL_SET_ERR_MSG(extack, "Invalid parent - parent class must have FSC"); - return -EINVAL; - } if (classid == 0 || TC_H_MAJ(classid ^ sch->handle) != 0) return -EINVAL; @@ -1065,6 +1069,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid, cl->cf_tree = RB_ROOT; sch_tree_lock(sch); + /* Check if the inner class is a misconfigured 'rt' */ + if (!(parent->cl_flags & HFSC_FSC) && parent != &q->root) { + NL_SET_ERR_MSG(extack, + "Forced curve change on parent 'rt' to 'sc'"); + hfsc_upgrade_rt(parent); + } qdisc_class_hash_insert(&q->clhash, &cl->cl_common); list_add_tail(&cl->siblings, &parent->children); if (parent->level == 0) diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 546c10adcacd..28315166fe8e 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -213,7 +213,7 @@ static struct qfq_class *qfq_find_class(struct Qdisc *sch, u32 classid) return container_of(clc, struct qfq_class, common); } -static struct netlink_range_validation lmax_range = { +static const struct netlink_range_validation lmax_range = { .min = QFQ_MIN_LMAX, .max = QFQ_MAX_LMAX, }; @@ -1003,7 +1003,7 @@ static inline struct sk_buff *qfq_peek_skb(struct qfq_aggregate *agg, *cl = list_first_entry(&agg->active, struct qfq_class, alist); skb = (*cl)->qdisc->ops->peek((*cl)->qdisc); if (skb == NULL) - WARN_ONCE(1, "qfq_dequeue: non-workconserving leaf\n"); + qdisc_warn_nonwc("qfq_dequeue", (*cl)->qdisc); else *len = qdisc_pkt_len(skb); diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 1cb5e41c0ec7..2e1949de4171 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -1015,7 +1015,7 @@ static const struct nla_policy taprio_tc_policy[TCA_TAPRIO_TC_ENTRY_MAX + 1] = { TC_FP_PREEMPTIBLE), }; -static struct netlink_range_validation_signed taprio_cycle_time_range = { +static const struct netlink_range_validation_signed taprio_cycle_time_range = { .min = 0, .max = INT_MAX, }; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 297681601414..abd2667734d4 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1201,6 +1201,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, (struct smc_clc_msg_accept_confirm_v2 *)aclc; struct smc_clc_first_contact_ext *fce = smc_get_clc_first_contact_ext(clc_v2, false); + struct net *net = sock_net(&smc->sk); int rc; if (!ini->first_contact_peer || aclc->hdr.version == SMC_V1) @@ -1210,7 +1211,7 @@ static int smc_connect_rdma_v2_prepare(struct smc_sock *smc, memcpy(ini->smcrv2.nexthop_mac, &aclc->r0.lcl.mac, ETH_ALEN); ini->smcrv2.uses_gateway = false; } else { - if (smc_ib_find_route(smc->clcsock->sk->sk_rcv_saddr, + if (smc_ib_find_route(net, smc->clcsock->sk->sk_rcv_saddr, smc_ib_gid_to_ipv4(aclc->r0.lcl.gid), ini->smcrv2.nexthop_mac, &ini->smcrv2.uses_gateway)) @@ -2361,7 +2362,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc, smc_find_ism_store_rc(rc, ini); return (!rc) ? 0 : ini->rc; } - return SMC_CLC_DECL_NOSMCDEV; + return prfx_rc; } /* listen worker: finish RDMA setup */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 9b66d6aeeb1a..89981dbe46c9 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -193,7 +193,7 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport) return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE; } -int smc_ib_find_route(__be32 saddr, __be32 daddr, +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway) { struct neighbour *neigh = NULL; @@ -205,7 +205,7 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr, if (daddr == cpu_to_be32(INADDR_NONE)) goto out; - rt = ip_route_output_flow(&init_net, &fl4, NULL); + rt = ip_route_output_flow(net, &fl4, NULL); if (IS_ERR(rt)) goto out; if (rt->rt_uses_gateway && rt->rt_gw_family != AF_INET) @@ -235,6 +235,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev, if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP && smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) { struct in_device *in_dev = __in_dev_get_rcu(ndev); + struct net *net = dev_net(ndev); const struct in_ifaddr *ifa; bool subnet_match = false; @@ -248,7 +249,7 @@ static int smc_ib_determine_gid_rcu(const struct net_device *ndev, } if (!subnet_match) goto out; - if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr, + if (smcrv2->daddr && smc_ib_find_route(net, smcrv2->saddr, smcrv2->daddr, smcrv2->nexthop_mac, &smcrv2->uses_gateway)) diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h index 4df5f8c8a0a1..ef8ac2b7546d 100644 --- a/net/smc/smc_ib.h +++ b/net/smc/smc_ib.h @@ -112,7 +112,7 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk, int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport, unsigned short vlan_id, u8 gid[], u8 *sgid_index, struct smc_init_info_smcrv2 *smcrv2); -int smc_ib_find_route(__be32 saddr, __be32 daddr, +int smc_ib_find_route(struct net *net, __be32 saddr, __be32 daddr, u8 nexthop_mac[], u8 *uses_gateway); bool smc_ib_is_valid_local_systemid(void); int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/tls/tls.h b/net/tls/tls.h index 478b2c0060aa..762f424ff2d5 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -144,8 +144,7 @@ void tls_err_abort(struct sock *sk, int err); int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, - const struct tls_cipher_desc *cipher_desc, - int mode); + const struct tls_cipher_desc *cipher_desc); int tls_set_sw_offload(struct sock *sk, int tx); void tls_update_rx_zc_capable(struct tls_context *tls_ctx); void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index f01543557a60..bf8ed36b1ad6 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1099,7 +1099,7 @@ int tls_set_device_offload(struct sock *sk) goto release_netdev; } - rc = init_prot_info(prot, crypto_info, cipher_desc, TLS_HW); + rc = init_prot_info(prot, crypto_info, cipher_desc); if (rc) goto release_netdev; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index b125a08a618a..1c2c6800949d 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -140,8 +140,8 @@ void update_sk_prot(struct sock *sk, struct tls_context *ctx) int wait_on_pending_writer(struct sock *sk, long *timeo) { - int rc = 0; DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret, rc = 0; add_wait_queue(sk_sleep(sk), &wait); while (1) { @@ -155,9 +155,13 @@ int wait_on_pending_writer(struct sock *sk, long *timeo) break; } - if (sk_wait_event(sk, timeo, - !READ_ONCE(sk->sk_write_pending), &wait)) + ret = sk_wait_event(sk, timeo, + !READ_ONCE(sk->sk_write_pending), &wait); + if (ret) { + if (ret < 0) + rc = ret; break; + } } remove_wait_queue(sk_sleep(sk), &wait); return rc; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0f6da4ce3ed7..a78e8e722409 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1291,6 +1291,7 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); DEFINE_WAIT_FUNC(wait, woken_wake_function); + int ret = 0; long timeo; timeo = sock_rcvtimeo(sk, nonblock); @@ -1302,6 +1303,9 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, if (sk->sk_err) return sock_error(sk); + if (ret < 0) + return ret; + if (!skb_queue_empty(&sk->sk_receive_queue)) { tls_strp_check_rcv(&ctx->strp); if (tls_strp_msg_ready(ctx)) @@ -1320,10 +1324,10 @@ tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, released = true; add_wait_queue(sk_sleep(sk), &wait); sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); - sk_wait_event(sk, &timeo, - tls_strp_msg_ready(ctx) || - !sk_psock_queue_empty(psock), - &wait); + ret = sk_wait_event(sk, &timeo, + tls_strp_msg_ready(ctx) || + !sk_psock_queue_empty(psock), + &wait); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); remove_wait_queue(sk_sleep(sk), &wait); @@ -1852,6 +1856,7 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx, bool nonblock) { long timeo; + int ret; timeo = sock_rcvtimeo(sk, nonblock); @@ -1861,14 +1866,16 @@ static int tls_rx_reader_acquire(struct sock *sk, struct tls_sw_context_rx *ctx, ctx->reader_contended = 1; add_wait_queue(&ctx->wq, &wait); - sk_wait_event(sk, &timeo, - !READ_ONCE(ctx->reader_present), &wait); + ret = sk_wait_event(sk, &timeo, + !READ_ONCE(ctx->reader_present), &wait); remove_wait_queue(&ctx->wq, &wait); if (timeo <= 0) return -EAGAIN; if (signal_pending(current)) return sock_intr_errno(timeo); + if (ret < 0) + return ret; } WRITE_ONCE(ctx->reader_present, 1); @@ -2622,8 +2629,7 @@ static struct tls_sw_context_rx *init_ctx_rx(struct tls_context *ctx) int init_prot_info(struct tls_prot_info *prot, const struct tls_crypto_info *crypto_info, - const struct tls_cipher_desc *cipher_desc, - int mode) + const struct tls_cipher_desc *cipher_desc) { u16 nonce_size = cipher_desc->nonce; @@ -2636,11 +2642,6 @@ int init_prot_info(struct tls_prot_info *prot, prot->tail_size = 0; } - if (mode == TLS_HW) { - prot->aad_size = 0; - prot->tail_size = 0; - } - /* Sanity-check the sizes for stack allocations. */ if (nonce_size > TLS_MAX_IV_SIZE || prot->aad_size > TLS_MAX_AAD_SIZE) return -EINVAL; @@ -2700,7 +2701,7 @@ int tls_set_sw_offload(struct sock *sk, int tx) goto free_priv; } - rc = init_prot_info(prot, crypto_info, cipher_desc, TLS_SW); + rc = init_prot_info(prot, crypto_info, cipher_desc); if (rc) goto free_priv; diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index d324ae13e2f5..af5bab1acee1 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -636,6 +636,11 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) virtio_device_ready(vdev); + return 0; +} + +static void virtio_vsock_vqs_start(struct virtio_vsock *vsock) +{ mutex_lock(&vsock->tx_lock); vsock->tx_run = true; mutex_unlock(&vsock->tx_lock); @@ -650,7 +655,16 @@ static int virtio_vsock_vqs_init(struct virtio_vsock *vsock) vsock->event_run = true; mutex_unlock(&vsock->event_lock); - return 0; + /* virtio_transport_send_pkt() can queue packets once + * the_virtio_vsock is set, but they won't be processed until + * vsock->tx_run is set to true. We queue vsock->send_pkt_work + * when initialization finishes to send those packets queued + * earlier. + * We don't need to queue the other workers (rx, event) because + * as long as we don't fill the queues with empty buffers, the + * host can't send us any notification. + */ + queue_work(virtio_vsock_workqueue, &vsock->send_pkt_work); } static void virtio_vsock_vqs_del(struct virtio_vsock *vsock) @@ -749,6 +763,7 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->out_sgs[i] = &vsock->out_bufs[i]; rcu_assign_pointer(the_virtio_vsock, vsock); + virtio_vsock_vqs_start(vsock); mutex_unlock(&the_virtio_vsock_mutex); @@ -821,6 +836,7 @@ static int virtio_vsock_restore(struct virtio_device *vdev) goto out; rcu_assign_pointer(the_virtio_vsock, vsock); + virtio_vsock_vqs_start(vsock); out: mutex_unlock(&the_virtio_vsock_mutex); diff --git a/net/wireless/core.c b/net/wireless/core.c index 7df8ffcfa0c4..758c9a2a12c0 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1613,7 +1613,7 @@ void wiphy_work_queue(struct wiphy *wiphy, struct wiphy_work *work) list_add_tail(&work->entry, &rdev->wiphy_work_list); spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags); - schedule_work(&rdev->wiphy_work); + queue_work(system_unbound_wq, &rdev->wiphy_work); } EXPORT_SYMBOL_GPL(wiphy_work_queue); diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index f90f58c65688..bad9e4fd842f 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -43,10 +43,11 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, for (link_id = 0; link_id < ARRAY_SIZE(data->links); link_id++) { cr.links[link_id].status = data->links[link_id].status; + cr.links[link_id].bss = data->links[link_id].bss; + WARN_ON_ONCE(cr.links[link_id].status != WLAN_STATUS_SUCCESS && (!cr.ap_mld_addr || !cr.links[link_id].bss)); - cr.links[link_id].bss = data->links[link_id].bss; if (!cr.links[link_id].bss) continue; cr.links[link_id].bssid = data->links[link_id].bss->bssid; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 56fd7cf2563b..569234bc2be6 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -463,7 +463,7 @@ nl80211_sta_wme_policy[NL80211_STA_WME_MAX + 1] = { [NL80211_STA_WME_MAX_SP] = { .type = NLA_U8 }, }; -static struct netlink_range_validation nl80211_punct_bitmap_range = { +static const struct netlink_range_validation nl80211_punct_bitmap_range = { .min = 0, .max = 0xffff, }; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 6c2acd3fa36a..9e5ccffd6868 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2147,7 +2147,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy, if (!res) goto drop; - rdev_inform_bss(rdev, &res->pub, ies, data->drv_data); + rdev_inform_bss(rdev, &res->pub, ies, drv_data->drv_data); if (data->bss_source == BSS_SOURCE_MBSSID) { /* this is a nontransmitting bss, we need to add it to diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index f5e96e0d6e01..ae9f8cb611f6 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -33,6 +33,7 @@ #include "xsk.h" #define TX_BATCH_SIZE 32 +#define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE) static DEFINE_PER_CPU(struct list_head, xskmap_flush_list); @@ -391,6 +392,16 @@ void __xsk_map_flush(void) } } +#ifdef CONFIG_DEBUG_NET +bool xsk_map_check_flush(void) +{ + if (list_empty(this_cpu_ptr(&xskmap_flush_list))) + return false; + __xsk_map_flush(); + return true; +} +#endif + void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries) { xskq_prod_submit_n(pool->cq, nb_entries); @@ -413,16 +424,25 @@ EXPORT_SYMBOL(xsk_tx_release); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) { + bool budget_exhausted = false; struct xdp_sock *xs; rcu_read_lock(); +again: list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { + if (xs->tx_budget_spent >= MAX_PER_SOCKET_BUDGET) { + budget_exhausted = true; + continue; + } + if (!xskq_cons_peek_desc(xs->tx, desc, pool)) { if (xskq_has_descs(xs->tx)) xskq_cons_release(xs->tx); continue; } + xs->tx_budget_spent++; + /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement @@ -436,6 +456,14 @@ bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc) return true; } + if (budget_exhausted) { + list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) + xs->tx_budget_spent = 0; + + budget_exhausted = false; + goto again; + } + out: rcu_read_unlock(); return false; diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c index b86474084690..e21cc71095bb 100644 --- a/net/xfrm/xfrm_interface_core.c +++ b/net/xfrm/xfrm_interface_core.c @@ -380,8 +380,8 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err) skb->dev = dev; if (err) { - dev->stats.rx_errors++; - dev->stats.rx_dropped++; + DEV_STATS_INC(dev, rx_errors); + DEV_STATS_INC(dev, rx_dropped); return 0; } @@ -426,7 +426,6 @@ static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; @@ -473,7 +472,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) tdev = dst->dev; if (tdev == dev) { - stats->collisions++; + DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; @@ -512,13 +511,13 @@ xmit: if (net_xmit_eval(err) == 0) { dev_sw_netstats_tx_add(dev, 1, length); } else { - stats->tx_errors++; - stats->tx_aborted_errors++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_aborted_errors); } return 0; tx_err_link_failure: - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); @@ -528,7 +527,6 @@ tx_err_dst_release: static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); - struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -545,7 +543,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, dst); @@ -561,7 +559,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { - stats->tx_carrier_errors++; + DEV_STATS_INC(dev, tx_carrier_errors); goto tx_err; } skb_dst_set(skb, &rt->dst); @@ -580,8 +578,8 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; tx_err: - stats->tx_errors++; - stats->tx_dropped++; + DEV_STATS_INC(dev, tx_errors); + DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index c4c4fc29ccf5..5cdd3bca3637 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -851,7 +851,7 @@ static void xfrm_policy_inexact_list_reinsert(struct net *net, struct hlist_node *newpos = NULL; bool matches_s, matches_d; - if (!policy->bydst_reinsert) + if (policy->walk.dead || !policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); @@ -1256,8 +1256,11 @@ static void xfrm_hash_rebuild(struct work_struct *work) struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; + if (policy->walk.dead) + continue; + dir = xfrm_policy_id2dir(policy->index); - if (policy->walk.dead || dir >= XFRM_POLICY_MAX) + if (dir >= XFRM_POLICY_MAX) continue; if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { @@ -1372,8 +1375,6 @@ EXPORT_SYMBOL(xfrm_policy_hash_rebuild); * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { - static u32 idx_generator; - for (;;) { struct hlist_head *list; struct xfrm_policy *p; @@ -1381,8 +1382,8 @@ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) int found; if (!index) { - idx = (idx_generator | dir); - idx_generator += 8; + idx = (net->xfrm.idx_generator | dir); + net->xfrm.idx_generator += 8; } else { idx = index; index = 0; @@ -1823,9 +1824,11 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead) + continue; + dir = xfrm_policy_id2dir(pol->index); - if (pol->walk.dead || - dir >= XFRM_POLICY_MAX || + if (dir >= XFRM_POLICY_MAX || pol->type != type) continue; @@ -1862,9 +1865,11 @@ int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { + if (pol->walk.dead) + continue; + dir = xfrm_policy_id2dir(pol->index); - if (pol->walk.dead || - dir >= XFRM_POLICY_MAX || + if (dir >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; @@ -3215,7 +3220,7 @@ no_transform: } for (i = 0; i < num_pols; i++) - pols[i]->curlft.use_time = ktime_get_real_seconds(); + WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds()); if (num_xfrms < 0) { /* Prohibit the flow */ diff --git a/rust/Makefile b/rust/Makefile index 87958e864be0..7dbf9abe0d01 100644 --- a/rust/Makefile +++ b/rust/Makefile @@ -93,15 +93,14 @@ quiet_cmd_rustdoc = RUSTDOC $(if $(rustdoc_host),H, ) $< # and then retouch the generated files. rustdoc: rustdoc-core rustdoc-macros rustdoc-compiler_builtins \ rustdoc-alloc rustdoc-kernel - $(Q)cp $(srctree)/Documentation/images/logo.svg $(rustdoc_output) - $(Q)cp $(srctree)/Documentation/images/COPYING-logo $(rustdoc_output) + $(Q)cp $(srctree)/Documentation/images/logo.svg $(rustdoc_output)/static.files/ + $(Q)cp $(srctree)/Documentation/images/COPYING-logo $(rustdoc_output)/static.files/ $(Q)find $(rustdoc_output) -name '*.html' -type f -print0 | xargs -0 sed -Ei \ - -e 's:rust-logo\.svg:logo.svg:g' \ - -e 's:rust-logo\.png:logo.svg:g' \ - -e 's:favicon\.svg:logo.svg:g' \ - -e 's:<link rel="alternate icon" type="image/png" href="[./]*favicon-(16x16|32x32)\.png">::g' - $(Q)echo '.logo-container > img { object-fit: contain; }' \ - >> $(rustdoc_output)/rustdoc.css + -e 's:rust-logo-[0-9a-f]+\.svg:logo.svg:g' \ + -e 's:favicon-[0-9a-f]+\.svg:logo.svg:g' \ + -e 's:<link rel="alternate icon" type="image/png" href="[/.]+/static\.files/favicon-(16x16|32x32)-[0-9a-f]+\.png">::g' + $(Q)for f in $(rustdoc_output)/static.files/rustdoc-*.css; do \ + echo ".logo-container > img { object-fit: contain; }" >> $$f; done rustdoc-macros: private rustdoc_host = yes rustdoc-macros: private rustc_target_flags = --crate-type proc-macro \ @@ -290,6 +289,7 @@ bindgen_skip_c_flags := -mno-fp-ret-in-387 -mpreferred-stack-boundary=% \ -fno-reorder-blocks -fno-allow-store-data-races -fasan-shadow-offset=% \ -fzero-call-used-regs=% -fno-stack-clash-protection \ -fno-inline-functions-called-once -fsanitize=bounds-strict \ + -fstrict-flex-arrays=% \ --param=% --param asan-% # Derived from `scripts/Makefile.clang`. diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs index 05fcab6abfe6..032b64543953 100644 --- a/rust/kernel/error.rs +++ b/rust/kernel/error.rs @@ -37,7 +37,7 @@ pub mod code { declare_err!(E2BIG, "Argument list too long."); declare_err!(ENOEXEC, "Exec format error."); declare_err!(EBADF, "Bad file number."); - declare_err!(ECHILD, "Exec format error."); + declare_err!(ECHILD, "No child processes."); declare_err!(EAGAIN, "Try again."); declare_err!(ENOMEM, "Out of memory."); declare_err!(EACCES, "Permission denied."); @@ -133,7 +133,7 @@ impl Error { /// Returns the error encoded as a pointer. #[allow(dead_code)] pub(crate) fn to_ptr<T>(self) -> *mut T { - // SAFETY: self.0 is a valid error due to its invariant. + // SAFETY: `self.0` is a valid error due to its invariant. unsafe { bindings::ERR_PTR(self.0.into()) as *mut _ } } diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 90af76fa9dd8..933f6c3fe6b0 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -150,6 +150,9 @@ always-y += ibumad_kern.o always-y += hbm_out_kern.o always-y += hbm_edt_kern.o +TPROGS_CFLAGS = $(TPROGS_USER_CFLAGS) +TPROGS_LDFLAGS = $(TPROGS_USER_LDFLAGS) + ifeq ($(ARCH), arm) # Strip all except -D__LINUX_ARM_ARCH__ option needed to handle linux # headers when arm instruction set identification is requested. @@ -251,14 +254,15 @@ clean: $(LIBBPF): $(wildcard $(LIBBPF_SRC)/*.[ch] $(LIBBPF_SRC)/Makefile) | $(LIBBPF_OUTPUT) # Fix up variables inherited from Kbuild that tools/ build system won't like $(MAKE) -C $(LIBBPF_SRC) RM='rm -rf' EXTRA_CFLAGS="$(TPROGS_CFLAGS)" \ - LDFLAGS=$(TPROGS_LDFLAGS) srctree=$(BPF_SAMPLES_PATH)/../../ \ + LDFLAGS="$(TPROGS_LDFLAGS)" srctree=$(BPF_SAMPLES_PATH)/../../ \ O= OUTPUT=$(LIBBPF_OUTPUT)/ DESTDIR=$(LIBBPF_DESTDIR) prefix= \ $@ install_headers BPFTOOLDIR := $(TOOLS_PATH)/bpf/bpftool BPFTOOL_OUTPUT := $(abspath $(BPF_SAMPLES_PATH))/bpftool -BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool -$(BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) | $(BPFTOOL_OUTPUT) +DEFAULT_BPFTOOL := $(BPFTOOL_OUTPUT)/bootstrap/bpftool +BPFTOOL ?= $(DEFAULT_BPFTOOL) +$(DEFAULT_BPFTOOL): $(wildcard $(BPFTOOLDIR)/*.[ch] $(BPFTOOLDIR)/Makefile) | $(BPFTOOL_OUTPUT) $(MAKE) -C $(BPFTOOLDIR) srctree=$(BPF_SAMPLES_PATH)/../../ \ OUTPUT=$(BPFTOOL_OUTPUT)/ bootstrap @@ -316,7 +320,7 @@ XDP_SAMPLE_CFLAGS += -Wall -O2 \ -I$(LIBBPF_INCLUDE) \ -I$(src)/../../tools/testing/selftests/bpf -$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) +$(obj)/$(XDP_SAMPLE): TPROGS_CFLAGS = $(XDP_SAMPLE_CFLAGS) $(TPROGS_USER_CFLAGS) $(obj)/$(XDP_SAMPLE): $(src)/xdp_sample_user.h $(src)/xdp_sample_shared.h # Override includes for trace_helpers.o because __must_check won't be defined # in our include path. diff --git a/samples/bpf/syscall_tp_kern.c b/samples/bpf/syscall_tp_kern.c index 090fecfe641a..58fef969a60e 100644 --- a/samples/bpf/syscall_tp_kern.c +++ b/samples/bpf/syscall_tp_kern.c @@ -4,6 +4,7 @@ #include <uapi/linux/bpf.h> #include <bpf/bpf_helpers.h> +#if !defined(__aarch64__) struct syscalls_enter_open_args { unsigned long long unused; long syscall_nr; @@ -11,6 +12,7 @@ struct syscalls_enter_open_args { long flags; long mode; }; +#endif struct syscalls_exit_open_args { unsigned long long unused; @@ -18,6 +20,15 @@ struct syscalls_exit_open_args { long ret; }; +struct syscalls_enter_open_at_args { + unsigned long long unused; + long syscall_nr; + long long dfd; + long filename_ptr; + long flags; + long mode; +}; + struct { __uint(type, BPF_MAP_TYPE_ARRAY); __type(key, u32); @@ -54,14 +65,14 @@ int trace_enter_open(struct syscalls_enter_open_args *ctx) #endif SEC("tracepoint/syscalls/sys_enter_openat") -int trace_enter_open_at(struct syscalls_enter_open_args *ctx) +int trace_enter_open_at(struct syscalls_enter_open_at_args *ctx) { count(&enter_open_map); return 0; } SEC("tracepoint/syscalls/sys_enter_openat2") -int trace_enter_open_at2(struct syscalls_enter_open_args *ctx) +int trace_enter_open_at2(struct syscalls_enter_open_at_args *ctx) { count(&enter_open_map); return 0; diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 3eeecf67c17b..9677c09cf7a9 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -7078,6 +7078,24 @@ static void alc287_fixup_bind_dacs(struct hda_codec *codec, 0x0); /* Make sure 0x14 was disable */ } } +/* Fix none verb table of Headset Mic pin */ +static void alc_fixup_headset_mic(struct hda_codec *codec, + const struct hda_fixup *fix, int action) +{ + struct alc_spec *spec = codec->spec; + static const struct hda_pintbl pincfgs[] = { + { 0x19, 0x03a1103c }, + { } + }; + + switch (action) { + case HDA_FIXUP_ACT_PRE_PROBE: + snd_hda_apply_pincfgs(codec, pincfgs); + alc_update_coef_idx(codec, 0x45, 0xf<<12 | 1<<10, 5<<12); + spec->parse_flags |= HDA_PINCFG_HEADSET_MIC; + break; + } +} enum { @@ -7344,6 +7362,7 @@ enum { ALC245_FIXUP_HP_X360_MUTE_LEDS, ALC287_FIXUP_THINKPAD_I2S_SPK, ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD, + ALC2XX_FIXUP_HEADSET_MIC, }; /* A special fixup for Lenovo C940 and Yoga Duet 7; @@ -9448,6 +9467,10 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id = ALC287_FIXUP_CS35L41_I2C_2_THINKPAD_ACPI, }, + [ALC2XX_FIXUP_HEADSET_MIC] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_headset_mic, + }, }; static const struct snd_pci_quirk alc269_fixup_tbl[] = { @@ -9722,6 +9745,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x103c, 0x89c6, "Zbook Fury 17 G9", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED), SND_PCI_QUIRK(0x103c, 0x89ca, "HP", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), SND_PCI_QUIRK(0x103c, 0x89d3, "HP EliteBook 645 G9 (MB 89D2)", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF), + SND_PCI_QUIRK(0x103c, 0x8a20, "HP Laptop 15s-fq5xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2), SND_PCI_QUIRK(0x103c, 0x8a25, "HP Victus 16-d1xxx (MB 8A25)", ALC245_FIXUP_HP_MUTE_LED_COEFBIT), SND_PCI_QUIRK(0x103c, 0x8a78, "HP Dev One", ALC285_FIXUP_HP_LIMIT_INT_MIC_BOOST), SND_PCI_QUIRK(0x103c, 0x8aa0, "HP ProBook 440 G9 (MB 8A9E)", ALC236_FIXUP_HP_GPIO_LED), @@ -9791,6 +9815,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = { SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A), SND_PCI_QUIRK(0x1043, 0x1573, "ASUS GZ301V", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1662, "ASUS GV301QH", ALC294_FIXUP_ASUS_DUAL_SPK), + SND_PCI_QUIRK(0x1043, 0x1663, "ASUS GU603ZV", ALC285_FIXUP_ASUS_HEADSET_MIC), SND_PCI_QUIRK(0x1043, 0x1683, "ASUS UM3402YAR", ALC287_FIXUP_CS35L41_I2C_2), SND_PCI_QUIRK(0x1043, 0x16b2, "ASUS GU603", ALC289_FIXUP_ASUS_GA401), SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC), @@ -10750,6 +10775,8 @@ static const struct snd_hda_pin_quirk alc269_fallback_pin_fixup_tbl[] = { SND_HDA_PIN_QUIRK(0x10ec0274, 0x1028, "Dell", ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, {0x19, 0x40000000}, {0x1a, 0x40000000}), + SND_HDA_PIN_QUIRK(0x10ec0256, 0x1043, "ASUS", ALC2XX_FIXUP_HEADSET_MIC, + {0x19, 0x40000000}), {} }; diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c index f2e7c6d0be46..f9059780b7a7 100644 --- a/sound/soc/codecs/cs35l56.c +++ b/sound/soc/codecs/cs35l56.c @@ -706,7 +706,7 @@ static void cs35l56_patch(struct cs35l56_private *cs35l56) mutex_lock(&cs35l56->base.irq_lock); - init_completion(&cs35l56->init_completion); + reinit_completion(&cs35l56->init_completion); cs35l56->soft_resetting = true; cs35l56_system_reset(&cs35l56->base, !!cs35l56->sdw_peripheral); @@ -1186,6 +1186,12 @@ post_soft_reset: /* Registers could be dirty after soft reset or SoundWire enumeration */ regcache_sync(cs35l56->base.regmap); + /* Set ASP1 DOUT to high-impedance when it is not transmitting audio data. */ + ret = regmap_set_bits(cs35l56->base.regmap, CS35L56_ASP1_CONTROL3, + CS35L56_ASP1_DOUT_HIZ_CTRL_MASK); + if (ret) + return dev_err_probe(cs35l56->base.dev, ret, "Failed to write ASP1_CONTROL3\n"); + cs35l56->base.init_done = true; complete(&cs35l56->init_completion); diff --git a/sound/soc/codecs/cs42l42-sdw.c b/sound/soc/codecs/cs42l42-sdw.c index 974bae4abfad..94a66a325303 100644 --- a/sound/soc/codecs/cs42l42-sdw.c +++ b/sound/soc/codecs/cs42l42-sdw.c @@ -6,6 +6,7 @@ #include <linux/acpi.h> #include <linux/device.h> +#include <linux/gpio/consumer.h> #include <linux/iopoll.h> #include <linux/module.h> #include <linux/mod_devicetable.h> diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c index 92e37bc1df9d..9f5f1a92561d 100644 --- a/sound/soc/codecs/cs42l43-jack.c +++ b/sound/soc/codecs/cs42l43-jack.c @@ -34,7 +34,7 @@ static const unsigned int cs42l43_accdet_db_ms[] = { static const unsigned int cs42l43_accdet_ramp_ms[] = { 10, 40, 90, 170 }; static const unsigned int cs42l43_accdet_bias_sense[] = { - 14, 23, 41, 50, 60, 68, 86, 95, 0, + 14, 24, 43, 52, 61, 71, 90, 99, 0, }; static int cs42l43_find_index(struct cs42l43_codec *priv, const char * const prop, diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c index 581b334a6631..3bbe85091649 100644 --- a/sound/soc/codecs/da7219-aad.c +++ b/sound/soc/codecs/da7219-aad.c @@ -59,9 +59,6 @@ static void da7219_aad_btn_det_work(struct work_struct *work) bool micbias_up = false; int retries = 0; - /* Disable ground switch */ - snd_soc_component_update_bits(component, 0xFB, 0x01, 0x00); - /* Drive headphones/lineout */ snd_soc_component_update_bits(component, DA7219_HP_L_CTRL, DA7219_HP_L_AMP_OE_MASK, @@ -155,9 +152,6 @@ static void da7219_aad_hptest_work(struct work_struct *work) tonegen_freq_hptest = cpu_to_le16(DA7219_AAD_HPTEST_RAMP_FREQ_INT_OSC); } - /* Disable ground switch */ - snd_soc_component_update_bits(component, 0xFB, 0x01, 0x00); - /* Ensure gain ramping at fastest rate */ gain_ramp_ctrl = snd_soc_component_read(component, DA7219_GAIN_RAMP_CTRL); snd_soc_component_write(component, DA7219_GAIN_RAMP_CTRL, DA7219_GAIN_RAMP_RATE_X8); @@ -421,6 +415,11 @@ static irqreturn_t da7219_aad_irq_thread(int irq, void *data) * handle a removal, and we can check at the end of * hptest if we have a valid result or not. */ + + cancel_delayed_work_sync(&da7219_aad->jack_det_work); + /* Disable ground switch */ + snd_soc_component_update_bits(component, 0xFB, 0x01, 0x00); + if (statusa & DA7219_JACK_TYPE_STS_MASK) { report |= SND_JACK_HEADSET; mask |= SND_JACK_HEADSET | SND_JACK_LINEOUT; diff --git a/sound/soc/codecs/lpass-wsa-macro.c b/sound/soc/codecs/lpass-wsa-macro.c index ec6859ec0d38..fff4a8b862a7 100644 --- a/sound/soc/codecs/lpass-wsa-macro.c +++ b/sound/soc/codecs/lpass-wsa-macro.c @@ -1675,12 +1675,12 @@ static int wsa_macro_spk_boost_event(struct snd_soc_dapm_widget *w, u16 boost_path_ctl, boost_path_cfg1; u16 reg, reg_mix; - if (!strcmp(w->name, "WSA_RX INT0 CHAIN")) { + if (!snd_soc_dapm_widget_name_cmp(w, "WSA_RX INT0 CHAIN")) { boost_path_ctl = CDC_WSA_BOOST0_BOOST_PATH_CTL; boost_path_cfg1 = CDC_WSA_RX0_RX_PATH_CFG1; reg = CDC_WSA_RX0_RX_PATH_CTL; reg_mix = CDC_WSA_RX0_RX_PATH_MIX_CTL; - } else if (!strcmp(w->name, "WSA_RX INT1 CHAIN")) { + } else if (!snd_soc_dapm_widget_name_cmp(w, "WSA_RX INT1 CHAIN")) { boost_path_ctl = CDC_WSA_BOOST1_BOOST_PATH_CTL; boost_path_cfg1 = CDC_WSA_RX1_RX_PATH_CFG1; reg = CDC_WSA_RX1_RX_PATH_CTL; diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c index 1a137ca3f496..7938b52d741d 100644 --- a/sound/soc/codecs/rt5645.c +++ b/sound/soc/codecs/rt5645.c @@ -3257,6 +3257,8 @@ int rt5645_set_jack_detect(struct snd_soc_component *component, RT5645_GP1_PIN_IRQ, RT5645_GP1_PIN_IRQ); regmap_update_bits(rt5645->regmap, RT5645_GEN_CTRL1, RT5645_DIG_GATE_CTRL, RT5645_DIG_GATE_CTRL); + regmap_update_bits(rt5645->regmap, RT5645_DEPOP_M1, + RT5645_HP_CB_MASK, RT5645_HP_CB_PU); } rt5645_irq(0, rt5645); diff --git a/sound/soc/codecs/tas2780.c b/sound/soc/codecs/tas2780.c index 86bd6c18a944..41076be23854 100644 --- a/sound/soc/codecs/tas2780.c +++ b/sound/soc/codecs/tas2780.c @@ -39,7 +39,7 @@ static void tas2780_reset(struct tas2780_priv *tas2780) usleep_range(2000, 2050); } - snd_soc_component_write(tas2780->component, TAS2780_SW_RST, + ret = snd_soc_component_write(tas2780->component, TAS2780_SW_RST, TAS2780_RST); if (ret) dev_err(tas2780->dev, "%s:errCode:0x%x Reset error!\n", diff --git a/sound/soc/codecs/wcd938x-sdw.c b/sound/soc/codecs/wcd938x-sdw.c index 6951120057e5..a1f04010da95 100644 --- a/sound/soc/codecs/wcd938x-sdw.c +++ b/sound/soc/codecs/wcd938x-sdw.c @@ -1278,7 +1278,31 @@ static int wcd9380_probe(struct sdw_slave *pdev, pm_runtime_set_active(dev); pm_runtime_enable(dev); - return component_add(dev, &wcd938x_sdw_component_ops); + ret = component_add(dev, &wcd938x_sdw_component_ops); + if (ret) + goto err_disable_rpm; + + return 0; + +err_disable_rpm: + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_dont_use_autosuspend(dev); + + return ret; +} + +static int wcd9380_remove(struct sdw_slave *pdev) +{ + struct device *dev = &pdev->dev; + + component_del(dev, &wcd938x_sdw_component_ops); + + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_dont_use_autosuspend(dev); + + return 0; } static const struct sdw_device_id wcd9380_slave_id[] = { @@ -1320,6 +1344,7 @@ static const struct dev_pm_ops wcd938x_sdw_pm_ops = { static struct sdw_driver wcd9380_codec_driver = { .probe = wcd9380_probe, + .remove = wcd9380_remove, .ops = &wcd9380_slave_ops, .id_table = wcd9380_slave_id, .driver = { diff --git a/sound/soc/codecs/wcd938x.c b/sound/soc/codecs/wcd938x.c index a3c680661377..d27b919c63b4 100644 --- a/sound/soc/codecs/wcd938x.c +++ b/sound/soc/codecs/wcd938x.c @@ -3325,8 +3325,10 @@ static int wcd938x_populate_dt_data(struct wcd938x_priv *wcd938x, struct device return dev_err_probe(dev, ret, "Failed to get supplies\n"); ret = regulator_bulk_enable(WCD938X_MAX_SUPPLY, wcd938x->supplies); - if (ret) + if (ret) { + regulator_bulk_free(WCD938X_MAX_SUPPLY, wcd938x->supplies); return dev_err_probe(dev, ret, "Failed to enable supplies\n"); + } wcd938x_dt_parse_micbias_info(dev, wcd938x); @@ -3435,7 +3437,8 @@ static int wcd938x_bind(struct device *dev) wcd938x->rxdev = wcd938x_sdw_device_get(wcd938x->rxnode); if (!wcd938x->rxdev) { dev_err(dev, "could not find slave with matching of node\n"); - return -EINVAL; + ret = -EINVAL; + goto err_unbind; } wcd938x->sdw_priv[AIF1_PB] = dev_get_drvdata(wcd938x->rxdev); wcd938x->sdw_priv[AIF1_PB]->wcd938x = wcd938x; @@ -3443,46 +3446,47 @@ static int wcd938x_bind(struct device *dev) wcd938x->txdev = wcd938x_sdw_device_get(wcd938x->txnode); if (!wcd938x->txdev) { dev_err(dev, "could not find txslave with matching of node\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_rxdev; } wcd938x->sdw_priv[AIF1_CAP] = dev_get_drvdata(wcd938x->txdev); wcd938x->sdw_priv[AIF1_CAP]->wcd938x = wcd938x; wcd938x->tx_sdw_dev = dev_to_sdw_dev(wcd938x->txdev); - if (!wcd938x->tx_sdw_dev) { - dev_err(dev, "could not get txslave with matching of dev\n"); - return -EINVAL; - } /* As TX is main CSR reg interface, which should not be suspended first. * expicilty add the dependency link */ if (!device_link_add(wcd938x->rxdev, wcd938x->txdev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME)) { dev_err(dev, "could not devlink tx and rx\n"); - return -EINVAL; + ret = -EINVAL; + goto err_put_txdev; } if (!device_link_add(dev, wcd938x->txdev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME)) { dev_err(dev, "could not devlink wcd and tx\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_rxtx_link; } if (!device_link_add(dev, wcd938x->rxdev, DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME)) { dev_err(dev, "could not devlink wcd and rx\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_tx_link; } wcd938x->regmap = dev_get_regmap(&wcd938x->tx_sdw_dev->dev, NULL); if (!wcd938x->regmap) { dev_err(dev, "could not get TX device regmap\n"); - return -EINVAL; + ret = -EINVAL; + goto err_remove_rx_link; } ret = wcd938x_irq_init(wcd938x, dev); if (ret) { dev_err(dev, "%s: IRQ init failed: %d\n", __func__, ret); - return ret; + goto err_remove_rx_link; } wcd938x->sdw_priv[AIF1_PB]->slave_irq = wcd938x->virq; @@ -3491,27 +3495,45 @@ static int wcd938x_bind(struct device *dev) ret = wcd938x_set_micbias_data(wcd938x); if (ret < 0) { dev_err(dev, "%s: bad micbias pdata\n", __func__); - return ret; + goto err_remove_rx_link; } ret = snd_soc_register_component(dev, &soc_codec_dev_wcd938x, wcd938x_dais, ARRAY_SIZE(wcd938x_dais)); - if (ret) + if (ret) { dev_err(dev, "%s: Codec registration failed\n", __func__); + goto err_remove_rx_link; + } - return ret; + return 0; +err_remove_rx_link: + device_link_remove(dev, wcd938x->rxdev); +err_remove_tx_link: + device_link_remove(dev, wcd938x->txdev); +err_remove_rxtx_link: + device_link_remove(wcd938x->rxdev, wcd938x->txdev); +err_put_txdev: + put_device(wcd938x->txdev); +err_put_rxdev: + put_device(wcd938x->rxdev); +err_unbind: + component_unbind_all(dev, wcd938x); + + return ret; } static void wcd938x_unbind(struct device *dev) { struct wcd938x_priv *wcd938x = dev_get_drvdata(dev); + snd_soc_unregister_component(dev); device_link_remove(dev, wcd938x->txdev); device_link_remove(dev, wcd938x->rxdev); device_link_remove(wcd938x->rxdev, wcd938x->txdev); - snd_soc_unregister_component(dev); + put_device(wcd938x->txdev); + put_device(wcd938x->rxdev); component_unbind_all(dev, wcd938x); } @@ -3572,13 +3594,13 @@ static int wcd938x_probe(struct platform_device *pdev) ret = wcd938x_add_slave_components(wcd938x, dev, &match); if (ret) - return ret; + goto err_disable_regulators; wcd938x_reset(wcd938x); ret = component_master_add_with_match(dev, &wcd938x_comp_ops, match); if (ret) - return ret; + goto err_disable_regulators; pm_runtime_set_autosuspend_delay(dev, 1000); pm_runtime_use_autosuspend(dev); @@ -3588,11 +3610,27 @@ static int wcd938x_probe(struct platform_device *pdev) pm_runtime_idle(dev); return 0; + +err_disable_regulators: + regulator_bulk_disable(WCD938X_MAX_SUPPLY, wcd938x->supplies); + regulator_bulk_free(WCD938X_MAX_SUPPLY, wcd938x->supplies); + + return ret; } static void wcd938x_remove(struct platform_device *pdev) { - component_master_del(&pdev->dev, &wcd938x_comp_ops); + struct device *dev = &pdev->dev; + struct wcd938x_priv *wcd938x = dev_get_drvdata(dev); + + component_master_del(dev, &wcd938x_comp_ops); + + pm_runtime_disable(dev); + pm_runtime_set_suspended(dev); + pm_runtime_dont_use_autosuspend(dev); + + regulator_bulk_disable(WCD938X_MAX_SUPPLY, wcd938x->supplies); + regulator_bulk_free(WCD938X_MAX_SUPPLY, wcd938x->supplies); } #if defined(CONFIG_OF) diff --git a/sound/soc/dwc/dwc-i2s.c b/sound/soc/dwc/dwc-i2s.c index 22c004179214..9ea4be56d3b7 100644 --- a/sound/soc/dwc/dwc-i2s.c +++ b/sound/soc/dwc/dwc-i2s.c @@ -917,7 +917,7 @@ static int jh7110_i2stx0_clk_cfg(struct i2s_clk_config_data *config) static int dw_i2s_probe(struct platform_device *pdev) { - const struct i2s_platform_data *pdata = of_device_get_match_data(&pdev->dev); + const struct i2s_platform_data *pdata = pdev->dev.platform_data; struct dw_i2s_dev *dev; struct resource *res; int ret, irq; diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c index b70034c07eee..b8a3cb8b7597 100644 --- a/sound/soc/pxa/pxa-ssp.c +++ b/sound/soc/pxa/pxa-ssp.c @@ -773,7 +773,7 @@ static int pxa_ssp_probe(struct snd_soc_dai *dai) if (IS_ERR(priv->extclk)) { ret = PTR_ERR(priv->extclk); if (ret == -EPROBE_DEFER) - return ret; + goto err_priv; priv->extclk = NULL; } diff --git a/sound/soc/soc-component.c b/sound/soc/soc-component.c index ba7c0ae82e00..566033f7dd2e 100644 --- a/sound/soc/soc-component.c +++ b/sound/soc/soc-component.c @@ -242,6 +242,7 @@ int snd_soc_component_notify_control(struct snd_soc_component *component, char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; struct snd_kcontrol *kctl; + /* When updating, change also snd_soc_dapm_widget_name_cmp() */ if (component->name_prefix) snprintf(name, ARRAY_SIZE(name), "%s %s", component->name_prefix, ctl); else diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c index f07e83678373..312e55579831 100644 --- a/sound/soc/soc-dapm.c +++ b/sound/soc/soc-dapm.c @@ -2728,6 +2728,18 @@ int snd_soc_dapm_update_dai(struct snd_pcm_substream *substream, } EXPORT_SYMBOL_GPL(snd_soc_dapm_update_dai); +int snd_soc_dapm_widget_name_cmp(struct snd_soc_dapm_widget *widget, const char *s) +{ + struct snd_soc_component *component = snd_soc_dapm_to_component(widget->dapm); + const char *wname = widget->name; + + if (component->name_prefix) + wname += strlen(component->name_prefix) + 1; /* plus space */ + + return strcmp(wname, s); +} +EXPORT_SYMBOL_GPL(snd_soc_dapm_widget_name_cmp); + /* * dapm_update_widget_flags() - Re-compute widget sink and source flags * @w: The widget for which to update the flags diff --git a/sound/soc/ti/ams-delta.c b/sound/soc/ti/ams-delta.c index 371943350fdf..666057d50ea0 100644 --- a/sound/soc/ti/ams-delta.c +++ b/sound/soc/ti/ams-delta.c @@ -336,8 +336,8 @@ static void cx81801_hangup(struct tty_struct *tty) } /* Line discipline .receive_buf() */ -static void cx81801_receive(struct tty_struct *tty, const u8 *cp, - const char *fp, int count) +static void cx81801_receive(struct tty_struct *tty, const u8 *cp, const u8 *fp, + size_t count) { struct snd_soc_component *component = tty->disc_data; const unsigned char *c; diff --git a/tools/arch/x86/include/uapi/asm/unistd_32.h b/tools/arch/x86/include/uapi/asm/unistd_32.h index 4798f9d18fe8..9de35df1afc3 100644 --- a/tools/arch/x86/include/uapi/asm/unistd_32.h +++ b/tools/arch/x86/include/uapi/asm/unistd_32.h @@ -26,6 +26,6 @@ #ifndef __NR_setns #define __NR_setns 346 #endif -#ifdef __NR_seccomp +#ifndef __NR_seccomp #define __NR_seccomp 354 #endif diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst index 5e2abd3de5ab..dd3f9469765b 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-net.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -37,7 +37,7 @@ DESCRIPTION **bpftool net { show | list }** [ **dev** *NAME* ] List bpf program attachments in the kernel networking subsystem. - Currently, device driver xdp attachments, tcx and old-style tc + Currently, device driver xdp attachments, tcx, netkit and old-style tc classifier/action attachments, flow_dissector as well as netfilter attachments are implemented, i.e., for program types **BPF_PROG_TYPE_XDP**, **BPF_PROG_TYPE_SCHED_CLS**, @@ -52,11 +52,11 @@ DESCRIPTION bpf programs, users should consult other tools, e.g., iproute2. The current output will start with all xdp program attachments, followed by - all tcx, then tc class/qdisc bpf program attachments, then flow_dissector - and finally netfilter programs. Both xdp programs and tcx/tc programs are + all tcx, netkit, then tc class/qdisc bpf program attachments, then flow_dissector + and finally netfilter programs. Both xdp programs and tcx/netkit/tc programs are ordered based on ifindex number. If multiple bpf programs attached to the same networking device through **tc**, the order will be first - all bpf programs attached to tcx, then tc classes, then all bpf programs + all bpf programs attached to tcx, netkit, then tc classes, then all bpf programs attached to non clsact qdiscs, and finally all bpf programs attached to root and clsact qdisc. diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c index 1b7f69714604..527fe867a8fb 100644 --- a/tools/bpf/bpftool/btf_dumper.c +++ b/tools/bpf/bpftool/btf_dumper.c @@ -127,7 +127,7 @@ static void btf_dumper_ptr(const struct btf_dumper *d, print_ptr_value: if (d->is_plain_text) - jsonw_printf(d->jw, "%p", (void *)value); + jsonw_printf(d->jw, "\"%p\"", (void *)value); else jsonw_printf(d->jw, "%lu", value); } diff --git a/tools/bpf/bpftool/link.c b/tools/bpf/bpftool/link.c index 4b1407b05056..a1528cde81ab 100644 --- a/tools/bpf/bpftool/link.c +++ b/tools/bpf/bpftool/link.c @@ -451,6 +451,10 @@ static int show_link_close_json(int fd, struct bpf_link_info *info) show_link_ifindex_json(info->tcx.ifindex, json_wtr); show_link_attach_type_json(info->tcx.attach_type, json_wtr); break; + case BPF_LINK_TYPE_NETKIT: + show_link_ifindex_json(info->netkit.ifindex, json_wtr); + show_link_attach_type_json(info->netkit.attach_type, json_wtr); + break; case BPF_LINK_TYPE_XDP: show_link_ifindex_json(info->xdp.ifindex, json_wtr); break; @@ -791,6 +795,11 @@ static int show_link_close_plain(int fd, struct bpf_link_info *info) show_link_ifindex_plain(info->tcx.ifindex); show_link_attach_type_plain(info->tcx.attach_type); break; + case BPF_LINK_TYPE_NETKIT: + printf("\n\t"); + show_link_ifindex_plain(info->netkit.ifindex); + show_link_attach_type_plain(info->netkit.attach_type); + break; case BPF_LINK_TYPE_XDP: printf("\n\t"); show_link_ifindex_plain(info->xdp.ifindex); diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c index 66a8ce8ae012..968714b4c3d4 100644 --- a/tools/bpf/bpftool/net.c +++ b/tools/bpf/bpftool/net.c @@ -79,6 +79,8 @@ static const char * const attach_type_strings[] = { static const char * const attach_loc_strings[] = { [BPF_TCX_INGRESS] = "tcx/ingress", [BPF_TCX_EGRESS] = "tcx/egress", + [BPF_NETKIT_PRIMARY] = "netkit/primary", + [BPF_NETKIT_PEER] = "netkit/peer", }; const size_t net_attach_type_size = ARRAY_SIZE(attach_type_strings); @@ -506,6 +508,9 @@ static void show_dev_tc_bpf(struct ip_devname_ifindex *dev) { __show_dev_tc_bpf(dev, BPF_TCX_INGRESS); __show_dev_tc_bpf(dev, BPF_TCX_EGRESS); + + __show_dev_tc_bpf(dev, BPF_NETKIT_PRIMARY); + __show_dev_tc_bpf(dev, BPF_NETKIT_PEER); } static int show_dev_tc_bpf_classic(int sock, unsigned int nl_pid, @@ -926,7 +931,7 @@ static int do_help(int argc, char **argv) " ATTACH_TYPE := { xdp | xdpgeneric | xdpdrv | xdpoffload }\n" " " HELP_SPEC_OPTIONS " }\n" "\n" - "Note: Only xdp, tcx, tc, flow_dissector and netfilter attachments\n" + "Note: Only xdp, tcx, tc, netkit, flow_dissector and netfilter attachments\n" " are currently supported.\n" " For progs attached to cgroups, use \"bpftool cgroup\"\n" " to dump program attachments. For program types\n" diff --git a/tools/bpf/bpftool/struct_ops.c b/tools/bpf/bpftool/struct_ops.c index 3ebc9fe91e0e..d573f2640d8e 100644 --- a/tools/bpf/bpftool/struct_ops.c +++ b/tools/bpf/bpftool/struct_ops.c @@ -276,6 +276,9 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, res.nr_maps++; + if (wtr) + jsonw_start_array(wtr); + if (func(fd, info, data, wtr)) res.nr_errs++; else if (!wtr && json_output) @@ -288,6 +291,9 @@ static struct res do_one_id(const char *id_str, work_func func, void *data, */ jsonw_null(json_wtr); + if (wtr) + jsonw_end_array(wtr); + done: free(info); close(fd); diff --git a/tools/build/feature/test-llvm.cpp b/tools/build/feature/test-llvm.cpp new file mode 100644 index 000000000000..88a3d1bdd9f6 --- /dev/null +++ b/tools/build/feature/test-llvm.cpp @@ -0,0 +1,14 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "llvm/Support/ManagedStatic.h" +#include "llvm/Support/raw_ostream.h" +#define NUM_VERSION (((LLVM_VERSION_MAJOR) << 16) + (LLVM_VERSION_MINOR << 8) + LLVM_VERSION_PATCH) + +#if NUM_VERSION < 0x030900 +# error "LLVM version too low" +#endif +int main() +{ + llvm::errs() << "Hello World!\n"; + llvm::llvm_shutdown(); + return 0; +} diff --git a/tools/include/linux/rwsem.h b/tools/include/linux/rwsem.h new file mode 100644 index 000000000000..83971b3cbfce --- /dev/null +++ b/tools/include/linux/rwsem.h @@ -0,0 +1,40 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +#ifndef _TOOLS__RWSEM_H +#define _TOOLS__RWSEM_H + +#include <pthread.h> + +struct rw_semaphore { + pthread_rwlock_t lock; +}; + +static inline int init_rwsem(struct rw_semaphore *sem) +{ + return pthread_rwlock_init(&sem->lock, NULL); +} + +static inline int exit_rwsem(struct rw_semaphore *sem) +{ + return pthread_rwlock_destroy(&sem->lock); +} + +static inline int down_read(struct rw_semaphore *sem) +{ + return pthread_rwlock_rdlock(&sem->lock); +} + +static inline int up_read(struct rw_semaphore *sem) +{ + return pthread_rwlock_unlock(&sem->lock); +} + +static inline int down_write(struct rw_semaphore *sem) +{ + return pthread_rwlock_wrlock(&sem->lock); +} + +static inline int up_write(struct rw_semaphore *sem) +{ + return pthread_rwlock_unlock(&sem->lock); +} +#endif /* _TOOLS_RWSEM_H */ diff --git a/tools/include/nolibc/arch-i386.h b/tools/include/nolibc/arch-i386.h index 64415b9fac77..28c26a00a762 100644 --- a/tools/include/nolibc/arch-i386.h +++ b/tools/include/nolibc/arch-i386.h @@ -167,7 +167,9 @@ void __attribute__((weak, noreturn, optimize("Os", "omit-frame-pointer"))) __no_ __asm__ volatile ( "xor %ebp, %ebp\n" /* zero the stack frame */ "mov %esp, %eax\n" /* save stack pointer to %eax, as arg1 of _start_c */ - "and $-16, %esp\n" /* last pushed argument must be 16-byte aligned */ + "add $12, %esp\n" /* avoid over-estimating after the 'and' & 'sub' below */ + "and $-16, %esp\n" /* the %esp must be 16-byte aligned on 'call' */ + "sub $12, %esp\n" /* sub 12 to keep it aligned after the push %eax */ "push %eax\n" /* push arg1 on stack to support plain stack modes too */ "call _start_c\n" /* transfer to c runtime */ "hlt\n" /* ensure it does not return */ diff --git a/tools/include/nolibc/crt.h b/tools/include/nolibc/crt.h index a5f33fef1672..a05655b4ce1d 100644 --- a/tools/include/nolibc/crt.h +++ b/tools/include/nolibc/crt.h @@ -13,6 +13,7 @@ const unsigned long *_auxv __attribute__((weak)); static void __stack_chk_init(void); static void exit(int); +__attribute__((weak)) void _start_c(long *sp) { long argc; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 7ba61b75bc0e..0f6cdf52b1da 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1052,6 +1052,8 @@ enum bpf_attach_type { BPF_CGROUP_UNIX_RECVMSG, BPF_CGROUP_UNIX_GETPEERNAME, BPF_CGROUP_UNIX_GETSOCKNAME, + BPF_NETKIT_PRIMARY, + BPF_NETKIT_PEER, __MAX_BPF_ATTACH_TYPE }; @@ -1071,6 +1073,7 @@ enum bpf_link_type { BPF_LINK_TYPE_NETFILTER = 10, BPF_LINK_TYPE_TCX = 11, BPF_LINK_TYPE_UPROBE_MULTI = 12, + BPF_LINK_TYPE_NETKIT = 13, MAX_BPF_LINK_TYPE, }; @@ -1656,6 +1659,13 @@ union bpf_attr { __u32 flags; __u32 pid; } uprobe_multi; + struct { + union { + __u32 relative_fd; + __u32 relative_id; + }; + __u64 expected_revision; + } netkit; }; } link_create; @@ -6576,6 +6586,10 @@ struct bpf_link_info { __u32 ifindex; __u32 attach_type; } tcx; + struct { + __u32 ifindex; + __u32 attach_type; + } netkit; }; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h index 39e659c83cfd..a0aa05a28cf2 100644 --- a/tools/include/uapi/linux/if_link.h +++ b/tools/include/uapi/linux/if_link.h @@ -211,6 +211,9 @@ struct rtnl_link_stats { * @rx_nohandler: Number of packets received on the interface * but dropped by the networking stack because the device is * not designated to receive packets (e.g. backup link in a bond). + * + * @rx_otherhost_dropped: Number of packets dropped due to mismatch + * in destination MAC address. */ struct rtnl_link_stats64 { __u64 rx_packets; @@ -243,6 +246,23 @@ struct rtnl_link_stats64 { __u64 rx_compressed; __u64 tx_compressed; __u64 rx_nohandler; + + __u64 rx_otherhost_dropped; +}; + +/* Subset of link stats useful for in-HW collection. Meaning of the fields is as + * for struct rtnl_link_stats64. + */ +struct rtnl_hw_stats64 { + __u64 rx_packets; + __u64 tx_packets; + __u64 rx_bytes; + __u64 tx_bytes; + __u64 rx_errors; + __u64 tx_errors; + __u64 rx_dropped; + __u64 tx_dropped; + __u64 multicast; }; /* The struct should be in sync with struct ifmap */ @@ -350,7 +370,13 @@ enum { IFLA_GRO_MAX_SIZE, IFLA_TSO_MAX_SIZE, IFLA_TSO_MAX_SEGS, + IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */ + + IFLA_DEVLINK_PORT, + IFLA_GSO_IPV4_MAX_SIZE, + IFLA_GRO_IPV4_MAX_SIZE, + IFLA_DPLL_PIN, __IFLA_MAX }; @@ -539,6 +565,12 @@ enum { IFLA_BRPORT_MRP_IN_OPEN, IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, + IFLA_BRPORT_LOCKED, + IFLA_BRPORT_MAB, + IFLA_BRPORT_MCAST_N_GROUPS, + IFLA_BRPORT_MCAST_MAX_GROUPS, + IFLA_BRPORT_NEIGH_VLAN_SUPPRESS, + IFLA_BRPORT_BACKUP_NHID, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) @@ -716,7 +748,79 @@ enum ipvlan_mode { #define IPVLAN_F_PRIVATE 0x01 #define IPVLAN_F_VEPA 0x02 +/* Tunnel RTM header */ +struct tunnel_msg { + __u8 family; + __u8 flags; + __u16 reserved2; + __u32 ifindex; +}; + +/* netkit section */ +enum netkit_action { + NETKIT_NEXT = -1, + NETKIT_PASS = 0, + NETKIT_DROP = 2, + NETKIT_REDIRECT = 7, +}; + +enum netkit_mode { + NETKIT_L2, + NETKIT_L3, +}; + +enum { + IFLA_NETKIT_UNSPEC, + IFLA_NETKIT_PEER_INFO, + IFLA_NETKIT_PRIMARY, + IFLA_NETKIT_POLICY, + IFLA_NETKIT_PEER_POLICY, + IFLA_NETKIT_MODE, + __IFLA_NETKIT_MAX, +}; +#define IFLA_NETKIT_MAX (__IFLA_NETKIT_MAX - 1) + /* VXLAN section */ + +/* include statistics in the dump */ +#define TUNNEL_MSG_FLAG_STATS 0x01 + +#define TUNNEL_MSG_VALID_USER_FLAGS TUNNEL_MSG_FLAG_STATS + +/* Embedded inside VXLAN_VNIFILTER_ENTRY_STATS */ +enum { + VNIFILTER_ENTRY_STATS_UNSPEC, + VNIFILTER_ENTRY_STATS_RX_BYTES, + VNIFILTER_ENTRY_STATS_RX_PKTS, + VNIFILTER_ENTRY_STATS_RX_DROPS, + VNIFILTER_ENTRY_STATS_RX_ERRORS, + VNIFILTER_ENTRY_STATS_TX_BYTES, + VNIFILTER_ENTRY_STATS_TX_PKTS, + VNIFILTER_ENTRY_STATS_TX_DROPS, + VNIFILTER_ENTRY_STATS_TX_ERRORS, + VNIFILTER_ENTRY_STATS_PAD, + __VNIFILTER_ENTRY_STATS_MAX +}; +#define VNIFILTER_ENTRY_STATS_MAX (__VNIFILTER_ENTRY_STATS_MAX - 1) + +enum { + VXLAN_VNIFILTER_ENTRY_UNSPEC, + VXLAN_VNIFILTER_ENTRY_START, + VXLAN_VNIFILTER_ENTRY_END, + VXLAN_VNIFILTER_ENTRY_GROUP, + VXLAN_VNIFILTER_ENTRY_GROUP6, + VXLAN_VNIFILTER_ENTRY_STATS, + __VXLAN_VNIFILTER_ENTRY_MAX +}; +#define VXLAN_VNIFILTER_ENTRY_MAX (__VXLAN_VNIFILTER_ENTRY_MAX - 1) + +enum { + VXLAN_VNIFILTER_UNSPEC, + VXLAN_VNIFILTER_ENTRY, + __VXLAN_VNIFILTER_MAX +}; +#define VXLAN_VNIFILTER_MAX (__VXLAN_VNIFILTER_MAX - 1) + enum { IFLA_VXLAN_UNSPEC, IFLA_VXLAN_ID, @@ -748,6 +852,8 @@ enum { IFLA_VXLAN_GPE, IFLA_VXLAN_TTL_INHERIT, IFLA_VXLAN_DF, + IFLA_VXLAN_VNIFILTER, /* only applicable with COLLECT_METADATA mode */ + IFLA_VXLAN_LOCALBYPASS, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) @@ -781,6 +887,7 @@ enum { IFLA_GENEVE_LABEL, IFLA_GENEVE_TTL_INHERIT, IFLA_GENEVE_DF, + IFLA_GENEVE_INNER_PROTO_INHERIT, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) @@ -826,6 +933,8 @@ enum { IFLA_GTP_FD1, IFLA_GTP_PDP_HASHSIZE, IFLA_GTP_ROLE, + IFLA_GTP_CREATE_SOCKETS, + IFLA_GTP_RESTART_COUNT, __IFLA_GTP_MAX, }; #define IFLA_GTP_MAX (__IFLA_GTP_MAX - 1) @@ -1162,6 +1271,17 @@ enum { #define IFLA_STATS_FILTER_BIT(ATTR) (1 << (ATTR - 1)) +enum { + IFLA_STATS_GETSET_UNSPEC, + IFLA_STATS_GET_FILTERS, /* Nest of IFLA_STATS_LINK_xxx, each a u32 with + * a filter mask for the corresponding group. + */ + IFLA_STATS_SET_OFFLOAD_XSTATS_L3_STATS, /* 0 or 1 as u8 */ + __IFLA_STATS_GETSET_MAX, +}; + +#define IFLA_STATS_GETSET_MAX (__IFLA_STATS_GETSET_MAX - 1) + /* These are embedded into IFLA_STATS_LINK_XSTATS: * [IFLA_STATS_LINK_XSTATS] * -> [LINK_XSTATS_TYPE_xxx] @@ -1179,10 +1299,21 @@ enum { enum { IFLA_OFFLOAD_XSTATS_UNSPEC, IFLA_OFFLOAD_XSTATS_CPU_HIT, /* struct rtnl_link_stats64 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO, /* HW stats info. A nest */ + IFLA_OFFLOAD_XSTATS_L3_STATS, /* struct rtnl_hw_stats64 */ __IFLA_OFFLOAD_XSTATS_MAX }; #define IFLA_OFFLOAD_XSTATS_MAX (__IFLA_OFFLOAD_XSTATS_MAX - 1) +enum { + IFLA_OFFLOAD_XSTATS_HW_S_INFO_UNSPEC, + IFLA_OFFLOAD_XSTATS_HW_S_INFO_REQUEST, /* u8 */ + IFLA_OFFLOAD_XSTATS_HW_S_INFO_USED, /* u8 */ + __IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX, +}; +#define IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX \ + (__IFLA_OFFLOAD_XSTATS_HW_S_INFO_MAX - 1) + /* XDP section */ #define XDP_FLAGS_UPDATE_IF_NOEXIST (1U << 0) @@ -1281,4 +1412,14 @@ enum { #define IFLA_MCTP_MAX (__IFLA_MCTP_MAX - 1) +/* DSA section */ + +enum { + IFLA_DSA_UNSPEC, + IFLA_DSA_MASTER, + __IFLA_DSA_MAX, +}; + +#define IFLA_DSA_MAX (__IFLA_DSA_MAX - 1) + #endif /* _UAPI_LINUX_IF_LINK_H */ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index b0f1913763a3..9dc9625651dc 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -810,6 +810,22 @@ int bpf_link_create(int prog_fd, int target_fd, if (!OPTS_ZEROED(opts, tcx)) return libbpf_err(-EINVAL); break; + case BPF_NETKIT_PRIMARY: + case BPF_NETKIT_PEER: + relative_fd = OPTS_GET(opts, netkit.relative_fd, 0); + relative_id = OPTS_GET(opts, netkit.relative_id, 0); + if (relative_fd && relative_id) + return libbpf_err(-EINVAL); + if (relative_id) { + attr.link_create.netkit.relative_id = relative_id; + attr.link_create.flags |= BPF_F_ID; + } else { + attr.link_create.netkit.relative_fd = relative_fd; + } + attr.link_create.netkit.expected_revision = OPTS_GET(opts, netkit.expected_revision, 0); + if (!OPTS_ZEROED(opts, netkit)) + return libbpf_err(-EINVAL); + break; default: if (!OPTS_ZEROED(opts, flags)) return libbpf_err(-EINVAL); diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 74c2887cfd24..d0f53772bdc0 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -415,6 +415,11 @@ struct bpf_link_create_opts { __u32 relative_id; __u64 expected_revision; } tcx; + struct { + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + } netkit; }; size_t :0; }; diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c index 2a158e8a8b7c..2a62bf411bb3 100644 --- a/tools/lib/bpf/elf.c +++ b/tools/lib/bpf/elf.c @@ -141,14 +141,15 @@ static int elf_sym_iter_new(struct elf_sym_iter *iter, iter->versyms = elf_getdata(scn, 0); scn = elf_find_next_scn_by_type(elf, SHT_GNU_verdef, NULL); - if (!scn) { - pr_debug("elf: failed to find verdef ELF sections in '%s'\n", binary_path); - return -ENOENT; - } - if (!gelf_getshdr(scn, &sh)) + if (!scn) + return 0; + + iter->verdefs = elf_getdata(scn, 0); + if (!iter->verdefs || !gelf_getshdr(scn, &sh)) { + pr_warn("elf: failed to get verdef ELF section in '%s'\n", binary_path); return -EINVAL; + } iter->verdef_strtabidx = sh.sh_link; - iter->verdefs = elf_getdata(scn, 0); return 0; } @@ -199,6 +200,9 @@ static const char *elf_get_vername(struct elf_sym_iter *iter, int ver) GElf_Verdef verdef; int offset; + if (!iter->verdefs) + return NULL; + offset = 0; while (gelf_getverdef(iter->verdefs, offset, &verdef)) { if (verdef.vd_ndx != ver) { diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index a295f6acf98f..e067be95da3c 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -126,6 +126,8 @@ static const char * const attach_type_name[] = { [BPF_TCX_INGRESS] = "tcx_ingress", [BPF_TCX_EGRESS] = "tcx_egress", [BPF_TRACE_UPROBE_MULTI] = "trace_uprobe_multi", + [BPF_NETKIT_PRIMARY] = "netkit_primary", + [BPF_NETKIT_PEER] = "netkit_peer", }; static const char * const link_type_name[] = { @@ -142,6 +144,7 @@ static const char * const link_type_name[] = { [BPF_LINK_TYPE_NETFILTER] = "netfilter", [BPF_LINK_TYPE_TCX] = "tcx", [BPF_LINK_TYPE_UPROBE_MULTI] = "uprobe_multi", + [BPF_LINK_TYPE_NETKIT] = "netkit", }; static const char * const map_type_name[] = { @@ -8915,6 +8918,8 @@ static const struct bpf_sec_def section_defs[] = { SEC_DEF("tc", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ SEC_DEF("classifier", SCHED_CLS, 0, SEC_NONE), /* deprecated / legacy, use tcx */ SEC_DEF("action", SCHED_ACT, 0, SEC_NONE), /* deprecated / legacy, use tcx */ + SEC_DEF("netkit/primary", SCHED_CLS, BPF_NETKIT_PRIMARY, SEC_NONE), + SEC_DEF("netkit/peer", SCHED_CLS, BPF_NETKIT_PEER, SEC_NONE), SEC_DEF("tracepoint+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("tp+", TRACEPOINT, 0, SEC_NONE, attach_tp), SEC_DEF("raw_tracepoint+", RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp), @@ -12126,6 +12131,40 @@ bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, return bpf_program_attach_fd(prog, ifindex, "tcx", &link_create_opts); } +struct bpf_link * +bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex, + const struct bpf_netkit_opts *opts) +{ + LIBBPF_OPTS(bpf_link_create_opts, link_create_opts); + __u32 relative_id; + int relative_fd; + + if (!OPTS_VALID(opts, bpf_netkit_opts)) + return libbpf_err_ptr(-EINVAL); + + relative_id = OPTS_GET(opts, relative_id, 0); + relative_fd = OPTS_GET(opts, relative_fd, 0); + + /* validate we don't have unexpected combinations of non-zero fields */ + if (!ifindex) { + pr_warn("prog '%s': target netdevice ifindex cannot be zero\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + if (relative_fd && relative_id) { + pr_warn("prog '%s': relative_fd and relative_id cannot be set at the same time\n", + prog->name); + return libbpf_err_ptr(-EINVAL); + } + + link_create_opts.netkit.expected_revision = OPTS_GET(opts, expected_revision, 0); + link_create_opts.netkit.relative_fd = relative_fd; + link_create_opts.netkit.relative_id = relative_id; + link_create_opts.flags = OPTS_GET(opts, flags, 0); + + return bpf_program_attach_fd(prog, ifindex, "netkit", &link_create_opts); +} + struct bpf_link *bpf_program__attach_freplace(const struct bpf_program *prog, int target_fd, const char *attach_func_name) diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 475378438545..6cd9c501624f 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -800,6 +800,21 @@ LIBBPF_API struct bpf_link * bpf_program__attach_tcx(const struct bpf_program *prog, int ifindex, const struct bpf_tcx_opts *opts); +struct bpf_netkit_opts { + /* size of this struct, for forward/backward compatibility */ + size_t sz; + __u32 flags; + __u32 relative_fd; + __u32 relative_id; + __u64 expected_revision; + size_t :0; +}; +#define bpf_netkit_opts__last_field expected_revision + +LIBBPF_API struct bpf_link * +bpf_program__attach_netkit(const struct bpf_program *prog, int ifindex, + const struct bpf_netkit_opts *opts); + struct bpf_map; LIBBPF_API struct bpf_link *bpf_map__attach_struct_ops(const struct bpf_map *map); diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index cc973b678a39..b52dc28dc8af 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -398,6 +398,7 @@ LIBBPF_1.3.0 { bpf_object__unpin; bpf_prog_detach_opts; bpf_program__attach_netfilter; + bpf_program__attach_netkit; bpf_program__attach_tcx; bpf_program__attach_uprobe_multi; ring__avail_data_size; diff --git a/tools/net/ynl/generated/devlink-user.c b/tools/net/ynl/generated/devlink-user.c index 3a8d8499fab6..75b744b47986 100644 --- a/tools/net/ynl/generated/devlink-user.c +++ b/tools/net/ynl/generated/devlink-user.c @@ -16,19 +16,30 @@ static const char * const devlink_op_strmap[] = { [3] = "get", [7] = "port-get", - [DEVLINK_CMD_SB_GET] = "sb-get", - [DEVLINK_CMD_SB_POOL_GET] = "sb-pool-get", - [DEVLINK_CMD_SB_PORT_POOL_GET] = "sb-port-pool-get", - [DEVLINK_CMD_SB_TC_POOL_BIND_GET] = "sb-tc-pool-bind-get", + [DEVLINK_CMD_PORT_NEW] = "port-new", + [13] = "sb-get", + [17] = "sb-pool-get", + [21] = "sb-port-pool-get", + [25] = "sb-tc-pool-bind-get", + [DEVLINK_CMD_ESWITCH_GET] = "eswitch-get", + [DEVLINK_CMD_DPIPE_TABLE_GET] = "dpipe-table-get", + [DEVLINK_CMD_DPIPE_ENTRIES_GET] = "dpipe-entries-get", + [DEVLINK_CMD_DPIPE_HEADERS_GET] = "dpipe-headers-get", + [DEVLINK_CMD_RESOURCE_DUMP] = "resource-dump", + [DEVLINK_CMD_RELOAD] = "reload", [DEVLINK_CMD_PARAM_GET] = "param-get", [DEVLINK_CMD_REGION_GET] = "region-get", + [DEVLINK_CMD_REGION_NEW] = "region-new", + [DEVLINK_CMD_REGION_READ] = "region-read", + [DEVLINK_CMD_PORT_PARAM_GET] = "port-param-get", [DEVLINK_CMD_INFO_GET] = "info-get", [DEVLINK_CMD_HEALTH_REPORTER_GET] = "health-reporter-get", - [DEVLINK_CMD_TRAP_GET] = "trap-get", - [DEVLINK_CMD_TRAP_GROUP_GET] = "trap-group-get", - [DEVLINK_CMD_TRAP_POLICER_GET] = "trap-policer-get", - [DEVLINK_CMD_RATE_GET] = "rate-get", - [DEVLINK_CMD_LINECARD_GET] = "linecard-get", + [DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET] = "health-reporter-dump-get", + [63] = "trap-get", + [67] = "trap-group-get", + [71] = "trap-policer-get", + [76] = "rate-get", + [80] = "linecard-get", [DEVLINK_CMD_SELFTESTS_GET] = "selftests-get", }; @@ -51,7 +62,303 @@ const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value) return devlink_sb_pool_type_strmap[value]; } +static const char * const devlink_port_type_strmap[] = { + [0] = "notset", + [1] = "auto", + [2] = "eth", + [3] = "ib", +}; + +const char *devlink_port_type_str(enum devlink_port_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_type_strmap)) + return NULL; + return devlink_port_type_strmap[value]; +} + +static const char * const devlink_port_flavour_strmap[] = { + [0] = "physical", + [1] = "cpu", + [2] = "dsa", + [3] = "pci_pf", + [4] = "pci_vf", + [5] = "virtual", + [6] = "unused", + [7] = "pci_sf", +}; + +const char *devlink_port_flavour_str(enum devlink_port_flavour value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_flavour_strmap)) + return NULL; + return devlink_port_flavour_strmap[value]; +} + +static const char * const devlink_port_fn_state_strmap[] = { + [0] = "inactive", + [1] = "active", +}; + +const char *devlink_port_fn_state_str(enum devlink_port_fn_state value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_state_strmap)) + return NULL; + return devlink_port_fn_state_strmap[value]; +} + +static const char * const devlink_port_fn_opstate_strmap[] = { + [0] = "detached", + [1] = "attached", +}; + +const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_opstate_strmap)) + return NULL; + return devlink_port_fn_opstate_strmap[value]; +} + +static const char * const devlink_port_fn_attr_cap_strmap[] = { + [0] = "roce-bit", + [1] = "migratable-bit", +}; + +const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_port_fn_attr_cap_strmap)) + return NULL; + return devlink_port_fn_attr_cap_strmap[value]; +} + +static const char * const devlink_sb_threshold_type_strmap[] = { + [0] = "static", + [1] = "dynamic", +}; + +const char *devlink_sb_threshold_type_str(enum devlink_sb_threshold_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_sb_threshold_type_strmap)) + return NULL; + return devlink_sb_threshold_type_strmap[value]; +} + +static const char * const devlink_eswitch_mode_strmap[] = { + [0] = "legacy", + [1] = "switchdev", +}; + +const char *devlink_eswitch_mode_str(enum devlink_eswitch_mode value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_mode_strmap)) + return NULL; + return devlink_eswitch_mode_strmap[value]; +} + +static const char * const devlink_eswitch_inline_mode_strmap[] = { + [0] = "none", + [1] = "link", + [2] = "network", + [3] = "transport", +}; + +const char * +devlink_eswitch_inline_mode_str(enum devlink_eswitch_inline_mode value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_inline_mode_strmap)) + return NULL; + return devlink_eswitch_inline_mode_strmap[value]; +} + +static const char * const devlink_eswitch_encap_mode_strmap[] = { + [0] = "none", + [1] = "basic", +}; + +const char * +devlink_eswitch_encap_mode_str(enum devlink_eswitch_encap_mode value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_eswitch_encap_mode_strmap)) + return NULL; + return devlink_eswitch_encap_mode_strmap[value]; +} + +static const char * const devlink_dpipe_match_type_strmap[] = { + [0] = "field-exact", +}; + +const char *devlink_dpipe_match_type_str(enum devlink_dpipe_match_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_match_type_strmap)) + return NULL; + return devlink_dpipe_match_type_strmap[value]; +} + +static const char * const devlink_dpipe_action_type_strmap[] = { + [0] = "field-modify", +}; + +const char *devlink_dpipe_action_type_str(enum devlink_dpipe_action_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_action_type_strmap)) + return NULL; + return devlink_dpipe_action_type_strmap[value]; +} + +static const char * const devlink_dpipe_field_mapping_type_strmap[] = { + [0] = "none", + [1] = "ifindex", +}; + +const char * +devlink_dpipe_field_mapping_type_str(enum devlink_dpipe_field_mapping_type value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_dpipe_field_mapping_type_strmap)) + return NULL; + return devlink_dpipe_field_mapping_type_strmap[value]; +} + +static const char * const devlink_resource_unit_strmap[] = { + [0] = "entry", +}; + +const char *devlink_resource_unit_str(enum devlink_resource_unit value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_resource_unit_strmap)) + return NULL; + return devlink_resource_unit_strmap[value]; +} + +static const char * const devlink_reload_action_strmap[] = { + [1] = "driver-reinit", + [2] = "fw-activate", +}; + +const char *devlink_reload_action_str(enum devlink_reload_action value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_reload_action_strmap)) + return NULL; + return devlink_reload_action_strmap[value]; +} + +static const char * const devlink_param_cmode_strmap[] = { + [0] = "runtime", + [1] = "driverinit", + [2] = "permanent", +}; + +const char *devlink_param_cmode_str(enum devlink_param_cmode value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_param_cmode_strmap)) + return NULL; + return devlink_param_cmode_strmap[value]; +} + +static const char * const devlink_flash_overwrite_strmap[] = { + [0] = "settings-bit", + [1] = "identifiers-bit", +}; + +const char *devlink_flash_overwrite_str(enum devlink_flash_overwrite value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_flash_overwrite_strmap)) + return NULL; + return devlink_flash_overwrite_strmap[value]; +} + +static const char * const devlink_trap_action_strmap[] = { + [0] = "drop", + [1] = "trap", + [2] = "mirror", +}; + +const char *devlink_trap_action_str(enum devlink_trap_action value) +{ + if (value < 0 || value >= (int)MNL_ARRAY_SIZE(devlink_trap_action_strmap)) + return NULL; + return devlink_trap_action_strmap[value]; +} + /* Policies */ +struct ynl_policy_attr devlink_dl_dpipe_match_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_MATCH_TYPE] = { .name = "dpipe-match-type", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_match_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_match_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_match_value_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, }, + [DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,}, + [DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,}, + [DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_match_value_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_match_value_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_action_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_ACTION_TYPE] = { .name = "dpipe-action-type", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_action_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_action_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_action_value_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, }, + [DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,}, + [DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,}, + [DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_action_value_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_action_value_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_field_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_FIELD_NAME] = { .name = "dpipe-field-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH] = { .name = "dpipe-field-bitwidth", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE] = { .name = "dpipe-field-mapping-type", .type = YNL_PT_U32, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_field_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_field_policy, +}; + +struct ynl_policy_attr devlink_dl_resource_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RESOURCE_NAME] = { .name = "resource-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_RESOURCE_ID] = { .name = "resource-id", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE] = { .name = "resource-size", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_NEW] = { .name = "resource-size-new", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_VALID] = { .name = "resource-size-valid", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RESOURCE_SIZE_MIN] = { .name = "resource-size-min", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_MAX] = { .name = "resource-size-max", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_GRAN] = { .name = "resource-size-gran", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_UNIT] = { .name = "resource-unit", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RESOURCE_OCC] = { .name = "resource-occ", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest devlink_dl_resource_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_resource_policy, +}; + struct ynl_policy_attr devlink_dl_info_version_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, @@ -62,6 +369,31 @@ struct ynl_policy_nest devlink_dl_info_version_nest = { .table = devlink_dl_info_version_policy, }; +struct ynl_policy_attr devlink_dl_fmsg_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_FMSG_OBJ_NEST_START] = { .name = "fmsg-obj-nest-start", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_PAIR_NEST_START] = { .name = "fmsg-pair-nest-start", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_ARR_NEST_START] = { .name = "fmsg-arr-nest-start", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_NEST_END] = { .name = "fmsg-nest-end", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_OBJ_NAME] = { .name = "fmsg-obj-name", .type = YNL_PT_NUL_STR, }, +}; + +struct ynl_policy_nest devlink_dl_fmsg_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_fmsg_policy, +}; + +struct ynl_policy_attr devlink_dl_port_function_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { + [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .name = "hw-addr", .type = YNL_PT_BINARY,}, + [DEVLINK_PORT_FN_ATTR_STATE] = { .name = "state", .type = YNL_PT_U8, }, + [DEVLINK_PORT_FN_ATTR_OPSTATE] = { .name = "opstate", .type = YNL_PT_U8, }, + [DEVLINK_PORT_FN_ATTR_CAPS] = { .name = "caps", .type = YNL_PT_BITFIELD32, }, +}; + +struct ynl_policy_nest devlink_dl_port_function_nest = { + .max_attr = DEVLINK_PORT_FUNCTION_ATTR_MAX, + .table = devlink_dl_port_function_policy, +}; + struct ynl_policy_attr devlink_dl_reload_stats_entry_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_STATS_LIMIT] = { .name = "reload-stats-limit", .type = YNL_PT_U8, }, [DEVLINK_ATTR_RELOAD_STATS_VALUE] = { .name = "reload-stats-value", .type = YNL_PT_U32, }, @@ -81,6 +413,69 @@ struct ynl_policy_nest devlink_dl_reload_act_stats_nest = { .table = devlink_dl_reload_act_stats_policy, }; +struct ynl_policy_attr devlink_dl_selftest_id_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { + [DEVLINK_ATTR_SELFTEST_ID_FLASH] = { .name = "flash", .type = YNL_PT_FLAG, }, +}; + +struct ynl_policy_nest devlink_dl_selftest_id_nest = { + .max_attr = DEVLINK_ATTR_SELFTEST_ID_MAX, + .table = devlink_dl_selftest_id_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_table_matches_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_table_matches_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_table_matches_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_table_actions_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_table_actions_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_table_actions_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_entry_match_values_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_MATCH_VALUE] = { .name = "dpipe-match-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_value_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_entry_match_values_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_entry_match_values_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_entry_action_values_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_ACTION_VALUE] = { .name = "dpipe-action-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_value_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_entry_action_values_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_entry_action_values_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_header_fields_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_FIELD] = { .name = "dpipe-field", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_field_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_header_fields_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_header_fields_policy, +}; + +struct ynl_policy_attr devlink_dl_resource_list_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_RESOURCE] = { .name = "resource", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_nest, }, +}; + +struct ynl_policy_nest devlink_dl_resource_list_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_resource_list_policy, +}; + struct ynl_policy_attr devlink_dl_reload_act_info_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, @@ -91,6 +486,45 @@ struct ynl_policy_nest devlink_dl_reload_act_info_nest = { .table = devlink_dl_reload_act_info_policy, }; +struct ynl_policy_attr devlink_dl_dpipe_table_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .name = "dpipe-table-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DPIPE_TABLE_SIZE] = { .name = "dpipe-table-size", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_TABLE_MATCHES] = { .name = "dpipe-table-matches", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_matches_nest, }, + [DEVLINK_ATTR_DPIPE_TABLE_ACTIONS] = { .name = "dpipe-table-actions", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_actions_nest, }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .name = "dpipe-table-counters-enabled", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID] = { .name = "dpipe-table-resource-id", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS] = { .name = "dpipe-table-resource-units", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_table_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_table_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_entry_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_ENTRY_INDEX] = { .name = "dpipe-entry-index", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES] = { .name = "dpipe-entry-match-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_match_values_nest, }, + [DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES] = { .name = "dpipe-entry-action-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_action_values_nest, }, + [DEVLINK_ATTR_DPIPE_ENTRY_COUNTER] = { .name = "dpipe-entry-counter", .type = YNL_PT_U64, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_entry_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_entry_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_header_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_HEADER_NAME] = { .name = "dpipe-header-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DPIPE_HEADER_FIELDS] = { .name = "dpipe-header-fields", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_fields_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_header_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_header_policy, +}; + struct ynl_policy_attr devlink_dl_reload_stats_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, }; @@ -100,6 +534,33 @@ struct ynl_policy_nest devlink_dl_reload_stats_nest = { .table = devlink_dl_reload_stats_policy, }; +struct ynl_policy_attr devlink_dl_dpipe_tables_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_TABLE] = { .name = "dpipe-table", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_tables_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_tables_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_entries_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_ENTRY] = { .name = "dpipe-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_entries_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_entries_policy, +}; + +struct ynl_policy_attr devlink_dl_dpipe_headers_policy[DEVLINK_ATTR_MAX + 1] = { + [DEVLINK_ATTR_DPIPE_HEADER] = { .name = "dpipe-header", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_nest, }, +}; + +struct ynl_policy_nest devlink_dl_dpipe_headers_nest = { + .max_attr = DEVLINK_ATTR_MAX, + .table = devlink_dl_dpipe_headers_policy, +}; + struct ynl_policy_attr devlink_dl_dev_stats_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, @@ -114,12 +575,75 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .name = "bus-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_DEV_NAME] = { .name = "dev-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_PORT_INDEX] = { .name = "port-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_PORT_TYPE] = { .name = "port-type", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .name = "port-split-count", .type = YNL_PT_U32, }, [DEVLINK_ATTR_SB_INDEX] = { .name = "sb-index", .type = YNL_PT_U32, }, [DEVLINK_ATTR_SB_POOL_INDEX] = { .name = "sb-pool-index", .type = YNL_PT_U16, }, [DEVLINK_ATTR_SB_POOL_TYPE] = { .name = "sb-pool-type", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_SB_POOL_SIZE] = { .name = "sb-pool-size", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .name = "sb-pool-threshold-type", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_SB_THRESHOLD] = { .name = "sb-threshold", .type = YNL_PT_U32, }, [DEVLINK_ATTR_SB_TC_INDEX] = { .name = "sb-tc-index", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_ESWITCH_MODE] = { .name = "eswitch-mode", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .name = "eswitch-inline-mode", .type = YNL_PT_U16, }, + [DEVLINK_ATTR_DPIPE_TABLES] = { .name = "dpipe-tables", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_tables_nest, }, + [DEVLINK_ATTR_DPIPE_TABLE] = { .name = "dpipe-table", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_nest, }, + [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .name = "dpipe-table-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DPIPE_TABLE_SIZE] = { .name = "dpipe-table-size", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_TABLE_MATCHES] = { .name = "dpipe-table-matches", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_matches_nest, }, + [DEVLINK_ATTR_DPIPE_TABLE_ACTIONS] = { .name = "dpipe-table-actions", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_table_actions_nest, }, + [DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .name = "dpipe-table-counters-enabled", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DPIPE_ENTRIES] = { .name = "dpipe-entries", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entries_nest, }, + [DEVLINK_ATTR_DPIPE_ENTRY] = { .name = "dpipe-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_nest, }, + [DEVLINK_ATTR_DPIPE_ENTRY_INDEX] = { .name = "dpipe-entry-index", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES] = { .name = "dpipe-entry-match-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_match_values_nest, }, + [DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES] = { .name = "dpipe-entry-action-values", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_entry_action_values_nest, }, + [DEVLINK_ATTR_DPIPE_ENTRY_COUNTER] = { .name = "dpipe-entry-counter", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_MATCH] = { .name = "dpipe-match", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_nest, }, + [DEVLINK_ATTR_DPIPE_MATCH_VALUE] = { .name = "dpipe-match-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_match_value_nest, }, + [DEVLINK_ATTR_DPIPE_MATCH_TYPE] = { .name = "dpipe-match-type", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_ACTION] = { .name = "dpipe-action", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_nest, }, + [DEVLINK_ATTR_DPIPE_ACTION_VALUE] = { .name = "dpipe-action-value", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_action_value_nest, }, + [DEVLINK_ATTR_DPIPE_ACTION_TYPE] = { .name = "dpipe-action-type", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_VALUE] = { .name = "dpipe-value", .type = YNL_PT_BINARY,}, + [DEVLINK_ATTR_DPIPE_VALUE_MASK] = { .name = "dpipe-value-mask", .type = YNL_PT_BINARY,}, + [DEVLINK_ATTR_DPIPE_VALUE_MAPPING] = { .name = "dpipe-value-mapping", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADERS] = { .name = "dpipe-headers", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_headers_nest, }, + [DEVLINK_ATTR_DPIPE_HEADER] = { .name = "dpipe-header", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_nest, }, + [DEVLINK_ATTR_DPIPE_HEADER_NAME] = { .name = "dpipe-header-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DPIPE_HEADER_ID] = { .name = "dpipe-header-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_HEADER_FIELDS] = { .name = "dpipe-header-fields", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_header_fields_nest, }, + [DEVLINK_ATTR_DPIPE_HEADER_GLOBAL] = { .name = "dpipe-header-global", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_DPIPE_HEADER_INDEX] = { .name = "dpipe-header-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD] = { .name = "dpipe-field", .type = YNL_PT_NEST, .nest = &devlink_dl_dpipe_field_nest, }, + [DEVLINK_ATTR_DPIPE_FIELD_NAME] = { .name = "dpipe-field-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_DPIPE_FIELD_ID] = { .name = "dpipe-field-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH] = { .name = "dpipe-field-bitwidth", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE] = { .name = "dpipe-field-mapping-type", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_PAD] = { .name = "pad", .type = YNL_PT_IGNORE, }, + [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .name = "eswitch-encap-mode", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RESOURCE_LIST] = { .name = "resource-list", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_list_nest, }, + [DEVLINK_ATTR_RESOURCE] = { .name = "resource", .type = YNL_PT_NEST, .nest = &devlink_dl_resource_nest, }, + [DEVLINK_ATTR_RESOURCE_NAME] = { .name = "resource-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_RESOURCE_ID] = { .name = "resource-id", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE] = { .name = "resource-size", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_NEW] = { .name = "resource-size-new", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_VALID] = { .name = "resource-size-valid", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RESOURCE_SIZE_MIN] = { .name = "resource-size-min", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_MAX] = { .name = "resource-size-max", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_SIZE_GRAN] = { .name = "resource-size-gran", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RESOURCE_UNIT] = { .name = "resource-unit", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RESOURCE_OCC] = { .name = "resource-occ", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID] = { .name = "dpipe-table-resource-id", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS] = { .name = "dpipe-table-resource-units", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_PORT_FLAVOUR] = { .name = "port-flavour", .type = YNL_PT_U16, }, [DEVLINK_ATTR_PARAM_NAME] = { .name = "param-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_PARAM_TYPE] = { .name = "param-type", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .name = "param-value-cmode", .type = YNL_PT_U8, }, [DEVLINK_ATTR_REGION_NAME] = { .name = "region-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .name = "region-snapshot-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .name = "region-chunk-addr", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .name = "region-chunk-len", .type = YNL_PT_U64, }, [DEVLINK_ATTR_INFO_DRIVER_NAME] = { .name = "info-driver-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_SERIAL_NUMBER] = { .name = "info-serial-number", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_FIXED] = { .name = "info-version-fixed", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, @@ -127,12 +651,35 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_INFO_VERSION_STORED] = { .name = "info-version-stored", .type = YNL_PT_NEST, .nest = &devlink_dl_info_version_nest, }, [DEVLINK_ATTR_INFO_VERSION_NAME] = { .name = "info-version-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_INFO_VERSION_VALUE] = { .name = "info-version-value", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_FMSG] = { .name = "fmsg", .type = YNL_PT_NEST, .nest = &devlink_dl_fmsg_nest, }, + [DEVLINK_ATTR_FMSG_OBJ_NEST_START] = { .name = "fmsg-obj-nest-start", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_PAIR_NEST_START] = { .name = "fmsg-pair-nest-start", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_ARR_NEST_START] = { .name = "fmsg-arr-nest-start", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_NEST_END] = { .name = "fmsg-nest-end", .type = YNL_PT_FLAG, }, + [DEVLINK_ATTR_FMSG_OBJ_NAME] = { .name = "fmsg-obj-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .name = "health-reporter-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .name = "health-reporter-graceful-period", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .name = "health-reporter-auto-recover", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .name = "flash-update-file-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .name = "flash-update-component", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_PORT_PCI_PF_NUMBER] = { .name = "port-pci-pf-number", .type = YNL_PT_U16, }, [DEVLINK_ATTR_TRAP_NAME] = { .name = "trap-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_TRAP_ACTION] = { .name = "trap-action", .type = YNL_PT_U8, }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .name = "trap-group-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_RELOAD_FAILED] = { .name = "reload-failed", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_NETNS_FD] = { .name = "netns-fd", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_NETNS_PID] = { .name = "netns-pid", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_NETNS_ID] = { .name = "netns-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP] = { .name = "health-reporter-auto-dump", .type = YNL_PT_U8, }, [DEVLINK_ATTR_TRAP_POLICER_ID] = { .name = "trap-policer-id", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .name = "trap-policer-rate", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .name = "trap-policer-burst", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_PORT_FUNCTION] = { .name = "port-function", .type = YNL_PT_NEST, .nest = &devlink_dl_port_function_nest, }, + [DEVLINK_ATTR_PORT_CONTROLLER_NUMBER] = { .name = "port-controller-number", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = { .name = "flash-update-overwrite-mask", .type = YNL_PT_BITFIELD32, }, [DEVLINK_ATTR_RELOAD_ACTION] = { .name = "reload-action", .type = YNL_PT_U8, }, + [DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED] = { .name = "reload-actions-performed", .type = YNL_PT_BITFIELD32, }, + [DEVLINK_ATTR_RELOAD_LIMITS] = { .name = "reload-limits", .type = YNL_PT_BITFIELD32, }, [DEVLINK_ATTR_DEV_STATS] = { .name = "dev-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_dev_stats_nest, }, [DEVLINK_ATTR_RELOAD_STATS] = { .name = "reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, [DEVLINK_ATTR_RELOAD_STATS_ENTRY] = { .name = "reload-stats-entry", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_entry_nest, }, @@ -141,8 +688,17 @@ struct ynl_policy_attr devlink_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_REMOTE_RELOAD_STATS] = { .name = "remote-reload-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_stats_nest, }, [DEVLINK_ATTR_RELOAD_ACTION_INFO] = { .name = "reload-action-info", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_info_nest, }, [DEVLINK_ATTR_RELOAD_ACTION_STATS] = { .name = "reload-action-stats", .type = YNL_PT_NEST, .nest = &devlink_dl_reload_act_stats_nest, }, + [DEVLINK_ATTR_PORT_PCI_SF_NUMBER] = { .name = "port-pci-sf-number", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_RATE_TX_SHARE] = { .name = "rate-tx-share", .type = YNL_PT_U64, }, + [DEVLINK_ATTR_RATE_TX_MAX] = { .name = "rate-tx-max", .type = YNL_PT_U64, }, [DEVLINK_ATTR_RATE_NODE_NAME] = { .name = "rate-node-name", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_RATE_PARENT_NODE_NAME] = { .name = "rate-parent-node-name", .type = YNL_PT_NUL_STR, }, [DEVLINK_ATTR_LINECARD_INDEX] = { .name = "linecard-index", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_LINECARD_TYPE] = { .name = "linecard-type", .type = YNL_PT_NUL_STR, }, + [DEVLINK_ATTR_SELFTESTS] = { .name = "selftests", .type = YNL_PT_NEST, .nest = &devlink_dl_selftest_id_nest, }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .name = "rate-tx-priority", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .name = "rate-tx-weight", .type = YNL_PT_U32, }, + [DEVLINK_ATTR_REGION_DIRECT] = { .name = "region-direct", .type = YNL_PT_FLAG, }, }; struct ynl_policy_nest devlink_nest = { @@ -151,6 +707,370 @@ struct ynl_policy_nest devlink_nest = { }; /* Common nested types */ +void devlink_dl_dpipe_match_free(struct devlink_dl_dpipe_match *obj) +{ +} + +int devlink_dl_dpipe_match_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_match *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_MATCH_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_match_type = 1; + dst->dpipe_match_type = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_id = 1; + dst->dpipe_header_id = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_global = 1; + dst->dpipe_header_global = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_index = 1; + dst->dpipe_header_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_field_id = 1; + dst->dpipe_field_id = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void +devlink_dl_dpipe_match_value_free(struct devlink_dl_dpipe_match_value *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_match; i++) + devlink_dl_dpipe_match_free(&obj->dpipe_match[i]); + free(obj->dpipe_match); + free(obj->dpipe_value); + free(obj->dpipe_value_mask); +} + +int devlink_dl_dpipe_match_value_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_match_value *dst = yarg->data; + unsigned int n_dpipe_match = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_match) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-match-value.dpipe-match)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_MATCH) { + n_dpipe_match++; + } else if (type == DEVLINK_ATTR_DPIPE_VALUE) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.dpipe_value_len = len; + dst->dpipe_value = malloc(len); + memcpy(dst->dpipe_value, mnl_attr_get_payload(attr), len); + } else if (type == DEVLINK_ATTR_DPIPE_VALUE_MASK) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.dpipe_value_mask_len = len; + dst->dpipe_value_mask = malloc(len); + memcpy(dst->dpipe_value_mask, mnl_attr_get_payload(attr), len); + } else if (type == DEVLINK_ATTR_DPIPE_VALUE_MAPPING) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_value_mapping = 1; + dst->dpipe_value_mapping = mnl_attr_get_u32(attr); + } + } + + if (n_dpipe_match) { + dst->dpipe_match = calloc(n_dpipe_match, sizeof(*dst->dpipe_match)); + dst->n_dpipe_match = n_dpipe_match; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_match_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH) { + parg.data = &dst->dpipe_match[i]; + if (devlink_dl_dpipe_match_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_dpipe_action_free(struct devlink_dl_dpipe_action *obj) +{ +} + +int devlink_dl_dpipe_action_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_action *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_ACTION_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_action_type = 1; + dst->dpipe_action_type = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_id = 1; + dst->dpipe_header_id = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_global = 1; + dst->dpipe_header_global = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_index = 1; + dst->dpipe_header_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_field_id = 1; + dst->dpipe_field_id = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void +devlink_dl_dpipe_action_value_free(struct devlink_dl_dpipe_action_value *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_action; i++) + devlink_dl_dpipe_action_free(&obj->dpipe_action[i]); + free(obj->dpipe_action); + free(obj->dpipe_value); + free(obj->dpipe_value_mask); +} + +int devlink_dl_dpipe_action_value_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_action_value *dst = yarg->data; + unsigned int n_dpipe_action = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_action) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-action-value.dpipe-action)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_ACTION) { + n_dpipe_action++; + } else if (type == DEVLINK_ATTR_DPIPE_VALUE) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.dpipe_value_len = len; + dst->dpipe_value = malloc(len); + memcpy(dst->dpipe_value, mnl_attr_get_payload(attr), len); + } else if (type == DEVLINK_ATTR_DPIPE_VALUE_MASK) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = mnl_attr_get_payload_len(attr); + dst->_present.dpipe_value_mask_len = len; + dst->dpipe_value_mask = malloc(len); + memcpy(dst->dpipe_value_mask, mnl_attr_get_payload(attr), len); + } else if (type == DEVLINK_ATTR_DPIPE_VALUE_MAPPING) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_value_mapping = 1; + dst->dpipe_value_mapping = mnl_attr_get_u32(attr); + } + } + + if (n_dpipe_action) { + dst->dpipe_action = calloc(n_dpipe_action, sizeof(*dst->dpipe_action)); + dst->n_dpipe_action = n_dpipe_action; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_action_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION) { + parg.data = &dst->dpipe_action[i]; + if (devlink_dl_dpipe_action_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_dpipe_field_free(struct devlink_dl_dpipe_field *obj) +{ + free(obj->dpipe_field_name); +} + +int devlink_dl_dpipe_field_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_field *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_FIELD_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dpipe_field_name_len = len; + dst->dpipe_field_name = malloc(len + 1); + memcpy(dst->dpipe_field_name, mnl_attr_get_str(attr), len); + dst->dpipe_field_name[len] = 0; + } else if (type == DEVLINK_ATTR_DPIPE_FIELD_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_field_id = 1; + dst->dpipe_field_id = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_FIELD_BITWIDTH) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_field_bitwidth = 1; + dst->dpipe_field_bitwidth = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_FIELD_MAPPING_TYPE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_field_mapping_type = 1; + dst->dpipe_field_mapping_type = mnl_attr_get_u32(attr); + } + } + + return 0; +} + +void devlink_dl_resource_free(struct devlink_dl_resource *obj) +{ + free(obj->resource_name); +} + +int devlink_dl_resource_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_resource *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RESOURCE_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.resource_name_len = len; + dst->resource_name = malloc(len + 1); + memcpy(dst->resource_name, mnl_attr_get_str(attr), len); + dst->resource_name[len] = 0; + } else if (type == DEVLINK_ATTR_RESOURCE_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_id = 1; + dst->resource_id = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_size = 1; + dst->resource_size = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_SIZE_NEW) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_size_new = 1; + dst->resource_size_new = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_SIZE_VALID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_size_valid = 1; + dst->resource_size_valid = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_SIZE_MIN) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_size_min = 1; + dst->resource_size_min = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_SIZE_MAX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_size_max = 1; + dst->resource_size_max = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_SIZE_GRAN) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_size_gran = 1; + dst->resource_size_gran = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_UNIT) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_unit = 1; + dst->resource_unit = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_RESOURCE_OCC) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_occ = 1; + dst->resource_occ = mnl_attr_get_u64(attr); + } + } + + return 0; +} + void devlink_dl_info_version_free(struct devlink_dl_info_version *obj) { free(obj->info_version_name); @@ -194,6 +1114,77 @@ int devlink_dl_info_version_parse(struct ynl_parse_arg *yarg, return 0; } +void devlink_dl_fmsg_free(struct devlink_dl_fmsg *obj) +{ + free(obj->fmsg_obj_name); +} + +int devlink_dl_fmsg_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_fmsg *dst = yarg->data; + const struct nlattr *attr; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_FMSG_OBJ_NEST_START) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.fmsg_obj_nest_start = 1; + } else if (type == DEVLINK_ATTR_FMSG_PAIR_NEST_START) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.fmsg_pair_nest_start = 1; + } else if (type == DEVLINK_ATTR_FMSG_ARR_NEST_START) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.fmsg_arr_nest_start = 1; + } else if (type == DEVLINK_ATTR_FMSG_NEST_END) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.fmsg_nest_end = 1; + } else if (type == DEVLINK_ATTR_FMSG_OBJ_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.fmsg_obj_name_len = len; + dst->fmsg_obj_name = malloc(len + 1); + memcpy(dst->fmsg_obj_name, mnl_attr_get_str(attr), len); + dst->fmsg_obj_name[len] = 0; + } + } + + return 0; +} + +void devlink_dl_port_function_free(struct devlink_dl_port_function *obj) +{ + free(obj->hw_addr); +} + +int devlink_dl_port_function_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct devlink_dl_port_function *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.hw_addr_len) + mnl_attr_put(nlh, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, obj->_present.hw_addr_len, obj->hw_addr); + if (obj->_present.state) + mnl_attr_put_u8(nlh, DEVLINK_PORT_FN_ATTR_STATE, obj->state); + if (obj->_present.opstate) + mnl_attr_put_u8(nlh, DEVLINK_PORT_FN_ATTR_OPSTATE, obj->opstate); + if (obj->_present.caps) + mnl_attr_put(nlh, DEVLINK_PORT_FN_ATTR_CAPS, sizeof(struct nla_bitfield32), &obj->caps); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + void devlink_dl_reload_stats_entry_free(struct devlink_dl_reload_stats_entry *obj) { @@ -273,6 +1264,322 @@ int devlink_dl_reload_act_stats_parse(struct ynl_parse_arg *yarg, return 0; } +void devlink_dl_selftest_id_free(struct devlink_dl_selftest_id *obj) +{ +} + +int devlink_dl_selftest_id_put(struct nlmsghdr *nlh, unsigned int attr_type, + struct devlink_dl_selftest_id *obj) +{ + struct nlattr *nest; + + nest = mnl_attr_nest_start(nlh, attr_type); + if (obj->_present.flash) + mnl_attr_put(nlh, DEVLINK_ATTR_SELFTEST_ID_FLASH, 0, NULL); + mnl_attr_nest_end(nlh, nest); + + return 0; +} + +void +devlink_dl_dpipe_table_matches_free(struct devlink_dl_dpipe_table_matches *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_match; i++) + devlink_dl_dpipe_match_free(&obj->dpipe_match[i]); + free(obj->dpipe_match); +} + +int devlink_dl_dpipe_table_matches_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_table_matches *dst = yarg->data; + unsigned int n_dpipe_match = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_match) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-table-matches.dpipe-match)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_MATCH) { + n_dpipe_match++; + } + } + + if (n_dpipe_match) { + dst->dpipe_match = calloc(n_dpipe_match, sizeof(*dst->dpipe_match)); + dst->n_dpipe_match = n_dpipe_match; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_match_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH) { + parg.data = &dst->dpipe_match[i]; + if (devlink_dl_dpipe_match_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void +devlink_dl_dpipe_table_actions_free(struct devlink_dl_dpipe_table_actions *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_action; i++) + devlink_dl_dpipe_action_free(&obj->dpipe_action[i]); + free(obj->dpipe_action); +} + +int devlink_dl_dpipe_table_actions_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_table_actions *dst = yarg->data; + unsigned int n_dpipe_action = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_action) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-table-actions.dpipe-action)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_ACTION) { + n_dpipe_action++; + } + } + + if (n_dpipe_action) { + dst->dpipe_action = calloc(n_dpipe_action, sizeof(*dst->dpipe_action)); + dst->n_dpipe_action = n_dpipe_action; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_action_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION) { + parg.data = &dst->dpipe_action[i]; + if (devlink_dl_dpipe_action_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void +devlink_dl_dpipe_entry_match_values_free(struct devlink_dl_dpipe_entry_match_values *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_match_value; i++) + devlink_dl_dpipe_match_value_free(&obj->dpipe_match_value[i]); + free(obj->dpipe_match_value); +} + +int devlink_dl_dpipe_entry_match_values_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_entry_match_values *dst = yarg->data; + unsigned int n_dpipe_match_value = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_match_value) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entry-match-values.dpipe-match-value)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_MATCH_VALUE) { + n_dpipe_match_value++; + } + } + + if (n_dpipe_match_value) { + dst->dpipe_match_value = calloc(n_dpipe_match_value, sizeof(*dst->dpipe_match_value)); + dst->n_dpipe_match_value = n_dpipe_match_value; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_match_value_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_MATCH_VALUE) { + parg.data = &dst->dpipe_match_value[i]; + if (devlink_dl_dpipe_match_value_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void +devlink_dl_dpipe_entry_action_values_free(struct devlink_dl_dpipe_entry_action_values *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_action_value; i++) + devlink_dl_dpipe_action_value_free(&obj->dpipe_action_value[i]); + free(obj->dpipe_action_value); +} + +int devlink_dl_dpipe_entry_action_values_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_entry_action_values *dst = yarg->data; + unsigned int n_dpipe_action_value = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_action_value) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entry-action-values.dpipe-action-value)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_ACTION_VALUE) { + n_dpipe_action_value++; + } + } + + if (n_dpipe_action_value) { + dst->dpipe_action_value = calloc(n_dpipe_action_value, sizeof(*dst->dpipe_action_value)); + dst->n_dpipe_action_value = n_dpipe_action_value; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_action_value_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ACTION_VALUE) { + parg.data = &dst->dpipe_action_value[i]; + if (devlink_dl_dpipe_action_value_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void +devlink_dl_dpipe_header_fields_free(struct devlink_dl_dpipe_header_fields *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_field; i++) + devlink_dl_dpipe_field_free(&obj->dpipe_field[i]); + free(obj->dpipe_field); +} + +int devlink_dl_dpipe_header_fields_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_header_fields *dst = yarg->data; + unsigned int n_dpipe_field = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_field) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-header-fields.dpipe-field)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_FIELD) { + n_dpipe_field++; + } + } + + if (n_dpipe_field) { + dst->dpipe_field = calloc(n_dpipe_field, sizeof(*dst->dpipe_field)); + dst->n_dpipe_field = n_dpipe_field; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_field_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_FIELD) { + parg.data = &dst->dpipe_field[i]; + if (devlink_dl_dpipe_field_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_resource_list_free(struct devlink_dl_resource_list *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_resource; i++) + devlink_dl_resource_free(&obj->resource[i]); + free(obj->resource); +} + +int devlink_dl_resource_list_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_resource_list *dst = yarg->data; + unsigned int n_resource = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->resource) + return ynl_error_parse(yarg, "attribute already present (dl-resource-list.resource)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_RESOURCE) { + n_resource++; + } + } + + if (n_resource) { + dst->resource = calloc(n_resource, sizeof(*dst->resource)); + dst->n_resource = n_resource; + i = 0; + parg.rsp_policy = &devlink_dl_resource_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_RESOURCE) { + parg.data = &dst->resource[i]; + if (devlink_dl_resource_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + void devlink_dl_reload_act_info_free(struct devlink_dl_reload_act_info *obj) { unsigned int i; @@ -327,6 +1634,186 @@ int devlink_dl_reload_act_info_parse(struct ynl_parse_arg *yarg, return 0; } +void devlink_dl_dpipe_table_free(struct devlink_dl_dpipe_table *obj) +{ + free(obj->dpipe_table_name); + devlink_dl_dpipe_table_matches_free(&obj->dpipe_table_matches); + devlink_dl_dpipe_table_actions_free(&obj->dpipe_table_actions); +} + +int devlink_dl_dpipe_table_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_table *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_TABLE_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dpipe_table_name_len = len; + dst->dpipe_table_name = malloc(len + 1); + memcpy(dst->dpipe_table_name, mnl_attr_get_str(attr), len); + dst->dpipe_table_name[len] = 0; + } else if (type == DEVLINK_ATTR_DPIPE_TABLE_SIZE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_table_size = 1; + dst->dpipe_table_size = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_DPIPE_TABLE_MATCHES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_table_matches = 1; + + parg.rsp_policy = &devlink_dl_dpipe_table_matches_nest; + parg.data = &dst->dpipe_table_matches; + if (devlink_dl_dpipe_table_matches_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == DEVLINK_ATTR_DPIPE_TABLE_ACTIONS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_table_actions = 1; + + parg.rsp_policy = &devlink_dl_dpipe_table_actions_nest; + parg.data = &dst->dpipe_table_actions; + if (devlink_dl_dpipe_table_actions_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_table_counters_enabled = 1; + dst->dpipe_table_counters_enabled = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_table_resource_id = 1; + dst->dpipe_table_resource_id = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_DPIPE_TABLE_RESOURCE_UNITS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_table_resource_units = 1; + dst->dpipe_table_resource_units = mnl_attr_get_u64(attr); + } + } + + return 0; +} + +void devlink_dl_dpipe_entry_free(struct devlink_dl_dpipe_entry *obj) +{ + devlink_dl_dpipe_entry_match_values_free(&obj->dpipe_entry_match_values); + devlink_dl_dpipe_entry_action_values_free(&obj->dpipe_entry_action_values); +} + +int devlink_dl_dpipe_entry_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_entry *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_ENTRY_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_entry_index = 1; + dst->dpipe_entry_index = mnl_attr_get_u64(attr); + } else if (type == DEVLINK_ATTR_DPIPE_ENTRY_MATCH_VALUES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_entry_match_values = 1; + + parg.rsp_policy = &devlink_dl_dpipe_entry_match_values_nest; + parg.data = &dst->dpipe_entry_match_values; + if (devlink_dl_dpipe_entry_match_values_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == DEVLINK_ATTR_DPIPE_ENTRY_ACTION_VALUES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_entry_action_values = 1; + + parg.rsp_policy = &devlink_dl_dpipe_entry_action_values_nest; + parg.data = &dst->dpipe_entry_action_values; + if (devlink_dl_dpipe_entry_action_values_parse(&parg, attr)) + return MNL_CB_ERROR; + } else if (type == DEVLINK_ATTR_DPIPE_ENTRY_COUNTER) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_entry_counter = 1; + dst->dpipe_entry_counter = mnl_attr_get_u64(attr); + } + } + + return 0; +} + +void devlink_dl_dpipe_header_free(struct devlink_dl_dpipe_header *obj) +{ + free(obj->dpipe_header_name); + devlink_dl_dpipe_header_fields_free(&obj->dpipe_header_fields); +} + +int devlink_dl_dpipe_header_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_header *dst = yarg->data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + parg.ys = yarg->ys; + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_HEADER_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dpipe_header_name_len = len; + dst->dpipe_header_name = malloc(len + 1); + memcpy(dst->dpipe_header_name, mnl_attr_get_str(attr), len); + dst->dpipe_header_name[len] = 0; + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_id = 1; + dst->dpipe_header_id = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_GLOBAL) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_global = 1; + dst->dpipe_header_global = mnl_attr_get_u8(attr); + } else if (type == DEVLINK_ATTR_DPIPE_HEADER_FIELDS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_header_fields = 1; + + parg.rsp_policy = &devlink_dl_dpipe_header_fields_nest; + parg.data = &dst->dpipe_header_fields; + if (devlink_dl_dpipe_header_fields_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return 0; +} + void devlink_dl_reload_stats_free(struct devlink_dl_reload_stats *obj) { unsigned int i; @@ -376,6 +1863,153 @@ int devlink_dl_reload_stats_parse(struct ynl_parse_arg *yarg, return 0; } +void devlink_dl_dpipe_tables_free(struct devlink_dl_dpipe_tables *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_table; i++) + devlink_dl_dpipe_table_free(&obj->dpipe_table[i]); + free(obj->dpipe_table); +} + +int devlink_dl_dpipe_tables_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_tables *dst = yarg->data; + unsigned int n_dpipe_table = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_table) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-tables.dpipe-table)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_TABLE) { + n_dpipe_table++; + } + } + + if (n_dpipe_table) { + dst->dpipe_table = calloc(n_dpipe_table, sizeof(*dst->dpipe_table)); + dst->n_dpipe_table = n_dpipe_table; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_table_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_TABLE) { + parg.data = &dst->dpipe_table[i]; + if (devlink_dl_dpipe_table_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_dpipe_entries_free(struct devlink_dl_dpipe_entries *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_entry; i++) + devlink_dl_dpipe_entry_free(&obj->dpipe_entry[i]); + free(obj->dpipe_entry); +} + +int devlink_dl_dpipe_entries_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_entries *dst = yarg->data; + unsigned int n_dpipe_entry = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_entry) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-entries.dpipe-entry)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_ENTRY) { + n_dpipe_entry++; + } + } + + if (n_dpipe_entry) { + dst->dpipe_entry = calloc(n_dpipe_entry, sizeof(*dst->dpipe_entry)); + dst->n_dpipe_entry = n_dpipe_entry; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_entry_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_ENTRY) { + parg.data = &dst->dpipe_entry[i]; + if (devlink_dl_dpipe_entry_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + +void devlink_dl_dpipe_headers_free(struct devlink_dl_dpipe_headers *obj) +{ + unsigned int i; + + for (i = 0; i < obj->n_dpipe_header; i++) + devlink_dl_dpipe_header_free(&obj->dpipe_header[i]); + free(obj->dpipe_header); +} + +int devlink_dl_dpipe_headers_parse(struct ynl_parse_arg *yarg, + const struct nlattr *nested) +{ + struct devlink_dl_dpipe_headers *dst = yarg->data; + unsigned int n_dpipe_header = 0; + const struct nlattr *attr; + struct ynl_parse_arg parg; + int i; + + parg.ys = yarg->ys; + + if (dst->dpipe_header) + return ynl_error_parse(yarg, "attribute already present (dl-dpipe-headers.dpipe-header)"); + + mnl_attr_for_each_nested(attr, nested) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_DPIPE_HEADER) { + n_dpipe_header++; + } + } + + if (n_dpipe_header) { + dst->dpipe_header = calloc(n_dpipe_header, sizeof(*dst->dpipe_header)); + dst->n_dpipe_header = n_dpipe_header; + i = 0; + parg.rsp_policy = &devlink_dl_dpipe_header_nest; + mnl_attr_for_each_nested(attr, nested) { + if (mnl_attr_get_type(attr) == DEVLINK_ATTR_DPIPE_HEADER) { + parg.data = &dst->dpipe_header[i]; + if (devlink_dl_dpipe_header_parse(&parg, attr)) + return MNL_CB_ERROR; + i++; + } + } + } + + return 0; +} + void devlink_dl_dev_stats_free(struct devlink_dl_dev_stats *obj) { devlink_dl_reload_stats_free(&obj->reload_stats); @@ -475,11 +2109,6 @@ int devlink_get_rsp_parse(const struct nlmsghdr *nlh, void *data) return MNL_CB_ERROR; dst->_present.reload_failed = 1; dst->reload_failed = mnl_attr_get_u8(attr); - } else if (type == DEVLINK_ATTR_RELOAD_ACTION) { - if (ynl_attr_validate(yarg, attr)) - return MNL_CB_ERROR; - dst->_present.reload_action = 1; - dst->reload_action = mnl_attr_get_u8(attr); } else if (type == DEVLINK_ATTR_DEV_STATS) { if (ynl_attr_validate(yarg, attr)) return MNL_CB_ERROR; @@ -756,6 +2385,241 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_PORT_SET ============== */ +/* DEVLINK_CMD_PORT_SET - do */ +void devlink_port_set_req_free(struct devlink_port_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + devlink_dl_port_function_free(&req->port_function); + free(req); +} + +int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.port_type) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_TYPE, req->port_type); + if (req->_present.port_function) + devlink_dl_port_function_put(nlh, DEVLINK_ATTR_PORT_FUNCTION, &req->port_function); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_PORT_NEW ============== */ +/* DEVLINK_CMD_PORT_NEW - do */ +void devlink_port_new_req_free(struct devlink_port_new_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_port_new_rsp_free(struct devlink_port_new_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_port_new_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_port_new_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_port_new_rsp * +devlink_port_new(struct ynl_sock *ys, struct devlink_port_new_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_port_new_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_NEW, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.port_flavour) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_FLAVOUR, req->port_flavour); + if (req->_present.port_pci_pf_number) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, req->port_pci_pf_number); + if (req->_present.port_pci_sf_number) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_PCI_SF_NUMBER, req->port_pci_sf_number); + if (req->_present.port_controller_number) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, req->port_controller_number); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_port_new_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_PORT_NEW; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_port_new_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_PORT_DEL ============== */ +/* DEVLINK_CMD_PORT_DEL - do */ +void devlink_port_del_req_free(struct devlink_port_del_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_DEL, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_PORT_SPLIT ============== */ +/* DEVLINK_CMD_PORT_SPLIT - do */ +void devlink_port_split_req_free(struct devlink_port_split_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_SPLIT, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.port_split_count) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_SPLIT_COUNT, req->port_split_count); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_PORT_UNSPLIT ============== */ +/* DEVLINK_CMD_PORT_UNSPLIT - do */ +void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_port_unsplit(struct ynl_sock *ys, + struct devlink_port_unsplit_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_UNSPLIT, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_SB_GET ============== */ /* DEVLINK_CMD_SB_GET - do */ void devlink_sb_get_req_free(struct devlink_sb_get_req *req) @@ -838,7 +2702,7 @@ devlink_sb_get(struct ynl_sock *ys, struct devlink_sb_get_req *req) rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_sb_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_SB_GET; + yrs.rsp_cmd = 13; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -876,7 +2740,7 @@ devlink_sb_get_dump(struct ynl_sock *ys, struct devlink_sb_get_req_dump *req) yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_sb_get_list); yds.cb = devlink_sb_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_SB_GET; + yds.rsp_cmd = 13; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_GET, 1); @@ -987,7 +2851,7 @@ devlink_sb_pool_get(struct ynl_sock *ys, struct devlink_sb_pool_get_req *req) rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_sb_pool_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_SB_POOL_GET; + yrs.rsp_cmd = 17; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -1026,7 +2890,7 @@ devlink_sb_pool_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_sb_pool_get_list); yds.cb = devlink_sb_pool_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_SB_POOL_GET; + yds.rsp_cmd = 17; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_POOL_GET, 1); @@ -1048,6 +2912,44 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_SB_POOL_SET ============== */ +/* DEVLINK_CMD_SB_POOL_SET - do */ +void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_sb_pool_set(struct ynl_sock *ys, + struct devlink_sb_pool_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_POOL_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + if (req->_present.sb_pool_threshold_type) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, req->sb_pool_threshold_type); + if (req->_present.sb_pool_size) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_POOL_SIZE, req->sb_pool_size); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */ /* DEVLINK_CMD_SB_PORT_POOL_GET - do */ void @@ -1147,7 +3049,7 @@ devlink_sb_port_pool_get(struct ynl_sock *ys, rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_sb_port_pool_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET; + yrs.rsp_cmd = 21; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -1187,7 +3089,7 @@ devlink_sb_port_pool_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_sb_port_pool_get_list); yds.cb = devlink_sb_port_pool_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_SB_PORT_POOL_GET; + yds.rsp_cmd = 21; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_GET, 1); @@ -1209,6 +3111,45 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_SB_PORT_POOL_SET ============== */ +/* DEVLINK_CMD_SB_PORT_POOL_SET - do */ +void +devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_sb_port_pool_set(struct ynl_sock *ys, + struct devlink_sb_port_pool_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_PORT_POOL_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + if (req->_present.sb_threshold) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */ /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ void @@ -1316,7 +3257,7 @@ devlink_sb_tc_pool_bind_get(struct ynl_sock *ys, rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_sb_tc_pool_bind_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET; + yrs.rsp_cmd = 25; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -1356,7 +3297,7 @@ devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_sb_tc_pool_bind_get_list); yds.cb = devlink_sb_tc_pool_bind_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_SB_TC_POOL_BIND_GET; + yds.rsp_cmd = 25; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_GET, 1); @@ -1378,6 +3319,840 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_SET ============== */ +/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */ +void +devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_TC_POOL_BIND_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + if (req->_present.sb_pool_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_POOL_INDEX, req->sb_pool_index); + if (req->_present.sb_pool_type) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_SB_POOL_TYPE, req->sb_pool_type); + if (req->_present.sb_tc_index) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_SB_TC_INDEX, req->sb_tc_index); + if (req->_present.sb_threshold) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_THRESHOLD, req->sb_threshold); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_SB_OCC_SNAPSHOT ============== */ +/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */ +void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_sb_occ_snapshot(struct ynl_sock *ys, + struct devlink_sb_occ_snapshot_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_OCC_SNAPSHOT, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_SB_OCC_MAX_CLEAR ============== */ +/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */ +void +devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_sb_occ_max_clear(struct ynl_sock *ys, + struct devlink_sb_occ_max_clear_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SB_OCC_MAX_CLEAR, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.sb_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_SB_INDEX, req->sb_index); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_ESWITCH_GET ============== */ +/* DEVLINK_CMD_ESWITCH_GET - do */ +void devlink_eswitch_get_req_free(struct devlink_eswitch_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_eswitch_get_rsp_free(struct devlink_eswitch_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_eswitch_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_eswitch_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_ESWITCH_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.eswitch_mode = 1; + dst->eswitch_mode = mnl_attr_get_u16(attr); + } else if (type == DEVLINK_ATTR_ESWITCH_INLINE_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.eswitch_inline_mode = 1; + dst->eswitch_inline_mode = mnl_attr_get_u16(attr); + } else if (type == DEVLINK_ATTR_ESWITCH_ENCAP_MODE) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.eswitch_encap_mode = 1; + dst->eswitch_encap_mode = mnl_attr_get_u8(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_eswitch_get_rsp * +devlink_eswitch_get(struct ynl_sock *ys, struct devlink_eswitch_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_eswitch_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_ESWITCH_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_eswitch_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_ESWITCH_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_eswitch_get_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_ESWITCH_SET ============== */ +/* DEVLINK_CMD_ESWITCH_SET - do */ +void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_eswitch_set(struct ynl_sock *ys, + struct devlink_eswitch_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_ESWITCH_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.eswitch_mode) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_ESWITCH_MODE, req->eswitch_mode); + if (req->_present.eswitch_inline_mode) + mnl_attr_put_u16(nlh, DEVLINK_ATTR_ESWITCH_INLINE_MODE, req->eswitch_inline_mode); + if (req->_present.eswitch_encap_mode) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_ESWITCH_ENCAP_MODE, req->eswitch_encap_mode); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_DPIPE_TABLE_GET ============== */ +/* DEVLINK_CMD_DPIPE_TABLE_GET - do */ +void devlink_dpipe_table_get_req_free(struct devlink_dpipe_table_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->dpipe_table_name); + free(req); +} + +void devlink_dpipe_table_get_rsp_free(struct devlink_dpipe_table_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + devlink_dl_dpipe_tables_free(&rsp->dpipe_tables); + free(rsp); +} + +int devlink_dpipe_table_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_dpipe_table_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_DPIPE_TABLES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_tables = 1; + + parg.rsp_policy = &devlink_dl_dpipe_tables_nest; + parg.data = &dst->dpipe_tables; + if (devlink_dl_dpipe_tables_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct devlink_dpipe_table_get_rsp * +devlink_dpipe_table_get(struct ynl_sock *ys, + struct devlink_dpipe_table_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_dpipe_table_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_TABLE_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.dpipe_table_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_dpipe_table_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_DPIPE_TABLE_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_dpipe_table_get_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_DPIPE_ENTRIES_GET ============== */ +/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */ +void +devlink_dpipe_entries_get_req_free(struct devlink_dpipe_entries_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->dpipe_table_name); + free(req); +} + +void +devlink_dpipe_entries_get_rsp_free(struct devlink_dpipe_entries_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + devlink_dl_dpipe_entries_free(&rsp->dpipe_entries); + free(rsp); +} + +int devlink_dpipe_entries_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_dpipe_entries_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_DPIPE_ENTRIES) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_entries = 1; + + parg.rsp_policy = &devlink_dl_dpipe_entries_nest; + parg.data = &dst->dpipe_entries; + if (devlink_dl_dpipe_entries_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct devlink_dpipe_entries_get_rsp * +devlink_dpipe_entries_get(struct ynl_sock *ys, + struct devlink_dpipe_entries_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_dpipe_entries_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_ENTRIES_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.dpipe_table_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_dpipe_entries_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_DPIPE_ENTRIES_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_dpipe_entries_get_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_DPIPE_HEADERS_GET ============== */ +/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */ +void +devlink_dpipe_headers_get_req_free(struct devlink_dpipe_headers_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void +devlink_dpipe_headers_get_rsp_free(struct devlink_dpipe_headers_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + devlink_dl_dpipe_headers_free(&rsp->dpipe_headers); + free(rsp); +} + +int devlink_dpipe_headers_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_dpipe_headers_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_DPIPE_HEADERS) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.dpipe_headers = 1; + + parg.rsp_policy = &devlink_dl_dpipe_headers_nest; + parg.data = &dst->dpipe_headers; + if (devlink_dl_dpipe_headers_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct devlink_dpipe_headers_get_rsp * +devlink_dpipe_headers_get(struct ynl_sock *ys, + struct devlink_dpipe_headers_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_dpipe_headers_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_HEADERS_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_dpipe_headers_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_DPIPE_HEADERS_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_dpipe_headers_get_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET ============== */ +/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */ +void +devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->dpipe_table_name); + free(req); +} + +int devlink_dpipe_table_counters_set(struct ynl_sock *ys, + struct devlink_dpipe_table_counters_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.dpipe_table_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DPIPE_TABLE_NAME, req->dpipe_table_name); + if (req->_present.dpipe_table_counters_enabled) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED, req->dpipe_table_counters_enabled); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_RESOURCE_SET ============== */ +/* DEVLINK_CMD_RESOURCE_SET - do */ +void devlink_resource_set_req_free(struct devlink_resource_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_resource_set(struct ynl_sock *ys, + struct devlink_resource_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RESOURCE_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.resource_id) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_ID, req->resource_id); + if (req->_present.resource_size) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_RESOURCE_SIZE, req->resource_size); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_RESOURCE_DUMP ============== */ +/* DEVLINK_CMD_RESOURCE_DUMP - do */ +void devlink_resource_dump_req_free(struct devlink_resource_dump_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_resource_dump_rsp_free(struct devlink_resource_dump_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + devlink_dl_resource_list_free(&rsp->resource_list); + free(rsp); +} + +int devlink_resource_dump_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_resource_dump_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_RESOURCE_LIST) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.resource_list = 1; + + parg.rsp_policy = &devlink_dl_resource_list_nest; + parg.data = &dst->resource_list; + if (devlink_dl_resource_list_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +struct devlink_resource_dump_rsp * +devlink_resource_dump(struct ynl_sock *ys, + struct devlink_resource_dump_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_resource_dump_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RESOURCE_DUMP, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_resource_dump_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_RESOURCE_DUMP; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_resource_dump_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_RELOAD ============== */ +/* DEVLINK_CMD_RELOAD - do */ +void devlink_reload_req_free(struct devlink_reload_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_reload_rsp_free(struct devlink_reload_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_reload_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct ynl_parse_arg *yarg = data; + struct devlink_reload_rsp *dst; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.reload_actions_performed = 1; + memcpy(&dst->reload_actions_performed, mnl_attr_get_payload(attr), sizeof(struct nla_bitfield32)); + } + } + + return MNL_CB_OK; +} + +struct devlink_reload_rsp * +devlink_reload(struct ynl_sock *ys, struct devlink_reload_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_reload_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RELOAD, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.reload_action) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_RELOAD_ACTION, req->reload_action); + if (req->_present.reload_limits) + mnl_attr_put(nlh, DEVLINK_ATTR_RELOAD_LIMITS, sizeof(struct nla_bitfield32), &req->reload_limits); + if (req->_present.netns_pid) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_PID, req->netns_pid); + if (req->_present.netns_fd) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_FD, req->netns_fd); + if (req->_present.netns_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_NETNS_ID, req->netns_id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_reload_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_RELOAD; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_reload_rsp_free(rsp); + return NULL; +} + /* ============== DEVLINK_CMD_PARAM_GET ============== */ /* DEVLINK_CMD_PARAM_GET - do */ void devlink_param_get_req_free(struct devlink_param_get_req *req) @@ -1530,6 +4305,42 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_PARAM_SET ============== */ +/* DEVLINK_CMD_PARAM_SET - do */ +void devlink_param_set_req_free(struct devlink_param_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->param_name); + free(req); +} + +int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PARAM_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.param_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_PARAM_NAME, req->param_name); + if (req->_present.param_type) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_TYPE, req->param_type); + if (req->_present.param_value_cmode) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_PARAM_VALUE_CMODE, req->param_value_cmode); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_REGION_GET ============== */ /* DEVLINK_CMD_REGION_GET - do */ void devlink_region_get_req_free(struct devlink_region_get_req *req) @@ -1689,6 +4500,446 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_REGION_NEW ============== */ +/* DEVLINK_CMD_REGION_NEW - do */ +void devlink_region_new_req_free(struct devlink_region_new_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->region_name); + free(req); +} + +void devlink_region_new_rsp_free(struct devlink_region_new_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp->region_name); + free(rsp); +} + +int devlink_region_new_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_region_new_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_REGION_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.region_name_len = len; + dst->region_name = malloc(len + 1); + memcpy(dst->region_name, mnl_attr_get_str(attr), len); + dst->region_name[len] = 0; + } else if (type == DEVLINK_ATTR_REGION_SNAPSHOT_ID) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.region_snapshot_id = 1; + dst->region_snapshot_id = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_region_new_rsp * +devlink_region_new(struct ynl_sock *ys, struct devlink_region_new_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_region_new_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_NEW, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.region_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name); + if (req->_present.region_snapshot_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_region_new_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_REGION_NEW; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_region_new_rsp_free(rsp); + return NULL; +} + +/* ============== DEVLINK_CMD_REGION_DEL ============== */ +/* DEVLINK_CMD_REGION_DEL - do */ +void devlink_region_del_req_free(struct devlink_region_del_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->region_name); + free(req); +} + +int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_REGION_DEL, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.region_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name); + if (req->_present.region_snapshot_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_REGION_READ ============== */ +/* DEVLINK_CMD_REGION_READ - dump */ +int devlink_region_read_rsp_dump_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_region_read_rsp_dump *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } else if (type == DEVLINK_ATTR_REGION_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.region_name_len = len; + dst->region_name = malloc(len + 1); + memcpy(dst->region_name, mnl_attr_get_str(attr), len); + dst->region_name[len] = 0; + } + } + + return MNL_CB_OK; +} + +void +devlink_region_read_rsp_list_free(struct devlink_region_read_rsp_list *rsp) +{ + struct devlink_region_read_rsp_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp->obj.region_name); + free(rsp); + } +} + +struct devlink_region_read_rsp_list * +devlink_region_read_dump(struct ynl_sock *ys, + struct devlink_region_read_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_region_read_rsp_list); + yds.cb = devlink_region_read_rsp_dump_parse; + yds.rsp_cmd = DEVLINK_CMD_REGION_READ; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_REGION_READ, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.region_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_REGION_NAME, req->region_name); + if (req->_present.region_snapshot_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_REGION_SNAPSHOT_ID, req->region_snapshot_id); + if (req->_present.region_direct) + mnl_attr_put(nlh, DEVLINK_ATTR_REGION_DIRECT, 0, NULL); + if (req->_present.region_chunk_addr) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_ADDR, req->region_chunk_addr); + if (req->_present.region_chunk_len) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_REGION_CHUNK_LEN, req->region_chunk_len); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_region_read_rsp_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_PORT_PARAM_GET ============== */ +/* DEVLINK_CMD_PORT_PARAM_GET - do */ +void devlink_port_param_get_req_free(struct devlink_port_param_get_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +void devlink_port_param_get_rsp_free(struct devlink_port_param_get_rsp *rsp) +{ + free(rsp->bus_name); + free(rsp->dev_name); + free(rsp); +} + +int devlink_port_param_get_rsp_parse(const struct nlmsghdr *nlh, void *data) +{ + struct devlink_port_param_get_rsp *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + + dst = yarg->data; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_BUS_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.bus_name_len = len; + dst->bus_name = malloc(len + 1); + memcpy(dst->bus_name, mnl_attr_get_str(attr), len); + dst->bus_name[len] = 0; + } else if (type == DEVLINK_ATTR_DEV_NAME) { + unsigned int len; + + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + + len = strnlen(mnl_attr_get_str(attr), mnl_attr_get_payload_len(attr)); + dst->_present.dev_name_len = len; + dst->dev_name = malloc(len + 1); + memcpy(dst->dev_name, mnl_attr_get_str(attr), len); + dst->dev_name[len] = 0; + } else if (type == DEVLINK_ATTR_PORT_INDEX) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.port_index = 1; + dst->port_index = mnl_attr_get_u32(attr); + } + } + + return MNL_CB_OK; +} + +struct devlink_port_param_get_rsp * +devlink_port_param_get(struct ynl_sock *ys, + struct devlink_port_param_get_req *req) +{ + struct ynl_req_state yrs = { .yarg = { .ys = ys, }, }; + struct devlink_port_param_get_rsp *rsp; + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_GET, 1); + ys->req_policy = &devlink_nest; + yrs.yarg.rsp_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + rsp = calloc(1, sizeof(*rsp)); + yrs.yarg.data = rsp; + yrs.cb = devlink_port_param_get_rsp_parse; + yrs.rsp_cmd = DEVLINK_CMD_PORT_PARAM_GET; + + err = ynl_exec(ys, nlh, &yrs); + if (err < 0) + goto err_free; + + return rsp; + +err_free: + devlink_port_param_get_rsp_free(rsp); + return NULL; +} + +/* DEVLINK_CMD_PORT_PARAM_GET - dump */ +void devlink_port_param_get_list_free(struct devlink_port_param_get_list *rsp) +{ + struct devlink_port_param_get_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + free(rsp->obj.bus_name); + free(rsp->obj.dev_name); + free(rsp); + } +} + +struct devlink_port_param_get_list * +devlink_port_param_get_dump(struct ynl_sock *ys) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_port_param_get_list); + yds.cb = devlink_port_param_get_rsp_parse; + yds.rsp_cmd = DEVLINK_CMD_PORT_PARAM_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_GET, 1); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_port_param_get_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_PORT_PARAM_SET ============== */ +/* DEVLINK_CMD_PORT_PARAM_SET - do */ +void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_port_param_set(struct ynl_sock *ys, + struct devlink_port_param_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_PORT_PARAM_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_INFO_GET ============== */ /* DEVLINK_CMD_INFO_GET - do */ void devlink_info_get_req_free(struct devlink_info_get_req *req) @@ -2093,6 +5344,276 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_HEALTH_REPORTER_SET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */ +void +devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +int devlink_health_reporter_set(struct ynl_sock *ys, + struct devlink_health_reporter_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + if (req->_present.health_reporter_graceful_period) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, req->health_reporter_graceful_period); + if (req->_present.health_reporter_auto_recover) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, req->health_reporter_auto_recover); + if (req->_present.health_reporter_auto_dump) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_DUMP, req->health_reporter_auto_dump); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_RECOVER ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */ +void +devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +int devlink_health_reporter_recover(struct ynl_sock *ys, + struct devlink_health_reporter_recover_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_RECOVER, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */ +void +devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnose_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +int devlink_health_reporter_diagnose(struct ynl_sock *ys, + struct devlink_health_reporter_diagnose_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */ +int devlink_health_reporter_dump_get_rsp_dump_parse(const struct nlmsghdr *nlh, + void *data) +{ + struct devlink_health_reporter_dump_get_rsp_dump *dst; + struct ynl_parse_arg *yarg = data; + const struct nlattr *attr; + struct ynl_parse_arg parg; + + dst = yarg->data; + parg.ys = yarg->ys; + + mnl_attr_for_each(attr, nlh, sizeof(struct genlmsghdr)) { + unsigned int type = mnl_attr_get_type(attr); + + if (type == DEVLINK_ATTR_FMSG) { + if (ynl_attr_validate(yarg, attr)) + return MNL_CB_ERROR; + dst->_present.fmsg = 1; + + parg.rsp_policy = &devlink_dl_fmsg_nest; + parg.data = &dst->fmsg; + if (devlink_dl_fmsg_parse(&parg, attr)) + return MNL_CB_ERROR; + } + } + + return MNL_CB_OK; +} + +void +devlink_health_reporter_dump_get_rsp_list_free(struct devlink_health_reporter_dump_get_rsp_list *rsp) +{ + struct devlink_health_reporter_dump_get_rsp_list *next = rsp; + + while ((void *)next != YNL_LIST_END) { + rsp = next; + next = rsp->next; + + devlink_dl_fmsg_free(&rsp->obj.fmsg); + free(rsp); + } +} + +struct devlink_health_reporter_dump_get_rsp_list * +devlink_health_reporter_dump_get_dump(struct ynl_sock *ys, + struct devlink_health_reporter_dump_get_req_dump *req) +{ + struct ynl_dump_state yds = {}; + struct nlmsghdr *nlh; + int err; + + yds.ys = ys; + yds.alloc_sz = sizeof(struct devlink_health_reporter_dump_get_rsp_list); + yds.cb = devlink_health_reporter_dump_get_rsp_dump_parse; + yds.rsp_cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET; + yds.rsp_policy = &devlink_nest; + + nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + err = ynl_exec_dump(ys, nlh, &yds); + if (err < 0) + goto free_list; + + return yds.first; + +free_list: + devlink_health_reporter_dump_get_rsp_list_free(yds.first); + return NULL; +} + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */ +void +devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_clear_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +int devlink_health_reporter_dump_clear(struct ynl_sock *ys, + struct devlink_health_reporter_dump_clear_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_FLASH_UPDATE ============== */ +/* DEVLINK_CMD_FLASH_UPDATE - do */ +void devlink_flash_update_req_free(struct devlink_flash_update_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->flash_update_file_name); + free(req->flash_update_component); + free(req); +} + +int devlink_flash_update(struct ynl_sock *ys, + struct devlink_flash_update_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_FLASH_UPDATE, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.flash_update_file_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME, req->flash_update_file_name); + if (req->_present.flash_update_component_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, req->flash_update_component); + if (req->_present.flash_update_overwrite_mask) + mnl_attr_put(nlh, DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK, sizeof(struct nla_bitfield32), &req->flash_update_overwrite_mask); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_TRAP_GET ============== */ /* DEVLINK_CMD_TRAP_GET - do */ void devlink_trap_get_req_free(struct devlink_trap_get_req *req) @@ -2183,7 +5704,7 @@ devlink_trap_get(struct ynl_sock *ys, struct devlink_trap_get_req *req) rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_trap_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_TRAP_GET; + yrs.rsp_cmd = 63; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -2223,7 +5744,7 @@ devlink_trap_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_trap_get_list); yds.cb = devlink_trap_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_TRAP_GET; + yds.rsp_cmd = 63; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GET, 1); @@ -2245,6 +5766,40 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_TRAP_SET ============== */ +/* DEVLINK_CMD_TRAP_SET - do */ +void devlink_trap_set_req_free(struct devlink_trap_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->trap_name); + free(req); +} + +int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_NAME, req->trap_name); + if (req->_present.trap_action) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */ /* DEVLINK_CMD_TRAP_GROUP_GET - do */ void devlink_trap_group_get_req_free(struct devlink_trap_group_get_req *req) @@ -2336,7 +5891,7 @@ devlink_trap_group_get(struct ynl_sock *ys, rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_trap_group_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET; + yrs.rsp_cmd = 67; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -2376,7 +5931,7 @@ devlink_trap_group_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_trap_group_get_list); yds.cb = devlink_trap_group_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_TRAP_GROUP_GET; + yds.rsp_cmd = 67; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_GET, 1); @@ -2398,6 +5953,43 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_TRAP_GROUP_SET ============== */ +/* DEVLINK_CMD_TRAP_GROUP_SET - do */ +void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->trap_group_name); + free(req); +} + +int devlink_trap_group_set(struct ynl_sock *ys, + struct devlink_trap_group_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_GROUP_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_group_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_TRAP_GROUP_NAME, req->trap_group_name); + if (req->_present.trap_action) + mnl_attr_put_u8(nlh, DEVLINK_ATTR_TRAP_ACTION, req->trap_action); + if (req->_present.trap_policer_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */ /* DEVLINK_CMD_TRAP_POLICER_GET - do */ void @@ -2483,7 +6075,7 @@ devlink_trap_policer_get(struct ynl_sock *ys, rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_trap_policer_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET; + yrs.rsp_cmd = 71; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -2523,7 +6115,7 @@ devlink_trap_policer_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_trap_policer_get_list); yds.cb = devlink_trap_policer_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_TRAP_POLICER_GET; + yds.rsp_cmd = 71; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_GET, 1); @@ -2545,6 +6137,79 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_TRAP_POLICER_SET ============== */ +/* DEVLINK_CMD_TRAP_POLICER_SET - do */ +void +devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req); +} + +int devlink_trap_policer_set(struct ynl_sock *ys, + struct devlink_trap_policer_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_TRAP_POLICER_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.trap_policer_id) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_TRAP_POLICER_ID, req->trap_policer_id); + if (req->_present.trap_policer_rate) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_RATE, req->trap_policer_rate); + if (req->_present.trap_policer_burst) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_TRAP_POLICER_BURST, req->trap_policer_burst); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_TEST ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */ +void +devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->health_reporter_name); + free(req); +} + +int devlink_health_reporter_test(struct ynl_sock *ys, + struct devlink_health_reporter_test_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_HEALTH_REPORTER_TEST, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.port_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_PORT_INDEX, req->port_index); + if (req->_present.health_reporter_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_HEALTH_REPORTER_NAME, req->health_reporter_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_RATE_GET ============== */ /* DEVLINK_CMD_RATE_GET - do */ void devlink_rate_get_req_free(struct devlink_rate_get_req *req) @@ -2642,7 +6307,7 @@ devlink_rate_get(struct ynl_sock *ys, struct devlink_rate_get_req *req) rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_rate_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_RATE_GET; + yrs.rsp_cmd = 76; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -2682,7 +6347,7 @@ devlink_rate_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_rate_get_list); yds.cb = devlink_rate_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_RATE_GET; + yds.rsp_cmd = 76; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_RATE_GET, 1); @@ -2704,6 +6369,124 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_RATE_SET ============== */ +/* DEVLINK_CMD_RATE_SET - do */ +void devlink_rate_set_req_free(struct devlink_rate_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->rate_node_name); + free(req->rate_parent_node_name); + free(req); +} + +int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.rate_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name); + if (req->_present.rate_tx_share) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE, req->rate_tx_share); + if (req->_present.rate_tx_max) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX, req->rate_tx_max); + if (req->_present.rate_tx_priority) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_PRIORITY, req->rate_tx_priority); + if (req->_present.rate_tx_weight) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_WEIGHT, req->rate_tx_weight); + if (req->_present.rate_parent_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_RATE_NEW ============== */ +/* DEVLINK_CMD_RATE_NEW - do */ +void devlink_rate_new_req_free(struct devlink_rate_new_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->rate_node_name); + free(req->rate_parent_node_name); + free(req); +} + +int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_NEW, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.rate_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name); + if (req->_present.rate_tx_share) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_SHARE, req->rate_tx_share); + if (req->_present.rate_tx_max) + mnl_attr_put_u64(nlh, DEVLINK_ATTR_RATE_TX_MAX, req->rate_tx_max); + if (req->_present.rate_tx_priority) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_PRIORITY, req->rate_tx_priority); + if (req->_present.rate_tx_weight) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_RATE_TX_WEIGHT, req->rate_tx_weight); + if (req->_present.rate_parent_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, req->rate_parent_node_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + +/* ============== DEVLINK_CMD_RATE_DEL ============== */ +/* DEVLINK_CMD_RATE_DEL - do */ +void devlink_rate_del_req_free(struct devlink_rate_del_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->rate_node_name); + free(req); +} + +int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_RATE_DEL, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.rate_node_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_RATE_NODE_NAME, req->rate_node_name); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_LINECARD_GET ============== */ /* DEVLINK_CMD_LINECARD_GET - do */ void devlink_linecard_get_req_free(struct devlink_linecard_get_req *req) @@ -2786,7 +6569,7 @@ devlink_linecard_get(struct ynl_sock *ys, struct devlink_linecard_get_req *req) rsp = calloc(1, sizeof(*rsp)); yrs.yarg.data = rsp; yrs.cb = devlink_linecard_get_rsp_parse; - yrs.rsp_cmd = DEVLINK_CMD_LINECARD_GET; + yrs.rsp_cmd = 80; err = ynl_exec(ys, nlh, &yrs); if (err < 0) @@ -2825,7 +6608,7 @@ devlink_linecard_get_dump(struct ynl_sock *ys, yds.ys = ys; yds.alloc_sz = sizeof(struct devlink_linecard_get_list); yds.cb = devlink_linecard_get_rsp_parse; - yds.rsp_cmd = DEVLINK_CMD_LINECARD_GET; + yds.rsp_cmd = 80; yds.rsp_policy = &devlink_nest; nlh = ynl_gemsg_start_dump(ys, ys->family_id, DEVLINK_CMD_LINECARD_GET, 1); @@ -2847,6 +6630,41 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_LINECARD_SET ============== */ +/* DEVLINK_CMD_LINECARD_SET - do */ +void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req) +{ + free(req->bus_name); + free(req->dev_name); + free(req->linecard_type); + free(req); +} + +int devlink_linecard_set(struct ynl_sock *ys, + struct devlink_linecard_set_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_LINECARD_SET, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.linecard_index) + mnl_attr_put_u32(nlh, DEVLINK_ATTR_LINECARD_INDEX, req->linecard_index); + if (req->_present.linecard_type_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_LINECARD_TYPE, req->linecard_type); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + /* ============== DEVLINK_CMD_SELFTESTS_GET ============== */ /* DEVLINK_CMD_SELFTESTS_GET - do */ void devlink_selftests_get_req_free(struct devlink_selftests_get_req *req) @@ -2977,6 +6795,39 @@ free_list: return NULL; } +/* ============== DEVLINK_CMD_SELFTESTS_RUN ============== */ +/* DEVLINK_CMD_SELFTESTS_RUN - do */ +void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req) +{ + free(req->bus_name); + free(req->dev_name); + devlink_dl_selftest_id_free(&req->selftests); + free(req); +} + +int devlink_selftests_run(struct ynl_sock *ys, + struct devlink_selftests_run_req *req) +{ + struct nlmsghdr *nlh; + int err; + + nlh = ynl_gemsg_start_req(ys, ys->family_id, DEVLINK_CMD_SELFTESTS_RUN, 1); + ys->req_policy = &devlink_nest; + + if (req->_present.bus_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_BUS_NAME, req->bus_name); + if (req->_present.dev_name_len) + mnl_attr_put_strz(nlh, DEVLINK_ATTR_DEV_NAME, req->dev_name); + if (req->_present.selftests) + devlink_dl_selftest_id_put(nlh, DEVLINK_ATTR_SELFTESTS, &req->selftests); + + err = ynl_exec(ys, nlh, NULL); + if (err < 0) + return -1; + + return 0; +} + const struct ynl_family ynl_devlink_family = { .name = "devlink", }; diff --git a/tools/net/ynl/generated/devlink-user.h b/tools/net/ynl/generated/devlink-user.h index 4b686d147613..1db4edc36eaa 100644 --- a/tools/net/ynl/generated/devlink-user.h +++ b/tools/net/ynl/generated/devlink-user.h @@ -9,6 +9,7 @@ #include <stdlib.h> #include <string.h> #include <linux/types.h> +#include <linux/netlink.h> #include <linux/devlink.h> struct ynl_sock; @@ -18,8 +19,130 @@ extern const struct ynl_family ynl_devlink_family; /* Enums */ const char *devlink_op_str(int op); const char *devlink_sb_pool_type_str(enum devlink_sb_pool_type value); +const char *devlink_port_type_str(enum devlink_port_type value); +const char *devlink_port_flavour_str(enum devlink_port_flavour value); +const char *devlink_port_fn_state_str(enum devlink_port_fn_state value); +const char *devlink_port_fn_opstate_str(enum devlink_port_fn_opstate value); +const char *devlink_port_fn_attr_cap_str(enum devlink_port_fn_attr_cap value); +const char * +devlink_sb_threshold_type_str(enum devlink_sb_threshold_type value); +const char *devlink_eswitch_mode_str(enum devlink_eswitch_mode value); +const char * +devlink_eswitch_inline_mode_str(enum devlink_eswitch_inline_mode value); +const char * +devlink_eswitch_encap_mode_str(enum devlink_eswitch_encap_mode value); +const char *devlink_dpipe_match_type_str(enum devlink_dpipe_match_type value); +const char * +devlink_dpipe_action_type_str(enum devlink_dpipe_action_type value); +const char * +devlink_dpipe_field_mapping_type_str(enum devlink_dpipe_field_mapping_type value); +const char *devlink_resource_unit_str(enum devlink_resource_unit value); +const char *devlink_reload_action_str(enum devlink_reload_action value); +const char *devlink_param_cmode_str(enum devlink_param_cmode value); +const char *devlink_flash_overwrite_str(enum devlink_flash_overwrite value); +const char *devlink_trap_action_str(enum devlink_trap_action value); /* Common nested types */ +struct devlink_dl_dpipe_match { + struct { + __u32 dpipe_match_type:1; + __u32 dpipe_header_id:1; + __u32 dpipe_header_global:1; + __u32 dpipe_header_index:1; + __u32 dpipe_field_id:1; + } _present; + + enum devlink_dpipe_match_type dpipe_match_type; + __u32 dpipe_header_id; + __u8 dpipe_header_global; + __u32 dpipe_header_index; + __u32 dpipe_field_id; +}; + +struct devlink_dl_dpipe_match_value { + struct { + __u32 dpipe_value_len; + __u32 dpipe_value_mask_len; + __u32 dpipe_value_mapping:1; + } _present; + + unsigned int n_dpipe_match; + struct devlink_dl_dpipe_match *dpipe_match; + void *dpipe_value; + void *dpipe_value_mask; + __u32 dpipe_value_mapping; +}; + +struct devlink_dl_dpipe_action { + struct { + __u32 dpipe_action_type:1; + __u32 dpipe_header_id:1; + __u32 dpipe_header_global:1; + __u32 dpipe_header_index:1; + __u32 dpipe_field_id:1; + } _present; + + enum devlink_dpipe_action_type dpipe_action_type; + __u32 dpipe_header_id; + __u8 dpipe_header_global; + __u32 dpipe_header_index; + __u32 dpipe_field_id; +}; + +struct devlink_dl_dpipe_action_value { + struct { + __u32 dpipe_value_len; + __u32 dpipe_value_mask_len; + __u32 dpipe_value_mapping:1; + } _present; + + unsigned int n_dpipe_action; + struct devlink_dl_dpipe_action *dpipe_action; + void *dpipe_value; + void *dpipe_value_mask; + __u32 dpipe_value_mapping; +}; + +struct devlink_dl_dpipe_field { + struct { + __u32 dpipe_field_name_len; + __u32 dpipe_field_id:1; + __u32 dpipe_field_bitwidth:1; + __u32 dpipe_field_mapping_type:1; + } _present; + + char *dpipe_field_name; + __u32 dpipe_field_id; + __u32 dpipe_field_bitwidth; + enum devlink_dpipe_field_mapping_type dpipe_field_mapping_type; +}; + +struct devlink_dl_resource { + struct { + __u32 resource_name_len; + __u32 resource_id:1; + __u32 resource_size:1; + __u32 resource_size_new:1; + __u32 resource_size_valid:1; + __u32 resource_size_min:1; + __u32 resource_size_max:1; + __u32 resource_size_gran:1; + __u32 resource_unit:1; + __u32 resource_occ:1; + } _present; + + char *resource_name; + __u64 resource_id; + __u64 resource_size; + __u64 resource_size_new; + __u8 resource_size_valid; + __u64 resource_size_min; + __u64 resource_size_max; + __u64 resource_size_gran; + enum devlink_resource_unit resource_unit; + __u64 resource_occ; +}; + struct devlink_dl_info_version { struct { __u32 info_version_name_len; @@ -30,6 +153,32 @@ struct devlink_dl_info_version { char *info_version_value; }; +struct devlink_dl_fmsg { + struct { + __u32 fmsg_obj_nest_start:1; + __u32 fmsg_pair_nest_start:1; + __u32 fmsg_arr_nest_start:1; + __u32 fmsg_nest_end:1; + __u32 fmsg_obj_name_len; + } _present; + + char *fmsg_obj_name; +}; + +struct devlink_dl_port_function { + struct { + __u32 hw_addr_len; + __u32 state:1; + __u32 opstate:1; + __u32 caps:1; + } _present; + + void *hw_addr; + enum devlink_port_fn_state state; + enum devlink_port_fn_opstate opstate; + struct nla_bitfield32 caps; +}; + struct devlink_dl_reload_stats_entry { struct { __u32 reload_stats_limit:1; @@ -45,21 +194,120 @@ struct devlink_dl_reload_act_stats { struct devlink_dl_reload_stats_entry *reload_stats_entry; }; +struct devlink_dl_selftest_id { + struct { + __u32 flash:1; + } _present; +}; + +struct devlink_dl_dpipe_table_matches { + unsigned int n_dpipe_match; + struct devlink_dl_dpipe_match *dpipe_match; +}; + +struct devlink_dl_dpipe_table_actions { + unsigned int n_dpipe_action; + struct devlink_dl_dpipe_action *dpipe_action; +}; + +struct devlink_dl_dpipe_entry_match_values { + unsigned int n_dpipe_match_value; + struct devlink_dl_dpipe_match_value *dpipe_match_value; +}; + +struct devlink_dl_dpipe_entry_action_values { + unsigned int n_dpipe_action_value; + struct devlink_dl_dpipe_action_value *dpipe_action_value; +}; + +struct devlink_dl_dpipe_header_fields { + unsigned int n_dpipe_field; + struct devlink_dl_dpipe_field *dpipe_field; +}; + +struct devlink_dl_resource_list { + unsigned int n_resource; + struct devlink_dl_resource *resource; +}; + struct devlink_dl_reload_act_info { struct { __u32 reload_action:1; } _present; - __u8 reload_action; + enum devlink_reload_action reload_action; unsigned int n_reload_action_stats; struct devlink_dl_reload_act_stats *reload_action_stats; }; +struct devlink_dl_dpipe_table { + struct { + __u32 dpipe_table_name_len; + __u32 dpipe_table_size:1; + __u32 dpipe_table_matches:1; + __u32 dpipe_table_actions:1; + __u32 dpipe_table_counters_enabled:1; + __u32 dpipe_table_resource_id:1; + __u32 dpipe_table_resource_units:1; + } _present; + + char *dpipe_table_name; + __u64 dpipe_table_size; + struct devlink_dl_dpipe_table_matches dpipe_table_matches; + struct devlink_dl_dpipe_table_actions dpipe_table_actions; + __u8 dpipe_table_counters_enabled; + __u64 dpipe_table_resource_id; + __u64 dpipe_table_resource_units; +}; + +struct devlink_dl_dpipe_entry { + struct { + __u32 dpipe_entry_index:1; + __u32 dpipe_entry_match_values:1; + __u32 dpipe_entry_action_values:1; + __u32 dpipe_entry_counter:1; + } _present; + + __u64 dpipe_entry_index; + struct devlink_dl_dpipe_entry_match_values dpipe_entry_match_values; + struct devlink_dl_dpipe_entry_action_values dpipe_entry_action_values; + __u64 dpipe_entry_counter; +}; + +struct devlink_dl_dpipe_header { + struct { + __u32 dpipe_header_name_len; + __u32 dpipe_header_id:1; + __u32 dpipe_header_global:1; + __u32 dpipe_header_fields:1; + } _present; + + char *dpipe_header_name; + __u32 dpipe_header_id; + __u8 dpipe_header_global; + struct devlink_dl_dpipe_header_fields dpipe_header_fields; +}; + struct devlink_dl_reload_stats { unsigned int n_reload_action_info; struct devlink_dl_reload_act_info *reload_action_info; }; +struct devlink_dl_dpipe_tables { + unsigned int n_dpipe_table; + struct devlink_dl_dpipe_table *dpipe_table; +}; + +struct devlink_dl_dpipe_entries { + unsigned int n_dpipe_entry; + struct devlink_dl_dpipe_entry *dpipe_entry; +}; + +struct devlink_dl_dpipe_headers { + unsigned int n_dpipe_header; + struct devlink_dl_dpipe_header *dpipe_header; +}; + struct devlink_dl_dev_stats { struct { __u32 reload_stats:1; @@ -112,14 +360,12 @@ struct devlink_get_rsp { __u32 bus_name_len; __u32 dev_name_len; __u32 reload_failed:1; - __u32 reload_action:1; __u32 dev_stats:1; } _present; char *bus_name; char *dev_name; __u8 reload_failed; - __u8 reload_action; struct devlink_dl_dev_stats dev_stats; }; @@ -134,7 +380,7 @@ devlink_get(struct ynl_sock *ys, struct devlink_get_req *req); /* DEVLINK_CMD_GET - dump */ struct devlink_get_list { struct devlink_get_list *next; - struct devlink_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_get_rsp obj __attribute__((aligned(8))); }; void devlink_get_list_free(struct devlink_get_list *rsp); @@ -262,7 +508,7 @@ struct devlink_port_get_rsp_dump { struct devlink_port_get_rsp_list { struct devlink_port_get_rsp_list *next; - struct devlink_port_get_rsp_dump obj __attribute__ ((aligned (8))); + struct devlink_port_get_rsp_dump obj __attribute__((aligned(8))); }; void devlink_port_get_rsp_list_free(struct devlink_port_get_rsp_list *rsp); @@ -271,6 +517,377 @@ struct devlink_port_get_rsp_list * devlink_port_get_dump(struct ynl_sock *ys, struct devlink_port_get_req_dump *req); +/* ============== DEVLINK_CMD_PORT_SET ============== */ +/* DEVLINK_CMD_PORT_SET - do */ +struct devlink_port_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 port_type:1; + __u32 port_function:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + enum devlink_port_type port_type; + struct devlink_dl_port_function port_function; +}; + +static inline struct devlink_port_set_req *devlink_port_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_set_req)); +} +void devlink_port_set_req_free(struct devlink_port_set_req *req); + +static inline void +devlink_port_set_req_set_bus_name(struct devlink_port_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_set_req_set_dev_name(struct devlink_port_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_set_req_set_port_index(struct devlink_port_set_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_port_set_req_set_port_type(struct devlink_port_set_req *req, + enum devlink_port_type port_type) +{ + req->_present.port_type = 1; + req->port_type = port_type; +} +static inline void +devlink_port_set_req_set_port_function_hw_addr(struct devlink_port_set_req *req, + const void *hw_addr, size_t len) +{ + free(req->port_function.hw_addr); + req->port_function._present.hw_addr_len = len; + req->port_function.hw_addr = malloc(req->port_function._present.hw_addr_len); + memcpy(req->port_function.hw_addr, hw_addr, req->port_function._present.hw_addr_len); +} +static inline void +devlink_port_set_req_set_port_function_state(struct devlink_port_set_req *req, + enum devlink_port_fn_state state) +{ + req->_present.port_function = 1; + req->port_function._present.state = 1; + req->port_function.state = state; +} +static inline void +devlink_port_set_req_set_port_function_opstate(struct devlink_port_set_req *req, + enum devlink_port_fn_opstate opstate) +{ + req->_present.port_function = 1; + req->port_function._present.opstate = 1; + req->port_function.opstate = opstate; +} +static inline void +devlink_port_set_req_set_port_function_caps(struct devlink_port_set_req *req, + struct nla_bitfield32 *caps) +{ + req->_present.port_function = 1; + req->port_function._present.caps = 1; + memcpy(&req->port_function.caps, caps, sizeof(struct nla_bitfield32)); +} + +/* + * Set devlink port instances. + */ +int devlink_port_set(struct ynl_sock *ys, struct devlink_port_set_req *req); + +/* ============== DEVLINK_CMD_PORT_NEW ============== */ +/* DEVLINK_CMD_PORT_NEW - do */ +struct devlink_port_new_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 port_flavour:1; + __u32 port_pci_pf_number:1; + __u32 port_pci_sf_number:1; + __u32 port_controller_number:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + enum devlink_port_flavour port_flavour; + __u16 port_pci_pf_number; + __u32 port_pci_sf_number; + __u32 port_controller_number; +}; + +static inline struct devlink_port_new_req *devlink_port_new_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_new_req)); +} +void devlink_port_new_req_free(struct devlink_port_new_req *req); + +static inline void +devlink_port_new_req_set_bus_name(struct devlink_port_new_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_new_req_set_dev_name(struct devlink_port_new_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_new_req_set_port_index(struct devlink_port_new_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_port_new_req_set_port_flavour(struct devlink_port_new_req *req, + enum devlink_port_flavour port_flavour) +{ + req->_present.port_flavour = 1; + req->port_flavour = port_flavour; +} +static inline void +devlink_port_new_req_set_port_pci_pf_number(struct devlink_port_new_req *req, + __u16 port_pci_pf_number) +{ + req->_present.port_pci_pf_number = 1; + req->port_pci_pf_number = port_pci_pf_number; +} +static inline void +devlink_port_new_req_set_port_pci_sf_number(struct devlink_port_new_req *req, + __u32 port_pci_sf_number) +{ + req->_present.port_pci_sf_number = 1; + req->port_pci_sf_number = port_pci_sf_number; +} +static inline void +devlink_port_new_req_set_port_controller_number(struct devlink_port_new_req *req, + __u32 port_controller_number) +{ + req->_present.port_controller_number = 1; + req->port_controller_number = port_controller_number; +} + +struct devlink_port_new_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +void devlink_port_new_rsp_free(struct devlink_port_new_rsp *rsp); + +/* + * Create devlink port instances. + */ +struct devlink_port_new_rsp * +devlink_port_new(struct ynl_sock *ys, struct devlink_port_new_req *req); + +/* ============== DEVLINK_CMD_PORT_DEL ============== */ +/* DEVLINK_CMD_PORT_DEL - do */ +struct devlink_port_del_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_port_del_req *devlink_port_del_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_del_req)); +} +void devlink_port_del_req_free(struct devlink_port_del_req *req); + +static inline void +devlink_port_del_req_set_bus_name(struct devlink_port_del_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_del_req_set_dev_name(struct devlink_port_del_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_del_req_set_port_index(struct devlink_port_del_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +/* + * Delete devlink port instances. + */ +int devlink_port_del(struct ynl_sock *ys, struct devlink_port_del_req *req); + +/* ============== DEVLINK_CMD_PORT_SPLIT ============== */ +/* DEVLINK_CMD_PORT_SPLIT - do */ +struct devlink_port_split_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 port_split_count:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 port_split_count; +}; + +static inline struct devlink_port_split_req *devlink_port_split_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_split_req)); +} +void devlink_port_split_req_free(struct devlink_port_split_req *req); + +static inline void +devlink_port_split_req_set_bus_name(struct devlink_port_split_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_split_req_set_dev_name(struct devlink_port_split_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_split_req_set_port_index(struct devlink_port_split_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_port_split_req_set_port_split_count(struct devlink_port_split_req *req, + __u32 port_split_count) +{ + req->_present.port_split_count = 1; + req->port_split_count = port_split_count; +} + +/* + * Split devlink port instances. + */ +int devlink_port_split(struct ynl_sock *ys, struct devlink_port_split_req *req); + +/* ============== DEVLINK_CMD_PORT_UNSPLIT ============== */ +/* DEVLINK_CMD_PORT_UNSPLIT - do */ +struct devlink_port_unsplit_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_port_unsplit_req * +devlink_port_unsplit_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_unsplit_req)); +} +void devlink_port_unsplit_req_free(struct devlink_port_unsplit_req *req); + +static inline void +devlink_port_unsplit_req_set_bus_name(struct devlink_port_unsplit_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_unsplit_req_set_dev_name(struct devlink_port_unsplit_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_unsplit_req_set_port_index(struct devlink_port_unsplit_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +/* + * Unplit devlink port instances. + */ +int devlink_port_unsplit(struct ynl_sock *ys, + struct devlink_port_unsplit_req *req); + /* ============== DEVLINK_CMD_SB_GET ============== */ /* DEVLINK_CMD_SB_GET - do */ struct devlink_sb_get_req { @@ -379,7 +996,7 @@ devlink_sb_get_req_dump_set_dev_name(struct devlink_sb_get_req_dump *req, struct devlink_sb_get_list { struct devlink_sb_get_list *next; - struct devlink_sb_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_sb_get_rsp obj __attribute__((aligned(8))); }; void devlink_sb_get_list_free(struct devlink_sb_get_list *rsp); @@ -509,7 +1126,7 @@ devlink_sb_pool_get_req_dump_set_dev_name(struct devlink_sb_pool_get_req_dump *r struct devlink_sb_pool_get_list { struct devlink_sb_pool_get_list *next; - struct devlink_sb_pool_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_sb_pool_get_rsp obj __attribute__((aligned(8))); }; void devlink_sb_pool_get_list_free(struct devlink_sb_pool_get_list *rsp); @@ -518,6 +1135,88 @@ struct devlink_sb_pool_get_list * devlink_sb_pool_get_dump(struct ynl_sock *ys, struct devlink_sb_pool_get_req_dump *req); +/* ============== DEVLINK_CMD_SB_POOL_SET ============== */ +/* DEVLINK_CMD_SB_POOL_SET - do */ +struct devlink_sb_pool_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + __u32 sb_pool_index:1; + __u32 sb_pool_threshold_type:1; + __u32 sb_pool_size:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; + __u16 sb_pool_index; + enum devlink_sb_threshold_type sb_pool_threshold_type; + __u32 sb_pool_size; +}; + +static inline struct devlink_sb_pool_set_req * +devlink_sb_pool_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_pool_set_req)); +} +void devlink_sb_pool_set_req_free(struct devlink_sb_pool_set_req *req); + +static inline void +devlink_sb_pool_set_req_set_bus_name(struct devlink_sb_pool_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_pool_set_req_set_dev_name(struct devlink_sb_pool_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_pool_set_req_set_sb_index(struct devlink_sb_pool_set_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_pool_set_req_set_sb_pool_index(struct devlink_sb_pool_set_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} +static inline void +devlink_sb_pool_set_req_set_sb_pool_threshold_type(struct devlink_sb_pool_set_req *req, + enum devlink_sb_threshold_type sb_pool_threshold_type) +{ + req->_present.sb_pool_threshold_type = 1; + req->sb_pool_threshold_type = sb_pool_threshold_type; +} +static inline void +devlink_sb_pool_set_req_set_sb_pool_size(struct devlink_sb_pool_set_req *req, + __u32 sb_pool_size) +{ + req->_present.sb_pool_size = 1; + req->sb_pool_size = sb_pool_size; +} + +/* + * Set shared buffer pool instances. + */ +int devlink_sb_pool_set(struct ynl_sock *ys, + struct devlink_sb_pool_set_req *req); + /* ============== DEVLINK_CMD_SB_PORT_POOL_GET ============== */ /* DEVLINK_CMD_SB_PORT_POOL_GET - do */ struct devlink_sb_port_pool_get_req { @@ -654,7 +1353,7 @@ devlink_sb_port_pool_get_req_dump_set_dev_name(struct devlink_sb_port_pool_get_r struct devlink_sb_port_pool_get_list { struct devlink_sb_port_pool_get_list *next; - struct devlink_sb_port_pool_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_sb_port_pool_get_rsp obj __attribute__((aligned(8))); }; void @@ -664,6 +1363,89 @@ struct devlink_sb_port_pool_get_list * devlink_sb_port_pool_get_dump(struct ynl_sock *ys, struct devlink_sb_port_pool_get_req_dump *req); +/* ============== DEVLINK_CMD_SB_PORT_POOL_SET ============== */ +/* DEVLINK_CMD_SB_PORT_POOL_SET - do */ +struct devlink_sb_port_pool_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_index:1; + __u32 sb_threshold:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + __u16 sb_pool_index; + __u32 sb_threshold; +}; + +static inline struct devlink_sb_port_pool_set_req * +devlink_sb_port_pool_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_port_pool_set_req)); +} +void +devlink_sb_port_pool_set_req_free(struct devlink_sb_port_pool_set_req *req); + +static inline void +devlink_sb_port_pool_set_req_set_bus_name(struct devlink_sb_port_pool_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_port_pool_set_req_set_dev_name(struct devlink_sb_port_pool_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_port_pool_set_req_set_port_index(struct devlink_sb_port_pool_set_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_sb_port_pool_set_req_set_sb_index(struct devlink_sb_port_pool_set_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_port_pool_set_req_set_sb_pool_index(struct devlink_sb_port_pool_set_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} +static inline void +devlink_sb_port_pool_set_req_set_sb_threshold(struct devlink_sb_port_pool_set_req *req, + __u32 sb_threshold) +{ + req->_present.sb_threshold = 1; + req->sb_threshold = sb_threshold; +} + +/* + * Set shared buffer port-pool combinations and threshold. + */ +int devlink_sb_port_pool_set(struct ynl_sock *ys, + struct devlink_sb_port_pool_set_req *req); + /* ============== DEVLINK_CMD_SB_TC_POOL_BIND_GET ============== */ /* DEVLINK_CMD_SB_TC_POOL_BIND_GET - do */ struct devlink_sb_tc_pool_bind_get_req { @@ -811,7 +1593,7 @@ devlink_sb_tc_pool_bind_get_req_dump_set_dev_name(struct devlink_sb_tc_pool_bind struct devlink_sb_tc_pool_bind_get_list { struct devlink_sb_tc_pool_bind_get_list *next; - struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_sb_tc_pool_bind_get_rsp obj __attribute__((aligned(8))); }; void @@ -821,6 +1603,861 @@ struct devlink_sb_tc_pool_bind_get_list * devlink_sb_tc_pool_bind_get_dump(struct ynl_sock *ys, struct devlink_sb_tc_pool_bind_get_req_dump *req); +/* ============== DEVLINK_CMD_SB_TC_POOL_BIND_SET ============== */ +/* DEVLINK_CMD_SB_TC_POOL_BIND_SET - do */ +struct devlink_sb_tc_pool_bind_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 sb_index:1; + __u32 sb_pool_index:1; + __u32 sb_pool_type:1; + __u32 sb_tc_index:1; + __u32 sb_threshold:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + __u32 sb_index; + __u16 sb_pool_index; + enum devlink_sb_pool_type sb_pool_type; + __u16 sb_tc_index; + __u32 sb_threshold; +}; + +static inline struct devlink_sb_tc_pool_bind_set_req * +devlink_sb_tc_pool_bind_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_tc_pool_bind_set_req)); +} +void +devlink_sb_tc_pool_bind_set_req_free(struct devlink_sb_tc_pool_bind_set_req *req); + +static inline void +devlink_sb_tc_pool_bind_set_req_set_bus_name(struct devlink_sb_tc_pool_bind_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_dev_name(struct devlink_sb_tc_pool_bind_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_port_index(struct devlink_sb_tc_pool_bind_set_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_sb_index(struct devlink_sb_tc_pool_bind_set_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_sb_pool_index(struct devlink_sb_tc_pool_bind_set_req *req, + __u16 sb_pool_index) +{ + req->_present.sb_pool_index = 1; + req->sb_pool_index = sb_pool_index; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_sb_pool_type(struct devlink_sb_tc_pool_bind_set_req *req, + enum devlink_sb_pool_type sb_pool_type) +{ + req->_present.sb_pool_type = 1; + req->sb_pool_type = sb_pool_type; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_sb_tc_index(struct devlink_sb_tc_pool_bind_set_req *req, + __u16 sb_tc_index) +{ + req->_present.sb_tc_index = 1; + req->sb_tc_index = sb_tc_index; +} +static inline void +devlink_sb_tc_pool_bind_set_req_set_sb_threshold(struct devlink_sb_tc_pool_bind_set_req *req, + __u32 sb_threshold) +{ + req->_present.sb_threshold = 1; + req->sb_threshold = sb_threshold; +} + +/* + * Set shared buffer port-TC to pool bindings and threshold. + */ +int devlink_sb_tc_pool_bind_set(struct ynl_sock *ys, + struct devlink_sb_tc_pool_bind_set_req *req); + +/* ============== DEVLINK_CMD_SB_OCC_SNAPSHOT ============== */ +/* DEVLINK_CMD_SB_OCC_SNAPSHOT - do */ +struct devlink_sb_occ_snapshot_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; +}; + +static inline struct devlink_sb_occ_snapshot_req * +devlink_sb_occ_snapshot_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_occ_snapshot_req)); +} +void devlink_sb_occ_snapshot_req_free(struct devlink_sb_occ_snapshot_req *req); + +static inline void +devlink_sb_occ_snapshot_req_set_bus_name(struct devlink_sb_occ_snapshot_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_occ_snapshot_req_set_dev_name(struct devlink_sb_occ_snapshot_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_occ_snapshot_req_set_sb_index(struct devlink_sb_occ_snapshot_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} + +/* + * Take occupancy snapshot of shared buffer. + */ +int devlink_sb_occ_snapshot(struct ynl_sock *ys, + struct devlink_sb_occ_snapshot_req *req); + +/* ============== DEVLINK_CMD_SB_OCC_MAX_CLEAR ============== */ +/* DEVLINK_CMD_SB_OCC_MAX_CLEAR - do */ +struct devlink_sb_occ_max_clear_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 sb_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 sb_index; +}; + +static inline struct devlink_sb_occ_max_clear_req * +devlink_sb_occ_max_clear_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_sb_occ_max_clear_req)); +} +void +devlink_sb_occ_max_clear_req_free(struct devlink_sb_occ_max_clear_req *req); + +static inline void +devlink_sb_occ_max_clear_req_set_bus_name(struct devlink_sb_occ_max_clear_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_sb_occ_max_clear_req_set_dev_name(struct devlink_sb_occ_max_clear_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_sb_occ_max_clear_req_set_sb_index(struct devlink_sb_occ_max_clear_req *req, + __u32 sb_index) +{ + req->_present.sb_index = 1; + req->sb_index = sb_index; +} + +/* + * Clear occupancy watermarks of shared buffer. + */ +int devlink_sb_occ_max_clear(struct ynl_sock *ys, + struct devlink_sb_occ_max_clear_req *req); + +/* ============== DEVLINK_CMD_ESWITCH_GET ============== */ +/* DEVLINK_CMD_ESWITCH_GET - do */ +struct devlink_eswitch_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_eswitch_get_req * +devlink_eswitch_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_eswitch_get_req)); +} +void devlink_eswitch_get_req_free(struct devlink_eswitch_get_req *req); + +static inline void +devlink_eswitch_get_req_set_bus_name(struct devlink_eswitch_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_eswitch_get_req_set_dev_name(struct devlink_eswitch_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_eswitch_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 eswitch_mode:1; + __u32 eswitch_inline_mode:1; + __u32 eswitch_encap_mode:1; + } _present; + + char *bus_name; + char *dev_name; + enum devlink_eswitch_mode eswitch_mode; + enum devlink_eswitch_inline_mode eswitch_inline_mode; + enum devlink_eswitch_encap_mode eswitch_encap_mode; +}; + +void devlink_eswitch_get_rsp_free(struct devlink_eswitch_get_rsp *rsp); + +/* + * Get eswitch attributes. + */ +struct devlink_eswitch_get_rsp * +devlink_eswitch_get(struct ynl_sock *ys, struct devlink_eswitch_get_req *req); + +/* ============== DEVLINK_CMD_ESWITCH_SET ============== */ +/* DEVLINK_CMD_ESWITCH_SET - do */ +struct devlink_eswitch_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 eswitch_mode:1; + __u32 eswitch_inline_mode:1; + __u32 eswitch_encap_mode:1; + } _present; + + char *bus_name; + char *dev_name; + enum devlink_eswitch_mode eswitch_mode; + enum devlink_eswitch_inline_mode eswitch_inline_mode; + enum devlink_eswitch_encap_mode eswitch_encap_mode; +}; + +static inline struct devlink_eswitch_set_req * +devlink_eswitch_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_eswitch_set_req)); +} +void devlink_eswitch_set_req_free(struct devlink_eswitch_set_req *req); + +static inline void +devlink_eswitch_set_req_set_bus_name(struct devlink_eswitch_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_eswitch_set_req_set_dev_name(struct devlink_eswitch_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_eswitch_set_req_set_eswitch_mode(struct devlink_eswitch_set_req *req, + enum devlink_eswitch_mode eswitch_mode) +{ + req->_present.eswitch_mode = 1; + req->eswitch_mode = eswitch_mode; +} +static inline void +devlink_eswitch_set_req_set_eswitch_inline_mode(struct devlink_eswitch_set_req *req, + enum devlink_eswitch_inline_mode eswitch_inline_mode) +{ + req->_present.eswitch_inline_mode = 1; + req->eswitch_inline_mode = eswitch_inline_mode; +} +static inline void +devlink_eswitch_set_req_set_eswitch_encap_mode(struct devlink_eswitch_set_req *req, + enum devlink_eswitch_encap_mode eswitch_encap_mode) +{ + req->_present.eswitch_encap_mode = 1; + req->eswitch_encap_mode = eswitch_encap_mode; +} + +/* + * Set eswitch attributes. + */ +int devlink_eswitch_set(struct ynl_sock *ys, + struct devlink_eswitch_set_req *req); + +/* ============== DEVLINK_CMD_DPIPE_TABLE_GET ============== */ +/* DEVLINK_CMD_DPIPE_TABLE_GET - do */ +struct devlink_dpipe_table_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 dpipe_table_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *dpipe_table_name; +}; + +static inline struct devlink_dpipe_table_get_req * +devlink_dpipe_table_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_dpipe_table_get_req)); +} +void devlink_dpipe_table_get_req_free(struct devlink_dpipe_table_get_req *req); + +static inline void +devlink_dpipe_table_get_req_set_bus_name(struct devlink_dpipe_table_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_dpipe_table_get_req_set_dev_name(struct devlink_dpipe_table_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_dpipe_table_get_req_set_dpipe_table_name(struct devlink_dpipe_table_get_req *req, + const char *dpipe_table_name) +{ + free(req->dpipe_table_name); + req->_present.dpipe_table_name_len = strlen(dpipe_table_name); + req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1); + memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len); + req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0; +} + +struct devlink_dpipe_table_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 dpipe_tables:1; + } _present; + + char *bus_name; + char *dev_name; + struct devlink_dl_dpipe_tables dpipe_tables; +}; + +void devlink_dpipe_table_get_rsp_free(struct devlink_dpipe_table_get_rsp *rsp); + +/* + * Get dpipe table attributes. + */ +struct devlink_dpipe_table_get_rsp * +devlink_dpipe_table_get(struct ynl_sock *ys, + struct devlink_dpipe_table_get_req *req); + +/* ============== DEVLINK_CMD_DPIPE_ENTRIES_GET ============== */ +/* DEVLINK_CMD_DPIPE_ENTRIES_GET - do */ +struct devlink_dpipe_entries_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 dpipe_table_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *dpipe_table_name; +}; + +static inline struct devlink_dpipe_entries_get_req * +devlink_dpipe_entries_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_dpipe_entries_get_req)); +} +void +devlink_dpipe_entries_get_req_free(struct devlink_dpipe_entries_get_req *req); + +static inline void +devlink_dpipe_entries_get_req_set_bus_name(struct devlink_dpipe_entries_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_dpipe_entries_get_req_set_dev_name(struct devlink_dpipe_entries_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_dpipe_entries_get_req_set_dpipe_table_name(struct devlink_dpipe_entries_get_req *req, + const char *dpipe_table_name) +{ + free(req->dpipe_table_name); + req->_present.dpipe_table_name_len = strlen(dpipe_table_name); + req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1); + memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len); + req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0; +} + +struct devlink_dpipe_entries_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 dpipe_entries:1; + } _present; + + char *bus_name; + char *dev_name; + struct devlink_dl_dpipe_entries dpipe_entries; +}; + +void +devlink_dpipe_entries_get_rsp_free(struct devlink_dpipe_entries_get_rsp *rsp); + +/* + * Get dpipe entries attributes. + */ +struct devlink_dpipe_entries_get_rsp * +devlink_dpipe_entries_get(struct ynl_sock *ys, + struct devlink_dpipe_entries_get_req *req); + +/* ============== DEVLINK_CMD_DPIPE_HEADERS_GET ============== */ +/* DEVLINK_CMD_DPIPE_HEADERS_GET - do */ +struct devlink_dpipe_headers_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_dpipe_headers_get_req * +devlink_dpipe_headers_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_dpipe_headers_get_req)); +} +void +devlink_dpipe_headers_get_req_free(struct devlink_dpipe_headers_get_req *req); + +static inline void +devlink_dpipe_headers_get_req_set_bus_name(struct devlink_dpipe_headers_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_dpipe_headers_get_req_set_dev_name(struct devlink_dpipe_headers_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_dpipe_headers_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 dpipe_headers:1; + } _present; + + char *bus_name; + char *dev_name; + struct devlink_dl_dpipe_headers dpipe_headers; +}; + +void +devlink_dpipe_headers_get_rsp_free(struct devlink_dpipe_headers_get_rsp *rsp); + +/* + * Get dpipe headers attributes. + */ +struct devlink_dpipe_headers_get_rsp * +devlink_dpipe_headers_get(struct ynl_sock *ys, + struct devlink_dpipe_headers_get_req *req); + +/* ============== DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET ============== */ +/* DEVLINK_CMD_DPIPE_TABLE_COUNTERS_SET - do */ +struct devlink_dpipe_table_counters_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 dpipe_table_name_len; + __u32 dpipe_table_counters_enabled:1; + } _present; + + char *bus_name; + char *dev_name; + char *dpipe_table_name; + __u8 dpipe_table_counters_enabled; +}; + +static inline struct devlink_dpipe_table_counters_set_req * +devlink_dpipe_table_counters_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_dpipe_table_counters_set_req)); +} +void +devlink_dpipe_table_counters_set_req_free(struct devlink_dpipe_table_counters_set_req *req); + +static inline void +devlink_dpipe_table_counters_set_req_set_bus_name(struct devlink_dpipe_table_counters_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_dpipe_table_counters_set_req_set_dev_name(struct devlink_dpipe_table_counters_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_dpipe_table_counters_set_req_set_dpipe_table_name(struct devlink_dpipe_table_counters_set_req *req, + const char *dpipe_table_name) +{ + free(req->dpipe_table_name); + req->_present.dpipe_table_name_len = strlen(dpipe_table_name); + req->dpipe_table_name = malloc(req->_present.dpipe_table_name_len + 1); + memcpy(req->dpipe_table_name, dpipe_table_name, req->_present.dpipe_table_name_len); + req->dpipe_table_name[req->_present.dpipe_table_name_len] = 0; +} +static inline void +devlink_dpipe_table_counters_set_req_set_dpipe_table_counters_enabled(struct devlink_dpipe_table_counters_set_req *req, + __u8 dpipe_table_counters_enabled) +{ + req->_present.dpipe_table_counters_enabled = 1; + req->dpipe_table_counters_enabled = dpipe_table_counters_enabled; +} + +/* + * Set dpipe counter attributes. + */ +int devlink_dpipe_table_counters_set(struct ynl_sock *ys, + struct devlink_dpipe_table_counters_set_req *req); + +/* ============== DEVLINK_CMD_RESOURCE_SET ============== */ +/* DEVLINK_CMD_RESOURCE_SET - do */ +struct devlink_resource_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 resource_id:1; + __u32 resource_size:1; + } _present; + + char *bus_name; + char *dev_name; + __u64 resource_id; + __u64 resource_size; +}; + +static inline struct devlink_resource_set_req * +devlink_resource_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_resource_set_req)); +} +void devlink_resource_set_req_free(struct devlink_resource_set_req *req); + +static inline void +devlink_resource_set_req_set_bus_name(struct devlink_resource_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_resource_set_req_set_dev_name(struct devlink_resource_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_resource_set_req_set_resource_id(struct devlink_resource_set_req *req, + __u64 resource_id) +{ + req->_present.resource_id = 1; + req->resource_id = resource_id; +} +static inline void +devlink_resource_set_req_set_resource_size(struct devlink_resource_set_req *req, + __u64 resource_size) +{ + req->_present.resource_size = 1; + req->resource_size = resource_size; +} + +/* + * Set resource attributes. + */ +int devlink_resource_set(struct ynl_sock *ys, + struct devlink_resource_set_req *req); + +/* ============== DEVLINK_CMD_RESOURCE_DUMP ============== */ +/* DEVLINK_CMD_RESOURCE_DUMP - do */ +struct devlink_resource_dump_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + } _present; + + char *bus_name; + char *dev_name; +}; + +static inline struct devlink_resource_dump_req * +devlink_resource_dump_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_resource_dump_req)); +} +void devlink_resource_dump_req_free(struct devlink_resource_dump_req *req); + +static inline void +devlink_resource_dump_req_set_bus_name(struct devlink_resource_dump_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_resource_dump_req_set_dev_name(struct devlink_resource_dump_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} + +struct devlink_resource_dump_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 resource_list:1; + } _present; + + char *bus_name; + char *dev_name; + struct devlink_dl_resource_list resource_list; +}; + +void devlink_resource_dump_rsp_free(struct devlink_resource_dump_rsp *rsp); + +/* + * Get resource attributes. + */ +struct devlink_resource_dump_rsp * +devlink_resource_dump(struct ynl_sock *ys, + struct devlink_resource_dump_req *req); + +/* ============== DEVLINK_CMD_RELOAD ============== */ +/* DEVLINK_CMD_RELOAD - do */ +struct devlink_reload_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 reload_action:1; + __u32 reload_limits:1; + __u32 netns_pid:1; + __u32 netns_fd:1; + __u32 netns_id:1; + } _present; + + char *bus_name; + char *dev_name; + enum devlink_reload_action reload_action; + struct nla_bitfield32 reload_limits; + __u32 netns_pid; + __u32 netns_fd; + __u32 netns_id; +}; + +static inline struct devlink_reload_req *devlink_reload_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_reload_req)); +} +void devlink_reload_req_free(struct devlink_reload_req *req); + +static inline void +devlink_reload_req_set_bus_name(struct devlink_reload_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_reload_req_set_dev_name(struct devlink_reload_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_reload_req_set_reload_action(struct devlink_reload_req *req, + enum devlink_reload_action reload_action) +{ + req->_present.reload_action = 1; + req->reload_action = reload_action; +} +static inline void +devlink_reload_req_set_reload_limits(struct devlink_reload_req *req, + struct nla_bitfield32 *reload_limits) +{ + req->_present.reload_limits = 1; + memcpy(&req->reload_limits, reload_limits, sizeof(struct nla_bitfield32)); +} +static inline void +devlink_reload_req_set_netns_pid(struct devlink_reload_req *req, + __u32 netns_pid) +{ + req->_present.netns_pid = 1; + req->netns_pid = netns_pid; +} +static inline void +devlink_reload_req_set_netns_fd(struct devlink_reload_req *req, __u32 netns_fd) +{ + req->_present.netns_fd = 1; + req->netns_fd = netns_fd; +} +static inline void +devlink_reload_req_set_netns_id(struct devlink_reload_req *req, __u32 netns_id) +{ + req->_present.netns_id = 1; + req->netns_id = netns_id; +} + +struct devlink_reload_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 reload_actions_performed:1; + } _present; + + char *bus_name; + char *dev_name; + struct nla_bitfield32 reload_actions_performed; +}; + +void devlink_reload_rsp_free(struct devlink_reload_rsp *rsp); + +/* + * Reload devlink. + */ +struct devlink_reload_rsp * +devlink_reload(struct ynl_sock *ys, struct devlink_reload_req *req); + /* ============== DEVLINK_CMD_PARAM_GET ============== */ /* DEVLINK_CMD_PARAM_GET - do */ struct devlink_param_get_req { @@ -933,7 +2570,7 @@ devlink_param_get_req_dump_set_dev_name(struct devlink_param_get_req_dump *req, struct devlink_param_get_list { struct devlink_param_get_list *next; - struct devlink_param_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_param_get_rsp obj __attribute__((aligned(8))); }; void devlink_param_get_list_free(struct devlink_param_get_list *rsp); @@ -942,6 +2579,80 @@ struct devlink_param_get_list * devlink_param_get_dump(struct ynl_sock *ys, struct devlink_param_get_req_dump *req); +/* ============== DEVLINK_CMD_PARAM_SET ============== */ +/* DEVLINK_CMD_PARAM_SET - do */ +struct devlink_param_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 param_name_len; + __u32 param_type:1; + __u32 param_value_cmode:1; + } _present; + + char *bus_name; + char *dev_name; + char *param_name; + __u8 param_type; + enum devlink_param_cmode param_value_cmode; +}; + +static inline struct devlink_param_set_req *devlink_param_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_param_set_req)); +} +void devlink_param_set_req_free(struct devlink_param_set_req *req); + +static inline void +devlink_param_set_req_set_bus_name(struct devlink_param_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_param_set_req_set_dev_name(struct devlink_param_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_param_set_req_set_param_name(struct devlink_param_set_req *req, + const char *param_name) +{ + free(req->param_name); + req->_present.param_name_len = strlen(param_name); + req->param_name = malloc(req->_present.param_name_len + 1); + memcpy(req->param_name, param_name, req->_present.param_name_len); + req->param_name[req->_present.param_name_len] = 0; +} +static inline void +devlink_param_set_req_set_param_type(struct devlink_param_set_req *req, + __u8 param_type) +{ + req->_present.param_type = 1; + req->param_type = param_type; +} +static inline void +devlink_param_set_req_set_param_value_cmode(struct devlink_param_set_req *req, + enum devlink_param_cmode param_value_cmode) +{ + req->_present.param_value_cmode = 1; + req->param_value_cmode = param_value_cmode; +} + +/* + * Set param instances. + */ +int devlink_param_set(struct ynl_sock *ys, struct devlink_param_set_req *req); + /* ============== DEVLINK_CMD_REGION_GET ============== */ /* DEVLINK_CMD_REGION_GET - do */ struct devlink_region_get_req { @@ -1065,7 +2776,7 @@ devlink_region_get_req_dump_set_dev_name(struct devlink_region_get_req_dump *req struct devlink_region_get_list { struct devlink_region_get_list *next; - struct devlink_region_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_region_get_rsp obj __attribute__((aligned(8))); }; void devlink_region_get_list_free(struct devlink_region_get_list *rsp); @@ -1074,6 +2785,430 @@ struct devlink_region_get_list * devlink_region_get_dump(struct ynl_sock *ys, struct devlink_region_get_req_dump *req); +/* ============== DEVLINK_CMD_REGION_NEW ============== */ +/* DEVLINK_CMD_REGION_NEW - do */ +struct devlink_region_new_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + __u32 region_snapshot_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; + __u32 region_snapshot_id; +}; + +static inline struct devlink_region_new_req *devlink_region_new_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_new_req)); +} +void devlink_region_new_req_free(struct devlink_region_new_req *req); + +static inline void +devlink_region_new_req_set_bus_name(struct devlink_region_new_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_new_req_set_dev_name(struct devlink_region_new_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_region_new_req_set_port_index(struct devlink_region_new_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_region_new_req_set_region_name(struct devlink_region_new_req *req, + const char *region_name) +{ + free(req->region_name); + req->_present.region_name_len = strlen(region_name); + req->region_name = malloc(req->_present.region_name_len + 1); + memcpy(req->region_name, region_name, req->_present.region_name_len); + req->region_name[req->_present.region_name_len] = 0; +} +static inline void +devlink_region_new_req_set_region_snapshot_id(struct devlink_region_new_req *req, + __u32 region_snapshot_id) +{ + req->_present.region_snapshot_id = 1; + req->region_snapshot_id = region_snapshot_id; +} + +struct devlink_region_new_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + __u32 region_snapshot_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; + __u32 region_snapshot_id; +}; + +void devlink_region_new_rsp_free(struct devlink_region_new_rsp *rsp); + +/* + * Create region snapshot. + */ +struct devlink_region_new_rsp * +devlink_region_new(struct ynl_sock *ys, struct devlink_region_new_req *req); + +/* ============== DEVLINK_CMD_REGION_DEL ============== */ +/* DEVLINK_CMD_REGION_DEL - do */ +struct devlink_region_del_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + __u32 region_snapshot_id:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; + __u32 region_snapshot_id; +}; + +static inline struct devlink_region_del_req *devlink_region_del_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_del_req)); +} +void devlink_region_del_req_free(struct devlink_region_del_req *req); + +static inline void +devlink_region_del_req_set_bus_name(struct devlink_region_del_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_del_req_set_dev_name(struct devlink_region_del_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_region_del_req_set_port_index(struct devlink_region_del_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_region_del_req_set_region_name(struct devlink_region_del_req *req, + const char *region_name) +{ + free(req->region_name); + req->_present.region_name_len = strlen(region_name); + req->region_name = malloc(req->_present.region_name_len + 1); + memcpy(req->region_name, region_name, req->_present.region_name_len); + req->region_name[req->_present.region_name_len] = 0; +} +static inline void +devlink_region_del_req_set_region_snapshot_id(struct devlink_region_del_req *req, + __u32 region_snapshot_id) +{ + req->_present.region_snapshot_id = 1; + req->region_snapshot_id = region_snapshot_id; +} + +/* + * Delete region snapshot. + */ +int devlink_region_del(struct ynl_sock *ys, struct devlink_region_del_req *req); + +/* ============== DEVLINK_CMD_REGION_READ ============== */ +/* DEVLINK_CMD_REGION_READ - dump */ +struct devlink_region_read_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + __u32 region_snapshot_id:1; + __u32 region_direct:1; + __u32 region_chunk_addr:1; + __u32 region_chunk_len:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; + __u32 region_snapshot_id; + __u64 region_chunk_addr; + __u64 region_chunk_len; +}; + +static inline struct devlink_region_read_req_dump * +devlink_region_read_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_region_read_req_dump)); +} +void +devlink_region_read_req_dump_free(struct devlink_region_read_req_dump *req); + +static inline void +devlink_region_read_req_dump_set_bus_name(struct devlink_region_read_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_region_read_req_dump_set_dev_name(struct devlink_region_read_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_region_read_req_dump_set_port_index(struct devlink_region_read_req_dump *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_region_read_req_dump_set_region_name(struct devlink_region_read_req_dump *req, + const char *region_name) +{ + free(req->region_name); + req->_present.region_name_len = strlen(region_name); + req->region_name = malloc(req->_present.region_name_len + 1); + memcpy(req->region_name, region_name, req->_present.region_name_len); + req->region_name[req->_present.region_name_len] = 0; +} +static inline void +devlink_region_read_req_dump_set_region_snapshot_id(struct devlink_region_read_req_dump *req, + __u32 region_snapshot_id) +{ + req->_present.region_snapshot_id = 1; + req->region_snapshot_id = region_snapshot_id; +} +static inline void +devlink_region_read_req_dump_set_region_direct(struct devlink_region_read_req_dump *req) +{ + req->_present.region_direct = 1; +} +static inline void +devlink_region_read_req_dump_set_region_chunk_addr(struct devlink_region_read_req_dump *req, + __u64 region_chunk_addr) +{ + req->_present.region_chunk_addr = 1; + req->region_chunk_addr = region_chunk_addr; +} +static inline void +devlink_region_read_req_dump_set_region_chunk_len(struct devlink_region_read_req_dump *req, + __u64 region_chunk_len) +{ + req->_present.region_chunk_len = 1; + req->region_chunk_len = region_chunk_len; +} + +struct devlink_region_read_rsp_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 region_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *region_name; +}; + +struct devlink_region_read_rsp_list { + struct devlink_region_read_rsp_list *next; + struct devlink_region_read_rsp_dump obj __attribute__((aligned(8))); +}; + +void +devlink_region_read_rsp_list_free(struct devlink_region_read_rsp_list *rsp); + +struct devlink_region_read_rsp_list * +devlink_region_read_dump(struct ynl_sock *ys, + struct devlink_region_read_req_dump *req); + +/* ============== DEVLINK_CMD_PORT_PARAM_GET ============== */ +/* DEVLINK_CMD_PORT_PARAM_GET - do */ +struct devlink_port_param_get_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_port_param_get_req * +devlink_port_param_get_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_param_get_req)); +} +void devlink_port_param_get_req_free(struct devlink_port_param_get_req *req); + +static inline void +devlink_port_param_get_req_set_bus_name(struct devlink_port_param_get_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_param_get_req_set_dev_name(struct devlink_port_param_get_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_param_get_req_set_port_index(struct devlink_port_param_get_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +struct devlink_port_param_get_rsp { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +void devlink_port_param_get_rsp_free(struct devlink_port_param_get_rsp *rsp); + +/* + * Get port param instances. + */ +struct devlink_port_param_get_rsp * +devlink_port_param_get(struct ynl_sock *ys, + struct devlink_port_param_get_req *req); + +/* DEVLINK_CMD_PORT_PARAM_GET - dump */ +struct devlink_port_param_get_list { + struct devlink_port_param_get_list *next; + struct devlink_port_param_get_rsp obj __attribute__((aligned(8))); +}; + +void devlink_port_param_get_list_free(struct devlink_port_param_get_list *rsp); + +struct devlink_port_param_get_list * +devlink_port_param_get_dump(struct ynl_sock *ys); + +/* ============== DEVLINK_CMD_PORT_PARAM_SET ============== */ +/* DEVLINK_CMD_PORT_PARAM_SET - do */ +struct devlink_port_param_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; +}; + +static inline struct devlink_port_param_set_req * +devlink_port_param_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_port_param_set_req)); +} +void devlink_port_param_set_req_free(struct devlink_port_param_set_req *req); + +static inline void +devlink_port_param_set_req_set_bus_name(struct devlink_port_param_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_port_param_set_req_set_dev_name(struct devlink_port_param_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_port_param_set_req_set_port_index(struct devlink_port_param_set_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} + +/* + * Set port param instances. + */ +int devlink_port_param_set(struct ynl_sock *ys, + struct devlink_port_param_set_req *req); + /* ============== DEVLINK_CMD_INFO_GET ============== */ /* DEVLINK_CMD_INFO_GET - do */ struct devlink_info_get_req { @@ -1144,7 +3279,7 @@ devlink_info_get(struct ynl_sock *ys, struct devlink_info_get_req *req); /* DEVLINK_CMD_INFO_GET - dump */ struct devlink_info_get_list { struct devlink_info_get_list *next; - struct devlink_info_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_info_get_rsp obj __attribute__((aligned(8))); }; void devlink_info_get_list_free(struct devlink_info_get_list *rsp); @@ -1288,7 +3423,7 @@ devlink_health_reporter_get_req_dump_set_port_index(struct devlink_health_report struct devlink_health_reporter_get_list { struct devlink_health_reporter_get_list *next; - struct devlink_health_reporter_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_health_reporter_get_rsp obj __attribute__((aligned(8))); }; void @@ -1298,6 +3433,466 @@ struct devlink_health_reporter_get_list * devlink_health_reporter_get_dump(struct ynl_sock *ys, struct devlink_health_reporter_get_req_dump *req); +/* ============== DEVLINK_CMD_HEALTH_REPORTER_SET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_SET - do */ +struct devlink_health_reporter_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + __u32 health_reporter_graceful_period:1; + __u32 health_reporter_auto_recover:1; + __u32 health_reporter_auto_dump:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; + __u64 health_reporter_graceful_period; + __u8 health_reporter_auto_recover; + __u8 health_reporter_auto_dump; +}; + +static inline struct devlink_health_reporter_set_req * +devlink_health_reporter_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_set_req)); +} +void +devlink_health_reporter_set_req_free(struct devlink_health_reporter_set_req *req); + +static inline void +devlink_health_reporter_set_req_set_bus_name(struct devlink_health_reporter_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_set_req_set_dev_name(struct devlink_health_reporter_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_set_req_set_port_index(struct devlink_health_reporter_set_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_set_req_set_health_reporter_name(struct devlink_health_reporter_set_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} +static inline void +devlink_health_reporter_set_req_set_health_reporter_graceful_period(struct devlink_health_reporter_set_req *req, + __u64 health_reporter_graceful_period) +{ + req->_present.health_reporter_graceful_period = 1; + req->health_reporter_graceful_period = health_reporter_graceful_period; +} +static inline void +devlink_health_reporter_set_req_set_health_reporter_auto_recover(struct devlink_health_reporter_set_req *req, + __u8 health_reporter_auto_recover) +{ + req->_present.health_reporter_auto_recover = 1; + req->health_reporter_auto_recover = health_reporter_auto_recover; +} +static inline void +devlink_health_reporter_set_req_set_health_reporter_auto_dump(struct devlink_health_reporter_set_req *req, + __u8 health_reporter_auto_dump) +{ + req->_present.health_reporter_auto_dump = 1; + req->health_reporter_auto_dump = health_reporter_auto_dump; +} + +/* + * Set health reporter instances. + */ +int devlink_health_reporter_set(struct ynl_sock *ys, + struct devlink_health_reporter_set_req *req); + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_RECOVER ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_RECOVER - do */ +struct devlink_health_reporter_recover_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_recover_req * +devlink_health_reporter_recover_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_recover_req)); +} +void +devlink_health_reporter_recover_req_free(struct devlink_health_reporter_recover_req *req); + +static inline void +devlink_health_reporter_recover_req_set_bus_name(struct devlink_health_reporter_recover_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_recover_req_set_dev_name(struct devlink_health_reporter_recover_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_recover_req_set_port_index(struct devlink_health_reporter_recover_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_recover_req_set_health_reporter_name(struct devlink_health_reporter_recover_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +/* + * Recover health reporter instances. + */ +int devlink_health_reporter_recover(struct ynl_sock *ys, + struct devlink_health_reporter_recover_req *req); + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE - do */ +struct devlink_health_reporter_diagnose_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_diagnose_req * +devlink_health_reporter_diagnose_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_diagnose_req)); +} +void +devlink_health_reporter_diagnose_req_free(struct devlink_health_reporter_diagnose_req *req); + +static inline void +devlink_health_reporter_diagnose_req_set_bus_name(struct devlink_health_reporter_diagnose_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_diagnose_req_set_dev_name(struct devlink_health_reporter_diagnose_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_diagnose_req_set_port_index(struct devlink_health_reporter_diagnose_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_diagnose_req_set_health_reporter_name(struct devlink_health_reporter_diagnose_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +/* + * Diagnose health reporter instances. + */ +int devlink_health_reporter_diagnose(struct ynl_sock *ys, + struct devlink_health_reporter_diagnose_req *req); + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET - dump */ +struct devlink_health_reporter_dump_get_req_dump { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_dump_get_req_dump * +devlink_health_reporter_dump_get_req_dump_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_dump_get_req_dump)); +} +void +devlink_health_reporter_dump_get_req_dump_free(struct devlink_health_reporter_dump_get_req_dump *req); + +static inline void +devlink_health_reporter_dump_get_req_dump_set_bus_name(struct devlink_health_reporter_dump_get_req_dump *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_dump_get_req_dump_set_dev_name(struct devlink_health_reporter_dump_get_req_dump *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_dump_get_req_dump_set_port_index(struct devlink_health_reporter_dump_get_req_dump *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_dump_get_req_dump_set_health_reporter_name(struct devlink_health_reporter_dump_get_req_dump *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +struct devlink_health_reporter_dump_get_rsp_dump { + struct { + __u32 fmsg:1; + } _present; + + struct devlink_dl_fmsg fmsg; +}; + +struct devlink_health_reporter_dump_get_rsp_list { + struct devlink_health_reporter_dump_get_rsp_list *next; + struct devlink_health_reporter_dump_get_rsp_dump obj __attribute__((aligned(8))); +}; + +void +devlink_health_reporter_dump_get_rsp_list_free(struct devlink_health_reporter_dump_get_rsp_list *rsp); + +struct devlink_health_reporter_dump_get_rsp_list * +devlink_health_reporter_dump_get_dump(struct ynl_sock *ys, + struct devlink_health_reporter_dump_get_req_dump *req); + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR - do */ +struct devlink_health_reporter_dump_clear_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_dump_clear_req * +devlink_health_reporter_dump_clear_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_dump_clear_req)); +} +void +devlink_health_reporter_dump_clear_req_free(struct devlink_health_reporter_dump_clear_req *req); + +static inline void +devlink_health_reporter_dump_clear_req_set_bus_name(struct devlink_health_reporter_dump_clear_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_dump_clear_req_set_dev_name(struct devlink_health_reporter_dump_clear_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_dump_clear_req_set_port_index(struct devlink_health_reporter_dump_clear_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_dump_clear_req_set_health_reporter_name(struct devlink_health_reporter_dump_clear_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +/* + * Clear dump of health reporter instances. + */ +int devlink_health_reporter_dump_clear(struct ynl_sock *ys, + struct devlink_health_reporter_dump_clear_req *req); + +/* ============== DEVLINK_CMD_FLASH_UPDATE ============== */ +/* DEVLINK_CMD_FLASH_UPDATE - do */ +struct devlink_flash_update_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 flash_update_file_name_len; + __u32 flash_update_component_len; + __u32 flash_update_overwrite_mask:1; + } _present; + + char *bus_name; + char *dev_name; + char *flash_update_file_name; + char *flash_update_component; + struct nla_bitfield32 flash_update_overwrite_mask; +}; + +static inline struct devlink_flash_update_req * +devlink_flash_update_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_flash_update_req)); +} +void devlink_flash_update_req_free(struct devlink_flash_update_req *req); + +static inline void +devlink_flash_update_req_set_bus_name(struct devlink_flash_update_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_flash_update_req_set_dev_name(struct devlink_flash_update_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_flash_update_req_set_flash_update_file_name(struct devlink_flash_update_req *req, + const char *flash_update_file_name) +{ + free(req->flash_update_file_name); + req->_present.flash_update_file_name_len = strlen(flash_update_file_name); + req->flash_update_file_name = malloc(req->_present.flash_update_file_name_len + 1); + memcpy(req->flash_update_file_name, flash_update_file_name, req->_present.flash_update_file_name_len); + req->flash_update_file_name[req->_present.flash_update_file_name_len] = 0; +} +static inline void +devlink_flash_update_req_set_flash_update_component(struct devlink_flash_update_req *req, + const char *flash_update_component) +{ + free(req->flash_update_component); + req->_present.flash_update_component_len = strlen(flash_update_component); + req->flash_update_component = malloc(req->_present.flash_update_component_len + 1); + memcpy(req->flash_update_component, flash_update_component, req->_present.flash_update_component_len); + req->flash_update_component[req->_present.flash_update_component_len] = 0; +} +static inline void +devlink_flash_update_req_set_flash_update_overwrite_mask(struct devlink_flash_update_req *req, + struct nla_bitfield32 *flash_update_overwrite_mask) +{ + req->_present.flash_update_overwrite_mask = 1; + memcpy(&req->flash_update_overwrite_mask, flash_update_overwrite_mask, sizeof(struct nla_bitfield32)); +} + +/* + * Flash update devlink instances. + */ +int devlink_flash_update(struct ynl_sock *ys, + struct devlink_flash_update_req *req); + /* ============== DEVLINK_CMD_TRAP_GET ============== */ /* DEVLINK_CMD_TRAP_GET - do */ struct devlink_trap_get_req { @@ -1410,7 +4005,7 @@ devlink_trap_get_req_dump_set_dev_name(struct devlink_trap_get_req_dump *req, struct devlink_trap_get_list { struct devlink_trap_get_list *next; - struct devlink_trap_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_trap_get_rsp obj __attribute__((aligned(8))); }; void devlink_trap_get_list_free(struct devlink_trap_get_list *rsp); @@ -1419,6 +4014,71 @@ struct devlink_trap_get_list * devlink_trap_get_dump(struct ynl_sock *ys, struct devlink_trap_get_req_dump *req); +/* ============== DEVLINK_CMD_TRAP_SET ============== */ +/* DEVLINK_CMD_TRAP_SET - do */ +struct devlink_trap_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_name_len; + __u32 trap_action:1; + } _present; + + char *bus_name; + char *dev_name; + char *trap_name; + enum devlink_trap_action trap_action; +}; + +static inline struct devlink_trap_set_req *devlink_trap_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_set_req)); +} +void devlink_trap_set_req_free(struct devlink_trap_set_req *req); + +static inline void +devlink_trap_set_req_set_bus_name(struct devlink_trap_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_set_req_set_dev_name(struct devlink_trap_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_set_req_set_trap_name(struct devlink_trap_set_req *req, + const char *trap_name) +{ + free(req->trap_name); + req->_present.trap_name_len = strlen(trap_name); + req->trap_name = malloc(req->_present.trap_name_len + 1); + memcpy(req->trap_name, trap_name, req->_present.trap_name_len); + req->trap_name[req->_present.trap_name_len] = 0; +} +static inline void +devlink_trap_set_req_set_trap_action(struct devlink_trap_set_req *req, + enum devlink_trap_action trap_action) +{ + req->_present.trap_action = 1; + req->trap_action = trap_action; +} + +/* + * Set trap instances. + */ +int devlink_trap_set(struct ynl_sock *ys, struct devlink_trap_set_req *req); + /* ============== DEVLINK_CMD_TRAP_GROUP_GET ============== */ /* DEVLINK_CMD_TRAP_GROUP_GET - do */ struct devlink_trap_group_get_req { @@ -1534,7 +4194,7 @@ devlink_trap_group_get_req_dump_set_dev_name(struct devlink_trap_group_get_req_d struct devlink_trap_group_get_list { struct devlink_trap_group_get_list *next; - struct devlink_trap_group_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_trap_group_get_rsp obj __attribute__((aligned(8))); }; void devlink_trap_group_get_list_free(struct devlink_trap_group_get_list *rsp); @@ -1543,6 +4203,82 @@ struct devlink_trap_group_get_list * devlink_trap_group_get_dump(struct ynl_sock *ys, struct devlink_trap_group_get_req_dump *req); +/* ============== DEVLINK_CMD_TRAP_GROUP_SET ============== */ +/* DEVLINK_CMD_TRAP_GROUP_SET - do */ +struct devlink_trap_group_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_group_name_len; + __u32 trap_action:1; + __u32 trap_policer_id:1; + } _present; + + char *bus_name; + char *dev_name; + char *trap_group_name; + enum devlink_trap_action trap_action; + __u32 trap_policer_id; +}; + +static inline struct devlink_trap_group_set_req * +devlink_trap_group_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_group_set_req)); +} +void devlink_trap_group_set_req_free(struct devlink_trap_group_set_req *req); + +static inline void +devlink_trap_group_set_req_set_bus_name(struct devlink_trap_group_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_group_set_req_set_dev_name(struct devlink_trap_group_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_group_set_req_set_trap_group_name(struct devlink_trap_group_set_req *req, + const char *trap_group_name) +{ + free(req->trap_group_name); + req->_present.trap_group_name_len = strlen(trap_group_name); + req->trap_group_name = malloc(req->_present.trap_group_name_len + 1); + memcpy(req->trap_group_name, trap_group_name, req->_present.trap_group_name_len); + req->trap_group_name[req->_present.trap_group_name_len] = 0; +} +static inline void +devlink_trap_group_set_req_set_trap_action(struct devlink_trap_group_set_req *req, + enum devlink_trap_action trap_action) +{ + req->_present.trap_action = 1; + req->trap_action = trap_action; +} +static inline void +devlink_trap_group_set_req_set_trap_policer_id(struct devlink_trap_group_set_req *req, + __u32 trap_policer_id) +{ + req->_present.trap_policer_id = 1; + req->trap_policer_id = trap_policer_id; +} + +/* + * Set trap group instances. + */ +int devlink_trap_group_set(struct ynl_sock *ys, + struct devlink_trap_group_set_req *req); + /* ============== DEVLINK_CMD_TRAP_POLICER_GET ============== */ /* DEVLINK_CMD_TRAP_POLICER_GET - do */ struct devlink_trap_policer_get_req { @@ -1657,7 +4393,7 @@ devlink_trap_policer_get_req_dump_set_dev_name(struct devlink_trap_policer_get_r struct devlink_trap_policer_get_list { struct devlink_trap_policer_get_list *next; - struct devlink_trap_policer_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_trap_policer_get_rsp obj __attribute__((aligned(8))); }; void @@ -1667,6 +4403,148 @@ struct devlink_trap_policer_get_list * devlink_trap_policer_get_dump(struct ynl_sock *ys, struct devlink_trap_policer_get_req_dump *req); +/* ============== DEVLINK_CMD_TRAP_POLICER_SET ============== */ +/* DEVLINK_CMD_TRAP_POLICER_SET - do */ +struct devlink_trap_policer_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 trap_policer_id:1; + __u32 trap_policer_rate:1; + __u32 trap_policer_burst:1; + } _present; + + char *bus_name; + char *dev_name; + __u32 trap_policer_id; + __u64 trap_policer_rate; + __u64 trap_policer_burst; +}; + +static inline struct devlink_trap_policer_set_req * +devlink_trap_policer_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_trap_policer_set_req)); +} +void +devlink_trap_policer_set_req_free(struct devlink_trap_policer_set_req *req); + +static inline void +devlink_trap_policer_set_req_set_bus_name(struct devlink_trap_policer_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_trap_policer_set_req_set_dev_name(struct devlink_trap_policer_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_trap_policer_set_req_set_trap_policer_id(struct devlink_trap_policer_set_req *req, + __u32 trap_policer_id) +{ + req->_present.trap_policer_id = 1; + req->trap_policer_id = trap_policer_id; +} +static inline void +devlink_trap_policer_set_req_set_trap_policer_rate(struct devlink_trap_policer_set_req *req, + __u64 trap_policer_rate) +{ + req->_present.trap_policer_rate = 1; + req->trap_policer_rate = trap_policer_rate; +} +static inline void +devlink_trap_policer_set_req_set_trap_policer_burst(struct devlink_trap_policer_set_req *req, + __u64 trap_policer_burst) +{ + req->_present.trap_policer_burst = 1; + req->trap_policer_burst = trap_policer_burst; +} + +/* + * Get trap policer instances. + */ +int devlink_trap_policer_set(struct ynl_sock *ys, + struct devlink_trap_policer_set_req *req); + +/* ============== DEVLINK_CMD_HEALTH_REPORTER_TEST ============== */ +/* DEVLINK_CMD_HEALTH_REPORTER_TEST - do */ +struct devlink_health_reporter_test_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 port_index:1; + __u32 health_reporter_name_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 port_index; + char *health_reporter_name; +}; + +static inline struct devlink_health_reporter_test_req * +devlink_health_reporter_test_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_health_reporter_test_req)); +} +void +devlink_health_reporter_test_req_free(struct devlink_health_reporter_test_req *req); + +static inline void +devlink_health_reporter_test_req_set_bus_name(struct devlink_health_reporter_test_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_health_reporter_test_req_set_dev_name(struct devlink_health_reporter_test_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_health_reporter_test_req_set_port_index(struct devlink_health_reporter_test_req *req, + __u32 port_index) +{ + req->_present.port_index = 1; + req->port_index = port_index; +} +static inline void +devlink_health_reporter_test_req_set_health_reporter_name(struct devlink_health_reporter_test_req *req, + const char *health_reporter_name) +{ + free(req->health_reporter_name); + req->_present.health_reporter_name_len = strlen(health_reporter_name); + req->health_reporter_name = malloc(req->_present.health_reporter_name_len + 1); + memcpy(req->health_reporter_name, health_reporter_name, req->_present.health_reporter_name_len); + req->health_reporter_name[req->_present.health_reporter_name_len] = 0; +} + +/* + * Test health reporter instances. + */ +int devlink_health_reporter_test(struct ynl_sock *ys, + struct devlink_health_reporter_test_req *req); + /* ============== DEVLINK_CMD_RATE_GET ============== */ /* DEVLINK_CMD_RATE_GET - do */ struct devlink_rate_get_req { @@ -1790,7 +4668,7 @@ devlink_rate_get_req_dump_set_dev_name(struct devlink_rate_get_req_dump *req, struct devlink_rate_get_list { struct devlink_rate_get_list *next; - struct devlink_rate_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_rate_get_rsp obj __attribute__((aligned(8))); }; void devlink_rate_get_list_free(struct devlink_rate_get_list *rsp); @@ -1799,6 +4677,270 @@ struct devlink_rate_get_list * devlink_rate_get_dump(struct ynl_sock *ys, struct devlink_rate_get_req_dump *req); +/* ============== DEVLINK_CMD_RATE_SET ============== */ +/* DEVLINK_CMD_RATE_SET - do */ +struct devlink_rate_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 rate_node_name_len; + __u32 rate_tx_share:1; + __u32 rate_tx_max:1; + __u32 rate_tx_priority:1; + __u32 rate_tx_weight:1; + __u32 rate_parent_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *rate_node_name; + __u64 rate_tx_share; + __u64 rate_tx_max; + __u32 rate_tx_priority; + __u32 rate_tx_weight; + char *rate_parent_node_name; +}; + +static inline struct devlink_rate_set_req *devlink_rate_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_set_req)); +} +void devlink_rate_set_req_free(struct devlink_rate_set_req *req); + +static inline void +devlink_rate_set_req_set_bus_name(struct devlink_rate_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_set_req_set_dev_name(struct devlink_rate_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_rate_set_req_set_rate_node_name(struct devlink_rate_set_req *req, + const char *rate_node_name) +{ + free(req->rate_node_name); + req->_present.rate_node_name_len = strlen(rate_node_name); + req->rate_node_name = malloc(req->_present.rate_node_name_len + 1); + memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len); + req->rate_node_name[req->_present.rate_node_name_len] = 0; +} +static inline void +devlink_rate_set_req_set_rate_tx_share(struct devlink_rate_set_req *req, + __u64 rate_tx_share) +{ + req->_present.rate_tx_share = 1; + req->rate_tx_share = rate_tx_share; +} +static inline void +devlink_rate_set_req_set_rate_tx_max(struct devlink_rate_set_req *req, + __u64 rate_tx_max) +{ + req->_present.rate_tx_max = 1; + req->rate_tx_max = rate_tx_max; +} +static inline void +devlink_rate_set_req_set_rate_tx_priority(struct devlink_rate_set_req *req, + __u32 rate_tx_priority) +{ + req->_present.rate_tx_priority = 1; + req->rate_tx_priority = rate_tx_priority; +} +static inline void +devlink_rate_set_req_set_rate_tx_weight(struct devlink_rate_set_req *req, + __u32 rate_tx_weight) +{ + req->_present.rate_tx_weight = 1; + req->rate_tx_weight = rate_tx_weight; +} +static inline void +devlink_rate_set_req_set_rate_parent_node_name(struct devlink_rate_set_req *req, + const char *rate_parent_node_name) +{ + free(req->rate_parent_node_name); + req->_present.rate_parent_node_name_len = strlen(rate_parent_node_name); + req->rate_parent_node_name = malloc(req->_present.rate_parent_node_name_len + 1); + memcpy(req->rate_parent_node_name, rate_parent_node_name, req->_present.rate_parent_node_name_len); + req->rate_parent_node_name[req->_present.rate_parent_node_name_len] = 0; +} + +/* + * Set rate instances. + */ +int devlink_rate_set(struct ynl_sock *ys, struct devlink_rate_set_req *req); + +/* ============== DEVLINK_CMD_RATE_NEW ============== */ +/* DEVLINK_CMD_RATE_NEW - do */ +struct devlink_rate_new_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 rate_node_name_len; + __u32 rate_tx_share:1; + __u32 rate_tx_max:1; + __u32 rate_tx_priority:1; + __u32 rate_tx_weight:1; + __u32 rate_parent_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *rate_node_name; + __u64 rate_tx_share; + __u64 rate_tx_max; + __u32 rate_tx_priority; + __u32 rate_tx_weight; + char *rate_parent_node_name; +}; + +static inline struct devlink_rate_new_req *devlink_rate_new_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_new_req)); +} +void devlink_rate_new_req_free(struct devlink_rate_new_req *req); + +static inline void +devlink_rate_new_req_set_bus_name(struct devlink_rate_new_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_new_req_set_dev_name(struct devlink_rate_new_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_rate_new_req_set_rate_node_name(struct devlink_rate_new_req *req, + const char *rate_node_name) +{ + free(req->rate_node_name); + req->_present.rate_node_name_len = strlen(rate_node_name); + req->rate_node_name = malloc(req->_present.rate_node_name_len + 1); + memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len); + req->rate_node_name[req->_present.rate_node_name_len] = 0; +} +static inline void +devlink_rate_new_req_set_rate_tx_share(struct devlink_rate_new_req *req, + __u64 rate_tx_share) +{ + req->_present.rate_tx_share = 1; + req->rate_tx_share = rate_tx_share; +} +static inline void +devlink_rate_new_req_set_rate_tx_max(struct devlink_rate_new_req *req, + __u64 rate_tx_max) +{ + req->_present.rate_tx_max = 1; + req->rate_tx_max = rate_tx_max; +} +static inline void +devlink_rate_new_req_set_rate_tx_priority(struct devlink_rate_new_req *req, + __u32 rate_tx_priority) +{ + req->_present.rate_tx_priority = 1; + req->rate_tx_priority = rate_tx_priority; +} +static inline void +devlink_rate_new_req_set_rate_tx_weight(struct devlink_rate_new_req *req, + __u32 rate_tx_weight) +{ + req->_present.rate_tx_weight = 1; + req->rate_tx_weight = rate_tx_weight; +} +static inline void +devlink_rate_new_req_set_rate_parent_node_name(struct devlink_rate_new_req *req, + const char *rate_parent_node_name) +{ + free(req->rate_parent_node_name); + req->_present.rate_parent_node_name_len = strlen(rate_parent_node_name); + req->rate_parent_node_name = malloc(req->_present.rate_parent_node_name_len + 1); + memcpy(req->rate_parent_node_name, rate_parent_node_name, req->_present.rate_parent_node_name_len); + req->rate_parent_node_name[req->_present.rate_parent_node_name_len] = 0; +} + +/* + * Create rate instances. + */ +int devlink_rate_new(struct ynl_sock *ys, struct devlink_rate_new_req *req); + +/* ============== DEVLINK_CMD_RATE_DEL ============== */ +/* DEVLINK_CMD_RATE_DEL - do */ +struct devlink_rate_del_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 rate_node_name_len; + } _present; + + char *bus_name; + char *dev_name; + char *rate_node_name; +}; + +static inline struct devlink_rate_del_req *devlink_rate_del_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_rate_del_req)); +} +void devlink_rate_del_req_free(struct devlink_rate_del_req *req); + +static inline void +devlink_rate_del_req_set_bus_name(struct devlink_rate_del_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_rate_del_req_set_dev_name(struct devlink_rate_del_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_rate_del_req_set_rate_node_name(struct devlink_rate_del_req *req, + const char *rate_node_name) +{ + free(req->rate_node_name); + req->_present.rate_node_name_len = strlen(rate_node_name); + req->rate_node_name = malloc(req->_present.rate_node_name_len + 1); + memcpy(req->rate_node_name, rate_node_name, req->_present.rate_node_name_len); + req->rate_node_name[req->_present.rate_node_name_len] = 0; +} + +/* + * Delete rate instances. + */ +int devlink_rate_del(struct ynl_sock *ys, struct devlink_rate_del_req *req); + /* ============== DEVLINK_CMD_LINECARD_GET ============== */ /* DEVLINK_CMD_LINECARD_GET - do */ struct devlink_linecard_get_req { @@ -1910,7 +5052,7 @@ devlink_linecard_get_req_dump_set_dev_name(struct devlink_linecard_get_req_dump struct devlink_linecard_get_list { struct devlink_linecard_get_list *next; - struct devlink_linecard_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_linecard_get_rsp obj __attribute__((aligned(8))); }; void devlink_linecard_get_list_free(struct devlink_linecard_get_list *rsp); @@ -1919,6 +5061,73 @@ struct devlink_linecard_get_list * devlink_linecard_get_dump(struct ynl_sock *ys, struct devlink_linecard_get_req_dump *req); +/* ============== DEVLINK_CMD_LINECARD_SET ============== */ +/* DEVLINK_CMD_LINECARD_SET - do */ +struct devlink_linecard_set_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 linecard_index:1; + __u32 linecard_type_len; + } _present; + + char *bus_name; + char *dev_name; + __u32 linecard_index; + char *linecard_type; +}; + +static inline struct devlink_linecard_set_req * +devlink_linecard_set_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_linecard_set_req)); +} +void devlink_linecard_set_req_free(struct devlink_linecard_set_req *req); + +static inline void +devlink_linecard_set_req_set_bus_name(struct devlink_linecard_set_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_linecard_set_req_set_dev_name(struct devlink_linecard_set_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_linecard_set_req_set_linecard_index(struct devlink_linecard_set_req *req, + __u32 linecard_index) +{ + req->_present.linecard_index = 1; + req->linecard_index = linecard_index; +} +static inline void +devlink_linecard_set_req_set_linecard_type(struct devlink_linecard_set_req *req, + const char *linecard_type) +{ + free(req->linecard_type); + req->_present.linecard_type_len = strlen(linecard_type); + req->linecard_type = malloc(req->_present.linecard_type_len + 1); + memcpy(req->linecard_type, linecard_type, req->_present.linecard_type_len); + req->linecard_type[req->_present.linecard_type_len] = 0; +} + +/* + * Set line card instances. + */ +int devlink_linecard_set(struct ynl_sock *ys, + struct devlink_linecard_set_req *req); + /* ============== DEVLINK_CMD_SELFTESTS_GET ============== */ /* DEVLINK_CMD_SELFTESTS_GET - do */ struct devlink_selftests_get_req { @@ -1981,7 +5190,7 @@ devlink_selftests_get(struct ynl_sock *ys, /* DEVLINK_CMD_SELFTESTS_GET - dump */ struct devlink_selftests_get_list { struct devlink_selftests_get_list *next; - struct devlink_selftests_get_rsp obj __attribute__ ((aligned (8))); + struct devlink_selftests_get_rsp obj __attribute__((aligned(8))); }; void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp); @@ -1989,4 +5198,58 @@ void devlink_selftests_get_list_free(struct devlink_selftests_get_list *rsp); struct devlink_selftests_get_list * devlink_selftests_get_dump(struct ynl_sock *ys); +/* ============== DEVLINK_CMD_SELFTESTS_RUN ============== */ +/* DEVLINK_CMD_SELFTESTS_RUN - do */ +struct devlink_selftests_run_req { + struct { + __u32 bus_name_len; + __u32 dev_name_len; + __u32 selftests:1; + } _present; + + char *bus_name; + char *dev_name; + struct devlink_dl_selftest_id selftests; +}; + +static inline struct devlink_selftests_run_req * +devlink_selftests_run_req_alloc(void) +{ + return calloc(1, sizeof(struct devlink_selftests_run_req)); +} +void devlink_selftests_run_req_free(struct devlink_selftests_run_req *req); + +static inline void +devlink_selftests_run_req_set_bus_name(struct devlink_selftests_run_req *req, + const char *bus_name) +{ + free(req->bus_name); + req->_present.bus_name_len = strlen(bus_name); + req->bus_name = malloc(req->_present.bus_name_len + 1); + memcpy(req->bus_name, bus_name, req->_present.bus_name_len); + req->bus_name[req->_present.bus_name_len] = 0; +} +static inline void +devlink_selftests_run_req_set_dev_name(struct devlink_selftests_run_req *req, + const char *dev_name) +{ + free(req->dev_name); + req->_present.dev_name_len = strlen(dev_name); + req->dev_name = malloc(req->_present.dev_name_len + 1); + memcpy(req->dev_name, dev_name, req->_present.dev_name_len); + req->dev_name[req->_present.dev_name_len] = 0; +} +static inline void +devlink_selftests_run_req_set_selftests_flash(struct devlink_selftests_run_req *req) +{ + req->_present.selftests = 1; + req->selftests._present.flash = 1; +} + +/* + * Run device selftest instances. + */ +int devlink_selftests_run(struct ynl_sock *ys, + struct devlink_selftests_run_req *req); + #endif /* _LINUX_DEVLINK_GEN_H */ diff --git a/tools/net/ynl/generated/ethtool-user.h b/tools/net/ynl/generated/ethtool-user.h index ddc1a5209992..ca0ec5fd7798 100644 --- a/tools/net/ynl/generated/ethtool-user.h +++ b/tools/net/ynl/generated/ethtool-user.h @@ -347,7 +347,7 @@ ethtool_strset_get_req_dump_set_counts_only(struct ethtool_strset_get_req_dump * struct ethtool_strset_get_list { struct ethtool_strset_get_list *next; - struct ethtool_strset_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_strset_get_rsp obj __attribute__((aligned(8))); }; void ethtool_strset_get_list_free(struct ethtool_strset_get_list *rsp); @@ -472,7 +472,7 @@ ethtool_linkinfo_get_req_dump_set_header_flags(struct ethtool_linkinfo_get_req_d struct ethtool_linkinfo_get_list { struct ethtool_linkinfo_get_list *next; - struct ethtool_linkinfo_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_linkinfo_get_rsp obj __attribute__((aligned(8))); }; void ethtool_linkinfo_get_list_free(struct ethtool_linkinfo_get_list *rsp); @@ -487,7 +487,7 @@ struct ethtool_linkinfo_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_linkinfo_get_ntf *ntf); - struct ethtool_linkinfo_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_linkinfo_get_rsp obj __attribute__((aligned(8))); }; void ethtool_linkinfo_get_ntf_free(struct ethtool_linkinfo_get_ntf *rsp); @@ -712,7 +712,7 @@ ethtool_linkmodes_get_req_dump_set_header_flags(struct ethtool_linkmodes_get_req struct ethtool_linkmodes_get_list { struct ethtool_linkmodes_get_list *next; - struct ethtool_linkmodes_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_linkmodes_get_rsp obj __attribute__((aligned(8))); }; void ethtool_linkmodes_get_list_free(struct ethtool_linkmodes_get_list *rsp); @@ -727,7 +727,7 @@ struct ethtool_linkmodes_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_linkmodes_get_ntf *ntf); - struct ethtool_linkmodes_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_linkmodes_get_rsp obj __attribute__((aligned(8))); }; void ethtool_linkmodes_get_ntf_free(struct ethtool_linkmodes_get_ntf *rsp); @@ -1014,7 +1014,7 @@ ethtool_linkstate_get_req_dump_set_header_flags(struct ethtool_linkstate_get_req struct ethtool_linkstate_get_list { struct ethtool_linkstate_get_list *next; - struct ethtool_linkstate_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_linkstate_get_rsp obj __attribute__((aligned(8))); }; void ethtool_linkstate_get_list_free(struct ethtool_linkstate_get_list *rsp); @@ -1129,7 +1129,7 @@ ethtool_debug_get_req_dump_set_header_flags(struct ethtool_debug_get_req_dump *r struct ethtool_debug_get_list { struct ethtool_debug_get_list *next; - struct ethtool_debug_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_debug_get_rsp obj __attribute__((aligned(8))); }; void ethtool_debug_get_list_free(struct ethtool_debug_get_list *rsp); @@ -1144,7 +1144,7 @@ struct ethtool_debug_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_debug_get_ntf *ntf); - struct ethtool_debug_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_debug_get_rsp obj __attribute__((aligned(8))); }; void ethtool_debug_get_ntf_free(struct ethtool_debug_get_ntf *rsp); @@ -1330,7 +1330,7 @@ ethtool_wol_get_req_dump_set_header_flags(struct ethtool_wol_get_req_dump *req, struct ethtool_wol_get_list { struct ethtool_wol_get_list *next; - struct ethtool_wol_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_wol_get_rsp obj __attribute__((aligned(8))); }; void ethtool_wol_get_list_free(struct ethtool_wol_get_list *rsp); @@ -1344,7 +1344,7 @@ struct ethtool_wol_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_wol_get_ntf *ntf); - struct ethtool_wol_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_wol_get_rsp obj __attribute__((aligned(8))); }; void ethtool_wol_get_ntf_free(struct ethtool_wol_get_ntf *rsp); @@ -1546,7 +1546,7 @@ ethtool_features_get_req_dump_set_header_flags(struct ethtool_features_get_req_d struct ethtool_features_get_list { struct ethtool_features_get_list *next; - struct ethtool_features_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_features_get_rsp obj __attribute__((aligned(8))); }; void ethtool_features_get_list_free(struct ethtool_features_get_list *rsp); @@ -1561,7 +1561,7 @@ struct ethtool_features_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_features_get_ntf *ntf); - struct ethtool_features_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_features_get_rsp obj __attribute__((aligned(8))); }; void ethtool_features_get_ntf_free(struct ethtool_features_get_ntf *rsp); @@ -1843,7 +1843,7 @@ ethtool_privflags_get_req_dump_set_header_flags(struct ethtool_privflags_get_req struct ethtool_privflags_get_list { struct ethtool_privflags_get_list *next; - struct ethtool_privflags_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_privflags_get_rsp obj __attribute__((aligned(8))); }; void ethtool_privflags_get_list_free(struct ethtool_privflags_get_list *rsp); @@ -1858,7 +1858,7 @@ struct ethtool_privflags_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_privflags_get_ntf *ntf); - struct ethtool_privflags_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_privflags_get_rsp obj __attribute__((aligned(8))); }; void ethtool_privflags_get_ntf_free(struct ethtool_privflags_get_ntf *rsp); @@ -2072,7 +2072,7 @@ ethtool_rings_get_req_dump_set_header_flags(struct ethtool_rings_get_req_dump *r struct ethtool_rings_get_list { struct ethtool_rings_get_list *next; - struct ethtool_rings_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_rings_get_rsp obj __attribute__((aligned(8))); }; void ethtool_rings_get_list_free(struct ethtool_rings_get_list *rsp); @@ -2087,7 +2087,7 @@ struct ethtool_rings_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_rings_get_ntf *ntf); - struct ethtool_rings_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_rings_get_rsp obj __attribute__((aligned(8))); }; void ethtool_rings_get_ntf_free(struct ethtool_rings_get_ntf *rsp); @@ -2395,7 +2395,7 @@ ethtool_channels_get_req_dump_set_header_flags(struct ethtool_channels_get_req_d struct ethtool_channels_get_list { struct ethtool_channels_get_list *next; - struct ethtool_channels_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_channels_get_rsp obj __attribute__((aligned(8))); }; void ethtool_channels_get_list_free(struct ethtool_channels_get_list *rsp); @@ -2410,7 +2410,7 @@ struct ethtool_channels_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_channels_get_ntf *ntf); - struct ethtool_channels_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_channels_get_rsp obj __attribute__((aligned(8))); }; void ethtool_channels_get_ntf_free(struct ethtool_channels_get_ntf *rsp); @@ -2697,7 +2697,7 @@ ethtool_coalesce_get_req_dump_set_header_flags(struct ethtool_coalesce_get_req_d struct ethtool_coalesce_get_list { struct ethtool_coalesce_get_list *next; - struct ethtool_coalesce_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_coalesce_get_rsp obj __attribute__((aligned(8))); }; void ethtool_coalesce_get_list_free(struct ethtool_coalesce_get_list *rsp); @@ -2712,7 +2712,7 @@ struct ethtool_coalesce_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_coalesce_get_ntf *ntf); - struct ethtool_coalesce_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_coalesce_get_rsp obj __attribute__((aligned(8))); }; void ethtool_coalesce_get_ntf_free(struct ethtool_coalesce_get_ntf *rsp); @@ -3124,7 +3124,7 @@ ethtool_pause_get_req_dump_set_header_flags(struct ethtool_pause_get_req_dump *r struct ethtool_pause_get_list { struct ethtool_pause_get_list *next; - struct ethtool_pause_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_pause_get_rsp obj __attribute__((aligned(8))); }; void ethtool_pause_get_list_free(struct ethtool_pause_get_list *rsp); @@ -3139,7 +3139,7 @@ struct ethtool_pause_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_pause_get_ntf *ntf); - struct ethtool_pause_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_pause_get_rsp obj __attribute__((aligned(8))); }; void ethtool_pause_get_ntf_free(struct ethtool_pause_get_ntf *rsp); @@ -3360,7 +3360,7 @@ ethtool_eee_get_req_dump_set_header_flags(struct ethtool_eee_get_req_dump *req, struct ethtool_eee_get_list { struct ethtool_eee_get_list *next; - struct ethtool_eee_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_eee_get_rsp obj __attribute__((aligned(8))); }; void ethtool_eee_get_list_free(struct ethtool_eee_get_list *rsp); @@ -3374,7 +3374,7 @@ struct ethtool_eee_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_eee_get_ntf *ntf); - struct ethtool_eee_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_eee_get_rsp obj __attribute__((aligned(8))); }; void ethtool_eee_get_ntf_free(struct ethtool_eee_get_ntf *rsp); @@ -3623,7 +3623,7 @@ ethtool_tsinfo_get_req_dump_set_header_flags(struct ethtool_tsinfo_get_req_dump struct ethtool_tsinfo_get_list { struct ethtool_tsinfo_get_list *next; - struct ethtool_tsinfo_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_tsinfo_get_rsp obj __attribute__((aligned(8))); }; void ethtool_tsinfo_get_list_free(struct ethtool_tsinfo_get_list *rsp); @@ -3842,7 +3842,7 @@ ethtool_tunnel_info_get_req_dump_set_header_flags(struct ethtool_tunnel_info_get struct ethtool_tunnel_info_get_list { struct ethtool_tunnel_info_get_list *next; - struct ethtool_tunnel_info_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_tunnel_info_get_rsp obj __attribute__((aligned(8))); }; void @@ -3964,7 +3964,7 @@ ethtool_fec_get_req_dump_set_header_flags(struct ethtool_fec_get_req_dump *req, struct ethtool_fec_get_list { struct ethtool_fec_get_list *next; - struct ethtool_fec_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_fec_get_rsp obj __attribute__((aligned(8))); }; void ethtool_fec_get_list_free(struct ethtool_fec_get_list *rsp); @@ -3978,7 +3978,7 @@ struct ethtool_fec_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_fec_get_ntf *ntf); - struct ethtool_fec_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_fec_get_rsp obj __attribute__((aligned(8))); }; void ethtool_fec_get_ntf_free(struct ethtool_fec_get_ntf *rsp); @@ -4221,7 +4221,7 @@ ethtool_module_eeprom_get_req_dump_set_header_flags(struct ethtool_module_eeprom struct ethtool_module_eeprom_get_list { struct ethtool_module_eeprom_get_list *next; - struct ethtool_module_eeprom_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_module_eeprom_get_rsp obj __attribute__((aligned(8))); }; void @@ -4340,7 +4340,7 @@ ethtool_phc_vclocks_get_req_dump_set_header_flags(struct ethtool_phc_vclocks_get struct ethtool_phc_vclocks_get_list { struct ethtool_phc_vclocks_get_list *next; - struct ethtool_phc_vclocks_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_phc_vclocks_get_rsp obj __attribute__((aligned(8))); }; void @@ -4458,7 +4458,7 @@ ethtool_module_get_req_dump_set_header_flags(struct ethtool_module_get_req_dump struct ethtool_module_get_list { struct ethtool_module_get_list *next; - struct ethtool_module_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_module_get_rsp obj __attribute__((aligned(8))); }; void ethtool_module_get_list_free(struct ethtool_module_get_list *rsp); @@ -4473,7 +4473,7 @@ struct ethtool_module_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_module_get_ntf *ntf); - struct ethtool_module_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_module_get_rsp obj __attribute__((aligned(8))); }; void ethtool_module_get_ntf_free(struct ethtool_module_get_ntf *rsp); @@ -4654,7 +4654,7 @@ ethtool_pse_get_req_dump_set_header_flags(struct ethtool_pse_get_req_dump *req, struct ethtool_pse_get_list { struct ethtool_pse_get_list *next; - struct ethtool_pse_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_pse_get_rsp obj __attribute__((aligned(8))); }; void ethtool_pse_get_list_free(struct ethtool_pse_get_list *rsp); @@ -4849,7 +4849,7 @@ ethtool_rss_get_req_dump_set_header_flags(struct ethtool_rss_get_req_dump *req, struct ethtool_rss_get_list { struct ethtool_rss_get_list *next; - struct ethtool_rss_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_rss_get_rsp obj __attribute__((aligned(8))); }; void ethtool_rss_get_list_free(struct ethtool_rss_get_list *rsp); @@ -4979,7 +4979,7 @@ ethtool_plca_get_cfg_req_dump_set_header_flags(struct ethtool_plca_get_cfg_req_d struct ethtool_plca_get_cfg_list { struct ethtool_plca_get_cfg_list *next; - struct ethtool_plca_get_cfg_rsp obj __attribute__ ((aligned (8))); + struct ethtool_plca_get_cfg_rsp obj __attribute__((aligned(8))); }; void ethtool_plca_get_cfg_list_free(struct ethtool_plca_get_cfg_list *rsp); @@ -4994,7 +4994,7 @@ struct ethtool_plca_get_cfg_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_plca_get_cfg_ntf *ntf); - struct ethtool_plca_get_cfg_rsp obj __attribute__ ((aligned (8))); + struct ethtool_plca_get_cfg_rsp obj __attribute__((aligned(8))); }; void ethtool_plca_get_cfg_ntf_free(struct ethtool_plca_get_cfg_ntf *rsp); @@ -5244,7 +5244,7 @@ ethtool_plca_get_status_req_dump_set_header_flags(struct ethtool_plca_get_status struct ethtool_plca_get_status_list { struct ethtool_plca_get_status_list *next; - struct ethtool_plca_get_status_rsp obj __attribute__ ((aligned (8))); + struct ethtool_plca_get_status_rsp obj __attribute__((aligned(8))); }; void @@ -5376,7 +5376,7 @@ ethtool_mm_get_req_dump_set_header_flags(struct ethtool_mm_get_req_dump *req, struct ethtool_mm_get_list { struct ethtool_mm_get_list *next; - struct ethtool_mm_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_mm_get_rsp obj __attribute__((aligned(8))); }; void ethtool_mm_get_list_free(struct ethtool_mm_get_list *rsp); @@ -5390,7 +5390,7 @@ struct ethtool_mm_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_mm_get_ntf *ntf); - struct ethtool_mm_get_rsp obj __attribute__ ((aligned (8))); + struct ethtool_mm_get_rsp obj __attribute__((aligned(8))); }; void ethtool_mm_get_ntf_free(struct ethtool_mm_get_ntf *rsp); @@ -5504,7 +5504,7 @@ struct ethtool_cable_test_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_cable_test_ntf *ntf); - struct ethtool_cable_test_ntf_rsp obj __attribute__ ((aligned (8))); + struct ethtool_cable_test_ntf_rsp obj __attribute__((aligned(8))); }; void ethtool_cable_test_ntf_free(struct ethtool_cable_test_ntf *rsp); @@ -5527,7 +5527,7 @@ struct ethtool_cable_test_tdr_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ethtool_cable_test_tdr_ntf *ntf); - struct ethtool_cable_test_tdr_ntf_rsp obj __attribute__ ((aligned (8))); + struct ethtool_cable_test_tdr_ntf_rsp obj __attribute__((aligned(8))); }; void ethtool_cable_test_tdr_ntf_free(struct ethtool_cable_test_tdr_ntf *rsp); diff --git a/tools/net/ynl/generated/fou-user.h b/tools/net/ynl/generated/fou-user.h index a8f860892540..fd566716ddd6 100644 --- a/tools/net/ynl/generated/fou-user.h +++ b/tools/net/ynl/generated/fou-user.h @@ -333,7 +333,7 @@ struct fou_get_rsp *fou_get(struct ynl_sock *ys, struct fou_get_req *req); /* FOU_CMD_GET - dump */ struct fou_get_list { struct fou_get_list *next; - struct fou_get_rsp obj __attribute__ ((aligned (8))); + struct fou_get_rsp obj __attribute__((aligned(8))); }; void fou_get_list_free(struct fou_get_list *rsp); diff --git a/tools/net/ynl/generated/handshake-user.h b/tools/net/ynl/generated/handshake-user.h index 2b34acc608de..bce537d8b8cc 100644 --- a/tools/net/ynl/generated/handshake-user.h +++ b/tools/net/ynl/generated/handshake-user.h @@ -90,7 +90,7 @@ struct handshake_accept_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct handshake_accept_ntf *ntf); - struct handshake_accept_rsp obj __attribute__ ((aligned (8))); + struct handshake_accept_rsp obj __attribute__((aligned(8))); }; void handshake_accept_ntf_free(struct handshake_accept_ntf *rsp); diff --git a/tools/net/ynl/generated/netdev-user.h b/tools/net/ynl/generated/netdev-user.h index b4351ff34595..4fafac879df3 100644 --- a/tools/net/ynl/generated/netdev-user.h +++ b/tools/net/ynl/generated/netdev-user.h @@ -69,7 +69,7 @@ netdev_dev_get(struct ynl_sock *ys, struct netdev_dev_get_req *req); /* NETDEV_CMD_DEV_GET - dump */ struct netdev_dev_get_list { struct netdev_dev_get_list *next; - struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); + struct netdev_dev_get_rsp obj __attribute__((aligned(8))); }; void netdev_dev_get_list_free(struct netdev_dev_get_list *rsp); @@ -82,7 +82,7 @@ struct netdev_dev_get_ntf { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct netdev_dev_get_ntf *ntf); - struct netdev_dev_get_rsp obj __attribute__ ((aligned (8))); + struct netdev_dev_get_rsp obj __attribute__((aligned(8))); }; void netdev_dev_get_ntf_free(struct netdev_dev_get_ntf *rsp); diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index 37bcb4d8b37b..92889298b197 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -149,6 +149,7 @@ class SpecAttr(SpecElement): Represents a single attribute type within an attr space. Attributes: + type string, attribute type value numerical ID when serialized attr_set Attribute Set containing this attr is_multi bool, attr may repeat multiple times @@ -157,10 +158,13 @@ class SpecAttr(SpecElement): len integer, optional byte length of binary types display_hint string, hint to help choose format specifier when displaying the value + + is_auto_scalar bool, attr is a variable-size scalar """ def __init__(self, family, attr_set, yaml, value): super().__init__(family, yaml) + self.type = yaml['type'] self.value = value self.attr_set = attr_set self.is_multi = yaml.get('multi-attr', False) @@ -170,6 +174,8 @@ class SpecAttr(SpecElement): self.len = yaml.get('len') self.display_hint = yaml.get('display-hint') + self.is_auto_scalar = self.type == "sint" or self.type == "uint" + class SpecAttrSet(SpecElement): """ Netlink Attribute Set class. diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index 514e0d69e731..830d25097009 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -352,6 +352,12 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, "Invalid attribute (u64 %s)", policy->name); return -1; + case YNL_PT_UINT: + if (len == sizeof(__u32) || len == sizeof(__u64)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (uint %s)", policy->name); + return -1; case YNL_PT_FLAG: /* Let flags grow into real attrs, why not.. */ break; @@ -373,6 +379,12 @@ int ynl_attr_validate(struct ynl_parse_arg *yarg, const struct nlattr *attr) yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, "Invalid attribute (string %s)", policy->name); return -1; + case YNL_PT_BITFIELD32: + if (len == sizeof(struct nla_bitfield32)) + break; + yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, + "Invalid attribute (bitfield32 %s)", policy->name); + return -1; default: yerr(yarg->ys, YNL_ERROR_ATTR_INVALID, "Invalid attribute (unknown %s)", policy->name); diff --git a/tools/net/ynl/lib/ynl.h b/tools/net/ynl/lib/ynl.h index 9eafa3552c16..e974378e3b8c 100644 --- a/tools/net/ynl/lib/ynl.h +++ b/tools/net/ynl/lib/ynl.h @@ -133,7 +133,9 @@ enum ynl_policy_type { YNL_PT_U16, YNL_PT_U32, YNL_PT_U64, + YNL_PT_UINT, YNL_PT_NUL_STR, + YNL_PT_BITFIELD32, }; struct ynl_policy_attr { @@ -156,7 +158,7 @@ struct ynl_parse_arg { struct ynl_dump_list_type { struct ynl_dump_list_type *next; - unsigned char data[] __attribute__ ((aligned (8))); + unsigned char data[] __attribute__((aligned(8))); }; extern struct ynl_dump_list_type *YNL_LIST_END; @@ -186,7 +188,7 @@ struct ynl_ntf_base_type { __u8 cmd; struct ynl_ntf_base_type *next; void (*free)(struct ynl_ntf_base_type *ntf); - unsigned char data[] __attribute__ ((aligned (8))); + unsigned char data[] __attribute__((aligned(8))); }; extern mnl_cb_t ynl_cb_array[NLMSG_MIN_TYPE]; @@ -234,4 +236,20 @@ int ynl_exec_dump(struct ynl_sock *ys, struct nlmsghdr *req_nlh, void ynl_error_unknown_notification(struct ynl_sock *ys, __u8 cmd); int ynl_error_parse(struct ynl_parse_arg *yarg, const char *msg); +#ifndef MNL_HAS_AUTO_SCALARS +static inline uint64_t mnl_attr_get_uint(const struct nlattr *attr) +{ + if (mnl_attr_get_len(attr) == 4) + return mnl_attr_get_u32(attr); + return mnl_attr_get_u64(attr); +} + +static inline void +mnl_attr_put_uint(struct nlmsghdr *nlh, uint16_t type, uint64_t data) +{ + if ((uint32_t)data == (uint64_t)data) + return mnl_attr_put_u32(nlh, type, data); + return mnl_attr_put_u64(nlh, type, data); +} +#endif #endif diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index 28ac35008e65..b1da4aea9336 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -130,6 +130,13 @@ class NlAttr: format = self.get_format(attr_type, byte_order) return format.unpack(self.raw)[0] + def as_auto_scalar(self, attr_type, byte_order=None): + if len(self.raw) != 4 and len(self.raw) != 8: + raise Exception(f"Auto-scalar len payload be 4 or 8 bytes, got {len(self.raw)}") + real_type = attr_type[0] + str(len(self.raw) * 8) + format = self.get_format(real_type, byte_order) + return format.unpack(self.raw)[0] + def as_strz(self): return self.raw.decode('ascii')[:-1] @@ -463,9 +470,16 @@ class YnlFamily(SpecFamily): attr_payload = bytes.fromhex(value) else: raise Exception(f'Unknown type for binary attribute, value: {value}') + elif attr.is_auto_scalar: + scalar = int(value) + real_type = attr["type"][0] + ('32' if scalar.bit_length() <= 32 else '64') + format = NlAttr.get_format(real_type, attr.byte_order) + attr_payload = format.pack(int(value)) elif attr['type'] in NlAttr.type_formats: format = NlAttr.get_format(attr['type'], attr.byte_order) attr_payload = format.pack(int(value)) + elif attr['type'] in "bitfield32": + attr_payload = struct.pack("II", int(value["value"]), int(value["selector"])) else: raise Exception(f'Unknown type at {space} {name} {value} {attr["type"]}') @@ -529,16 +543,23 @@ class YnlFamily(SpecFamily): decoded = self._decode_binary(attr, attr_spec) elif attr_spec["type"] == 'flag': decoded = True + elif attr_spec.is_auto_scalar: + decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) elif attr_spec["type"] in NlAttr.type_formats: decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) + if 'enum' in attr_spec: + decoded = self._decode_enum(decoded, attr_spec) elif attr_spec["type"] == 'array-nest': decoded = self._decode_array_nest(attr, attr_spec) + elif attr_spec["type"] == 'bitfield32': + value, selector = struct.unpack("II", attr.raw) + if 'enum' in attr_spec: + value = self._decode_enum(value, attr_spec) + selector = self._decode_enum(selector, attr_spec) + decoded = {"value": value, "selector": selector} else: raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') - if 'enum' in attr_spec: - decoded = self._decode_enum(decoded, attr_spec) - if not attr_spec.is_multi: rsp[attr_spec['name']] = decoded elif attr_spec.name in rsp: diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index f125b5f704ba..13427436bfb7 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -20,6 +20,21 @@ def c_lower(name): return name.lower().replace('-', '_') +def limit_to_number(name): + """ + Turn a string limit like u32-max or s64-min into its numerical value + """ + if name[0] == 'u' and name.endswith('-min'): + return 0 + width = int(name[1:-4]) + if name[0] == 's': + width -= 1 + value = (1 << width) - 1 + if name[0] == 's' and name.endswith('-min'): + value = -value - 1 + return value + + class BaseNlLib: def get_family_id(self): return 'ys->family_id' @@ -42,8 +57,12 @@ class Type(SpecAttr): self.type = attr['type'] self.checks = attr.get('checks', {}) + self.request = False + self.reply = False + if 'len' in attr: self.len = attr['len'] + if 'nested-attributes' in attr: self.nested_attrs = attr['nested-attributes'] if self.nested_attrs == family.name: @@ -64,6 +83,14 @@ class Type(SpecAttr): self.enum_name = None delattr(self, "enum_name") + def get_limit(self, limit, default=None): + value = self.checks.get(limit, default) + if value is None: + return value + if not isinstance(value, int): + value = limit_to_number(value) + return value + def resolve(self): if 'name-prefix' in self.attr: enum_name = f"{self.attr['name-prefix']}{self.name}" @@ -132,6 +159,15 @@ class Type(SpecAttr): spec = self._attr_policy(policy) cw.p(f"\t[{self.enum_name}] = {spec},") + def _mnl_type(self): + # mnl does not have helpers for signed integer types + # turn signed type into unsigned + # this only makes sense for scalar types + t = self.type + if t[0] == 's': + t = 'u' + t[1:] + return t + def _attr_typol(self): raise Exception(f"Type policy not implemented for class type {self.type}") @@ -259,6 +295,27 @@ class TypeScalar(Type): if 'byte-order' in attr: self.byte_order_comment = f" /* {attr['byte-order']} */" + if 'enum' in self.attr: + enum = self.family.consts[self.attr['enum']] + low, high = enum.value_range() + if 'min' not in self.checks: + if low != 0 or self.type[0] == 's': + self.checks['min'] = low + if 'max' not in self.checks: + self.checks['max'] = high + + if 'min' in self.checks and 'max' in self.checks: + if self.get_limit('min') > self.get_limit('max'): + raise Exception(f'Invalid limit for "{self.name}" min: {self.get_limit("min")} max: {self.get_limit("max")}') + self.checks['range'] = True + + low = min(self.get_limit('min', 0), self.get_limit('max', 0)) + high = max(self.get_limit('min', 0), self.get_limit('max', 0)) + if low < 0 and self.type[0] == 'u': + raise Exception(f'Invalid limit for "{self.name}" negative limit for unsigned type') + if low < -32768 or high > 32767: + self.checks['full-range'] = True + # Added by resolve(): self.is_bitfield = None delattr(self, "is_bitfield") @@ -278,15 +335,13 @@ class TypeScalar(Type): maybe_enum = not self.is_bitfield and 'enum' in self.attr if maybe_enum and self.family.consts[self.attr['enum']].enum_name: self.type_name = f"enum {self.family.name}_{c_lower(self.attr['enum'])}" + elif self.is_auto_scalar: + self.type_name = '__' + self.type[0] + '64' else: self.type_name = '__' + self.type - def _mnl_type(self): - t = self.type - # mnl does not have a helper for signed types - if t[0] == 's': - t = 'u' + t[1:] - return t + def mnl_type(self): + return self._mnl_type() def _attr_policy(self, policy): if 'flags-mask' in self.checks or self.is_bitfield: @@ -298,27 +353,27 @@ class TypeScalar(Type): flag_cnt = len(flags['entries']) mask = (1 << flag_cnt) - 1 return f"NLA_POLICY_MASK({policy}, 0x{mask:x})" + elif 'full-range' in self.checks: + return f"NLA_POLICY_FULL_RANGE({policy}, &{c_lower(self.enum_name)}_range)" + elif 'range' in self.checks: + return f"NLA_POLICY_RANGE({policy}, {self.get_limit('min')}, {self.get_limit('max')})" elif 'min' in self.checks: - return f"NLA_POLICY_MIN({policy}, {self.checks['min']})" - elif 'enum' in self.attr: - enum = self.family.consts[self.attr['enum']] - low, high = enum.value_range() - if low == 0: - return f"NLA_POLICY_MAX({policy}, {high})" - return f"NLA_POLICY_RANGE({policy}, {low}, {high})" + return f"NLA_POLICY_MIN({policy}, {self.get_limit('min')})" + elif 'max' in self.checks: + return f"NLA_POLICY_MAX({policy}, {self.get_limit('max')})" return super()._attr_policy(policy) def _attr_typol(self): - return f'.type = YNL_PT_U{self.type[1:]}, ' + return f'.type = YNL_PT_U{c_upper(self.type[1:])}, ' def arg_member(self, ri): return [f'{self.type_name} {self.c_name}{self.byte_order_comment}'] def attr_put(self, ri, var): - self._attr_put_simple(ri, var, self._mnl_type()) + self._attr_put_simple(ri, var, self.mnl_type()) def _attr_get(self, ri, var): - return f"{var}->{self.c_name} = mnl_attr_get_{self._mnl_type()}(attr);", None, None + return f"{var}->{self.c_name} = mnl_attr_get_{self.mnl_type()}(attr);", None, None def _setter_lines(self, ri, member, presence): return [f"{member} = {self.c_name};"] @@ -355,10 +410,13 @@ class TypeString(Type): return f'.type = YNL_PT_NUL_STR, ' def _attr_policy(self, policy): - mem = '{ .type = ' + policy - if 'max-len' in self.checks: - mem += ', .len = ' + str(self.checks['max-len']) - mem += ', }' + if 'exact-len' in self.checks: + mem = 'NLA_POLICY_EXACT_LEN(' + str(self.checks['exact-len']) + ')' + else: + mem = '{ .type = ' + policy + if 'max-len' in self.checks: + mem += ', .len = ' + str(self.get_limit('max-len')) + mem += ', }' return mem def attr_policy(self, cw): @@ -404,14 +462,17 @@ class TypeBinary(Type): return f'.type = YNL_PT_BINARY,' def _attr_policy(self, policy): - mem = '{ ' - if len(self.checks) == 1 and 'min-len' in self.checks: - mem += '.len = ' + str(self.checks['min-len']) - elif len(self.checks) == 0: - mem += '.type = NLA_BINARY' + if 'exact-len' in self.checks: + mem = 'NLA_POLICY_EXACT_LEN(' + str(self.checks['exact-len']) + ')' else: - raise Exception('One or more of binary type checks not implemented, yet') - mem += ', }' + mem = '{ ' + if len(self.checks) == 1 and 'min-len' in self.checks: + mem += '.len = ' + str(self.get_limit('min-len')) + elif len(self.checks) == 0: + mem += '.type = NLA_BINARY' + else: + raise Exception('One or more of binary type checks not implemented, yet') + mem += ', }' return mem def attr_put(self, ri, var): @@ -433,6 +494,31 @@ class TypeBinary(Type): f'memcpy({member}, {self.c_name}, {presence}_len);'] +class TypeBitfield32(Type): + def _complex_member_type(self, ri): + return "struct nla_bitfield32" + + def _attr_typol(self): + return f'.type = YNL_PT_BITFIELD32, ' + + def _attr_policy(self, policy): + if not 'enum' in self.attr: + raise Exception('Enum required for bitfield32 attr') + enum = self.family.consts[self.attr['enum']] + mask = enum.get_mask(as_flags=True) + return f"NLA_POLICY_BITFIELD32({mask})" + + def attr_put(self, ri, var): + line = f"mnl_attr_put(nlh, {self.enum_name}, sizeof(struct nla_bitfield32), &{var}->{self.c_name})" + self._attr_put_line(ri, var, line) + + def _attr_get(self, ri, var): + return f"memcpy(&{var}->{self.c_name}, mnl_attr_get_payload(attr), sizeof(struct nla_bitfield32));", None, None + + def _setter_lines(self, ri, member, presence): + return [f"memcpy(&{member}, {self.c_name}, sizeof(struct nla_bitfield32));"] + + class TypeNest(Type): def _complex_member_type(self, ri): return self.nested_struct_type @@ -476,12 +562,8 @@ class TypeMultiAttr(Type): def presence_type(self): return 'count' - def _mnl_type(self): - t = self.type - # mnl does not have a helper for signed types - if t[0] == 's': - t = 'u' + t[1:] - return t + def mnl_type(self): + return self._mnl_type() def _complex_member_type(self, ri): if 'type' not in self.attr or self.attr['type'] == 'nest': @@ -516,7 +598,7 @@ class TypeMultiAttr(Type): def attr_put(self, ri, var): if self.attr['type'] in scalars: - put_type = self._mnl_type() + put_type = self.mnl_type() ri.cw.p(f"for (unsigned int i = 0; i < {var}->n_{self.c_name}; i++)") ri.cw.p(f"mnl_attr_put_{put_type}(nlh, {self.enum_name}, {var}->{self.c_name}[i]);") elif 'type' not in self.attr or self.attr['type'] == 'nest': @@ -707,9 +789,11 @@ class AttrSet(SpecAttrSet): pfx = f"{family.name}-a-{self.name}-" self.name_prefix = c_upper(pfx) self.max_name = c_upper(self.yaml.get('attr-max-name', f"{self.name_prefix}max")) + self.cnt_name = c_upper(self.yaml.get('attr-cnt-name', f"__{self.name_prefix}max")) else: self.name_prefix = family.attr_sets[self.subset_of].name_prefix self.max_name = family.attr_sets[self.subset_of].max_name + self.cnt_name = family.attr_sets[self.subset_of].cnt_name # Added by resolve: self.c_name = None @@ -735,6 +819,8 @@ class AttrSet(SpecAttrSet): t = TypeString(self.family, self, elem, value) elif elem['type'] == 'binary': t = TypeBinary(self.family, self, elem, value) + elif elem['type'] == 'bitfield32': + t = TypeBitfield32(self.family, self, elem, value) elif elem['type'] == 'nest': t = TypeNest(self.family, self, elem, value) elif elem['type'] == 'array-nest': @@ -846,6 +932,7 @@ class Family(SpecFamily): self._load_root_sets() self._load_nested_sets() + self._load_attr_use() self._load_hooks() self.kernel_policy = self.yaml.get('kernel-policy', 'split') @@ -966,6 +1053,22 @@ class Family(SpecFamily): child.request |= struct.request child.reply |= struct.reply + def _load_attr_use(self): + for _, struct in self.pure_nested_structs.items(): + if struct.request: + for _, arg in struct.member_list(): + arg.request = True + if struct.reply: + for _, arg in struct.member_list(): + arg.reply = True + + for root_set, rs_members in self.root_sets.items(): + for attr, spec in self.attr_sets[root_set].items(): + if attr in rs_members['request']: + spec.request = True + if attr in rs_members['reply']: + spec.reply = True + def _load_global_policy(self): global_set = set() attr_set_name = None @@ -1017,10 +1120,13 @@ class RenderInfo: # 'do' and 'dump' response parsing is identical self.type_consistent = True - if op_mode != 'do' and 'dump' in op and 'do' in op: - if ('reply' in op['do']) != ('reply' in op["dump"]): - self.type_consistent = False - elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]: + if op_mode != 'do' and 'dump' in op: + if 'do' in op: + if ('reply' in op['do']) != ('reply' in op["dump"]): + self.type_consistent = False + elif 'reply' in op['do'] and op["do"]["reply"] != op["dump"]["reply"]: + self.type_consistent = False + else: self.type_consistent = False self.attr_set = attr_set @@ -1058,6 +1164,7 @@ class CodeWriter: self._block_end = False self._silent_block = False self._ind = 0 + self._ifdef_block = None if out_file is None: self._out = os.sys.stdout else: @@ -1098,6 +1205,8 @@ class CodeWriter: if self._silent_block: ind += 1 self._silent_block = line.endswith(')') and CodeWriter._is_cond(line) + if line[0] == '#': + ind = 0 if add_ind: ind += add_ind self._out.write('\t' * ind + line + '\n') @@ -1221,11 +1330,24 @@ class CodeWriter: for one in members: line = '.' + one[0] line += '\t' * ((longest - len(one[0]) - 1 + 7) // 8) - line += '= ' + one[1] + ',' + line += '= ' + str(one[1]) + ',' self.p(line) + def ifdef_block(self, config): + config_option = None + if config: + config_option = 'CONFIG_' + c_upper(config) + if self._ifdef_block == config_option: + return + + if self._ifdef_block: + self.p('#endif /* ' + self._ifdef_block + ' */') + if config_option: + self.p('#ifdef ' + config_option) + self._ifdef_block = config_option -scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64'} + +scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64', 'uint', 'sint'} direction_to_suffix = { 'reply': '_rsp', @@ -1515,11 +1637,8 @@ def _multi_parse(ri, struct, init_lines, local_vars): ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];") ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr))") ri.cw.p('return MNL_CB_ERROR;') - elif aspec['type'] in scalars: - t = aspec['type'] - if t[0] == 's': - t = 'u' + t[1:] - ri.cw.p(f"dst->{aspec.c_name}[i] = mnl_attr_get_{t}(attr);") + elif aspec.type in scalars: + ri.cw.p(f"dst->{aspec.c_name}[i] = mnl_attr_get_{aspec.mnl_type()}(attr);") else: raise Exception('Nest parsing type not supported yet') ri.cw.p('i++;') @@ -1807,7 +1926,7 @@ def print_wrapped_type(ri): ri.cw.p('__u8 cmd;') ri.cw.p('struct ynl_ntf_base_type *next;') ri.cw.p(f"void (*free)({type_name(ri, 'reply')} *ntf);") - ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__ ((aligned (8)));") + ri.cw.p(f"{type_name(ri, 'reply', deref=True)} obj __attribute__((aligned(8)));") ri.cw.block_end(line=';') ri.cw.nl() print_free_prototype(ri, 'reply') @@ -1905,10 +2024,13 @@ def print_req_policy_fwd(cw, struct, ri=None, terminate=True): def print_req_policy(cw, struct, ri=None): + if ri and ri.op: + cw.ifdef_block(ri.op.get('config-cond', None)) print_req_policy_fwd(cw, struct, ri=ri, terminate=False) for _, arg in struct.member_list(): arg.attr_policy(cw) cw.p("};") + cw.ifdef_block(None) cw.nl() @@ -1920,6 +2042,34 @@ def policy_should_be_static(family): return family.kernel_policy == 'split' or kernel_can_gen_family_struct(family) +def print_kernel_policy_ranges(family, cw): + first = True + for _, attr_set in family.attr_sets.items(): + if attr_set.subset_of: + continue + + for _, attr in attr_set.items(): + if not attr.request: + continue + if 'full-range' not in attr.checks: + continue + + if first: + cw.p('/* Integer value ranges */') + first = False + + sign = '' if attr.type[0] == 'u' else '_signed' + cw.block_start(line=f'static const struct netlink_range_validation{sign} {c_lower(attr.enum_name)}_range =') + members = [] + if 'min' in attr.checks: + members.append(('min', attr.get_limit('min'))) + if 'max' in attr.checks: + members.append(('max', attr.get_limit('max'))) + cw.write_struct_init(members) + cw.block_end(line=';') + cw.nl() + + def print_kernel_op_table_fwd(family, cw, terminate): exported = not kernel_can_gen_family_struct(family) @@ -1998,6 +2148,7 @@ def print_kernel_op_table(family, cw): if op.is_async: continue + cw.ifdef_block(op.get('config-cond', None)) cw.block_start() members = [('cmd', op.enum_name)] if 'dont-validate' in op: @@ -2028,6 +2179,7 @@ def print_kernel_op_table(family, cw): if op.is_async or op_mode not in op: continue + cw.ifdef_block(op.get('config-cond', None)) cw.block_start() members = [('cmd', op.enum_name)] if 'dont-validate' in op: @@ -2063,6 +2215,7 @@ def print_kernel_op_table(family, cw): members.append(('flags', ' | '.join([c_upper('genl-' + x) for x in flags]))) cw.write_struct_init(members) cw.block_end(line=',') + cw.ifdef_block(None) cw.block_end(line=';') cw.nl() @@ -2203,8 +2356,7 @@ def render_uapi(family, cw): if attr_set.subset_of: continue - cnt_name = c_upper(family.get('attr-cnt-name', f"__{attr_set.name_prefix}MAX")) - max_value = f"({cnt_name} - 1)" + max_value = f"({attr_set.cnt_name} - 1)" val = 0 uapi_enum_start(family, cw, attr_set.yaml, 'enum-name') @@ -2216,7 +2368,7 @@ def render_uapi(family, cw): val += 1 cw.p(attr.enum_name + suffix) cw.nl() - cw.p(cnt_name + ('' if max_by_define else ',')) + cw.p(attr_set.cnt_name + ('' if max_by_define else ',')) if not max_by_define: cw.p(f"{attr_set.max_name} = {max_value}") cw.block_end(line=';') @@ -2321,6 +2473,16 @@ def render_user_family(family, cw, prototype): cw.block_end(line=';') +def family_contains_bitfield32(family): + for _, attr_set in family.attr_sets.items(): + if attr_set.subset_of: + continue + for _, attr in attr_set.items(): + if attr.type == "bitfield32": + return True + return False + + def find_kernel_root(full_path): sub_path = '' while True: @@ -2406,6 +2568,8 @@ def main(): cw.p('#include <string.h>') if args.header: cw.p('#include <linux/types.h>') + if family_contains_bitfield32(parsed): + cw.p('#include <linux/netlink.h>') else: cw.p(f'#include "{parsed.name}-user.h"') cw.p('#include "ynl.h"') @@ -2459,6 +2623,8 @@ def main(): print_kernel_mcgrp_hdr(parsed, cw) print_kernel_family_struct_hdr(parsed, cw) else: + print_kernel_policy_ranges(parsed, cw) + for _, struct in sorted(parsed.pure_nested_structs.items()): if struct.request: cw.p('/* Common nested types */') diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c index 72f263d49121..4083b1abeaab 100644 --- a/tools/perf/dlfilters/dlfilter-test-api-v0.c +++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c @@ -289,6 +289,15 @@ static int check_attr(void *ctx) return 0; } +static int check_object_code(void *ctx, const struct perf_dlfilter_sample *sample) +{ + __u8 buf[15]; + + CHECK(perf_dlfilter_fns.object_code(ctx, sample->ip, buf, sizeof(buf)) > 0); + + return 0; +} + static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void *ctx, bool early) { struct filter_data *d = data; @@ -314,7 +323,8 @@ static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void if (early && !d->do_early) return 0; - if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample)) + if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample) || + check_object_code(ctx, sample)) return -1; if (early) diff --git a/tools/perf/dlfilters/dlfilter-test-api-v2.c b/tools/perf/dlfilters/dlfilter-test-api-v2.c index 38e593d92920..32ff619e881c 100644 --- a/tools/perf/dlfilters/dlfilter-test-api-v2.c +++ b/tools/perf/dlfilters/dlfilter-test-api-v2.c @@ -308,6 +308,15 @@ static int check_attr(void *ctx) return 0; } +static int check_object_code(void *ctx, const struct perf_dlfilter_sample *sample) +{ + __u8 buf[15]; + + CHECK(perf_dlfilter_fns.object_code(ctx, sample->ip, buf, sizeof(buf)) > 0); + + return 0; +} + static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void *ctx, bool early) { struct filter_data *d = data; @@ -333,7 +342,8 @@ static int do_checks(void *data, const struct perf_dlfilter_sample *sample, void if (early && !d->do_early) return 0; - if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample)) + if (check_al(ctx) || check_addr_al(ctx) || check_address_al(ctx, sample) || + check_object_code(ctx, sample)) return -1; if (early) diff --git a/tools/perf/util/dlfilter.c b/tools/perf/util/dlfilter.c index 1dbf27822ee2..4a1dc21b0450 100644 --- a/tools/perf/util/dlfilter.c +++ b/tools/perf/util/dlfilter.c @@ -282,13 +282,21 @@ static struct perf_event_attr *dlfilter__attr(void *ctx) return &d->evsel->core.attr; } +static __s32 code_read(__u64 ip, struct map *map, struct machine *machine, void *buf, __u32 len) +{ + u64 offset = map__map_ip(map, ip); + + if (ip + len >= map__end(map)) + len = map__end(map) - ip; + + return dso__data_read_offset(map__dso(map), machine, offset, buf, len); +} + static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) { struct dlfilter *d = (struct dlfilter *)ctx; struct addr_location *al; struct addr_location a; - struct map *map; - u64 offset; __s32 ret; if (!d->ctx_valid) @@ -298,27 +306,17 @@ static __s32 dlfilter__object_code(void *ctx, __u64 ip, void *buf, __u32 len) if (!al) return -1; - map = al->map; - - if (map && ip >= map__start(map) && ip < map__end(map) && + if (al->map && ip >= map__start(al->map) && ip < map__end(al->map) && machine__kernel_ip(d->machine, ip) == machine__kernel_ip(d->machine, d->sample->ip)) - goto have_map; + return code_read(ip, al->map, d->machine, buf, len); addr_location__init(&a); + thread__find_map_fb(al->thread, d->sample->cpumode, ip, &a); - if (!a.map) { - ret = -1; - goto out; - } + ret = a.map ? code_read(ip, a.map, d->machine, buf, len) : -1; - map = a.map; -have_map: - offset = map__map_ip(map, ip); - if (ip + len >= map__end(map)) - len = map__end(map) - ip; - ret = dso__data_read_offset(map__dso(map), d->machine, offset, buf, len); -out: addr_location__exit(&a); + return ret; } diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c index 8de6f39abd1b..d515ba8a0e16 100644 --- a/tools/perf/util/pmu.c +++ b/tools/perf/util/pmu.c @@ -295,7 +295,7 @@ static int perf_pmu__parse_scale(struct perf_pmu *pmu, struct perf_pmu_alias *al len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); if (!len) return 0; - scnprintf(path + len, sizeof(path) - len, "%s/%s.scale", pmu->name, alias->name); + scnprintf(path + len, sizeof(path) - len, "%s/events/%s.scale", pmu->name, alias->name); fd = open(path, O_RDONLY); if (fd == -1) @@ -330,7 +330,7 @@ static int perf_pmu__parse_unit(struct perf_pmu *pmu, struct perf_pmu_alias *ali len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); if (!len) return 0; - scnprintf(path + len, sizeof(path) - len, "%s/%s.unit", pmu->name, alias->name); + scnprintf(path + len, sizeof(path) - len, "%s/events/%s.unit", pmu->name, alias->name); fd = open(path, O_RDONLY); if (fd == -1) @@ -364,7 +364,7 @@ perf_pmu__parse_per_pkg(struct perf_pmu *pmu, struct perf_pmu_alias *alias) len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); if (!len) return 0; - scnprintf(path + len, sizeof(path) - len, "%s/%s.per-pkg", pmu->name, alias->name); + scnprintf(path + len, sizeof(path) - len, "%s/events/%s.per-pkg", pmu->name, alias->name); fd = open(path, O_RDONLY); if (fd == -1) @@ -385,7 +385,7 @@ static int perf_pmu__parse_snapshot(struct perf_pmu *pmu, struct perf_pmu_alias len = perf_pmu__event_source_devices_scnprintf(path, sizeof(path)); if (!len) return 0; - scnprintf(path + len, sizeof(path) - len, "%s/%s.snapshot", pmu->name, alias->name); + scnprintf(path + len, sizeof(path) - len, "%s/events/%s.snapshot", pmu->name, alias->name); fd = open(path, O_RDONLY); if (fd == -1) diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 4225f975fce3..9c27b67bc7b1 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -585,11 +585,20 @@ endef # Define test_progs test runner. TRUNNER_TESTS_DIR := prog_tests TRUNNER_BPF_PROGS_DIR := progs -TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ - network_helpers.c testing_helpers.c \ - btf_helpers.c flow_dissector_load.h \ - cap_helpers.c test_loader.c xsk.c disasm.c \ - json_writer.c unpriv_helpers.c \ +TRUNNER_EXTRA_SOURCES := test_progs.c \ + cgroup_helpers.c \ + trace_helpers.c \ + network_helpers.c \ + testing_helpers.c \ + btf_helpers.c \ + cap_helpers.c \ + unpriv_helpers.c \ + netlink_helpers.c \ + test_loader.c \ + xsk.c \ + disasm.c \ + json_writer.c \ + flow_dissector_load.h \ ip_check_defrag_frags.h TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ $(OUTPUT)/liburandom_read.so \ diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 2c8cb3f61529..1386baf9ae4a 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -458,4 +458,23 @@ extern void bpf_throw(u64 cookie) __ksym; __bpf_assert_op(LHS, <=, END, value, false); \ }) +struct bpf_iter_css_task; +struct cgroup_subsys_state; +extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym; +extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym; + +struct bpf_iter_task; +extern int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym; +extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym; + +struct bpf_iter_css; +extern int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) __weak __ksym; +extern struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym; +extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym; + #endif diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 02dd4409200e..3ec5927ec3e5 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -71,6 +71,7 @@ CONFIG_NETFILTER_SYNPROXY=y CONFIG_NETFILTER_XT_CONNMARK=y CONFIG_NETFILTER_XT_MATCH_STATE=y CONFIG_NETFILTER_XT_TARGET_CT=y +CONFIG_NETKIT=y CONFIG_NF_CONNTRACK=y CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_DEFRAG_IPV4=y diff --git a/tools/testing/selftests/bpf/netlink_helpers.c b/tools/testing/selftests/bpf/netlink_helpers.c new file mode 100644 index 000000000000..caf36eb1d032 --- /dev/null +++ b/tools/testing/selftests/bpf/netlink_helpers.c @@ -0,0 +1,358 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Taken & modified from iproute2's libnetlink.c + * Authors: Alexey Kuznetsov, <[email protected]> + */ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <errno.h> +#include <time.h> +#include <sys/socket.h> + +#include "netlink_helpers.h" + +static int rcvbuf = 1024 * 1024; + +void rtnl_close(struct rtnl_handle *rth) +{ + if (rth->fd >= 0) { + close(rth->fd); + rth->fd = -1; + } +} + +int rtnl_open_byproto(struct rtnl_handle *rth, unsigned int subscriptions, + int protocol) +{ + socklen_t addr_len; + int sndbuf = 32768; + int one = 1; + + memset(rth, 0, sizeof(*rth)); + rth->proto = protocol; + rth->fd = socket(AF_NETLINK, SOCK_RAW | SOCK_CLOEXEC, protocol); + if (rth->fd < 0) { + perror("Cannot open netlink socket"); + return -1; + } + if (setsockopt(rth->fd, SOL_SOCKET, SO_SNDBUF, + &sndbuf, sizeof(sndbuf)) < 0) { + perror("SO_SNDBUF"); + goto err; + } + if (setsockopt(rth->fd, SOL_SOCKET, SO_RCVBUF, + &rcvbuf, sizeof(rcvbuf)) < 0) { + perror("SO_RCVBUF"); + goto err; + } + + /* Older kernels may no support extended ACK reporting */ + setsockopt(rth->fd, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)); + + memset(&rth->local, 0, sizeof(rth->local)); + rth->local.nl_family = AF_NETLINK; + rth->local.nl_groups = subscriptions; + + if (bind(rth->fd, (struct sockaddr *)&rth->local, + sizeof(rth->local)) < 0) { + perror("Cannot bind netlink socket"); + goto err; + } + addr_len = sizeof(rth->local); + if (getsockname(rth->fd, (struct sockaddr *)&rth->local, + &addr_len) < 0) { + perror("Cannot getsockname"); + goto err; + } + if (addr_len != sizeof(rth->local)) { + fprintf(stderr, "Wrong address length %d\n", addr_len); + goto err; + } + if (rth->local.nl_family != AF_NETLINK) { + fprintf(stderr, "Wrong address family %d\n", + rth->local.nl_family); + goto err; + } + rth->seq = time(NULL); + return 0; +err: + rtnl_close(rth); + return -1; +} + +int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions) +{ + return rtnl_open_byproto(rth, subscriptions, NETLINK_ROUTE); +} + +static int __rtnl_recvmsg(int fd, struct msghdr *msg, int flags) +{ + int len; + + do { + len = recvmsg(fd, msg, flags); + } while (len < 0 && (errno == EINTR || errno == EAGAIN)); + if (len < 0) { + fprintf(stderr, "netlink receive error %s (%d)\n", + strerror(errno), errno); + return -errno; + } + if (len == 0) { + fprintf(stderr, "EOF on netlink\n"); + return -ENODATA; + } + return len; +} + +static int rtnl_recvmsg(int fd, struct msghdr *msg, char **answer) +{ + struct iovec *iov = msg->msg_iov; + char *buf; + int len; + + iov->iov_base = NULL; + iov->iov_len = 0; + + len = __rtnl_recvmsg(fd, msg, MSG_PEEK | MSG_TRUNC); + if (len < 0) + return len; + if (len < 32768) + len = 32768; + buf = malloc(len); + if (!buf) { + fprintf(stderr, "malloc error: not enough buffer\n"); + return -ENOMEM; + } + iov->iov_base = buf; + iov->iov_len = len; + len = __rtnl_recvmsg(fd, msg, 0); + if (len < 0) { + free(buf); + return len; + } + if (answer) + *answer = buf; + else + free(buf); + return len; +} + +static void rtnl_talk_error(struct nlmsghdr *h, struct nlmsgerr *err, + nl_ext_ack_fn_t errfn) +{ + fprintf(stderr, "RTNETLINK answers: %s\n", + strerror(-err->error)); +} + +static int __rtnl_talk_iov(struct rtnl_handle *rtnl, struct iovec *iov, + size_t iovlen, struct nlmsghdr **answer, + bool show_rtnl_err, nl_ext_ack_fn_t errfn) +{ + struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; + struct iovec riov; + struct msghdr msg = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = iov, + .msg_iovlen = iovlen, + }; + unsigned int seq = 0; + struct nlmsghdr *h; + int i, status; + char *buf; + + for (i = 0; i < iovlen; i++) { + h = iov[i].iov_base; + h->nlmsg_seq = seq = ++rtnl->seq; + if (answer == NULL) + h->nlmsg_flags |= NLM_F_ACK; + } + status = sendmsg(rtnl->fd, &msg, 0); + if (status < 0) { + perror("Cannot talk to rtnetlink"); + return -1; + } + /* change msg to use the response iov */ + msg.msg_iov = &riov; + msg.msg_iovlen = 1; + i = 0; + while (1) { +next: + status = rtnl_recvmsg(rtnl->fd, &msg, &buf); + ++i; + if (status < 0) + return status; + if (msg.msg_namelen != sizeof(nladdr)) { + fprintf(stderr, + "Sender address length == %d!\n", + msg.msg_namelen); + exit(1); + } + for (h = (struct nlmsghdr *)buf; status >= sizeof(*h); ) { + int len = h->nlmsg_len; + int l = len - sizeof(*h); + + if (l < 0 || len > status) { + if (msg.msg_flags & MSG_TRUNC) { + fprintf(stderr, "Truncated message!\n"); + free(buf); + return -1; + } + fprintf(stderr, + "Malformed message: len=%d!\n", + len); + exit(1); + } + if (nladdr.nl_pid != 0 || + h->nlmsg_pid != rtnl->local.nl_pid || + h->nlmsg_seq > seq || h->nlmsg_seq < seq - iovlen) { + /* Don't forget to skip that message. */ + status -= NLMSG_ALIGN(len); + h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len)); + continue; + } + if (h->nlmsg_type == NLMSG_ERROR) { + struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h); + int error = err->error; + + if (l < sizeof(struct nlmsgerr)) { + fprintf(stderr, "ERROR truncated\n"); + free(buf); + return -1; + } + if (error) { + errno = -error; + if (rtnl->proto != NETLINK_SOCK_DIAG && + show_rtnl_err) + rtnl_talk_error(h, err, errfn); + } + if (i < iovlen) { + free(buf); + goto next; + } + if (error) { + free(buf); + return -i; + } + if (answer) + *answer = (struct nlmsghdr *)buf; + else + free(buf); + return 0; + } + if (answer) { + *answer = (struct nlmsghdr *)buf; + return 0; + } + fprintf(stderr, "Unexpected reply!\n"); + status -= NLMSG_ALIGN(len); + h = (struct nlmsghdr *)((char *)h + NLMSG_ALIGN(len)); + } + free(buf); + if (msg.msg_flags & MSG_TRUNC) { + fprintf(stderr, "Message truncated!\n"); + continue; + } + if (status) { + fprintf(stderr, "Remnant of size %d!\n", status); + exit(1); + } + } +} + +static int __rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, + struct nlmsghdr **answer, bool show_rtnl_err, + nl_ext_ack_fn_t errfn) +{ + struct iovec iov = { + .iov_base = n, + .iov_len = n->nlmsg_len, + }; + + return __rtnl_talk_iov(rtnl, &iov, 1, answer, show_rtnl_err, errfn); +} + +int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, + struct nlmsghdr **answer) +{ + return __rtnl_talk(rtnl, n, answer, true, NULL); +} + +int addattr(struct nlmsghdr *n, int maxlen, int type) +{ + return addattr_l(n, maxlen, type, NULL, 0); +} + +int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u8)); +} + +int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u16)); +} + +int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u32)); +} + +int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data) +{ + return addattr_l(n, maxlen, type, &data, sizeof(__u64)); +} + +int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *str) +{ + return addattr_l(n, maxlen, type, str, strlen(str)+1); +} + +int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, + int alen) +{ + int len = RTA_LENGTH(alen); + struct rtattr *rta; + + if (NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len) > maxlen) { + fprintf(stderr, "%s: Message exceeded bound of %d\n", + __func__, maxlen); + return -1; + } + rta = NLMSG_TAIL(n); + rta->rta_type = type; + rta->rta_len = len; + if (alen) + memcpy(RTA_DATA(rta), data, alen); + n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len); + return 0; +} + +int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len) +{ + if (NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len) > maxlen) { + fprintf(stderr, "%s: Message exceeded bound of %d\n", + __func__, maxlen); + return -1; + } + + memcpy(NLMSG_TAIL(n), data, len); + memset((void *) NLMSG_TAIL(n) + len, 0, NLMSG_ALIGN(len) - len); + n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + NLMSG_ALIGN(len); + return 0; +} + +struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type) +{ + struct rtattr *nest = NLMSG_TAIL(n); + + addattr_l(n, maxlen, type, NULL, 0); + return nest; +} + +int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest) +{ + nest->rta_len = (void *)NLMSG_TAIL(n) - (void *)nest; + return n->nlmsg_len; +} diff --git a/tools/testing/selftests/bpf/netlink_helpers.h b/tools/testing/selftests/bpf/netlink_helpers.h new file mode 100644 index 000000000000..68116818a47e --- /dev/null +++ b/tools/testing/selftests/bpf/netlink_helpers.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +#ifndef NETLINK_HELPERS_H +#define NETLINK_HELPERS_H + +#include <string.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> + +struct rtnl_handle { + int fd; + struct sockaddr_nl local; + struct sockaddr_nl peer; + __u32 seq; + __u32 dump; + int proto; + FILE *dump_fp; +#define RTNL_HANDLE_F_LISTEN_ALL_NSID 0x01 +#define RTNL_HANDLE_F_SUPPRESS_NLERR 0x02 +#define RTNL_HANDLE_F_STRICT_CHK 0x04 + int flags; +}; + +#define NLMSG_TAIL(nmsg) \ + ((struct rtattr *) (((void *) (nmsg)) + NLMSG_ALIGN((nmsg)->nlmsg_len))) + +typedef int (*nl_ext_ack_fn_t)(const char *errmsg, uint32_t off, + const struct nlmsghdr *inner_nlh); + +int rtnl_open(struct rtnl_handle *rth, unsigned int subscriptions) + __attribute__((warn_unused_result)); +void rtnl_close(struct rtnl_handle *rth); +int rtnl_talk(struct rtnl_handle *rtnl, struct nlmsghdr *n, + struct nlmsghdr **answer) + __attribute__((warn_unused_result)); + +int addattr(struct nlmsghdr *n, int maxlen, int type); +int addattr8(struct nlmsghdr *n, int maxlen, int type, __u8 data); +int addattr16(struct nlmsghdr *n, int maxlen, int type, __u16 data); +int addattr32(struct nlmsghdr *n, int maxlen, int type, __u32 data); +int addattr64(struct nlmsghdr *n, int maxlen, int type, __u64 data); +int addattrstrz(struct nlmsghdr *n, int maxlen, int type, const char *data); +int addattr_l(struct nlmsghdr *n, int maxlen, int type, const void *data, int alen); +int addraw_l(struct nlmsghdr *n, int maxlen, const void *data, int len); +struct rtattr *addattr_nest(struct nlmsghdr *n, int maxlen, int type); +int addattr_nest_end(struct nlmsghdr *n, struct rtattr *nest); +#endif /* NETLINK_HELPERS_H */ diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 41aba139b20b..e3498f607b49 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -7,7 +7,7 @@ #include "bpf_iter_ipv6_route.skel.h" #include "bpf_iter_netlink.skel.h" #include "bpf_iter_bpf_map.skel.h" -#include "bpf_iter_task.skel.h" +#include "bpf_iter_tasks.skel.h" #include "bpf_iter_task_stack.skel.h" #include "bpf_iter_task_file.skel.h" #include "bpf_iter_task_vmas.skel.h" @@ -215,12 +215,12 @@ static void *do_nothing_wait(void *arg) static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, int *num_unknown, int *num_known) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; pthread_t thread_id; void *ret; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; ASSERT_OK(pthread_mutex_lock(&do_nothing_mutex), "pthread_mutex_lock"); @@ -239,7 +239,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_FALSE(pthread_join(thread_id, &ret) || ret != NULL, "pthread_join"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, int num_known) @@ -307,10 +307,10 @@ static void test_task_pidfd(void) static void test_task_sleepable(void) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; do_dummy_read(skel->progs.dump_task_sleepable); @@ -320,7 +320,7 @@ static void test_task_sleepable(void) ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, "num_success_copy_from_user_task"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_stack(void) diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c index b696873c5455..c2425791c923 100644 --- a/tools/testing/selftests/bpf/prog_tests/iters.c +++ b/tools/testing/selftests/bpf/prog_tests/iters.c @@ -1,7 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include <sys/syscall.h> +#include <sys/mman.h> +#include <sys/wait.h> +#include <unistd.h> +#include <malloc.h> +#include <stdlib.h> #include <test_progs.h> +#include "cgroup_helpers.h" #include "iters.skel.h" #include "iters_state_safety.skel.h" @@ -9,6 +16,10 @@ #include "iters_num.skel.h" #include "iters_testmod_seq.skel.h" #include "iters_task_vma.skel.h" +#include "iters_task.skel.h" +#include "iters_css_task.skel.h" +#include "iters_css.skel.h" +#include "iters_task_failure.skel.h" static void subtest_num_iters(void) { @@ -146,6 +157,138 @@ cleanup: iters_task_vma__destroy(skel); } +static pthread_mutex_t do_nothing_mutex; + +static void *do_nothing_wait(void *arg) +{ + pthread_mutex_lock(&do_nothing_mutex); + pthread_mutex_unlock(&do_nothing_mutex); + + pthread_exit(arg); +} + +#define thread_num 2 + +static void subtest_task_iters(void) +{ + struct iters_task *skel = NULL; + pthread_t thread_ids[thread_num]; + void *ret; + int err; + + skel = iters_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + skel->bss->target_pid = getpid(); + err = iters_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + pthread_mutex_lock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL), + "pthread_create"); + + syscall(SYS_getpgid); + iters_task__detach(skel); + ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt"); + ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt"); + ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt"); + pthread_mutex_unlock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join"); +cleanup: + iters_task__destroy(skel); +} + +extern int stack_mprotect(void); + +static void subtest_css_task_iters(void) +{ + struct iters_css_task *skel = NULL; + int err, cg_fd, cg_id; + const char *cgrp_path = "/cg1"; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + cg_fd = create_and_get_cgroup(cgrp_path); + if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup")) + goto cleanup; + cg_id = get_cgroup_id(cgrp_path); + err = join_cgroup(cgrp_path); + if (!ASSERT_OK(err, "join_cgroup")) + goto cleanup; + + skel = iters_css_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->cg_id = cg_id; + err = iters_css_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) + goto cleanup; + iters_css_task__detach(skel); + ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt"); + +cleanup: + cleanup_cgroup_environment(); + iters_css_task__destroy(skel); +} + +static void subtest_css_iters(void) +{ + struct iters_css *skel = NULL; + struct { + const char *path; + int fd; + } cgs[] = { + { "/cg1" }, + { "/cg1/cg2" }, + { "/cg1/cg2/cg3" }, + { "/cg1/cg2/cg3/cg4" }, + }; + int err, cg_nr = ARRAY_SIZE(cgs); + int i; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + for (i = 0; i < cg_nr; i++) { + cgs[i].fd = create_and_get_cgroup(cgs[i].path); + if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup")) + goto cleanup; + } + + skel = iters_css__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->root_cg_id = get_cgroup_id(cgs[0].path); + skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path); + err = iters_css__attach(skel); + + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + + syscall(SYS_getpgid); + ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt"); + ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id"); + + ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt"); + ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id"); + ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high"); + iters_css__detach(skel); +cleanup: + cleanup_cgroup_environment(); + iters_css__destroy(skel); +} + void test_iters(void) { RUN_TESTS(iters_state_safety); @@ -161,4 +304,11 @@ void test_iters(void) subtest_testmod_seq_iters(); if (test__start_subtest("task_vma")) subtest_task_vma_iters(); + if (test__start_subtest("task")) + subtest_task_iters(); + if (test__start_subtest("css_task")) + subtest_css_task_iters(); + if (test__start_subtest("css")) + subtest_css_iters(); + RUN_TESTS(iters_task_failure); } diff --git a/tools/testing/selftests/bpf/prog_tests/linked_list.c b/tools/testing/selftests/bpf/prog_tests/linked_list.c index 69dc31383b78..2fb89de63bd2 100644 --- a/tools/testing/selftests/bpf/prog_tests/linked_list.c +++ b/tools/testing/selftests/bpf/prog_tests/linked_list.c @@ -94,14 +94,8 @@ static struct { { "incorrect_head_var_off2", "variable ptr_ access var_off=(0x0; 0xffffffff) disallowed" }, { "incorrect_head_off1", "bpf_list_head not found at offset=25" }, { "incorrect_head_off2", "bpf_list_head not found at offset=1" }, - { "pop_front_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" - "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, - { "pop_back_off", - "15: (bf) r1 = r6 ; R1_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) " - "R6_w=ptr_or_null_foo(id=4,ref_obj_id=4,off=48,imm=0) refs=2,4\n" - "16: (85) call bpf_this_cpu_ptr#154\nR1 type=ptr_or_null_ expected=percpu_ptr_" }, + { "pop_front_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" }, + { "pop_back_off", "off 48 doesn't point to 'struct bpf_spin_lock' that is at 40" }, }; static void test_linked_list_fail_prog(const char *prog_name, const char *err_msg) diff --git a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c index 4224727fb364..626d76fe43a2 100644 --- a/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c +++ b/tools/testing/selftests/bpf/prog_tests/task_under_cgroup.c @@ -30,8 +30,15 @@ void test_task_under_cgroup(void) if (!ASSERT_OK(ret, "test_task_under_cgroup__load")) goto cleanup; - ret = test_task_under_cgroup__attach(skel); - if (!ASSERT_OK(ret, "test_task_under_cgroup__attach")) + /* First, attach the LSM program, and then it will be triggered when the + * TP_BTF program is attached. + */ + skel->links.lsm_run = bpf_program__attach_lsm(skel->progs.lsm_run); + if (!ASSERT_OK_PTR(skel->links.lsm_run, "attach_lsm")) + goto cleanup; + + skel->links.tp_btf_run = bpf_program__attach_trace(skel->progs.tp_btf_run); + if (!ASSERT_OK_PTR(skel->links.tp_btf_run, "attach_tp_btf")) goto cleanup; pid = fork(); diff --git a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h index 67f985f7d215..924d0e25320c 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_helpers.h +++ b/tools/testing/selftests/bpf/prog_tests/tc_helpers.h @@ -4,6 +4,10 @@ #define TC_HELPERS #include <test_progs.h> +#ifndef loopback +# define loopback 1 +#endif + static inline __u32 id_from_prog_fd(int fd) { struct bpf_prog_info prog_info = {}; diff --git a/tools/testing/selftests/bpf/prog_tests/tc_netkit.c b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c new file mode 100644 index 000000000000..15ee7b2fc410 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/tc_netkit.c @@ -0,0 +1,687 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Isovalent */ +#include <uapi/linux/if_link.h> +#include <net/if.h> +#include <test_progs.h> + +#define netkit_peer "nk0" +#define netkit_name "nk1" + +#define ping_addr_neigh 0x0a000002 /* 10.0.0.2 */ +#define ping_addr_noneigh 0x0a000003 /* 10.0.0.3 */ + +#include "test_tc_link.skel.h" +#include "netlink_helpers.h" +#include "tc_helpers.h" + +#define ICMP_ECHO 8 + +struct icmphdr { + __u8 type; + __u8 code; + __sum16 checksum; + struct { + __be16 id; + __be16 sequence; + } echo; +}; + +struct iplink_req { + struct nlmsghdr n; + struct ifinfomsg i; + char buf[1024]; +}; + +static int create_netkit(int mode, int policy, int peer_policy, int *ifindex, + bool same_netns) +{ + struct rtnl_handle rth = { .fd = -1 }; + struct iplink_req req = {}; + struct rtattr *linkinfo, *data; + const char *type = "netkit"; + int err; + + err = rtnl_open(&rth, 0); + if (!ASSERT_OK(err, "open_rtnetlink")) + return err; + + memset(&req, 0, sizeof(req)); + req.n.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL; + req.n.nlmsg_type = RTM_NEWLINK; + req.i.ifi_family = AF_UNSPEC; + + addattr_l(&req.n, sizeof(req), IFLA_IFNAME, netkit_name, + strlen(netkit_name)); + linkinfo = addattr_nest(&req.n, sizeof(req), IFLA_LINKINFO); + addattr_l(&req.n, sizeof(req), IFLA_INFO_KIND, type, strlen(type)); + data = addattr_nest(&req.n, sizeof(req), IFLA_INFO_DATA); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_POLICY, policy); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_PEER_POLICY, peer_policy); + addattr32(&req.n, sizeof(req), IFLA_NETKIT_MODE, mode); + addattr_nest_end(&req.n, data); + addattr_nest_end(&req.n, linkinfo); + + err = rtnl_talk(&rth, &req.n, NULL); + ASSERT_OK(err, "talk_rtnetlink"); + rtnl_close(&rth); + *ifindex = if_nametoindex(netkit_name); + + ASSERT_GT(*ifindex, 0, "retrieve_ifindex"); + ASSERT_OK(system("ip netns add foo"), "create netns"); + ASSERT_OK(system("ip link set dev " netkit_name " up"), + "up primary"); + ASSERT_OK(system("ip addr add dev " netkit_name " 10.0.0.1/24"), + "addr primary"); + if (same_netns) { + ASSERT_OK(system("ip link set dev " netkit_peer " up"), + "up peer"); + ASSERT_OK(system("ip addr add dev " netkit_peer " 10.0.0.2/24"), + "addr peer"); + } else { + ASSERT_OK(system("ip link set " netkit_peer " netns foo"), + "move peer"); + ASSERT_OK(system("ip netns exec foo ip link set dev " + netkit_peer " up"), "up peer"); + ASSERT_OK(system("ip netns exec foo ip addr add dev " + netkit_peer " 10.0.0.2/24"), "addr peer"); + } + return err; +} + +static void destroy_netkit(void) +{ + ASSERT_OK(system("ip link del dev " netkit_name), "del primary"); + ASSERT_OK(system("ip netns del foo"), "delete netns"); + ASSERT_EQ(if_nametoindex(netkit_name), 0, netkit_name "_ifindex"); +} + +static int __send_icmp(__u32 dest) +{ + struct sockaddr_in addr; + struct icmphdr icmp; + int sock, ret; + + ret = write_sysctl("/proc/sys/net/ipv4/ping_group_range", "0 0"); + if (!ASSERT_OK(ret, "write_sysctl(net.ipv4.ping_group_range)")) + return ret; + + sock = socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP); + if (!ASSERT_GE(sock, 0, "icmp_socket")) + return -errno; + + ret = setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, + netkit_name, strlen(netkit_name) + 1); + if (!ASSERT_OK(ret, "setsockopt(SO_BINDTODEVICE)")) + goto out; + + memset(&addr, 0, sizeof(addr)); + addr.sin_family = AF_INET; + addr.sin_addr.s_addr = htonl(dest); + + memset(&icmp, 0, sizeof(icmp)); + icmp.type = ICMP_ECHO; + icmp.echo.id = 1234; + icmp.echo.sequence = 1; + + ret = sendto(sock, &icmp, sizeof(icmp), 0, + (struct sockaddr *)&addr, sizeof(addr)); + if (!ASSERT_GE(ret, 0, "icmp_sendto")) + ret = -errno; + else + ret = 0; +out: + close(sock); + return ret; +} + +static int send_icmp(void) +{ + return __send_icmp(ping_addr_neigh); +} + +void serial_test_tc_netkit_basic(void) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, pid2, lid1, lid2; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(NETKIT_L2, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, + BPF_NETKIT_PEER), 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + ASSERT_NEQ(lid1, lid2, "link_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 1); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PEER, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + destroy_netkit(); +} + +static void serial_test_tc_netkit_multi_links_target(int mode, int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[3], link_ids[3]; + __u32 pid1, pid2, lid1, lid2; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + target), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, + target), 0, "tc2_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, target, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, target, 1); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + LIBBPF_OPTS_RESET(optl, + .flags = BPF_F_BEFORE, + .relative_fd = bpf_program__fd(skel->progs.tc1), + ); + + link = bpf_program__attach_netkit(skel->progs.tc2, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc2 = link; + + lid2 = id_from_link_fd(bpf_link__fd(skel->links.tc2)); + ASSERT_NEQ(lid1, lid2, "link_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid2, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], lid1, "link_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(optq.link_ids[2], 0, "link_ids[2]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, target, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_multi_links(void) +{ + serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_links_target(NETKIT_L2, BPF_NETKIT_PEER); + serial_test_tc_netkit_multi_links_target(NETKIT_L3, BPF_NETKIT_PEER); +} + +static void serial_test_tc_netkit_multi_opts_target(int mode, int target) +{ + LIBBPF_OPTS(bpf_prog_attach_opts, opta); + LIBBPF_OPTS(bpf_prog_detach_opts, optd); + LIBBPF_OPTS(bpf_prog_query_opts, optq); + __u32 pid1, pid2, fd1, fd2; + __u32 prog_ids[3]; + struct test_tc_link *skel; + int err, ifindex; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open_and_load(); + if (!ASSERT_OK_PTR(skel, "skel_load")) + goto cleanup; + + fd1 = bpf_program__fd(skel->progs.tc1); + fd2 = bpf_program__fd(skel->progs.tc2); + + pid1 = id_from_prog_fd(fd1); + pid2 = id_from_prog_fd(fd2); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, target, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + err = bpf_prog_attach_opts(fd1, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup; + + assert_mprog_count_ifindex(ifindex, target, 1); + + optq.prog_ids = prog_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_fd1; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + LIBBPF_OPTS_RESET(opta, + .flags = BPF_F_BEFORE, + .relative_fd = fd1, + ); + + err = bpf_prog_attach_opts(fd2, ifindex, target, &opta); + if (!ASSERT_EQ(err, 0, "prog_attach")) + goto cleanup_fd1; + + assert_mprog_count_ifindex(ifindex, target, 2); + + memset(prog_ids, 0, sizeof(prog_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup_fd2; + + ASSERT_EQ(optq.count, 2, "count"); + ASSERT_EQ(optq.revision, 3, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid2, "prog_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], pid1, "prog_ids[1]"); + ASSERT_EQ(optq.prog_ids[2], 0, "prog_ids[2]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, true, "seen_eth"); + ASSERT_EQ(skel->bss->seen_tc2, true, "seen_tc2"); + +cleanup_fd2: + err = bpf_prog_detach_opts(fd2, ifindex, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count_ifindex(ifindex, target, 1); +cleanup_fd1: + err = bpf_prog_detach_opts(fd1, ifindex, target, &optd); + ASSERT_OK(err, "prog_detach"); + assert_mprog_count_ifindex(ifindex, target, 0); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, target, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_multi_opts(void) +{ + serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_multi_opts_target(NETKIT_L2, BPF_NETKIT_PEER); + serial_test_tc_netkit_multi_opts_target(NETKIT_L3, BPF_NETKIT_PEER); +} + +void serial_test_tc_netkit_device(void) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, pid2, lid1; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex, ifindex2; + + err = create_netkit(NETKIT_L3, NETKIT_PASS, NETKIT_PASS, + &ifindex, true); + if (err) + return; + + ifindex2 = if_nametoindex(netkit_peer); + ASSERT_NEQ(ifindex, ifindex2, "ifindex_1_2"); + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc2, + BPF_NETKIT_PEER), 0, "tc2_attach_type"); + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc3, + BPF_NETKIT_PRIMARY), 0, "tc3_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + pid2 = id_from_prog_fd(bpf_program__fd(skel->progs.tc2)); + + ASSERT_NEQ(pid1, pid2, "prog_ids_1_2"); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, BPF_NETKIT_PRIMARY, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(send_icmp(), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_tc2, false, "seen_tc2"); + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PRIMARY, &optq); + ASSERT_EQ(err, -EACCES, "prog_query_should_fail"); + + err = bpf_prog_query_opts(ifindex2, BPF_NETKIT_PEER, &optq); + ASSERT_EQ(err, -EACCES, "prog_query_should_fail"); + + link = bpf_program__attach_netkit(skel->progs.tc2, ifindex2, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + link = bpf_program__attach_netkit(skel->progs.tc3, ifindex2, &optl); + if (!ASSERT_ERR_PTR(link, "link_attach_should_fail")) { + bpf_link__destroy(link); + goto cleanup; + } + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 1); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PRIMARY, 0); + assert_mprog_count_ifindex(ifindex, BPF_NETKIT_PEER, 0); + destroy_netkit(); +} + +static void serial_test_tc_netkit_neigh_links_target(int mode, int target) +{ + LIBBPF_OPTS(bpf_prog_query_opts, optq); + LIBBPF_OPTS(bpf_netkit_opts, optl); + __u32 prog_ids[2], link_ids[2]; + __u32 pid1, lid1; + struct test_tc_link *skel; + struct bpf_link *link; + int err, ifindex; + + err = create_netkit(mode, NETKIT_PASS, NETKIT_PASS, + &ifindex, false); + if (err) + return; + + skel = test_tc_link__open(); + if (!ASSERT_OK_PTR(skel, "skel_open")) + goto cleanup; + + ASSERT_EQ(bpf_program__set_expected_attach_type(skel->progs.tc1, + BPF_NETKIT_PRIMARY), 0, "tc1_attach_type"); + + err = test_tc_link__load(skel); + if (!ASSERT_OK(err, "skel_load")) + goto cleanup; + + pid1 = id_from_prog_fd(bpf_program__fd(skel->progs.tc1)); + + assert_mprog_count_ifindex(ifindex, target, 0); + + ASSERT_EQ(skel->bss->seen_tc1, false, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, false, "seen_eth"); + + link = bpf_program__attach_netkit(skel->progs.tc1, ifindex, &optl); + if (!ASSERT_OK_PTR(link, "link_attach")) + goto cleanup; + + skel->links.tc1 = link; + + lid1 = id_from_link_fd(bpf_link__fd(skel->links.tc1)); + + assert_mprog_count_ifindex(ifindex, target, 1); + + optq.prog_ids = prog_ids; + optq.link_ids = link_ids; + + memset(prog_ids, 0, sizeof(prog_ids)); + memset(link_ids, 0, sizeof(link_ids)); + optq.count = ARRAY_SIZE(prog_ids); + + err = bpf_prog_query_opts(ifindex, target, &optq); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup; + + ASSERT_EQ(optq.count, 1, "count"); + ASSERT_EQ(optq.revision, 2, "revision"); + ASSERT_EQ(optq.prog_ids[0], pid1, "prog_ids[0]"); + ASSERT_EQ(optq.link_ids[0], lid1, "link_ids[0]"); + ASSERT_EQ(optq.prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(optq.link_ids[1], 0, "link_ids[1]"); + + tc_skel_reset_all_seen(skel); + ASSERT_EQ(__send_icmp(ping_addr_noneigh), 0, "icmp_pkt"); + + ASSERT_EQ(skel->bss->seen_tc1, true /* L2: ARP */, "seen_tc1"); + ASSERT_EQ(skel->bss->seen_eth, mode == NETKIT_L3, "seen_eth"); +cleanup: + test_tc_link__destroy(skel); + + assert_mprog_count_ifindex(ifindex, target, 0); + destroy_netkit(); +} + +void serial_test_tc_netkit_neigh_links(void) +{ + serial_test_tc_netkit_neigh_links_target(NETKIT_L2, BPF_NETKIT_PRIMARY); + serial_test_tc_netkit_neigh_links_target(NETKIT_L3, BPF_NETKIT_PRIMARY); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tc_opts.c b/tools/testing/selftests/bpf/prog_tests/tc_opts.c index ca506d2fcf58..51883ccb8020 100644 --- a/tools/testing/selftests/bpf/prog_tests/tc_opts.c +++ b/tools/testing/selftests/bpf/prog_tests/tc_opts.c @@ -2471,7 +2471,7 @@ static void test_tc_opts_query_target(int target) __u32 fd1, fd2, fd3, fd4, id1, id2, id3, id4; struct test_tc_link *skel; union bpf_attr attr; - __u32 prog_ids[5]; + __u32 prog_ids[10]; int err; skel = test_tc_link__open_and_load(); @@ -2599,6 +2599,135 @@ static void test_tc_opts_query_target(int target) ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + /* Test 3: Query with smaller prog_ids array */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.prog_ids = ptr_to_u64(prog_ids); + attr.query.count = 2; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + ASSERT_EQ(err, -1, "prog_query_should_fail"); + ASSERT_EQ(errno, ENOSPC, "prog_query_should_fail"); + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids"); + ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 4: Query with larger prog_ids array */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.prog_ids = ptr_to_u64(prog_ids); + attr.query.count = 10; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids"); + ASSERT_EQ(prog_ids[0], id1, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], id2, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], id3, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], id4, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 5: Query with NULL prog_ids array but with count > 0 */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.count = sizeof(prog_ids); + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_ids, 0, "prog_ids"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 6: Query with non-NULL prog_ids array but with count == 0 */ + memset(&attr, 0, attr_size); + attr.query.target_ifindex = loopback; + attr.query.attach_type = target; + + memset(prog_ids, 0, sizeof(prog_ids)); + attr.query.prog_ids = ptr_to_u64(prog_ids); + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + if (!ASSERT_OK(err, "prog_query")) + goto cleanup4; + + ASSERT_EQ(attr.query.count, 4, "count"); + ASSERT_EQ(attr.query.revision, 5, "revision"); + ASSERT_EQ(attr.query.query_flags, 0, "query_flags"); + ASSERT_EQ(attr.query.attach_flags, 0, "attach_flags"); + ASSERT_EQ(attr.query.target_ifindex, loopback, "target_ifindex"); + ASSERT_EQ(attr.query.attach_type, target, "attach_type"); + ASSERT_EQ(prog_ids[0], 0, "prog_ids[0]"); + ASSERT_EQ(prog_ids[1], 0, "prog_ids[1]"); + ASSERT_EQ(prog_ids[2], 0, "prog_ids[2]"); + ASSERT_EQ(prog_ids[3], 0, "prog_ids[3]"); + ASSERT_EQ(prog_ids[4], 0, "prog_ids[4]"); + ASSERT_EQ(attr.query.prog_ids, ptr_to_u64(prog_ids), "prog_ids"); + ASSERT_EQ(attr.query.prog_attach_flags, 0, "prog_attach_flags"); + ASSERT_EQ(attr.query.link_ids, 0, "link_ids"); + ASSERT_EQ(attr.query.link_attach_flags, 0, "link_attach_flags"); + + /* Test 7: Query with invalid flags */ + attr.query.attach_flags = 0; + attr.query.query_flags = 1; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + ASSERT_EQ(err, -1, "prog_query_should_fail"); + ASSERT_EQ(errno, EINVAL, "prog_query_should_fail"); + + attr.query.attach_flags = 1; + attr.query.query_flags = 0; + + err = syscall(__NR_bpf, BPF_PROG_QUERY, &attr, attr_size); + ASSERT_EQ(err, -1, "prog_query_should_fail"); + ASSERT_EQ(errno, EINVAL, "prog_query_should_fail"); + cleanup4: err = bpf_prog_detach_opts(fd4, loopback, target, &optd); ASSERT_OK(err, "prog_detach"); diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c index 0cca4e8ae38e..d3491a84b3b9 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_ma.c @@ -9,9 +9,10 @@ #include "test_bpf_ma.skel.h" -void test_test_bpf_ma(void) +static void do_bpf_ma_test(const char *name) { struct test_bpf_ma *skel; + struct bpf_program *prog; struct btf *btf; int i, err; @@ -34,6 +35,11 @@ void test_test_bpf_ma(void) skel->rodata->data_btf_ids[i] = id; } + prog = bpf_object__find_program_by_name(skel->obj, name); + if (!ASSERT_OK_PTR(prog, "invalid prog name")) + goto out; + bpf_program__set_autoload(prog, true); + err = test_bpf_ma__load(skel); if (!ASSERT_OK(err, "load")) goto out; @@ -48,3 +54,15 @@ void test_test_bpf_ma(void) out: test_bpf_ma__destroy(skel); } + +void test_test_bpf_ma(void) +{ + if (test__start_subtest("batch_alloc_free")) + do_bpf_ma_test("test_batch_alloc_free"); + if (test__start_subtest("free_through_map_free")) + do_bpf_ma_test("test_free_through_map_free"); + if (test__start_subtest("batch_percpu_alloc_free")) + do_bpf_ma_test("test_batch_percpu_alloc_free"); + if (test__start_subtest("percpu_free_through_map_free")) + do_bpf_ma_test("test_percpu_free_through_map_free"); +} diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c index 96131b9a1caa..96131b9a1caa 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_task.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c index 6b9b3c56f009..c20c4e38b71c 100644 --- a/tools/testing/selftests/bpf/progs/iters.c +++ b/tools/testing/selftests/bpf/progs/iters.c @@ -14,6 +14,13 @@ int my_pid; int arr[256]; int small_arr[16] SEC(".data.small_arr"); +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(max_entries, 10); + __type(key, int); + __type(value, int); +} amap SEC(".maps"); + #ifdef REAL_TEST #define MY_PID_GUARD() if (my_pid != (bpf_get_current_pid_tgid() >> 32)) return 0 #else @@ -716,4 +723,692 @@ int iter_pass_iter_ptr_to_subprog(const void *ctx) return 0; } +SEC("?raw_tp") +__failure +__msg("R1 type=scalar expected=fp") +__naked int delayed_read_mark(void) +{ + /* This is equivalent to C program below. + * The call to bpf_iter_num_next() is reachable with r7 values &fp[-16] and 0xdead. + * State with r7=&fp[-16] is visited first and follows r6 != 42 ... continue branch. + * At this point iterator next() call is reached with r7 that has no read mark. + * Loop body with r7=0xdead would only be visited if verifier would decide to continue + * with second loop iteration. Absence of read mark on r7 might affect state + * equivalent logic used for iterator convergence tracking. + * + * r7 = &fp[-16] + * fp[-16] = 0 + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * r6++ + * if (r6 != 42) { + * r7 = 0xdead + * continue; + * } + * bpf_probe_read_user(r7, 8, 0xdeadbeef); // this is not safe + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r7 = r10;" + "r7 += -16;" + "r0 = 0;" + "*(u64 *)(r7 + 0) = r0;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "r6 += 1;" + "if r6 != 42 goto 3f;" + "r7 = 0xdead;" + "goto 1b;" + "3:" + "r1 = r7;" + "r2 = 8;" + "r3 = 0xdeadbeef;" + "call %[bpf_probe_read_user];" + "goto 1b;" + "2:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_probe_read_user) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__naked int delayed_precision_mark(void) +{ + /* This is equivalent to C program below. + * The test is similar to delayed_iter_mark but verifies that incomplete + * precision don't fool verifier. + * The call to bpf_iter_num_next() is reachable with r7 values -16 and -32. + * State with r7=-16 is visited first and follows r6 != 42 ... continue branch. + * At this point iterator next() call is reached with r7 that has no read + * and precision marks. + * Loop body with r7=-32 would only be visited if verifier would decide to continue + * with second loop iteration. Absence of precision mark on r7 might affect state + * equivalent logic used for iterator convergence tracking. + * + * r8 = 0 + * fp[-16] = 0 + * r7 = -16 + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * if (r6 != 42) { + * r7 = -32 + * r6 = bpf_get_prandom_u32() + * continue; + * } + * r0 = r10 + * r0 += r7 + * r8 = *(u64 *)(r0 + 0) // this is not safe + * r6 = bpf_get_prandom_u32() + * } + * bpf_iter_num_destroy(&fp[-8]) + * return r8 + */ + asm volatile ( + "r8 = 0;" + "*(u64 *)(r10 - 16) = r8;" + "r7 = -16;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "1:" + "r1 = r10;" + "r1 += -8;\n" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto 2f;" + "if r6 != 42 goto 3f;" + "r7 = -32;" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "goto 1b;\n" + "3:" + "r0 = r10;" + "r0 += r7;" + "r8 = *(u64 *)(r0 + 0);" + "call %[bpf_get_prandom_u32];" + "r6 = r0;" + "goto 1b;\n" + "2:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = r8;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm(bpf_probe_read_user) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps1(void) +{ + /* This is equivalent to C program below. + * + * The case turns out to be tricky in a sense that: + * - states with c=-25 are explored only on a second iteration + * of the outer loop; + * - states with read+precise mark on c are explored only on + * second iteration of the inner loop and in a state which + * is pushed to states stack first. + * + * Depending on the details of iterator convergence logic + * verifier might stop states traversal too early and miss + * unsafe c=-25 memory access. + * + * j = iter_new(); // fp[-16] + * a = 0; // r6 + * b = 0; // r7 + * c = -24; // r8 + * while (iter_next(j)) { + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * *(r10 + c) = 7; // this is not safe + * iter_destroy(i); + * iter_destroy(j); + * return; + * } + * } + * } + * iter_destroy(i); + * a = 0; + * b = 0; + * c = -25; + * } + * iter_destroy(j); + * return; + */ + asm volatile ( + "r1 = r10;" + "r1 += -16;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "r8 = -24;" + "j_loop_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto j_loop_end_%=;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i_loop_end_%=;" + "check_one_r6_%=:" + "if r6 != 1 goto check_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i_loop_%=;" + "check_zero_r6_%=:" + "if r6 != 0 goto i_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check_one_r7_%=;" + "goto i_loop_%=;" + "check_one_r7_%=:" + "if r7 != 1 goto i_loop_%=;" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "i_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r6 = 0;" + "r7 = 0;" + "r8 = -25;" + "goto j_loop_%=;" + "j_loop_end_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__failure +__msg("math between fp pointer and register with unbounded") +__flag(BPF_F_TEST_STATE_FREQ) +__naked int loop_state_deps2(void) +{ + /* This is equivalent to C program below. + * + * The case turns out to be tricky in a sense that: + * - states with read+precise mark on c are explored only on a second + * iteration of the first inner loop and in a state which is pushed to + * states stack first. + * - states with c=-25 are explored only on a second iteration of the + * second inner loop and in a state which is pushed to states stack + * first. + * + * Depending on the details of iterator convergence logic + * verifier might stop states traversal too early and miss + * unsafe c=-25 memory access. + * + * j = iter_new(); // fp[-16] + * a = 0; // r6 + * b = 0; // r7 + * c = -24; // r8 + * while (iter_next(j)) { + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * *(r10 + c) = 7; // this is not safe + * iter_destroy(i); + * iter_destroy(j); + * return; + * } + * } + * } + * iter_destroy(i); + * i = iter_new(); // fp[-8] + * a = 0; // r6 + * b = 0; // r7 + * while (iter_next(i)) { + * if (a == 1) { + * a = 0; + * b = 1; + * } else if (a == 0) { + * a = 1; + * if (random() == 42) + * continue; + * if (b == 1) { + * a = 0; + * c = -25; + * } + * } + * } + * iter_destroy(i); + * } + * iter_destroy(j); + * return; + */ + asm volatile ( + "r1 = r10;" + "r1 += -16;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "r8 = -24;" + "j_loop_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto j_loop_end_%=;" + + /* first inner loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i_loop_end_%=;" + "check_one_r6_%=:" + "if r6 != 1 goto check_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i_loop_%=;" + "check_zero_r6_%=:" + "if r6 != 0 goto i_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check_one_r7_%=;" + "goto i_loop_%=;" + "check_one_r7_%=:" + "if r7 != 1 goto i_loop_%=;" + "r0 = r10;" + "r0 += r8;" + "r1 = 7;" + "*(u64 *)(r0 + 0) = r1;" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + "i_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + + /* second inner loop */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "r6 = 0;" + "r7 = 0;" + "i2_loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto i2_loop_end_%=;" + "check2_one_r6_%=:" + "if r6 != 1 goto check2_zero_r6_%=;" + "r6 = 0;" + "r7 = 1;" + "goto i2_loop_%=;" + "check2_zero_r6_%=:" + "if r6 != 0 goto i2_loop_%=;" + "r6 = 1;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto check2_one_r7_%=;" + "goto i2_loop_%=;" + "check2_one_r7_%=:" + "if r7 != 1 goto i2_loop_%=;" + "r6 = 0;" + "r8 = -25;" + "goto i2_loop_%=;" + "i2_loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + + "r6 = 0;" + "r7 = 0;" + "goto j_loop_%=;" + "j_loop_end_%=:" + "r1 = r10;" + "r1 += -16;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__success +__naked int triple_continue(void) +{ + /* This is equivalent to C program below. + * High branching factor of the loop body turned out to be + * problematic for one of the iterator convergence tracking + * algorithms explored. + * + * r6 = bpf_get_prandom_u32() + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * if (bpf_get_prandom_u32() != 42) + * continue; + * if (bpf_get_prandom_u32() != 42) + * continue; + * if (bpf_get_prandom_u32() != 42) + * continue; + * r0 += 0; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "call %[bpf_get_prandom_u32];" + "if r0 != 42 goto loop_%=;" + "r0 += 0;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_get_prandom_u32), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("?raw_tp") +__success +__naked int widen_spill(void) +{ + /* This is equivalent to C program below. + * The counter is stored in fp[-16], if this counter is not widened + * verifier states representing loop iterations would never converge. + * + * fp[-16] = 0 + * bpf_iter_num_new(&fp[-8], 0, 10) + * while (bpf_iter_num_next(&fp[-8])) { + * r0 = fp[-16]; + * r0 += 1; + * fp[-16] = r0; + * } + * bpf_iter_num_destroy(&fp[-8]) + * return 0 + */ + asm volatile ( + "r0 = 0;" + "*(u64 *)(r10 - 16) = r0;" + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + "r0 = *(u64 *)(r10 - 16);" + "r0 += 1;" + "*(u64 *)(r10 - 16) = r0;" + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy) + : __clobber_all + ); +} + +SEC("raw_tp") +__success +__naked int checkpoint_states_deletion(void) +{ + /* This is equivalent to C program below. + * + * int *a, *b, *c, *d, *e, *f; + * int i, sum = 0; + * bpf_for(i, 0, 10) { + * a = bpf_map_lookup_elem(&amap, &i); + * b = bpf_map_lookup_elem(&amap, &i); + * c = bpf_map_lookup_elem(&amap, &i); + * d = bpf_map_lookup_elem(&amap, &i); + * e = bpf_map_lookup_elem(&amap, &i); + * f = bpf_map_lookup_elem(&amap, &i); + * if (a) sum += 1; + * if (b) sum += 1; + * if (c) sum += 1; + * if (d) sum += 1; + * if (e) sum += 1; + * if (f) sum += 1; + * } + * return 0; + * + * The body of the loop spawns multiple simulation paths + * with different combination of NULL/non-NULL information for a/b/c/d/e/f. + * Each combination is unique from states_equal() point of view. + * Explored states checkpoint is created after each iterator next call. + * Iterator convergence logic expects that eventually current state + * would get equal to one of the explored states and thus loop + * exploration would be finished (at-least for a specific path). + * Verifier evicts explored states with high miss to hit ratio + * to to avoid comparing current state with too many explored + * states per instruction. + * This test is designed to "stress test" eviction policy defined using formula: + * + * sl->miss_cnt > sl->hit_cnt * N + N // if true sl->state is evicted + * + * Currently N is set to 64, which allows for 6 variables in this test. + */ + asm volatile ( + "r6 = 0;" /* a */ + "r7 = 0;" /* b */ + "r8 = 0;" /* c */ + "*(u64 *)(r10 - 24) = r6;" /* d */ + "*(u64 *)(r10 - 32) = r6;" /* e */ + "*(u64 *)(r10 - 40) = r6;" /* f */ + "r9 = 0;" /* sum */ + "r1 = r10;" + "r1 += -8;" + "r2 = 0;" + "r3 = 10;" + "call %[bpf_iter_num_new];" + "loop_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_next];" + "if r0 == 0 goto loop_end_%=;" + + "*(u64 *)(r10 - 16) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r6 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r7 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "r8 = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 24) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 32) = r0;" + + "r1 = %[amap] ll;" + "r2 = r10;" + "r2 += -16;" + "call %[bpf_map_lookup_elem];" + "*(u64 *)(r10 - 40) = r0;" + + "if r6 == 0 goto +1;" + "r9 += 1;" + "if r7 == 0 goto +1;" + "r9 += 1;" + "if r8 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 24);" + "if r0 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 32);" + "if r0 == 0 goto +1;" + "r9 += 1;" + "r0 = *(u64 *)(r10 - 40);" + "if r0 == 0 goto +1;" + "r9 += 1;" + + "goto loop_%=;" + "loop_end_%=:" + "r1 = r10;" + "r1 += -8;" + "call %[bpf_iter_num_destroy];" + "r0 = 0;" + "exit;" + : + : __imm(bpf_map_lookup_elem), + __imm(bpf_iter_num_new), + __imm(bpf_iter_num_next), + __imm(bpf_iter_num_destroy), + __imm_addr(amap) + : __clobber_all + ); +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c new file mode 100644 index 000000000000..ec1f6c2f590b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <[email protected]> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +u64 root_cg_id, leaf_cg_id; +u64 first_cg_id, last_cg_id; + +int pre_order_cnt, post_order_cnt, tree_high; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_css_for_each(const void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *root_css, *leaf_css, *pos; + struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp; + + if (cur_task->pid != target_pid) + return 0; + + root_cgrp = bpf_cgroup_from_id(root_cg_id); + + if (!root_cgrp) + return 0; + + leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id); + + if (!leaf_cgrp) { + bpf_cgroup_release(root_cgrp); + return 0; + } + root_css = &root_cgrp->self; + leaf_css = &leaf_cgrp->self; + pre_order_cnt = post_order_cnt = tree_high = 0; + first_cg_id = last_cg_id = 0; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + cur_cgrp = pos->cgroup; + post_order_cnt++; + last_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) { + cur_cgrp = pos->cgroup; + pre_order_cnt++; + if (!first_cg_id) + first_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high++; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high--; + bpf_rcu_read_unlock(); + bpf_cgroup_release(root_cgrp); + bpf_cgroup_release(leaf_cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c new file mode 100644 index 000000000000..5089ce384a1c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css_task.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <[email protected]> */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; + +pid_t target_pid; +int css_task_cnt; +u64 cg_id; + +SEC("lsm/file_mprotect") +int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *css; + struct task_struct *task; + struct cgroup *cgrp; + + if (cur_task->pid != target_pid) + return ret; + + cgrp = bpf_cgroup_from_id(cg_id); + + if (!cgrp) + return -EPERM; + + css = &cgrp->self; + css_task_cnt = 0; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) + if (task->pid == target_pid) + css_task_cnt++; + + bpf_cgroup_release(cgrp); + + return -EPERM; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c new file mode 100644 index 000000000000..c9b4055cd410 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <[email protected]> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +int procs_cnt, threads_cnt, proc_threads_cnt; + +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_task_for_each_sleep(void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct task_struct *pos; + + if (cur_task->pid != target_pid) + return 0; + procs_cnt = threads_cnt = proc_threads_cnt = 0; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) + if (pos->pid == target_pid) + procs_cnt++; + + bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS) + proc_threads_cnt++; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS) + if (pos->tgid == target_pid) + threads_cnt++; + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c new file mode 100644 index 000000000000..c3bf96a67dba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou <[email protected]> */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_without_lock) +{ + struct task_struct *pos; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + + } + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_without_lock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + + } + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_lock_and_unlock) +{ + struct task_struct *pos; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_lock_and_unlock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s") +int BPF_PROG(iter_css_task_for_each) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *css; + struct task_struct *task; + + if (cgrp == NULL) + return 0; + css = &cgrp->self; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) { + + } + bpf_cgroup_release(cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_vma.c b/tools/testing/selftests/bpf/progs/iters_task_vma.c index 44edecfdfaee..e085a51d153e 100644 --- a/tools/testing/selftests/bpf/progs/iters_task_vma.c +++ b/tools/testing/selftests/bpf/progs/iters_task_vma.c @@ -30,6 +30,7 @@ int iter_task_vma_for_each(const void *ctx) bpf_for_each(task_vma, vma, task, 0) { if (seen >= 1000) break; + barrier_var(seen); vm_ranges[seen].vm_start = vma->vm_start; vm_ranges[seen].vm_end = vma->vm_end; diff --git a/tools/testing/selftests/bpf/progs/linked_list_fail.c b/tools/testing/selftests/bpf/progs/linked_list_fail.c index f4c63daba229..6438982b928b 100644 --- a/tools/testing/selftests/bpf/progs/linked_list_fail.c +++ b/tools/testing/selftests/bpf/progs/linked_list_fail.c @@ -591,7 +591,9 @@ int pop_ptr_off(void *(*op)(void *head)) n = op(&p->head); bpf_spin_unlock(&p->lock); - bpf_this_cpu_ptr(n); + if (!n) + return 0; + bpf_spin_lock((void *)n); return 0; } diff --git a/tools/testing/selftests/bpf/progs/test_bpf_ma.c b/tools/testing/selftests/bpf/progs/test_bpf_ma.c index ecde41ae0fc8..b685a4aba6bd 100644 --- a/tools/testing/selftests/bpf/progs/test_bpf_ma.c +++ b/tools/testing/selftests/bpf/progs/test_bpf_ma.c @@ -37,10 +37,20 @@ int pid = 0; __type(key, int); \ __type(value, struct map_value_##_size); \ __uint(max_entries, 128); \ - } array_##_size SEC(".maps"); + } array_##_size SEC(".maps") -static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int batch, - unsigned int idx) +#define DEFINE_ARRAY_WITH_PERCPU_KPTR(_size) \ + struct map_value_percpu_##_size { \ + struct bin_data_##_size __percpu_kptr * data; \ + }; \ + struct { \ + __uint(type, BPF_MAP_TYPE_ARRAY); \ + __type(key, int); \ + __type(value, struct map_value_percpu_##_size); \ + __uint(max_entries, 128); \ + } array_percpu_##_size SEC(".maps") + +static __always_inline void batch_alloc(struct bpf_map *map, unsigned int batch, unsigned int idx) { struct generic_map_value *value; unsigned int i, key; @@ -65,6 +75,14 @@ static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int b return; } } +} + +static __always_inline void batch_free(struct bpf_map *map, unsigned int batch, unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old; + for (i = 0; i < batch; i++) { key = i; value = bpf_map_lookup_elem(map, &key); @@ -81,8 +99,72 @@ static __always_inline void batch_alloc_free(struct bpf_map *map, unsigned int b } } +static __always_inline void batch_percpu_alloc(struct bpf_map *map, unsigned int batch, + unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old, *new; + + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 1; + return; + } + /* per-cpu allocator may not be able to refill in time */ + new = bpf_percpu_obj_new_impl(data_btf_ids[idx], NULL); + if (!new) + continue; + + old = bpf_kptr_xchg(&value->data, new); + if (old) { + bpf_percpu_obj_drop(old); + err = 2; + return; + } + } +} + +static __always_inline void batch_percpu_free(struct bpf_map *map, unsigned int batch, + unsigned int idx) +{ + struct generic_map_value *value; + unsigned int i, key; + void *old; + + for (i = 0; i < batch; i++) { + key = i; + value = bpf_map_lookup_elem(map, &key); + if (!value) { + err = 3; + return; + } + old = bpf_kptr_xchg(&value->data, NULL); + if (!old) + continue; + bpf_percpu_obj_drop(old); + } +} + +#define CALL_BATCH_ALLOC(size, batch, idx) \ + batch_alloc((struct bpf_map *)(&array_##size), batch, idx) + #define CALL_BATCH_ALLOC_FREE(size, batch, idx) \ - batch_alloc_free((struct bpf_map *)(&array_##size), batch, idx) + do { \ + batch_alloc((struct bpf_map *)(&array_##size), batch, idx); \ + batch_free((struct bpf_map *)(&array_##size), batch, idx); \ + } while (0) + +#define CALL_BATCH_PERCPU_ALLOC(size, batch, idx) \ + batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx) + +#define CALL_BATCH_PERCPU_ALLOC_FREE(size, batch, idx) \ + do { \ + batch_percpu_alloc((struct bpf_map *)(&array_percpu_##size), batch, idx); \ + batch_percpu_free((struct bpf_map *)(&array_percpu_##size), batch, idx); \ + } while (0) DEFINE_ARRAY_WITH_KPTR(8); DEFINE_ARRAY_WITH_KPTR(16); @@ -97,8 +179,21 @@ DEFINE_ARRAY_WITH_KPTR(1024); DEFINE_ARRAY_WITH_KPTR(2048); DEFINE_ARRAY_WITH_KPTR(4096); -SEC("fentry/" SYS_PREFIX "sys_nanosleep") -int test_bpf_mem_alloc_free(void *ctx) +/* per-cpu kptr doesn't support bin_data_8 which is a zero-sized array */ +DEFINE_ARRAY_WITH_PERCPU_KPTR(16); +DEFINE_ARRAY_WITH_PERCPU_KPTR(32); +DEFINE_ARRAY_WITH_PERCPU_KPTR(64); +DEFINE_ARRAY_WITH_PERCPU_KPTR(96); +DEFINE_ARRAY_WITH_PERCPU_KPTR(128); +DEFINE_ARRAY_WITH_PERCPU_KPTR(192); +DEFINE_ARRAY_WITH_PERCPU_KPTR(256); +DEFINE_ARRAY_WITH_PERCPU_KPTR(512); +DEFINE_ARRAY_WITH_PERCPU_KPTR(1024); +DEFINE_ARRAY_WITH_PERCPU_KPTR(2048); +DEFINE_ARRAY_WITH_PERCPU_KPTR(4096); + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_batch_alloc_free(void *ctx) { if ((u32)bpf_get_current_pid_tgid() != pid) return 0; @@ -121,3 +216,76 @@ int test_bpf_mem_alloc_free(void *ctx) return 0; } + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_free_through_map_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 8-bytes objects in batch to trigger refilling, + * then free these objects through map free. + */ + CALL_BATCH_ALLOC(8, 128, 0); + CALL_BATCH_ALLOC(16, 128, 1); + CALL_BATCH_ALLOC(32, 128, 2); + CALL_BATCH_ALLOC(64, 128, 3); + CALL_BATCH_ALLOC(96, 128, 4); + CALL_BATCH_ALLOC(128, 128, 5); + CALL_BATCH_ALLOC(192, 128, 6); + CALL_BATCH_ALLOC(256, 128, 7); + CALL_BATCH_ALLOC(512, 64, 8); + CALL_BATCH_ALLOC(1024, 32, 9); + CALL_BATCH_ALLOC(2048, 16, 10); + CALL_BATCH_ALLOC(4096, 8, 11); + + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_batch_percpu_alloc_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, + * then free 128 16-bytes per-cpu objects in batch to trigger freeing. + */ + CALL_BATCH_PERCPU_ALLOC_FREE(16, 128, 1); + CALL_BATCH_PERCPU_ALLOC_FREE(32, 128, 2); + CALL_BATCH_PERCPU_ALLOC_FREE(64, 128, 3); + CALL_BATCH_PERCPU_ALLOC_FREE(96, 128, 4); + CALL_BATCH_PERCPU_ALLOC_FREE(128, 128, 5); + CALL_BATCH_PERCPU_ALLOC_FREE(192, 128, 6); + CALL_BATCH_PERCPU_ALLOC_FREE(256, 128, 7); + CALL_BATCH_PERCPU_ALLOC_FREE(512, 64, 8); + CALL_BATCH_PERCPU_ALLOC_FREE(1024, 32, 9); + CALL_BATCH_PERCPU_ALLOC_FREE(2048, 16, 10); + CALL_BATCH_PERCPU_ALLOC_FREE(4096, 8, 11); + + return 0; +} + +SEC("?fentry/" SYS_PREFIX "sys_nanosleep") +int test_percpu_free_through_map_free(void *ctx) +{ + if ((u32)bpf_get_current_pid_tgid() != pid) + return 0; + + /* Alloc 128 16-bytes per-cpu objects in batch to trigger refilling, + * then free these object through map free. + */ + CALL_BATCH_PERCPU_ALLOC(16, 128, 1); + CALL_BATCH_PERCPU_ALLOC(32, 128, 2); + CALL_BATCH_PERCPU_ALLOC(64, 128, 3); + CALL_BATCH_PERCPU_ALLOC(96, 128, 4); + CALL_BATCH_PERCPU_ALLOC(128, 128, 5); + CALL_BATCH_PERCPU_ALLOC(192, 128, 6); + CALL_BATCH_PERCPU_ALLOC(256, 128, 7); + CALL_BATCH_PERCPU_ALLOC(512, 64, 8); + CALL_BATCH_PERCPU_ALLOC(1024, 32, 9); + CALL_BATCH_PERCPU_ALLOC(2048, 16, 10); + CALL_BATCH_PERCPU_ALLOC(4096, 8, 11); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c index 56cdc0a553f0..7e750309ce27 100644 --- a/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c +++ b/tools/testing/selftests/bpf/progs/test_task_under_cgroup.c @@ -18,7 +18,7 @@ const volatile __u64 cgid; int remote_pid; SEC("tp_btf/task_newtask") -int BPF_PROG(handle__task_newtask, struct task_struct *task, u64 clone_flags) +int BPF_PROG(tp_btf_run, struct task_struct *task, u64 clone_flags) { struct cgroup *cgrp = NULL; struct task_struct *acquired; @@ -48,4 +48,30 @@ out: return 0; } +SEC("lsm.s/bpf") +int BPF_PROG(lsm_run, int cmd, union bpf_attr *attr, unsigned int size) +{ + struct cgroup *cgrp = NULL; + struct task_struct *task; + int ret = 0; + + task = bpf_get_current_task_btf(); + if (local_pid != task->pid) + return 0; + + if (cmd != BPF_LINK_CREATE) + return 0; + + /* 1 is the root cgroup */ + cgrp = bpf_cgroup_from_id(1); + if (!cgrp) + goto out; + if (!bpf_task_under_cgroup(task, cgrp)) + ret = -1; + bpf_cgroup_release(cgrp); + +out: + return ret; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tc_link.c b/tools/testing/selftests/bpf/progs/test_tc_link.c index 30e7124c49a1..992400acb957 100644 --- a/tools/testing/selftests/bpf/progs/test_tc_link.c +++ b/tools/testing/selftests/bpf/progs/test_tc_link.c @@ -1,7 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Isovalent */ #include <stdbool.h> + #include <linux/bpf.h> +#include <linux/if_ether.h> + +#include <bpf/bpf_endian.h> #include <bpf/bpf_helpers.h> char LICENSE[] SEC("license") = "GPL"; @@ -12,10 +16,19 @@ bool seen_tc3; bool seen_tc4; bool seen_tc5; bool seen_tc6; +bool seen_eth; SEC("tc/ingress") int tc1(struct __sk_buff *skb) { + struct ethhdr eth = {}; + + if (skb->protocol != __bpf_constant_htons(ETH_P_IP)) + goto out; + if (bpf_skb_load_bytes(skb, 0, ð, sizeof(eth))) + goto out; + seen_eth = eth.h_proto == bpf_htons(ETH_P_IP); +out: seen_tc1 = true; return TCX_NEXT; } diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index b2dfd7066c6e..f6d1cc9ad892 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -21,7 +21,7 @@ extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, enum xdp_rss_hash_type *rss_type) __ksym; -SEC("xdp") +SEC("xdp.frags") int rx(struct xdp_md *ctx) { void *data, *data_meta, *data_end; diff --git a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c index 07d786329105..e959336c7a73 100644 --- a/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c +++ b/tools/testing/selftests/bpf/progs/xdp_synproxy_kern.c @@ -177,7 +177,7 @@ static __always_inline __u32 tcp_ns_to_ts(__u64 ns) return ns / (NSEC_PER_SEC / TCP_TS_HZ); } -static __always_inline __u32 tcp_time_stamp_raw(void) +static __always_inline __u32 tcp_clock_ms(void) { return tcp_ns_to_ts(tcp_clock_ns()); } @@ -274,7 +274,7 @@ static __always_inline bool tscookie_init(struct tcphdr *tcp_header, if (!loop_ctx.option_timestamp) return false; - cookie = tcp_time_stamp_raw() & ~TSMASK; + cookie = tcp_clock_ms() & ~TSMASK; cookie |= loop_ctx.wscale & TS_OPT_WSCALE_MASK; if (loop_ctx.option_sack) cookie |= TS_OPT_SACK; diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c index 2a6efbd0401e..b6d016461fb0 100644 --- a/tools/testing/selftests/bpf/unpriv_helpers.c +++ b/tools/testing/selftests/bpf/unpriv_helpers.c @@ -4,9 +4,40 @@ #include <stdlib.h> #include <error.h> #include <stdio.h> +#include <string.h> +#include <unistd.h> +#include <fcntl.h> #include "unpriv_helpers.h" +static bool get_mitigations_off(void) +{ + char cmdline[4096], *c; + int fd, ret = false; + + fd = open("/proc/cmdline", O_RDONLY); + if (fd < 0) { + perror("open /proc/cmdline"); + return false; + } + + if (read(fd, cmdline, sizeof(cmdline) - 1) < 0) { + perror("read /proc/cmdline"); + goto out; + } + + cmdline[sizeof(cmdline) - 1] = '\0'; + for (c = strtok(cmdline, " \n"); c; c = strtok(NULL, " \n")) { + if (strncmp(c, "mitigations=off", strlen(c))) + continue; + ret = true; + break; + } +out: + close(fd); + return ret; +} + bool get_unpriv_disabled(void) { bool disabled; @@ -22,5 +53,5 @@ bool get_unpriv_disabled(void) disabled = true; } - return disabled; + return disabled ? true : get_mitigations_off(); } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 17c980138796..17c0f92ff160 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -26,6 +26,7 @@ #include <linux/sockios.h> #include <sys/mman.h> #include <net/if.h> +#include <ctype.h> #include <poll.h> #include <time.h> @@ -47,6 +48,7 @@ struct xsk { }; struct xdp_hw_metadata *bpf_obj; +__u16 bind_flags = XDP_COPY; struct xsk *rx_xsk; const char *ifname; int ifindex; @@ -60,7 +62,7 @@ static int open_xsk(int ifindex, struct xsk *xsk, __u32 queue_id) const struct xsk_socket_config socket_config = { .rx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, .tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, - .bind_flags = XDP_COPY, + .bind_flags = bind_flags, }; const struct xsk_umem_config umem_config = { .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, @@ -263,11 +265,14 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t verify_skb_metadata(server_fd); for (i = 0; i < rxq; i++) { + bool first_seg = true; + bool is_eop = true; + if (fds[i].revents == 0) continue; struct xsk *xsk = &rx_xsk[i]; - +peek: ret = xsk_ring_cons__peek(&xsk->rx, 1, &idx); printf("xsk_ring_cons__peek: %d\n", ret); if (ret != 1) @@ -276,12 +281,19 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t rx_desc = xsk_ring_cons__rx_desc(&xsk->rx, idx); comp_addr = xsk_umem__extract_addr(rx_desc->addr); addr = xsk_umem__add_offset_to_addr(rx_desc->addr); - printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx\n", - xsk, idx, rx_desc->addr, addr, comp_addr); - verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), - clock_id); + is_eop = !(rx_desc->options & XDP_PKT_CONTD); + printf("%p: rx_desc[%u]->addr=%llx addr=%llx comp_addr=%llx%s\n", + xsk, idx, rx_desc->addr, addr, comp_addr, is_eop ? " EoP" : ""); + if (first_seg) { + verify_xdp_metadata(xsk_umem__get_data(xsk->umem_area, addr), + clock_id); + first_seg = false; + } + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); + if (!is_eop) + goto peek; } } @@ -404,6 +416,53 @@ static void timestamping_enable(int fd, int val) error(1, errno, "setsockopt(SO_TIMESTAMPING)"); } +static void print_usage(void) +{ + const char *usage = + "Usage: xdp_hw_metadata [OPTIONS] [IFNAME]\n" + " -m Enable multi-buffer XDP for larger MTU\n" + " -h Display this help and exit\n\n" + "Generate test packets on the other machine with:\n" + " echo -n xdp | nc -u -q1 <dst_ip> 9091\n"; + + printf("%s", usage); +} + +static void read_args(int argc, char *argv[]) +{ + char opt; + + while ((opt = getopt(argc, argv, "mh")) != -1) { + switch (opt) { + case 'm': + bind_flags |= XDP_USE_SG; + break; + case 'h': + print_usage(); + exit(0); + case '?': + if (isprint(optopt)) + fprintf(stderr, "Unknown option: -%c\n", optopt); + fallthrough; + default: + print_usage(); + error(-1, opterr, "Command line options error"); + } + } + + if (optind >= argc) { + fprintf(stderr, "No device name provided\n"); + print_usage(); + exit(-1); + } + + ifname = argv[optind]; + ifindex = if_nametoindex(ifname); + + if (!ifname) + error(-1, errno, "Invalid interface name"); +} + int main(int argc, char *argv[]) { clockid_t clock_id = CLOCK_TAI; @@ -413,13 +472,8 @@ int main(int argc, char *argv[]) struct bpf_program *prog; - if (argc != 2) { - fprintf(stderr, "pass device name\n"); - return -1; - } + read_args(argc, argv); - ifname = argv[1]; - ifindex = if_nametoindex(ifname); rxq = rxq_num(ifname); printf("rxq: %d\n", rxq); diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc new file mode 100644 index 000000000000..bc9514428dba --- /dev/null +++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_non_uniq_symbol.tc @@ -0,0 +1,13 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# description: Test failure of registering kprobe on non unique symbol +# requires: kprobe_events + +SYMBOL='name_show' + +# We skip this test on kernel where SYMBOL is unique or does not exist. +if [ "$(grep -c -E "[[:alnum:]]+ t ${SYMBOL}" /proc/kallsyms)" -le '1' ]; then + exit_unsupported +fi + +! echo "p:test_non_unique ${SYMBOL}" > kprobe_events diff --git a/tools/testing/selftests/kvm/include/ucall_common.h b/tools/testing/selftests/kvm/include/ucall_common.h index 112bc1da732a..ce33d306c2cb 100644 --- a/tools/testing/selftests/kvm/include/ucall_common.h +++ b/tools/testing/selftests/kvm/include/ucall_common.h @@ -1,7 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * tools/testing/selftests/kvm/include/kvm_util.h - * * Copyright (C) 2018, Google LLC. */ #ifndef SELFTEST_KVM_UCALL_COMMON_H diff --git a/tools/testing/selftests/kvm/include/x86_64/processor.h b/tools/testing/selftests/kvm/include/x86_64/processor.h index 4fd042112526..25bc61dac5fb 100644 --- a/tools/testing/selftests/kvm/include/x86_64/processor.h +++ b/tools/testing/selftests/kvm/include/x86_64/processor.h @@ -68,6 +68,12 @@ struct xstate { #define XFEATURE_MASK_OPMASK BIT_ULL(5) #define XFEATURE_MASK_ZMM_Hi256 BIT_ULL(6) #define XFEATURE_MASK_Hi16_ZMM BIT_ULL(7) +#define XFEATURE_MASK_PT BIT_ULL(8) +#define XFEATURE_MASK_PKRU BIT_ULL(9) +#define XFEATURE_MASK_PASID BIT_ULL(10) +#define XFEATURE_MASK_CET_USER BIT_ULL(11) +#define XFEATURE_MASK_CET_KERNEL BIT_ULL(12) +#define XFEATURE_MASK_LBR BIT_ULL(15) #define XFEATURE_MASK_XTILE_CFG BIT_ULL(17) #define XFEATURE_MASK_XTILE_DATA BIT_ULL(18) @@ -147,6 +153,7 @@ struct kvm_x86_cpu_feature { #define X86_FEATURE_CLWB KVM_X86_CPU_FEATURE(0x7, 0, EBX, 24) #define X86_FEATURE_UMIP KVM_X86_CPU_FEATURE(0x7, 0, ECX, 2) #define X86_FEATURE_PKU KVM_X86_CPU_FEATURE(0x7, 0, ECX, 3) +#define X86_FEATURE_OSPKE KVM_X86_CPU_FEATURE(0x7, 0, ECX, 4) #define X86_FEATURE_LA57 KVM_X86_CPU_FEATURE(0x7, 0, ECX, 16) #define X86_FEATURE_RDPID KVM_X86_CPU_FEATURE(0x7, 0, ECX, 22) #define X86_FEATURE_SGX_LC KVM_X86_CPU_FEATURE(0x7, 0, ECX, 30) @@ -553,6 +560,13 @@ static inline void xsetbv(u32 index, u64 value) __asm__ __volatile__("xsetbv" :: "a" (eax), "d" (edx), "c" (index)); } +static inline void wrpkru(u32 pkru) +{ + /* Note, ECX and EDX are architecturally required to be '0'. */ + asm volatile(".byte 0x0f,0x01,0xef\n\t" + : : "a" (pkru), "c"(0), "d"(0)); +} + static inline struct desc_ptr get_gdt(void) { struct desc_ptr gdt; @@ -908,6 +922,15 @@ static inline bool kvm_pmu_has(struct kvm_x86_pmu_feature feature) !kvm_cpu_has(feature.anti_feature); } +static __always_inline uint64_t kvm_cpu_supported_xcr0(void) +{ + if (!kvm_cpu_has_p(X86_PROPERTY_SUPPORTED_XCR0_LO)) + return 0; + + return kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_LO) | + ((uint64_t)kvm_cpu_property(X86_PROPERTY_SUPPORTED_XCR0_HI) << 32); +} + static inline size_t kvm_cpuid2_size(int nr_entries) { return sizeof(struct kvm_cpuid2) + diff --git a/tools/testing/selftests/kvm/lib/guest_sprintf.c b/tools/testing/selftests/kvm/lib/guest_sprintf.c index c4a69d8aeb68..74627514c4d4 100644 --- a/tools/testing/selftests/kvm/lib/guest_sprintf.c +++ b/tools/testing/selftests/kvm/lib/guest_sprintf.c @@ -200,6 +200,13 @@ repeat: ++fmt; } + /* + * Play nice with %llu, %llx, etc. KVM selftests only support + * 64-bit builds, so just treat %ll* the same as %l*. + */ + if (qualifier == 'l' && *fmt == 'l') + ++fmt; + /* default base */ base = 10; diff --git a/tools/testing/selftests/kvm/lib/x86_64/apic.c b/tools/testing/selftests/kvm/lib/x86_64/apic.c index 7168e25c194e..89153a333e83 100644 --- a/tools/testing/selftests/kvm/lib/x86_64/apic.c +++ b/tools/testing/selftests/kvm/lib/x86_64/apic.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/lib/x86_64/processor.c - * * Copyright (C) 2021, Google LLC. */ diff --git a/tools/testing/selftests/kvm/memslot_perf_test.c b/tools/testing/selftests/kvm/memslot_perf_test.c index 20eb2e730800..8698d1ab60d0 100644 --- a/tools/testing/selftests/kvm/memslot_perf_test.c +++ b/tools/testing/selftests/kvm/memslot_perf_test.c @@ -1033,9 +1033,8 @@ static bool test_loop(const struct test_data *data, struct test_result *rbestruntime) { uint64_t maxslots; - struct test_result result; + struct test_result result = {}; - result.nloops = 0; if (!test_execute(targs->nslots, &maxslots, targs->seconds, data, &result.nloops, &result.slot_runtime, &result.guest_runtime)) { @@ -1089,7 +1088,7 @@ int main(int argc, char *argv[]) .seconds = 5, .runs = 1, }; - struct test_result rbestslottime; + struct test_result rbestslottime = {}; int tctr; if (!check_memory_sizes()) @@ -1098,11 +1097,10 @@ int main(int argc, char *argv[]) if (!parse_args(argc, argv, &targs)) return -1; - rbestslottime.slottimens = 0; for (tctr = targs.tfirst; tctr <= targs.tlast; tctr++) { const struct test_data *data = &tests[tctr]; unsigned int runctr; - struct test_result rbestruntime; + struct test_result rbestruntime = {}; if (tctr > targs.tfirst) pr_info("\n"); @@ -1110,7 +1108,6 @@ int main(int argc, char *argv[]) pr_info("Testing %s performance with %i runs, %d seconds each\n", data->name, targs.runs, targs.seconds); - rbestruntime.runtimens = 0; for (runctr = 0; runctr < targs.runs; runctr++) if (!test_loop(data, &targs, &rbestslottime, &rbestruntime)) diff --git a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c index e446d76d1c0c..6c1278562090 100644 --- a/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c +++ b/tools/testing/selftests/kvm/x86_64/hyperv_svm_test.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * KVM_GET/SET_* tests - * * Copyright (C) 2022, Red Hat, Inc. * * Tests for Hyper-V extensions to SVM. diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c index 7f36c32fa760..18ac5c1952a3 100644 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.c @@ -1,7 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * tools/testing/selftests/kvm/nx_huge_page_test.c - * * Usage: to be run via nx_huge_page_test.sh, which does the necessary * environment setup and teardown * diff --git a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh index 0560149e66ed..7cbb409801ee 100755 --- a/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh +++ b/tools/testing/selftests/kvm/x86_64/nx_huge_pages_test.sh @@ -4,7 +4,6 @@ # Wrapper script which performs setup and cleanup for nx_huge_pages_test. # Makes use of root privileges to set up huge pages and KVM module parameters. # -# tools/testing/selftests/kvm/nx_huge_page_test.sh # Copyright (C) 2022, Google LLC. set -e diff --git a/tools/testing/selftests/kvm/x86_64/state_test.c b/tools/testing/selftests/kvm/x86_64/state_test.c index 4c4925a8ab45..88b58aab7207 100644 --- a/tools/testing/selftests/kvm/x86_64/state_test.c +++ b/tools/testing/selftests/kvm/x86_64/state_test.c @@ -139,6 +139,83 @@ static void vmx_l1_guest_code(struct vmx_pages *vmx_pages) static void __attribute__((__flatten__)) guest_code(void *arg) { GUEST_SYNC(1); + + if (this_cpu_has(X86_FEATURE_XSAVE)) { + uint64_t supported_xcr0 = this_cpu_supported_xcr0(); + uint8_t buffer[4096]; + + memset(buffer, 0xcc, sizeof(buffer)); + + set_cr4(get_cr4() | X86_CR4_OSXSAVE); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSXSAVE)); + + xsetbv(0, xgetbv(0) | supported_xcr0); + + /* + * Modify state for all supported xfeatures to take them out of + * their "init" state, i.e. to make them show up in XSTATE_BV. + * + * Note off-by-default features, e.g. AMX, are out of scope for + * this particular testcase as they have a different ABI. + */ + GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_FP); + asm volatile ("fincstp"); + + GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_SSE); + asm volatile ("vmovdqu %0, %%xmm0" :: "m" (buffer)); + + if (supported_xcr0 & XFEATURE_MASK_YMM) + asm volatile ("vmovdqu %0, %%ymm0" :: "m" (buffer)); + + if (supported_xcr0 & XFEATURE_MASK_AVX512) { + asm volatile ("kmovq %0, %%k1" :: "r" (-1ull)); + asm volatile ("vmovupd %0, %%zmm0" :: "m" (buffer)); + asm volatile ("vmovupd %0, %%zmm16" :: "m" (buffer)); + } + + if (this_cpu_has(X86_FEATURE_MPX)) { + uint64_t bounds[2] = { 10, 0xffffffffull }; + uint64_t output[2] = { }; + + GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDREGS); + GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_BNDCSR); + + /* + * Don't bother trying to get BNDCSR into the INUSE + * state. MSR_IA32_BNDCFGS doesn't count as it isn't + * managed via XSAVE/XRSTOR, and BNDCFGU can only be + * modified by XRSTOR. Stuffing XSTATE_BV in the host + * is simpler than doing XRSTOR here in the guest. + * + * However, temporarily enable MPX in BNDCFGS so that + * BNDMOV actually loads BND1. If MPX isn't *fully* + * enabled, all MPX instructions are treated as NOPs. + * + * Hand encode "bndmov (%rax),%bnd1" as support for MPX + * mnemonics/registers has been removed from gcc and + * clang (and was never fully supported by clang). + */ + wrmsr(MSR_IA32_BNDCFGS, BIT_ULL(0)); + asm volatile (".byte 0x66,0x0f,0x1a,0x08" :: "a" (bounds)); + /* + * Hand encode "bndmov %bnd1, (%rax)" to sanity check + * that BND1 actually got loaded. + */ + asm volatile (".byte 0x66,0x0f,0x1b,0x08" :: "a" (output)); + wrmsr(MSR_IA32_BNDCFGS, 0); + + GUEST_ASSERT_EQ(bounds[0], output[0]); + GUEST_ASSERT_EQ(bounds[1], output[1]); + } + if (this_cpu_has(X86_FEATURE_PKU)) { + GUEST_ASSERT(supported_xcr0 & XFEATURE_MASK_PKRU); + set_cr4(get_cr4() | X86_CR4_PKE); + GUEST_ASSERT(this_cpu_has(X86_FEATURE_OSPKE)); + + wrpkru(-1u); + } + } + GUEST_SYNC(2); if (arg) { @@ -153,10 +230,11 @@ static void __attribute__((__flatten__)) guest_code(void *arg) int main(int argc, char *argv[]) { + uint64_t *xstate_bv, saved_xstate_bv; vm_vaddr_t nested_gva = 0; - + struct kvm_cpuid2 empty_cpuid = {}; struct kvm_regs regs1, regs2; - struct kvm_vcpu *vcpu; + struct kvm_vcpu *vcpu, *vcpuN; struct kvm_vm *vm; struct kvm_x86_state *state; struct ucall uc; @@ -209,6 +287,34 @@ int main(int argc, char *argv[]) /* Restore state in a new VM. */ vcpu = vm_recreate_with_one_vcpu(vm); vcpu_load_state(vcpu, state); + + /* + * Restore XSAVE state in a dummy vCPU, first without doing + * KVM_SET_CPUID2, and then with an empty guest CPUID. Except + * for off-by-default xfeatures, e.g. AMX, KVM is supposed to + * allow KVM_SET_XSAVE regardless of guest CPUID. Manually + * load only XSAVE state, MSRs in particular have a much more + * convoluted ABI. + * + * Load two versions of XSAVE state: one with the actual guest + * XSAVE state, and one with all supported features forced "on" + * in xstate_bv, e.g. to ensure that KVM allows loading all + * supported features, even if something goes awry in saving + * the original snapshot. + */ + xstate_bv = (void *)&((uint8_t *)state->xsave->region)[512]; + saved_xstate_bv = *xstate_bv; + + vcpuN = __vm_vcpu_add(vm, vcpu->id + 1); + vcpu_xsave_set(vcpuN, state->xsave); + *xstate_bv = kvm_cpu_supported_xcr0(); + vcpu_xsave_set(vcpuN, state->xsave); + + vcpu_init_cpuid(vcpuN, &empty_cpuid); + vcpu_xsave_set(vcpuN, state->xsave); + *xstate_bv = saved_xstate_bv; + vcpu_xsave_set(vcpuN, state->xsave); + kvm_x86_state_cleanup(state); memset(®s2, 0, sizeof(regs2)); diff --git a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c index 5b669818e39a..59c7304f805e 100644 --- a/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c +++ b/tools/testing/selftests/kvm/x86_64/tsc_scaling_sync.c @@ -1,10 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * svm_vmcall_test - * * Copyright © 2021 Amazon.com, Inc. or its affiliates. - * - * Xen shared_info / pvclock testing */ #include "test_util.h" diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 05898ad9f4d9..9ec9ab60b63e 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -1,10 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only /* - * svm_vmcall_test - * * Copyright © 2021 Amazon.com, Inc. or its affiliates. - * - * Xen shared_info / pvclock testing */ #include "test_util.h" diff --git a/tools/testing/selftests/mm/mremap_dontunmap.c b/tools/testing/selftests/mm/mremap_dontunmap.c index ca2359835e75..a06e73ec8568 100644 --- a/tools/testing/selftests/mm/mremap_dontunmap.c +++ b/tools/testing/selftests/mm/mremap_dontunmap.c @@ -7,6 +7,7 @@ */ #define _GNU_SOURCE #include <sys/mman.h> +#include <linux/mman.h> #include <errno.h> #include <stdio.h> #include <stdlib.h> diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 61939a695f95..b9804ceb9494 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -34,6 +34,7 @@ TEST_PROGS += gro.sh TEST_PROGS += gre_gso.sh TEST_PROGS += cmsg_so_mark.sh TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh +TEST_PROGS += netns-name.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 diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index e7d2a530618a..66d0db7a2614 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -2437,6 +2437,9 @@ ipv4_mpath_list_test() run_cmd "ip -n ns2 route add 203.0.113.0/24 nexthop via 172.16.201.2 nexthop via 172.16.202.2" run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.fib_multipath_hash_policy=1" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.veth2.rp_filter=0" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.all.rp_filter=0" + run_cmd "ip netns exec ns2 sysctl -qw net.ipv4.conf.default.rp_filter=0" set +e local dmac=$(ip -n ns2 -j link show dev veth2 | jq -r '.[]["address"]') @@ -2449,7 +2452,7 @@ ipv4_mpath_list_test() # words, the FIB lookup tracepoint needs to be triggered for every # packet. local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets) - run_cmd "perf stat -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" + run_cmd "perf stat -a -e fib:fib_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets) local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l) list_rcv_eval $tmp_file $diff @@ -2494,7 +2497,7 @@ ipv6_mpath_list_test() # words, the FIB lookup tracepoint needs to be triggered for every # packet. local t0_rx_pkts=$(link_stats_get ns2 veth2 rx packets) - run_cmd "perf stat -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" + run_cmd "perf stat -a -e fib6:fib6_table_lookup --filter 'err == 0' -j -o $tmp_file -- $cmd" local t1_rx_pkts=$(link_stats_get ns2 veth2 rx packets) local diff=$(echo $t1_rx_pkts - $t0_rx_pkts | bc -l) list_rcv_eval $tmp_file $diff diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 61a2a1988ce6..b1fc8afd072d 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -716,7 +716,7 @@ run_test_transparent() # the required infrastructure in MPTCP sockopt code. To support TOS, the # following function has been exported (T). Not great but better than # checking for a specific kernel version. - if ! mptcp_lib_kallsyms_has "T ip_sock_set_tos$"; then + if ! mptcp_lib_kallsyms_has "T __ip_sock_set_tos$"; then echo "INFO: ${msg} not supported by the kernel: SKIP" mptcp_lib_result_skip "${TEST_GROUP}" return diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index ee1f89a872b3..dc895b7b94e1 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1432,7 +1432,9 @@ chk_rst_nr() count=$(get_counter ${ns_tx} "MPTcpExtMPRstTx") if [ -z "$count" ]; then print_skip - elif [ $count -lt $rst_tx ]; then + # accept more rst than expected except if we don't expect any + elif { [ $rst_tx -ne 0 ] && [ $count -lt $rst_tx ]; } || + { [ $rst_tx -eq 0 ] && [ $count -ne 0 ]; }; then fail_test "got $count MP_RST[s] TX expected $rst_tx" else print_ok @@ -1442,7 +1444,9 @@ chk_rst_nr() count=$(get_counter ${ns_rx} "MPTcpExtMPRstRx") if [ -z "$count" ]; then print_skip - elif [ "$count" -lt "$rst_rx" ]; then + # accept more rst than expected except if we don't expect any + elif { [ $rst_rx -ne 0 ] && [ $count -lt $rst_rx ]; } || + { [ $rst_rx -eq 0 ] && [ $count -ne 0 ]; }; then fail_test "got $count MP_RST[s] RX expected $rst_rx" else print_ok @@ -2305,6 +2309,7 @@ remove_tests() chk_join_nr 1 1 1 chk_rm_tx_nr 1 chk_rm_nr 1 1 + chk_rst_nr 0 0 fi # multiple subflows, remove @@ -2317,6 +2322,7 @@ remove_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 2 2 2 chk_rm_nr 2 2 + chk_rst_nr 0 0 fi # single address, remove @@ -2329,6 +2335,7 @@ remove_tests() chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert + chk_rst_nr 0 0 fi # subflow and signal, remove @@ -2342,6 +2349,7 @@ remove_tests() chk_join_nr 2 2 2 chk_add_nr 1 1 chk_rm_nr 1 1 + chk_rst_nr 0 0 fi # subflows and signal, remove @@ -2356,6 +2364,7 @@ remove_tests() chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 2 2 + chk_rst_nr 0 0 fi # addresses remove @@ -2370,6 +2379,7 @@ remove_tests() chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert + chk_rst_nr 0 0 fi # invalid addresses remove @@ -2384,6 +2394,7 @@ remove_tests() chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert + chk_rst_nr 0 0 fi # subflows and signal, flush @@ -2398,6 +2409,7 @@ remove_tests() chk_join_nr 3 3 3 chk_add_nr 1 1 chk_rm_nr 1 3 invert simult + chk_rst_nr 0 0 fi # subflows flush @@ -2417,6 +2429,7 @@ remove_tests() else chk_rm_nr 3 3 fi + chk_rst_nr 0 0 fi # addresses flush @@ -2431,6 +2444,7 @@ remove_tests() chk_join_nr 3 3 3 chk_add_nr 3 3 chk_rm_nr 3 3 invert simult + chk_rst_nr 0 0 fi # invalid addresses flush @@ -2445,6 +2459,7 @@ remove_tests() chk_join_nr 1 1 1 chk_add_nr 3 3 chk_rm_nr 3 1 invert + chk_rst_nr 0 0 fi # remove id 0 subflow @@ -2456,6 +2471,7 @@ remove_tests() run_tests $ns1 $ns2 10.0.1.1 chk_join_nr 1 1 1 chk_rm_nr 1 1 + chk_rst_nr 0 0 fi # remove id 0 address @@ -2468,6 +2484,7 @@ remove_tests() chk_join_nr 1 1 1 chk_add_nr 1 1 chk_rm_nr 1 1 invert + chk_rst_nr 0 0 invert fi } diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh new file mode 100755 index 000000000000..7d3d3fc99461 --- /dev/null +++ b/tools/testing/selftests/net/netns-name.sh @@ -0,0 +1,87 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -o pipefail + +NS=netns-name-test +DEV=dummy-dev0 +DEV2=dummy-dev1 +ALT_NAME=some-alt-name + +RET_CODE=0 + +cleanup() { + ip netns del $NS +} + +trap cleanup EXIT + +fail() { + echo "ERROR: ${1:-unexpected return code} (ret: $_)" >&2 + RET_CODE=1 +} + +ip netns add $NS + +# +# Test basic move without a rename +# +ip -netns $NS link add name $DEV type dummy || fail +ip -netns $NS link set dev $DEV netns 1 || + fail "Can't perform a netns move" +ip link show dev $DEV >> /dev/null || fail "Device not found after move" +ip link del $DEV || fail + +# +# Test move with a conflict +# +ip link add name $DEV type dummy +ip -netns $NS link add name $DEV type dummy || fail +ip -netns $NS link set dev $DEV netns 1 2> /dev/null && + fail "Performed a netns move with a name conflict" +ip link show dev $DEV >> /dev/null || fail "Device not found after move" +ip -netns $NS link del $DEV || fail +ip link del $DEV || fail + +# +# Test move with a conflict and rename +# +ip link add name $DEV type dummy +ip -netns $NS link add name $DEV type dummy || fail +ip -netns $NS link set dev $DEV netns 1 name $DEV2 || + fail "Can't perform a netns move with rename" +ip link del $DEV2 || fail +ip link del $DEV || fail + +# +# Test dup alt-name with netns move +# +ip link add name $DEV type dummy || fail +ip link property add dev $DEV altname $ALT_NAME || fail +ip -netns $NS link add name $DEV2 type dummy || fail +ip -netns $NS link property add dev $DEV2 altname $ALT_NAME || fail + +ip -netns $NS link set dev $DEV2 netns 1 2> /dev/null && + fail "Moved with alt-name dup" + +ip link del $DEV || fail +ip -netns $NS link del $DEV2 || fail + +# +# Test creating alt-name in one net-ns and using in another +# +ip -netns $NS link add name $DEV type dummy || fail +ip -netns $NS link property add dev $DEV altname $ALT_NAME || fail +ip -netns $NS link set dev $DEV netns 1 || fail +ip link show dev $ALT_NAME >> /dev/null || fail "Can't find alt-name after move" +ip -netns $NS link show dev $ALT_NAME 2> /dev/null && + fail "Can still find alt-name after move" +ip link del $DEV || fail + +echo -ne "$(basename $0) \t\t\t\t" +if [ $RET_CODE -eq 0 ]; then + echo "[ OK ]" +else + echo "[ FAIL ]" +fi +exit $RET_CODE diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh index 9c2012d70b08..f8499d4c87f3 100755 --- a/tools/testing/selftests/net/openvswitch/openvswitch.sh +++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh @@ -3,6 +3,8 @@ # # OVS kernel module self tests +trap ovs_exit_sig EXIT TERM INT ERR + # Kselftest framework requirement - SKIP code is 4. ksft_skip=4 @@ -142,6 +144,12 @@ ovs_add_flow () { return 0 } +ovs_del_flows () { + info "Deleting all flows from DP: sbx:$1 br:$2" + ovs_sbx "$1" python3 $ovs_base/ovs-dpctl.py del-flows "$2" + return 0 +} + ovs_drop_record_and_run () { local sbx=$1 shift @@ -198,6 +206,17 @@ test_drop_reason() { ip netns exec server ip addr add 172.31.110.20/24 dev s1 ip netns exec server ip link set s1 up + # Check if drop reasons can be sent + ovs_add_flow "test_drop_reason" dropreason \ + 'in_port(1),eth(),eth_type(0x0806),arp()' 'drop(10)' 2>/dev/null + if [ $? == 1 ]; then + info "no support for drop reasons - skipping" + ovs_exit_sig + return $ksft_skip + fi + + ovs_del_flows "test_drop_reason" dropreason + # Allow ARP ovs_add_flow "test_drop_reason" dropreason \ 'in_port(1),eth(),eth_type(0x0806),arp()' '2' || return 1 @@ -525,7 +544,7 @@ run_test() { fi if python3 ovs-dpctl.py -h 2>&1 | \ - grep "Need to install the python" >/dev/null 2>&1; then + grep -E "Need to (install|upgrade) the python" >/dev/null 2>&1; then stdbuf -o0 printf "TEST: %-60s [PYLIB]\n" "${tdesc}" return $ksft_skip fi diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 912dc8c49085..b97e621face9 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -28,8 +28,10 @@ try: from pyroute2.netlink import nlmsg_atoms from pyroute2.netlink.exceptions import NetlinkError from pyroute2.netlink.generic import GenericNetlinkSocket + import pyroute2 + except ModuleNotFoundError: - print("Need to install the python pyroute2 package.") + print("Need to install the python pyroute2 package >= 0.6.") sys.exit(0) @@ -1117,12 +1119,14 @@ class ovskey(nla): "src", lambda x: str(ipaddress.IPv4Address(x)), int, + convert_ipv4, ), ( "dst", "dst", - lambda x: str(ipaddress.IPv6Address(x)), + lambda x: str(ipaddress.IPv4Address(x)), int, + convert_ipv4, ), ("tp_src", "tp_src", "%d", int), ("tp_dst", "tp_dst", "%d", int), @@ -1904,6 +1908,32 @@ class OvsFlow(GenericNetlinkSocket): raise ne return reply + def del_flows(self, dpifindex): + """ + Send a del message to the kernel that will drop all flows. + + dpifindex should be a valid datapath obtained by calling + into the OvsDatapath lookup + """ + + flowmsg = OvsFlow.ovs_flow_msg() + flowmsg["cmd"] = OVS_FLOW_CMD_DEL + flowmsg["version"] = OVS_DATAPATH_VERSION + flowmsg["reserved"] = 0 + flowmsg["dpifindex"] = dpifindex + + try: + reply = self.nlm_request( + flowmsg, + msg_type=self.prid, + msg_flags=NLM_F_REQUEST | NLM_F_ACK, + ) + reply = reply[0] + except NetlinkError as ne: + print(flowmsg) + raise ne + return reply + def dump(self, dpifindex, flowspec=None): """ Returns a list of messages containing flows. @@ -1998,6 +2028,12 @@ def main(argv): nlmsg_atoms.ovskey = ovskey nlmsg_atoms.ovsactions = ovsactions + # version check for pyroute2 + prverscheck = pyroute2.__version__.split(".") + if int(prverscheck[0]) == 0 and int(prverscheck[1]) < 6: + print("Need to upgrade the python pyroute2 package to >= 0.6.") + sys.exit(0) + parser = argparse.ArgumentParser() parser.add_argument( "-v", @@ -2060,6 +2096,9 @@ def main(argv): addflcmd.add_argument("flow", help="Flow specification") addflcmd.add_argument("acts", help="Flow actions") + delfscmd = subparsers.add_parser("del-flows") + delfscmd.add_argument("flsbr", help="Datapath name") + args = parser.parse_args() if args.verbose > 0: @@ -2143,6 +2182,11 @@ def main(argv): flow = OvsFlow.ovs_flow_msg() flow.parse(args.flow, args.acts, rep["dpifindex"]) ovsflow.add_flow(rep["dpifindex"], flow) + elif hasattr(args, "flsbr"): + rep = ovsdp.info(args.flsbr, 0) + if rep is None: + print("DP '%s' not found." % args.flsbr) + ovsflow.del_flows(rep["dpifindex"]) return 0 diff --git a/tools/testing/selftests/net/route_localnet.sh b/tools/testing/selftests/net/route_localnet.sh index 116bfeab72fa..e08701c750e3 100755 --- a/tools/testing/selftests/net/route_localnet.sh +++ b/tools/testing/selftests/net/route_localnet.sh @@ -18,8 +18,10 @@ setup() { ip route del 127.0.0.0/8 dev lo table local ip netns exec "${PEER_NS}" ip route del 127.0.0.0/8 dev lo table local - ifconfig veth0 127.25.3.4/24 up - ip netns exec "${PEER_NS}" ifconfig veth1 127.25.3.14/24 up + ip address add 127.25.3.4/24 dev veth0 + ip link set dev veth0 up + ip netns exec "${PEER_NS}" ip address add 127.25.3.14/24 dev veth1 + ip netns exec "${PEER_NS}" ip link set dev veth1 up ip route flush cache ip netns exec "${PEER_NS}" ip route flush cache diff --git a/tools/testing/selftests/netfilter/Makefile b/tools/testing/selftests/netfilter/Makefile index ef90aca4cc96..bced422b78f7 100644 --- a/tools/testing/selftests/netfilter/Makefile +++ b/tools/testing/selftests/netfilter/Makefile @@ -7,7 +7,7 @@ TEST_PROGS := nft_trans_stress.sh nft_fib.sh nft_nat.sh bridge_brouter.sh \ nft_queue.sh nft_meta.sh nf_nat_edemux.sh \ ipip-conntrack-mtu.sh conntrack_tcp_unreplied.sh \ conntrack_vrf.sh nft_synproxy.sh rpath.sh nft_audit.sh \ - conntrack_sctp_collision.sh + conntrack_sctp_collision.sh xt_string.sh HOSTPKG_CONFIG := pkg-config diff --git a/tools/testing/selftests/netfilter/nft_audit.sh b/tools/testing/selftests/netfilter/nft_audit.sh index bb34329e02a7..99ed5bd6e840 100755 --- a/tools/testing/selftests/netfilter/nft_audit.sh +++ b/tools/testing/selftests/netfilter/nft_audit.sh @@ -11,6 +11,12 @@ nft --version >/dev/null 2>&1 || { exit $SKIP_RC } +# Run everything in a separate network namespace +[ "${1}" != "run" ] && { unshare -n "${0}" run; exit $?; } + +# give other scripts a chance to finish - audit_logread sees all activity +sleep 1 + logfile=$(mktemp) rulefile=$(mktemp) echo "logging into $logfile" @@ -93,6 +99,12 @@ do_test 'nft add counter t1 c1' \ do_test 'nft add counter t2 c1; add counter t2 c2' \ 'table=t2 family=2 entries=2 op=nft_register_obj' +for ((i = 3; i <= 500; i++)); do + echo "add counter t2 c$i" +done >$rulefile +do_test "nft -f $rulefile" \ +'table=t2 family=2 entries=498 op=nft_register_obj' + # adding/updating quotas do_test 'nft add quota t1 q1 { 10 bytes }' \ @@ -101,6 +113,12 @@ do_test 'nft add quota t1 q1 { 10 bytes }' \ do_test 'nft add quota t2 q1 { 10 bytes }; add quota t2 q2 { 10 bytes }' \ 'table=t2 family=2 entries=2 op=nft_register_obj' +for ((i = 3; i <= 500; i++)); do + echo "add quota t2 q$i { 10 bytes }" +done >$rulefile +do_test "nft -f $rulefile" \ +'table=t2 family=2 entries=498 op=nft_register_obj' + # changing the quota value triggers obj update path do_test 'nft add quota t1 q1 { 20 bytes }' \ 'table=t1 family=2 entries=1 op=nft_register_obj' @@ -150,6 +168,40 @@ done do_test 'nft reset set t1 s' \ 'table=t1 family=2 entries=3 op=nft_reset_setelem' +# resetting counters + +do_test 'nft reset counter t1 c1' \ +'table=t1 family=2 entries=1 op=nft_reset_obj' + +do_test 'nft reset counters t1' \ +'table=t1 family=2 entries=1 op=nft_reset_obj' + +do_test 'nft reset counters t2' \ +'table=t2 family=2 entries=342 op=nft_reset_obj +table=t2 family=2 entries=158 op=nft_reset_obj' + +do_test 'nft reset counters' \ +'table=t1 family=2 entries=1 op=nft_reset_obj +table=t2 family=2 entries=341 op=nft_reset_obj +table=t2 family=2 entries=159 op=nft_reset_obj' + +# resetting quotas + +do_test 'nft reset quota t1 q1' \ +'table=t1 family=2 entries=1 op=nft_reset_obj' + +do_test 'nft reset quotas t1' \ +'table=t1 family=2 entries=1 op=nft_reset_obj' + +do_test 'nft reset quotas t2' \ +'table=t2 family=2 entries=315 op=nft_reset_obj +table=t2 family=2 entries=185 op=nft_reset_obj' + +do_test 'nft reset quotas' \ +'table=t1 family=2 entries=1 op=nft_reset_obj +table=t2 family=2 entries=314 op=nft_reset_obj +table=t2 family=2 entries=186 op=nft_reset_obj' + # deleting rules readarray -t handles < <(nft -a list chain t1 c1 | \ diff --git a/tools/testing/selftests/netfilter/xt_string.sh b/tools/testing/selftests/netfilter/xt_string.sh new file mode 100755 index 000000000000..1802653a4728 --- /dev/null +++ b/tools/testing/selftests/netfilter/xt_string.sh @@ -0,0 +1,128 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# return code to signal skipped test +ksft_skip=4 +rc=0 + +if ! iptables --version >/dev/null 2>&1; then + echo "SKIP: Test needs iptables" + exit $ksft_skip +fi +if ! ip -V >/dev/null 2>&1; then + echo "SKIP: Test needs iproute2" + exit $ksft_skip +fi +if ! nc -h >/dev/null 2>&1; then + echo "SKIP: Test needs netcat" + exit $ksft_skip +fi + +pattern="foo bar baz" +patlen=11 +hdrlen=$((20 + 8)) # IPv4 + UDP +ns="ns-$(mktemp -u XXXXXXXX)" +trap 'ip netns del $ns' EXIT +ip netns add "$ns" +ip -net "$ns" link add d0 type dummy +ip -net "$ns" link set d0 up +ip -net "$ns" addr add 10.1.2.1/24 dev d0 + +#ip netns exec "$ns" tcpdump -npXi d0 & +#tcpdump_pid=$! +#trap 'kill $tcpdump_pid; ip netns del $ns' EXIT + +add_rule() { # (alg, from, to) + ip netns exec "$ns" \ + iptables -A OUTPUT -o d0 -m string \ + --string "$pattern" --algo $1 --from $2 --to $3 +} +showrules() { # () + ip netns exec "$ns" iptables -v -S OUTPUT | grep '^-A' +} +zerorules() { + ip netns exec "$ns" iptables -Z OUTPUT +} +countrule() { # (pattern) + showrules | grep -c -- "$*" +} +send() { # (offset) + ( for ((i = 0; i < $1 - $hdrlen; i++)); do + printf " " + done + printf "$pattern" + ) | ip netns exec "$ns" nc -w 1 -u 10.1.2.2 27374 +} + +add_rule bm 1000 1500 +add_rule bm 1400 1600 +add_rule kmp 1000 1500 +add_rule kmp 1400 1600 + +zerorules +send 0 +send $((1000 - $patlen)) +if [ $(countrule -c 0 0) -ne 4 ]; then + echo "FAIL: rules match data before --from" + showrules + ((rc--)) +fi + +zerorules +send 1000 +send $((1400 - $patlen)) +if [ $(countrule -c 2) -ne 2 ]; then + echo "FAIL: only two rules should match at low offset" + showrules + ((rc--)) +fi + +zerorules +send $((1500 - $patlen)) +if [ $(countrule -c 1) -ne 4 ]; then + echo "FAIL: all rules should match at end of packet" + showrules + ((rc--)) +fi + +zerorules +send 1495 +if [ $(countrule -c 1) -ne 1 ]; then + echo "FAIL: only kmp with proper --to should match pattern spanning fragments" + showrules + ((rc--)) +fi + +zerorules +send 1500 +if [ $(countrule -c 1) -ne 2 ]; then + echo "FAIL: two rules should match pattern at start of second fragment" + showrules + ((rc--)) +fi + +zerorules +send $((1600 - $patlen)) +if [ $(countrule -c 1) -ne 2 ]; then + echo "FAIL: two rules should match pattern at end of largest --to" + showrules + ((rc--)) +fi + +zerorules +send $((1600 - $patlen + 1)) +if [ $(countrule -c 1) -ne 0 ]; then + echo "FAIL: no rules should match pattern extending largest --to" + showrules + ((rc--)) +fi + +zerorules +send 1600 +if [ $(countrule -c 1) -ne 0 ]; then + echo "FAIL: no rule should match pattern past largest --to" + showrules + ((rc--)) +fi + +exit $rc diff --git a/tools/testing/selftests/riscv/mm/Makefile b/tools/testing/selftests/riscv/mm/Makefile index 11e0f0568923..c333263f2b27 100644 --- a/tools/testing/selftests/riscv/mm/Makefile +++ b/tools/testing/selftests/riscv/mm/Makefile @@ -5,11 +5,11 @@ # Additional include paths needed by kselftest.h and local headers CFLAGS += -D_GNU_SOURCE -std=gnu99 -I. -TEST_GEN_FILES := testcases/mmap_default testcases/mmap_bottomup +TEST_GEN_FILES := mmap_default mmap_bottomup -TEST_PROGS := testcases/run_mmap.sh +TEST_PROGS := run_mmap.sh include ../../lib.mk -$(OUTPUT)/mm: testcases/mmap_default.c testcases/mmap_bottomup.c testcases/mmap_tests.h +$(OUTPUT)/mm: mmap_default.c mmap_bottomup.c mmap_tests.h $(CC) -o$@ $(CFLAGS) $(LDFLAGS) $^ diff --git a/tools/testing/selftests/riscv/mm/testcases/mmap_bottomup.c b/tools/testing/selftests/riscv/mm/mmap_bottomup.c index b29379f7e478..1757d19ca89b 100644 --- a/tools/testing/selftests/riscv/mm/testcases/mmap_bottomup.c +++ b/tools/testing/selftests/riscv/mm/mmap_bottomup.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <sys/mman.h> -#include <testcases/mmap_test.h> +#include <mmap_test.h> #include "../../kselftest_harness.h" diff --git a/tools/testing/selftests/riscv/mm/testcases/mmap_default.c b/tools/testing/selftests/riscv/mm/mmap_default.c index d1accb91b726..c63c60b9397e 100644 --- a/tools/testing/selftests/riscv/mm/testcases/mmap_default.c +++ b/tools/testing/selftests/riscv/mm/mmap_default.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only #include <sys/mman.h> -#include <testcases/mmap_test.h> +#include <mmap_test.h> #include "../../kselftest_harness.h" diff --git a/tools/testing/selftests/riscv/mm/testcases/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h index 9b8434f62f57..9b8434f62f57 100644 --- a/tools/testing/selftests/riscv/mm/testcases/mmap_test.h +++ b/tools/testing/selftests/riscv/mm/mmap_test.h diff --git a/tools/testing/selftests/riscv/mm/testcases/run_mmap.sh b/tools/testing/selftests/riscv/mm/run_mmap.sh index ca5ad7c48bad..ca5ad7c48bad 100755 --- a/tools/testing/selftests/riscv/mm/testcases/run_mmap.sh +++ b/tools/testing/selftests/riscv/mm/run_mmap.sh diff --git a/tools/testing/selftests/tc-testing/Makefile b/tools/testing/selftests/tc-testing/Makefile index 3c4b7fa05075..b1fa2e177e2f 100644 --- a/tools/testing/selftests/tc-testing/Makefile +++ b/tools/testing/selftests/tc-testing/Makefile @@ -28,4 +28,4 @@ $(OUTPUT)/%.o: %.c $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ TEST_PROGS += ./tdc.sh -TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests +TEST_FILES := tdc*.py Tdc*.py plugins plugin-lib tc-tests scripts diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 5aa8705751f0..012aa33b341b 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -1,12 +1,21 @@ # +# Network +# + +CONFIG_DUMMY=y +CONFIG_VETH=y + +# # Core Netfilter Configuration # +CONFIG_NETFILTER_ADVANCED=y CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y CONFIG_NF_CONNTRACK_PROCFS=y CONFIG_NF_FLOW_TABLE=m +CONFIG_NF_TABLES=m CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m diff --git a/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh b/tools/testing/selftests/tc-testing/scripts/taprio_wait_for_admin.sh index f5335e8ad6b4..f5335e8ad6b4 100755 --- a/tools/testing/selftests/tc-testing/taprio_wait_for_admin.sh +++ b/tools/testing/selftests/tc-testing/scripts/taprio_wait_for_admin.sh diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json index 0ddb8e1b4369..c98c339424d4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/hfsc.json @@ -9,8 +9,7 @@ "plugins": { "requires": "nsPlugin" }, - "setup": [ - ], + "setup": [], "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hfsc", "expExitCode": "0", "verifyCmd": "$TC qdisc show dev $DUMMY", @@ -126,8 +125,7 @@ "verifyCmd": "$TC qdisc show dev $DUMMY", "matchPattern": "qdisc hfsc 1: root refcnt [0-9]+", "matchCount": "0", - "teardown": [ - ] + "teardown": [] }, { "id": "8436", @@ -139,8 +137,7 @@ "plugins": { "requires": "nsPlugin" }, - "setup": [ - ], + "setup": [], "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root hfsc", "expExitCode": "0", "verifyCmd": "$TC class show dev $DUMMY", @@ -149,5 +146,28 @@ "teardown": [ "$TC qdisc del dev $DUMMY handle 1: root" ] + }, + { + "id": "bef4", + "name": "HFSC rt inner class upgrade to sc", + "category": [ + "qdisc", + "hfsc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$TC qdisc add dev $DUMMY handle 1: root hfsc default 1", + "$TC class add dev $DUMMY parent 1: classid 1:1 hfsc rt rate 8" + ], + "cmdUnderTest": "$TC class add dev $DUMMY parent 1:1 classid 1:2 hfsc rt rate 8", + "expExitCode": "0", + "verifyCmd": "$TC class show dev $DUMMY", + "matchPattern": "class hfsc 1:1 parent 1: sc m1 0bit d 0us m2 8bit.*rt m1 0bit d 0us m2 8bit", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY handle 1: root" + ] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json index 0599635c4bc6..2d603ef2e375 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/taprio.json @@ -170,11 +170,11 @@ "setup": [ "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 clockid CLOCK_TAI", - "./taprio_wait_for_admin.sh $TC $ETH" + "./scripts/taprio_wait_for_admin.sh $TC $ETH" ], "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 clockid CLOCK_TAI", "expExitCode": "2", - "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"", + "verifyCmd": "bash -c \"./scripts/taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"", "matchPattern": "0", "matchCount": "1", "teardown": [ @@ -195,11 +195,11 @@ "setup": [ "echo \"1 1 8\" > /sys/bus/netdevsim/new_device", "$TC qdisc replace dev $ETH handle 8001: parent root stab overhead 24 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 0 sched-entry S ff 20000000 flags 0x2", - "./taprio_wait_for_admin.sh $TC $ETH" + "./scripts/taprio_wait_for_admin.sh $TC $ETH" ], "cmdUnderTest": "$TC qdisc replace dev $ETH parent 8001:7 taprio num_tc 8 map 0 1 2 3 4 5 6 7 queues 1@0 1@1 1@2 1@3 1@4 1@5 1@6 1@7 base-time 200 sched-entry S ff 20000000 flags 0x2", "expExitCode": "2", - "verifyCmd": "bash -c \"./taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"", + "verifyCmd": "bash -c \"./scripts/taprio_wait_for_admin.sh $TC $ETH && $TC -j qdisc show dev $ETH root | jq '.[].options.base_time'\"", "matchPattern": "0", "matchCount": "1", "teardown": [ diff --git a/tools/testing/selftests/user_events/abi_test.c b/tools/testing/selftests/user_events/abi_test.c index 8202f1327c39..f5575ef2007c 100644 --- a/tools/testing/selftests/user_events/abi_test.c +++ b/tools/testing/selftests/user_events/abi_test.c @@ -47,7 +47,7 @@ static int change_event(bool enable) return ret; } -static int reg_enable(long *enable, int size, int bit) +static int reg_enable(void *enable, int size, int bit) { struct user_reg reg = {0}; int fd = open(data_file, O_RDWR); @@ -69,7 +69,7 @@ static int reg_enable(long *enable, int size, int bit) return ret; } -static int reg_disable(long *enable, int bit) +static int reg_disable(void *enable, int bit) { struct user_unreg reg = {0}; int fd = open(data_file, O_RDWR); @@ -90,7 +90,8 @@ static int reg_disable(long *enable, int bit) } FIXTURE(user) { - long check; + int check; + long check_long; bool umount; }; @@ -99,6 +100,7 @@ FIXTURE_SETUP(user) { change_event(false); self->check = 0; + self->check_long = 0; } FIXTURE_TEARDOWN(user) { @@ -136,9 +138,9 @@ TEST_F(user, bit_sizes) { #if BITS_PER_LONG == 8 /* Allow 0-64 bits for 64-bit */ - ASSERT_EQ(0, reg_enable(&self->check, sizeof(long), 63)); - ASSERT_NE(0, reg_enable(&self->check, sizeof(long), 64)); - ASSERT_EQ(0, reg_disable(&self->check, 63)); + ASSERT_EQ(0, reg_enable(&self->check_long, sizeof(long), 63)); + ASSERT_NE(0, reg_enable(&self->check_long, sizeof(long), 64)); + ASSERT_EQ(0, reg_disable(&self->check_long, 63)); #endif /* Disallowed sizes (everything beside 4 and 8) */ @@ -200,7 +202,7 @@ static int clone_check(void *check) for (i = 0; i < 10; ++i) { usleep(100000); - if (*(long *)check) + if (*(int *)check) return 0; } diff --git a/tools/virtio/linux/dma-mapping.h b/tools/virtio/linux/dma-mapping.h index 834a90bd3270..822ecaa8e4df 100644 --- a/tools/virtio/linux/dma-mapping.h +++ b/tools/virtio/linux/dma-mapping.h @@ -24,11 +24,23 @@ enum dma_data_direction { #define dma_map_page(d, p, o, s, dir) (page_to_phys(p) + (o)) #define dma_map_single(d, p, s, dir) (virt_to_phys(p)) +#define dma_map_single_attrs(d, p, s, dir, a) (virt_to_phys(p)) #define dma_mapping_error(...) (0) #define dma_unmap_single(d, a, s, r) do { (void)(d); (void)(a); (void)(s); (void)(r); } while (0) #define dma_unmap_page(d, a, s, r) do { (void)(d); (void)(a); (void)(s); (void)(r); } while (0) +#define sg_dma_address(sg) (0) +#define dma_need_sync(v, a) (0) +#define dma_unmap_single_attrs(d, a, s, r, t) do { \ + (void)(d); (void)(a); (void)(s); (void)(r); (void)(t); \ +} while (0) +#define dma_sync_single_range_for_cpu(d, a, o, s, r) do { \ + (void)(d); (void)(a); (void)(o); (void)(s); (void)(r); \ +} while (0) +#define dma_sync_single_range_for_device(d, a, o, s, r) do { \ + (void)(d); (void)(a); (void)(o); (void)(s); (void)(r); \ +} while (0) #define dma_max_mapping_size(...) SIZE_MAX #endif |