diff options
Diffstat (limited to 'Documentation')
45 files changed, 4659 insertions, 175 deletions
diff --git a/Documentation/ABI/testing/sysfs-bus-optee-devices b/Documentation/ABI/testing/sysfs-bus-optee-devices index 0f58701367b6..af31e5a22d89 100644 --- a/Documentation/ABI/testing/sysfs-bus-optee-devices +++ b/Documentation/ABI/testing/sysfs-bus-optee-devices @@ -6,3 +6,12 @@ Description: OP-TEE bus provides reference to registered drivers under this directory. The <uuid> matches Trusted Application (TA) driver and corresponding TA in secure OS. Drivers are free to create needed API under optee-ta-<uuid> directory. + +What: /sys/bus/tee/devices/optee-ta-<uuid>/need_supplicant +Date: November 2023 +KernelVersion: 6.7 +Contact: op-tee@lists.trustedfirmware.org +Description: + Allows to distinguish whether an OP-TEE based TA/device requires user-space + tee-supplicant to function properly or not. This attribute will be present for + devices which depend on tee-supplicant to be running. diff --git a/Documentation/Makefile b/Documentation/Makefile index 5c156fbb6cdf..3885bbe260eb 100644 --- a/Documentation/Makefile +++ b/Documentation/Makefile @@ -106,10 +106,10 @@ YNL_RST_FILES_TMP := $(patsubst %.yaml,%.rst,$(wildcard $(YNL_YAML_DIR)/*.yaml)) YNL_RST_FILES := $(patsubst $(YNL_YAML_DIR)%,$(YNL_RST_DIR)%, $(YNL_RST_FILES_TMP)) $(YNL_INDEX): $(YNL_RST_FILES) - @$(YNL_TOOL) -o $@ -x + $(Q)$(YNL_TOOL) -o $@ -x -$(YNL_RST_DIR)/%.rst: $(YNL_YAML_DIR)/%.yaml - @$(YNL_TOOL) -i $< -o $@ +$(YNL_RST_DIR)/%.rst: $(YNL_YAML_DIR)/%.yaml $(YNL_TOOL) + $(Q)$(YNL_TOOL) -i $< -o $@ htmldocs: $(YNL_INDEX) @$(srctree)/scripts/sphinx-pre-install --version-check diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index c7525942f12c..396091651955 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -345,7 +345,10 @@ optmem_max ---------- Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence -of struct cmsghdr structures with appended data. +of struct cmsghdr structures with appended data. TCP tx zerocopy also uses +optmem_max as a limit for its internal structures. + +Default : 128 KB fb_tunnels_only_for_init_net ---------------------------- diff --git a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml index 987aa83c2649..df20a3c9c744 100644 --- a/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml +++ b/Documentation/devicetree/bindings/display/bridge/adi,adv7533.yaml @@ -9,6 +9,9 @@ title: Analog Devices ADV7533/35 HDMI Encoders maintainers: - Laurent Pinchart <laurent.pinchart@ideasonboard.com> +allOf: + - $ref: /schemas/sound/dai-common.yaml# + description: | The ADV7533 and ADV7535 are HDMI audio and video transmitters compatible with HDMI 1.4 and DVI 1.0. They support color space @@ -89,6 +92,9 @@ properties: $ref: /schemas/types.yaml#/definitions/uint32 enum: [ 1, 2, 3, 4 ] + "#sound-dai-cells": + const: 0 + ports: description: The ADV7533/35 has two video ports and one audio port. diff --git a/Documentation/devicetree/bindings/display/fsl,lcdif.yaml b/Documentation/devicetree/bindings/display/fsl,lcdif.yaml index fc11ab5fc465..1c2be8d6f633 100644 --- a/Documentation/devicetree/bindings/display/fsl,lcdif.yaml +++ b/Documentation/devicetree/bindings/display/fsl,lcdif.yaml @@ -51,7 +51,10 @@ properties: minItems: 1 interrupts: - maxItems: 1 + items: + - description: LCDIF DMA interrupt + - description: LCDIF Error interrupt + minItems: 1 power-domains: maxItems: 1 @@ -131,6 +134,21 @@ allOf: then: required: - power-domains + - if: + properties: + compatible: + contains: + enum: + - fsl,imx23-lcdif + then: + properties: + interrupts: + minItems: 2 + maxItems: 2 + else: + properties: + interrupts: + maxItems: 1 examples: - | diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml index 537e5304b730..ed24b617090b 100644 --- a/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml +++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,dsi.yaml @@ -10,7 +10,6 @@ maintainers: - Chun-Kuang Hu <chunkuang.hu@kernel.org> - Philipp Zabel <p.zabel@pengutronix.de> - Jitao Shi <jitao.shi@mediatek.com> - - Xinlei Lee <xinlei.lee@mediatek.com> description: | The MediaTek DSI function block is a sink of the display subsystem and can diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml index 509d20c091af..6a206111d4e0 100644 --- a/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml +++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,mpm.yaml @@ -62,6 +62,9 @@ properties: - description: MPM pin number - description: GIC SPI number for the MPM pin + '#power-domain-cells': + const: 0 + required: - compatible - reg @@ -93,4 +96,5 @@ examples: <86 183>, <90 260>, <91 260>; + #power-domain-cells = <0>; }; diff --git a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml index b3029c64d0d5..c963dc09e8e1 100644 --- a/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml +++ b/Documentation/devicetree/bindings/net/dsa/microchip,ksz.yaml @@ -11,7 +11,6 @@ maintainers: - Woojung Huh <Woojung.Huh@microchip.com> allOf: - - $ref: dsa.yaml#/$defs/ethernet-ports - $ref: /schemas/spi/spi-peripheral-props.yaml# properties: @@ -78,6 +77,39 @@ required: - compatible - reg +if: + not: + properties: + compatible: + enum: + - microchip,ksz8863 + - microchip,ksz8873 +then: + $ref: dsa.yaml#/$defs/ethernet-ports +else: + patternProperties: + "^(ethernet-)?ports$": + patternProperties: + "^(ethernet-)?port@[0-2]$": + $ref: dsa-port.yaml# + unevaluatedProperties: false + properties: + microchip,rmii-clk-internal: + $ref: /schemas/types.yaml#/definitions/flag + description: + When ksz88x3 is acting as clock provier (via REFCLKO) it + can select between internal and external RMII reference + clock. Internal reference clock means that the clock for + the RMII of ksz88x3 is provided by the ksz88x3 internally + and the REFCLKI pin is unconnected. For the external + reference clock, the clock needs to be fed back to ksz88x3 + via REFCLKI. + If microchip,rmii-clk-internal is set, ksz88x3 will provide + rmii reference clock internally, otherwise reference clock + should be provided externally. + dependencies: + microchip,rmii-clk-internal: [ethernet] + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/net/lantiq,pef2256.yaml b/Documentation/devicetree/bindings/net/lantiq,pef2256.yaml new file mode 100644 index 000000000000..7da8370e2468 --- /dev/null +++ b/Documentation/devicetree/bindings/net/lantiq,pef2256.yaml @@ -0,0 +1,213 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/lantiq,pef2256.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Lantiq PEF2256 + +maintainers: + - Herve Codina <herve.codina@bootlin.com> + +description: + The Lantiq PEF2256, also known as Infineon PEF2256 or FALC56, is a framer and + line interface component designed to fulfill all required interfacing between + an analog E1/T1/J1 line and the digital PCM system highway/H.100 bus. + +properties: + compatible: + items: + - const: lantiq,pef2256 + + reg: + maxItems: 1 + + clocks: + items: + - description: Master Clock + - description: System Clock Receive + - description: System Clock Transmit + + clock-names: + items: + - const: mclk + - const: sclkr + - const: sclkx + + interrupts: + maxItems: 1 + + reset-gpios: + description: + GPIO used to reset the device. + maxItems: 1 + + pinctrl: + $ref: /schemas/pinctrl/pinctrl.yaml# + additionalProperties: false + + patternProperties: + '-pins$': + type: object + $ref: /schemas/pinctrl/pinmux-node.yaml# + additionalProperties: false + + properties: + pins: + enum: [ RPA, RPB, RPC, RPD, XPA, XPB, XPC, XPD ] + + function: + enum: [ SYPR, RFM, RFMB, RSIGM, RSIG, DLR, FREEZE, RFSP, LOS, + SYPX, XFMS, XSIG, TCLK, XMFB, XSIGM, DLX, XCLK, XLT, + GPI, GPOH, GPOL ] + + required: + - pins + - function + + lantiq,data-rate-bps: + enum: [2048000, 4096000, 8192000, 16384000] + default: 2048000 + description: + Data rate (bit per seconds) on the system highway. + + lantiq,clock-falling-edge: + $ref: /schemas/types.yaml#/definitions/flag + description: + Data is sent on falling edge of the clock (and received on the rising + edge). If 'clock-falling-edge' is not present, data is sent on the + rising edge (and received on the falling edge). + + lantiq,channel-phase: + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1, 2, 3, 4, 5, 6, 7] + default: 0 + description: | + The pef2256 delivers a full frame (32 8-bit time-slots in E1 and 24 8-bit + time-slots 8 8-bit signaling in E1/J1) every 125us. This lead to a data + rate of 2048000 bit/s. When lantiq,data-rate-bps is more than 2048000 + bit/s, the data (all 32 8-bit) present in the frame are interleave with + unused time-slots. The lantiq,channel-phase property allows to set the + correct alignment of the interleave mechanism. + For instance, suppose lantiq,data-rate-bps = 8192000 (ie 4*2048000), and + lantiq,channel-phase = 2, the interleave schema with unused time-slots + (nu) and used time-slots (XX) for TSi is + nu nu XX nu nu nu XX nu nu nu XX nu + <-- TSi --> <- TSi+1 -> <- TSi+2 -> + With lantiq,data-rate-bps = 8192000, and lantiq,channel-phase = 1, the + interleave schema is + nu XX nu nu nu XX nu nu nu XX nu nu + <-- TSi --> <- TSi+1 -> <- TSi+2 -> + With lantiq,data-rate-bps = 4096000 (ie 2*2048000), and + lantiq,channel-phase = 1, the interleave schema is + nu XX nu XX nu XX + <-- TSi --> <- TSi+1 -> <- TSi+2 -> + +patternProperties: + '^codec(-([0-9]|[1-2][0-9]|3[0-1]))?$': + type: object + $ref: /schemas/sound/dai-common.yaml + unevaluatedProperties: false + description: + Codec provided by the pef2256. This codec allows to use some of the PCM + system highway time-slots as audio channels to transport audio data over + the E1/T1/J1 lines. + The time-slots used by the codec must be set and so, the properties + 'dai-tdm-slot-num', 'dai-tdm-slot-width', 'dai-tdm-slot-tx-mask' and + 'dai-tdm-slot-rx-mask' must be present in the sound card node for + sub-nodes that involve the codec. The codec uses 8-bit time-slots. + 'dai-tdm-tdm-slot-with' must be set to 8. + The tx and rx masks define the pef2256 time-slots assigned to the codec. + + properties: + compatible: + const: lantiq,pef2256-codec + + '#sound-dai-cells': + const: 0 + + required: + - compatible + - '#sound-dai-cells' + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/interrupt-controller/irq.h> + + pef2256: framer@2000000 { + compatible = "lantiq,pef2256"; + reg = <0x2000000 0x100>; + interrupts = <8 IRQ_TYPE_LEVEL_LOW>; + interrupt-parent = <&intc>; + clocks = <&clk_mclk>, <&clk_sclkr>, <&clk_sclkx>; + clock-names = "mclk", "sclkr", "sclkx"; + reset-gpios = <&gpio 11 GPIO_ACTIVE_LOW>; + lantiq,data-rate-bps = <4096000>; + + pinctrl { + pef2256_rpa_sypr: rpa-pins { + pins = "RPA"; + function = "SYPR"; + }; + pef2256_xpa_sypx: xpa-pins { + pins = "XPA"; + function = "SYPX"; + }; + }; + + pef2256_codec0: codec-0 { + compatible = "lantiq,pef2256-codec"; + #sound-dai-cells = <0>; + sound-name-prefix = "PEF2256_0"; + }; + + pef2256_codec1: codec-1 { + compatible = "lantiq,pef2256-codec"; + #sound-dai-cells = <0>; + sound-name-prefix = "PEF2256_1"; + }; + }; + + sound { + compatible = "simple-audio-card"; + #address-cells = <1>; + #size-cells = <0>; + simple-audio-card,dai-link@0 { /* CPU DAI1 - pef2256 codec 1 */ + reg = <0>; + cpu { + sound-dai = <&cpu_dai1>; + }; + codec { + sound-dai = <&pef2256_codec0>; + dai-tdm-slot-num = <4>; + dai-tdm-slot-width = <8>; + /* TS 1, 2, 3, 4 */ + dai-tdm-slot-tx-mask = <0 1 1 1 1>; + dai-tdm-slot-rx-mask = <0 1 1 1 1>; + }; + }; + simple-audio-card,dai-link@1 { /* CPU DAI2 - pef2256 codec 2 */ + reg = <1>; + cpu { + sound-dai = <&cpu_dai2>; + }; + codec { + sound-dai = <&pef2256_codec1>; + dai-tdm-slot-num = <4>; + dai-tdm-slot-width = <8>; + /* TS 5, 6, 7, 8 */ + dai-tdm-slot-tx-mask = <0 0 0 0 0 1 1 1 1>; + dai-tdm-slot-rx-mask = <0 0 0 0 0 1 1 1 1>; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml b/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml index e35da8b01dc2..73429855d584 100644 --- a/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml +++ b/Documentation/devicetree/bindings/net/marvell,orion-mdio.yaml @@ -39,28 +39,6 @@ required: allOf: - $ref: mdio.yaml# - - if: - required: - - interrupts - - then: - properties: - reg: - items: - - items: - - $ref: /schemas/types.yaml#/definitions/cell - - const: 0x84 - - else: - properties: - reg: - items: - - items: - - $ref: /schemas/types.yaml#/definitions/cell - - enum: - - 0x4 - - 0x10 - unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/net/qcom,ipa.yaml b/Documentation/devicetree/bindings/net/qcom,ipa.yaml index 702eadccdf99..c30218684cfe 100644 --- a/Documentation/devicetree/bindings/net/qcom,ipa.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ipa.yaml @@ -43,16 +43,21 @@ description: properties: compatible: - enum: - - qcom,msm8998-ipa - - qcom,sc7180-ipa - - qcom,sc7280-ipa - - qcom,sdm845-ipa - - qcom,sdx55-ipa - - qcom,sdx65-ipa - - qcom,sm6350-ipa - - qcom,sm8350-ipa - - qcom,sm8550-ipa + oneOf: + - enum: + - qcom,msm8998-ipa + - qcom,sc7180-ipa + - qcom,sc7280-ipa + - qcom,sdm845-ipa + - qcom,sdx55-ipa + - qcom,sdx65-ipa + - qcom,sm6350-ipa + - qcom,sm8350-ipa + - qcom,sm8550-ipa + - items: + - enum: + - qcom,sm8650-ipa + - const: qcom,sm8550-ipa reg: items: diff --git a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml index c8448de2f2a0..d01c677ad3c7 100644 --- a/Documentation/devicetree/bindings/perf/riscv,pmu.yaml +++ b/Documentation/devicetree/bindings/perf/riscv,pmu.yaml @@ -90,7 +90,7 @@ properties: bitmap of all MHPMCOUNTERx that can monitor the range of events dependencies: - "riscv,event-to-mhpmevent": [ "riscv,event-to-mhpmcounters" ] + riscv,event-to-mhpmevent: [ "riscv,event-to-mhpmcounters" ] required: - compatible diff --git a/Documentation/devicetree/bindings/pwm/imx-pwm.yaml b/Documentation/devicetree/bindings/pwm/imx-pwm.yaml index c01dff3b7f84..a84a240a61dc 100644 --- a/Documentation/devicetree/bindings/pwm/imx-pwm.yaml +++ b/Documentation/devicetree/bindings/pwm/imx-pwm.yaml @@ -14,12 +14,10 @@ allOf: properties: "#pwm-cells": - description: | - Should be 2 for i.MX1 and 3 for i.MX27 and newer SoCs. See pwm.yaml - in this directory for a description of the cells format. - enum: - - 2 - - 3 + description: + The only third cell flag supported by this binding is + PWM_POLARITY_INVERTED. fsl,imx1-pwm does not support this flags. + const: 3 compatible: oneOf: diff --git a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml index e4fa6a07b4fa..1309bf5ae0cd 100644 --- a/Documentation/devicetree/bindings/soc/rockchip/grf.yaml +++ b/Documentation/devicetree/bindings/soc/rockchip/grf.yaml @@ -233,6 +233,7 @@ allOf: - rockchip,rk3399-grf - rockchip,rk3399-pmugrf - rockchip,rk3568-pmugrf + - rockchip,rk3588-pmugrf - rockchip,rv1108-grf - rockchip,rv1108-pmugrf diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst index f549a68951d7..8bc4ebe7a36f 100644 --- a/Documentation/driver-api/index.rst +++ b/Documentation/driver-api/index.rst @@ -115,6 +115,7 @@ available subsections can be seen below. hte/index wmi dpll + wbrf .. only:: subproject and html diff --git a/Documentation/driver-api/wbrf.rst b/Documentation/driver-api/wbrf.rst new file mode 100644 index 000000000000..f48bfa029813 --- /dev/null +++ b/Documentation/driver-api/wbrf.rst @@ -0,0 +1,78 @@ +.. SPDX-License-Identifier: GPL-2.0-or-later + +================================= +WBRF - Wifi Band RFI Mitigations +================================= + +Due to electrical and mechanical constraints in certain platform designs +there may be likely interference of relatively high-powered harmonics of +the GPU memory clocks with local radio module frequency bands used by +certain Wifi bands. + +To mitigate possible RFI interference producers can advertise the +frequencies in use and consumers can use this information to avoid using +these frequencies for sensitive features. + +When a platform is known to have this issue with any contained devices, +the platform designer will advertise the availability of this feature via +ACPI devices with a device specific method (_DSM). +* Producers with this _DSM will be able to advertise the frequencies in use. +* Consumers with this _DSM will be able to register for notifications of +frequencies in use. + +Some general terms +================== + +Producer: such component who can produce high-powered radio frequency +Consumer: such component who can adjust its in-use frequency in +response to the radio frequencies of other components to mitigate the +possible RFI. + +To make the mechanism function, those producers should notify active use +of their particular frequencies so that other consumers can make relative +internal adjustments as necessary to avoid this resonance. + +ACPI interface +============== + +Although initially used by for wifi + dGPU use cases, the ACPI interface +can be scaled to any type of device that a platform designer discovers +can cause interference. + +The GUID used for the _DSM is 7B7656CF-DC3D-4C1C-83E9-66E721DE3070. + +3 functions are available in this _DSM: + +* 0: discover # of functions available +* 1: record RF bands in use +* 2: retrieve RF bands in use + +Driver programming interface +============================ + +.. kernel-doc:: drivers/platform/x86/amd/wbrf.c + +Sample Usage +============= + +The expected flow for the producers: +1. During probe, call `acpi_amd_wbrf_supported_producer` to check if WBRF +can be enabled for the device. +2. On using some frequency band, call `acpi_amd_wbrf_add_remove` with 'add' +param to get other consumers properly notified. +3. Or on stopping using some frequency band, call +`acpi_amd_wbrf_add_remove` with 'remove' param to get other consumers notified. + +The expected flow for the consumers: +1. During probe, call `acpi_amd_wbrf_supported_consumer` to check if WBRF +can be enabled for the device. +2. Call `amd_wbrf_register_notifier` to register for notification +of frequency band change(add or remove) from other producers. +3. Call the `amd_wbrf_retrieve_freq_band` initally to retrieve +current active frequency bands considering some producers may broadcast +such information before the consumer is up. +4. On receiving a notification for frequency band change, run +`amd_wbrf_retrieve_freq_band` again to retrieve the latest +active frequency bands. +5. During driver cleanup, call `amd_wbrf_unregister_notifier` to +unregister the notifier. diff --git a/Documentation/filesystems/fuse-io.rst b/Documentation/filesystems/fuse-io.rst index 255a368fe534..6464de4266ad 100644 --- a/Documentation/filesystems/fuse-io.rst +++ b/Documentation/filesystems/fuse-io.rst @@ -15,7 +15,8 @@ The direct-io mode can be selected with the FOPEN_DIRECT_IO flag in the FUSE_OPEN reply. In direct-io mode the page cache is completely bypassed for reads and writes. -No read-ahead takes place. Shared mmap is disabled. +No read-ahead takes place. Shared mmap is disabled by default. To allow shared +mmap, the FUSE_DIRECT_IO_ALLOW_MMAP flag may be enabled in the FUSE_INIT reply. In cached mode reads may be satisfied from the page cache, and data may be read-ahead by the kernel to fill the cache. The cache is always kept consistent diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index 775cce8c548a..04b92f1a5cd6 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -126,8 +126,10 @@ properties: name: type: string type: - description: The netlink attribute type - enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary ] + description: | + The netlink attribute type. Members of type 'binary' or 'pad' + must also have the 'len' property set. + enum: [ u8, u16, u32, u64, s8, s16, s32, s64, string, binary, pad ] len: $ref: '#/$defs/len-or-define' byte-order: @@ -150,6 +152,14 @@ properties: the right formatting mechanism when displaying values of this type. enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + if: + properties: + type: + oneOf: + - const: binary + - const: pad + then: + required: [ len ] # End genetlink-legacy attribute-sets: @@ -200,8 +210,10 @@ properties: type: string type: &attr-type description: The netlink attribute type - enum: [ unused, pad, flag, binary, u8, u16, u32, u64, s32, s64, - string, nest, array-nest, nest-type-value ] + enum: [ unused, pad, flag, binary, bitfield32, + u8, u16, u32, u64, s8, s16, s32, s64, + string, nest, array-nest, nest-type-value, + sub-message ] doc: description: Documentation of the attribute. type: string @@ -260,6 +272,17 @@ properties: description: Name of the struct type used for the attribute. type: string # End genetlink-legacy + # Start netlink-raw + sub-message: + description: | + Name of the sub-message definition to use for the attribute. + type: string + selector: + description: | + Name of the attribute to use for dynamic selection of sub-message + format specifier. + type: string + # End netlink-raw # Make sure name-prefix does not appear in subsets (subsets inherit naming) dependencies: @@ -282,6 +305,43 @@ properties: items: required: [ type ] + # Start netlink-raw + sub-messages: + description: Definition of sub message attributes + type: array + items: + type: object + additionalProperties: False + required: [ name, formats ] + properties: + name: + description: Name of the sub-message definition + type: string + formats: + description: Dynamically selected format specifiers + type: array + items: + type: object + additionalProperties: False + required: [ value ] + properties: + value: + description: | + Value to match for dynamic selection of sub-message format + specifier. + type: string + fixed-header: + description: | + Name of the struct definition to use as the fixed header + for the sub message. + type: string + attribute-set: + description: | + Name of the attribute space from which to resolve attributes + in the sub message. + type: string + # End netlink-raw + operations: description: Operations supported by the protocol. type: object diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 43067e1f63aa..c3a438197964 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -77,6 +77,14 @@ definitions: name: ipsec-packet-bit - type: enum + name: rate-type + entries: + - + name: leaf + - + name: node + - + type: enum name: sb-threshold-type entries: - @@ -113,6 +121,16 @@ definitions: name: basic - type: enum + name: dpipe-header-id + entries: + - + name: ethernet + - + name: ipv4 + - + name: ipv6 + - + type: enum name: dpipe-match-type entries: - @@ -174,6 +192,16 @@ definitions: name: trap - name: mirror + - + type: enum + name: trap-type + entries: + - + name: drop + - + name: exception + - + name: control attribute-sets: - @@ -194,27 +222,45 @@ attribute-sets: name: port-type type: u16 enum: port-type - - # TODO: fill in the attributes in between - + - + name: port-desired-type + type: u16 + - + name: port-netdev-ifindex + type: u32 + - + name: port-netdev-name + type: string + - + name: port-ibdev-name + type: string - name: port-split-count type: u32 - value: 9 - - # TODO: fill in the attributes in between - + - + name: port-split-group + type: u32 - name: sb-index type: u32 - value: 11 - - # TODO: fill in the attributes in between - + - + name: sb-size + type: u32 + - + name: sb-ingress-pool-count + type: u16 + - + name: sb-egress-pool-count + type: u16 + - + name: sb-ingress-tc-count + type: u16 + - + name: sb-egress-tc-count + type: u16 - name: sb-pool-index type: u16 - value: 17 - name: sb-pool-type type: u8 @@ -232,16 +278,16 @@ attribute-sets: - name: sb-tc-index type: u16 - value: 22 - - # TODO: fill in the attributes in between - + - + name: sb-occ-cur + type: u32 + - + name: sb-occ-max + type: u32 - name: eswitch-mode type: u16 - value: 25 enum: eswitch-mode - - name: eswitch-inline-mode type: u16 @@ -347,6 +393,7 @@ attribute-sets: - name: dpipe-header-id type: u32 + enum: dpipe-header-id - name: dpipe-header-fields type: nest @@ -381,7 +428,6 @@ attribute-sets: - name: eswitch-encap-mode type: u8 - value: 62 enum: eswitch-encap-mode - name: resource-list @@ -433,20 +479,25 @@ attribute-sets: name: port-flavour type: u16 enum: port-flavour - - # TODO: fill in the attributes in between - + - + name: port-number + type: u32 + - + name: port-split-subport-number + type: u32 + - + name: param + type: nest + nested-attributes: dl-param - name: param-name type: string - value: 81 - - # TODO: fill in the attributes in between - + - + name: param-generic + type: flag - name: param-type type: u8 - value: 83 # TODO: fill in the attributes in between @@ -458,20 +509,34 @@ attribute-sets: - name: region-name type: string - - # TODO: fill in the attributes in between - + - + name: region-size + type: u64 + - + name: region-snapshots + type: nest + nested-attributes: dl-region-snapshots + - + name: region-snapshot + type: nest + nested-attributes: dl-region-snapshot - name: region-snapshot-id type: u32 - value: 92 - - # TODO: fill in the attributes in between - + - + name: region-chunks + type: nest + nested-attributes: dl-region-chunks + - + name: region-chunk + type: nest + nested-attributes: dl-region-chunk + - + name: region-chunk-data + type: binary - name: region-chunk-addr type: u64 - value: 96 - name: region-chunk-len type: u64 @@ -502,14 +567,13 @@ attribute-sets: - name: info-version-value type: string - - # TODO: fill in the attributes in between - + - + name: sb-pool-cell-size + type: u32 - name: fmsg type: nest nested-attributes: dl-fmsg - value: 106 - name: fmsg-obj-nest-start type: flag @@ -525,20 +589,35 @@ attribute-sets: - name: fmsg-obj-name type: string + - + name: fmsg-obj-value-type + type: u8 # TODO: fill in the attributes in between - + name: health-reporter + type: nest + value: 114 + nested-attributes: dl-health-reporter + - name: health-reporter-name type: string - value: 115 - - # TODO: fill in the attributes in between - + - + name: health-reporter-state + type: u8 + - + name: health-reporter-err-count + type: u64 + - + name: health-reporter-recover-count + type: u64 + - + name: health-reporter-dump-ts + type: u64 - name: health-reporter-graceful-period type: u64 - value: 120 - name: health-reporter-auto-recover type: u8 @@ -548,55 +627,64 @@ attribute-sets: - name: flash-update-component type: string - - # TODO: fill in the attributes in between - + - + name: flash-update-status-msg + type: string + - + name: flash-update-status-done + type: u64 + - + name: flash-update-status-total + type: u64 - name: port-pci-pf-number type: u16 - value: 127 - - # TODO: fill in the attributes in between - + - + name: port-pci-vf-number + type: u16 + - + name: stats + type: nest + nested-attributes: dl-attr-stats - name: trap-name type: string - value: 130 - name: trap-action type: u8 enum: trap-action - - # TODO: fill in the attributes in between - + - + name: trap-type + type: u8 + enum: trap-type + - + name: trap-generic + type: flag + - + name: trap-metadata + type: nest + nested-attributes: dl-trap-metadata - name: trap-group-name type: string - value: 135 - - name: reload-failed type: u8 - - # TODO: fill in the attributes in between - + - + name: health-reporter-dump-ts-ns + type: u64 - name: netns-fd type: u32 - value: 138 - name: netns-pid type: u32 - name: netns-id type: u32 - - # TODO: fill in the attributes in between - - name: health-reporter-auto-dump type: u8 - value: 141 - name: trap-policer-id type: u32 @@ -610,22 +698,29 @@ attribute-sets: name: port-function type: nest nested-attributes: dl-port-function - - # TODO: fill in the attributes in between - + - + name: info-board-serial-number + type: string + - + name: port-lanes + type: u32 + - + name: port-splittable + type: u8 + - + name: port-external + type: u8 - name: port-controller-number type: u32 - value: 150 - - # TODO: fill in the attributes in between - + - + name: flash-update-status-timeout + type: u64 - name: flash-update-overwrite-mask type: bitfield32 enum: flash-overwrite enum-as-flags: True - value: 152 - name: reload-action type: u8 @@ -673,20 +768,16 @@ attribute-sets: type: nest multi-attr: true nested-attributes: dl-reload-act-stats - - # 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-type + type: u16 + enum: rate-type - name: rate-tx-share type: u64 - value: 166 - name: rate-tx-max type: u64 @@ -696,20 +787,22 @@ attribute-sets: - name: rate-parent-node-name type: string - - # TODO: fill in the attributes in between - + - + name: region-max-snapshots + type: u32 - name: linecard-index type: u32 - value: 171 - - # TODO: fill in the attributes in between - + - + name: linecard-state + type: u8 - name: linecard-type type: string - value: 173 + - + name: linecard-supported-types + type: nest + nested-attributes: dl-linecard-supported-types # TODO: fill in the attributes in between @@ -736,12 +829,14 @@ attribute-sets: name: reload-stats - name: remote-reload-stats + - name: dl-reload-stats subset-of: devlink attributes: - name: reload-action-info + - name: dl-reload-act-info subset-of: devlink @@ -750,12 +845,14 @@ attribute-sets: name: reload-action - name: reload-action-stats + - name: dl-reload-act-stats subset-of: devlink attributes: - name: reload-stats-entry + - name: dl-reload-stats-entry subset-of: devlink @@ -764,6 +861,7 @@ attribute-sets: name: reload-stats-limit - name: reload-stats-value + - name: dl-info-version subset-of: devlink @@ -772,6 +870,7 @@ attribute-sets: name: info-version-name - name: info-version-value + - name: dl-port-function name-prefix: devlink-port-fn-attr- @@ -1006,6 +1105,49 @@ attribute-sets: name: resource - + name: dl-param + subset-of: devlink + attributes: + - + name: param-name + - + name: param-generic + - + name: param-type + + # TODO: fill in the attribute param-value-list + + - + name: dl-region-snapshots + subset-of: devlink + attributes: + - + name: region-snapshot + + - + name: dl-region-snapshot + subset-of: devlink + attributes: + - + name: region-snapshot-id + + - + name: dl-region-chunks + subset-of: devlink + attributes: + - + name: region-chunk + + - + name: dl-region-chunk + subset-of: devlink + attributes: + - + name: region-chunk-data + - + name: region-chunk-addr + + - name: dl-fmsg subset-of: devlink attributes: @@ -1021,6 +1163,62 @@ attribute-sets: name: fmsg-obj-name - + name: dl-health-reporter + subset-of: devlink + attributes: + - + name: health-reporter-name + - + name: health-reporter-state + - + name: health-reporter-err-count + - + name: health-reporter-recover-count + - + name: health-reporter-graceful-period + - + name: health-reporter-auto-recover + - + name: health-reporter-dump-ts + - + name: health-reporter-dump-ts-ns + - + name: health-reporter-auto-dump + + - + name: dl-attr-stats + name-prefix: devlink-attr- + attributes: + - name: stats-rx-packets + type: u64 + value: 0 + - + name: stats-rx-bytes + type: u64 + - + name: stats-rx-dropped + type: u64 + + - + name: dl-trap-metadata + name-prefix: devlink-attr- + attributes: + - + name: trap-metadata-type-in-port + type: flag + value: 0 + - + name: trap-metadata-type-fa-cookie + type: flag + + - + name: dl-linecard-supported-types + subset-of: devlink + attributes: + - + name: linecard-type + + - name: dl-selftest-id name-prefix: devlink-attr-selftest-id- attributes: @@ -1077,6 +1275,7 @@ 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. diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 5c7a65b009b4..197208f419dc 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -908,6 +908,9 @@ attribute-sets: - name: hkey type: binary + - + name: input_xfrm + type: u32 - name: plca attributes: @@ -1598,6 +1601,7 @@ operations: - hfunc - indir - hkey + - input_xfrm dump: *rss-get-op - name: plca-get-cfg diff --git a/Documentation/netlink/specs/mptcp.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index 49f90cfb4698..49f90cfb4698 100644 --- a/Documentation/netlink/specs/mptcp.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index aeec090e1387..3addac970680 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -70,6 +70,10 @@ definitions: name: tx-checksum doc: L3 checksum HW offload is supported by the driver. + - + name: queue-type + type: enum + entries: [ rx, tx ] attribute-sets: - @@ -213,6 +217,54 @@ attribute-sets: name: recycle-released-refcnt type: uint + - + name: napi + attributes: + - + name: ifindex + doc: ifindex of the netdevice to which NAPI instance belongs. + type: u32 + checks: + min: 1 + - + name: id + doc: ID of the NAPI instance. + type: u32 + - + name: irq + doc: The associated interrupt vector number for the napi + type: u32 + - + name: pid + doc: PID of the napi thread, if NAPI is configured to operate in + threaded mode. If NAPI is not in threaded mode (i.e. uses normal + softirq context), the attribute will be absent. + type: u32 + - + name: queue + attributes: + - + name: id + doc: Queue index; most queue types are indexed like a C array, with + indexes starting at 0 and ending at queue count - 1. Queue indexes + are scoped to an interface and queue type. + type: u32 + - + name: ifindex + doc: ifindex of the netdevice to which the queue belongs. + type: u32 + checks: + min: 1 + - + name: type + doc: Queue type as rx, tx. Each queue type defines a separate ID space. + type: u32 + enum: queue-type + - + name: napi-id + doc: ID of the NAPI instance which services this queue. + type: u32 + operations: list: - @@ -311,6 +363,48 @@ operations: dump: reply: *pp-stats-reply config-cond: page-pool-stats + - + name: queue-get + doc: Get queue information from the kernel. + Only configured queues will be reported (as opposed to all available + hardware queues). + attribute-set: queue + do: + request: + attributes: + - ifindex + - type + - id + reply: &queue-get-op + attributes: + - id + - type + - napi-id + - ifindex + dump: + request: + attributes: + - ifindex + reply: *queue-get-op + - + name: napi-get + doc: Get information about NAPI instances configured on the system. + attribute-set: napi + do: + request: + attributes: + - id + reply: &napi-get-op + attributes: + - id + - ifindex + - irq + - pid + dump: + request: + attributes: + - ifindex + reply: *napi-get-op mcast-groups: list: diff --git a/Documentation/netlink/specs/ovs_datapath.yaml b/Documentation/netlink/specs/ovs_datapath.yaml index f709c26c3e92..edc8c95ca6f5 100644 --- a/Documentation/netlink/specs/ovs_datapath.yaml +++ b/Documentation/netlink/specs/ovs_datapath.yaml @@ -20,6 +20,7 @@ definitions: name: user-features type: flags name-prefix: ovs-dp-f- + enum-name: entries: - name: unaligned @@ -142,7 +143,6 @@ operations: do: request: attributes: - - dp-ifindex - name - upcall-pid - user-features @@ -154,7 +154,6 @@ operations: do: request: attributes: - - dp-ifindex - name mcast-groups: diff --git a/Documentation/netlink/specs/ovs_flow.yaml b/Documentation/netlink/specs/ovs_flow.yaml index 109ca1f57b6c..4fdfc6b5cae9 100644 --- a/Documentation/netlink/specs/ovs_flow.yaml +++ b/Documentation/netlink/specs/ovs_flow.yaml @@ -124,6 +124,7 @@ definitions: - name: ovs-frag-type name-prefix: ovs-frag-type- + enum-name: ovs-frag-type type: enum entries: - @@ -269,6 +270,7 @@ definitions: - name: ovs-ufid-flags name-prefix: ovs-ufid-f- + enum-name: type: flags entries: - omit-key @@ -288,6 +290,7 @@ definitions: doc: Basis used for computing hash. - name: ovs-hash-alg + enum-name: ovs-hash-alg type: enum doc: | Data path hash algorithm for computing Datapath hash. The algorithm type only specifies @@ -339,6 +342,7 @@ definitions: MPLS tunnel attributes. - name: ct-state-flags + enum-name: type: flags name-prefix: ovs-cs-f- entries: @@ -947,13 +951,11 @@ operations: do: &flow-get-op request: attributes: - - dp-ifindex - key - ufid - ufid-flags reply: attributes: - - dp-ifindex - key - ufid - mask @@ -968,7 +970,6 @@ operations: do: request: attributes: - - dp-ifindex - key - ufid - mask diff --git a/Documentation/netlink/specs/ovs_vport.yaml b/Documentation/netlink/specs/ovs_vport.yaml index f65ce62cd60d..86ba9ac2a521 100644 --- a/Documentation/netlink/specs/ovs_vport.yaml +++ b/Documentation/netlink/specs/ovs_vport.yaml @@ -135,7 +135,6 @@ operations: - name - type - upcall-pid - - dp-ifindex - ifindex - options - @@ -146,7 +145,6 @@ operations: do: request: attributes: - - dp-ifindex - port-no - type - name @@ -158,11 +156,9 @@ operations: do: &vport-get-op request: attributes: - - dp-ifindex - name reply: &dev-all attributes: - - dp-ifindex - port-no - type - name diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index d86a68f8475c..1ad01d52a863 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -66,8 +66,9 @@ definitions: name: ifi-family type: u8 - - name: padding - type: u8 + name: pad + type: pad + len: 1 - name: ifi-type type: u16 @@ -83,6 +84,18 @@ definitions: name: ifi-change type: u32 - + name: ifla-bridge-id + type: struct + members: + - + name: prio + type: u16 + - + name: addr + type: binary + len: 6 + display-hint: mac + - name: ifla-cacheinfo type: struct members: @@ -707,11 +720,9 @@ definitions: name: family type: u8 - - name: pad1 - type: u8 - - - name: pad2 - type: u16 + name: pad + type: pad + len: 3 - name: ifindex type: u32 @@ -966,8 +977,9 @@ attribute-sets: type: string - name: data - type: binary - # kind specific nest, e.g. linkinfo-bridge-attrs + type: sub-message + sub-message: linkinfo-data-msg + selector: kind - name: xstats type: binary @@ -976,10 +988,12 @@ attribute-sets: type: string - name: slave-data - type: binary - # kind specific nest + type: sub-message + sub-message: linkinfo-member-data-msg + selector: slave-kind - name: linkinfo-bridge-attrs + name-prefix: ifla-br- attributes: - name: forward-delay @@ -1011,9 +1025,11 @@ attribute-sets: - name: root-id type: binary + struct: ifla-bridge-id - name: bridge-id type: binary + struct: ifla-bridge-id - name: root-port type: u16 @@ -1041,6 +1057,7 @@ attribute-sets: - name: group-addr type: binary + display-hint: mac - name: fdb-flush type: binary @@ -1124,6 +1141,376 @@ attribute-sets: name: mcast-querier-state type: binary - + name: linkinfo-brport-attrs + name-prefix: ifla-brport- + attributes: + - + name: state + type: u8 + - + name: priority + type: u16 + - + name: cost + type: u32 + - + name: mode + type: flag + - + name: guard + type: flag + - + name: protect + type: flag + - + name: fast-leave + type: flag + - + name: learning + type: flag + - + name: unicast-flood + type: flag + - + name: proxyarp + type: flag + - + name: learning-sync + type: flag + - + name: proxyarp-wifi + type: flag + - + name: root-id + type: binary + struct: ifla-bridge-id + - + name: bridge-id + type: binary + struct: ifla-bridge-id + - + name: designated-port + type: u16 + - + name: designated-cost + type: u16 + - + name: id + type: u16 + - + name: "no" + type: u16 + - + name: topology-change-ack + type: u8 + - + name: config-pending + type: u8 + - + name: message-age-timer + type: u64 + - + name: forward-delay-timer + type: u64 + - + name: hold-timer + type: u64 + - + name: flush + type: flag + - + name: multicast-router + type: u8 + - + name: pad + type: pad + - + name: mcast-flood + type: flag + - + name: mcast-to-ucast + type: flag + - + name: vlan-tunnel + type: flag + - + name: bcast-flood + type: flag + - + name: group-fwd-mask + type: u16 + - + name: neigh-suppress + type: flag + - + name: isolated + type: flag + - + name: backup-port + type: u32 + - + name: mrp-ring-open + type: flag + - + name: mrp-in-open + type: flag + - + name: mcast-eht-hosts-limit + type: u32 + - + name: mcast-eht-hosts-cnt + type: u32 + - + name: locked + type: flag + - + name: mab + type: flag + - + name: mcast-n-groups + type: u32 + - + name: mcast-max-groups + type: u32 + - + name: neigh-vlan-suppress + type: flag + - + name: backup-nhid + type: u32 + - + name: linkinfo-gre-attrs + name-prefix: ifla-gre- + attributes: + - + name: link + type: u32 + - + name: iflags + type: u16 + - + name: oflags + type: u16 + - + name: ikey + type: u32 + - + name: okey + type: u32 + - + name: local + type: binary + display-hint: ipv4 + - + name: remote + type: binary + display-hint: ipv4 + - + name: ttl + type: u8 + - + name: tos + type: u8 + - + name: pmtudisc + type: u8 + - + name: encap-limit + type: u32 + - + name: flowinfo + type: u32 + - + name: flags + type: u32 + - + name: encap-type + type: u16 + - + name: encap-flags + type: u16 + - + name: encap-sport + type: u16 + - + name: encap-dport + type: u16 + - + name: collect-metadata + type: flag + - + name: ignore-df + type: u8 + - + name: fwmark + type: u32 + - + name: erspan-index + type: u32 + - + name: erspan-ver + type: u8 + - + name: erspan-dir + type: u8 + - + name: erspan-hwid + type: u16 + - + name: linkinfo-geneve-attrs + name-prefix: ifla-geneve- + attributes: + - + name: id + type: u32 + - + name: remote + type: binary + display-hint: ipv4 + - + name: ttl + type: u8 + - + name: tos + type: u8 + - + name: port + type: u16 + - + name: collect-metadata + type: flag + - + name: remote6 + type: binary + display-hint: ipv6 + - + name: udp-csum + type: u8 + - + name: udp-zero-csum6-tx + type: u8 + - + name: udp-zero-csum6-rx + type: u8 + - + name: label + type: u32 + - + name: ttl-inherit + type: u8 + - + name: df + type: u8 + - + name: inner-proto-inherit + type: flag + - + name: linkinfo-iptun-attrs + name-prefix: ifla-iptun- + attributes: + - + name: link + type: u32 + - + name: local + type: binary + display-hint: ipv4 + - + name: remote + type: binary + display-hint: ipv4 + - + name: ttl + type: u8 + - + name: tos + type: u8 + - + name: encap-limit + type: u8 + - + name: flowinfo + type: u32 + - + name: flags + type: u16 + - + name: proto + type: u8 + - + name: pmtudisc + type: u8 + - + name: 6rd-prefix + type: binary + display-hint: ipv6 + - + name: 6rd-relay-prefix + type: binary + display-hint: ipv4 + - + name: 6rd-prefixlen + type: u16 + - + name: 6rd-relay-prefixlen + type: u16 + - + name: encap-type + type: u16 + - + name: encap-flags + type: u16 + - + name: encap-sport + type: u16 + - + name: encap-dport + type: u16 + - + name: collect-metadata + type: flag + - + name: fwmark + type: u32 + - + name: linkinfo-tun-attrs + name-prefix: ifla-tun- + attributes: + - + name: owner + type: u32 + - + name: group + type: u32 + - + name: type + type: u8 + - + name: pi + type: u8 + - + name: vnet-hdr + type: u8 + - + name: persist + type: u8 + - + name: multi-queue + type: u8 + - + name: num-queues + type: u32 + - + name: num-disabled-queues + type: u32 + - + name: linkinfo-vrf-attrs + name-prefix: ifla-vrf- + attributes: + - + name: table + type: u32 + - name: xdp-attrs attributes: - @@ -1241,6 +1628,46 @@ attribute-sets: name: used type: u8 +sub-messages: + - + name: linkinfo-data-msg + formats: + - + value: bridge + attribute-set: linkinfo-bridge-attrs + - + value: erspan + attribute-set: linkinfo-gre-attrs + - + value: gre + attribute-set: linkinfo-gre-attrs + - + value: gretap + attribute-set: linkinfo-gre-attrs + - + value: geneve + attribute-set: linkinfo-geneve-attrs + - + value: ipip + attribute-set: linkinfo-iptun-attrs + - + value: sit + attribute-set: linkinfo-iptun-attrs + - + value: tun + attribute-set: linkinfo-tun-attrs + - + value: vrf + attribute-set: linkinfo-vrf-attrs + - + name: linkinfo-member-data-msg + formats: + - + value: bridge + attribute-set: linkinfo-brport-attrs + - + value: bond + operations: enum-model: directional list: diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml new file mode 100644 index 000000000000..4346fa402fc9 --- /dev/null +++ b/Documentation/netlink/specs/tc.yaml @@ -0,0 +1,2031 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) + +name: tc +protocol: netlink-raw +protonum: 0 + +doc: + Netlink raw family for tc qdisc, chain, class and filter configuration + over rtnetlink. + +definitions: + - + name: tcmsg + type: struct + members: + - + name: family + type: u8 + - + name: pad + type: pad + len: 3 + - + name: ifindex + type: s32 + - + name: handle + type: u32 + - + name: parent + type: u32 + - + name: info + type: u32 + - + name: tc-cls-flags + type: flags + entries: + - skip-hw + - skip-sw + - in-hw + - not-in-nw + - verbose + - + name: tc-stats + type: struct + members: + - + name: bytes + type: u64 + - + name: packets + type: u32 + - + name: drops + type: u32 + - + name: overlimits + type: u32 + - + name: bps + type: u32 + - + name: pps + type: u32 + - + name: qlen + type: u32 + - + name: backlog + type: u32 + - + name: tc-cbs-qopt + type: struct + members: + - + name: offload + type: u8 + - + name: pad + type: pad + len: 3 + - + name: hicredit + type: s32 + - + name: locredit + type: s32 + - + name: idleslope + type: s32 + - + name: sendslope + type: s32 + - + name: tc-etf-qopt + type: struct + members: + - + name: delta + type: s32 + - + name: clockid + type: s32 + - + name: flags + type: s32 + - + name: tc-fifo-qopt + type: struct + members: + - + name: limit + type: u32 + - + name: tc-htb-opt + type: struct + members: + - + name: rate + type: binary + len: 12 + - + name: ceil + type: binary + len: 12 + - + name: buffer + type: u32 + - + name: cbuffer + type: u32 + - + name: quantum + type: u32 + - + name: level + type: u32 + - + name: prio + type: u32 + - + name: tc-htb-glob + type: struct + members: + - + name: version + type: u32 + - + name: rate2quantum + type: u32 + - + name: defcls + type: u32 + - + name: debug + type: u32 + - + name: direct-pkts + type: u32 + - + name: tc-gred-qopt + type: struct + members: + - + name: limit + type: u32 + - + name: qth-min + type: u32 + - + name: qth-max + type: u32 + - + name: DP + type: u32 + - + name: backlog + type: u32 + - + name: qave + type: u32 + - + name: forced + type: u32 + - + name: early + type: u32 + - + name: other + type: u32 + - + name: pdrop + type: u32 + - + name: Wlog + type: u8 + - + name: Plog + type: u8 + - + name: Scell_log + type: u8 + - + name: prio + type: u8 + - + name: packets + type: u32 + - + name: bytesin + type: u32 + - + name: tc-gred-sopt + type: struct + members: + - + name: DPs + type: u32 + - + name: def_DP + type: u32 + - + name: grio + type: u8 + - + name: flags + type: u8 + - + name: pad + type: pad + len: 2 + - + name: tc-hfsc-qopt + type: struct + members: + - + name: defcls + type: u16 + - + name: tc-mqprio-qopt + type: struct + members: + - + name: num-tc + type: u8 + - + name: prio-tc-map + type: binary + len: 16 + - + name: hw + type: u8 + - + name: count + type: binary + len: 32 + - + name: offset + type: binary + len: 32 + - + name: tc-multiq-qopt + type: struct + members: + - + name: bands + type: u16 + - + name: max-bands + type: u16 + - + name: tc-netem-qopt + type: struct + members: + - + name: latency + type: u32 + - + name: limit + type: u32 + - + name: loss + type: u32 + - + name: gap + type: u32 + - + name: duplicate + type: u32 + - + name: jitter + type: u32 + - + name: tc-plug-qopt + type: struct + members: + - + name: action + type: s32 + - + name: limit + type: u32 + - + name: tc-prio-qopt + type: struct + members: + - + name: bands + type: u16 + - + name: priomap + type: binary + len: 16 + - + name: tc-red-qopt + type: struct + members: + - + name: limit + type: u32 + - + name: qth-min + type: u32 + - + name: qth-max + type: u32 + - + name: Wlog + type: u8 + - + name: Plog + type: u8 + - + name: Scell-log + type: u8 + - + name: flags + type: u8 + - + name: tc-sfb-qopt + type: struct + members: + - + name: rehash-interval + type: u32 + - + name: warmup-time + type: u32 + - + name: max + type: u32 + - + name: bin-size + type: u32 + - + name: increment + type: u32 + - + name: decrement + type: u32 + - + name: limit + type: u32 + - + name: penalty-rate + type: u32 + - + name: penalty-burst + type: u32 + - + name: tc-sfq-qopt-v1 # TODO nested structs + type: struct + members: + - + name: quantum + type: u32 + - + name: perturb-period + type: s32 + - + name: limit + type: u32 + - + name: divisor + type: u32 + - + name: flows + type: u32 + - + name: depth + type: u32 + - + name: headdrop + type: u32 + - + name: limit + type: u32 + - + name: qth-min + type: u32 + - + name: qth-mac + type: u32 + - + name: Wlog + type: u8 + - + name: Plog + type: u8 + - + name: Scell-log + type: u8 + - + name: flags + type: u8 + - + name: max-P + type: u32 + - + name: prob-drop + type: u32 + - + name: forced-drop + type: u32 + - + name: prob-mark + type: u32 + - + name: forced-mark + type: u32 + - + name: prob-mark-head + type: u32 + - + name: forced-mark-head + type: u32 + - + name: tc-tbf-qopt + type: struct + members: + - + name: rate + type: binary # TODO nested struct tc_ratespec + len: 12 + - + name: peakrate + type: binary # TODO nested struct tc_ratespec + len: 12 + - + name: limit + type: u32 + - + name: buffer + type: u32 + - + name: mtu + type: u32 + - + name: tc-sizespec + type: struct + members: + - + name: cell-log + type: u8 + - + name: size-log + type: u8 + - + name: cell-align + type: s16 + - + name: overhead + type: s32 + - + name: linklayer + type: u32 + - + name: mpu + type: u32 + - + name: mtu + type: u32 + - + name: tsize + type: u32 + - + name: gnet-estimator + type: struct + members: + - + name: interval + type: s8 + - + name: ewma-log + type: u8 +attribute-sets: + - + name: tc-attrs + attributes: + - + name: kind + type: string + - + name: options + type: sub-message + sub-message: tc-options-msg + selector: kind + - + name: stats + type: binary + struct: tc-stats + - + name: xstats + type: binary + - + name: rate + type: binary + struct: gnet-estimator + - + name: fcnt + type: u32 + - + name: stats2 + type: nest + nested-attributes: tca-stats-attrs + - + name: stab + type: nest + nested-attributes: tca-stab-attrs + - + name: pad + type: pad + - + name: dump-invisible + type: flag + - + name: chain + type: u32 + - + name: hw-offload + type: u8 + - + name: ingress-block + type: u32 + - + name: egress-block + type: u32 + - + name: dump-flags + type: bitfield32 + - + name: ext-warn-msg + type: string + - + name: tc-cake-attrs + attributes: + - + name: pad + type: pad + - + name: base-rate64 + type: u64 + - + name: diffserv-mode + type: u32 + - + name: atm + type: u32 + - + name: flow-mode + type: u32 + - + name: overhead + type: u32 + - + name: rtt + type: u32 + - + name: target + type: u32 + - + name: autorate + type: u32 + - + name: memory + type: u32 + - + name: nat + type: u32 + - + name: raw + type: u32 + - + name: wash + type: u32 + - + name: mpu + type: u32 + - + name: ingress + type: u32 + - + name: ack-filter + type: u32 + - + name: split-gso + type: u32 + - + name: fwmark + type: u32 + - + name: tc-cake-stats-attrs + attributes: + - + name: pad + type: pad + - + name: capacity-estimate64 + type: u64 + - + name: memory-limit + type: u32 + - + name: memory-used + type: u32 + - + name: avg-netoff + type: u32 + - + name: min-netlen + type: u32 + - + name: max-netlen + type: u32 + - + name: min-adjlen + type: u32 + - + name: max-adjlen + type: u32 + - + name: tin-stats + type: binary + - + name: deficit + type: s32 + - + name: cobalt-count + type: u32 + - + name: dropping + type: u32 + - + name: drop-next-us + type: s32 + - + name: p-drop + type: u32 + - + name: blue-timer-us + type: s32 + - + name: tc-cbs-attrs + attributes: + - + name: parms + type: binary + struct: tc-cbs-qopt + - + name: tc-choke-attrs + attributes: + - + name: parms + type: binary + struct: tc-red-qopt + - + name: stab + type: binary + - + name: max-p + type: u32 + - + name: tc-codel-attrs + attributes: + - + name: target + type: u32 + - + name: limit + type: u32 + - + name: interval + type: u32 + - + name: ecn + type: u32 + - + name: ce-threshold + type: u32 + - + name: tc-drr-attrs + attributes: + - + name: quantum + type: u32 + - + name: tc-flower-attrs + attributes: + - + name: classid + type: u32 + - + name: indev + type: string + - + name: act + type: array-nest + nested-attributes: tc-act-attrs + - + name: key-eth-dst + type: binary + display-hint: mac + - + name: key-eth-dst-mask + type: binary + display-hint: mac + - + name: key-eth-src + type: binary + display-hint: mac + - + name: key-eth-src-mask + type: binary + display-hint: mac + - + name: key-eth-type + type: u16 + byte-order: big-endian + - + name: key-ip-proto + type: u8 + - + name: key-ipv4-src + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-ipv4-src-mask + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-ipv4-dst + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-ipv4-dst-mask + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-ipv6-src + type: binary + display-hint: ipv6 + - + name: key-ipv6-src-mask + type: binary + display-hint: ipv6 + - + name: key-ipv6-dst + type: binary + display-hint: ipv6 + - + name: key-ipv6-dst-mask + type: binary + display-hint: ipv6 + - + name: key-tcp-src + type: u16 + byte-order: big-endian + - + name: key-tcp-dst + type: u16 + byte-order: big-endian + - + name: key-udp-src + type: u16 + byte-order: big-endian + - + name: key-udp-dst + type: u16 + byte-order: big-endian + - + name: flags + type: u32 + enum: tc-cls-flags + enum-as-flags: true + - + name: key-vlan-id + type: u16 + byte-order: big-endian + - + name: key-vlan-prio + type: u8 + - + name: key-vlan-eth-type + type: u16 + byte-order: big-endian + - + name: key-enc-key-id + type: u32 + byte-order: big-endian + - + name: key-enc-ipv4-src + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-enc-ipv4-src-mask + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-enc-ipv4-dst + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-enc-ipv4-dst-mask + type: u32 + byte-order: big-endian + display-hint: ipv4 + - + name: key-enc-ipv6-src + type: binary + display-hint: ipv6 + - + name: key-enc-ipv6-src-mask + type: binary + display-hint: ipv6 + - + name: key-enc-ipv6-dst + type: binary + display-hint: ipv6 + - + name: key-enc-ipv6-dst-mask + type: binary + display-hint: ipv6 + - + name: key-tcp-src-mask + type: u16 + byte-order: big-endian + - + name: key-tcp-dst-mask + type: u16 + byte-order: big-endian + - + name: key-udp-src-mask + type: u16 + byte-order: big-endian + - + name: key-udp-dst-mask + type: u16 + byte-order: big-endian + - + name: key-sctp-src-mask + type: u16 + byte-order: big-endian + - + name: key-sctp-dst-mask + type: u16 + byte-order: big-endian + - + name: key-sctp-src + type: u16 + byte-order: big-endian + - + name: key-sctp-dst + type: u16 + byte-order: big-endian + - + name: key-enc-udp-src-port + type: u16 + byte-order: big-endian + - + name: key-enc-udp-src-port-mask + type: u16 + byte-order: big-endian + - + name: key-enc-udp-dst-port + type: u16 + byte-order: big-endian + - + name: key-enc-udp-dst-port-mask + type: u16 + byte-order: big-endian + - + name: key-flags + type: u32 + byte-order: big-endian + - + name: key-flags-mask + type: u32 + byte-order: big-endian + - + name: key-icmpv4-code + type: u8 + - + name: key-icmpv4-code-mask + type: u8 + - + name: key-icmpv4-type + type: u8 + - + name: key-icmpv4-type-mask + type: u8 + - + name: key-icmpv6-code + type: u8 + - + name: key-icmpv6-code-mask + type: u8 + - + name: key-icmpv6-type + type: u8 + - + name: key-icmpv6-type-mask + type: u8 + - + name: key-arp-sip + type: u32 + byte-order: big-endian + - + name: key-arp-sip-mask + type: u32 + byte-order: big-endian + - + name: key-arp-tip + type: u32 + byte-order: big-endian + - + name: key-arp-tip-mask + type: u32 + byte-order: big-endian + - + name: key-arp-op + type: u8 + - + name: key-arp-op-mask + type: u8 + - + name: key-arp-sha + type: binary + - + name: key-arp-sha-mask + type: binary + - + name: key-arp-tha + type: binary + - + name: key-arp-tha-mask + type: binary + - + name: key-mpls-ttl + type: u8 + - + name: key-mpls-bos + type: u8 + - + name: key-mpls-tc + type: u8 + - + name: key-mpls-label + type: u32 + byte-order: big-endian + - + name: key-tcp-flags + type: u16 + byte-order: big-endian + - + name: key-tcp-flags-mask + type: u16 + byte-order: big-endian + - + name: key-ip-tos + type: u8 + - + name: key-ip-tos-mask + type: u8 + - + name: key-ip-ttl + type: u8 + - + name: key-ip-ttl-mask + type: u8 + - + name: key-cvlan-id + type: u16 + byte-order: big-endian + - + name: key-cvlan-prio + type: u8 + - + name: key-cvlan-eth-type + type: u16 + byte-order: big-endian + - + name: key-enc-ip-tos + type: u8 + - + name: key-enc-ip-tos-mask + type: u8 + - + name: key-enc-ip-ttl + type: u8 + - + name: key-enc-ip-ttl-mask + type: u8 + - + name: key-enc-opts + type: binary + - + name: key-enc-opts-mask + type: binary + - + name: in-hw-count + type: u32 + - + name: key-port-src-min + type: u16 + byte-order: big-endian + - + name: key-port-src-max + type: u16 + byte-order: big-endian + - + name: key-port-dst-min + type: u16 + byte-order: big-endian + - + name: key-port-dst-max + type: u16 + byte-order: big-endian + - + name: key-ct-state + type: u16 + - + name: key-ct-state-mask + type: u16 + - + name: key-ct-zone + type: u16 + - + name: key-ct-zone-mask + type: u16 + - + name: key-ct-mark + type: u32 + - + name: key-ct-mark-mask + type: u32 + - + name: key-ct-labels + type: binary + - + name: key-ct-labels-mask + type: binary + - + name: key-mpls-opts + type: binary + - + name: key-hash + type: u32 + - + name: key-hash-mask + type: u32 + - + name: key-num-of-vlans + type: u8 + - + name: key-pppoe-sid + type: u16 + byte-order: big-endian + - + name: key-ppp-proto + type: u16 + byte-order: big-endian + - + name: key-l2-tpv3-sid + type: u32 + byte-order: big-endian + - + name: tc-gred-attrs + attributes: + - + name: parms + type: binary # array of struct: tc-gred-qopt + - + name: stab + type: binary + sub-type: u8 + - + name: dps + type: binary + struct: tc-gred-sopt + - + name: max-p + type: binary + sub-type: u32 + - + name: limit + type: u32 + - + name: vq-list + type: nest + nested-attributes: tca-gred-vq-list-attrs + - + name: tca-gred-vq-list-attrs + attributes: + - + name: entry + type: nest + nested-attributes: tca-gred-vq-entry-attrs + multi-attr: true + - + name: tca-gred-vq-entry-attrs + attributes: + - + name: pad + type: pad + - + name: dp + type: u32 + - + name: stat-bytes + type: u32 + - + name: stat-packets + type: u32 + - + name: stat-backlog + type: u32 + - + name: stat-prob-drop + type: u32 + - + name: stat-prob-mark + type: u32 + - + name: stat-forced-drop + type: u32 + - + name: stat-forced-mark + type: u32 + - + name: stat-pdrop + type: u32 + - + name: stat-other + type: u32 + - + name: flags + type: u32 + - + name: tc-hfsc-attrs + attributes: + - + name: rsc + type: binary + - + name: fsc + type: binary + - + name: usc + type: binary + - + name: tc-hhf-attrs + attributes: + - + name: backlog-limit + type: u32 + - + name: quantum + type: u32 + - + name: hh-flows-limit + type: u32 + - + name: reset-timeout + type: u32 + - + name: admit-bytes + type: u32 + - + name: evict-timeout + type: u32 + - + name: non-hh-weight + type: u32 + - + name: tc-htb-attrs + attributes: + - + name: parms + type: binary + struct: tc-htb-opt + - + name: init + type: binary + struct: tc-htb-glob + - + name: ctab + type: binary + - + name: rtab + type: binary + - + name: direct-qlen + type: u32 + - + name: rate64 + type: u64 + - + name: ceil64 + type: u64 + - + name: pad + type: pad + - + name: offload + type: flag + - + name: tc-act-attrs + attributes: + - + name: kind + type: string + - + name: options + type: sub-message + sub-message: tc-act-options-msg + selector: kind + - + name: index + type: u32 + - + name: stats + type: binary + - + name: pad + type: pad + - + name: cookie + type: binary + - + name: flags + type: bitfield32 + - + name: hw-stats + type: bitfield32 + - + name: used-hw-stats + type: bitfield32 + - + name: in-hw-count + type: u32 + - + name: tc-etf-attrs + attributes: + - + name: parms + type: binary + struct: tc-etf-qopt + - + name: tc-ets-attrs + attributes: + - + name: nbands + type: u8 + - + name: nstrict + type: u8 + - + name: quanta + type: nest + nested-attributes: tc-ets-attrs + - + name: quanta-band + type: u32 + multi-attr: true + - + name: priomap + type: nest + nested-attributes: tc-ets-attrs + - + name: priomap-band + type: u8 + multi-attr: true + - + name: tc-fq-attrs + attributes: + - + name: plimit + type: u32 + - + name: flow-plimit + type: u32 + - + name: quantum + type: u32 + - + name: initial-quantum + type: u32 + - + name: rate-enable + type: u32 + - + name: flow-default-rate + type: u32 + - + name: flow-max-rate + type: u32 + - + name: buckets-log + type: u32 + - + name: flow-refill-delay + type: u32 + - + name: orphan-mask + type: u32 + - + name: low-rate-threshold + type: u32 + - + name: ce-threshold + type: u32 + - + name: timer-slack + type: u32 + - + name: horizon + type: u32 + - + name: horizon-drop + type: u8 + - + name: tc-fq-codel-attrs + attributes: + - + name: target + type: u32 + - + name: limit + type: u32 + - + name: interval + type: u32 + - + name: ecn + type: u32 + - + name: flows + type: u32 + - + name: quantum + type: u32 + - + name: ce-threshold + type: u32 + - + name: drop-batch-size + type: u32 + - + name: memory-limit + type: u32 + - + name: ce-threshold-selector + type: u8 + - + name: ce-threshold-mask + type: u8 + - + name: tc-fq-pie-attrs + attributes: + - + name: limit + type: u32 + - + name: flows + type: u32 + - + name: target + type: u32 + - + name: tupdate + type: u32 + - + name: alpha + type: u32 + - + name: beta + type: u32 + - + name: quantum + type: u32 + - + name: memory-limit + type: u32 + - + name: ecn-prob + type: u32 + - + name: ecn + type: u32 + - + name: bytemode + type: u32 + - + name: dq-rate-estimator + type: u32 + - + name: tc-netem-attrs + attributes: + - + name: corr + type: binary + - + name: delay-dist + type: binary + sub-type: s16 + - + name: reorder + type: binary + - + name: corrupt + type: binary + - + name: loss + type: binary + - + name: rate + type: binary + - + name: ecn + type: u32 + - + name: rate64 + type: u64 + - + name: pad + type: u32 + - + name: latency64 + type: s64 + - + name: jitter64 + type: s64 + - + name: slot + type: binary + - + name: slot-dist + type: binary + sub-type: s16 + - + name: tc-pie-attrs + attributes: + - + name: target + type: u32 + - + name: limit + type: u32 + - + name: tupdate + type: u32 + - + name: alpha + type: u32 + - + name: beta + type: u32 + - + name: ecn + type: u32 + - + name: bytemode + type: u32 + - + name: dq-rate-estimator + type: u32 + - + name: tc-qfq-attrs + attributes: + - + name: weight + type: u32 + - + name: lmax + type: u32 + - + name: tc-red-attrs + attributes: + - + name: parms + type: binary + struct: tc-red-qopt + - + name: stab + type: binary + - + name: max-p + type: u32 + - + name: flags + type: binary + - + name: early-drop-block + type: u32 + - + name: mark-block + type: u32 + - + name: tc-taprio-attrs + attributes: + - + name: priomap + type: binary + struct: tc-mqprio-qopt + - + name: sched-entry-list + type: nest + nested-attributes: tc-taprio-sched-entry-list + - + name: sched-base-time + type: s64 + - + name: sched-single-entry + type: nest + nested-attributes: tc-taprio-sched-entry + - + name: sched-clockid + type: s32 + - + name: pad + type: pad + - + name: admin-sched + type: binary + - + name: sched-cycle-time + type: s64 + - + name: sched-cycle-time-extension + type: s64 + - + name: flags + type: u32 + - + name: txtime-delay + type: u32 + - + name: tc-entry + type: nest + nested-attributes: tc-taprio-tc-entry-attrs + - + name: tc-taprio-sched-entry-list + attributes: + - + name: entry + type: nest + nested-attributes: tc-taprio-sched-entry + - + name: tc-taprio-sched-entry + attributes: + - + name: index + type: u32 + - + name: cmd + type: u8 + - + name: gate-mask + type: u32 + - + name: interval + type: u32 + - + name: tc-taprio-tc-entry-attrs + attributes: + - + name: index + type: u32 + - + name: max-sdu + type: u32 + - + name: fp + type: u32 + - + name: tc-tbf-attrs + attributes: + - + name: parms + type: binary + struct: tc-tbf-qopt + - + name: rtab + type: binary + - + name: ptab + type: binary + - + name: rate64 + type: u64 + - + name: prate4 + type: u64 + - + name: burst + type: u32 + - + name: pburst + type: u32 + - + name: pad + type: pad + - + name: tca-gact-attrs + attributes: + - + name: tm + type: binary + - + name: parms + type: binary + - + name: prob + type: binary + - + name: pad + type: pad + - + name: tca-stab-attrs + attributes: + - + name: base + type: binary + struct: tc-sizespec + - + name: data + type: binary + - + name: tca-stats-attrs + attributes: + - + name: basic + type: binary + - + name: rate-est + type: binary + - + name: queue + type: binary + - + name: app + type: binary # TODO sub-message needs 2+ level deep lookup + sub-message: tca-stats-app-msg + selector: kind + - + name: rate-est64 + type: binary + - + name: pad + type: pad + - + name: basic-hw + type: binary + - + name: pkt64 + type: binary + +sub-messages: + - + name: tc-options-msg + formats: + - + value: bfifo + fixed-header: tc-fifo-qopt + - + value: cake + attribute-set: tc-cake-attrs + - + value: cbs + attribute-set: tc-cbs-attrs + - + value: choke + attribute-set: tc-choke-attrs + - + value: clsact # no content + - + value: codel + attribute-set: tc-codel-attrs + - + value: drr + attribute-set: tc-drr-attrs + - + value: etf + attribute-set: tc-etf-attrs + - + value: ets + attribute-set: tc-ets-attrs + - + value: fq + attribute-set: tc-fq-attrs + - + value: fq_codel + attribute-set: tc-fq-codel-attrs + - + value: fq_pie + attribute-set: tc-fq-pie-attrs + - + value: flower + attribute-set: tc-flower-attrs + - + value: gred + attribute-set: tc-gred-attrs + - + value: hfsc + fixed-header: tc-hfsc-qopt + - + value: hhf + attribute-set: tc-hhf-attrs + - + value: htb + attribute-set: tc-htb-attrs + - + value: ingress # no content + - + value: mq # no content + - + value: mqprio + fixed-header: tc-mqprio-qopt + - + value: multiq + fixed-header: tc-multiq-qopt + - + value: netem + fixed-header: tc-netem-qopt + attribute-set: tc-netem-attrs + - + value: pfifo + fixed-header: tc-fifo-qopt + - + value: pfifo_fast + fixed-header: tc-prio-qopt + - + value: pfifo_head_drop + fixed-header: tc-fifo-qopt + - + value: pie + attribute-set: tc-pie-attrs + - + value: plug + fixed-header: tc-plug-qopt + - + value: prio + fixed-header: tc-prio-qopt + - + value: qfq + attribute-set: tc-qfq-attrs + - + value: red + attribute-set: tc-red-attrs + - + value: sfb + fixed-header: tc-sfb-qopt + - + value: sfq + fixed-header: tc-sfq-qopt-v1 + - + value: taprio + attribute-set: tc-taprio-attrs + - + value: tbf + attribute-set: tc-tbf-attrs + - + name: tc-act-options-msg + formats: + - + value: gact + attribute-set: tca-gact-attrs + - + name: tca-stats-app-msg + formats: + - + value: bfifo + - + value: blackhole + - + value: cake + attribute-set: tc-cake-stats-attrs + - + value: cbs + - + value: choke + - + value: clsact + - + value: codel + - + value: drr + - + value: etf + - + value: ets + - + value: fq + - + value: fq_codel + - + value: fq_pie + - + value: flower + - + value: gred + - + value: hfsc + - + value: hhf + - + value: htb + - + value: ingress + - + value: mq + - + value: mqprio + - + value: multiq + - + value: netem + - + value: noqueue + - + value: pfifo + - + value: pfifo_fast + - + value: pfifo_head_drop + - + value: pie + - + value: plug + - + value: prio + - + value: qfq + - + value: red + - + value: sfb + - + value: sfq + - + value: taprio + - + value: tbf + +operations: + enum-model: directional + list: + - + name: newqdisc + doc: Create new tc qdisc. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 36 + attributes: &create-params + - kind + - options + - rate + - chain + - ingress-block + - egress-block + - + name: delqdisc + doc: Delete existing tc qdisc. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 37 + - + name: getqdisc + doc: Get / dump tc qdisc information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 38 + attributes: + - dump-invisible + reply: + value: 36 + attributes: &tc-all + - kind + - options + - stats + - xstats + - rate + - fcnt + - stats2 + - stab + - chain + - ingress-block + - egress-block + - + name: newtclass + doc: Get / dump tc traffic class information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 40 + attributes: *create-params + - + name: deltclass + doc: Get / dump tc traffic class information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 41 + - + name: gettclass + doc: Get / dump tc traffic class information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 42 + reply: + value: 40 + attributes: *tc-all + - + name: newtfilter + doc: Get / dump tc filter information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 44 + attributes: *create-params + - + name: deltfilter + doc: Get / dump tc filter information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 45 + attributes: + - chain + - kind + - + name: gettfilter + doc: Get / dump tc filter information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 46 + attributes: + - chain + - kind + reply: + value: 44 + attributes: *tc-all + dump: + request: + value: 46 + attributes: + - chain + - dump-flags + reply: + value: 44 + attributes: *tc-all + - + name: newchain + doc: Get / dump tc chain information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 100 + attributes: *create-params + - + name: delchain + doc: Get / dump tc chain information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 101 + attributes: + - chain + - + name: getchain + doc: Get / dump tc chain information. + attribute-set: tc-attrs + fixed-header: tcmsg + do: + request: + value: 102 + attributes: + - chain + reply: + value: 100 + attributes: *tc-all + +mcast-groups: + list: + - + name: rtnlgrp-tc + value: 4 diff --git a/Documentation/networking/bridge.rst b/Documentation/networking/bridge.rst index c859f3c1636e..ba14e7b07869 100644 --- a/Documentation/networking/bridge.rst +++ b/Documentation/networking/bridge.rst @@ -4,18 +4,332 @@ Ethernet Bridging ================= -In order to use the Ethernet bridging functionality, you'll need the -userspace tools. +Introduction +============ -Documentation for Linux bridging is on: - https://wiki.linuxfoundation.org/networking/bridge +The IEEE 802.1Q-2022 (Bridges and Bridged Networks) standard defines the +operation of bridges in computer networks. A bridge, in the context of this +standard, is a device that connects two or more network segments and operates +at the data link layer (Layer 2) of the OSI (Open Systems Interconnection) +model. The purpose of a bridge is to filter and forward frames between +different segments based on the destination MAC (Media Access Control) address. -The bridge-utilities are maintained at: - git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git +Bridge kAPI +=========== -Additionally, the iproute2 utilities can be used to configure -bridge devices. +Here are some core structures of bridge code. Note that the kAPI is *unstable*, +and can be changed at any time. -If you still have questions, don't hesitate to post to the mailing list -(more info https://lists.linux-foundation.org/mailman/listinfo/bridge). +.. kernel-doc:: net/bridge/br_private.h + :identifiers: net_bridge_vlan +Bridge uAPI +=========== + +Modern Linux bridge uAPI is accessed via Netlink interface. You can find +below files where the bridge and bridge port netlink attributes are defined. + +Bridge netlink attributes +------------------------- + +.. kernel-doc:: include/uapi/linux/if_link.h + :doc: Bridge enum definition + +Bridge port netlink attributes +------------------------------ + +.. kernel-doc:: include/uapi/linux/if_link.h + :doc: Bridge port enum definition + +Bridge sysfs +------------ + +The sysfs interface is deprecated and should not be extended if new +options are added. + +STP +=== + +The STP (Spanning Tree Protocol) implementation in the Linux bridge driver +is a critical feature that helps prevent loops and broadcast storms in +Ethernet networks by identifying and disabling redundant links. In a Linux +bridge context, STP is crucial for network stability and availability. + +STP is a Layer 2 protocol that operates at the Data Link Layer of the OSI +model. It was originally developed as IEEE 802.1D and has since evolved into +multiple versions, including Rapid Spanning Tree Protocol (RSTP) and +`Multiple Spanning Tree Protocol (MSTP) +<https://lore.kernel.org/netdev/20220316150857.2442916-1-tobias@waldekranz.com/>`_. + +The 802.1D-2004 removed the original Spanning Tree Protocol, instead +incorporating the Rapid Spanning Tree Protocol (RSTP). By 2014, all the +functionality defined by IEEE 802.1D has been incorporated into either +IEEE 802.1Q (Bridges and Bridged Networks) or IEEE 802.1AC (MAC Service +Definition). 802.1D has been officially withdrawn in 2022. + +Bridge Ports and STP States +--------------------------- + +In the context of STP, bridge ports can be in one of the following states: + * Blocking: The port is disabled for data traffic and only listens for + BPDUs (Bridge Protocol Data Units) from other devices to determine the + network topology. + * Listening: The port begins to participate in the STP process and listens + for BPDUs. + * Learning: The port continues to listen for BPDUs and begins to learn MAC + addresses from incoming frames but does not forward data frames. + * Forwarding: The port is fully operational and forwards both BPDUs and + data frames. + * Disabled: The port is administratively disabled and does not participate + in the STP process. The data frames forwarding are also disabled. + +Root Bridge and Convergence +--------------------------- + +In the context of networking and Ethernet bridging in Linux, the root bridge +is a designated switch in a bridged network that serves as a reference point +for the spanning tree algorithm to create a loop-free topology. + +Here's how the STP works and root bridge is chosen: + 1. Bridge Priority: Each bridge running a spanning tree protocol, has a + configurable Bridge Priority value. The lower the value, the higher the + priority. By default, the Bridge Priority is set to a standard value + (e.g., 32768). + 2. Bridge ID: The Bridge ID is composed of two components: Bridge Priority + and the MAC address of the bridge. It uniquely identifies each bridge + in the network. The Bridge ID is used to compare the priorities of + different bridges. + 3. Bridge Election: When the network starts, all bridges initially assume + that they are the root bridge. They start advertising Bridge Protocol + Data Units (BPDU) to their neighbors, containing their Bridge ID and + other information. + 4. BPDU Comparison: Bridges exchange BPDUs to determine the root bridge. + Each bridge examines the received BPDUs, including the Bridge Priority + and Bridge ID, to determine if it should adjust its own priorities. + The bridge with the lowest Bridge ID will become the root bridge. + 5. Root Bridge Announcement: Once the root bridge is determined, it sends + BPDUs with information about the root bridge to all other bridges in the + network. This information is used by other bridges to calculate the + shortest path to the root bridge and, in doing so, create a loop-free + topology. + 6. Forwarding Ports: After the root bridge is selected and the spanning tree + topology is established, each bridge determines which of its ports should + be in the forwarding state (used for data traffic) and which should be in + the blocking state (used to prevent loops). The root bridge's ports are + all in the forwarding state. while other bridges have some ports in the + blocking state to avoid loops. + 7. Root Ports: After the root bridge is selected and the spanning tree + topology is established, each non-root bridge processes incoming + BPDUs and determines which of its ports provides the shortest path to the + root bridge based on the information in the received BPDUs. This port is + designated as the root port. And it is in the Forwarding state, allowing + it to actively forward network traffic. + 8. Designated ports: A designated port is the port through which the non-root + bridge will forward traffic towards the designated segment. Designated ports + are placed in the Forwarding state. All other ports on the non-root + bridge that are not designated for specific segments are placed in the + Blocking state to prevent network loops. + +STP ensures network convergence by calculating the shortest path and disabling +redundant links. When network topology changes occur (e.g., a link failure), +STP recalculates the network topology to restore connectivity while avoiding loops. + +Proper configuration of STP parameters, such as the bridge priority, can +influence network performance, path selection and which bridge becomes the +Root Bridge. + +User space STP helper +--------------------- + +The user space STP helper *bridge-stp* is a program to control whether to use +user mode spanning tree. The ``/sbin/bridge-stp <bridge> <start|stop>`` is +called by the kernel when STP is enabled/disabled on a bridge +(via ``brctl stp <bridge> <on|off>`` or ``ip link set <bridge> type bridge +stp_state <0|1>``). The kernel enables user_stp mode if that command returns +0, or enables kernel_stp mode if that command returns any other value. + +VLAN +==== + +A LAN (Local Area Network) is a network that covers a small geographic area, +typically within a single building or a campus. LANs are used to connect +computers, servers, printers, and other networked devices within a localized +area. LANs can be wired (using Ethernet cables) or wireless (using Wi-Fi). + +A VLAN (Virtual Local Area Network) is a logical segmentation of a physical +network into multiple isolated broadcast domains. VLANs are used to divide +a single physical LAN into multiple virtual LANs, allowing different groups of +devices to communicate as if they were on separate physical networks. + +Typically there are two VLAN implementations, IEEE 802.1Q and IEEE 802.1ad +(also known as QinQ). IEEE 802.1Q is a standard for VLAN tagging in Ethernet +networks. It allows network administrators to create logical VLANs on a +physical network and tag Ethernet frames with VLAN information, which is +called *VLAN-tagged frames*. IEEE 802.1ad, commonly known as QinQ or Double +VLAN, is an extension of the IEEE 802.1Q standard. QinQ allows for the +stacking of multiple VLAN tags within a single Ethernet frame. The Linux +bridge supports both the IEEE 802.1Q and `802.1AD +<https://lore.kernel.org/netdev/1402401565-15423-1-git-send-email-makita.toshiaki@lab.ntt.co.jp/>`_ +protocol for VLAN tagging. + +`VLAN filtering <https://lore.kernel.org/netdev/1360792820-14116-1-git-send-email-vyasevic@redhat.com/>`_ +on a bridge is disabled by default. After enabling VLAN filtering on a bridge, +it will start forwarding frames to appropriate destinations based on their +destination MAC address and VLAN tag (both must match). + +Multicast +========= + +The Linux bridge driver has multicast support allowing it to process Internet +Group Management Protocol (IGMP) or Multicast Listener Discovery (MLD) +messages, and to efficiently forward multicast data packets. The bridge +driver supports IGMPv2/IGMPv3 and MLDv1/MLDv2. + +Multicast snooping +------------------ + +Multicast snooping is a networking technology that allows network switches +to intelligently manage multicast traffic within a local area network (LAN). + +The switch maintains a multicast group table, which records the association +between multicast group addresses and the ports where hosts have joined these +groups. The group table is dynamically updated based on the IGMP/MLD messages +received. With the multicast group information gathered through snooping, the +switch optimizes the forwarding of multicast traffic. Instead of blindly +broadcasting the multicast traffic to all ports, it sends the multicast +traffic based on the destination MAC address only to ports which have +subscribed the respective destination multicast group. + +When created, the Linux bridge devices have multicast snooping enabled by +default. It maintains a Multicast forwarding database (MDB) which keeps track +of port and group relationships. + +IGMPv3/MLDv2 EHT support +------------------------ + +The Linux bridge supports IGMPv3/MLDv2 EHT (Explicit Host Tracking), which +was added by `474ddb37fa3a ("net: bridge: multicast: add EHT allow/block handling") +<https://lore.kernel.org/netdev/20210120145203.1109140-1-razor@blackwall.org/>`_ + +The explicit host tracking enables the device to keep track of each +individual host that is joined to a particular group or channel. The main +benefit of the explicit host tracking in IGMP is to allow minimal leave +latencies when a host leaves a multicast group or channel. + +The length of time between a host wanting to leave and a device stopping +traffic forwarding is called the IGMP leave latency. A device configured +with IGMPv3 or MLDv2 and explicit tracking can immediately stop forwarding +traffic if the last host to request to receive traffic from the device +indicates that it no longer wants to receive traffic. The leave latency +is thus bound only by the packet transmission latencies in the multiaccess +network and the processing time in the device. + +Other multicast features +------------------------ + +The Linux bridge also supports `per-VLAN multicast snooping +<https://lore.kernel.org/netdev/20210719170637.435541-1-razor@blackwall.org/>`_, +which is disabled by default but can be enabled. And `Multicast Router Discovery +<https://lore.kernel.org/netdev/20190121062628.2710-1-linus.luessing@c0d3.blue/>`_, +which help identify the location of multicast routers. + +Switchdev +========= + +Linux Bridge Switchdev is a feature in the Linux kernel that extends the +capabilities of the traditional Linux bridge to work more efficiently with +hardware switches that support switchdev. With Linux Bridge Switchdev, certain +networking functions like forwarding, filtering, and learning of Ethernet +frames can be offloaded to a hardware switch. This offloading reduces the +burden on the Linux kernel and CPU, leading to improved network performance +and lower latency. + +To use Linux Bridge Switchdev, you need hardware switches that support the +switchdev interface. This means that the switch hardware needs to have the +necessary drivers and functionality to work in conjunction with the Linux +kernel. + +Please see the :ref:`switchdev` document for more details. + +Netfilter +========= + +The bridge netfilter module is a legacy feature that allows to filter bridged +packets with iptables and ip6tables. Its use is discouraged. Users should +consider using nftables for packet filtering. + +The older ebtables tool is more feature-limited compared to nftables, but +just like nftables it doesn't need this module either to function. + +The br_netfilter module intercepts packets entering the bridge, performs +minimal sanity tests on ipv4 and ipv6 packets and then pretends that +these packets are being routed, not bridged. br_netfilter then calls +the ip and ipv6 netfilter hooks from the bridge layer, i.e. ip(6)tables +rulesets will also see these packets. + +br_netfilter is also the reason for the iptables *physdev* match: +This match is the only way to reliably tell routed and bridged packets +apart in an iptables ruleset. + +Note that ebtables and nftables will work fine without the br_netfilter module. +iptables/ip6tables/arptables do not work for bridged traffic because they +plug in the routing stack. nftables rules in ip/ip6/inet/arp families won't +see traffic that is forwarded by a bridge either, but that's very much how it +should be. + +Historically the feature set of ebtables was very limited (it still is), +this module was added to pretend packets are routed and invoke the ipv4/ipv6 +netfilter hooks from the bridge so users had access to the more feature-rich +iptables matching capabilities (including conntrack). nftables doesn't have +this limitation, pretty much all features work regardless of the protocol family. + +So, br_netfilter is only needed if users, for some reason, need to use +ip(6)tables to filter packets forwarded by the bridge, or NAT bridged +traffic. For pure link layer filtering, this module isn't needed. + +Other Features +============== + +The Linux bridge also supports `IEEE 802.11 Proxy ARP +<https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=958501163ddd6ea22a98f94fa0e7ce6d4734e5c4>`_, +`Media Redundancy Protocol (MRP) +<https://lore.kernel.org/netdev/20200426132208.3232-1-horatiu.vultur@microchip.com/>`_, +`Media Redundancy Protocol (MRP) LC mode +<https://lore.kernel.org/r/20201124082525.273820-1-horatiu.vultur@microchip.com>`_, +`IEEE 802.1X port authentication +<https://lore.kernel.org/netdev/20220218155148.2329797-1-schultz.hans+netdev@gmail.com/>`_, +and `MAC Authentication Bypass (MAB) +<https://lore.kernel.org/netdev/20221101193922.2125323-2-idosch@nvidia.com/>`_. + +FAQ +=== + +What does a bridge do? +---------------------- + +A bridge transparently forwards traffic between multiple network interfaces. +In plain English this means that a bridge connects two or more physical +Ethernet networks, to form one larger (logical) Ethernet network. + +Is it L3 protocol independent? +------------------------------ + +Yes. The bridge sees all frames, but it *uses* only L2 headers/information. +As such, the bridging functionality is protocol independent, and there should +be no trouble forwarding IPX, NetBEUI, IP, IPv6, etc. + +Contact Info +============ + +The code is currently maintained by Roopa Prabhu <roopa@nvidia.com> and +Nikolay Aleksandrov <razor@blackwall.org>. Bridge bugs and enhancements +are discussed on the linux-netdev mailing list netdev@vger.kernel.org and +bridge@lists.linux-foundation.org. + +The list is open to anyone interested: http://vger.kernel.org/vger-lists.html#netdev + +External Links +============== + +The old Documentation for Linux bridging is on: +https://wiki.linuxfoundation.org/networking/bridge diff --git a/Documentation/networking/device_drivers/ethernet/intel/ice.rst b/Documentation/networking/device_drivers/ethernet/intel/ice.rst index e4d065c55ea8..5038e54586af 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/ice.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/ice.rst @@ -895,6 +895,147 @@ driver writes raw bytes by the GNSS object to the receiver through i2c. Please refer to the hardware GNSS module documentation for configuration details. +Firmware (FW) logging +--------------------- +The driver supports FW logging via the debugfs interface on PF 0 only. The FW +running on the NIC must support FW logging; if the FW doesn't support FW logging +the 'fwlog' file will not get created in the ice debugfs directory. + +Module configuration +~~~~~~~~~~~~~~~~~~~~ +Firmware logging is configured on a per module basis. Each module can be set to +a value independent of the other modules (unless the module 'all' is specified). +The modules will be instantiated under the 'fwlog/modules' directory. + +The user can set the log level for a module by writing to the module file like +this:: + + # echo <log_level> > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/<module> + +where + +* log_level is a name as described below. Each level includes the + messages from the previous/lower level + + * none + * error + * warning + * normal + * verbose + +* module is a name that represents the module to receive events for. The + module names are + + * general + * ctrl + * link + * link_topo + * dnl + * i2c + * sdp + * mdio + * adminq + * hdma + * lldp + * dcbx + * dcb + * xlr + * nvm + * auth + * vpd + * iosf + * parser + * sw + * scheduler + * txq + * rsvd + * post + * watchdog + * task_dispatch + * mng + * synce + * health + * tsdrv + * pfreg + * mdlver + * all + +The name 'all' is special and allows the user to set all of the modules to the +specified log_level or to read the log_level of all of the modules. + +Example usage to configure the modules +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +To set a single module to 'verbose':: + + # echo verbose > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/link + +To set multiple modules then issue the command multiple times:: + + # echo verbose > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/link + # echo warning > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/ctrl + # echo none > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/dcb + +To set all the modules to the same value:: + + # echo normal > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/all + +To read the log_level of a specific module (e.g. module 'general'):: + + # cat /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/general + +To read the log_level of all the modules:: + + # cat /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/modules/all + +Enabling FW log +~~~~~~~~~~~~~~~ +Configuring the modules indicates to the FW that the configured modules should +generate events that the driver is interested in, but it **does not** send the +events to the driver until the enable message is sent to the FW. To do this +the user can write a 1 (enable) or 0 (disable) to 'fwlog/enable'. An example +is:: + + # echo 1 > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/enable + +Retrieving FW log data +~~~~~~~~~~~~~~~~~~~~~~ +The FW log data can be retrieved by reading from 'fwlog/data'. The user can +write any value to 'fwlog/data' to clear the data. The data can only be cleared +when FW logging is disabled. The FW log data is a binary file that is sent to +Intel and used to help debug user issues. + +An example to read the data is:: + + # cat /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/data > fwlog.bin + +An example to clear the data is:: + + # echo 0 > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/data + +Changing how often the log events are sent to the driver +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +The driver receives FW log data from the Admin Receive Queue (ARQ). The +frequency that the FW sends the ARQ events can be configured by writing to +'fwlog/nr_messages'. The range is 1-128 (1 means push every log message, 128 +means push only when the max AQ command buffer is full). The suggested value is +10. The user can see what the value is configured to by reading +'fwlog/nr_messages'. An example to set the value is:: + + # echo 50 > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/nr_messages + +Configuring the amount of memory used to store FW log data +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ +The driver stores FW log data within the driver. The default size of the memory +used to store the data is 1MB. Some use cases may require more or less data so +the user can change the amount of memory that is allocated for FW log data. +To change the amount of memory then write to 'fwlog/log_size'. The value must be +one of: 128K, 256K, 512K, 1M, or 2M. FW logging must be disabled to change the +value. An example of changing the value is:: + + # echo 128K > /sys/kernel/debug/ice/0000\:18\:00.0/fwlog/log_size + + Performance Optimization ======================== Driver defaults are meant to fit a wide variety of workloads, but if further diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index 2f60e34ab926..7f30ebd5debb 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -38,6 +38,10 @@ The ``ice`` driver reports the following versions - fixed - K65390-000 - The Product Board Assembly (PBA) identifier of the board. + * - ``cgu.id`` + - fixed + - 36 + - The Clock Generation Unit (CGU) hardware revision identifier. * - ``fw.mgmt`` - running - 2.1.7 @@ -104,6 +108,11 @@ The ``ice`` driver reports the following versions - running - 0xee16ced7 - The first 4 bytes of the hash of the netlist module contents. + * - ``fw.cgu`` + - running + - 8032.16973825.6021 + - The version of Clock Generation Unit (CGU). Format: + <CGU type>.<configuration version>.<firmware version>. Flash Update ============ diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index 2540c70952ff..d583d9abf2f8 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -223,6 +223,9 @@ Userspace to kernel: ``ETHTOOL_MSG_PSE_SET`` set PSE parameters ``ETHTOOL_MSG_PSE_GET`` get PSE parameters ``ETHTOOL_MSG_RSS_GET`` get RSS settings + ``ETHTOOL_MSG_PLCA_GET_CFG`` get PLCA RS parameters + ``ETHTOOL_MSG_PLCA_SET_CFG`` set PLCA RS parameters + ``ETHTOOL_MSG_PLCA_GET_STATUS`` get PLCA RS status ``ETHTOOL_MSG_MM_GET`` get MAC merge layer state ``ETHTOOL_MSG_MM_SET`` set MAC merge layer parameters ===================================== ================================= @@ -267,6 +270,9 @@ Kernel to userspace: ``ETHTOOL_MSG_MODULE_GET_REPLY`` transceiver module parameters ``ETHTOOL_MSG_PSE_GET_REPLY`` PSE parameters ``ETHTOOL_MSG_RSS_GET_REPLY`` RSS settings + ``ETHTOOL_MSG_PLCA_GET_CFG_REPLY`` PLCA RS parameters + ``ETHTOOL_MSG_PLCA_GET_STATUS_REPLY`` PLCA RS status + ``ETHTOOL_MSG_PLCA_NTF`` PLCA RS parameters ``ETHTOOL_MSG_MM_GET_REPLY`` MAC merge layer status ======================================== ================================= @@ -1768,12 +1774,16 @@ Kernel response contents: ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes + ``ETHTOOL_A_RSS_INPUT_XFRM`` u32 RSS input data transformation ===================================== ====== ========================== ETHTOOL_A_RSS_HFUNC attribute is bitmap indicating the hash function being used. Current supported options are toeplitz, xor or crc32. -ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte +ETHTOOL_A_RSS_INDIR attribute returns RSS indirection table where each byte indicates queue number. +ETHTOOL_A_RSS_INPUT_XFRM attribute is a bitmap indicating the type of +transformation applied to the input protocol fields before given to the RSS +hfunc. Current supported option is symmetric-xor. PLCA_GET_CFG ============ diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index d9424dcb19bf..69f3d6dcd9fd 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -75,6 +75,7 @@ Contents: mptcp-sysctl multiqueue napi + net_cachelines/index netconsole netdev-features netdevices diff --git a/Documentation/networking/net_cachelines/index.rst b/Documentation/networking/net_cachelines/index.rst new file mode 100644 index 000000000000..2669e4cda086 --- /dev/null +++ b/Documentation/networking/net_cachelines/index.rst @@ -0,0 +1,16 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +=================================== +Common Networking Struct Cachelines +=================================== + +.. toctree:: + :maxdepth: 1 + + inet_connection_sock + inet_sock + net_device + netns_ipv4_sysctl + snmp + tcp_sock diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst new file mode 100644 index 000000000000..7a911dc95652 --- /dev/null +++ b/Documentation/networking/net_cachelines/inet_connection_sock.rst @@ -0,0 +1,50 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +===================================================== +inet_connection_sock struct fast path usage breakdown +===================================================== + +Type Name fastpath_tx_access fastpath_rx_access comment +..struct ..inet_connection_sock +struct_inet_sock icsk_inet read_mostly read_mostly tcp_init_buffer_space,tcp_init_transfer,tcp_finish_connect,tcp_connect,tcp_send_rcvq,tcp_send_syn_data +struct_request_sock_queue icsk_accept_queue - - +struct_inet_bind_bucket icsk_bind_hash read_mostly - tcp_set_state +struct_inet_bind2_bucket icsk_bind2_hash read_mostly - tcp_set_state,inet_put_port +unsigned_long icsk_timeout read_mostly - inet_csk_reset_xmit_timer,tcp_connect +struct_timer_list icsk_retransmit_timer read_mostly - inet_csk_reset_xmit_timer,tcp_connect +struct_timer_list icsk_delack_timer read_mostly - inet_csk_reset_xmit_timer,tcp_connect +u32 icsk_rto read_write - tcp_cwnd_validate,tcp_schedule_loss_probe,tcp_connect_init,tcp_connect,tcp_write_xmit,tcp_push_one +u32 icsk_rto_min - - +u32 icsk_delack_max - - +u32 icsk_pmtu_cookie read_write - tcp_sync_mss,tcp_current_mss,tcp_send_syn_data,tcp_connect_init,tcp_connect +struct_tcp_congestion_ops icsk_ca_ops read_write - tcp_cwnd_validate,tcp_tso_segs,tcp_ca_dst_init,tcp_connect_init,tcp_connect,tcp_write_xmit +struct_inet_connection_sock_af_ops icsk_af_ops read_mostly - tcp_finish_connect,tcp_send_syn_data,tcp_mtup_init,tcp_mtu_check_reprobe,tcp_mtu_probe,tcp_connect_init,tcp_connect,__tcp_transmit_skb +struct_tcp_ulp_ops* icsk_ulp_ops - - +void* icsk_ulp_data - - +u8:5 icsk_ca_state read_write - tcp_cwnd_application_limited,tcp_set_ca_state,tcp_enter_cwr,tcp_tso_should_defer,tcp_mtu_probe,tcp_schedule_loss_probe,tcp_write_xmit,__tcp_transmit_skb +u8:1 icsk_ca_initialized read_write - tcp_init_transfer,tcp_init_congestion_control,tcp_init_transfer,tcp_finish_connect,tcp_connect +u8:1 icsk_ca_setsockopt - - +u8:1 icsk_ca_dst_locked write_mostly - tcp_ca_dst_init,tcp_connect_init,tcp_connect +u8 icsk_retransmits write_mostly - tcp_connect_init,tcp_connect +u8 icsk_pending read_write - inet_csk_reset_xmit_timer,tcp_connect,tcp_check_probe_timer,__tcp_push_pending_frames,tcp_rearm_rto,tcp_event_new_data_sent,tcp_event_new_data_sent +u8 icsk_backoff write_mostly - tcp_write_queue_purge,tcp_connect_init +u8 icsk_syn_retries - - +u8 icsk_probes_out - - +u16 icsk_ext_hdr_len read_mostly - __tcp_mtu_to_mss,tcp_mtu_to_rss,tcp_mtu_probe,tcp_write_xmit,tcp_mtu_to_mss, +struct_icsk_ack_u8 pending read_write read_write inet_csk_ack_scheduled,__tcp_cleanup_rbuf,tcp_cleanup_rbuf,inet_csk_clear_xmit_timer,tcp_event_ack-sent,inet_csk_reset_xmit_timer +struct_icsk_ack_u8 quick read_write write_mostly tcp_dec_quickack_mode,tcp_event_ack_sent,__tcp_transmit_skb,__tcp_select_window,__tcp_cleanup_rbuf +struct_icsk_ack_u8 pingpong - - +struct_icsk_ack_u8 retry write_mostly read_write inet_csk_clear_xmit_timer,tcp_rearm_rto,tcp_event_new_data_sent,tcp_write_xmit,__tcp_send_ack,tcp_send_ack, +struct_icsk_ack_u8 ato read_mostly write_mostly tcp_dec_quickack_mode,tcp_event_ack_sent,__tcp_transmit_skb,__tcp_send_ack,tcp_send_ack +struct_icsk_ack_unsigned_long timeout read_write read_write inet_csk_reset_xmit_timer,tcp_connect +struct_icsk_ack_u32 lrcvtime read_write - tcp_finish_connect,tcp_connect,tcp_event_data_sent,__tcp_transmit_skb +struct_icsk_ack_u16 rcv_mss write_mostly read_mostly __tcp_select_window,__tcp_cleanup_rbuf,tcp_initialize_rcv_mss,tcp_connect_init +struct_icsk_mtup_int search_high read_write - tcp_mtup_init,tcp_sync_mss,tcp_connect_init,tcp_mtu_check_reprobe,tcp_write_xmit +struct_icsk_mtup_int search_low read_write - tcp_mtu_probe,tcp_mtu_check_reprobe,tcp_write_xmit,tcp_sync_mss,tcp_connect_init,tcp_mtup_init +struct_icsk_mtup_u32:31 probe_size read_write - tcp_mtup_init,tcp_connect_init,__tcp_transmit_skb +struct_icsk_mtup_u32:1 enabled read_write - tcp_mtup_init,tcp_sync_mss,tcp_connect_init,tcp_mtu_probe,tcp_write_xmit +struct_icsk_mtup_u32 probe_timestamp read_write - tcp_mtup_init,tcp_connect_init,tcp_mtu_check_reprobe,tcp_mtu_probe +u32 icsk_probes_tstamp - - +u32 icsk_user_timeout - - +u64[104/sizeof(u64)] icsk_ca_priv - - diff --git a/Documentation/networking/net_cachelines/inet_sock.rst b/Documentation/networking/net_cachelines/inet_sock.rst new file mode 100644 index 000000000000..a2babd0d7954 --- /dev/null +++ b/Documentation/networking/net_cachelines/inet_sock.rst @@ -0,0 +1,44 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +===================================================== +inet_connection_sock struct fast path usage breakdown +===================================================== + +Type Name fastpath_tx_access fastpath_rx_access comment +..struct ..inet_sock +struct_sock sk read_mostly read_mostly tcp_init_buffer_space,tcp_init_transfer,tcp_finish_connect,tcp_connect,tcp_send_rcvq,tcp_send_syn_data +struct_ipv6_pinfo* pinet6 - - +be16 inet_sport read_mostly - __tcp_transmit_skb +be32 inet_daddr read_mostly - ip_select_ident_segs +be32 inet_rcv_saddr - - +be16 inet_dport read_mostly - __tcp_transmit_skb +u16 inet_num - - +be32 inet_saddr - - +s16 uc_ttl read_mostly - __ip_queue_xmit/ip_select_ttl +u16 cmsg_flags - - +struct_ip_options_rcu* inet_opt read_mostly - __ip_queue_xmit +u16 inet_id read_mostly - ip_select_ident_segs +u8 tos read_mostly - ip_queue_xmit +u8 min_ttl - - +u8 mc_ttl - - +u8 pmtudisc - - +u8:1 recverr - - +u8:1 is_icsk - - +u8:1 freebind - - +u8:1 hdrincl - - +u8:1 mc_loop - - +u8:1 transparent - - +u8:1 mc_all - - +u8:1 nodefrag - - +u8:1 bind_address_no_port - - +u8:1 recverr_rfc4884 - - +u8:1 defer_connect read_mostly - tcp_sendmsg_fastopen +u8 rcv_tos - - +u8 convert_csum - - +int uc_index - - +int mc_index - - +be32 mc_addr - - +struct_ip_mc_socklist* mc_list - - +struct_inet_cork_full cork read_mostly - __tcp_transmit_skb +struct local_port_range - - diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst new file mode 100644 index 000000000000..6cab1b797739 --- /dev/null +++ b/Documentation/networking/net_cachelines/net_device.rst @@ -0,0 +1,178 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +=========================================== +net_device struct fast path usage breakdown +=========================================== + +Type Name fastpath_tx_access fastpath_rx_access Comments +..struct ..net_device +char name[16] - - +struct_netdev_name_node* name_node +struct_dev_ifalias* ifalias +unsigned_long mem_end +unsigned_long mem_start +unsigned_long base_addr +unsigned_long state +struct_list_head dev_list +struct_list_head napi_list +struct_list_head unreg_list +struct_list_head close_list +struct_list_head ptype_all read_mostly - dev_nit_active(tx) +struct_list_head ptype_specific read_mostly deliver_ptype_list_skb/__netif_receive_skb_core(rx) +struct adj_list +unsigned_int flags read_mostly read_mostly __dev_queue_xmit,__dev_xmit_skb,ip6_output,__ip6_finish_output(tx);ip6_rcv_core(rx) +xdp_features_t xdp_features +unsigned_long_long priv_flags read_mostly - __dev_queue_xmit(tx) +struct_net_device_ops* netdev_ops read_mostly - netdev_core_pick_tx,netdev_start_xmit(tx) +struct_xdp_metadata_ops* xdp_metadata_ops +int ifindex - read_mostly ip6_rcv_core +unsigned_short gflags +unsigned_short hard_header_len read_mostly read_mostly ip6_xmit(tx);gro_list_prepare(rx) +unsigned_int mtu read_mostly - ip_finish_output2 +unsigned_short needed_headroom read_mostly - LL_RESERVED_SPACE/ip_finish_output2 +unsigned_short needed_tailroom +netdev_features_t features read_mostly read_mostly HARD_TX_LOCK,netif_skb_features,sk_setup_caps(tx);netif_elide_gro(rx) +netdev_features_t hw_features +netdev_features_t wanted_features +netdev_features_t vlan_features +netdev_features_t hw_enc_features - - netif_skb_features +netdev_features_t mpls_features +netdev_features_t gso_partial_features +unsigned_int min_mtu +unsigned_int max_mtu +unsigned_short type +unsigned_char min_header_len +unsigned_char name_assign_type +int group +struct_net_device_stats stats +struct_net_device_core_stats* core_stats +atomic_t carrier_up_count +atomic_t carrier_down_count +struct_iw_handler_def* wireless_handlers +struct_iw_public_data* wireless_data +struct_ethtool_ops* ethtool_ops +struct_l3mdev_ops* l3mdev_ops +struct_ndisc_ops* ndisc_ops +struct_xfrmdev_ops* xfrmdev_ops +struct_tlsdev_ops* tlsdev_ops +struct_header_ops* header_ops read_mostly - ip_finish_output2,ip6_finish_output2(tx) +unsigned_char operstate +unsigned_char link_mode +unsigned_char if_port +unsigned_char dma +unsigned_char perm_addr[32] +unsigned_char addr_assign_type +unsigned_char addr_len +unsigned_char upper_level +unsigned_char lower_level +unsigned_short neigh_priv_len +unsigned_short padded +unsigned_short dev_id +unsigned_short dev_port +spinlock_t addr_list_lock +int irq +struct_netdev_hw_addr_list uc +struct_netdev_hw_addr_list mc +struct_netdev_hw_addr_list dev_addrs +struct_kset* queues_kset +struct_list_head unlink_list +unsigned_int promiscuity +unsigned_int allmulti +bool uc_promisc +unsigned_char nested_level +struct_in_device* ip_ptr read_mostly read_mostly __in_dev_get +struct_inet6_dev* ip6_ptr read_mostly read_mostly __in6_dev_get +struct_vlan_info* vlan_info +struct_dsa_port* dsa_ptr +struct_tipc_bearer* tipc_ptr +void* atalk_ptr +void* ax25_ptr +struct_wireless_dev* ieee80211_ptr +struct_wpan_dev* ieee802154_ptr +struct_mpls_dev* mpls_ptr +struct_mctp_dev* mctp_ptr +unsigned_char* dev_addr +struct_netdev_queue* _rx read_mostly - netdev_get_rx_queue(rx) +unsigned_int num_rx_queues +unsigned_int real_num_rx_queues - read_mostly get_rps_cpu +struct_bpf_prog* xdp_prog +unsigned_long gro_flush_timeout - read_mostly napi_complete_done +int napi_defer_hard_irqs - read_mostly napi_complete_done +unsigned_int gro_max_size - read_mostly skb_gro_receive +unsigned_int gro_ipv4_max_size - read_mostly skb_gro_receive +rx_handler_func_t* rx_handler read_mostly - __netif_receive_skb_core +void* rx_handler_data read_mostly - +struct_netdev_queue* ingress_queue read_mostly - +struct_bpf_mprog_entry tcx_ingress - read_mostly sch_handle_ingress +struct_nf_hook_entries* nf_hooks_ingress +unsigned_char broadcast[32] +struct_cpu_rmap* rx_cpu_rmap +struct_hlist_node index_hlist +struct_netdev_queue* _tx read_mostly - netdev_get_tx_queue(tx) +unsigned_int num_tx_queues - - +unsigned_int real_num_tx_queues read_mostly - skb_tx_hash,netdev_core_pick_tx(tx) +unsigned_int tx_queue_len +spinlock_t tx_global_lock +struct_xdp_dev_bulk_queue__percpu* xdp_bulkq +struct_xps_dev_maps* xps_maps[2] read_mostly - __netif_set_xps_queue +struct_bpf_mprog_entry tcx_egress read_mostly - sch_handle_egress +struct_nf_hook_entries* nf_hooks_egress read_mostly - +struct_hlist_head qdisc_hash[16] +struct_timer_list watchdog_timer +int watchdog_timeo +u32 proto_down_reason +struct_list_head todo_list +int__percpu* pcpu_refcnt +refcount_t dev_refcnt +struct_ref_tracker_dir refcnt_tracker +struct_list_head link_watch_list +enum:8 reg_state +bool dismantle +enum:16 rtnl_link_state +bool needs_free_netdev +void*priv_destructor struct_net_device +struct_netpoll_info* npinfo - read_mostly napi_poll/napi_poll_lock +possible_net_t nd_net - read_mostly (dev_net)napi_busy_loop,tcp_v(4/6)_rcv,ip(v6)_rcv,ip(6)_input,ip(6)_input_finish +void* ml_priv +enum_netdev_ml_priv_type ml_priv_type +struct_pcpu_lstats__percpu* lstats +struct_pcpu_sw_netstats__percpu* tstats +struct_pcpu_dstats__percpu* dstats +struct_garp_port* garp_port +struct_mrp_port* mrp_port +struct_dm_hw_stat_delta* dm_private +struct_device dev - - +struct_attribute_group* sysfs_groups[4] +struct_attribute_group* sysfs_rx_queue_group +struct_rtnl_link_ops* rtnl_link_ops +unsigned_int gso_max_size read_mostly - sk_dst_gso_max_size +unsigned_int tso_max_size +u16 gso_max_segs read_mostly - gso_max_segs +u16 tso_max_segs +unsigned_int gso_ipv4_max_size read_mostly - sk_dst_gso_max_size +struct_dcbnl_rtnl_ops* dcbnl_ops +s16 num_tc read_mostly - skb_tx_hash +struct_netdev_tc_txq tc_to_txq[16] read_mostly - skb_tx_hash +u8 prio_tc_map[16] +unsigned_int fcoe_ddp_xid +struct_netprio_map* priomap +struct_phy_device* phydev +struct_sfp_bus* sfp_bus +struct_lock_class_key* qdisc_tx_busylock +bool proto_down +unsigned:1 wol_enabled +unsigned:1 threaded - - napi_poll(napi_enable,dev_set_threaded) +struct_list_head net_notifier_list +struct_macsec_ops* macsec_ops +struct_udp_tunnel_nic_info* udp_tunnel_nic_info +struct_udp_tunnel_nic* udp_tunnel_nic +unsigned_int xdp_zc_max_segs +struct_bpf_xdp_entity xdp_state[3] +u8 dev_addr_shadow[32] +netdevice_tracker linkwatch_dev_tracker +netdevice_tracker watchdog_dev_tracker +netdevice_tracker dev_registered_tracker +struct_rtnl_hw_stats64* offload_xstats_l3 +struct_devlink_port* devlink_port +struct_dpll_pin* dpll_pin diff --git a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst new file mode 100644 index 000000000000..9b87089a84c6 --- /dev/null +++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst @@ -0,0 +1,158 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +=========================================== +netns_ipv4 struct fast path usage breakdown +=========================================== + +Type Name fastpath_tx_access fastpath_rx_access comment +..struct ..netns_ipv4 +struct_inet_timewait_death_row tcp_death_row +struct_udp_table* udp_table +struct_ctl_table_header* forw_hdr +struct_ctl_table_header* frags_hdr +struct_ctl_table_header* ipv4_hdr +struct_ctl_table_header* route_hdr +struct_ctl_table_header* xfrm4_hdr +struct_ipv4_devconf* devconf_all +struct_ipv4_devconf* devconf_dflt +struct_ip_ra_chain ra_chain +struct_mutex ra_mutex +struct_fib_rules_ops* rules_ops +struct_fib_table fib_main +struct_fib_table fib_default +unsigned_int fib_rules_require_fldissect +bool fib_has_custom_rules +bool fib_has_custom_local_routes +bool fib_offload_disabled +atomic_t fib_num_tclassid_users +struct_hlist_head* fib_table_hash +struct_sock* fibnl +struct_sock* mc_autojoin_sk +struct_inet_peer_base* peers +struct_fqdir* fqdir +u8 sysctl_icmp_echo_ignore_all +u8 sysctl_icmp_echo_enable_probe +u8 sysctl_icmp_echo_ignore_broadcasts +u8 sysctl_icmp_ignore_bogus_error_responses +u8 sysctl_icmp_errors_use_inbound_ifaddr +int sysctl_icmp_ratelimit +int sysctl_icmp_ratemask +u32 ip_rt_min_pmtu - - +int ip_rt_mtu_expires - - +int ip_rt_min_advmss - - +struct_local_ports ip_local_ports - - +u8 sysctl_tcp_ecn - - +u8 sysctl_tcp_ecn_fallback - - +u8 sysctl_ip_default_ttl - - ip4_dst_hoplimit/ip_select_ttl +u8 sysctl_ip_no_pmtu_disc - - +u8 sysctl_ip_fwd_use_pmtu read_mostly - ip_dst_mtu_maybe_forward/ip_skb_dst_mtu +u8 sysctl_ip_fwd_update_priority - - ip_forward +u8 sysctl_ip_nonlocal_bind - - +u8 sysctl_ip_autobind_reuse - - +u8 sysctl_ip_dynaddr - - +u8 sysctl_ip_early_demux - read_mostly ip(6)_rcv_finish_core +u8 sysctl_raw_l3mdev_accept - - +u8 sysctl_tcp_early_demux - read_mostly ip(6)_rcv_finish_core +u8 sysctl_udp_early_demux +u8 sysctl_nexthop_compat_mode - - +u8 sysctl_fwmark_reflect - - +u8 sysctl_tcp_fwmark_accept - - +u8 sysctl_tcp_l3mdev_accept - - +u8 sysctl_tcp_mtu_probing - - +int sysctl_tcp_mtu_probe_floor - - +int sysctl_tcp_base_mss - - +int sysctl_tcp_min_snd_mss read_mostly - __tcp_mtu_to_mss(tcp_write_xmit) +int sysctl_tcp_probe_threshold - - tcp_mtu_probe(tcp_write_xmit) +u32 sysctl_tcp_probe_interval - - tcp_mtu_check_reprobe(tcp_write_xmit) +int sysctl_tcp_keepalive_time - - +int sysctl_tcp_keepalive_intvl - - +u8 sysctl_tcp_keepalive_probes - - +u8 sysctl_tcp_syn_retries - - +u8 sysctl_tcp_synack_retries - - +u8 sysctl_tcp_syncookies - - generated_on_syn +u8 sysctl_tcp_migrate_req - - reuseport +u8 sysctl_tcp_comp_sack_nr - - __tcp_ack_snd_check +int sysctl_tcp_reordering - read_mostly tcp_may_raise_cwnd/tcp_cong_control +u8 sysctl_tcp_retries1 - - +u8 sysctl_tcp_retries2 - - +u8 sysctl_tcp_orphan_retries - - +u8 sysctl_tcp_tw_reuse - - timewait_sock_ops +int sysctl_tcp_fin_timeout - - TCP_LAST_ACK/tcp_rcv_state_process +unsigned_int sysctl_tcp_notsent_lowat read_mostly - tcp_notsent_lowat/tcp_stream_memory_free +u8 sysctl_tcp_sack - - tcp_syn_options +u8 sysctl_tcp_window_scaling - - tcp_syn_options,tcp_parse_options +u8 sysctl_tcp_timestamps +u8 sysctl_tcp_early_retrans read_mostly - tcp_schedule_loss_probe(tcp_write_xmit) +u8 sysctl_tcp_recovery - - tcp_fastretrans_alert +u8 sysctl_tcp_thin_linear_timeouts - - tcp_retrans_timer(on_thin_streams) +u8 sysctl_tcp_slow_start_after_idle - - unlikely(tcp_cwnd_validate-network-not-starved) +u8 sysctl_tcp_retrans_collapse - - +u8 sysctl_tcp_stdurg - - unlikely(tcp_check_urg) +u8 sysctl_tcp_rfc1337 - - +u8 sysctl_tcp_abort_on_overflow - - +u8 sysctl_tcp_fack - - +int sysctl_tcp_max_reordering - - tcp_check_sack_reordering +int sysctl_tcp_adv_win_scale - - tcp_init_buffer_space +u8 sysctl_tcp_dsack - - partial_packet_or_retrans_in_tcp_data_queue +u8 sysctl_tcp_app_win - - tcp_win_from_space +u8 sysctl_tcp_frto - - tcp_enter_loss +u8 sysctl_tcp_nometrics_save - - TCP_LAST_ACK/tcp_update_metrics +u8 sysctl_tcp_no_ssthresh_metrics_save - - TCP_LAST_ACK/tcp_(update/init)_metrics +u8 sysctl_tcp_moderate_rcvbuf read_mostly read_mostly tcp_tso_should_defer(tx);tcp_rcv_space_adjust(rx) +u8 sysctl_tcp_tso_win_divisor read_mostly - tcp_tso_should_defer(tcp_write_xmit) +u8 sysctl_tcp_workaround_signed_windows - - tcp_select_window +int sysctl_tcp_limit_output_bytes read_mostly - tcp_small_queue_check(tcp_write_xmit) +int sysctl_tcp_challenge_ack_limit - - +int sysctl_tcp_min_rtt_wlen read_mostly - tcp_ack_update_rtt +u8 sysctl_tcp_min_tso_segs - - unlikely(icsk_ca_ops-written) +u8 sysctl_tcp_tso_rtt_log read_mostly - tcp_tso_autosize +u8 sysctl_tcp_autocorking read_mostly - tcp_push/tcp_should_autocork +u8 sysctl_tcp_reflect_tos - - tcp_v(4/6)_send_synack +int sysctl_tcp_invalid_ratelimit - - +int sysctl_tcp_pacing_ss_ratio - - default_cong_cont(tcp_update_pacing_rate) +int sysctl_tcp_pacing_ca_ratio - - default_cong_cont(tcp_update_pacing_rate) +int sysctl_tcp_wmem[3] read_mostly - tcp_wmem_schedule(sendmsg/sendpage) +int sysctl_tcp_rmem[3] - read_mostly __tcp_grow_window(tx),tcp_rcv_space_adjust(rx) +unsigned_int sysctl_tcp_child_ehash_entries +unsigned_long sysctl_tcp_comp_sack_delay_ns - - __tcp_ack_snd_check +unsigned_long sysctl_tcp_comp_sack_slack_ns - - __tcp_ack_snd_check +int sysctl_max_syn_backlog - - +int sysctl_tcp_fastopen - - +struct_tcp_congestion_ops tcp_congestion_control - - init_cc +struct_tcp_fastopen_context tcp_fastopen_ctx - - +unsigned_int sysctl_tcp_fastopen_blackhole_timeout - - +atomic_t tfo_active_disable_times - - +unsigned_long tfo_active_disable_stamp - - +u32 tcp_challenge_timestamp - - +u32 tcp_challenge_count - - +u8 sysctl_tcp_plb_enabled - - +u8 sysctl_tcp_plb_idle_rehash_rounds - - +u8 sysctl_tcp_plb_rehash_rounds - - +u8 sysctl_tcp_plb_suspend_rto_sec - - +int sysctl_tcp_plb_cong_thresh - - +int sysctl_udp_wmem_min +int sysctl_udp_rmem_min +u8 sysctl_fib_notify_on_flag_change +u8 sysctl_udp_l3mdev_accept +u8 sysctl_igmp_llm_reports +int sysctl_igmp_max_memberships +int sysctl_igmp_max_msf +int sysctl_igmp_qrv +struct_ping_group_range ping_group_range +atomic_t dev_addr_genid +unsigned_int sysctl_udp_child_hash_entries +unsigned_long* sysctl_local_reserved_ports +int sysctl_ip_prot_sock +struct_mr_table* mrt +struct_list_head mr_tables +struct_fib_rules_ops* mr_rules_ops +u32 sysctl_fib_multipath_hash_fields +u8 sysctl_fib_multipath_use_neigh +u8 sysctl_fib_multipath_hash_policy +struct_fib_notifier_ops* notifier_ops +unsigned_int fib_seq +struct_fib_notifier_ops* ipmr_notifier_ops +unsigned_int ipmr_seq +atomic_t rt_genid +siphash_key_t ip_id_key diff --git a/Documentation/networking/net_cachelines/snmp.rst b/Documentation/networking/net_cachelines/snmp.rst new file mode 100644 index 000000000000..6a071538566c --- /dev/null +++ b/Documentation/networking/net_cachelines/snmp.rst @@ -0,0 +1,135 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +=========================================== +netns_ipv4 enum fast path usage breakdown +=========================================== + +Type Name fastpath_tx_access fastpath_rx_access comment +..enum +unsigned_long LINUX_MIB_TCPKEEPALIVE write_mostly - tcp_keepalive_timer +unsigned_long LINUX_MIB_DELAYEDACKS write_mostly - tcp_delack_timer_handler,tcp_delack_timer +unsigned_long LINUX_MIB_DELAYEDACKLOCKED write_mostly - tcp_delack_timer_handler,tcp_delack_timer +unsigned_long LINUX_MIB_TCPAUTOCORKING write_mostly - tcp_push,tcp_sendmsg_locked +unsigned_long LINUX_MIB_TCPFROMZEROWINDOWADV write_mostly - tcp_select_window,tcp_transmit-skb +unsigned_long LINUX_MIB_TCPTOZEROWINDOWADV write_mostly - tcp_select_window,tcp_transmit-skb +unsigned_long LINUX_MIB_TCPWANTZEROWINDOWADV write_mostly - tcp_select_window,tcp_transmit-skb +unsigned_long LINUX_MIB_TCPORIGDATASENT write_mostly - tcp_write_xmit +unsigned_long LINUX_MIB_TCPHPHITS - write_mostly tcp_rcv_established,tcp_v4_do_rcv,tcp_v6_do_rcv +unsigned_long LINUX_MIB_TCPRCVCOALESCE - write_mostly tcp_try_coalesce,tcp_queue_rcv,tcp_rcv_established +unsigned_long LINUX_MIB_TCPPUREACKS - write_mostly tcp_ack,tcp_rcv_established +unsigned_long LINUX_MIB_TCPHPACKS - write_mostly tcp_ack,tcp_rcv_established +unsigned_long LINUX_MIB_TCPDELIVERED - write_mostly tcp_newly_delivered,tcp_ack,tcp_rcv_established +unsigned_long LINUX_MIB_SYNCOOKIESSENT +unsigned_long LINUX_MIB_SYNCOOKIESRECV +unsigned_long LINUX_MIB_SYNCOOKIESFAILED +unsigned_long LINUX_MIB_EMBRYONICRSTS +unsigned_long LINUX_MIB_PRUNECALLED +unsigned_long LINUX_MIB_RCVPRUNED +unsigned_long LINUX_MIB_OFOPRUNED +unsigned_long LINUX_MIB_OUTOFWINDOWICMPS +unsigned_long LINUX_MIB_LOCKDROPPEDICMPS +unsigned_long LINUX_MIB_ARPFILTER +unsigned_long LINUX_MIB_TIMEWAITED +unsigned_long LINUX_MIB_TIMEWAITRECYCLED +unsigned_long LINUX_MIB_TIMEWAITKILLED +unsigned_long LINUX_MIB_PAWSACTIVEREJECTED +unsigned_long LINUX_MIB_PAWSESTABREJECTED +unsigned_long LINUX_MIB_DELAYEDACKLOST +unsigned_long LINUX_MIB_LISTENOVERFLOWS +unsigned_long LINUX_MIB_LISTENDROPS +unsigned_long LINUX_MIB_TCPRENORECOVERY +unsigned_long LINUX_MIB_TCPSACKRECOVERY +unsigned_long LINUX_MIB_TCPSACKRENEGING +unsigned_long LINUX_MIB_TCPSACKREORDER +unsigned_long LINUX_MIB_TCPRENOREORDER +unsigned_long LINUX_MIB_TCPTSREORDER +unsigned_long LINUX_MIB_TCPFULLUNDO +unsigned_long LINUX_MIB_TCPPARTIALUNDO +unsigned_long LINUX_MIB_TCPDSACKUNDO +unsigned_long LINUX_MIB_TCPLOSSUNDO +unsigned_long LINUX_MIB_TCPLOSTRETRANSMIT +unsigned_long LINUX_MIB_TCPRENOFAILURES +unsigned_long LINUX_MIB_TCPSACKFAILURES +unsigned_long LINUX_MIB_TCPLOSSFAILURES +unsigned_long LINUX_MIB_TCPFASTRETRANS +unsigned_long LINUX_MIB_TCPSLOWSTARTRETRANS +unsigned_long LINUX_MIB_TCPTIMEOUTS +unsigned_long LINUX_MIB_TCPLOSSPROBES +unsigned_long LINUX_MIB_TCPLOSSPROBERECOVERY +unsigned_long LINUX_MIB_TCPRENORECOVERYFAIL +unsigned_long LINUX_MIB_TCPSACKRECOVERYFAIL +unsigned_long LINUX_MIB_TCPRCVCOLLAPSED +unsigned_long LINUX_MIB_TCPDSACKOLDSENT +unsigned_long LINUX_MIB_TCPDSACKOFOSENT +unsigned_long LINUX_MIB_TCPDSACKRECV +unsigned_long LINUX_MIB_TCPDSACKOFORECV +unsigned_long LINUX_MIB_TCPABORTONDATA +unsigned_long LINUX_MIB_TCPABORTONCLOSE +unsigned_long LINUX_MIB_TCPABORTONMEMORY +unsigned_long LINUX_MIB_TCPABORTONTIMEOUT +unsigned_long LINUX_MIB_TCPABORTONLINGER +unsigned_long LINUX_MIB_TCPABORTFAILED +unsigned_long LINUX_MIB_TCPMEMORYPRESSURES +unsigned_long LINUX_MIB_TCPMEMORYPRESSURESCHRONO +unsigned_long LINUX_MIB_TCPSACKDISCARD +unsigned_long LINUX_MIB_TCPDSACKIGNOREDOLD +unsigned_long LINUX_MIB_TCPDSACKIGNOREDNOUNDO +unsigned_long LINUX_MIB_TCPSPURIOUSRTOS +unsigned_long LINUX_MIB_TCPMD5NOTFOUND +unsigned_long LINUX_MIB_TCPMD5UNEXPECTED +unsigned_long LINUX_MIB_TCPMD5FAILURE +unsigned_long LINUX_MIB_SACKSHIFTED +unsigned_long LINUX_MIB_SACKMERGED +unsigned_long LINUX_MIB_SACKSHIFTFALLBACK +unsigned_long LINUX_MIB_TCPBACKLOGDROP +unsigned_long LINUX_MIB_PFMEMALLOCDROP +unsigned_long LINUX_MIB_TCPMINTTLDROP +unsigned_long LINUX_MIB_TCPDEFERACCEPTDROP +unsigned_long LINUX_MIB_IPRPFILTER +unsigned_long LINUX_MIB_TCPTIMEWAITOVERFLOW +unsigned_long LINUX_MIB_TCPREQQFULLDOCOOKIES +unsigned_long LINUX_MIB_TCPREQQFULLDROP +unsigned_long LINUX_MIB_TCPRETRANSFAIL +unsigned_long LINUX_MIB_TCPBACKLOGCOALESCE +unsigned_long LINUX_MIB_TCPOFOQUEUE +unsigned_long LINUX_MIB_TCPOFODROP +unsigned_long LINUX_MIB_TCPOFOMERGE +unsigned_long LINUX_MIB_TCPCHALLENGEACK +unsigned_long LINUX_MIB_TCPSYNCHALLENGE +unsigned_long LINUX_MIB_TCPFASTOPENACTIVE +unsigned_long LINUX_MIB_TCPFASTOPENACTIVEFAIL +unsigned_long LINUX_MIB_TCPFASTOPENPASSIVE +unsigned_long LINUX_MIB_TCPFASTOPENPASSIVEFAIL +unsigned_long LINUX_MIB_TCPFASTOPENLISTENOVERFLOW +unsigned_long LINUX_MIB_TCPFASTOPENCOOKIEREQD +unsigned_long LINUX_MIB_TCPFASTOPENBLACKHOLE +unsigned_long LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES +unsigned_long LINUX_MIB_BUSYPOLLRXPACKETS +unsigned_long LINUX_MIB_TCPSYNRETRANS +unsigned_long LINUX_MIB_TCPHYSTARTTRAINDETECT +unsigned_long LINUX_MIB_TCPHYSTARTTRAINCWND +unsigned_long LINUX_MIB_TCPHYSTARTDELAYDETECT +unsigned_long LINUX_MIB_TCPHYSTARTDELAYCWND +unsigned_long LINUX_MIB_TCPACKSKIPPEDSYNRECV +unsigned_long LINUX_MIB_TCPACKSKIPPEDPAWS +unsigned_long LINUX_MIB_TCPACKSKIPPEDSEQ +unsigned_long LINUX_MIB_TCPACKSKIPPEDFINWAIT2 +unsigned_long LINUX_MIB_TCPACKSKIPPEDTIMEWAIT +unsigned_long LINUX_MIB_TCPACKSKIPPEDCHALLENGE +unsigned_long LINUX_MIB_TCPWINPROBE +unsigned_long LINUX_MIB_TCPMTUPFAIL +unsigned_long LINUX_MIB_TCPMTUPSUCCESS +unsigned_long LINUX_MIB_TCPDELIVEREDCE +unsigned_long LINUX_MIB_TCPACKCOMPRESSED +unsigned_long LINUX_MIB_TCPZEROWINDOWDROP +unsigned_long LINUX_MIB_TCPRCVQDROP +unsigned_long LINUX_MIB_TCPWQUEUETOOBIG +unsigned_long LINUX_MIB_TCPFASTOPENPASSIVEALTKEY +unsigned_long LINUX_MIB_TCPTIMEOUTREHASH +unsigned_long LINUX_MIB_TCPDUPLICATEDATAREHASH +unsigned_long LINUX_MIB_TCPDSACKRECVSEGS +unsigned_long LINUX_MIB_TCPDSACKIGNOREDDUBIOUS +unsigned_long LINUX_MIB_TCPMIGRATEREQSUCCESS +unsigned_long LINUX_MIB_TCPMIGRATEREQFAILURE +unsigned_long __LINUX_MIB_MAX diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst new file mode 100644 index 000000000000..97d7a5c8e01c --- /dev/null +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -0,0 +1,157 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. Copyright (C) 2023 Google LLC + +========================================= +tcp_sock struct fast path usage breakdown +========================================= + +Type Name fastpath_tx_access fastpath_rx_access Comments +..struct ..tcp_sock +struct_inet_connection_sock inet_conn +u16 tcp_header_len read_mostly read_mostly tcp_bound_to_half_wnd,tcp_current_mss(tx);tcp_rcv_established(rx) +u16 gso_segs read_mostly - tcp_xmit_size_goal +__be32 pred_flags read_write read_mostly tcp_select_window(tx);tcp_rcv_established(rx) +u64 bytes_received - read_write tcp_rcv_nxt_update(rx) +u32 segs_in - read_write tcp_v6_rcv(rx) +u32 data_segs_in - read_write tcp_v6_rcv(rx) +u32 rcv_nxt read_mostly read_write tcp_cleanup_rbuf,tcp_send_ack,tcp_inq_hint,tcp_transmit_skb,tcp_receive_window(tx);tcp_v6_do_rcv,tcp_rcv_established,tcp_data_queue,tcp_receive_window,tcp_rcv_nxt_update(write)(rx) +u32 copied_seq - read_mostly tcp_cleanup_rbuf,tcp_rcv_space_adjust,tcp_inq_hint +u32 rcv_wup - read_write __tcp_cleanup_rbuf,tcp_receive_window,tcp_receive_established +u32 snd_nxt read_write read_mostly tcp_rate_check_app_limited,__tcp_transmit_skb,tcp_event_new_data_sent(write)(tx);tcp_rcv_established,tcp_ack,tcp_clean_rtx_queue(rx) +u32 segs_out read_write - __tcp_transmit_skb +u32 data_segs_out read_write - __tcp_transmit_skb,tcp_update_skb_after_send +u64 bytes_sent read_write - __tcp_transmit_skb +u64 bytes_acked - read_write tcp_snd_una_update/tcp_ack +u32 dsack_dups +u32 snd_una read_mostly read_write tcp_wnd_end,tcp_urg_mode,tcp_minshall_check,tcp_cwnd_validate(tx);tcp_ack,tcp_may_update_window,tcp_clean_rtx_queue(write),tcp_ack_tstamp(rx) +u32 snd_sml read_write - tcp_minshall_check,tcp_minshall_update +u32 rcv_tstamp - read_mostly tcp_ack +u32 lsndtime read_write - tcp_slow_start_after_idle_check,tcp_event_data_sent +u32 last_oow_ack_time +u32 compressed_ack_rcv_nxt +u32 tsoffset read_mostly read_mostly tcp_established_options(tx);tcp_fast_parse_options(rx) +struct_list_head tsq_node - - +struct_list_head tsorted_sent_queue read_write - tcp_update_skb_after_send +u32 snd_wl1 - read_mostly tcp_may_update_window +u32 snd_wnd read_mostly read_mostly tcp_wnd_end,tcp_tso_should_defer(tx);tcp_fast_path_on(rx) +u32 max_window read_mostly - tcp_bound_to_half_wnd,forced_push +u32 mss_cache read_mostly read_mostly tcp_rate_check_app_limited,tcp_current_mss,tcp_sync_mss,tcp_sndbuf_expand,tcp_tso_should_defer(tx);tcp_update_pacing_rate,tcp_clean_rtx_queue(rx) +u32 window_clamp read_mostly read_write tcp_rcv_space_adjust,__tcp_select_window +u32 rcv_ssthresh read_mostly - __tcp_select_window +u82 scaling_ratio +struct tcp_rack +u16 advmss - read_mostly tcp_rcv_space_adjust +u8 compressed_ack +u8:2 dup_ack_counter +u8:1 tlp_retrans +u8:1 tcp_usec_ts +u32 chrono_start read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data) +u32[3] chrono_stat read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data) +u8:2 chrono_type read_write - tcp_chrono_start/stop(tcp_write_xmit,tcp_cwnd_validate,tcp_send_syn_data) +u8:1 rate_app_limited - read_write tcp_rate_gen +u8:1 fastopen_connect +u8:1 fastopen_no_cookie +u8:1 is_sack_reneg - read_mostly tcp_skb_entail,tcp_ack +u8:2 fastopen_client_fail +u8:4 nonagle read_write - tcp_skb_entail,tcp_push_pending_frames +u8:1 thin_lto +u8:1 recvmsg_inq +u8:1 repair read_mostly - tcp_write_xmit +u8:1 frto +u8 repair_queue - - +u8:2 save_syn +u8:1 syn_data +u8:1 syn_fastopen +u8:1 syn_fastopen_exp +u8:1 syn_fastopen_ch +u8:1 syn_data_acked +u8:1 is_cwnd_limited read_mostly - tcp_cwnd_validate,tcp_is_cwnd_limited +u32 tlp_high_seq - read_mostly tcp_ack +u32 tcp_tx_delay +u64 tcp_wstamp_ns read_write - tcp_pacing_check,tcp_tso_should_defer,tcp_update_skb_after_send +u64 tcp_clock_cache read_write read_write tcp_mstamp_refresh(tcp_write_xmit/tcp_rcv_space_adjust),__tcp_transmit_skb,tcp_tso_should_defer;timer +u64 tcp_mstamp read_write read_write tcp_mstamp_refresh(tcp_write_xmit/tcp_rcv_space_adjust)(tx);tcp_rcv_space_adjust,tcp_rate_gen,tcp_clean_rtx_queue,tcp_ack_update_rtt/tcp_time_stamp(rx);timer +u32 srtt_us read_mostly read_write tcp_tso_should_defer(tx);tcp_update_pacing_rate,__tcp_set_rto,tcp_rtt_estimator(rx) +u32 mdev_us read_write - tcp_rtt_estimator +u32 mdev_max_us +u32 rttvar_us - read_mostly __tcp_set_rto +u32 rtt_seq read_write tcp_rtt_estimator +struct_minmax rtt_min - read_mostly tcp_min_rtt/tcp_rate_gen,tcp_min_rtttcp_update_rtt_min +u32 packets_out read_write read_write tcp_packets_in_flight(tx/rx);tcp_slow_start_after_idle_check,tcp_nagle_check,tcp_rate_skb_sent,tcp_event_new_data_sent,tcp_cwnd_validate,tcp_write_xmit(tx);tcp_ack,tcp_clean_rtx_queue,tcp_update_pacing_rate(rx) +u32 retrans_out - read_mostly tcp_packets_in_flight,tcp_rate_check_app_limited +u32 max_packets_out - read_write tcp_cwnd_validate +u32 cwnd_usage_seq - read_write tcp_cwnd_validate +u16 urg_data - read_mostly tcp_fast_path_check +u8 ecn_flags read_write - tcp_ecn_send +u8 keepalive_probes +u32 reordering read_mostly - tcp_sndbuf_expand +u32 reord_seen +u32 snd_up read_write read_mostly tcp_mark_urg,tcp_urg_mode,__tcp_transmit_skb(tx);tcp_clean_rtx_queue(rx) +struct_tcp_options_received rx_opt read_mostly read_write tcp_established_options(tx);tcp_fast_path_on,tcp_ack_update_window,tcp_is_sack,tcp_data_queue,tcp_rcv_established,tcp_ack_update_rtt(rx) +u32 snd_ssthresh - read_mostly tcp_update_pacing_rate +u32 snd_cwnd read_mostly read_mostly tcp_snd_cwnd,tcp_rate_check_app_limited,tcp_tso_should_defer(tx);tcp_update_pacing_rate +u32 snd_cwnd_cnt +u32 snd_cwnd_clamp +u32 snd_cwnd_used +u32 snd_cwnd_stamp +u32 prior_cwnd +u32 prr_delivered +u32 prr_out read_mostly read_mostly tcp_rate_skb_sent,tcp_newly_delivered(tx);tcp_ack,tcp_rate_gen,tcp_clean_rtx_queue(rx) +u32 delivered read_mostly read_write tcp_rate_skb_sent, tcp_newly_delivered(tx);tcp_ack, tcp_rate_gen, tcp_clean_rtx_queue (rx) +u32 delivered_ce read_mostly read_write tcp_rate_skb_sent(tx);tcp_rate_gen(rx) +u32 lost - read_mostly tcp_ack +u32 app_limited read_write read_mostly tcp_rate_check_app_limited,tcp_rate_skb_sent(tx);tcp_rate_gen(rx) +u64 first_tx_mstamp read_write - tcp_rate_skb_sent +u64 delivered_mstamp read_write - tcp_rate_skb_sent +u32 rate_delivered - read_mostly tcp_rate_gen +u32 rate_interval_us - read_mostly rate_delivered,rate_app_limited +u32 rcv_wnd read_write read_mostly tcp_select_window,tcp_receive_window,tcp_fast_path_check +u32 write_seq read_write - tcp_rate_check_app_limited,tcp_write_queue_empty,tcp_skb_entail,forced_push,tcp_mark_push +u32 notsent_lowat read_mostly - tcp_stream_memory_free +u32 pushed_seq read_write - tcp_mark_push,forced_push +u32 lost_out read_mostly read_mostly tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_rate_check_app_limited(rx) +u32 sacked_out read_mostly read_mostly tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_clean_rtx_queue(rx) +struct_hrtimer pacing_timer +struct_hrtimer compressed_ack_timer +struct_sk_buff* lost_skb_hint read_mostly tcp_clean_rtx_queue +struct_sk_buff* retransmit_skb_hint read_mostly - tcp_clean_rtx_queue +struct_rb_root out_of_order_queue - read_mostly tcp_data_queue,tcp_fast_path_check +struct_sk_buff* ooo_last_skb +struct_tcp_sack_block[1] duplicate_sack +struct_tcp_sack_block[4] selective_acks +struct_tcp_sack_block[4] recv_sack_cache +struct_sk_buff* highest_sack read_write - tcp_event_new_data_sent +int lost_cnt_hint +u32 prior_ssthresh +u32 high_seq +u32 retrans_stamp +u32 undo_marker +int undo_retrans +u64 bytes_retrans +u32 total_retrans +u32 rto_stamp +u16 total_rto +u16 total_rto_recoveries +u32 total_rto_time +u32 urg_seq - - +unsigned_int keepalive_time +unsigned_int keepalive_intvl +int linger2 +u8 bpf_sock_ops_cb_flags +u8:1 bpf_chg_cc_inprogress +u16 timeout_rehash +u32 rcv_ooopack +u32 rcv_rtt_last_tsecr +struct rcv_rtt_est - read_write tcp_rcv_space_adjust,tcp_rcv_established +struct rcvq_space - read_write tcp_rcv_space_adjust +struct mtu_probe +u32 plb_rehash +u32 mtu_info +bool is_mptcp +bool smc_hs_congested +bool syn_smc +struct_tcp_sock_af_ops* af_specific +struct_tcp_md5sig_info* md5sig_info +struct_tcp_fastopen_request* fastopen_req +struct_request_sock* fastopen_rsk +struct_saved_syn* saved_syn
\ No newline at end of file diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst index 03ae19a689fc..4eb50bcb9d42 100644 --- a/Documentation/networking/scaling.rst +++ b/Documentation/networking/scaling.rst @@ -44,6 +44,21 @@ by masking out the low order seven bits of the computed hash for the packet (usually a Toeplitz hash), taking this number as a key into the indirection table and reading the corresponding value. +Some NICs support symmetric RSS hashing where, if the IP (source address, +destination address) and TCP/UDP (source port, destination port) tuples +are swapped, the computed hash is the same. This is beneficial in some +applications that monitor TCP/IP flows (IDS, firewalls, ...etc) and need +both directions of the flow to land on the same Rx queue (and CPU). The +"Symmetric-XOR" is a type of RSS algorithms that achieves this hash +symmetry by XORing the input source and destination fields of the IP +and/or L4 protocols. This, however, results in reduced input entropy and +could potentially be exploited. Specifically, the algorithm XORs the input +as follows:: + + # (SRC_IP ^ DST_IP, SRC_IP ^ DST_IP, SRC_PORT ^ DST_PORT, SRC_PORT ^ DST_PORT) + +The result is then fed to the underlying RSS algorithm. + Some advanced NICs allow steering packets to queues based on programmable filters. For example, webserver bound TCP port 80 packets can be directed to their own receive queue. Such “n-tuple” filters can diff --git a/Documentation/networking/tcp_ao.rst b/Documentation/networking/tcp_ao.rst index cfa5bf1cc542..8a58321acce7 100644 --- a/Documentation/networking/tcp_ao.rst +++ b/Documentation/networking/tcp_ao.rst @@ -99,7 +99,7 @@ also [6.1]:: when it is no longer considered permitted. Linux TCP-AO will try its best to prevent you from removing a key that's -being used, considering it a key management failure. But sine keeping +being used, considering it a key management failure. But since keeping an outdated key may become a security issue and as a peer may unintentionally prevent the removal of an old key by always setting it as RNextKeyID - a forced key removal mechanism is provided, where diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index f17c01834a12..5e93cd71f99f 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -357,7 +357,8 @@ enabling SOF_TIMESTAMPING_OPT_ID and comparing the byte offset at send time with the value returned for each timestamp. It can prevent the situation by always flushing the TCP stack in between requests, for instance by enabling TCP_NODELAY and disabling TCP_CORK and -autocork. +autocork. After linux-4.7, a better way to prevent coalescing is +to use MSG_EOR flag at sendmsg() time. These precautions ensure that the timestamp is generated only when all bytes have passed a timestamp point, assuming that the network stack diff --git a/Documentation/trace/coresight/coresight.rst b/Documentation/trace/coresight/coresight.rst index 4a71ea6cb390..826e59a698da 100644 --- a/Documentation/trace/coresight/coresight.rst +++ b/Documentation/trace/coresight/coresight.rst @@ -130,7 +130,7 @@ Misc: Device Tree Bindings -------------------- -See Documentation/devicetree/bindings/arm/arm,coresight-\*.yaml for details. +See ``Documentation/devicetree/bindings/arm/arm,coresight-*.yaml`` for details. As of this writing drivers for ITM, STMs and CTIs are not provided but are expected to be added as the solution matures. diff --git a/Documentation/userspace-api/netlink/intro.rst b/Documentation/userspace-api/netlink/intro.rst index 7b1d401210ef..aacffade8f84 100644 --- a/Documentation/userspace-api/netlink/intro.rst +++ b/Documentation/userspace-api/netlink/intro.rst @@ -234,6 +234,10 @@ ACK attributes may be present:: | ** optionally extended ACK | ---------------------------------------------- +Note that some implementations may issue custom ``NLMSG_DONE`` messages +in reply to ``do`` action requests. In that case the payload is +implementation-specific and may also be absent. + .. _res_fam: Resolving the Family ID diff --git a/Documentation/userspace-api/netlink/netlink-raw.rst b/Documentation/userspace-api/netlink/netlink-raw.rst index f07fb9b9c101..1e14f5f22b8e 100644 --- a/Documentation/userspace-api/netlink/netlink-raw.rst +++ b/Documentation/userspace-api/netlink/netlink-raw.rst @@ -14,7 +14,8 @@ Specification The netlink-raw schema extends the :doc:`genetlink-legacy <genetlink-legacy>` schema with properties that are needed to specify the protocol numbers and multicast IDs used by raw netlink families. See :ref:`classic_netlink` for more -information. +information. The raw netlink families also make use of type-specific +sub-messages. Globals ------- @@ -56,3 +57,96 @@ group registration. - name: rtnlgrp-mctp-ifaddr value: 34 + +Sub-messages +------------ + +Several raw netlink families such as +:doc:`rt_link<../../networking/netlink_spec/rt_link>` and +:doc:`tc<../../networking/netlink_spec/tc>` use attribute nesting as an +abstraction to carry module specific information. + +Conceptually it looks as follows:: + + [OUTER NEST OR MESSAGE LEVEL] + [GENERIC ATTR 1] + [GENERIC ATTR 2] + [GENERIC ATTR 3] + [GENERIC ATTR - wrapper] + [MODULE SPECIFIC ATTR 1] + [MODULE SPECIFIC ATTR 2] + +The ``GENERIC ATTRs`` at the outer level are defined in the core (or rt_link or +core TC), while specific drivers, TC classifiers, qdiscs etc. can carry their +own information wrapped in the ``GENERIC ATTR - wrapper``. Even though the +example above shows attributes nesting inside the wrapper, the modules generally +have full freedom to define the format of the nest. In practice the payload of +the wrapper attr has very similar characteristics to a netlink message. It may +contain a fixed header / structure, netlink attributes, or both. Because of +those shared characteristics we refer to the payload of the wrapper attribute as +a sub-message. + +A sub-message attribute uses the value of another attribute as a selector key to +choose the right sub-message format. For example if the following attribute has +already been decoded: + +.. code-block:: json + + { "kind": "gre" } + +and we encounter the following attribute spec: + +.. code-block:: yaml + + - + name: data + type: sub-message + sub-message: linkinfo-data-msg + selector: kind + +Then we look for a sub-message definition called ``linkinfo-data-msg`` and use +the value of the ``kind`` attribute i.e. ``gre`` as the key to choose the +correct format for the sub-message: + +.. code-block:: yaml + + sub-messages: + name: linkinfo-data-msg + formats: + - + value: bridge + attribute-set: linkinfo-bridge-attrs + - + value: gre + attribute-set: linkinfo-gre-attrs + - + value: geneve + attribute-set: linkinfo-geneve-attrs + +This would decode the attribute value as a sub-message with the attribute-set +called ``linkinfo-gre-attrs`` as the attribute space. + +A sub-message can have an optional ``fixed-header`` followed by zero or more +attributes from an ``attribute-set``. For example the following +``tc-options-msg`` sub-message defines message formats that use a mixture of +``fixed-header``, ``attribute-set`` or both together: + +.. code-block:: yaml + + sub-messages: + - + name: tc-options-msg + formats: + - + value: bfifo + fixed-header: tc-fifo-qopt + - + value: cake + attribute-set: tc-cake-attrs + - + value: netem + fixed-header: tc-netem-qopt + attribute-set: tc-netem-attrs + +Note that a selector attribute must appear in a netlink message before any +sub-message attributes that depend on it. |