diff options
Diffstat (limited to 'Documentation')
77 files changed, 2209 insertions, 466 deletions
diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 2ef50828aff1..369a738a6819 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -212,6 +212,14 @@ mem_pcpu_rsv Per-cpu reserved forward alloc cache size in page units. Default 1MB per CPU. +bypass_prot_mem +--------------- + +Skip charging socket buffers to the global per-protocol memory +accounting controlled by net.ipv4.tcp_mem, net.ipv4.udp_mem, etc. + +Default: 0 (off) + rmem_default ------------ @@ -347,9 +355,9 @@ skb_defer_max ------------- Max size (in skbs) of the per-cpu list of skbs being freed -by the cpu which allocated them. Used by TCP stack so far. +by the cpu which allocated them. -Default: 64 +Default: 128 optmem_max ---------- @@ -406,6 +414,23 @@ to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). If set to 1 (default), hash rethink is performed on listening socket. If set to 0, hash rethink is not performed. +txq_reselection_ms +------------------ + +Controls how often (in ms) a busy connected flow can select another tx queue. + +A resection is desirable when/if user thread has migrated and XPS +would select a different queue. Same can occur without XPS +if the flow hash has changed. + +But switching txq can introduce reorders, especially if the +old queue is under high pressure. Modern TCP stacks deal +well with reorders if they happen not too often. + +To disable this feature, set the value to 0. + +Default : 1000 + gro_normal_batch ---------------- diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml index 6d22131ac2f9..fbe2ddcdd909 100644 --- a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml +++ b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml @@ -17,6 +17,7 @@ properties: compatible: enum: - airoha,en7581-eth + - airoha,an7583-eth reg: items: @@ -44,6 +45,7 @@ properties: - description: PDMA irq resets: + minItems: 7 maxItems: 8 reset-names: @@ -54,8 +56,9 @@ properties: - const: xsi-mac - const: hsi0-mac - const: hsi1-mac - - const: hsi-mac + - enum: [ hsi-mac, xfp-mac ] - const: xfp-mac + minItems: 7 memory-region: items: @@ -81,6 +84,36 @@ properties: interface to implement hardware flow offloading programming Packet Processor Engine (PPE) flow table. +allOf: + - $ref: ethernet-controller.yaml# + - if: + properties: + compatible: + contains: + enum: + - airoha,en7581-eth + then: + properties: + resets: + minItems: 8 + + reset-names: + minItems: 8 + + - if: + properties: + compatible: + contains: + enum: + - airoha,an7583-eth + then: + properties: + resets: + maxItems: 7 + + reset-names: + maxItems: 7 + patternProperties: "^ethernet@[1-4]$": type: object diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml index c7644e6586d3..59c57f58116b 100644 --- a/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml +++ b/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml @@ -18,6 +18,7 @@ properties: compatible: enum: - airoha,en7581-npu + - airoha,an7583-npu reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/amd,xgbe-seattle-v1a.yaml b/Documentation/devicetree/bindings/net/amd,xgbe-seattle-v1a.yaml new file mode 100644 index 000000000000..006add8b6410 --- /dev/null +++ b/Documentation/devicetree/bindings/net/amd,xgbe-seattle-v1a.yaml @@ -0,0 +1,147 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/amd,xgbe-seattle-v1a.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: AMD XGBE Seattle v1a + +maintainers: + - Shyam Sundar S K <Shyam-sundar.S-k@amd.com> + +allOf: + - $ref: /schemas/net/ethernet-controller.yaml# + +properties: + compatible: + const: amd,xgbe-seattle-v1a + + reg: + items: + - description: MAC registers + - description: PCS registers + - description: SerDes Rx/Tx registers + - description: SerDes integration registers (1/2) + - description: SerDes integration registers (2/2) + + interrupts: + description: Device interrupts. The first entry is the general device + interrupt. If amd,per-channel-interrupt is specified, each DMA channel + interrupt must be specified. The last entry is the PCS auto-negotiation + interrupt. + minItems: 2 + maxItems: 6 + + clocks: + items: + - description: DMA clock for the device + - description: PTP clock for the device + + clock-names: + items: + - const: dma_clk + - const: ptp_clk + + iommus: + maxItems: 1 + + phy-mode: true + + dma-coherent: true + + amd,per-channel-interrupt: + description: Indicates that Rx and Tx complete will generate a unique + interrupt for each DMA channel. + type: boolean + + amd,speed-set: + description: > + Speed capabilities of the device. + 0 = 1GbE and 10GbE + 1 = 2.5GbE and 10GbE + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [0, 1] + + amd,serdes-blwc: + description: Baseline wandering correction enablement for each speed. + $ref: /schemas/types.yaml#/definitions/uint32-array + minItems: 3 + maxItems: 3 + items: + enum: [0, 1] + + amd,serdes-cdr-rate: + description: CDR rate speed selection for each speed. + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: CDR rate for 1GbE + - description: CDR rate for 2.5GbE + - description: CDR rate for 10GbE + + amd,serdes-pq-skew: + description: PQ data sampling skew for each speed. + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: PQ skew for 1GbE + - description: PQ skew for 2.5GbE + - description: PQ skew for 10GbE + + amd,serdes-tx-amp: + description: TX amplitude boost for each speed. + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: TX amplitude for 1GbE + - description: TX amplitude for 2.5GbE + - description: TX amplitude for 10GbE + + amd,serdes-dfe-tap-config: + description: DFE taps available to run for each speed. + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: DFE taps available for 1GbE + - description: DFE taps available for 2.5GbE + - description: DFE taps available for 10GbE + + amd,serdes-dfe-tap-enable: + description: DFE taps to enable for each speed. + $ref: /schemas/types.yaml#/definitions/uint32-array + items: + - description: DFE taps to enable for 1GbE + - description: DFE taps to enable for 2.5GbE + - description: DFE taps to enable for 10GbE + +required: + - compatible + - reg + - interrupts + - clocks + - clock-names + - phy-mode + +unevaluatedProperties: false + +examples: + - | + ethernet@e0700000 { + compatible = "amd,xgbe-seattle-v1a"; + reg = <0xe0700000 0x80000>, + <0xe0780000 0x80000>, + <0xe1240800 0x00400>, + <0xe1250000 0x00060>, + <0xe1250080 0x00004>; + interrupts = <0 325 4>, + <0 326 1>, <0 327 1>, <0 328 1>, <0 329 1>, + <0 323 4>; + amd,per-channel-interrupt; + clocks = <&xgbe_dma_clk>, <&xgbe_ptp_clk>; + clock-names = "dma_clk", "ptp_clk"; + phy-mode = "xgmii"; + mac-address = [ 02 a1 a2 a3 a4 a5 ]; + amd,speed-set = <0>; + amd,serdes-blwc = <1>, <1>, <0>; + amd,serdes-cdr-rate = <2>, <2>, <7>; + amd,serdes-pq-skew = <10>, <10>, <30>; + amd,serdes-tx-amp = <15>, <15>, <10>; + amd,serdes-dfe-tap-config = <3>, <3>, <1>; + amd,serdes-dfe-tap-enable = <0>, <0>, <127>; + }; diff --git a/Documentation/devicetree/bindings/net/amd-xgbe.txt b/Documentation/devicetree/bindings/net/amd-xgbe.txt deleted file mode 100644 index 9c27dfcd1133..000000000000 --- a/Documentation/devicetree/bindings/net/amd-xgbe.txt +++ /dev/null @@ -1,76 +0,0 @@ -* AMD 10GbE driver (amd-xgbe) - -Required properties: -- compatible: Should be "amd,xgbe-seattle-v1a" -- reg: Address and length of the register sets for the device - - MAC registers - - PCS registers - - SerDes Rx/Tx registers - - SerDes integration registers (1/2) - - SerDes integration registers (2/2) -- interrupts: Should contain the amd-xgbe interrupt(s). The first interrupt - listed is required and is the general device interrupt. If the optional - amd,per-channel-interrupt property is specified, then one additional - interrupt for each DMA channel supported by the device should be specified. - The last interrupt listed should be the PCS auto-negotiation interrupt. -- clocks: - - DMA clock for the amd-xgbe device (used for calculating the - correct Rx interrupt watchdog timer value on a DMA channel - for coalescing) - - PTP clock for the amd-xgbe device -- clock-names: Should be the names of the clocks - - "dma_clk" for the DMA clock - - "ptp_clk" for the PTP clock -- phy-mode: See ethernet.txt file in the same directory - -Optional properties: -- dma-coherent: Present if dma operations are coherent -- amd,per-channel-interrupt: Indicates that Rx and Tx complete will generate - a unique interrupt for each DMA channel - this requires an additional - interrupt be configured for each DMA channel -- amd,speed-set: Speed capabilities of the device - 0 - 1GbE and 10GbE (default) - 1 - 2.5GbE and 10GbE - -The MAC address will be determined using the optional properties defined in -ethernet.txt. - -The following optional properties are represented by an array with each -value corresponding to a particular speed. The first array value represents -the setting for the 1GbE speed, the second value for the 2.5GbE speed and -the third value for the 10GbE speed. All three values are required if the -property is used. -- amd,serdes-blwc: Baseline wandering correction enablement - 0 - Off - 1 - On -- amd,serdes-cdr-rate: CDR rate speed selection -- amd,serdes-pq-skew: PQ (data sampling) skew -- amd,serdes-tx-amp: TX amplitude boost -- amd,serdes-dfe-tap-config: DFE taps available to run -- amd,serdes-dfe-tap-enable: DFE taps to enable - -Example: - xgbe@e0700000 { - compatible = "amd,xgbe-seattle-v1a"; - reg = <0 0xe0700000 0 0x80000>, - <0 0xe0780000 0 0x80000>, - <0 0xe1240800 0 0x00400>, - <0 0xe1250000 0 0x00060>, - <0 0xe1250080 0 0x00004>; - interrupt-parent = <&gic>; - interrupts = <0 325 4>, - <0 326 1>, <0 327 1>, <0 328 1>, <0 329 1>, - <0 323 4>; - amd,per-channel-interrupt; - clocks = <&xgbe_dma_clk>, <&xgbe_ptp_clk>; - clock-names = "dma_clk", "ptp_clk"; - phy-mode = "xgmii"; - mac-address = [ 02 a1 a2 a3 a4 a5 ]; - amd,speed-set = <0>; - amd,serdes-blwc = <1>, <1>, <0>; - amd,serdes-cdr-rate = <2>, <2>, <7>; - amd,serdes-pq-skew = <10>, <10>, <30>; - amd,serdes-tx-amp = <15>, <15>, <10>; - amd,serdes-dfe-tap-config = <3>, <3>, <1>; - amd,serdes-dfe-tap-enable = <0>, <0>, <127>; - }; diff --git a/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml b/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml index d6ef468495c5..a105dc07ed12 100644 --- a/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml +++ b/Documentation/devicetree/bindings/net/aspeed,ast2600-mdio.yaml @@ -19,7 +19,12 @@ allOf: properties: compatible: - const: aspeed,ast2600-mdio + oneOf: + - const: aspeed,ast2600-mdio + - items: + - enum: + - aspeed,ast2700-mdio + - const: aspeed,ast2600-mdio reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/bluetooth/marvell,sd8897-bt.yaml b/Documentation/devicetree/bindings/net/bluetooth/marvell,sd8897-bt.yaml new file mode 100644 index 000000000000..a307c64cfa4d --- /dev/null +++ b/Documentation/devicetree/bindings/net/bluetooth/marvell,sd8897-bt.yaml @@ -0,0 +1,79 @@ +# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/bluetooth/marvell,sd8897-bt.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Marvell 8897/8997 (sd8897/sd8997) bluetooth devices (SDIO) + +maintainers: + - Ariel D'Alessandro <ariel.dalessandro@collabora.com> + +allOf: + - $ref: /schemas/net/bluetooth/bluetooth-controller.yaml# + +properties: + compatible: + enum: + - marvell,sd8897-bt + - marvell,sd8997-bt + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + marvell,cal-data: + $ref: /schemas/types.yaml#/definitions/uint8-array + description: + Calibration data downloaded to the device during initialization. + maxItems: 28 + + marvell,wakeup-pin: + $ref: /schemas/types.yaml#/definitions/uint16 + description: + Wakeup pin number of the bluetooth chip. Used by firmware to wakeup host + system. + + marvell,wakeup-gap-ms: + $ref: /schemas/types.yaml#/definitions/uint16 + description: + Wakeup latency of the host platform. Required by the chip sleep feature. + +required: + - compatible + - reg + - interrupts + +additionalProperties: false + +examples: + - | + #include <dt-bindings/interrupt-controller/irq.h> + + mmc { + vmmc-supply = <&wlan_en_reg>; + bus-width = <4>; + cap-power-off-card; + keep-power-in-suspend; + + #address-cells = <1>; + #size-cells = <0>; + + bluetooth@2 { + compatible = "marvell,sd8897-bt"; + reg = <2>; + interrupt-parent = <&pio>; + interrupts = <119 IRQ_TYPE_LEVEL_LOW>; + + marvell,cal-data = /bits/ 8 < + 0x37 0x01 0x1c 0x00 0xff 0xff 0xff 0xff 0x01 0x7f 0x04 0x02 + 0x00 0x00 0xba 0xce 0xc0 0xc6 0x2d 0x00 0x00 0x00 0x00 0x00 + 0x00 0x00 0xf0 0x00>; + marvell,wakeup-pin = /bits/ 16 <0x0d>; + marvell,wakeup-gap-ms = /bits/ 16 <0x64>; + }; + }; + +... diff --git a/Documentation/devicetree/bindings/net/btusb.txt b/Documentation/devicetree/bindings/net/btusb.txt index f546b1f7dd6d..a68022a57c51 100644 --- a/Documentation/devicetree/bindings/net/btusb.txt +++ b/Documentation/devicetree/bindings/net/btusb.txt @@ -14,7 +14,7 @@ Required properties: Also, vendors that use btusb may have device additional properties, e.g: -Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt +Documentation/devicetree/bindings/net/bluetooth/marvell,sd8897-bt.yaml Optional properties: diff --git a/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml index 61ef60d8f1c7..2c9d37975bed 100644 --- a/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml +++ b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml @@ -109,6 +109,26 @@ properties: maximum: 32 minItems: 1 + pinctrl-0: + description: Default pinctrl state + + pinctrl-1: + description: Can be "sleep" or "wakeup" pinctrl state + + pinctrl-2: + description: Can be "sleep" or "wakeup" pinctrl state + + pinctrl-names: + description: + When present should contain at least "default" describing the default pin + states. Other states are "sleep" which describes the pinstate when + sleeping and "wakeup" describing the pins if wakeup is enabled. + minItems: 1 + items: + - const: default + - enum: [ sleep, wakeup ] + - const: wakeup + power-domains: description: Power domain provider node and an args specifier containing @@ -125,6 +145,11 @@ properties: minItems: 1 maxItems: 2 + wakeup-source: + $ref: /schemas/types.yaml#/definitions/phandle-array + description: + List of phandles to system idle states in which mcan can wakeup the system. + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml index c155c9c6db39..2d13638ebc6a 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml @@ -49,6 +49,11 @@ properties: Must be half or less of "clocks" frequency. maximum: 20000000 + gpio-controller: true + + "#gpio-cells": + const: 2 + required: - compatible - reg diff --git a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml index 1219c5cb601f..519a11fbe972 100644 --- a/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml +++ b/Documentation/devicetree/bindings/net/can/microchip,mpfs-can.yaml @@ -32,11 +32,15 @@ properties: - description: AHB peripheral clock - description: CAN bus clock + resets: + maxItems: 1 + required: - compatible - reg - interrupts - clocks + - resets additionalProperties: false @@ -46,6 +50,7 @@ examples: compatible = "microchip,mpfs-can"; reg = <0x2010c000 0x1000>; clocks = <&clkcfg 17>, <&clkcfg 37>; + resets = <&clkcfg 17>; interrupt-parent = <&plic>; interrupts = <56>; }; diff --git a/Documentation/devicetree/bindings/net/cdns,macb.yaml b/Documentation/devicetree/bindings/net/cdns,macb.yaml index 1029786a855c..cb14c35ba996 100644 --- a/Documentation/devicetree/bindings/net/cdns,macb.yaml +++ b/Documentation/devicetree/bindings/net/cdns,macb.yaml @@ -38,7 +38,10 @@ properties: - cdns,sam9x60-macb # Microchip sam9x60 SoC - microchip,mpfs-macb # Microchip PolarFire SoC - const: cdns,macb # Generic - + - items: + - const: microchip,pic64gx-macb # Microchip PIC64GX SoC + - const: microchip,mpfs-macb # Microchip PolarFire SoC + - const: cdns,macb # Generic - items: - enum: - atmel,sama5d3-macb # 10/100Mbit IP on Atmel sama5d3 SoCs @@ -47,18 +50,19 @@ properties: - const: cdns,macb # Generic - enum: - - atmel,sama5d29-gem # GEM XL IP (10/100) on Atmel sama5d29 SoCs - atmel,sama5d2-gem # GEM IP (10/100) on Atmel sama5d2 SoCs + - atmel,sama5d29-gem # GEM XL IP (10/100) on Atmel sama5d29 SoCs - atmel,sama5d3-gem # Gigabit IP on Atmel sama5d3 SoCs - atmel,sama5d4-gem # GEM IP (10/100) on Atmel sama5d4 SoCs + - cdns,emac # Generic + - cdns,gem # Generic + - cdns,macb # Generic - cdns,np4-macb # NP4 SoC devices - microchip,sama7g5-emac # Microchip SAMA7G5 ethernet interface - microchip,sama7g5-gem # Microchip SAMA7G5 gigabit ethernet interface + - mobileye,eyeq5-gem # Mobileye EyeQ5 SoCs - raspberrypi,rp1-gem # Raspberry Pi RP1 gigabit ethernet interface - sifive,fu540-c000-gem # SiFive FU540-C000 SoC - - cdns,emac # Generic - - cdns,gem # Generic - - cdns,macb # Generic - items: - enum: @@ -183,6 +187,15 @@ allOf: reg: maxItems: 1 + - if: + properties: + compatible: + contains: + const: mobileye,eyeq5-gem + then: + required: + - phys + unevaluatedProperties: false examples: diff --git a/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml b/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml index f3154b19af78..205b683849a5 100644 --- a/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml +++ b/Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml @@ -4,10 +4,14 @@ $id: http://devicetree.org/schemas/net/dsa/lantiq,gswip.yaml# $schema: http://devicetree.org/meta-schemas/core.yaml# -title: Lantiq GSWIP Ethernet switches +title: Lantiq GSWIP and MaxLinear GSW1xx Ethernet switches -allOf: - - $ref: dsa.yaml#/$defs/ethernet-ports +description: + Lantiq GSWIP and MaxLinear GSW1xx switches share the same hardware IP. + Lantiq switches are embedded in SoCs and accessed via memory-mapped I/O, + while MaxLinear switches are standalone ICs connected via MDIO. + +$ref: dsa.yaml# maintainers: - Hauke Mehrtens <hauke@hauke-m.de> @@ -18,9 +22,14 @@ properties: - lantiq,xrx200-gswip - lantiq,xrx300-gswip - lantiq,xrx330-gswip + - maxlinear,gsw120 + - maxlinear,gsw125 + - maxlinear,gsw140 + - maxlinear,gsw141 + - maxlinear,gsw145 reg: - minItems: 3 + minItems: 1 maxItems: 3 reg-names: @@ -37,9 +46,6 @@ properties: compatible: const: lantiq,xrx200-mdio - required: - - compatible - gphy-fw: type: object properties: @@ -91,10 +97,63 @@ properties: additionalProperties: false +patternProperties: + "^(ethernet-)?ports$": + type: object + patternProperties: + "^(ethernet-)?port@[0-6]$": + $ref: dsa-port.yaml# + unevaluatedProperties: false + + properties: + maxlinear,rmii-refclk-out: + type: boolean + description: + Configure the RMII reference clock to be a clock output + rather than an input. Only applicable for RMII mode. + tx-internal-delay-ps: + enum: [0, 500, 1000, 1500, 2000, 2500, 3000, 3500] + description: + RGMII TX Clock Delay defined in pico seconds. + The delay lines adjust the MII clock vs. data timing. + If this property is not present the delay is determined by + the interface mode. + rx-internal-delay-ps: + enum: [0, 500, 1000, 1500, 2000, 2500, 3000, 3500] + description: + RGMII RX Clock Delay defined in pico seconds. + The delay lines adjust the MII clock vs. data timing. + If this property is not present the delay is determined by + the interface mode. + required: - compatible - reg +allOf: + - if: + properties: + compatible: + contains: + enum: + - lantiq,xrx200-gswip + - lantiq,xrx300-gswip + - lantiq,xrx330-gswip + then: + properties: + reg: + minItems: 3 + maxItems: 3 + mdio: + required: + - compatible + else: + properties: + reg: + maxItems: 1 + reg-names: false + gphy-fw: false + unevaluatedProperties: false examples: @@ -113,8 +172,10 @@ examples: port@0 { reg = <0>; label = "lan3"; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; phy-handle = <&phy0>; + tx-internal-delay-ps = <2000>; + rx-internal-delay-ps = <2000>; }; port@1 { @@ -200,3 +261,90 @@ examples: }; }; }; + + - | + #include <dt-bindings/leds/common.h> + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switch@1f { + compatible = "maxlinear,gsw125"; + reg = <0x1f>; + + ports { + #address-cells = <1>; + #size-cells = <0>; + + port@0 { + reg = <0>; + label = "lan0"; + phy-handle = <&switchphy0>; + phy-mode = "internal"; + }; + + port@1 { + reg = <1>; + label = "lan1"; + phy-handle = <&switchphy1>; + phy-mode = "internal"; + }; + + port@4 { + reg = <4>; + label = "wan"; + phy-mode = "1000base-x"; + managed = "in-band-status"; + }; + + port@5 { + reg = <5>; + phy-mode = "rgmii-id"; + tx-internal-delay-ps = <2000>; + rx-internal-delay-ps = <2000>; + ethernet = <ð0>; + + fixed-link { + speed = <1000>; + full-duplex; + }; + }; + }; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switchphy0: switchphy@0 { + reg = <0>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + color = <LED_COLOR_ID_GREEN>; + function = LED_FUNCTION_LAN; + }; + }; + }; + + switchphy1: switchphy@1 { + reg = <1>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + color = <LED_COLOR_ID_GREEN>; + function = LED_FUNCTION_LAN; + }; + }; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/motorcomm,yt921x.yaml b/Documentation/devicetree/bindings/net/dsa/motorcomm,yt921x.yaml new file mode 100644 index 000000000000..33a6552e46fc --- /dev/null +++ b/Documentation/devicetree/bindings/net/dsa/motorcomm,yt921x.yaml @@ -0,0 +1,167 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/dsa/motorcomm,yt921x.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Motorcomm YT921x Ethernet switch family + +maintainers: + - David Yang <mmyangfl@gmail.com> + +description: | + The Motorcomm YT921x series is a family of Ethernet switches with up to 8 + internal GbE PHYs and up to 2 GMACs, including: + + - YT9215S / YT9215RB / YT9215SC: 5 GbE PHYs (Port 0-4) + 2 GMACs (Port 8-9) + - YT9213NB: 2 GbE PHYs (Port 1/3) + 1 GMAC (Port 9) + - YT9214NB: 2 GbE PHYs (Port 1/3) + 2 GMACs (Port 8-9) + - YT9218N: 8 GbE PHYs (Port 0-7) + - YT9218MB: 8 GbE PHYs (Port 0-7) + 2 GMACs (Port 8-9) + + Any port can be used as the CPU port. + +properties: + compatible: + const: motorcomm,yt9215 + + reg: + enum: [0x0, 0x1d] + + reset-gpios: + maxItems: 1 + + mdio: + $ref: /schemas/net/mdio.yaml# + unevaluatedProperties: false + description: + Internal MDIO bus for the internal GbE PHYs. PHY 0-7 are used for Port + 0-7 respectively. + + mdio-external: + $ref: /schemas/net/mdio.yaml# + unevaluatedProperties: false + description: + External MDIO bus to access external components. External PHYs for GMACs + (Port 8-9) are expected to be connected to the external MDIO bus in + vendor's reference design, but that is not a hard limitation from the + chip. + +required: + - compatible + - reg + +allOf: + - $ref: dsa.yaml#/$defs/ethernet-ports + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + switch@1d { + compatible = "motorcomm,yt9215"; + /* default 0x1d, alternate 0x0 */ + reg = <0x1d>; + reset-gpios = <&tlmm 39 GPIO_ACTIVE_LOW>; + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + sw_phy0: phy@0 { + reg = <0x0>; + }; + + sw_phy1: phy@1 { + reg = <0x1>; + }; + + sw_phy2: phy@2 { + reg = <0x2>; + }; + + sw_phy3: phy@3 { + reg = <0x3>; + }; + + sw_phy4: phy@4 { + reg = <0x4>; + }; + }; + + mdio-external { + #address-cells = <1>; + #size-cells = <0>; + + phy1: phy@b { + reg = <0xb>; + }; + }; + + ethernet-ports { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-port@0 { + reg = <0>; + label = "lan1"; + phy-mode = "internal"; + phy-handle = <&sw_phy0>; + }; + + ethernet-port@1 { + reg = <1>; + label = "lan2"; + phy-mode = "internal"; + phy-handle = <&sw_phy1>; + }; + + ethernet-port@2 { + reg = <2>; + label = "lan3"; + phy-mode = "internal"; + phy-handle = <&sw_phy2>; + }; + + ethernet-port@3 { + reg = <3>; + label = "lan4"; + phy-mode = "internal"; + phy-handle = <&sw_phy3>; + }; + + ethernet-port@4 { + reg = <4>; + label = "lan5"; + phy-mode = "internal"; + phy-handle = <&sw_phy4>; + }; + + /* CPU port */ + ethernet-port@8 { + reg = <8>; + phy-mode = "2500base-x"; + ethernet = <ð0>; + + fixed-link { + speed = <2500>; + full-duplex; + }; + }; + + /* if external phy is connected to a MAC */ + ethernet-port@9 { + reg = <9>; + label = "wan"; + phy-mode = "rgmii-id"; + phy-handle = <&phy1>; + }; + }; + }; + }; diff --git a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml index e9dd914b0734..607b7fe8d28e 100644 --- a/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml +++ b/Documentation/devicetree/bindings/net/dsa/nxp,sja1105.yaml @@ -41,6 +41,9 @@ properties: therefore discouraged. maxItems: 1 + clocks: + maxItems: 1 + spi-cpha: true spi-cpol: true diff --git a/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml b/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml new file mode 100644 index 000000000000..91e8cd1db67b --- /dev/null +++ b/Documentation/devicetree/bindings/net/eswin,eic7700-eth.yaml @@ -0,0 +1,129 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/eswin,eic7700-eth.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Eswin EIC7700 SOC Eth Controller + +maintainers: + - Shuang Liang <liangshuang@eswincomputing.com> + - Zhi Li <lizhi2@eswincomputing.com> + - Shangjuan Wei <weishangjuan@eswincomputing.com> + +description: + Platform glue layer implementation for STMMAC Ethernet driver. + +select: + properties: + compatible: + contains: + enum: + - eswin,eic7700-qos-eth + required: + - compatible + +allOf: + - $ref: snps,dwmac.yaml# + +properties: + compatible: + items: + - const: eswin,eic7700-qos-eth + - const: snps,dwmac-5.20 + + reg: + maxItems: 1 + + interrupts: + maxItems: 1 + + interrupt-names: + const: macirq + + clocks: + items: + - description: AXI clock + - description: Configuration clock + - description: GMAC main clock + - description: Tx clock + + clock-names: + items: + - const: axi + - const: cfg + - const: stmmaceth + - const: tx + + resets: + maxItems: 1 + + reset-names: + items: + - const: stmmaceth + + rx-internal-delay-ps: + enum: [0, 200, 600, 1200, 1600, 1800, 2000, 2200, 2400] + + tx-internal-delay-ps: + enum: [0, 200, 600, 1200, 1600, 1800, 2000, 2200, 2400] + + eswin,hsp-sp-csr: + description: + HSP CSR is to control and get status of different high-speed peripherals + (such as Ethernet, USB, SATA, etc.) via register, which can tune + board-level's parameters of PHY, etc. + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - items: + - description: Phandle to HSP(High-Speed Peripheral) device + - description: Offset of phy control register for internal + or external clock selection + - description: Offset of AXI clock controller Low-Power request + register + - description: Offset of register controlling TX/RX clock delay + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + - interrupt-names + - phy-mode + - resets + - reset-names + - rx-internal-delay-ps + - tx-internal-delay-ps + - eswin,hsp-sp-csr + +unevaluatedProperties: false + +examples: + - | + ethernet@50400000 { + compatible = "eswin,eic7700-qos-eth", "snps,dwmac-5.20"; + reg = <0x50400000 0x10000>; + clocks = <&d0_clock 186>, <&d0_clock 171>, <&d0_clock 40>, + <&d0_clock 193>; + clock-names = "axi", "cfg", "stmmaceth", "tx"; + interrupt-parent = <&plic>; + interrupts = <61>; + interrupt-names = "macirq"; + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + resets = <&reset 95>; + reset-names = "stmmaceth"; + rx-internal-delay-ps = <200>; + tx-internal-delay-ps = <200>; + eswin,hsp-sp-csr = <&hsp_sp_csr 0x100 0x108 0x118>; + snps,axi-config = <&stmmac_axi_setup>; + snps,aal; + snps,fixed-burst; + snps,tso; + stmmac_axi_setup: stmmac-axi-config { + snps,blen = <0 0 0 0 16 8 4>; + snps,rd_osr_lmt = <2>; + snps,wr_osr_lmt = <2>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml index 2ec2d9fda7e3..bb4c49fc5fd8 100644 --- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml @@ -35,9 +35,13 @@ properties: description: PHYs that implement IEEE802.3 clause 45 - pattern: "^ethernet-phy-id[a-f0-9]{4}\\.[a-f0-9]{4}$" description: - If the PHY reports an incorrect ID (or none at all) then the - compatible list may contain an entry with the correct PHY ID - in the above form. + PHYs contain identification registers. These will be read to + identify the PHY. If the PHY reports an incorrect ID, or the + PHY requires a specific initialization sequence (like a + particular order of clocks, resets, power supplies), in + order to be able to read the ID registers, then the + compatible list must contain an entry with the correct PHY + ID in the above form. The first group of digits is the 16 bit Phy Identifier 1 register, this is the chip vendor OUI bits 3:18. The second group of digits is the Phy Identifier 2 register, diff --git a/Documentation/devicetree/bindings/net/fsl,enetc.yaml b/Documentation/devicetree/bindings/net/fsl,enetc.yaml index ca70f0050171..aac20ab72ace 100644 --- a/Documentation/devicetree/bindings/net/fsl,enetc.yaml +++ b/Documentation/devicetree/bindings/net/fsl,enetc.yaml @@ -27,6 +27,7 @@ properties: - const: fsl,enetc - enum: - pci1131,e101 + - pci1131,e110 reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt deleted file mode 100644 index 957e5e5c2927..000000000000 --- a/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt +++ /dev/null @@ -1,83 +0,0 @@ -Marvell 8897/8997 (sd8897/sd8997) bluetooth devices (SDIO or USB based) ------- -The 8997 devices supports multiple interfaces. When used on SDIO interfaces, -the btmrvl driver is used and when used on USB interface, the btusb driver is -used. - -Required properties: - - - compatible : should be one of the following: - * "marvell,sd8897-bt" (for SDIO) - * "marvell,sd8997-bt" (for SDIO) - * "usb1286,204e" (for USB) - -Optional properties: - - - marvell,cal-data: Calibration data downloaded to the device during - initialization. This is an array of 28 values(u8). - This is only applicable to SDIO devices. - - - marvell,wakeup-pin: It represents wakeup pin number of the bluetooth chip. - firmware will use the pin to wakeup host system (u16). - - marvell,wakeup-gap-ms: wakeup gap represents wakeup latency of the host - platform. The value will be configured to firmware. This - is needed to work chip's sleep feature as expected (u16). - - interrupt-names: Used only for USB based devices (See below) - - interrupts : specifies the interrupt pin number to the cpu. For SDIO, the - driver will use the first interrupt specified in the interrupt - array. For USB based devices, the driver will use the interrupt - named "wakeup" from the interrupt-names and interrupt arrays. - The driver will request an irq based on this interrupt number. - During system suspend, the irq will be enabled so that the - bluetooth chip can wakeup host platform under certain - conditions. During system resume, the irq will be disabled - to make sure unnecessary interrupt is not received. - -Example: - -IRQ pin 119 is used as system wakeup source interrupt. -wakeup pin 13 and gap 100ms are configured so that firmware can wakeup host -using this device side pin and wakeup latency. - -Example for SDIO device follows (calibration data is also available in -below example). - -&mmc3 { - vmmc-supply = <&wlan_en_reg>; - bus-width = <4>; - cap-power-off-card; - keep-power-in-suspend; - - #address-cells = <1>; - #size-cells = <0>; - btmrvl: bluetooth@2 { - compatible = "marvell,sd8897-bt"; - reg = <2>; - interrupt-parent = <&pio>; - interrupts = <119 IRQ_TYPE_LEVEL_LOW>; - - marvell,cal-data = /bits/ 8 < - 0x37 0x01 0x1c 0x00 0xff 0xff 0xff 0xff 0x01 0x7f 0x04 0x02 - 0x00 0x00 0xba 0xce 0xc0 0xc6 0x2d 0x00 0x00 0x00 0x00 0x00 - 0x00 0x00 0xf0 0x00>; - marvell,wakeup-pin = /bits/ 16 <0x0d>; - marvell,wakeup-gap-ms = /bits/ 16 <0x64>; - }; -}; - -Example for USB device: - -&usb_host1_ohci { - #address-cells = <1>; - #size-cells = <0>; - - mvl_bt1: bt@1 { - compatible = "usb1286,204e"; - reg = <1>; - interrupt-parent = <&gpio0>; - interrupt-names = "wakeup"; - interrupts = <119 IRQ_TYPE_LEVEL_LOW>; - marvell,wakeup-pin = /bits/ 16 <0x0d>; - marvell,wakeup-gap-ms = /bits/ 16 <0x64>; - }; -}; diff --git a/Documentation/devicetree/bindings/net/mediatek,net.yaml b/Documentation/devicetree/bindings/net/mediatek,net.yaml index b45f67f92e80..cc346946291a 100644 --- a/Documentation/devicetree/bindings/net/mediatek,net.yaml +++ b/Documentation/devicetree/bindings/net/mediatek,net.yaml @@ -112,7 +112,7 @@ properties: mediatek,wed: $ref: /schemas/types.yaml#/definitions/phandle-array - minItems: 2 + minItems: 1 maxItems: 2 items: maxItems: 1 @@ -249,6 +249,9 @@ allOf: minItems: 1 maxItems: 1 + mediatek,wed: + minItems: 2 + mediatek,wed-pcie: false else: properties: @@ -338,12 +341,13 @@ allOf: - const: netsys0 - const: netsys1 - mediatek,infracfg: false - mediatek,sgmiisys: minItems: 2 maxItems: 2 + mediatek,wed: + maxItems: 1 + - if: properties: compatible: @@ -385,6 +389,9 @@ allOf: minItems: 2 maxItems: 2 + mediatek,wed: + minItems: 2 + - if: properties: compatible: @@ -429,6 +436,19 @@ allOf: - const: xgp2 - const: xgp3 + mediatek,wed: + minItems: 2 + + - if: + properties: + compatible: + contains: + const: ralink,rt5350-eth + then: + properties: + mediatek,wed: + minItems: 2 + patternProperties: "^mac@[0-2]$": type: object diff --git a/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt b/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt deleted file mode 100644 index 0a3647fe331b..000000000000 --- a/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt +++ /dev/null @@ -1,73 +0,0 @@ -* Microsemi - vsc8531 Giga bit ethernet phy - -Optional properties: -- vsc8531,vddmac : The vddmac in mV. Allowed values is listed - in the first row of Table 1 (below). - This property is only used in combination - with the 'edge-slowdown' property. - Default value is 3300. -- vsc8531,edge-slowdown : % the edge should be slowed down relative to - the fastest possible edge time. - Edge rate sets the drive strength of the MAC - interface output signals. Changing the - drive strength will affect the edge rate of - the output signal. The goal of this setting - is to help reduce electrical emission (EMI) - by being able to reprogram drive strength - and in effect slow down the edge rate if - desired. - To adjust the edge-slowdown, the 'vddmac' - must be specified. Table 1 lists the - supported edge-slowdown values for a given - 'vddmac'. - Default value is 0%. - Ref: Table:1 - Edge rate change (below). -- vsc8531,led-[N]-mode : LED mode. Specify how the LED[N] should behave. - N depends on the number of LEDs supported by a - PHY. - Allowed values are defined in - "include/dt-bindings/net/mscc-phy-vsc8531.h". - Default values are VSC8531_LINK_1000_ACTIVITY (1), - VSC8531_LINK_100_ACTIVITY (2), - VSC8531_LINK_ACTIVITY (0) and - VSC8531_DUPLEX_COLLISION (8). -- load-save-gpios : GPIO used for the load/save operation of the PTP - hardware clock (PHC). - - -Table: 1 - Edge rate change -----------------------------------------------------------------| -| Edge Rate Change (VDDMAC) | -| | -| 3300 mV 2500 mV 1800 mV 1500 mV | -|---------------------------------------------------------------| -| 0% 0% 0% 0% | -| (Fastest) (recommended) (recommended) | -|---------------------------------------------------------------| -| 2% 3% 5% 6% | -|---------------------------------------------------------------| -| 4% 6% 9% 14% | -|---------------------------------------------------------------| -| 7% 10% 16% 21% | -|(recommended) (recommended) | -|---------------------------------------------------------------| -| 10% 14% 23% 29% | -|---------------------------------------------------------------| -| 17% 23% 35% 42% | -|---------------------------------------------------------------| -| 29% 37% 52% 58% | -|---------------------------------------------------------------| -| 53% 63% 76% 77% | -| (slowest) | -|---------------------------------------------------------------| - -Example: - - vsc8531_0: ethernet-phy@0 { - compatible = "ethernet-phy-id0007.0570"; - vsc8531,vddmac = <3300>; - vsc8531,edge-slowdown = <7>; - vsc8531,led-0-mode = <VSC8531_LINK_1000_ACTIVITY>; - vsc8531,led-1-mode = <VSC8531_LINK_100_ACTIVITY>; - load-save-gpios = <&gpio 10 GPIO_ACTIVE_HIGH>; - }; diff --git a/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.yaml b/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.yaml new file mode 100644 index 000000000000..0afbd0ff126f --- /dev/null +++ b/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.yaml @@ -0,0 +1,131 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/mscc-phy-vsc8531.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Microsemi VSC8531 Gigabit Ethernet PHY + +maintainers: + - Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> + +description: + The VSC8531 is a Gigabit Ethernet PHY with configurable MAC interface + drive strength and LED modes. + +allOf: + - $ref: ethernet-phy.yaml# + +select: + properties: + compatible: + contains: + enum: + - ethernet-phy-id0007.0570 # VSC8531 + - ethernet-phy-id0007.0772 # VSC8541 + required: + - compatible + +properties: + compatible: + items: + - enum: + - ethernet-phy-id0007.0570 # VSC8531 + - ethernet-phy-id0007.0772 # VSC8541 + - const: ethernet-phy-ieee802.3-c22 + + vsc8531,vddmac: + $ref: /schemas/types.yaml#/definitions/uint32 + description: + The VDDMAC voltage in millivolts. This property is used in combination + with the edge-slowdown property to control the drive strength of the + MAC interface output signals. + enum: [3300, 2500, 1800, 1500] + default: 3300 + + vsc8531,edge-slowdown: + $ref: /schemas/types.yaml#/definitions/uint32 + description: > + Percentage by which the edge rate should be slowed down relative to + the fastest possible edge time. This setting helps reduce electromagnetic + interference (EMI) by adjusting the drive strength of the MAC interface + output signals. Valid values depend on the vddmac voltage setting + according to the edge rate change table in the datasheet. + + - When vsc8531,vddmac = 3300 mV: allowed values are 0, 2, 4, 7, 10, 17, 29, and 53. + (Recommended: 7) + - When vsc8531,vddmac = 2500 mV: allowed values are 0, 3, 6, 10, 14, 23, 37, and 63. + (Recommended: 10) + - When vsc8531,vddmac = 1800 mV: allowed values are 0, 5, 9, 16, 23, 35, 52, and 76. + (Recommended: 0) + - When vsc8531,vddmac = 1500 mV: allowed values are 0, 6, 14, 21, 29, 42, 58, and 77. + (Recommended: 0) + enum: [0, 2, 3, 4, 5, 6, 7, 9, 10, 14, 16, 17, 21, 23, 29, 35, 37, 42, 52, 53, 58, 63, 76, 77] + default: 0 + + vsc8531,led-0-mode: + $ref: /schemas/types.yaml#/definitions/uint32 + description: LED[0] behavior mode. See include/dt-bindings/net/mscc-phy-vsc8531.h + for available modes. + minimum: 0 + maximum: 15 + default: 1 + + vsc8531,led-1-mode: + $ref: /schemas/types.yaml#/definitions/uint32 + description: LED[1] behavior mode. See include/dt-bindings/net/mscc-phy-vsc8531.h + for available modes. + minimum: 0 + maximum: 15 + default: 2 + + vsc8531,led-2-mode: + $ref: /schemas/types.yaml#/definitions/uint32 + description: LED[2] behavior mode. See include/dt-bindings/net/mscc-phy-vsc8531.h + for available modes. + minimum: 0 + maximum: 15 + default: 0 + + vsc8531,led-3-mode: + $ref: /schemas/types.yaml#/definitions/uint32 + description: LED[3] behavior mode. See include/dt-bindings/net/mscc-phy-vsc8531.h + for available modes. + minimum: 0 + maximum: 15 + default: 8 + + load-save-gpios: + description: GPIO phandle used for the load/save operation of the PTP hardware + clock (PHC). + maxItems: 1 + +dependencies: + vsc8531,edge-slowdown: + - vsc8531,vddmac + +required: + - compatible + - reg + +unevaluatedProperties: false + +examples: + - | + #include <dt-bindings/gpio/gpio.h> + #include <dt-bindings/net/mscc-phy-vsc8531.h> + + mdio { + #address-cells = <1>; + #size-cells = <0>; + + ethernet-phy@0 { + compatible = "ethernet-phy-id0007.0772", "ethernet-phy-ieee802.3-c22"; + reg = <0>; + vsc8531,vddmac = <3300>; + vsc8531,edge-slowdown = <7>; + vsc8531,led-0-mode = <VSC8531_LINK_1000_ACTIVITY>; + vsc8531,led-1-mode = <VSC8531_LINK_100_ACTIVITY>; + load-save-gpios = <&gpio 10 GPIO_ACTIVE_HIGH>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml b/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml index 97389fd5dbbf..deea4fd73d76 100644 --- a/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml +++ b/Documentation/devicetree/bindings/net/nxp,netc-blk-ctrl.yaml @@ -21,6 +21,7 @@ maintainers: properties: compatible: enum: + - nxp,imx94-netc-blk-ctrl - nxp,imx95-netc-blk-ctrl reg: diff --git a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml index bb1ee3398655..0b3803f647b7 100644 --- a/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml +++ b/Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml @@ -16,6 +16,7 @@ properties: compatible: enum: - ti,tps23881 + - ti,tps23881b reg: maxItems: 1 diff --git a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml index e7ee0d9efed8..423959cb928d 100644 --- a/Documentation/devicetree/bindings/net/qcom,ethqos.yaml +++ b/Documentation/devicetree/bindings/net/qcom,ethqos.yaml @@ -73,6 +73,14 @@ properties: dma-coherent: true + interconnects: + maxItems: 2 + + interconnect-names: + items: + - const: cpu-mac + - const: mac-mem + phys: true phy-names: diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml index 0ac7c4b47d6b..d17112527dab 100644 --- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml @@ -24,6 +24,7 @@ select: - rockchip,rk3366-gmac - rockchip,rk3368-gmac - rockchip,rk3399-gmac + - rockchip,rk3506-gmac - rockchip,rk3528-gmac - rockchip,rk3568-gmac - rockchip,rk3576-gmac @@ -50,6 +51,7 @@ properties: - rockchip,rv1108-gmac - items: - enum: + - rockchip,rk3506-gmac - rockchip,rk3528-gmac - rockchip,rk3568-gmac - rockchip,rk3576-gmac @@ -148,6 +150,7 @@ allOf: compatible: contains: enum: + - rockchip,rk3506-gmac - rockchip,rk3528-gmac then: properties: diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml index 658c004e6a5c..dd3c72e8363e 100644 --- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml +++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml @@ -86,10 +86,14 @@ properties: - rockchip,rk3328-gmac - rockchip,rk3366-gmac - rockchip,rk3368-gmac + - rockchip,rk3399-gmac + - rockchip,rk3506-gmac + - rockchip,rk3528-gmac + - rockchip,rk3568-gmac - rockchip,rk3576-gmac - rockchip,rk3588-gmac - - rockchip,rk3399-gmac - rockchip,rv1108-gmac + - rockchip,rv1126-gmac - snps,dwmac - snps,dwmac-3.40a - snps,dwmac-3.50a diff --git a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml index ce21979a2d9a..e8d3814db0e9 100644 --- a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml +++ b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml @@ -70,6 +70,25 @@ required: allOf: - $ref: snps,dwmac.yaml# + - if: + properties: + compatible: + contains: + const: sophgo,sg2042-dwmac + then: + properties: + phy-mode: + enum: + - rgmii-rxid + - rgmii-id + else: + properties: + phy-mode: + enum: + - rgmii + - rgmii-rxid + - rgmii-txid + - rgmii-id unevaluatedProperties: false diff --git a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml index eabceb849537..ae6b97cdc44b 100644 --- a/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml +++ b/Documentation/devicetree/bindings/net/wireless/mediatek,mt76.yaml @@ -151,6 +151,12 @@ properties: - ETSI - JP + country: + $ref: /schemas/types.yaml#/definitions/string + pattern: '^[A-Z]{2}$' + description: + ISO 3166-1 alpha-2 country code for power limits + patternProperties: "^txpower-[256]g$": type: object @@ -210,6 +216,66 @@ properties: minItems: 13 maxItems: 13 + paths-cck: + $ref: /schemas/types.yaml#/definitions/uint8-array + minItems: 4 + maxItems: 4 + description: + 4 half-dBm backoff values (1 - 4 antennas, single spacial + stream) + + paths-ofdm: + $ref: /schemas/types.yaml#/definitions/uint8-array + minItems: 4 + maxItems: 4 + description: + 4 half-dBm backoff values (1 - 4 antennas, single spacial + stream) + + paths-ofdm-bf: + $ref: /schemas/types.yaml#/definitions/uint8-array + minItems: 4 + maxItems: 4 + description: + 4 half-dBm backoff values for beamforming + (1 - 4 antennas, single spacial stream) + + paths-ru: + $ref: /schemas/types.yaml#/definitions/uint8-matrix + description: + Sets of half-dBm backoff values for 802.11ax rates for + 1T1ss (aka 1 transmitting antenna with 1 spacial stream), + 2T1ss, 3T1ss, 4T1ss, 2T2ss, 3T2ss, 4T2ss, 3T3ss, 4T3ss + and 4T4ss. + Each set starts with the number of channel bandwidth or + resource unit settings for which the rate set applies, + followed by 10 power limit values. The order of the + channel resource unit settings is RU26, RU52, RU106, + RU242/SU20, RU484/SU40, RU996/SU80 and RU2x996/SU160. + minItems: 1 + maxItems: 7 + items: + minItems: 11 + maxItems: 11 + + paths-ru-bf: + $ref: /schemas/types.yaml#/definitions/uint8-matrix + description: + Sets of half-dBm backoff (beamforming) values for 802.11ax + rates for 1T1ss (aka 1 transmitting antenna with 1 spacial + stream), 2T1ss, 3T1ss, 4T1ss, 2T2ss, 3T2ss, 4T2ss, 3T3ss, + 4T3ss and 4T4ss. + Each set starts with the number of channel bandwidth or + resource unit settings for which the rate set applies, + followed by 10 power limit values. The order of the + channel resource unit settings is RU26, RU52, RU106, + RU242/SU20, RU484/SU40, RU996/SU80 and RU2x996/SU160. + minItems: 1 + maxItems: 7 + items: + minItems: 11 + maxItems: 11 + txs-delta: $ref: /schemas/types.yaml#/definitions/uint32-array description: diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index 647746e6f75f..beab81e462d2 100644 --- a/Documentation/devicetree/bindings/vendor-prefixes.yaml +++ b/Documentation/devicetree/bindings/vendor-prefixes.yaml @@ -20,7 +20,7 @@ patternProperties: "^(keypad|m25p|max8952|max8997|max8998|mpmc),.*": true "^(pciclass|pinctrl-single|#pinctrl-single|PowerPC),.*": true "^(pl022|pxa-mmc|rcar_sound|rotary-encoder|s5m8767|sdhci),.*": true - "^(simple-audio-card|st-plgpio|st-spics|ts),.*": true + "^(simple-audio-card|st-plgpio|st-spics|ts|vsc8531),.*": true "^pool[0-3],.*": true # Keep list in alphabetical order. diff --git a/Documentation/driver-api/dpll.rst b/Documentation/driver-api/dpll.rst index be1fc643b645..83118c728ed9 100644 --- a/Documentation/driver-api/dpll.rst +++ b/Documentation/driver-api/dpll.rst @@ -198,26 +198,28 @@ be requested with the same attribute with ``DPLL_CMD_DEVICE_SET`` command. ================================== ====================================== Device may also provide ability to adjust a signal phase on a pin. -If pin phase adjustment is supported, minimal and maximal values that pin -handle shall be provide to the user on ``DPLL_CMD_PIN_GET`` respond -with ``DPLL_A_PIN_PHASE_ADJUST_MIN`` and ``DPLL_A_PIN_PHASE_ADJUST_MAX`` +If pin phase adjustment is supported, minimal and maximal values and +granularity that pin handle shall be provided to the user on +``DPLL_CMD_PIN_GET`` respond with ``DPLL_A_PIN_PHASE_ADJUST_MIN``, +``DPLL_A_PIN_PHASE_ADJUST_MAX`` and ``DPLL_A_PIN_PHASE_ADJUST_GRAN`` attributes. Configured phase adjust value is provided with ``DPLL_A_PIN_PHASE_ADJUST`` attribute of a pin, and value change can be requested with the same attribute with ``DPLL_CMD_PIN_SET`` command. - =============================== ====================================== - ``DPLL_A_PIN_ID`` configured pin id - ``DPLL_A_PIN_PHASE_ADJUST_MIN`` attr minimum value of phase adjustment - ``DPLL_A_PIN_PHASE_ADJUST_MAX`` attr maximum value of phase adjustment - ``DPLL_A_PIN_PHASE_ADJUST`` attr configured value of phase - adjustment on parent dpll device - ``DPLL_A_PIN_PARENT_DEVICE`` nested attribute for requesting - configuration on given parent dpll - device - ``DPLL_A_PIN_PARENT_ID`` parent dpll device id - ``DPLL_A_PIN_PHASE_OFFSET`` attr measured phase difference - between a pin and parent dpll device - =============================== ====================================== + ================================ ========================================== + ``DPLL_A_PIN_ID`` configured pin id + ``DPLL_A_PIN_PHASE_ADJUST_GRAN`` attr granularity of phase adjustment value + ``DPLL_A_PIN_PHASE_ADJUST_MIN`` attr minimum value of phase adjustment + ``DPLL_A_PIN_PHASE_ADJUST_MAX`` attr maximum value of phase adjustment + ``DPLL_A_PIN_PHASE_ADJUST`` attr configured value of phase + adjustment on parent dpll device + ``DPLL_A_PIN_PARENT_DEVICE`` nested attribute for requesting + configuration on given parent dpll + device + ``DPLL_A_PIN_PARENT_ID`` parent dpll device id + ``DPLL_A_PIN_PHASE_OFFSET`` attr measured phase difference + between a pin and parent dpll device + ================================ ========================================== All phase related values are provided in pico seconds, which represents time difference between signals phase. The negative value means that @@ -384,6 +386,8 @@ according to attribute purpose. frequencies ``DPLL_A_PIN_ANY_FREQUENCY_MIN`` attr minimum value of frequency ``DPLL_A_PIN_ANY_FREQUENCY_MAX`` attr maximum value of frequency + ``DPLL_A_PIN_PHASE_ADJUST_GRAN`` attr granularity of phase + adjustment value ``DPLL_A_PIN_PHASE_ADJUST_MIN`` attr minimum value of phase adjustment ``DPLL_A_PIN_PHASE_ADJUST_MAX`` attr maximum value of phase diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml index 5a234e9b5fa2..57f59fe23e3f 100644 --- a/Documentation/netlink/genetlink-c.yaml +++ b/Documentation/netlink/genetlink-c.yaml @@ -227,7 +227,7 @@ properties: Optional format indicator that is intended only for choosing the right formatting mechanism when displaying values of this type. - enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + enum: [ hex, mac, fddi, ipv4, ipv6, ipv4-or-v6, uuid ] # Start genetlink-c name-prefix: type: string diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml index 7b1ec153e834..b020a537d8ac 100644 --- a/Documentation/netlink/genetlink.yaml +++ b/Documentation/netlink/genetlink.yaml @@ -185,7 +185,7 @@ properties: Optional format indicator that is intended only for choosing the right formatting mechanism when displaying values of this type. - enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + enum: [ hex, mac, fddi, ipv4, ipv6, ipv4-or-v6, uuid ] # Make sure name-prefix does not appear in subsets (subsets inherit naming) dependencies: diff --git a/Documentation/netlink/netlink-raw.yaml b/Documentation/netlink/netlink-raw.yaml index 246fa07bccf6..0166a7e4afbb 100644 --- a/Documentation/netlink/netlink-raw.yaml +++ b/Documentation/netlink/netlink-raw.yaml @@ -157,7 +157,7 @@ properties: Optional format indicator that is intended only for choosing the right formatting mechanism when displaying values of this type. - enum: [ hex, mac, fddi, ipv4, ipv6, uuid ] + enum: [ hex, mac, fddi, ipv4, ipv6, ipv4-or-v6, uuid ] struct: description: Name of the nested struct type. type: string diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml index bef528633b17..db7cddcda50a 100644 --- a/Documentation/netlink/specs/conntrack.yaml +++ b/Documentation/netlink/specs/conntrack.yaml @@ -457,7 +457,7 @@ attribute-sets: name: labels type: binary - - name: labels mask + name: labels-mask type: binary - name: synproxy diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 3db59c965869..837112da6738 100644 --- a/Documentation/netlink/specs/devlink.yaml +++ b/Documentation/netlink/specs/devlink.yaml @@ -99,6 +99,8 @@ definitions: name: legacy - name: switchdev + - + name: switchdev-inactive - type: enum name: eswitch-inline-mode @@ -857,6 +859,14 @@ attribute-sets: name: health-reporter-burst-period type: u64 doc: Time (in msec) for recoveries before starting the grace period. + + # TODO: fill in the attributes in between + + - + name: param-reset-default + type: flag + doc: Request restoring parameter to its default value. + value: 183 - name: dl-dev-stats subset-of: devlink @@ -1791,6 +1801,7 @@ operations: - param-type # param-value-data is missing here as the type is variable - param-value-cmode + - param-reset-default - name: region-get diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 80728f6f9bc8..78d0724d7e12 100644 --- a/Documentation/netlink/specs/dpll.yaml +++ b/Documentation/netlink/specs/dpll.yaml @@ -440,6 +440,12 @@ attribute-sets: doc: | Capable pin provides list of pins that can be bound to create a reference-sync pin pair. + - + name: phase-adjust-gran + type: u32 + doc: | + Granularity of phase adjustment, in picoseconds. The value of + phase adjustment must be a multiple of this granularity. - name: pin-parent-device @@ -616,6 +622,7 @@ operations: - capabilities - parent-device - parent-pin + - phase-adjust-gran - phase-adjust-min - phase-adjust-max - phase-adjust diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml index 6a0fb1974513..0a2d2343f79a 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -1269,7 +1269,7 @@ attribute-sets: - name: hist type: nest - multi-attr: True + multi-attr: true nested-attributes: fec-hist - name: fec @@ -1823,6 +1823,73 @@ attribute-sets: type: uint enum: pse-event doc: List of events reported by the PSE controller + - + name: mse-capabilities + doc: MSE capabilities attribute set + attr-cnt-name: --ethtool-a-mse-capabilities-cnt + attributes: + - + name: max-average-mse + type: uint + - + name: max-peak-mse + type: uint + - + name: refresh-rate-ps + type: uint + - + name: num-symbols + type: uint + - + name: mse-snapshot + doc: MSE snapshot attribute set + attr-cnt-name: --ethtool-a-mse-snapshot-cnt + attributes: + - + name: average-mse + type: uint + - + name: peak-mse + type: uint + - + name: worst-peak-mse + type: uint + - + name: mse + attr-cnt-name: --ethtool-a-mse-cnt + attributes: + - + name: header + type: nest + nested-attributes: header + - + name: capabilities + type: nest + nested-attributes: mse-capabilities + - + name: channel-a + type: nest + nested-attributes: mse-snapshot + - + name: channel-b + type: nest + nested-attributes: mse-snapshot + - + name: channel-c + type: nest + nested-attributes: mse-snapshot + - + name: channel-d + type: nest + nested-attributes: mse-snapshot + - + name: worst-channel + type: nest + nested-attributes: mse-snapshot + - + name: link + type: nest + nested-attributes: mse-snapshot operations: enum-model: directional @@ -2756,6 +2823,25 @@ operations: attributes: - header - context + - + name: mse-get + doc: Get PHY MSE measurement data and capabilities. + attribute-set: mse + do: &mse-get-op + request: + attributes: + - header + reply: + attributes: + - header + - capabilities + - channel-a + - channel-b + - channel-c + - channel-d + - worst-channel + - link + dump: *mse-get-op mcast-groups: list: diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index e00d3fa1c152..82bf5cb2617d 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -88,7 +88,7 @@ definitions: - name: napi-threaded type: enum - entries: [disabled, enabled] + entries: [disabled, enabled, busy-poll] attribute-sets: - @@ -291,7 +291,8 @@ attribute-sets: name: threaded doc: Whether the NAPI is configured to operate in threaded polling mode. If this is set to enabled then the NAPI context operates - in threaded polling mode. + in threaded polling mode. If this is set to busy-poll, then the + threaded polling mode also busy polls. type: u32 enum: napi-threaded - @@ -732,6 +733,29 @@ operations: - rx-bytes - tx-packets - tx-bytes + - rx-alloc-fail + - rx-hw-drops + - rx-hw-drop-overruns + - rx-csum-complete + - rx-csum-unnecessary + - rx-csum-none + - rx-csum-bad + - rx-hw-gro-packets + - rx-hw-gro-bytes + - rx-hw-gro-wire-packets + - rx-hw-gro-wire-bytes + - rx-hw-drop-ratelimits + - tx-hw-drops + - tx-hw-drop-errors + - tx-csum-none + - tx-needs-csum + - tx-hw-gso-packets + - tx-hw-gso-bytes + - tx-hw-gso-wire-packets + - tx-hw-gso-wire-bytes + - tx-hw-drop-ratelimits + - tx-stop + - tx-wake - name: bind-rx doc: Bind dmabuf to netdev diff --git a/Documentation/netlink/specs/nftables.yaml b/Documentation/netlink/specs/nftables.yaml index cce88819ba71..17ad707fa0d5 100644 --- a/Documentation/netlink/specs/nftables.yaml +++ b/Documentation/netlink/specs/nftables.yaml @@ -915,7 +915,7 @@ attribute-sets: type: string doc: Name of set to use - - name: set id + name: set-id type: u32 byte-order: big-endian doc: ID of set to use diff --git a/Documentation/netlink/specs/psp.yaml b/Documentation/netlink/specs/psp.yaml index 944429e5c9a8..f3a57782d2cf 100644 --- a/Documentation/netlink/specs/psp.yaml +++ b/Documentation/netlink/specs/psp.yaml @@ -76,6 +76,83 @@ attribute-sets: name: spi doc: Security Parameters Index (SPI) of the association. type: u32 + - + name: stats + attributes: + - + name: dev-id + doc: PSP device ID. + type: u32 + checks: + min: 1 + - + name: key-rotations + type: uint + doc: | + Number of key rotations during the lifetime of the device. + Kernel statistic. + - + name: stale-events + type: uint + doc: | + Number of times a socket's Rx got shut down due to using + a key which went stale (fully rotated out). + Kernel statistic. + - + name: rx-packets + type: uint + doc: | + Number of successfully processed and authenticated PSP packets. + Device statistic (from the PSP spec). + - + name: rx-bytes + type: uint + doc: | + Number of successfully authenticated PSP bytes received, counting from + the first byte after the IV through the last byte of payload. + The fixed initial portion of the PSP header (16 bytes) + and the PSP trailer/ICV (16 bytes) are not included in this count. + Device statistic (from the PSP spec). + - + name: rx-auth-fail + type: uint + doc: | + Number of received PSP packets with unsuccessful authentication. + Device statistic (from the PSP spec). + - + name: rx-error + type: uint + doc: | + Number of received PSP packets with length/framing errors. + Device statistic (from the PSP spec). + - + name: rx-bad + type: uint + doc: | + Number of received PSP packets with miscellaneous errors + (invalid master key indicated by SPI, unsupported version, etc.) + Device statistic (from the PSP spec). + - + name: tx-packets + type: uint + doc: | + Number of successfully processed PSP packets for transmission. + Device statistic (from the PSP spec). + - + name: tx-bytes + type: uint + doc: | + Number of successfully processed PSP bytes for transmit, counting from + the first byte after the IV through the last byte of payload. + The fixed initial portion of the PSP header (16 bytes) + and the PSP trailer/ICV (16 bytes) are not included in this count. + Device statistic (from the PSP spec). + - + name: tx-error + type: uint + doc: | + Number of PSP packets for transmission with errors. + Device statistic (from the PSP spec). operations: list: @@ -177,6 +254,24 @@ operations: pre: psp-assoc-device-get-locked post: psp-device-unlock + - + name: get-stats + doc: Get device statistics. + attribute-set: stats + do: + request: + attributes: + - dev-id + reply: &stats-all + attributes: + - dev-id + - key-rotations + - stale-events + pre: psp-device-get-locked + post: psp-device-unlock + dump: + reply: *stats-all + mcast-groups: list: - diff --git a/Documentation/netlink/specs/rt-addr.yaml b/Documentation/netlink/specs/rt-addr.yaml index 3a582eac1629..163a106c41bb 100644 --- a/Documentation/netlink/specs/rt-addr.yaml +++ b/Documentation/netlink/specs/rt-addr.yaml @@ -86,17 +86,18 @@ attribute-sets: - name: address type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: label type: string - name: broadcast - type: binary + type: u32 + byte-order: big-endian display-hint: ipv4 - name: anycast diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 2a23e9699c0b..6beeb6ee5adf 100644 --- a/Documentation/netlink/specs/rt-link.yaml +++ b/Documentation/netlink/specs/rt-link.yaml @@ -1707,11 +1707,11 @@ attribute-sets: - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: remote type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: ttl type: u8 @@ -1833,11 +1833,11 @@ attribute-sets: - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: remote type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: fwmark type: u32 @@ -1868,7 +1868,8 @@ attribute-sets: type: u32 - name: remote - type: binary + type: u32 + byte-order: big-endian display-hint: ipv4 - name: ttl @@ -1914,6 +1915,35 @@ attribute-sets: type: binary struct: ifla-geneve-port-range - + name: linkinfo-hsr-attrs + name-prefix: ifla-hsr- + attributes: + - + name: slave1 + type: u32 + - + name: slave2 + type: u32 + - + name: multicast-spec + type: u8 + - + name: supervision-addr + type: binary + display-hint: mac + - + name: seq-nr + type: u16 + - + name: version + type: u8 + - + name: protocol + type: u8 + - + name: interlink + type: u32 + - name: linkinfo-iptun-attrs name-prefix: ifla-iptun- attributes: @@ -1923,11 +1953,11 @@ attribute-sets: - name: local type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: remote type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: ttl type: u8 @@ -1957,7 +1987,8 @@ attribute-sets: display-hint: ipv6 - name: 6rd-relay-prefix - type: binary + type: u32 + byte-order: big-endian display-hint: ipv4 - name: 6rd-prefixlen @@ -2300,6 +2331,9 @@ sub-messages: value: geneve attribute-set: linkinfo-geneve-attrs - + value: hsr + attribute-set: linkinfo-hsr-attrs + - value: ipip attribute-set: linkinfo-iptun-attrs - diff --git a/Documentation/netlink/specs/rt-neigh.yaml b/Documentation/netlink/specs/rt-neigh.yaml index 2f568a6231c9..0f46ef313590 100644 --- a/Documentation/netlink/specs/rt-neigh.yaml +++ b/Documentation/netlink/specs/rt-neigh.yaml @@ -194,7 +194,7 @@ attribute-sets: - name: dst type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: lladdr type: binary diff --git a/Documentation/netlink/specs/rt-route.yaml b/Documentation/netlink/specs/rt-route.yaml index 1ecb3fadc067..33195db96746 100644 --- a/Documentation/netlink/specs/rt-route.yaml +++ b/Documentation/netlink/specs/rt-route.yaml @@ -87,11 +87,11 @@ attribute-sets: - name: dst type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: src type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: iif type: u32 @@ -101,14 +101,14 @@ attribute-sets: - name: gateway type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: priority type: u32 - name: prefsrc type: binary - display-hint: ipv4 + display-hint: ipv4-or-v6 - name: metrics type: nest diff --git a/Documentation/netlink/specs/rt-rule.yaml b/Documentation/netlink/specs/rt-rule.yaml index bebee452a950..7f03a44ab036 100644 --- a/Documentation/netlink/specs/rt-rule.yaml +++ b/Documentation/netlink/specs/rt-rule.yaml @@ -96,10 +96,12 @@ attribute-sets: attributes: - name: dst - type: u32 + type: binary + display-hint: ipv4-or-v6 - name: src - type: u32 + type: binary + display-hint: ipv4-or-v6 - name: iifname type: string diff --git a/Documentation/netlink/specs/wireguard.yaml b/Documentation/netlink/specs/wireguard.yaml new file mode 100644 index 000000000000..30479fc6bb69 --- /dev/null +++ b/Documentation/netlink/specs/wireguard.yaml @@ -0,0 +1,298 @@ +# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) +--- +name: wireguard +protocol: genetlink-legacy + +doc: | + **Netlink protocol to control WireGuard network devices.** + + The below enums and macros are for interfacing with WireGuard, using generic + netlink, with family ``WG_GENL_NAME`` and version ``WG_GENL_VERSION``. It + defines two commands: get and set. Note that while they share many common + attributes, these two commands actually accept a slightly different set of + inputs and outputs. These differences are noted under the individual + attributes. +c-family-name: wg-genl-name +c-version-name: wg-genl-version +max-by-define: true + +definitions: + - + name-prefix: wg- + name: key-len + type: const + value: 32 + - + name: --kernel-timespec + type: struct + header: linux/time_types.h + members: + - + name: sec + type: u64 + doc: Number of seconds, since UNIX epoch. + - + name: nsec + type: u64 + doc: Number of nanoseconds, after the second began. + - + name: wgdevice-flags + name-prefix: wgdevice-f- + enum-name: wgdevice-flag + type: flags + entries: + - replace-peers + - + name: wgpeer-flags + name-prefix: wgpeer-f- + enum-name: wgpeer-flag + type: flags + entries: + - remove-me + - replace-allowedips + - update-only + - + name: wgallowedip-flags + name-prefix: wgallowedip-f- + enum-name: wgallowedip-flag + type: flags + entries: + - remove-me + +attribute-sets: + - + name: wgdevice + enum-name: wgdevice-attribute + name-prefix: wgdevice-a- + attr-cnt-name: --wgdevice-a-last + attributes: + - + name: unspec + type: unused + value: 0 + - + name: ifindex + type: u32 + - + name: ifname + type: string + checks: + max-len: 15 + - + name: private-key + type: binary + doc: Set to all zeros to remove. + display-hint: hex + checks: + exact-len: wg-key-len + - + name: public-key + type: binary + display-hint: hex + checks: + exact-len: wg-key-len + - + name: flags + type: u32 + doc: | + ``0`` or ``WGDEVICE_F_REPLACE_PEERS`` if all current peers should be + removed prior to adding the list below. + enum: wgdevice-flags + - + name: listen-port + type: u16 + doc: Set as ``0`` to choose randomly. + - + name: fwmark + type: u32 + doc: Set as ``0`` to disable. + - + name: peers + type: indexed-array + sub-type: nest + nested-attributes: wgpeer + doc: | + The index/type parameter is unused on ``SET_DEVICE`` operations and is + zero on ``GET_DEVICE`` operations. + - + name: wgpeer + enum-name: wgpeer-attribute + name-prefix: wgpeer-a- + attr-cnt-name: --wgpeer-a-last + attributes: + - + name: unspec + type: unused + value: 0 + - + name: public-key + type: binary + display-hint: hex + checks: + exact-len: wg-key-len + - + name: preshared-key + type: binary + doc: Set as all zeros to remove. + display-hint: hex + checks: + exact-len: wg-key-len + - + name: flags + type: u32 + doc: | + ``0`` and/or ``WGPEER_F_REMOVE_ME`` if the specified peer should not + exist at the end of the operation, rather than added/updated and/or + ``WGPEER_F_REPLACE_ALLOWEDIPS`` if all current allowed IPs of this + peer should be removed prior to adding the list below and/or + ``WGPEER_F_UPDATE_ONLY`` if the peer should only be set if it already + exists. + enum: wgpeer-flags + - + name: endpoint + type: binary + doc: struct sockaddr_in or struct sockaddr_in6 + checks: + min-len: 16 + - + name: persistent-keepalive-interval + type: u16 + doc: Set as ``0`` to disable. + - + name: last-handshake-time + type: binary + struct: --kernel-timespec + checks: + exact-len: 16 + - + name: rx-bytes + type: u64 + - + name: tx-bytes + type: u64 + - + name: allowedips + type: indexed-array + sub-type: nest + nested-attributes: wgallowedip + doc: | + The index/type parameter is unused on ``SET_DEVICE`` operations and is + zero on ``GET_DEVICE`` operations. + - + name: protocol-version + type: u32 + doc: | + Should not be set or used at all by most users of this API, as the + most recent protocol will be used when this is unset. Otherwise, + must be set to ``1``. + - + name: wgallowedip + enum-name: wgallowedip-attribute + name-prefix: wgallowedip-a- + attr-cnt-name: --wgallowedip-a-last + attributes: + - + name: unspec + type: unused + value: 0 + - + name: family + type: u16 + doc: IP family, either ``AF_INET`` or ``AF_INET6``. + - + name: ipaddr + type: binary + doc: Either ``struct in_addr`` or ``struct in6_addr``. + display-hint: ipv4-or-v6 + checks: + min-len: 4 + - + name: cidr-mask + type: u8 + - + name: flags + type: u32 + doc: | + ``WGALLOWEDIP_F_REMOVE_ME`` if the specified IP should be removed; + otherwise, this IP will be added if it is not already present. + enum: wgallowedip-flags + +operations: + enum-name: wg-cmd + name-prefix: wg-cmd- + list: + - + name: get-device + value: 0 + doc: | + Retrieve WireGuard device + ~~~~~~~~~~~~~~~~~~~~~~~~~ + + The command should be called with one but not both of: + + - ``WGDEVICE_A_IFINDEX`` + - ``WGDEVICE_A_IFNAME`` + + The kernel will then return several messages (``NLM_F_MULTI``). It is + possible that all of the allowed IPs of a single peer will not fit + within a single netlink message. In that case, the same peer will be + written in the following message, except it will only contain + ``WGPEER_A_PUBLIC_KEY`` and ``WGPEER_A_ALLOWEDIPS``. This may occur + several times in a row for the same peer. It is then up to the receiver + to coalesce adjacent peers. Likewise, it is possible that all peers will + not fit within a single message. So, subsequent peers will be sent in + following messages, except those will only contain ``WGDEVICE_A_IFNAME`` + and ``WGDEVICE_A_PEERS``. It is then up to the receiver to coalesce + these messages to form the complete list of peers. + + Since this is an ``NLA_F_DUMP`` command, the final message will always + be ``NLMSG_DONE``, even if an error occurs. However, this ``NLMSG_DONE`` + message contains an integer error code. It is either zero or a negative + error code corresponding to the errno. + attribute-set: wgdevice + flags: [uns-admin-perm] + + dump: + pre: wg-get-device-start + post: wg-get-device-done + request: + attributes: + - ifindex + - ifname + reply: &all-attrs + attributes: + - ifindex + - ifname + - private-key + - public-key + - flags + - listen-port + - fwmark + - peers + - + name: set-device + value: 1 + doc: | + Set WireGuard device + ~~~~~~~~~~~~~~~~~~~~ + + This command should be called with a wgdevice set, containing one but + not both of ``WGDEVICE_A_IFINDEX`` and ``WGDEVICE_A_IFNAME``. + + It is possible that the amount of configuration data exceeds that of the + maximum message length accepted by the kernel. In that case, several + messages should be sent one after another, with each successive one + filling in information not contained in the prior. Note that if + ``WGDEVICE_F_REPLACE_PEERS`` is specified in the first message, it + probably should not be specified in fragments that come after, so that + the list of peers is only cleared the first time but appended after. + Likewise for peers, if ``WGPEER_F_REPLACE_ALLOWEDIPS`` is specified in + the first message of a peer, it likely should not be specified in + subsequent fragments. + + If an error occurs, ``NLMSG_ERROR`` will reply containing an errno. + attribute-set: wgdevice + flags: [uns-admin-perm] + + do: + request: *all-attrs diff --git a/Documentation/networking/6pack.rst b/Documentation/networking/6pack.rst index bc5bf1f1a98f..66d5fd4fc821 100644 --- a/Documentation/networking/6pack.rst +++ b/Documentation/networking/6pack.rst @@ -94,7 +94,7 @@ kernels may lead to a compilation error because the interface to a kernel function has been changed in the 2.1.8x kernels. How to turn on 6pack support: -============================= +----------------------------- - In the linux kernel configuration program, select the code maturity level options menu and turn on the prompting for development drivers. diff --git a/Documentation/networking/arcnet-hardware.rst b/Documentation/networking/arcnet-hardware.rst index 3bf7f99cd7bb..20e5075d0d0e 100644 --- a/Documentation/networking/arcnet-hardware.rst +++ b/Documentation/networking/arcnet-hardware.rst @@ -4,18 +4,20 @@ ARCnet Hardware =============== +:Author: Avery Pennarun <apenwarr@worldvisions.ca> + .. note:: - 1) This file is a supplement to arcnet.txt. Please read that for general + 1) This file is a supplement to arcnet.rst. Please read that for general driver configuration help. 2) This file is no longer Linux-specific. It should probably be moved out of the kernel sources. Ideas? Because so many people (myself included) seem to have obtained ARCnet cards without manuals, this file contains a quick introduction to ARCnet hardware, -some cabling tips, and a listing of all jumper settings I can find. Please -e-mail apenwarr@worldvisions.ca with any settings for your particular card, -or any other information you have! +some cabling tips, and a listing of all jumper settings I can find. If you +have any settings for your particular card, and/or any other information you +have, do not hesitate to :ref:`email to netdev <arcnet-netdev>`. Introduction to ARCnet @@ -72,11 +74,10 @@ level of encapsulation is defined by RFC1201, which I call "packet splitting," that allows "virtual packets" to grow as large as 64K each, although they are generally kept down to the Ethernet-style 1500 bytes. -For more information on the advantages and disadvantages (mostly the -advantages) of ARCnet networks, you might try the "ARCnet Trade Association" -WWW page: +For more information on ARCnet networks, visit the "ARCNET Resource Center" +WWW page at: - http://www.arcnet.com + https://www.arcnet.cc Cabling ARCnet Networks @@ -3226,9 +3227,6 @@ Settings for IRQ Selection (Lower Jumper Line) Other Cards =========== -I have no information on other models of ARCnet cards at the moment. Please -send any and all info to: - - apenwarr@worldvisions.ca +I have no information on other models of ARCnet cards at the moment. Thanks. diff --git a/Documentation/networking/arcnet.rst b/Documentation/networking/arcnet.rst index 82fce606c0f0..cd43a18ad149 100644 --- a/Documentation/networking/arcnet.rst +++ b/Documentation/networking/arcnet.rst @@ -4,6 +4,8 @@ ARCnet ====== +:Author: Avery Pennarun <apenwarr@worldvisions.ca> + .. note:: See also arcnet-hardware.txt in this directory for jumper-setting @@ -30,18 +32,7 @@ Come on, be a sport! Send me a success report! (hey, that was even better than my original poem... this is getting bad!) - -.. warning:: - - If you don't e-mail me about your success/failure soon, I may be forced to - start SINGING. And we don't want that, do we? - - (You know, it might be argued that I'm pushing this point a little too much. - If you think so, why not flame me in a quick little e-mail? Please also - include the type of card(s) you're using, software, size of network, and - whether it's working or not.) - - My e-mail address is: apenwarr@worldvisions.ca +---- These are the ARCnet drivers for Linux. @@ -59,23 +50,14 @@ ARCnet 2.10 ALPHA, Tomasz's all-new-and-improved RFC1051 support has been included and seems to be working fine! +.. _arcnet-netdev: + Where do I discuss these drivers? --------------------------------- -Tomasz has been so kind as to set up a new and improved mailing list. -Subscribe by sending a message with the BODY "subscribe linux-arcnet YOUR -REAL NAME" to listserv@tichy.ch.uj.edu.pl. Then, to submit messages to the -list, mail to linux-arcnet@tichy.ch.uj.edu.pl. - -There are archives of the mailing list at: - - http://epistolary.org/mailman/listinfo.cgi/arcnet - -The people on linux-net@vger.kernel.org (now defunct, replaced by -netdev@vger.kernel.org) have also been known to be very helpful, especially -when we're talking about ALPHA Linux kernels that may or may not work right -in the first place. - +ARCnet discussions take place on netdev. Simply send your email to +netdev@vger.kernel.org and make sure to Cc: maintainer listed in +"ARCNET NETWORK LAYER" heading of Documentation/process/maintainers.rst. Other Drivers and Info ---------------------- @@ -523,17 +505,9 @@ can set up your network then: It works: what now? ------------------- -Send mail describing your setup, preferably including driver version, kernel -version, ARCnet card model, CPU type, number of systems on your network, and -list of software in use to me at the following address: - - apenwarr@worldvisions.ca - -I do send (sometimes automated) replies to all messages I receive. My email -can be weird (and also usually gets forwarded all over the place along the -way to me), so if you don't get a reply within a reasonable time, please -resend. - +Send mail following :ref:`arcnet-netdev`. Describe your setup, preferably +including driver version, kernel version, ARCnet card model, CPU type, number +of systems on your network, and list of software in use. It doesn't work: what now? -------------------------- diff --git a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst index 6877a3260582..5aedbabb7382 100644 --- a/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst +++ b/Documentation/networking/device_drivers/cellular/qualcomm/rmnet.rst @@ -28,6 +28,7 @@ these MAP frames and send them to appropriate PDN's. ================ a. MAP packet v1 (data / control) +--------------------------------- MAP header fields are in big endian format. @@ -54,6 +55,7 @@ Payload length includes the padding length but does not include MAP header length. b. Map packet v4 (data / control) +--------------------------------- MAP header fields are in big endian format. @@ -107,6 +109,7 @@ over which checksum is computed. Checksum value, indicates the checksum computed. c. MAP packet v5 (data / control) +--------------------------------- MAP header fields are in big endian format. @@ -134,6 +137,7 @@ Payload length includes the padding length but does not include MAP header length. d. Checksum offload header v5 +----------------------------- Checksum offload header fields are in big endian format. @@ -158,7 +162,10 @@ indicates that the calculated packet checksum is invalid. Reserved bits must be zero when sent and ignored when received. -e. MAP packet v1/v5 (command specific):: +e. MAP packet v1/v5 (command specific) +-------------------------------------- + +Packet format:: Bit 0 1 2-7 8 - 15 16 - 31 Function Command Reserved Pad Multiplexer ID Payload length @@ -181,6 +188,7 @@ Command types = ========================================== f. Aggregation +-------------- Aggregation is multiple MAP packets (can be data or command) delivered to rmnet in a single linear skb. rmnet will process the individual diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst index 7cfcd183054f..bcc02355f828 100644 --- a/Documentation/networking/device_drivers/ethernet/index.rst +++ b/Documentation/networking/device_drivers/ethernet/index.rst @@ -47,6 +47,7 @@ Contents: mellanox/mlx5/index meta/fbnic microsoft/netvsc + mucse/rnpgbe neterion/s2io netronome/nfp pensando/ionic diff --git a/Documentation/networking/device_drivers/ethernet/mucse/rnpgbe.rst b/Documentation/networking/device_drivers/ethernet/mucse/rnpgbe.rst new file mode 100644 index 000000000000..d35cf8a46b6c --- /dev/null +++ b/Documentation/networking/device_drivers/ethernet/mucse/rnpgbe.rst @@ -0,0 +1,17 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=========================================================== +Linux Base Driver for MUCSE(R) Gigabit PCI Express Adapters +=========================================================== + +Contents +======== + +- Identifying Your Adapter + +Identifying Your Adapter +======================== +The driver is compatible with devices based on the following: + + * MUCSE(R) Ethernet Controller N210 series + * MUCSE(R) Ethernet Controller N500 series diff --git a/Documentation/networking/devlink/devlink-eswitch-attr.rst b/Documentation/networking/devlink/devlink-eswitch-attr.rst index 08bb39ab1528..eafe09abc40c 100644 --- a/Documentation/networking/devlink/devlink-eswitch-attr.rst +++ b/Documentation/networking/devlink/devlink-eswitch-attr.rst @@ -39,6 +39,10 @@ The following is a list of E-Switch attributes. rules. * ``switchdev`` allows for more advanced offloading capabilities of the E-Switch to hardware. + * ``switchdev_inactive`` switchdev mode but starts inactive, doesn't allow traffic + until explicitly activated. This mode is useful for orchestrators that + want to prepare the device in switchdev mode but only activate it when + all configurations are done. * - ``inline-mode`` - enum - Some HWs need the VF driver to put part of the packet @@ -74,3 +78,12 @@ Example Usage # enable encap-mode with legacy mode $ devlink dev eswitch set pci/0000:08:00.0 mode legacy inline-mode none encap-mode basic + + # start switchdev mode in inactive state + $ devlink dev eswitch set pci/0000:08:00.0 mode switchdev_inactive + + # setup switchdev configurations, representors, FDB entries, etc.. + ... + + # activate switchdev mode to allow traffic + $ devlink dev eswitch set pci/0000:08:00.0 mode switchdev diff --git a/Documentation/networking/devlink/devlink-params.rst b/Documentation/networking/devlink/devlink-params.rst index 0a9c20d70122..ea17756dcda6 100644 --- a/Documentation/networking/devlink/devlink-params.rst +++ b/Documentation/networking/devlink/devlink-params.rst @@ -41,6 +41,16 @@ In order for ``driverinit`` parameters to take effect, the driver must support reloading via the ``devlink-reload`` command. This command will request a reload of the device driver. +Default parameter values +========================= + +Drivers may optionally export default values for parameters of cmode +``runtime`` and ``permanent``. For ``driverinit`` parameters, the last +value set by the driver will be used as the default value. Drivers can +also support resetting params with cmode ``runtime`` and ``permanent`` +to their default values. Resetting ``driverinit`` params is supported +by devlink core without additional driver support needed. + .. _devlink_params_generic: Generic configuration parameters @@ -151,3 +161,7 @@ own name. * - ``num_doorbells`` - u32 - Controls the number of doorbells used by the device. + * - ``max_mac_per_vf`` + - u32 + - Controls the maximum number of MAC address filters that can be assigned + to a Virtual Function (VF). diff --git a/Documentation/networking/devlink/i40e.rst b/Documentation/networking/devlink/i40e.rst index d3cb5bb5197e..51c887f0dc83 100644 --- a/Documentation/networking/devlink/i40e.rst +++ b/Documentation/networking/devlink/i40e.rst @@ -7,6 +7,40 @@ i40e devlink support This document describes the devlink features implemented by the ``i40e`` device driver. +Parameters +========== + +.. list-table:: Generic parameters implemented + :widths: 5 5 90 + + * - Name + - Mode + - Notes + * - ``max_mac_per_vf`` + - runtime + - Controls the maximum number of MAC addresses a VF can use + on i40e devices. + + By default (``0``), the driver enforces its internally calculated per-VF + MAC filter limit, which is based on the number of allocated VFS. + + If set to a non-zero value, this parameter acts as a strict cap: + the driver will use the user-provided value instead of its internal + calculation. + + **Important notes:** + + - This value **must be set before enabling SR-IOV**. + Attempting to change it while SR-IOV is enabled will return an error. + - MAC filters are a **shared hardware resource** across all VFs. + Setting a high value may cause other VFs to be starved of filters. + - This value is a **Administrative policy**. The hardware may return + errors when its absolute limit is reached, regardless of the value + set here. + + The default value is ``0`` (internal calculation is used). + + Info versions ============= diff --git a/Documentation/networking/devlink/index.rst b/Documentation/networking/devlink/index.rst index 0c58e5c729d9..35b12a2bfeba 100644 --- a/Documentation/networking/devlink/index.rst +++ b/Documentation/networking/devlink/index.rst @@ -99,5 +99,6 @@ parameters, info versions, and other features it supports. prestera qed sfc + stmmac ti-cpsw-switch zl3073x diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst index 0e5f9c76e514..4bba4d780a4a 100644 --- a/Documentation/networking/devlink/mlx5.rst +++ b/Documentation/networking/devlink/mlx5.rst @@ -218,6 +218,20 @@ parameters. * ``balanced`` : Merges fewer CQEs, resulting in a moderate compression ratio but maintaining a balance between bandwidth savings and performance * ``aggressive`` : Merges more CQEs into a single entry, achieving a higher compression rate and maximizing performance, particularly under high traffic loads + * - ``swp_l4_csum_mode`` + - string + - permanent + - Configure how the L4 checksum is calculated by the device when using + Software Parser (SWP) hints for header locations. + + * ``default`` : Use the device's default checksum calculation + mode. The driver will discover during init whether or + full_csum or l4_only is in use. Setting this value explicitly + from userspace is not allowed, but some firmware versions may + return this value on param read. + * ``full_csum`` : Calculate full checksum including the pseudo-header + * ``l4_only`` : Calculate L4-only checksum, excluding the pseudo-header + The ``mlx5`` driver supports reloading via ``DEVLINK_CMD_RELOAD`` Info versions diff --git a/Documentation/networking/devlink/stmmac.rst b/Documentation/networking/devlink/stmmac.rst new file mode 100644 index 000000000000..47e3ff10bc08 --- /dev/null +++ b/Documentation/networking/devlink/stmmac.rst @@ -0,0 +1,40 @@ +.. SPDX-License-Identifier: GPL-2.0 + +======================================= +stmmac (synopsys dwmac) devlink support +======================================= + +This document describes the devlink features implemented by the ``stmmac`` +device driver. + +Parameters +========== + +The ``stmmac`` driver implements the following driver-specific parameters. + +.. list-table:: Driver-specific parameters implemented + :widths: 5 5 5 85 + + * - Name + - Type + - Mode + - Description + * - ``phc_coarse_adj`` + - Boolean + - runtime + - Enable the Coarse timestamping mode, as defined in the DWMAC TRM. + A detailed explanation of this timestamping mode can be found in the + Socfpga Functionnal Description [1]. + + In Coarse mode, the ptp clock is expected to be fed by a high-precision + clock that is externally adjusted, and the subsecond increment used for + timestamping is set to 1/ptp_clock_rate. + + In Fine mode (i.e. Coarse mode == false), the ptp clock frequency is + continuously adjusted, but the subsecond increment is set to + 2/ptp_clock_rate. + + Coarse mode is suitable for PTP Grand Master operation. If unsure, leave + the parameter to False. + + [1] https://www.intel.com/content/www/us/en/docs/programmable/683126/21-2/functional-description-of-the-emac.html diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 7b2e69cd7ef0..5c79740a533b 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -1104,12 +1104,11 @@ health of the network and for discovery of other nodes. In Linux, both HSR and PRP are implemented in the hsr driver, which instantiates a virtual, stackable network interface with two member ports. The driver only implements the basic roles of DANH (Doubly Attached Node -implementing HSR) and DANP (Doubly Attached Node implementing PRP); the roles -of RedBox and QuadBox are not implemented (therefore, bridging a hsr network -interface with a physical switch port does not produce the expected result). +implementing HSR), DANP (Doubly Attached Node implementing PRP) and RedBox +(allows non-HSR devices to connect to the ring via Interlink ports). -A driver which is able of offloading certain functions of a DANP or DANH should -declare the corresponding netdev features as indicated by the documentation at +A driver which is able of offloading certain functions should declare the +corresponding netdev features as indicated by the documentation at ``Documentation/networking/netdev-features.rst``. Additionally, the following methods must be implemented: @@ -1120,6 +1119,14 @@ methods must be implemented: - ``port_hsr_leave``: function invoked when a given switch port leaves a DANP/DANH and returns to normal operation as a standalone port. +Note that the ``NETIF_F_HW_HSR_DUP`` feature relies on transmission towards +multiple ports, which is generally available whenever the tagging protocol uses +the ``dsa_xmit_port_mask()`` helper function. If the helper is used, the HSR +offload feature should also be set. The ``dsa_port_simple_hsr_join()`` and +``dsa_port_simple_hsr_leave()`` methods can be used as generic implementations +of ``port_hsr_join`` and ``port_hsr_leave``, if this is the only supported +offload feature. + TODO ==== diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index b270886c5f5d..af56c304cef4 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -242,6 +242,7 @@ Userspace to kernel: ``ETHTOOL_MSG_RSS_SET`` set RSS settings ``ETHTOOL_MSG_RSS_CREATE_ACT`` create an additional RSS context ``ETHTOOL_MSG_RSS_DELETE_ACT`` delete an additional RSS context + ``ETHTOOL_MSG_MSE_GET`` get MSE diagnostic data ===================================== ================================= Kernel to userspace: @@ -299,6 +300,7 @@ Kernel to userspace: ``ETHTOOL_MSG_RSS_CREATE_ACT_REPLY`` create an additional RSS context ``ETHTOOL_MSG_RSS_CREATE_NTF`` additional RSS context created ``ETHTOOL_MSG_RSS_DELETE_NTF`` additional RSS context deleted + ``ETHTOOL_MSG_MSE_GET_REPLY`` MSE diagnostic data ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -2458,6 +2460,68 @@ Kernel response contents: For a description of each attribute, see ``TSCONFIG_GET``. +MSE_GET +======= + +Retrieves detailed Mean Square Error (MSE) diagnostic information from the PHY. + +Request Contents: + + ==================================== ====== ============================ + ``ETHTOOL_A_MSE_HEADER`` nested request header + ==================================== ====== ============================ + +Kernel Response Contents: + + ==================================== ====== ================================ + ``ETHTOOL_A_MSE_HEADER`` nested reply header + ``ETHTOOL_A_MSE_CAPABILITIES`` nested capability/scale info for MSE + measurements + ``ETHTOOL_A_MSE_CHANNEL_A`` nested snapshot for Channel A + ``ETHTOOL_A_MSE_CHANNEL_B`` nested snapshot for Channel B + ``ETHTOOL_A_MSE_CHANNEL_C`` nested snapshot for Channel C + ``ETHTOOL_A_MSE_CHANNEL_D`` nested snapshot for Channel D + ``ETHTOOL_A_MSE_WORST_CHANNEL`` nested snapshot for worst channel + ``ETHTOOL_A_MSE_LINK`` nested snapshot for link-wide aggregate + ==================================== ====== ================================ + +MSE Capabilities +---------------- + +This nested attribute reports the capability / scaling properties used to +interpret snapshot values. + + ============================================== ====== ========================= + ``ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE`` uint max avg_mse scale + ``ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE`` uint max peak_mse scale + ``ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS`` uint sample rate (picoseconds) + ``ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS`` uint symbols per HW sample + ============================================== ====== ========================= + +The max-average/peak fields are included only if the corresponding metric +is supported by the PHY. Their absence indicates that the metric is not +available. + +See ``struct phy_mse_capability`` kernel documentation in +``include/linux/phy.h``. + +MSE Snapshot +------------ + +Each per-channel nest contains an atomic snapshot of MSE values for that +selector (channel A/B/C/D, worst channel, or link). + + ========================================== ====== =================== + ``ETHTOOL_A_MSE_SNAPSHOT_AVERAGE_MSE`` uint average MSE value + ``ETHTOOL_A_MSE_SNAPSHOT_PEAK_MSE`` uint current peak MSE + ``ETHTOOL_A_MSE_SNAPSHOT_WORST_PEAK_MSE`` uint worst-case peak MSE + ========================================== ====== =================== + +Within each channel nest, only the metrics supported by the PHY will be present. + +See ``struct phy_mse_snapshot`` kernel documentation in +``include/linux/phy.h``. + Request translation =================== diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index c775cababc8c..75db2251649b 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -131,10 +131,7 @@ Contents: vxlan x25 x25-iface - xfrm_device - xfrm_proc - xfrm_sync - xfrm_sysctl + xfrm/index xdp-rx-metadata xsk-tx-metadata diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index a06cb99d66dc..bc9a01606daf 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -673,6 +673,16 @@ tcp_moderate_rcvbuf - BOOLEAN Default: 1 (enabled) +tcp_rcvbuf_low_rtt - INTEGER + rcvbuf autotuning can over estimate final socket rcvbuf, which + can lead to cache trashing for high throughput flows. + + For small RTT flows (below tcp_rcvbuf_low_rtt usecs), we can relax + rcvbuf growth: Few additional ms to reach the final (and smaller) + rcvbuf is a good tradeoff. + + Default : 1000 (1 ms) + tcp_mtu_probing - INTEGER Controls TCP Packetization-Layer Path MTU Discovery. Takes three values: @@ -854,9 +864,18 @@ tcp_sack - BOOLEAN Default: 1 (enabled) +tcp_comp_sack_rtt_percent - INTEGER + Percentage of SRTT used for the compressed SACK feature. + See tcp_comp_sack_nr, tcp_comp_sack_delay_ns, tcp_comp_sack_slack_ns. + + Possible values : 1 - 1000 + + Default : 33 % + tcp_comp_sack_delay_ns - LONG INTEGER - TCP tries to reduce number of SACK sent, using a timer - based on 5% of SRTT, capped by this sysctl, in nano seconds. + TCP tries to reduce number of SACK sent, using a timer based + on tcp_comp_sack_rtt_percent of SRTT, capped by this sysctl + in nano seconds. The default is 1ms, based on TSO autosizing period. Default : 1,000,000 ns (1 ms) @@ -866,8 +885,9 @@ tcp_comp_sack_slack_ns - LONG INTEGER timer used by SACK compression. This gives extra time for small RTT flows, and reduces system overhead by allowing opportunistic reduction of timer interrupts. + Too big values might reduce goodput. - Default : 100,000 ns (100 us) + Default : 10,000 ns (10 us) tcp_comp_sack_nr - INTEGER Max number of SACK that can be compressed. @@ -1796,6 +1816,23 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN Default: 0 (disabled) +icmp_errors_extension_mask - UNSIGNED INTEGER + Bitmask of ICMP extensions to append to ICMPv4 error messages + ("Destination Unreachable", "Time Exceeded" and "Parameter Problem"). + The original datagram is trimmed / padded to 128 bytes in order to be + compatible with applications that do not comply with RFC 4884. + + Possible extensions are: + + ==== ============================================================== + 0x01 Incoming IP interface information according to RFC 5837. + Extension will include the index, IPv4 address (if present), + name and MTU of the IP interface that received the datagram + which elicited the ICMP error. + ==== ============================================================== + + Default: 0x00 (no extensions) + igmp_max_memberships - INTEGER Change the maximum number of multicast groups we can subscribe to. Default: 20 @@ -3262,6 +3299,23 @@ error_anycast_as_unicast - BOOLEAN Default: 0 (disabled) +errors_extension_mask - UNSIGNED INTEGER + Bitmask of ICMP extensions to append to ICMPv6 error messages + ("Destination Unreachable" and "Time Exceeded"). The original datagram + is trimmed / padded to 128 bytes in order to be compatible with + applications that do not comply with RFC 4884. + + Possible extensions are: + + ==== ============================================================== + 0x01 Incoming IP interface information according to RFC 5837. + Extension will include the index, IPv6 address (if present), + name and MTU of the IP interface that received the datagram + which elicited the ICMP error. + ==== ============================================================== + + Default: 0x00 (no extensions) + xfrm6_gc_thresh - INTEGER (Obsolete since linux-4.14) The threshold at which we will start garbage collecting for IPv6 diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst index 7dd60366f4ff..4e008efebb35 100644 --- a/Documentation/networking/napi.rst +++ b/Documentation/networking/napi.rst @@ -263,7 +263,9 @@ are not well known). Busy polling is enabled by either setting ``SO_BUSY_POLL`` on selected sockets or using the global ``net.core.busy_poll`` and ``net.core.busy_read`` sysctls. An io_uring API for NAPI busy polling -also exists. +also exists. Threaded polling of NAPI also has a mode to busy poll for +packets (:ref:`threaded busy polling<threaded_busy_poll>`) using the NAPI +processing kthread. epoll-based busy polling ------------------------ @@ -426,6 +428,52 @@ Therefore, setting ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` is the recommended usage, because otherwise setting ``irq-suspend-timeout`` might not have any discernible effect. +.. _threaded_busy_poll: + +Threaded NAPI busy polling +-------------------------- + +Threaded NAPI busy polling extends threaded NAPI and adds support to do +continuous busy polling of the NAPI. This can be useful for forwarding or +AF_XDP applications. + +Threaded NAPI busy polling can be enabled on per NIC queue basis using Netlink. + +For example, using the following script: + +.. code-block:: bash + + $ ynl --family netdev --do napi-set \ + --json='{"id": 66, "threaded": "busy-poll"}' + +The kernel will create a kthread that busy polls on this NAPI. + +The user may elect to set the CPU affinity of this kthread to an unused CPU +core to improve how often the NAPI is polled at the expense of wasted CPU +cycles. Note that this will keep the CPU core busy with 100% usage. + +Once threaded busy polling is enabled for a NAPI, PID of the kthread can be +retrieved using Netlink so the affinity of the kthread can be set up. + +For example, the following script can be used to fetch the PID: + +.. code-block:: bash + + $ ynl --family netdev --do napi-get --json='{"id": 66}' + +This will output something like following, the pid `258` is the PID of the +kthread that is polling this NAPI. + +.. code-block:: bash + + $ {'defer-hard-irqs': 0, + 'gro-flush-timeout': 0, + 'id': 66, + 'ifindex': 2, + 'irq-suspend-timeout': 0, + 'pid': 258, + 'threaded': 'busy-poll'} + .. _threaded: Threaded NAPI diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst index 8fae85ebb773..cc2000f55c29 100644 --- a/Documentation/networking/net_cachelines/inet_connection_sock.rst +++ b/Documentation/networking/net_cachelines/inet_connection_sock.rst @@ -12,8 +12,8 @@ struct inet_sock icsk_inet read_mostly r 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 -struct timer_list icsk_retransmit_timer read_write inet_csk_reset_xmit_timer,tcp_connect struct timer_list icsk_delack_timer read_mostly inet_csk_reset_xmit_timer,tcp_connect +struct timer_list icsk_keepalive_timer 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_rto_max read_mostly tcp_reset_xmit_timer diff --git a/Documentation/networking/net_cachelines/inet_sock.rst b/Documentation/networking/net_cachelines/inet_sock.rst index b11bf48fa2b3..4c72a28a7012 100644 --- a/Documentation/networking/net_cachelines/inet_sock.rst +++ b/Documentation/networking/net_cachelines/inet_sock.rst @@ -5,42 +5,43 @@ inet_sock struct fast path usage breakdown ========================================== -======================= ===================== =================== =================== ====================================================================================================== -Type Name fastpath_tx_access fastpath_rx_access comment -======================= ===================== =================== =================== ====================================================================================================== -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 -======================= ===================== =================== =================== ====================================================================================================== +======================== ===================== =================== =================== ====================================================================================================== +Type Name fastpath_tx_access fastpath_rx_access comment +======================== ===================== =================== =================== ====================================================================================================== +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 +struct ipv6_fl_socklist* ipv6_fl_list read_mostly tcp_v6_connect,__ip6_datagram_connect,udpv6_sendmsg,rawv6_sendmsg +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/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst index 6e7b20afd2d4..beaf1880a19b 100644 --- a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst +++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst @@ -102,7 +102,8 @@ u8 sysctl_tcp_app_win 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_moderate_rcvbuf read_mostly tcp_rcvbuf_grow() +u32 sysctl_tcp_rcvbuf_low_rtt read_mostly tcp_rcvbuf_grow() 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) diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 2555e75e5cc1..4ab5d7b05cf1 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -88,7 +88,7 @@ for example: nc -u -l -p <port>' / 'nc -u -l <port> - or:: + or:: netcat -u -l -p <port>' / 'netcat -u -l <port> diff --git a/Documentation/networking/nfc.rst b/Documentation/networking/nfc.rst index 9aab3a88c9b2..401735006143 100644 --- a/Documentation/networking/nfc.rst +++ b/Documentation/networking/nfc.rst @@ -71,7 +71,8 @@ Userspace interface The userspace interface is divided in control operations and low-level data exchange operation. -CONTROL OPERATIONS: +Control operations +------------------ Generic netlink is used to implement the interface to the control operations. The operations are composed by commands and events, all listed below: @@ -100,7 +101,8 @@ relevant information such as the supported NFC protocols. All polling operations requested through one netlink socket are stopped when it's closed. -LOW-LEVEL DATA EXCHANGE: +Low-level data exchange +----------------------- The userspace must use PF_NFC sockets to perform any data communication with targets. All NFC sockets use AF_NFC:: diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst index a874d007f2db..904a910f198e 100644 --- a/Documentation/networking/smc-sysctl.rst +++ b/Documentation/networking/smc-sysctl.rst @@ -71,3 +71,43 @@ smcr_max_conns_per_lgr - INTEGER acceptable value ranges from 16 to 255. Only for SMC-R v2.1 and later. Default: 255 + +smcr_max_send_wr - INTEGER + So-called work request buffers are SMCR link (and RDMA queue pair) level + resources necessary for performing RDMA operations. Since up to 255 + connections can share a link group and thus also a link and the number + of the work request buffers is decided when the link is allocated, + depending on the workload it can be a bottleneck in a sense that threads + have to wait for work request buffers to become available. Before the + introduction of this control the maximal number of work request buffers + available on the send path used to be hard coded to 16. With this control + it becomes configurable. The acceptable range is between 2 and 2048. + + Please be aware that all the buffers need to be allocated as a physically + continuous array in which each element is a single buffer and has the size + of SMC_WR_BUF_SIZE (48) bytes. If the allocation fails, we keep retrying + with half of the buffer count until it is ether successful or (unlikely) + we dip below the old hard coded value which is 16 where we give up much + like before having this control. + + Default: 16 + +smcr_max_recv_wr - INTEGER + So-called work request buffers are SMCR link (and RDMA queue pair) level + resources necessary for performing RDMA operations. Since up to 255 + connections can share a link group and thus also a link and the number + of the work request buffers is decided when the link is allocated, + depending on the workload it can be a bottleneck in a sense that threads + have to wait for work request buffers to become available. Before the + introduction of this control the maximal number of work request buffers + available on the receive path used to be hard coded to 16. With this control + it becomes configurable. The acceptable range is between 2 and 2048. + + Please be aware that all the buffers need to be allocated as a physically + continuous array in which each element is a single buffer and has the size + of SMC_WR_BUF_SIZE (48) bytes. If the allocation fails, we keep retrying + with half of the buffer count until it is ether successful or (unlikely) + we dip below the old hard coded value which is 16 where we give up much + like before having this control. + + Default: 48 diff --git a/Documentation/networking/statistics.rst b/Documentation/networking/statistics.rst index 518284e287b0..66b0ef941457 100644 --- a/Documentation/networking/statistics.rst +++ b/Documentation/networking/statistics.rst @@ -184,9 +184,11 @@ Protocol-related statistics can be requested in get commands by setting the `ETHTOOL_FLAG_STATS` flag in `ETHTOOL_A_HEADER_FLAGS`. Currently statistics are supported in the following commands: - - `ETHTOOL_MSG_PAUSE_GET` - `ETHTOOL_MSG_FEC_GET` + - `ETHTOOL_MSG_LINKSTATE_GET` - `ETHTOOL_MSG_MM_GET` + - `ETHTOOL_MSG_PAUSE_GET` + - `ETHTOOL_MSG_TSINFO_GET` debugfs ------- diff --git a/Documentation/networking/tls.rst b/Documentation/networking/tls.rst index 36cc7afc2527..980c442d7161 100644 --- a/Documentation/networking/tls.rst +++ b/Documentation/networking/tls.rst @@ -280,6 +280,26 @@ If the record decrypted turns out to had been padded or is not a data record it will be decrypted again into a kernel buffer without zero copy. Such events are counted in the ``TlsDecryptRetry`` statistic. +TLS_TX_MAX_PAYLOAD_LEN +~~~~~~~~~~~~~~~~~~~~~~ + +Specifies the maximum size of the plaintext payload for transmitted TLS records. + +When this option is set, the kernel enforces the specified limit on all outgoing +TLS records. No plaintext fragment will exceed this size. This option can be used +to implement the TLS Record Size Limit extension [1]. + +* For TLS 1.2, the value corresponds directly to the record size limit. +* For TLS 1.3, the value should be set to record_size_limit - 1, since + the record size limit includes one additional byte for the ContentType + field. + +The valid range for this option is 64 to 16384 bytes for TLS 1.2, and 63 to +16384 bytes for TLS 1.3. The lower minimum for TLS 1.3 accounts for the +extra byte used by the ContentType field. + +[1] https://datatracker.ietf.org/doc/html/rfc8449 + Statistics ========== diff --git a/Documentation/networking/xfrm/index.rst b/Documentation/networking/xfrm/index.rst new file mode 100644 index 000000000000..7d866da836fe --- /dev/null +++ b/Documentation/networking/xfrm/index.rst @@ -0,0 +1,13 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============== +XFRM Framework +============== + +.. toctree:: + :maxdepth: 2 + + xfrm_device + xfrm_proc + xfrm_sync + xfrm_sysctl diff --git a/Documentation/networking/xfrm_device.rst b/Documentation/networking/xfrm/xfrm_device.rst index 122204da0fff..b0d85a5f57d1 100644 --- a/Documentation/networking/xfrm_device.rst +++ b/Documentation/networking/xfrm/xfrm_device.rst @@ -20,11 +20,15 @@ can radically increase throughput and decrease CPU utilization. The XFRM Device interface allows NIC drivers to offer to the stack access to the hardware offload. -Right now, there are two types of hardware offload that kernel supports. +Right now, there are two types of hardware offload that kernel supports: + * IPsec crypto offload: + * NIC performs encrypt/decrypt * Kernel does everything else + * IPsec packet offload: + * NIC performs encrypt/decrypt * NIC does encapsulation * Kernel and NIC have SA and policy in-sync @@ -34,7 +38,7 @@ Right now, there are two types of hardware offload that kernel supports. Userland access to the offload is typically through a system such as libreswan or KAME/raccoon, but the iproute2 'ip xfrm' command set can be handy when experimenting. An example command might look something -like this for crypto offload: +like this for crypto offload:: ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \ reqid 0x07 replay-window 32 \ @@ -42,7 +46,7 @@ like this for crypto offload: sel src 14.0.0.52/24 dst 14.0.0.70/24 proto tcp \ offload dev eth4 dir in -and for packet offload +and for packet offload:: ip x s add proto esp dst 14.0.0.70 src 14.0.0.52 spi 0x07 mode transport \ reqid 0x07 replay-window 32 \ @@ -153,26 +157,26 @@ the packet's skb. At this point the data should be decrypted but the IPsec headers are still in the packet data; they are removed later up the stack in xfrm_input(). - find and hold the SA that was used to the Rx skb:: +1. Find and hold the SA that was used to the Rx skb:: - get spi, protocol, and destination IP from packet headers + /* get spi, protocol, and destination IP from packet headers */ xs = find xs from (spi, protocol, dest_IP) xfrm_state_hold(xs); - store the state information into the skb:: +2. Store the state information into the skb:: sp = secpath_set(skb); if (!sp) return; sp->xvec[sp->len++] = xs; sp->olen++; - indicate the success and/or error status of the offload:: +3. Indicate the success and/or error status of the offload:: xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; xo->status = crypto_status; - hand the packet to napi_gro_receive() as usual +4. Hand the packet to napi_gro_receive() as usual. In ESN mode, xdo_dev_state_advance_esn() is called from xfrm_replay_advance_esn() for RX, and xfrm_replay_overflow_offload_esn for TX. diff --git a/Documentation/networking/xfrm_proc.rst b/Documentation/networking/xfrm/xfrm_proc.rst index 973d1571acac..973d1571acac 100644 --- a/Documentation/networking/xfrm_proc.rst +++ b/Documentation/networking/xfrm/xfrm_proc.rst diff --git a/Documentation/networking/xfrm_sync.rst b/Documentation/networking/xfrm/xfrm_sync.rst index 6246503ceab2..dfc2ec0df380 100644 --- a/Documentation/networking/xfrm_sync.rst +++ b/Documentation/networking/xfrm/xfrm_sync.rst @@ -1,8 +1,8 @@ .. SPDX-License-Identifier: GPL-2.0 -==== -XFRM -==== +========= +XFRM sync +========= The sync patches work is based on initial patches from Krisztian <hidden@balabit.hu> and others and additional patches @@ -36,7 +36,7 @@ is not driven by packet arrival. - the replay sequence for both inbound and outbound 1) Message Structure ----------------------- +-------------------- nlmsghdr:aevent_id:optional-TLVs. @@ -83,31 +83,31 @@ when going from kernel to user space) A program needs to subscribe to multicast group XFRMNLGRP_AEVENTS to get notified of these events. -2) TLVS reflect the different parameters: ------------------------------------------ +2) TLVS reflect the different parameters +---------------------------------------- a) byte value (XFRMA_LTIME_VAL) -This TLV carries the running/current counter for byte lifetime since -last event. + This TLV carries the running/current counter for byte lifetime since + last event. -b)replay value (XFRMA_REPLAY_VAL) +b) replay value (XFRMA_REPLAY_VAL) -This TLV carries the running/current counter for replay sequence since -last event. + This TLV carries the running/current counter for replay sequence since + last event. -c)replay threshold (XFRMA_REPLAY_THRESH) +c) replay threshold (XFRMA_REPLAY_THRESH) -This TLV carries the threshold being used by the kernel to trigger events -when the replay sequence is exceeded. + This TLV carries the threshold being used by the kernel to trigger events + when the replay sequence is exceeded. d) expiry timer (XFRMA_ETIMER_THRESH) -This is a timer value in milliseconds which is used as the nagle -value to rate limit the events. + This is a timer value in milliseconds which is used as the nagle + value to rate limit the events. -3) Default configurations for the parameters: ---------------------------------------------- +3) Default configurations for the parameters +-------------------------------------------- By default these events should be turned off unless there is at least one listener registered to listen to the multicast @@ -121,12 +121,14 @@ in case they are not specified. the two sysctls/proc entries are: a) /proc/sys/net/core/sysctl_xfrm_aevent_etime -used to provide default values for the XFRMA_ETIMER_THRESH in incremental -units of time of 100ms. The default is 10 (1 second) + + Used to provide default values for the XFRMA_ETIMER_THRESH in incremental + units of time of 100ms. The default is 10 (1 second) b) /proc/sys/net/core/sysctl_xfrm_aevent_rseqth -used to provide default values for XFRMA_REPLAY_THRESH parameter -in incremental packet count. The default is two packets. + + Used to provide default values for XFRMA_REPLAY_THRESH parameter + in incremental packet count. The default is two packets. 4) Message types ---------------- @@ -134,50 +136,51 @@ in incremental packet count. The default is two packets. a) XFRM_MSG_GETAE issued by user-->kernel. XFRM_MSG_GETAE does not carry any TLVs. -The response is a XFRM_MSG_NEWAE which is formatted based on what -XFRM_MSG_GETAE queried for. + The response is a XFRM_MSG_NEWAE which is formatted based on what + XFRM_MSG_GETAE queried for. + + The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -* if XFRM_AE_RTHR flag is set, then XFRMA_REPLAY_THRESH is also retrieved -* if XFRM_AE_ETHR flag is set, then XFRMA_ETIMER_THRESH is also retrieved + * if XFRM_AE_RTHR flag is set, then XFRMA_REPLAY_THRESH is also retrieved + * if XFRM_AE_ETHR flag is set, then XFRMA_ETIMER_THRESH is also retrieved b) XFRM_MSG_NEWAE is issued by either user space to configure or kernel to announce events or respond to a XFRM_MSG_GETAE. -i) user --> kernel to configure a specific SA. + i) user --> kernel to configure a specific SA. -any of the values or threshold parameters can be updated by passing the -appropriate TLV. + any of the values or threshold parameters can be updated by passing the + appropriate TLV. -A response is issued back to the sender in user space to indicate success -or failure. + A response is issued back to the sender in user space to indicate success + or failure. -In the case of success, additionally an event with -XFRM_MSG_NEWAE is also issued to any listeners as described in iii). + In the case of success, additionally an event with + XFRM_MSG_NEWAE is also issued to any listeners as described in iii). -ii) kernel->user direction as a response to XFRM_MSG_GETAE + ii) kernel->user direction as a response to XFRM_MSG_GETAE -The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. + The response will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -The threshold TLVs will be included if explicitly requested in -the XFRM_MSG_GETAE message. + The threshold TLVs will be included if explicitly requested in + the XFRM_MSG_GETAE message. -iii) kernel->user to report as event if someone sets any values or - thresholds for an SA using XFRM_MSG_NEWAE (as described in #i above). - In such a case XFRM_AE_CU flag is set to inform the user that - the change happened as a result of an update. - The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. + iii) kernel->user to report as event if someone sets any values or + thresholds for an SA using XFRM_MSG_NEWAE (as described in #i above). + In such a case XFRM_AE_CU flag is set to inform the user that + the change happened as a result of an update. + The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -iv) kernel->user to report event when replay threshold or a timeout - is exceeded. + iv) kernel->user to report event when replay threshold or a timeout + is exceeded. In such a case either XFRM_AE_CR (replay exceeded) or XFRM_AE_CE (timeout happened) is set to inform the user what happened. Note the two flags are mutually exclusive. The message will always have XFRMA_LTIME_VAL and XFRMA_REPLAY_VAL TLVs. -Exceptions to threshold settings --------------------------------- +5) Exceptions to threshold settings +----------------------------------- If you have an SA that is getting hit by traffic in bursts such that there is a period where the timer threshold expires with no packets diff --git a/Documentation/networking/xfrm_sysctl.rst b/Documentation/networking/xfrm/xfrm_sysctl.rst index 47b9bbdd0179..7d0c4b17c0bd 100644 --- a/Documentation/networking/xfrm_sysctl.rst +++ b/Documentation/networking/xfrm/xfrm_sysctl.rst @@ -4,8 +4,8 @@ XFRM Syscall ============ -/proc/sys/net/core/xfrm_* Variables: -==================================== +/proc/sys/net/core/xfrm_* Variables +=================================== xfrm_acq_expires - INTEGER default 30 - hard timeout in seconds for acquire requests |