diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 2ef50828aff16..369a738a68193 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 6d22131ac2f9e..fbe2ddcdd909c 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 c7644e6586d32..59c57f58116b5 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 0000000000000..006add8b6410a --- /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 + +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 9c27dfcd11334..0000000000000 --- 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/can/bosch,m_can.yaml b/Documentation/devicetree/bindings/net/can/bosch,m_can.yaml index 61ef60d8f1c78..2c9d37975bedd 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 c155c9c6db392..2d13638ebc6a6 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/cdns,macb.yaml b/Documentation/devicetree/bindings/net/cdns,macb.yaml index 1029786a855c5..ea8337846ab26 100644 --- a/Documentation/devicetree/bindings/net/cdns,macb.yaml +++ b/Documentation/devicetree/bindings/net/cdns,macb.yaml @@ -47,18 +47,19 @@ 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 +184,15 @@ 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 f3154b19af78a..205b683849a53 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. + +$ref: dsa.yaml# maintainers: - Hauke Mehrtens @@ -18,9 +22,14 @@ properties: - lantiq,xrx200-gswip - lantiq,xrx300-gswip - lantiq,xrx330-gswip + - maxlinear,gsw120 + - maxlinear,gsw125 + - maxlinear,gsw140 + - maxlinear,gsw141 + - maxlinear,gsw145 reg: - minItems: 3 + minItems: 1 maxItems: 3 reg-names: @@ -37,9 +46,6 @@ properties: compatible: const: lantiq,xrx200-mdio - required: - - compatible - gphy-fw: type: object properties: @@ -91,10 +97,63 @@ properties: additionalProperties: false +patternProperties: + "^(ethernet-)?ports$": + 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 + + 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 = ; + function = LED_FUNCTION_LAN; + }; + }; + }; + + switchphy1: switchphy@1 { + reg = <1>; + + leds { + #address-cells = <1>; + #size-cells = <0>; + + led@0 { + reg = <0>; + color = ; + 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 0000000000000..33a6552e46fc0 --- /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 + +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 + + 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 e9dd914b0734c..607b7fe8d28ee 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 0000000000000..91e8cd1db67b8 --- /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 + - Zhi Li + - Shangjuan Wei + +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. + $ref: /schemas/types.yaml#/definitions/phandle-array + items: + - items: + - description: Phandle to HSP(High-Speed Peripheral) device + - description: Offset of phy control register for internal + or external clock selection + - description: Offset of AXI clock controller Low-Power request + register + - description: Offset of register controlling TX/RX clock delay + +required: + - compatible + - reg + - clocks + - clock-names + - interrupts + - interrupt-names + - phy-mode + - resets + - reset-names + - rx-internal-delay-ps + - tx-internal-delay-ps + - eswin,hsp-sp-csr + +unevaluatedProperties: false + +examples: + - | + ethernet@50400000 { + compatible = "eswin,eic7700-qos-eth", "snps,dwmac-5.20"; + reg = <0x50400000 0x10000>; + clocks = <&d0_clock 186>, <&d0_clock 171>, <&d0_clock 40>, + <&d0_clock 193>; + clock-names = "axi", "cfg", "stmmaceth", "tx"; + interrupt-parent = <&plic>; + interrupts = <61>; + interrupt-names = "macirq"; + phy-mode = "rgmii-id"; + phy-handle = <&phy0>; + resets = <&reset 95>; + reset-names = "stmmaceth"; + rx-internal-delay-ps = <200>; + tx-internal-delay-ps = <200>; + eswin,hsp-sp-csr = <&hsp_sp_csr 0x100 0x108 0x118>; + snps,axi-config = <&stmmac_axi_setup>; + snps,aal; + snps,fixed-burst; + snps,tso; + stmmac_axi_setup: stmmac-axi-config { + snps,blen = <0 0 0 0 16 8 4>; + snps,rd_osr_lmt = <2>; + snps,wr_osr_lmt = <2>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/ethernet-connector.yaml b/Documentation/devicetree/bindings/net/ethernet-connector.yaml new file mode 100644 index 0000000000000..2ccac24bd8d60 --- /dev/null +++ b/Documentation/devicetree/bindings/net/ethernet-connector.yaml @@ -0,0 +1,57 @@ +# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +%YAML 1.2 +--- +$id: http://devicetree.org/schemas/net/ethernet-connector.yaml# +$schema: http://devicetree.org/meta-schemas/core.yaml# + +title: Generic Ethernet Connector + +maintainers: + - Maxime Chevallier + +description: + An Ethernet Connector represents the output of a network component such as + a PHY, an Ethernet controller with no PHY, or an SFP module. + +properties: + + pairs: + description: + Defines the number of BaseT pairs that are used on the connector. + $ref: /schemas/types.yaml#/definitions/uint32 + enum: [1, 2, 4] + + media: + description: + The mediums, as defined in 802.3, that can be used on the port. + enum: + - BaseT + - BaseK + - BaseS + - BaseC + - BaseL + - BaseD + - BaseE + - BaseF + - BaseV + - BaseMLD + +required: + - media + +allOf: + - if: + properties: + media: + contains: + const: BaseT + then: + required: + - pairs + else: + properties: + pairs: false + +additionalProperties: true + +... diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml index 2ec2d9fda7e30..58634fee9fc4d 100644 --- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml +++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml @@ -35,9 +35,13 @@ properties: description: PHYs that implement IEEE802.3 clause 45 - pattern: "^ethernet-phy-id[a-f0-9]{4}\\.[a-f0-9]{4}$" 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, @@ -277,6 +281,17 @@ properties: additionalProperties: false + mdi: + type: object + + patternProperties: + '^connector-[0-9]+$': + $ref: /schemas/net/ethernet-connector.yaml# + + unevaluatedProperties: false + + additionalProperties: false + required: - reg @@ -313,5 +328,12 @@ examples: default-state = "keep"; }; }; + /* Fast Ethernet port, with only 2 pairs wired */ + mdi { + connector-0 { + pairs = <2>; + media = "BaseT"; + }; + }; }; }; diff --git a/Documentation/devicetree/bindings/net/fsl,enetc.yaml b/Documentation/devicetree/bindings/net/fsl,enetc.yaml index ca70f00501711..aac20ab72ace7 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/mscc-phy-vsc8531.txt b/Documentation/devicetree/bindings/net/mscc-phy-vsc8531.txt deleted file mode 100644 index 0a3647fe331b6..0000000000000 --- 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,led-1-mode = ; - 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 0000000000000..0afbd0ff126f5 --- /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 + +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 + #include + + 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,led-1-mode = ; + 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 97389fd5dbbfa..deea4fd73d767 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 bb1ee33986555..0b3803f647b7b 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 e7ee0d9efed83..423959cb928d9 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 0ac7c4b47d6bf..d17112527dab0 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 658c004e6a5c8..dd3c72e8363e7 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 ce21979a2d9a4..e8d3814db0e94 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/ti,dp83822.yaml b/Documentation/devicetree/bindings/net/ti,dp83822.yaml index 28a0bddb9af94..23c70d863c398 100644 --- a/Documentation/devicetree/bindings/net/ti,dp83822.yaml +++ b/Documentation/devicetree/bindings/net/ti,dp83822.yaml @@ -47,6 +47,9 @@ properties: is disabled. In fiber mode, auto-negotiation is disabled and the PHY can only work in 100base-fx (full and half duplex) modes. + This property is deprecated, for details please refer to + Documentation/devicetree/bindings/net/ethernet-connector.yaml + deprecated: true rx-internal-delay-ps: description: | @@ -141,7 +144,11 @@ examples: tx-internal-delay-ps = <1>; ti,gpio2-clk-out = "xi"; mac-termination-ohms = <43>; + mdi { + connector-0 { + media = "BaseF"; + }; + }; }; }; - ... diff --git a/Documentation/devicetree/bindings/vendor-prefixes.yaml b/Documentation/devicetree/bindings/vendor-prefixes.yaml index f1d1882009ba9..424aa7b911a77 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 be1fc643b645e..83118c728ed90 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 5a234e9b5fa2e..57f59fe23e3f8 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 7b1ec153e8349..b020a537d8acd 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 246fa07bccf68..0166a7e4afbbf 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/devlink.yaml b/Documentation/netlink/specs/devlink.yaml index 3db59c9658694..426d5aa7d9551 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 diff --git a/Documentation/netlink/specs/dpll.yaml b/Documentation/netlink/specs/dpll.yaml index 80728f6f9bc87..78d0724d7e12c 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 6a0fb19745138..05d2b6508b59c 100644 --- a/Documentation/netlink/specs/ethtool.yaml +++ b/Documentation/netlink/specs/ethtool.yaml @@ -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 e00d3fa1c152d..82bf5cb2617d1 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/psp.yaml b/Documentation/netlink/specs/psp.yaml index 944429e5c9a84..f3a57782d2cf4 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 3a582eac1629e..abcbaa73fa9dc 100644 --- a/Documentation/netlink/specs/rt-addr.yaml +++ b/Documentation/netlink/specs/rt-addr.yaml @@ -86,17 +86,17 @@ 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 display-hint: ipv4 - name: anycast diff --git a/Documentation/netlink/specs/rt-link.yaml b/Documentation/netlink/specs/rt-link.yaml index 2a23e9699c0b6..ca22c68ca6914 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 +1868,7 @@ attribute-sets: type: u32 - name: remote - type: binary + type: u32 display-hint: ipv4 - name: ttl @@ -1913,6 +1913,35 @@ attribute-sets: name: port-range 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- @@ -1923,11 +1952,11 @@ 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 +1986,7 @@ attribute-sets: display-hint: ipv6 - name: 6rd-relay-prefix - type: binary + type: u32 display-hint: ipv4 - name: 6rd-prefixlen @@ -2299,6 +2328,9 @@ 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 2f568a6231c93..0f46ef3135905 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 1ecb3fadc0679..33195db96746c 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 bebee452a9507..7f03a44ab0361 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/networking/6pack.rst b/Documentation/networking/6pack.rst index bc5bf1f1a98fb..66d5fd4fc8212 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 3bf7f99cd7bbf..20e5075d0d0e7 100644 --- a/Documentation/networking/arcnet-hardware.rst +++ b/Documentation/networking/arcnet-hardware.rst @@ -4,18 +4,20 @@ ARCnet Hardware =============== +:Author: Avery Pennarun + .. 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 `. 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 82fce606c0f0b..cd43a18ad1494 100644 --- a/Documentation/networking/arcnet.rst +++ b/Documentation/networking/arcnet.rst @@ -4,6 +4,8 @@ ARCnet ====== +:Author: Avery Pennarun + .. 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 6877a32605820..5aedbabb73827 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 7cfcd183054f8..bcc02355f828b 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 0000000000000..d35cf8a46b6cd --- /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 08bb39ab15286..eafe09abc40c2 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 0a9c20d701225..c0597d456641d 100644 --- a/Documentation/networking/devlink/devlink-params.rst +++ b/Documentation/networking/devlink/devlink-params.rst @@ -151,3 +151,7 @@ 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 d3cb5bb5197e9..51c887f0dc833 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 0c58e5c729d92..35b12a2bfeba5 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/stmmac.rst b/Documentation/networking/devlink/stmmac.rst new file mode 100644 index 0000000000000..47e3ff10bc082 --- /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/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index b270886c5f5d5..af56c304cef43 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 c775cababc8c1..915c279777566 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -96,6 +96,7 @@ Contents: packet_mmap phonet phy-link-topology + phy-port pktgen plip ppp_generic diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index a06cb99d66dcd..db2b45b34f177 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -482,7 +482,9 @@ tcp_ecn_option - INTEGER 1 Send AccECN option sparingly according to the minimum option rules outlined in draft-ietf-tcpm-accurate-ecn. 2 Send AccECN option on every packet whenever it fits into TCP - option space. + option space except when AccECN fallback is triggered. + 3 Send AccECN option on every packet whenever it fits into TCP + option space even when AccECN fallback is triggered. = ============================================================ Default: 2 @@ -854,9 +856,18 @@ 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) @@ -1796,6 +1807,23 @@ 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 +3290,23 @@ 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 7dd60366f4ff3..4e008efebb352 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`) 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_sock.rst b/Documentation/networking/net_cachelines/inet_sock.rst index b11bf48fa2b36..4c72a28a7012e 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/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst index 26f32dbcf6ec9..563daea10d6c5 100644 --- a/Documentation/networking/net_cachelines/tcp_sock.rst +++ b/Documentation/networking/net_cachelines/tcp_sock.rst @@ -105,6 +105,7 @@ u32 received_ce read_mostly read_w u32[3] received_ecn_bytes read_mostly read_write u8:4 received_ce_pending read_mostly read_write u32[3] delivered_ecn_bytes read_write +u16 pkts_acked_ewma read_write u8:2 syn_ect_snt write_mostly read_write u8:2 syn_ect_rcv read_mostly read_write u8:2 accecn_minlen write_mostly read_write diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst index 2555e75e5cc1c..4ab5d7b05cf10 100644 --- a/Documentation/networking/netconsole.rst +++ b/Documentation/networking/netconsole.rst @@ -88,7 +88,7 @@ for example: nc -u -l -p ' / 'nc -u -l - or:: + or:: netcat -u -l -p ' / 'netcat -u -l diff --git a/Documentation/networking/nfc.rst b/Documentation/networking/nfc.rst index 9aab3a88c9b29..4017350061433 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/phy-port.rst b/Documentation/networking/phy-port.rst new file mode 100644 index 0000000000000..6e28d9094bce3 --- /dev/null +++ b/Documentation/networking/phy-port.rst @@ -0,0 +1,111 @@ +.. SPDX-License-Identifier: GPL-2.0 +.. _phy_port: + +================= +Ethernet ports +================= + +This document is a basic description of the phy_port infrastructure, +introduced to represent physical interfaces of Ethernet devices. + +Without phy_port, we already have quite a lot of information about what the +media-facing interface of a NIC can do and looks like, through the +:c:type:`struct ethtool_link_ksettings ` attributes, +which includes : + + - What the NIC can do through the :c:member:`supported` field + - What the Link Partner advertises through :c:member:`lp_advertising` + - Which features we're advertising through :c:member:`advertising` + +We also have info about the number of pairs and the PORT type. These settings +are built by aggregating together information reported by various devices that +are sitting on the link : + + - The NIC itself, through the :c:member:`get_link_ksettings` callback + - Precise information from the MAC and PCS by using phylink in the MAC driver + - Information reported by the PHY device + - Information reported by an SFP module (which can itself include a PHY) + +This model however starts showing its limitations when we consider devices that +have more than one media interface. In such a case, only information about the +actively used interface is reported, and it's not possible to know what the +other interfaces can do. In fact, we have very little information about whether +or not there are any other media interfaces. + +The goal of the phy_port representation is to provide a way of representing a +physical interface of a NIC, regardless of what is driving the port (NIC through +a firmware, SFP module, Ethernet PHY). + +Multi-port interfaces examples +============================== + +Several cases of multi-interface NICs have been observed so far : + +Internal MII Mux:: + + +------------------+ + | SoC | + | +-----+ | +-----+ + | +-----+ | |-------------| PHY | + | | MAC |--| Mux | | +-----+ +-----+ + | +-----+ | |-----| SFP | + | +-----+ | +-----+ + +------------------+ + +Internal Mux with internal PHY:: + + +------------------------+ + | SoC | + | +-----+ +-----+ + | +-----+ | |-| PHY | + | | MAC |--| Mux | +-----+ +-----+ + | +-----+ | |-----------| SFP | + | +-----+ | +-----+ + +------------------------+ + +External Mux:: + + +---------+ + | SoC | +-----+ +-----+ + | | | |--| PHY | + | +-----+ | | | +-----+ + | | MAC |----| Mux | +-----+ + | +-----+ | | |--| PHY | + | | +-----+ +-----+ + | | | + | GPIO-------+ + +---------+ + +Double-port PHY:: + + +---------+ + | SoC | +-----+ + | | | |--- RJ45 + | +-----+ | | | + | | MAC |---| PHY | +-----+ + | +-----+ | | |---| SFP | + +---------+ +-----+ +-----+ + +phy_port aims at providing a path to support all the above topologies, by +representing the media interfaces in a way that's agnostic to what's driving +the interface. the struct phy_port object has its own set of callback ops, and +will eventually be able to report its own ksettings:: + + _____ +------+ + ( )-----| Port | + +-----+ ( ) +------+ + | MAC |--( ??? ) + +-----+ ( ) +------+ + (_____)-----| Port | + +------+ + +Next steps +========== + +As of writing this documentation, only ports controlled by PHY devices are +supported. The next steps will be to add the Netlink API to expose these +to userspace and add support for raw ports (controlled by some firmware, and directly +managed by the NIC driver). + +Another parallel task is the introduction of a MII muxing framework to allow the +control of non-PHY driver multi-port setups. diff --git a/Documentation/networking/smc-sysctl.rst b/Documentation/networking/smc-sysctl.rst index a874d007f2db5..904a910f198e4 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 518284e287b04..66b0ef941457c 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 36cc7afc2527d..980c442d7161a 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/MAINTAINERS b/MAINTAINERS index 48aabeeed0297..aa9feced07cc1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -795,6 +795,14 @@ S: Maintained F: Documentation/i2c/busses/i2c-ali1563.rst F: drivers/i2c/busses/i2c-ali1563.c +ALIBABA ELASTIC ETHERNET ADAPTER DRIVER +M: Xuan Zhuo +M: Wen Gu +R: Philo Lu +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/alibaba/eea + ALIBABA ELASTIC RDMA DRIVER M: Cheng Xu M: Kai Shen @@ -3301,6 +3309,7 @@ F: drivers/*/*/*rockchip* F: drivers/*/*rockchip* F: drivers/clk/rockchip/ F: drivers/i2c/busses/i2c-rk3x.c +F: drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c F: sound/soc/rockchip/ N: rockchip @@ -5132,7 +5141,6 @@ F: Documentation/devicetree/bindings/net/brcm,unimac-mdio.yaml F: drivers/net/ethernet/broadcom/genet/ F: drivers/net/ethernet/broadcom/unimac.h F: drivers/net/mdio/mdio-bcm-unimac.c -F: include/linux/platform_data/bcmgenet.h F: include/linux/platform_data/mdio-bcm-unimac.h BROADCOM IPROC ARM ARCHITECTURE @@ -9267,7 +9275,6 @@ M: Ido Schimmel L: bridge@lists.linux.dev L: netdev@vger.kernel.org S: Maintained -W: http://www.linuxfoundation.org/en/Net:Bridge F: include/linux/if_bridge.h F: include/uapi/linux/if_bridge.h F: include/linux/netfilter_bridge/ @@ -9280,9 +9287,11 @@ R: Russell King L: netdev@vger.kernel.org S: Maintained F: Documentation/ABI/testing/sysfs-class-net-phydev +F: Documentation/devicetree/bindings/net/ethernet-connector.yaml F: Documentation/devicetree/bindings/net/ethernet-phy.yaml F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml +F: Documentation/networking/phy-port.rst F: Documentation/networking/phy.rst F: drivers/net/mdio/ F: drivers/net/mdio/acpi_mdio.c @@ -9299,6 +9308,7 @@ F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h F: include/linux/phy_link_topology.h +F: include/linux/phy_port.h F: include/linux/phylib_stubs.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/linux/platform_data/mdio-gpio.h @@ -14056,7 +14066,7 @@ F: tools/testing/selftests/landlock/ K: landlock K: LANDLOCK -LANTIQ / INTEL Ethernet drivers +LANTIQ / MAXLINEAR / INTEL Ethernet DSA drivers M: Hauke Mehrtens L: netdev@vger.kernel.org S: Maintained @@ -14064,6 +14074,7 @@ F: Documentation/devicetree/bindings/net/dsa/lantiq,gswip.yaml F: drivers/net/dsa/lantiq/* F: drivers/net/ethernet/lantiq_xrx200.c F: net/dsa/tag_gswip.c +F: net/dsa/tag_mxl-gsw1xx.c LANTIQ MIPS ARCHITECTURE M: John Crispin @@ -17456,6 +17467,14 @@ S: Maintained F: Documentation/devicetree/bindings/net/motorcomm,yt8xxx.yaml F: drivers/net/phy/motorcomm.c +MOTORCOMM YT921X ETHERNET SWITCH DRIVER +M: David Yang +L: netdev@vger.kernel.org +S: Maintained +F: Documentation/devicetree/bindings/net/dsa/motorcomm,yt921x.yaml +F: drivers/net/dsa/yt921x.* +F: net/dsa/tag_yt921x.c + MOXA SMARTIO/INDUSTIO/INTELLIO SERIAL CARD M: Jiri Slaby S: Maintained @@ -17611,6 +17630,14 @@ T: git git://linuxtv.org/media.git F: Documentation/devicetree/bindings/media/i2c/aptina,mt9v111.yaml F: drivers/media/i2c/mt9v111.c +MUCSE ETHERNET DRIVER +M: Yibo Dong +L: netdev@vger.kernel.org +S: Maintained +W: https://www.mucse.com/en/ +F: Documentation/networking/device_drivers/ethernet/mucse/ +F: drivers/net/ethernet/mucse/ + MULTIFUNCTION DEVICES (MFD) M: Lee Jones S: Maintained diff --git a/arch/m68k/coldfire/m5272.c b/arch/m68k/coldfire/m5272.c index 918e2a3236c5b..28b3ffa25ba0b 100644 --- a/arch/m68k/coldfire/m5272.c +++ b/arch/m68k/coldfire/m5272.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -103,23 +102,9 @@ void __init config_BSP(char *commandp, int size) /***************************************************************************/ -/* - * Some 5272 based boards have the FEC ethernet directly connected to - * an ethernet switch. In this case we need to use the fixed phy type, - * and we need to declare it early in boot. - */ -static const struct fixed_phy_status nettel_fixed_phy_status __initconst = { - .link = 1, - .speed = 100, - .duplex = 0, -}; - -/***************************************************************************/ - static int __init init_BSP(void) { m5272_uarts_init(); - fixed_phy_add(&nettel_fixed_phy_status); clkdev_add_table(m5272_clk_lookup, ARRAY_SIZE(m5272_clk_lookup)); return 0; } diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c index a93a4266dc1ef..38ed61b4bd962 100644 --- a/arch/mips/bcm47xx/setup.c +++ b/arch/mips/bcm47xx/setup.c @@ -256,12 +256,6 @@ static int __init bcm47xx_cpu_fixes(void) } arch_initcall(bcm47xx_cpu_fixes); -static const struct fixed_phy_status bcm47xx_fixed_phy_status __initconst = { - .link = 1, - .speed = SPEED_100, - .duplex = DUPLEX_FULL, -}; - static int __init bcm47xx_register_bus_complete(void) { switch (bcm47xx_bus_type) { @@ -282,7 +276,6 @@ static int __init bcm47xx_register_bus_complete(void) bcm47xx_leds_register(); bcm47xx_workarounds(); - fixed_phy_add(&bcm47xx_fixed_phy_status); return 0; } device_initcall(bcm47xx_register_bus_complete); diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 79fa38ca954d1..652896207f2f0 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -2,7 +2,7 @@ CONFIG_WERROR=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y -CONFIG_NO_HZ=y +CONFIG_HZ_PERIODIC=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_BSD_PROCESS_ACCT=y @@ -190,19 +190,6 @@ CONFIG_HPET=y # CONFIG_HPET_MMAP is not set CONFIG_I2C_I801=y CONFIG_WATCHDOG=y -CONFIG_AGP=y -CONFIG_AGP_AMD64=y -CONFIG_AGP_INTEL=y -CONFIG_DRM=y -CONFIG_DRM_I915=y -CONFIG_DRM_VIRTIO_GPU=y -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_HRTIMER=y -CONFIG_SND_SEQUENCER=y -CONFIG_SND_SEQ_DUMMY=y -CONFIG_SND_HDA_INTEL=y -CONFIG_SND_HDA_HWDEP=y CONFIG_HIDRAW=y CONFIG_HID_GYRATION=y CONFIG_HID_NTRIG=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 7d7310cdf8b0a..d9e4feeb5a3d5 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -2,7 +2,7 @@ CONFIG_WERROR=y CONFIG_SYSVIPC=y CONFIG_POSIX_MQUEUE=y CONFIG_AUDIT=y -CONFIG_NO_HZ=y +CONFIG_HZ_PERIODIC=y CONFIG_HIGH_RES_TIMERS=y CONFIG_PREEMPT_VOLUNTARY=y CONFIG_BSD_PROCESS_ACCT=y @@ -29,6 +29,7 @@ CONFIG_KALLSYMS_ALL=y CONFIG_PROFILING=y CONFIG_KEXEC=y CONFIG_SMP=y +CONFIG_CPU_MITIGATIONS=n CONFIG_HYPERVISOR_GUEST=y CONFIG_PARAVIRT=y CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y @@ -187,19 +188,6 @@ CONFIG_HPET=y # CONFIG_HPET_MMAP is not set CONFIG_I2C_I801=y CONFIG_WATCHDOG=y -CONFIG_AGP=y -CONFIG_AGP_AMD64=y -CONFIG_AGP_INTEL=y -CONFIG_DRM=y -CONFIG_DRM_I915=y -CONFIG_DRM_VIRTIO_GPU=y -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_HRTIMER=y -CONFIG_SND_SEQUENCER=y -CONFIG_SND_SEQ_DUMMY=y -CONFIG_SND_HDA_INTEL=y -CONFIG_SND_HDA_HWDEP=y CONFIG_HIDRAW=y CONFIG_HID_GYRATION=y CONFIG_HID_NTRIG=y diff --git a/crypto/af_alg.c b/crypto/af_alg.c index ca6fdcc6c54ac..5e760ab626183 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -145,7 +145,7 @@ void af_alg_release_parent(struct sock *sk) } EXPORT_SYMBOL_GPL(af_alg_release_parent); -static int alg_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int alg_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { const u32 allowed = CRYPTO_ALG_KERN_DRIVER_ONLY; struct sock *sk = sock->sk; diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index caaf2781136d0..33bc91665fe82 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -450,7 +450,7 @@ static struct socket *drbd_try_connect(struct drbd_connection *connection) * a free one dynamically. */ what = "bind before connect"; - err = sock->ops->bind(sock, (struct sockaddr *) &src_in6, my_addr_len); + err = sock->ops->bind(sock, (struct sockaddr_unsized *) &src_in6, my_addr_len); if (err < 0) goto out; @@ -458,7 +458,7 @@ static struct socket *drbd_try_connect(struct drbd_connection *connection) * stay C_WF_CONNECTION, don't go Disconnecting! */ disconnect_on_error = 0; what = "connect"; - err = sock->ops->connect(sock, (struct sockaddr *) &peer_in6, peer_addr_len, 0); + err = sock->ops->connect(sock, (struct sockaddr_unsized *) &peer_in6, peer_addr_len, 0); out: if (err < 0) { @@ -537,7 +537,7 @@ static int prepare_listen_socket(struct drbd_connection *connection, struct acce drbd_setbufsize(s_listen, sndbuf_size, rcvbuf_size); what = "bind before listen"; - err = s_listen->ops->bind(s_listen, (struct sockaddr *)&my_addr, my_addr_len); + err = s_listen->ops->bind(s_listen, (struct sockaddr_unsized *)&my_addr, my_addr_len); if (err < 0) goto out; diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig index 3a1611008e48e..7fd4192302c94 100644 --- a/drivers/clk/Kconfig +++ b/drivers/clk/Kconfig @@ -555,7 +555,6 @@ source "drivers/clk/zynqmp/Kconfig" config CLK_KUNIT_TEST tristate "Basic Clock Framework Kunit Tests" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS select DTC help Kunit tests for the common clock framework. @@ -563,7 +562,6 @@ config CLK_KUNIT_TEST config CLK_FIXED_RATE_KUNIT_TEST tristate "Basic fixed rate clk type KUnit test" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS select DTC help KUnit tests for the basic fixed rate clk type. @@ -572,14 +570,12 @@ config CLK_GATE_KUNIT_TEST tristate "Basic gate type Kunit test" if !KUNIT_ALL_TESTS depends on KUNIT depends on !S390 - default KUNIT_ALL_TESTS help Kunit test for the basic clk gate type. config CLK_FD_KUNIT_TEST tristate "Basic fractional divider type Kunit test" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS help Kunit test for the clk-fractional-divider type. diff --git a/drivers/dibs/dibs_main.c b/drivers/dibs/dibs_main.c index 0374f8350ff7f..dac14d843af73 100644 --- a/drivers/dibs/dibs_main.c +++ b/drivers/dibs/dibs_main.c @@ -254,9 +254,6 @@ static int __init dibs_init(void) { int rc; - memset(clients, 0, sizeof(clients)); - max_client = 0; - dibs_class = class_create("dibs"); if (IS_ERR(dibs_class)) return PTR_ERR(dibs_class); @@ -274,5 +271,5 @@ static void __exit dibs_exit(void) class_destroy(dibs_class); } -module_init(dibs_init); +subsys_initcall(dibs_init); module_exit(dibs_exit); diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c index a4153bcb6dcfe..64944f601ee5a 100644 --- a/drivers/dpll/dpll_netlink.c +++ b/drivers/dpll/dpll_netlink.c @@ -637,6 +637,10 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin, ret = dpll_msg_add_pin_freq(msg, pin, ref, extack); if (ret) return ret; + if (prop->phase_gran && + nla_put_u32(msg, DPLL_A_PIN_PHASE_ADJUST_GRAN, + prop->phase_gran)) + return -EMSGSIZE; if (nla_put_s32(msg, DPLL_A_PIN_PHASE_ADJUST_MIN, prop->phase_range.min)) return -EMSGSIZE; @@ -1261,7 +1265,13 @@ dpll_pin_phase_adj_set(struct dpll_pin *pin, struct nlattr *phase_adj_attr, if (phase_adj > pin->prop.phase_range.max || phase_adj < pin->prop.phase_range.min) { NL_SET_ERR_MSG_ATTR(extack, phase_adj_attr, - "phase adjust value not supported"); + "phase adjust value of out range"); + return -EINVAL; + } + if (pin->prop.phase_gran && phase_adj % (s32)pin->prop.phase_gran) { + NL_SET_ERR_MSG_ATTR_FMT(extack, phase_adj_attr, + "phase adjust value not multiple of %u", + pin->prop.phase_gran); return -EINVAL; } diff --git a/drivers/dpll/zl3073x/Makefile b/drivers/dpll/zl3073x/Makefile index 84e22aae57e5f..bd324c7fe7101 100644 --- a/drivers/dpll/zl3073x/Makefile +++ b/drivers/dpll/zl3073x/Makefile @@ -1,7 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ZL3073X) += zl3073x.o -zl3073x-objs := core.o devlink.o dpll.o flash.o fw.o prop.o +zl3073x-objs := core.o devlink.o dpll.o flash.o fw.o \ + out.o prop.o ref.o synth.o obj-$(CONFIG_ZL3073X_I2C) += zl3073x_i2c.o zl3073x_i2c-objs := i2c.o diff --git a/drivers/dpll/zl3073x/core.c b/drivers/dpll/zl3073x/core.c index e42e527813cf8..383e2397dd033 100644 --- a/drivers/dpll/zl3073x/core.c +++ b/drivers/dpll/zl3073x/core.c @@ -129,47 +129,6 @@ const struct regmap_config zl3073x_regmap_config = { }; EXPORT_SYMBOL_NS_GPL(zl3073x_regmap_config, "ZL3073X"); -/** - * zl3073x_ref_freq_factorize - factorize given frequency - * @freq: input frequency - * @base: base frequency - * @mult: multiplier - * - * Checks if the given frequency can be factorized using one of the - * supported base frequencies. If so the base frequency and multiplier - * are stored into appropriate parameters if they are not NULL. - * - * Return: 0 on success, -EINVAL if the frequency cannot be factorized - */ -int -zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult) -{ - static const u16 base_freqs[] = { - 1, 2, 4, 5, 8, 10, 16, 20, 25, 32, 40, 50, 64, 80, 100, 125, - 128, 160, 200, 250, 256, 320, 400, 500, 625, 640, 800, 1000, - 1250, 1280, 1600, 2000, 2500, 3125, 3200, 4000, 5000, 6250, - 6400, 8000, 10000, 12500, 15625, 16000, 20000, 25000, 31250, - 32000, 40000, 50000, 62500, - }; - u32 div; - int i; - - for (i = 0; i < ARRAY_SIZE(base_freqs); i++) { - div = freq / base_freqs[i]; - - if (div <= U16_MAX && (freq % base_freqs[i]) == 0) { - if (base) - *base = base_freqs[i]; - if (mult) - *mult = div; - - return 0; - } - } - - return -EINVAL; -} - static bool zl3073x_check_reg(struct zl3073x_dev *zldev, unsigned int reg, size_t size) { @@ -593,190 +552,6 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev, return rc; } -/** - * zl3073x_ref_state_fetch - get input reference state - * @zldev: pointer to zl3073x_dev structure - * @index: input reference index to fetch state for - * - * Function fetches information for the given input reference that are - * invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_ref *input = &zldev->ref[index]; - u8 ref_config; - int rc; - - /* If the input is differential then the configuration for N-pin - * reference is ignored and P-pin config is used for both. - */ - if (zl3073x_is_n_pin(index) && - zl3073x_ref_is_diff(zldev, index - 1)) { - input->enabled = zl3073x_ref_is_enabled(zldev, index - 1); - input->diff = true; - - return 0; - } - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* Read ref_config register */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_CONFIG, &ref_config); - if (rc) - return rc; - - input->enabled = FIELD_GET(ZL_REF_CONFIG_ENABLE, ref_config); - input->diff = FIELD_GET(ZL_REF_CONFIG_DIFF_EN, ref_config); - - dev_dbg(zldev->dev, "REF%u is %s and configured as %s\n", index, - str_enabled_disabled(input->enabled), - input->diff ? "differential" : "single-ended"); - - return rc; -} - -/** - * zl3073x_out_state_fetch - get output state - * @zldev: pointer to zl3073x_dev structure - * @index: output index to fetch state for - * - * Function fetches information for the given output (not output pin) - * that are invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_out *out = &zldev->out[index]; - u8 output_ctrl, output_mode; - int rc; - - /* Read output configuration */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_CTRL(index), &output_ctrl); - if (rc) - return rc; - - /* Store info about output enablement and synthesizer the output - * is connected to. - */ - out->enabled = FIELD_GET(ZL_OUTPUT_CTRL_EN, output_ctrl); - out->synth = FIELD_GET(ZL_OUTPUT_CTRL_SYNTH_SEL, output_ctrl); - - dev_dbg(zldev->dev, "OUT%u is %s and connected to SYNTH%u\n", index, - str_enabled_disabled(out->enabled), out->synth); - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* Read output_mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - - /* Extract and store output signal format */ - out->signal_format = FIELD_GET(ZL_OUTPUT_MODE_SIGNAL_FORMAT, - output_mode); - - dev_dbg(zldev->dev, "OUT%u has signal format 0x%02x\n", index, - out->signal_format); - - return rc; -} - -/** - * zl3073x_synth_state_fetch - get synth state - * @zldev: pointer to zl3073x_dev structure - * @index: synth index to fetch state for - * - * Function fetches information for the given synthesizer that are - * invariant and stores them for later use. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 index) -{ - struct zl3073x_synth *synth = &zldev->synth[index]; - u16 base, m, n; - u8 synth_ctrl; - u32 mult; - int rc; - - /* Read synth control register */ - rc = zl3073x_read_u8(zldev, ZL_REG_SYNTH_CTRL(index), &synth_ctrl); - if (rc) - return rc; - - /* Store info about synth enablement and DPLL channel the synth is - * driven by. - */ - synth->enabled = FIELD_GET(ZL_SYNTH_CTRL_EN, synth_ctrl); - synth->dpll = FIELD_GET(ZL_SYNTH_CTRL_DPLL_SEL, synth_ctrl); - - dev_dbg(zldev->dev, "SYNTH%u is %s and driven by DPLL%u\n", index, - str_enabled_disabled(synth->enabled), synth->dpll); - - guard(mutex)(&zldev->multiop_lock); - - /* Read synth configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_SYNTH_MB_SEM, ZL_SYNTH_MB_SEM_RD, - ZL_REG_SYNTH_MB_MASK, BIT(index)); - if (rc) - return rc; - - /* The output frequency is determined by the following formula: - * base * multiplier * numerator / denominator - * - * Read registers with these values - */ - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_BASE, &base); - if (rc) - return rc; - - rc = zl3073x_read_u32(zldev, ZL_REG_SYNTH_FREQ_MULT, &mult); - if (rc) - return rc; - - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_M, &m); - if (rc) - return rc; - - rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_N, &n); - if (rc) - return rc; - - /* Check denominator for zero to avoid div by 0 */ - if (!n) { - dev_err(zldev->dev, - "Zero divisor for SYNTH%u retrieved from device\n", - index); - return -EINVAL; - } - - /* Compute and store synth frequency */ - zldev->synth[index].freq = div_u64(mul_u32_u32(base * m, mult), n); - - dev_dbg(zldev->dev, "SYNTH%u frequency: %u Hz\n", index, - zldev->synth[index].freq); - - return rc; -} - static int zl3073x_dev_state_fetch(struct zl3073x_dev *zldev) { @@ -816,6 +591,21 @@ zl3073x_dev_state_fetch(struct zl3073x_dev *zldev) return rc; } +static void +zl3073x_dev_ref_status_update(struct zl3073x_dev *zldev) +{ + int i, rc; + + for (i = 0; i < ZL3073X_NUM_REFS; i++) { + rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(i), + &zldev->ref[i].mon_status); + if (rc) + dev_warn(zldev->dev, + "Failed to get REF%u status: %pe\n", i, + ERR_PTR(rc)); + } +} + /** * zl3073x_ref_phase_offsets_update - update reference phase offsets * @zldev: pointer to zl3073x_dev structure @@ -935,6 +725,9 @@ zl3073x_dev_periodic_work(struct kthread_work *work) struct zl3073x_dpll *zldpll; int rc; + /* Update input references status */ + zl3073x_dev_ref_status_update(zldev); + /* Update DPLL-to-connected-ref phase offsets registers */ rc = zl3073x_ref_phase_offsets_update(zldev, -1); if (rc) diff --git a/drivers/dpll/zl3073x/core.h b/drivers/dpll/zl3073x/core.h index 1dca4ddcf2350..09bca2d0926d5 100644 --- a/drivers/dpll/zl3073x/core.h +++ b/drivers/dpll/zl3073x/core.h @@ -9,7 +9,10 @@ #include #include +#include "out.h" +#include "ref.h" #include "regs.h" +#include "synth.h" struct device; struct regmap; @@ -27,42 +30,6 @@ struct zl3073x_dpll; #define ZL3073X_NUM_PINS (ZL3073X_NUM_INPUT_PINS + \ ZL3073X_NUM_OUTPUT_PINS) -/** - * struct zl3073x_ref - input reference invariant info - * @enabled: input reference is enabled or disabled - * @diff: true if input reference is differential - * @ffo: current fractional frequency offset - */ -struct zl3073x_ref { - bool enabled; - bool diff; - s64 ffo; -}; - -/** - * struct zl3073x_out - output invariant info - * @enabled: out is enabled or disabled - * @synth: synthesizer the out is connected to - * @signal_format: out signal format - */ -struct zl3073x_out { - bool enabled; - u8 synth; - u8 signal_format; -}; - -/** - * struct zl3073x_synth - synthesizer invariant info - * @freq: synthesizer frequency - * @dpll: ID of DPLL the synthesizer is driven by - * @enabled: synth is enabled or disabled - */ -struct zl3073x_synth { - u32 freq; - u8 dpll; - bool enabled; -}; - /** * struct zl3073x_dev - zl3073x device * @dev: pointer to device @@ -175,7 +142,6 @@ int zl3073x_write_hwreg_seq(struct zl3073x_dev *zldev, * Misc operations *****************/ -int zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult); int zl3073x_ref_phase_offsets_update(struct zl3073x_dev *zldev, int channel); static inline bool @@ -217,172 +183,141 @@ zl3073x_output_pin_out_get(u8 id) } /** - * zl3073x_ref_ffo_get - get current fractional frequency offset + * zl3073x_dev_ref_freq_get - get input reference frequency * @zldev: pointer to zl3073x device * @index: input reference index * - * Return: the latest measured fractional frequency offset + * Return: frequency of given input reference */ -static inline s64 -zl3073x_ref_ffo_get(struct zl3073x_dev *zldev, u8 index) +static inline u32 +zl3073x_dev_ref_freq_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].ffo; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_freq_get(ref); } /** - * zl3073x_ref_is_diff - check if the given input reference is differential + * zl3073x_dev_ref_is_diff - check if the given input reference is differential * @zldev: pointer to zl3073x device * @index: input reference index * * Return: true if reference is differential, false if reference is single-ended */ static inline bool -zl3073x_ref_is_diff(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_is_diff(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].diff; + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); + + return zl3073x_ref_is_diff(ref); } -/** - * zl3073x_ref_is_enabled - check if the given input reference is enabled +/* + * zl3073x_dev_ref_is_status_ok - check the given input reference status * @zldev: pointer to zl3073x device * @index: input reference index * - * Return: true if input refernce is enabled, false otherwise + * Return: true if the status is ok, false otherwise */ static inline bool -zl3073x_ref_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_ref_is_status_ok(struct zl3073x_dev *zldev, u8 index) { - return zldev->ref[index].enabled; -} + const struct zl3073x_ref *ref = zl3073x_ref_state_get(zldev, index); -/** - * zl3073x_synth_dpll_get - get DPLL ID the synth is driven by - * @zldev: pointer to zl3073x device - * @index: synth index - * - * Return: ID of DPLL the given synthetizer is driven by - */ -static inline u8 -zl3073x_synth_dpll_get(struct zl3073x_dev *zldev, u8 index) -{ - return zldev->synth[index].dpll; + return zl3073x_ref_is_status_ok(ref); } /** - * zl3073x_synth_freq_get - get synth current freq + * zl3073x_dev_synth_freq_get - get synth current freq * @zldev: pointer to zl3073x device * @index: synth index * * Return: frequency of given synthetizer */ static inline u32 -zl3073x_synth_freq_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_synth_freq_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->synth[index].freq; -} + const struct zl3073x_synth *synth; -/** - * zl3073x_synth_is_enabled - check if the given synth is enabled - * @zldev: pointer to zl3073x device - * @index: synth index - * - * Return: true if synth is enabled, false otherwise - */ -static inline bool -zl3073x_synth_is_enabled(struct zl3073x_dev *zldev, u8 index) -{ - return zldev->synth[index].enabled; + synth = zl3073x_synth_state_get(zldev, index); + return zl3073x_synth_freq_get(synth); } /** - * zl3073x_out_synth_get - get synth connected to given output + * zl3073x_dev_out_synth_get - get synth connected to given output * @zldev: pointer to zl3073x device * @index: output index * * Return: index of synth connected to given output. */ static inline u8 -zl3073x_out_synth_get(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_synth_get(struct zl3073x_dev *zldev, u8 index) { - return zldev->out[index].synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + + return zl3073x_out_synth_get(out); } /** - * zl3073x_out_is_enabled - check if the given output is enabled + * zl3073x_dev_out_is_enabled - check if the given output is enabled * @zldev: pointer to zl3073x device * @index: output index * * Return: true if the output is enabled, false otherwise */ static inline bool -zl3073x_out_is_enabled(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_is_enabled(struct zl3073x_dev *zldev, u8 index) { - u8 synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + const struct zl3073x_synth *synth; + u8 synth_id; /* Output is enabled only if associated synth is enabled */ - synth = zl3073x_out_synth_get(zldev, index); - if (zl3073x_synth_is_enabled(zldev, synth)) - return zldev->out[index].enabled; + synth_id = zl3073x_out_synth_get(out); + synth = zl3073x_synth_state_get(zldev, synth_id); - return false; + return zl3073x_synth_is_enabled(synth) && zl3073x_out_is_enabled(out); } /** - * zl3073x_out_signal_format_get - get output signal format - * @zldev: pointer to zl3073x device - * @index: output index - * - * Return: signal format of given output - */ -static inline u8 -zl3073x_out_signal_format_get(struct zl3073x_dev *zldev, u8 index) -{ - return zldev->out[index].signal_format; -} - -/** - * zl3073x_out_dpll_get - get DPLL ID the output is driven by + * zl3073x_dev_out_dpll_get - get DPLL ID the output is driven by * @zldev: pointer to zl3073x device * @index: output index * * Return: ID of DPLL the given output is driven by */ static inline -u8 zl3073x_out_dpll_get(struct zl3073x_dev *zldev, u8 index) +u8 zl3073x_dev_out_dpll_get(struct zl3073x_dev *zldev, u8 index) { - u8 synth; + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); + const struct zl3073x_synth *synth; + u8 synth_id; /* Get synthesizer connected to given output */ - synth = zl3073x_out_synth_get(zldev, index); + synth_id = zl3073x_out_synth_get(out); + synth = zl3073x_synth_state_get(zldev, synth_id); /* Return DPLL that drives the synth */ - return zl3073x_synth_dpll_get(zldev, synth); + return zl3073x_synth_dpll_get(synth); } /** - * zl3073x_out_is_diff - check if the given output is differential + * zl3073x_dev_out_is_diff - check if the given output is differential * @zldev: pointer to zl3073x device * @index: output index * * Return: true if output is differential, false if output is single-ended */ static inline bool -zl3073x_out_is_diff(struct zl3073x_dev *zldev, u8 index) +zl3073x_dev_out_is_diff(struct zl3073x_dev *zldev, u8 index) { - switch (zl3073x_out_signal_format_get(zldev, index)) { - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LVDS: - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DIFF: - case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LOWVCM: - return true; - default: - break; - } + const struct zl3073x_out *out = zl3073x_out_state_get(zldev, index); - return false; + return zl3073x_out_is_diff(out); } /** - * zl3073x_output_pin_is_enabled - check if the given output pin is enabled + * zl3073x_dev_output_pin_is_enabled - check if the given output pin is enabled * @zldev: pointer to zl3073x device * @id: output pin id * @@ -392,16 +327,21 @@ zl3073x_out_is_diff(struct zl3073x_dev *zldev, u8 index) * Return: true if output pin is enabled, false if output pin is disabled */ static inline bool -zl3073x_output_pin_is_enabled(struct zl3073x_dev *zldev, u8 id) +zl3073x_dev_output_pin_is_enabled(struct zl3073x_dev *zldev, u8 id) { - u8 output = zl3073x_output_pin_out_get(id); + u8 out_id = zl3073x_output_pin_out_get(id); + const struct zl3073x_out *out; + + out = zl3073x_out_state_get(zldev, out_id); - /* Check if the whole output is enabled */ - if (!zl3073x_out_is_enabled(zldev, output)) + /* Check if the output is enabled - call _dev_ helper that + * additionally checks for attached synth enablement. + */ + if (!zl3073x_dev_out_is_enabled(zldev, out_id)) return false; /* Check signal format */ - switch (zl3073x_out_signal_format_get(zldev, output)) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DISABLED: /* Both output pins are disabled by signal format */ return false; diff --git a/drivers/dpll/zl3073x/dpll.c b/drivers/dpll/zl3073x/dpll.c index f93f9a4583243..9879d85d29af0 100644 --- a/drivers/dpll/zl3073x/dpll.c +++ b/drivers/dpll/zl3073x/dpll.c @@ -35,6 +35,7 @@ * @prio: pin priority <0, 14> * @selectable: pin is selectable in automatic mode * @esync_control: embedded sync is controllable + * @phase_gran: phase adjustment granularity * @pin_state: last saved pin state * @phase_offset: last saved pin phase offset * @freq_offset: last saved fractional frequency offset @@ -49,6 +50,7 @@ struct zl3073x_dpll_pin { u8 prio; bool selectable; bool esync_control; + s32 phase_gran; enum dpll_pin_state pin_state; s64 phase_offset; s64 freq_offset; @@ -98,60 +100,6 @@ zl3073x_dpll_pin_direction_get(const struct dpll_pin *dpll_pin, void *pin_priv, return 0; } -/** - * zl3073x_dpll_input_ref_frequency_get - get input reference frequency - * @zldpll: pointer to zl3073x_dpll - * @ref_id: reference id - * @frequency: pointer to variable to store frequency - * - * Reads frequency of given input reference. - * - * Return: 0 on success, <0 on error - */ -static int -zl3073x_dpll_input_ref_frequency_get(struct zl3073x_dpll *zldpll, u8 ref_id, - u32 *frequency) -{ - struct zl3073x_dev *zldev = zldpll->dev; - u16 base, mult, num, denom; - int rc; - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref_id)); - if (rc) - return rc; - - /* Read registers to compute resulting frequency */ - rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_BASE, &base); - if (rc) - return rc; - rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_MULT, &mult); - if (rc) - return rc; - rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_M, &num); - if (rc) - return rc; - rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_N, &denom); - if (rc) - return rc; - - /* Sanity check that HW has not returned zero denominator */ - if (!denom) { - dev_err(zldev->dev, - "Zero divisor for ref %u frequency got from device\n", - ref_id); - return -EINVAL; - } - - /* Compute the frequency */ - *frequency = mul_u64_u32_div(base * mult, num, denom); - - return rc; -} - static int zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, void *pin_priv, @@ -163,39 +111,15 @@ zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 ref, ref_sync_ctrl, sync_mode; - u32 esync_div, ref_freq; - int rc; + const struct zl3073x_ref *ref; + u8 ref_id; - /* Get reference frequency */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, pin->id, &ref_freq); - if (rc) - return rc; - - guard(mutex)(&zldev->multiop_lock); + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); - /* Read reference configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; - - /* Get ref sync mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_SYNC_CTRL, &ref_sync_ctrl); - if (rc) - return rc; - - /* Get esync divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_REF_ESYNC_DIV, &esync_div); - if (rc) - return rc; - - sync_mode = FIELD_GET(ZL_REF_SYNC_CTRL_MODE, ref_sync_ctrl); - - switch (sync_mode) { + switch (FIELD_GET(ZL_REF_SYNC_CTRL_MODE, ref->sync_ctrl)) { case ZL_REF_SYNC_CTRL_MODE_50_50_ESYNC_25_75: - esync->freq = (esync_div == ZL_REF_ESYNC_DIV_1HZ) ? 1 : 0; + esync->freq = ref->esync_n_div == ZL_REF_ESYNC_DIV_1HZ ? 1 : 0; esync->pulse = 25; break; default: @@ -207,7 +131,7 @@ zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, /* If the pin supports esync control expose its range but only * if the current reference frequency is > 1 Hz. */ - if (pin->esync_control && ref_freq > 1) { + if (pin->esync_control && zl3073x_ref_freq_get(ref) > 1) { esync->range = esync_freq_ranges; esync->range_num = ARRAY_SIZE(esync_freq_ranges); } else { @@ -215,7 +139,7 @@ zl3073x_dpll_input_pin_esync_get(const struct dpll_pin *dpll_pin, esync->range_num = 0; } - return rc; + return 0; } static int @@ -228,22 +152,11 @@ zl3073x_dpll_input_pin_esync_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 ref, ref_sync_ctrl, sync_mode; - int rc; - - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration into mailbox */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; + struct zl3073x_ref ref; + u8 ref_id, sync_mode; - /* Get ref sync mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_SYNC_CTRL, &ref_sync_ctrl); - if (rc) - return rc; + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = *zl3073x_ref_state_get(zldev, ref_id); /* Use freq == 0 to disable esync */ if (!freq) @@ -251,25 +164,16 @@ zl3073x_dpll_input_pin_esync_set(const struct dpll_pin *dpll_pin, else sync_mode = ZL_REF_SYNC_CTRL_MODE_50_50_ESYNC_25_75; - ref_sync_ctrl &= ~ZL_REF_SYNC_CTRL_MODE; - ref_sync_ctrl |= FIELD_PREP(ZL_REF_SYNC_CTRL_MODE, sync_mode); - - /* Update ref sync control register */ - rc = zl3073x_write_u8(zldev, ZL_REG_REF_SYNC_CTRL, ref_sync_ctrl); - if (rc) - return rc; + ref.sync_ctrl &= ~ZL_REF_SYNC_CTRL_MODE; + ref.sync_ctrl |= FIELD_PREP(ZL_REF_SYNC_CTRL_MODE, sync_mode); if (freq) { - /* 1 Hz is only supported frequnecy currently */ - rc = zl3073x_write_u32(zldev, ZL_REG_REF_ESYNC_DIV, - ZL_REF_ESYNC_DIV_1HZ); - if (rc) - return rc; + /* 1 Hz is only supported frequency now */ + ref.esync_n_div = ZL_REF_ESYNC_DIV_1HZ; } - /* Commit reference configuration */ - return zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, - ZL_REG_REF_MB_MASK, BIT(ref)); + /* Update reference configuration */ + return zl3073x_ref_state_set(zldev, ref_id, &ref); } static int @@ -293,17 +197,12 @@ zl3073x_dpll_input_pin_frequency_get(const struct dpll_pin *dpll_pin, { struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dpll_pin *pin = pin_priv; - u32 ref_freq; - u8 ref; - int rc; + u8 ref_id; - /* Read and return ref frequency */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, ref, &ref_freq); - if (!rc) - *frequency = ref_freq; + ref_id = zl3073x_input_pin_ref_get(pin->id); + *frequency = zl3073x_dev_ref_freq_get(zldpll->dev, ref_id); - return rc; + return 0; } static int @@ -316,39 +215,18 @@ zl3073x_dpll_input_pin_frequency_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u16 base, mult; - u8 ref; - int rc; + struct zl3073x_ref ref; + u8 ref_id; - /* Get base frequency and multiplier for the requested frequency */ - rc = zl3073x_ref_freq_factorize(frequency, &base, &mult); - if (rc) - return rc; + /* Get reference state */ + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = *zl3073x_ref_state_get(zldev, ref_id); - guard(mutex)(&zldev->multiop_lock); - - /* Load reference configuration */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - - /* Update base frequency, multiplier, numerator & denominator */ - rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_BASE, base); - if (rc) - return rc; - rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_MULT, mult); - if (rc) - return rc; - rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_M, 1); - if (rc) - return rc; - rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_N, 1); - if (rc) - return rc; + /* Update frequency */ + zl3073x_ref_freq_set(&ref, frequency); - /* Commit reference configuration */ - return zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, - ZL_REG_REF_MB_MASK, BIT(ref)); + /* Commit reference state */ + return zl3073x_ref_state_set(zldev, ref_id, &ref); } /** @@ -495,19 +373,10 @@ zl3073x_dpll_connected_ref_get(struct zl3073x_dpll *zldpll, u8 *ref) if (rc) return rc; - if (ZL3073X_DPLL_REF_IS_VALID(*ref)) { - u8 ref_status; - - /* Read the reference monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(*ref), - &ref_status); - if (rc) - return rc; - - /* If the monitor indicates an error nothing is connected */ - if (ref_status != ZL_REF_MON_STATUS_OK) - *ref = ZL3073X_DPLL_REF_NONE; - } + /* If the monitor indicates an error nothing is connected */ + if (ZL3073X_DPLL_REF_IS_VALID(*ref) && + !zl3073x_dev_ref_is_status_ok(zldev, *ref)) + *ref = ZL3073X_DPLL_REF_NONE; return 0; } @@ -522,34 +391,25 @@ zl3073x_dpll_input_pin_phase_offset_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 conn_ref, ref, ref_status; + const struct zl3073x_ref *ref; + u8 conn_id, ref_id; s64 ref_phase; int rc; /* Get currently connected reference */ - rc = zl3073x_dpll_connected_ref_get(zldpll, &conn_ref); + rc = zl3073x_dpll_connected_ref_get(zldpll, &conn_id); if (rc) return rc; /* Report phase offset only for currently connected pin if the phase - * monitor feature is disabled. + * monitor feature is disabled and only if the input pin signal is + * present. */ - ref = zl3073x_input_pin_ref_get(pin->id); - if (!zldpll->phase_monitor && ref != conn_ref) { + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); + if ((!zldpll->phase_monitor && ref_id != conn_id) || + !zl3073x_ref_is_status_ok(ref)) { *phase_offset = 0; - - return 0; - } - - /* Get this pin monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), &ref_status); - if (rc) - return rc; - - /* Report phase offset only if the input pin signal is present */ - if (ref_status != ZL_REF_MON_STATUS_OK) { - *phase_offset = 0; - return 0; } @@ -559,20 +419,12 @@ zl3073x_dpll_input_pin_phase_offset_get(const struct dpll_pin *dpll_pin, * the phase offset is modded to the period of the signal * the dpll is locked to. */ - if (ZL3073X_DPLL_REF_IS_VALID(conn_ref) && conn_ref != ref) { + if (ZL3073X_DPLL_REF_IS_VALID(conn_id) && conn_id != ref_id) { u32 conn_freq, ref_freq; - /* Get frequency of connected ref */ - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, conn_ref, - &conn_freq); - if (rc) - return rc; - - /* Get frequency of given ref */ - rc = zl3073x_dpll_input_ref_frequency_get(zldpll, ref, - &ref_freq); - if (rc) - return rc; + /* Get frequency of connected and given ref */ + conn_freq = zl3073x_dev_ref_freq_get(zldev, conn_id); + ref_freq = zl3073x_ref_freq_get(ref); if (conn_freq > ref_freq) { s64 conn_period, div_factor; @@ -599,33 +451,23 @@ zl3073x_dpll_input_pin_phase_adjust_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; + const struct zl3073x_ref *ref; s64 phase_comp; - u8 ref; - int rc; - - guard(mutex)(&zldev->multiop_lock); + u8 ref_id; /* Read reference configuration */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; - - /* Read current phase offset compensation */ - rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, &phase_comp); - if (rc) - return rc; + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); /* Perform sign extension for 48bit signed value */ - phase_comp = sign_extend64(phase_comp, 47); + phase_comp = sign_extend64(ref->phase_comp, 47); /* Reverse two's complement negation applied during set and convert * to 32bit signed int */ *phase_adjust = (s32)-phase_comp; - return rc; + return 0; } static int @@ -639,32 +481,20 @@ zl3073x_dpll_input_pin_phase_adjust_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - s64 phase_comp; - u8 ref; - int rc; + struct zl3073x_ref ref; + u8 ref_id; + + /* Read reference configuration */ + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = *zl3073x_ref_state_get(zldev, ref_id); /* The value in the register is stored as two's complement negation * of requested value. */ - phase_comp = -phase_adjust; + ref.phase_comp = -phase_adjust; - guard(mutex)(&zldev->multiop_lock); - - /* Read reference configuration */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, - ZL_REG_REF_MB_MASK, BIT(ref)); - if (rc) - return rc; - - /* Write the requested value into the compensation register */ - rc = zl3073x_write_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, phase_comp); - if (rc) - return rc; - - /* Commit reference configuration */ - return zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, - ZL_REG_REF_MB_MASK, BIT(ref)); + /* Update reference configuration */ + return zl3073x_ref_state_set(zldev, ref_id, &ref); } /** @@ -775,7 +605,7 @@ zl3073x_dpll_ref_state_get(struct zl3073x_dpll_pin *pin, { struct zl3073x_dpll *zldpll = pin->dpll; struct zl3073x_dev *zldev = zldpll->dev; - u8 ref, ref_conn, status; + u8 ref, ref_conn; int rc; ref = zl3073x_input_pin_ref_get(pin->id); @@ -795,20 +625,9 @@ zl3073x_dpll_ref_state_get(struct zl3073x_dpll_pin *pin, * pin as selectable. */ if (zldpll->refsel_mode == ZL_DPLL_MODE_REFSEL_MODE_AUTO && - pin->selectable) { - /* Read reference monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), - &status); - if (rc) - return rc; - - /* If the monitor indicates errors report the reference - * as disconnected - */ - if (status == ZL_REF_MON_STATUS_OK) { - *state = DPLL_PIN_STATE_SELECTABLE; - return 0; - } + zl3073x_dev_ref_is_status_ok(zldev, ref) && pin->selectable) { + *state = DPLL_PIN_STATE_SELECTABLE; + return 0; } /* Otherwise report the pin as disconnected */ @@ -951,21 +770,19 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u32 esync_period, esync_width; - u8 clock_type, synth; - u8 out, output_mode; - u32 output_div; + const struct zl3073x_synth *synth; + const struct zl3073x_out *out; + u8 clock_type, out_id; u32 synth_freq; - int rc; - out = zl3073x_output_pin_out_get(pin->id); + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); /* If N-division is enabled, esync is not supported. The register used * for N-division is also used for the esync divider so both cannot * be used. */ - switch (zl3073x_out_signal_format_get(zldev, out)) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: return -EOPNOTSUPP; @@ -973,38 +790,11 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, break; } - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read output mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - - /* Read output divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!output_div) { - dev_err(dev, "Zero divisor for OUTPUT%u got from device\n", - out); - return -EINVAL; - } - - /* Get synth attached to output pin */ - synth = zl3073x_out_synth_get(zldev, out); + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(out)); + synth_freq = zl3073x_synth_freq_get(synth); - /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - clock_type = FIELD_GET(ZL_OUTPUT_MODE_CLOCK_TYPE, output_mode); + clock_type = FIELD_GET(ZL_OUTPUT_MODE_CLOCK_TYPE, out->mode); if (clock_type != ZL_OUTPUT_MODE_CLOCK_TYPE_ESYNC) { /* No need to read esync data if it is not enabled */ esync->freq = 0; @@ -1013,38 +803,21 @@ zl3073x_dpll_output_pin_esync_get(const struct dpll_pin *dpll_pin, goto finish; } - /* Read esync period */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, &esync_period); - if (rc) - return rc; - - /* Check esync divisor for zero */ - if (!esync_period) { - dev_err(dev, "Zero esync divisor for OUTPUT%u got from device\n", - out); - return -EINVAL; - } - - /* Get esync pulse width in units of half synth cycles */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, &esync_width); - if (rc) - return rc; - /* Compute esync frequency */ - esync->freq = synth_freq / output_div / esync_period; + esync->freq = synth_freq / out->div / out->esync_n_period; /* By comparing the esync_pulse_width to the half of the pulse width * the esync pulse percentage can be determined. * Note that half pulse width is in units of half synth cycles, which * is why it reduces down to be output_div. */ - esync->pulse = (50 * esync_width) / output_div; + esync->pulse = (50 * out->esync_n_width) / out->div; finish: /* Set supported esync ranges if the pin supports esync control and * if the output frequency is > 1 Hz. */ - if (pin->esync_control && (synth_freq / output_div) > 1) { + if (pin->esync_control && (synth_freq / out->div) > 1) { esync->range = esync_freq_ranges; esync->range_num = ARRAY_SIZE(esync_freq_ranges); } else { @@ -1062,21 +835,22 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, void *dpll_priv, u64 freq, struct netlink_ext_ack *extack) { - u32 esync_period, esync_width, output_div; struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u8 clock_type, out, output_mode, synth; + const struct zl3073x_synth *synth; + struct zl3073x_out out; + u8 clock_type, out_id; u32 synth_freq; - int rc; - out = zl3073x_output_pin_out_get(pin->id); + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); /* If N-division is enabled, esync is not supported. The register used * for N-division is also used for the esync divider so both cannot * be used. */ - switch (zl3073x_out_signal_format_get(zldev, out)) { + switch (zl3073x_out_signal_format_get(&out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: return -EOPNOTSUPP; @@ -1084,19 +858,6 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, break; } - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read output mode */ - rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &output_mode); - if (rc) - return rc; - /* Select clock type */ if (freq) clock_type = ZL_OUTPUT_MODE_CLOCK_TYPE_ESYNC; @@ -1104,38 +865,19 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, clock_type = ZL_OUTPUT_MODE_CLOCK_TYPE_NORMAL; /* Update clock type in output mode */ - output_mode &= ~ZL_OUTPUT_MODE_CLOCK_TYPE; - output_mode |= FIELD_PREP(ZL_OUTPUT_MODE_CLOCK_TYPE, clock_type); - rc = zl3073x_write_u8(zldev, ZL_REG_OUTPUT_MODE, output_mode); - if (rc) - return rc; + out.mode &= ~ZL_OUTPUT_MODE_CLOCK_TYPE; + out.mode |= FIELD_PREP(ZL_OUTPUT_MODE_CLOCK_TYPE, clock_type); /* If esync is being disabled just write mailbox and finish */ if (!freq) goto write_mailbox; - /* Get synth attached to output pin */ - synth = zl3073x_out_synth_get(zldev, out); - - /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!output_div) { - dev_err(zldev->dev, - "Zero divisor for OUTPUT%u got from device\n", out); - return -EINVAL; - } + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(&out)); + synth_freq = zl3073x_synth_freq_get(synth); /* Compute and update esync period */ - esync_period = synth_freq / (u32)freq / output_div; - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, esync_period); - if (rc) - return rc; + out.esync_n_period = synth_freq / (u32)freq / out.div; /* Half of the period in units of 1/2 synth cycle can be represented by * the output_div. To get the supported esync pulse width of 25% of the @@ -1143,15 +885,11 @@ zl3073x_dpll_output_pin_esync_set(const struct dpll_pin *dpll_pin, * assumes that output_div is even, otherwise some resolution will be * lost. */ - esync_width = output_div / 2; - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, esync_width); - if (rc) - return rc; + out.esync_n_width = out.div / 2; write_mailbox: /* Commit output configuration */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1164,83 +902,46 @@ zl3073x_dpll_output_pin_frequency_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u8 out, signal_format, synth; - u32 output_div, synth_freq; - int rc; - - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration into mailbox */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &output_div); - if (rc) - return rc; + const struct zl3073x_synth *synth; + const struct zl3073x_out *out; + u32 synth_freq; + u8 out_id; - /* Check output divisor for zero */ - if (!output_div) { - dev_err(dev, "Zero divisor for output %u got from device\n", - out); - return -EINVAL; - } + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); - /* Read used signal format for the given output */ - signal_format = zl3073x_out_signal_format_get(zldev, out); + /* Get attached synth frequency */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(out)); + synth_freq = zl3073x_synth_freq_get(synth); - switch (signal_format) { + switch (zl3073x_out_signal_format_get(out)) { case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV: case ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV_INV: /* In case of divided format we have to distiguish between * given output pin type. + * + * For P-pin the resulting frequency is computed as simple + * division of synth frequency and output divisor. + * + * For N-pin we have to divide additionally by divisor stored + * in esync_n_period output mailbox register that is used as + * N-pin divisor for these modes. */ - if (zl3073x_dpll_is_p_pin(pin)) { - /* For P-pin the resulting frequency is computed as - * simple division of synth frequency and output - * divisor. - */ - *frequency = synth_freq / output_div; - } else { - /* For N-pin we have to divide additionally by - * divisor stored in esync_period output mailbox - * register that is used as N-pin divisor for these - * modes. - */ - u32 ndiv; - - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, - &ndiv); - if (rc) - return rc; + *frequency = synth_freq / out->div; - /* Check N-pin divisor for zero */ - if (!ndiv) { - dev_err(dev, - "Zero N-pin divisor for output %u got from device\n", - out); - return -EINVAL; - } + if (!zl3073x_dpll_is_p_pin(pin)) + *frequency = (u32)*frequency / out->esync_n_period; - /* Compute final divisor for N-pin */ - *frequency = synth_freq / output_div / ndiv; - } break; default: /* In other modes the resulting frequency is computed as * division of synth frequency and output divisor. */ - *frequency = synth_freq / output_div; + *frequency = synth_freq / out->div; break; } - return rc; + return 0; } static int @@ -1253,28 +954,21 @@ zl3073x_dpll_output_pin_frequency_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - struct device *dev = zldev->dev; - u32 output_n_freq, output_p_freq; - u8 out, signal_format, synth; - u32 cur_div, new_div, ndiv; - u32 synth_freq; - int rc; + const struct zl3073x_synth *synth; + u8 out_id, signal_format; + u32 new_div, synth_freq; + struct zl3073x_out out; + + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); + /* Get attached synth frequency and compute new divisor */ + synth = zl3073x_synth_state_get(zldev, zl3073x_out_synth_get(&out)); + synth_freq = zl3073x_synth_freq_get(synth); new_div = synth_freq / (u32)frequency; /* Get used signal format for the given output */ - signal_format = zl3073x_out_signal_format_get(zldev, out); - - guard(mutex)(&zldev->multiop_lock); - - /* Load output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; + signal_format = zl3073x_out_signal_format_get(&out); /* Check signal format */ if (signal_format != ZL_OUTPUT_MODE_SIGNAL_FORMAT_2_NDIV && @@ -1282,99 +976,50 @@ zl3073x_dpll_output_pin_frequency_set(const struct dpll_pin *dpll_pin, /* For non N-divided signal formats the frequency is computed * as division of synth frequency and output divisor. */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, new_div); - if (rc) - return rc; + out.div = new_div; /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, new_div); - if (rc) - return rc; + out.width = new_div; /* Commit output configuration */ - return zl3073x_mb_op(zldev, - ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - } - - /* For N-divided signal format get current divisor */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &cur_div); - if (rc) - return rc; - - /* Check output divisor for zero */ - if (!cur_div) { - dev_err(dev, "Zero divisor for output %u got from device\n", - out); - return -EINVAL; - } - - /* Get N-pin divisor (shares the same register with esync */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, &ndiv); - if (rc) - return rc; - - /* Check N-pin divisor for zero */ - if (!ndiv) { - dev_err(dev, - "Zero N-pin divisor for output %u got from device\n", - out); - return -EINVAL; + return zl3073x_out_state_set(zldev, out_id, &out); } - /* Compute current output frequency for P-pin */ - output_p_freq = synth_freq / cur_div; - - /* Compute current N-pin frequency */ - output_n_freq = output_p_freq / ndiv; - if (zl3073x_dpll_is_p_pin(pin)) { /* We are going to change output frequency for P-pin but * if the requested frequency is less than current N-pin * frequency then indicate a failure as we are not able * to compute N-pin divisor to keep its frequency unchanged. + * + * Update divisor for N-pin to keep N-pin frequency. */ - if (frequency <= output_n_freq) + out.esync_n_period = (out.esync_n_period * out.div) / new_div; + if (!out.esync_n_period) return -EINVAL; /* Update the output divisor */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, new_div); - if (rc) - return rc; + out.div = new_div; /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, new_div); - if (rc) - return rc; - - /* Compute new divisor for N-pin */ - ndiv = (u32)frequency / output_n_freq; + out.width = out.div; } else { /* We are going to change frequency of N-pin but if * the requested freq is greater or equal than freq of P-pin * in the output pair we cannot compute divisor for the N-pin. * In this case indicate a failure. + * + * Update divisor for N-pin */ - if (output_p_freq <= frequency) + out.esync_n_period = div64_u64(synth_freq, frequency * out.div); + if (!out.esync_n_period) return -EINVAL; - - /* Compute new divisor for N-pin */ - ndiv = output_p_freq / (u32)frequency; } - /* Update divisor for the N-pin */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, ndiv); - if (rc) - return rc; - /* For 50/50 duty cycle the divisor is equal to width */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, ndiv); - if (rc) - return rc; + out.esync_n_width = out.esync_n_period; /* Commit output configuration */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1388,42 +1033,18 @@ zl3073x_dpll_output_pin_phase_adjust_get(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - u32 synth_freq; - s32 phase_comp; - u8 out, synth; - int rc; - - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); - synth_freq = zl3073x_synth_freq_get(zldev, synth); + const struct zl3073x_out *out; + u8 out_id; - /* Check synth freq for zero */ - if (!synth_freq) { - dev_err(zldev->dev, "Got zero synth frequency for output %u\n", - out); - return -EINVAL; - } + out_id = zl3073x_output_pin_out_get(pin->id); + out = zl3073x_out_state_get(zldev, out_id); - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Read current output phase compensation */ - rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, &phase_comp); - if (rc) - return rc; - - /* Value in register is expressed in half synth clock cycles */ - phase_comp *= (int)div_u64(PSEC_PER_SEC, 2 * synth_freq); - - /* Reverse two's complement negation applied during 'set' */ - *phase_adjust = -phase_comp; + /* Convert value to ps and reverse two's complement negation applied + * during 'set' + */ + *phase_adjust = -out->phase_comp * pin->phase_gran; - return rc; + return 0; } static int @@ -1437,52 +1058,19 @@ zl3073x_dpll_output_pin_phase_adjust_set(const struct dpll_pin *dpll_pin, struct zl3073x_dpll *zldpll = dpll_priv; struct zl3073x_dev *zldev = zldpll->dev; struct zl3073x_dpll_pin *pin = pin_priv; - int half_synth_cycle; - u32 synth_freq; - u8 out, synth; - int rc; - - /* Get attached synth */ - out = zl3073x_output_pin_out_get(pin->id); - synth = zl3073x_out_synth_get(zldev, out); + struct zl3073x_out out; + u8 out_id; - /* Get synth's frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); - - /* Value in register is expressed in half synth clock cycles so - * the given phase adjustment a multiple of half synth clock. - */ - half_synth_cycle = (int)div_u64(PSEC_PER_SEC, 2 * synth_freq); - - if ((phase_adjust % half_synth_cycle) != 0) { - NL_SET_ERR_MSG_FMT(extack, - "Phase adjustment value has to be multiple of %d", - half_synth_cycle); - return -EINVAL; - } - phase_adjust /= half_synth_cycle; + out_id = zl3073x_output_pin_out_get(pin->id); + out = *zl3073x_out_state_get(zldev, out_id); /* The value in the register is stored as two's complement negation - * of requested value. + * of requested value and expressed in half synth clock cycles. */ - phase_adjust = -phase_adjust; - - guard(mutex)(&zldev->multiop_lock); - - /* Read output configuration */ - rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); - if (rc) - return rc; - - /* Write the requested value into the compensation register */ - rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, phase_adjust); - if (rc) - return rc; + out.phase_comp = -phase_adjust / pin->phase_gran; /* Update output configuration from mailbox */ - return zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, - ZL_REG_OUTPUT_MB_MASK, BIT(out)); + return zl3073x_out_state_set(zldev, out_id, &out); } static int @@ -1758,9 +1346,10 @@ zl3073x_dpll_pin_register(struct zl3073x_dpll_pin *pin, u32 index) if (IS_ERR(props)) return PTR_ERR(props); - /* Save package label & esync capability */ + /* Save package label, esync capability and phase adjust granularity */ strscpy(pin->label, props->package_label); pin->esync_control = props->esync_control; + pin->phase_gran = props->dpll_props.phase_gran; if (zl3073x_dpll_is_input_pin(pin)) { rc = zl3073x_dpll_ref_prio_get(pin, &pin->prio); @@ -1878,33 +1467,32 @@ zl3073x_dpll_pin_is_registrable(struct zl3073x_dpll *zldpll, const char *name; if (dir == DPLL_PIN_DIRECTION_INPUT) { - u8 ref = zl3073x_input_pin_ref_get(index); - - name = "REF"; + u8 ref_id = zl3073x_input_pin_ref_get(index); + const struct zl3073x_ref *ref; /* Skip the pin if the DPLL is running in NCO mode */ if (zldpll->refsel_mode == ZL_DPLL_MODE_REFSEL_MODE_NCO) return false; - is_diff = zl3073x_ref_is_diff(zldev, ref); - is_enabled = zl3073x_ref_is_enabled(zldev, ref); + name = "REF"; + ref = zl3073x_ref_state_get(zldev, ref_id); + is_diff = zl3073x_ref_is_diff(ref); + is_enabled = zl3073x_ref_is_enabled(ref); } else { /* Output P&N pair shares single HW output */ u8 out = zl3073x_output_pin_out_get(index); - name = "OUT"; - /* Skip the pin if it is connected to different DPLL channel */ - if (zl3073x_out_dpll_get(zldev, out) != zldpll->id) { + if (zl3073x_dev_out_dpll_get(zldev, out) != zldpll->id) { dev_dbg(zldev->dev, - "%s%u is driven by different DPLL\n", name, - out); + "OUT%u is driven by different DPLL\n", out); return false; } - is_diff = zl3073x_out_is_diff(zldev, out); - is_enabled = zl3073x_output_pin_is_enabled(zldev, index); + name = "OUT"; + is_diff = zl3073x_dev_out_is_diff(zldev, out); + is_enabled = zl3073x_dev_output_pin_is_enabled(zldev, index); } /* Skip N-pin if the corresponding input/output is differential */ @@ -2061,42 +1649,26 @@ zl3073x_dpll_pin_phase_offset_check(struct zl3073x_dpll_pin *pin) struct zl3073x_dev *zldev = zldpll->dev; unsigned int reg; s64 phase_offset; - u8 ref; + u8 ref_id; int rc; - ref = zl3073x_input_pin_ref_get(pin->id); + /* No phase offset if the ref monitor reports signal errors */ + ref_id = zl3073x_input_pin_ref_get(pin->id); + if (!zl3073x_dev_ref_is_status_ok(zldev, ref_id)) + return false; /* Select register to read phase offset value depending on pin and * phase monitor state: * 1) For connected pin use dpll_phase_err_data register * 2) For other pins use appropriate ref_phase register if the phase - * monitor feature is enabled and reference monitor does not - * report signal errors for given input pin + * monitor feature is enabled. */ - if (pin->pin_state == DPLL_PIN_STATE_CONNECTED) { + if (pin->pin_state == DPLL_PIN_STATE_CONNECTED) reg = ZL_REG_DPLL_PHASE_ERR_DATA(zldpll->id); - } else if (zldpll->phase_monitor) { - u8 status; - - /* Get reference monitor status */ - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), - &status); - if (rc) { - dev_err(zldev->dev, - "Failed to read %s refmon status: %pe\n", - pin->label, ERR_PTR(rc)); - - return false; - } - - if (status != ZL_REF_MON_STATUS_OK) - return false; - - reg = ZL_REG_REF_PHASE(ref); - } else { - /* The pin is not connected or phase monitor disabled */ + else if (zldpll->phase_monitor) + reg = ZL_REG_REF_PHASE(ref_id); + else return false; - } /* Read measured phase offset value */ rc = zl3073x_read_u48(zldev, reg, &phase_offset); @@ -2135,32 +1707,22 @@ zl3073x_dpll_pin_ffo_check(struct zl3073x_dpll_pin *pin) { struct zl3073x_dpll *zldpll = pin->dpll; struct zl3073x_dev *zldev = zldpll->dev; - u8 ref, status; - s64 ffo; - int rc; + const struct zl3073x_ref *ref; + u8 ref_id; /* Get reference monitor status */ - ref = zl3073x_input_pin_ref_get(pin->id); - rc = zl3073x_read_u8(zldev, ZL_REG_REF_MON_STATUS(ref), &status); - if (rc) { - dev_err(zldev->dev, "Failed to read %s refmon status: %pe\n", - pin->label, ERR_PTR(rc)); - - return false; - } + ref_id = zl3073x_input_pin_ref_get(pin->id); + ref = zl3073x_ref_state_get(zldev, ref_id); /* Do not report ffo changes if the reference monitor report errors */ - if (status != ZL_REF_MON_STATUS_OK) + if (!zl3073x_ref_is_status_ok(ref)) return false; - /* Get the latest measured ref's ffo */ - ffo = zl3073x_ref_ffo_get(zldev, ref); - /* Compare with previous value */ - if (pin->freq_offset != ffo) { + if (pin->freq_offset != ref->ffo) { dev_dbg(zldev->dev, "%s freq offset changed: %lld -> %lld\n", - pin->label, pin->freq_offset, ffo); - pin->freq_offset = ffo; + pin->label, pin->freq_offset, ref->ffo); + pin->freq_offset = ref->ffo; return true; } diff --git a/drivers/dpll/zl3073x/fw.c b/drivers/dpll/zl3073x/fw.c index def37fe8d9b03..55b638247f4bb 100644 --- a/drivers/dpll/zl3073x/fw.c +++ b/drivers/dpll/zl3073x/fw.c @@ -352,12 +352,12 @@ struct zl3073x_fw *zl3073x_fw_load(struct zl3073x_dev *zldev, const char *data, } /** - * zl3073x_flash_bundle_flash - Flash all components + * zl3073x_fw_component_flash - Flash all components * @zldev: zl3073x device structure - * @components: pointer to components array + * @comp: pointer to components array * @extack: netlink extack pointer to report errors * - * Returns 0 in case of success or negative number otherwise. + * Return: 0 in case of success or negative number otherwise. */ static int zl3073x_fw_component_flash(struct zl3073x_dev *zldev, diff --git a/drivers/dpll/zl3073x/out.c b/drivers/dpll/zl3073x/out.c new file mode 100644 index 0000000000000..86829a0c1c022 --- /dev/null +++ b/drivers/dpll/zl3073x/out.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include + +#include "core.h" +#include "out.h" + +/** + * zl3073x_out_state_fetch - fetch output state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: output index to fetch state for + * + * Function fetches state of the given output from hardware and stores it + * for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_out *out = &zldev->out[index]; + int rc; + + /* Read output configuration */ + rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_CTRL(index), &out->ctrl); + if (rc) + return rc; + + dev_dbg(zldev->dev, "OUT%u is %s and connected to SYNTH%u\n", index, + str_enabled_disabled(zl3073x_out_is_enabled(out)), + zl3073x_out_synth_get(out)); + + guard(mutex)(&zldev->multiop_lock); + + /* Read output configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Read output mode */ + rc = zl3073x_read_u8(zldev, ZL_REG_OUTPUT_MODE, &out->mode); + if (rc) + return rc; + + dev_dbg(zldev->dev, "OUT%u has signal format 0x%02x\n", index, + zl3073x_out_signal_format_get(out)); + + /* Read output divisor */ + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_DIV, &out->div); + if (rc) + return rc; + + if (!out->div) { + dev_err(zldev->dev, "Zero divisor for OUT%u got from device\n", + index); + return -EINVAL; + } + + dev_dbg(zldev->dev, "OUT%u divisor: %u\n", index, out->div); + + /* Read output width */ + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_WIDTH, &out->width); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, + &out->esync_n_period); + if (rc) + return rc; + + if (!out->esync_n_period) { + dev_err(zldev->dev, + "Zero esync divisor for OUT%u got from device\n", + index); + return -EINVAL; + } + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, + &out->esync_n_width); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, + &out->phase_comp); + if (rc) + return rc; + + return rc; +} + +/** + * zl3073x_out_state_get - get current output state + * @zldev: pointer to zl3073x_dev structure + * @index: output index to get state for + * + * Return: pointer to given output state + */ +const struct zl3073x_out *zl3073x_out_state_get(struct zl3073x_dev *zldev, + u8 index) +{ + return &zldev->out[index]; +} + +int zl3073x_out_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_out *out) +{ + struct zl3073x_out *dout = &zldev->out[index]; + int rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read output configuration into mailbox */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_RD, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Update mailbox with changed values */ + if (dout->div != out->div) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_DIV, out->div); + if (!rc && dout->width != out->width) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_WIDTH, out->width); + if (!rc && dout->esync_n_period != out->esync_n_period) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_PERIOD, + out->esync_n_period); + if (!rc && dout->esync_n_width != out->esync_n_width) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_ESYNC_WIDTH, + out->esync_n_width); + if (!rc && dout->mode != out->mode) + rc = zl3073x_write_u8(zldev, ZL_REG_OUTPUT_MODE, out->mode); + if (!rc && dout->phase_comp != out->phase_comp) + rc = zl3073x_write_u32(zldev, ZL_REG_OUTPUT_PHASE_COMP, + out->phase_comp); + if (rc) + return rc; + + /* Commit output configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_OUTPUT_MB_SEM, ZL_OUTPUT_MB_SEM_WR, + ZL_REG_OUTPUT_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* After successful commit store new state */ + dout->div = out->div; + dout->width = out->width; + dout->esync_n_period = out->esync_n_period; + dout->esync_n_width = out->esync_n_width; + dout->mode = out->mode; + dout->phase_comp = out->phase_comp; + + return 0; +} diff --git a/drivers/dpll/zl3073x/out.h b/drivers/dpll/zl3073x/out.h new file mode 100644 index 0000000000000..e8ea7a0e0f071 --- /dev/null +++ b/drivers/dpll/zl3073x/out.h @@ -0,0 +1,93 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_OUT_H +#define _ZL3073X_OUT_H + +#include +#include + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_out - output state + * @div: output divisor + * @width: output pulse width + * @esync_n_period: embedded sync or n-pin period (for n-div formats) + * @esync_n_width: embedded sync or n-pin pulse width + * @phase_comp: phase compensation + * @ctrl: output control + * @mode: output mode + */ +struct zl3073x_out { + u32 div; + u32 width; + u32 esync_n_period; + u32 esync_n_width; + s32 phase_comp; + u8 ctrl; + u8 mode; +}; + +int zl3073x_out_state_fetch(struct zl3073x_dev *zldev, u8 index); +const struct zl3073x_out *zl3073x_out_state_get(struct zl3073x_dev *zldev, + u8 index); + +int zl3073x_out_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_out *out); + +/** + * zl3073x_out_signal_format_get - get output signal format + * @out: pointer to out state + * + * Return: signal format of given output + */ +static inline u8 zl3073x_out_signal_format_get(const struct zl3073x_out *out) +{ + return FIELD_GET(ZL_OUTPUT_MODE_SIGNAL_FORMAT, out->mode); +} + +/** + * zl3073x_out_is_diff - check if the given output is differential + * @out: pointer to out state + * + * Return: true if output is differential, false if output is single-ended + */ +static inline bool zl3073x_out_is_diff(const struct zl3073x_out *out) +{ + switch (zl3073x_out_signal_format_get(out)) { + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LVDS: + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_DIFF: + case ZL_OUTPUT_MODE_SIGNAL_FORMAT_LOWVCM: + return true; + default: + break; + } + + return false; +} + +/** + * zl3073x_out_is_enabled - check if the given output is enabled + * @out: pointer to out state + * + * Return: true if output is enabled, false if output is disabled + */ +static inline bool zl3073x_out_is_enabled(const struct zl3073x_out *out) +{ + return !!FIELD_GET(ZL_OUTPUT_CTRL_EN, out->ctrl); +} + +/** + * zl3073x_out_synth_get - get synth connected to given output + * @out: pointer to out state + * + * Return: index of synth connected to given output. + */ +static inline u8 zl3073x_out_synth_get(const struct zl3073x_out *out) +{ + return FIELD_GET(ZL_OUTPUT_CTRL_SYNTH_SEL, out->ctrl); +} + +#endif /* _ZL3073X_OUT_H */ diff --git a/drivers/dpll/zl3073x/prop.c b/drivers/dpll/zl3073x/prop.c index 4cf7e8aefcb37..4ed153087570b 100644 --- a/drivers/dpll/zl3073x/prop.c +++ b/drivers/dpll/zl3073x/prop.c @@ -46,10 +46,10 @@ zl3073x_pin_check_freq(struct zl3073x_dev *zldev, enum dpll_pin_direction dir, /* Get output pin synthesizer */ out = zl3073x_output_pin_out_get(id); - synth = zl3073x_out_synth_get(zldev, out); + synth = zl3073x_dev_out_synth_get(zldev, out); /* Get synth frequency */ - synth_freq = zl3073x_synth_freq_get(zldev, synth); + synth_freq = zl3073x_dev_synth_freq_get(zldev, synth); /* Check the frequency divides synth frequency */ if (synth_freq % (u32)freq) @@ -93,13 +93,13 @@ zl3073x_prop_pin_package_label_set(struct zl3073x_dev *zldev, prefix = "REF"; ref = zl3073x_input_pin_ref_get(id); - is_diff = zl3073x_ref_is_diff(zldev, ref); + is_diff = zl3073x_dev_ref_is_diff(zldev, ref); } else { u8 out; prefix = "OUT"; out = zl3073x_output_pin_out_get(id); - is_diff = zl3073x_out_is_diff(zldev, out); + is_diff = zl3073x_dev_out_is_diff(zldev, out); } if (!is_diff) @@ -208,7 +208,18 @@ struct zl3073x_pin_props *zl3073x_pin_props_get(struct zl3073x_dev *zldev, DPLL_PIN_CAPABILITIES_PRIORITY_CAN_CHANGE | DPLL_PIN_CAPABILITIES_STATE_CAN_CHANGE; } else { + u8 out, synth; + u32 f; + props->dpll_props.type = DPLL_PIN_TYPE_GNSS; + + /* The output pin phase adjustment granularity equals half of + * the synth frequency count. + */ + out = zl3073x_output_pin_out_get(index); + synth = zl3073x_dev_out_synth_get(zldev, out); + f = 2 * zl3073x_dev_synth_freq_get(zldev, synth); + props->dpll_props.phase_gran = f ? div_u64(PSEC_PER_SEC, f) : 1; } props->dpll_props.phase_range.min = S32_MIN; diff --git a/drivers/dpll/zl3073x/ref.c b/drivers/dpll/zl3073x/ref.c new file mode 100644 index 0000000000000..aa2de13effa87 --- /dev/null +++ b/drivers/dpll/zl3073x/ref.c @@ -0,0 +1,204 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include + +#include "core.h" +#include "ref.h" + +/** + * zl3073x_ref_freq_factorize - factorize given frequency + * @freq: input frequency + * @base: base frequency + * @mult: multiplier + * + * Checks if the given frequency can be factorized using one of the + * supported base frequencies. If so the base frequency and multiplier + * are stored into appropriate parameters if they are not NULL. + * + * Return: 0 on success, -EINVAL if the frequency cannot be factorized + */ +int +zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult) +{ + static const u16 base_freqs[] = { + 1, 2, 4, 5, 8, 10, 16, 20, 25, 32, 40, 50, 64, 80, 100, 125, + 128, 160, 200, 250, 256, 320, 400, 500, 625, 640, 800, 1000, + 1250, 1280, 1600, 2000, 2500, 3125, 3200, 4000, 5000, 6250, + 6400, 8000, 10000, 12500, 15625, 16000, 20000, 25000, 31250, + 32000, 40000, 50000, 62500, + }; + u32 div; + int i; + + for (i = 0; i < ARRAY_SIZE(base_freqs); i++) { + div = freq / base_freqs[i]; + + if (div <= U16_MAX && (freq % base_freqs[i]) == 0) { + if (base) + *base = base_freqs[i]; + if (mult) + *mult = div; + + return 0; + } + } + + return -EINVAL; +} + +/** + * zl3073x_ref_state_fetch - fetch input reference state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: input reference index to fetch state for + * + * Function fetches state for the given input reference from hardware and + * stores it for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_ref *ref = &zldev->ref[index]; + int rc; + + /* For differential type inputs the N-pin reference shares + * part of the configuration with the P-pin counterpart. + */ + if (zl3073x_is_n_pin(index) && zl3073x_ref_is_diff(ref - 1)) { + struct zl3073x_ref *p_ref = ref - 1; /* P-pin counterpart*/ + + /* Copy the shared items from the P-pin */ + ref->config = p_ref->config; + ref->esync_n_div = p_ref->esync_n_div; + ref->freq_base = p_ref->freq_base; + ref->freq_mult = p_ref->freq_mult; + ref->freq_ratio_m = p_ref->freq_ratio_m; + ref->freq_ratio_n = p_ref->freq_ratio_n; + ref->phase_comp = p_ref->phase_comp; + ref->sync_ctrl = p_ref->sync_ctrl; + + return 0; /* Finish - no non-shared items for now */ + } + + guard(mutex)(&zldev->multiop_lock); + + /* Read reference configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Read ref_config register */ + rc = zl3073x_read_u8(zldev, ZL_REG_REF_CONFIG, &ref->config); + if (rc) + return rc; + + /* Read frequency related registers */ + rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_BASE, &ref->freq_base); + if (rc) + return rc; + rc = zl3073x_read_u16(zldev, ZL_REG_REF_FREQ_MULT, &ref->freq_mult); + if (rc) + return rc; + rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_M, &ref->freq_ratio_m); + if (rc) + return rc; + rc = zl3073x_read_u16(zldev, ZL_REG_REF_RATIO_N, &ref->freq_ratio_n); + if (rc) + return rc; + + /* Read eSync and N-div rated registers */ + rc = zl3073x_read_u32(zldev, ZL_REG_REF_ESYNC_DIV, &ref->esync_n_div); + if (rc) + return rc; + rc = zl3073x_read_u8(zldev, ZL_REG_REF_SYNC_CTRL, &ref->sync_ctrl); + if (rc) + return rc; + + /* Read phase compensation register */ + rc = zl3073x_read_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, + &ref->phase_comp); + if (rc) + return rc; + + dev_dbg(zldev->dev, "REF%u is %s and configured as %s\n", index, + str_enabled_disabled(zl3073x_ref_is_enabled(ref)), + zl3073x_ref_is_diff(ref) ? "differential" : "single-ended"); + + return rc; +} + +/** + * zl3073x_ref_state_get - get current input reference state + * @zldev: pointer to zl3073x_dev structure + * @index: input reference index to get state for + * + * Return: pointer to given input reference state + */ +const struct zl3073x_ref * +zl3073x_ref_state_get(struct zl3073x_dev *zldev, u8 index) +{ + return &zldev->ref[index]; +} + +int zl3073x_ref_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_ref *ref) +{ + struct zl3073x_ref *dref = &zldev->ref[index]; + int rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read reference configuration into mailbox */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_RD, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* Update mailbox with changed values */ + if (dref->freq_base != ref->freq_base) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_BASE, + ref->freq_base); + if (!rc && dref->freq_mult != ref->freq_mult) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_FREQ_MULT, + ref->freq_mult); + if (!rc && dref->freq_ratio_m != ref->freq_ratio_m) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_M, + ref->freq_ratio_m); + if (!rc && dref->freq_ratio_n != ref->freq_ratio_n) + rc = zl3073x_write_u16(zldev, ZL_REG_REF_RATIO_N, + ref->freq_ratio_n); + if (!rc && dref->esync_n_div != ref->esync_n_div) + rc = zl3073x_write_u32(zldev, ZL_REG_REF_ESYNC_DIV, + ref->esync_n_div); + if (!rc && dref->sync_ctrl != ref->sync_ctrl) + rc = zl3073x_write_u8(zldev, ZL_REG_REF_SYNC_CTRL, + ref->sync_ctrl); + if (!rc && dref->phase_comp != ref->phase_comp) + rc = zl3073x_write_u48(zldev, ZL_REG_REF_PHASE_OFFSET_COMP, + ref->phase_comp); + if (rc) + return rc; + + /* Commit reference configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_REF_MB_SEM, ZL_REF_MB_SEM_WR, + ZL_REG_REF_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* After successful commit store new state */ + dref->freq_base = ref->freq_base; + dref->freq_mult = ref->freq_mult; + dref->freq_ratio_m = ref->freq_ratio_m; + dref->freq_ratio_n = ref->freq_ratio_n; + dref->esync_n_div = ref->esync_n_div; + dref->sync_ctrl = ref->sync_ctrl; + dref->phase_comp = ref->phase_comp; + + return 0; +} diff --git a/drivers/dpll/zl3073x/ref.h b/drivers/dpll/zl3073x/ref.h new file mode 100644 index 0000000000000..efc7f59cd9f9c --- /dev/null +++ b/drivers/dpll/zl3073x/ref.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_REF_H +#define _ZL3073X_REF_H + +#include +#include +#include + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_ref - input reference state + * @ffo: current fractional frequency offset + * @phase_comp: phase compensation + * @esync_n_div: divisor for embedded sync or n-divided signal formats + * @freq_base: frequency base + * @freq_mult: frequnecy multiplier + * @freq_ratio_m: FEC mode multiplier + * @freq_ratio_n: FEC mode divisor + * @config: reference config + * @sync_ctrl: reference sync control + * @mon_status: reference monitor status + */ +struct zl3073x_ref { + s64 ffo; + u64 phase_comp; + u32 esync_n_div; + u16 freq_base; + u16 freq_mult; + u16 freq_ratio_m; + u16 freq_ratio_n; + u8 config; + u8 sync_ctrl; + u8 mon_status; +}; + +int zl3073x_ref_state_fetch(struct zl3073x_dev *zldev, u8 index); + +const struct zl3073x_ref *zl3073x_ref_state_get(struct zl3073x_dev *zldev, + u8 index); + +int zl3073x_ref_state_set(struct zl3073x_dev *zldev, u8 index, + const struct zl3073x_ref *ref); + +int zl3073x_ref_freq_factorize(u32 freq, u16 *base, u16 *mult); + +/** + * zl3073x_ref_ffo_get - get current fractional frequency offset + * @ref: pointer to ref state + * + * Return: the latest measured fractional frequency offset + */ +static inline s64 +zl3073x_ref_ffo_get(const struct zl3073x_ref *ref) +{ + return ref->ffo; +} + +/** + * zl3073x_ref_freq_get - get given input reference frequency + * @ref: pointer to ref state + * + * Return: frequency of the given input reference + */ +static inline u32 +zl3073x_ref_freq_get(const struct zl3073x_ref *ref) +{ + return mul_u64_u32_div(ref->freq_base * ref->freq_mult, + ref->freq_ratio_m, ref->freq_ratio_n); +} + +/** + * zl3073x_ref_freq_set - set given input reference frequency + * @ref: pointer to ref state + * @freq: frequency to be set + * + * Return: 0 on success, <0 when frequency cannot be factorized + */ +static inline int +zl3073x_ref_freq_set(struct zl3073x_ref *ref, u32 freq) +{ + u16 base, mult; + int rc; + + rc = zl3073x_ref_freq_factorize(freq, &base, &mult); + if (rc) + return rc; + + ref->freq_base = base; + ref->freq_mult = mult; + + return 0; +} + +/** + * zl3073x_ref_is_diff - check if the given input reference is differential + * @ref: pointer to ref state + * + * Return: true if reference is differential, false if reference is single-ended + */ +static inline bool +zl3073x_ref_is_diff(const struct zl3073x_ref *ref) +{ + return !!FIELD_GET(ZL_REF_CONFIG_DIFF_EN, ref->config); +} + +/** + * zl3073x_ref_is_enabled - check if the given input reference is enabled + * @ref: pointer to ref state + * + * Return: true if input refernce is enabled, false otherwise + */ +static inline bool +zl3073x_ref_is_enabled(const struct zl3073x_ref *ref) +{ + return !!FIELD_GET(ZL_REF_CONFIG_ENABLE, ref->config); +} + +/** + * zl3073x_ref_is_status_ok - check the given input reference status + * @ref: pointer to ref state + * + * Return: true if the status is ok, false otherwise + */ +static inline bool +zl3073x_ref_is_status_ok(const struct zl3073x_ref *ref) +{ + return ref->mon_status == ZL_REF_MON_STATUS_OK; +} + +#endif /* _ZL3073X_REF_H */ diff --git a/drivers/dpll/zl3073x/synth.c b/drivers/dpll/zl3073x/synth.c new file mode 100644 index 0000000000000..da839572dab26 --- /dev/null +++ b/drivers/dpll/zl3073x/synth.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include +#include + +#include "core.h" +#include "synth.h" + +/** + * zl3073x_synth_state_fetch - fetch synth state from hardware + * @zldev: pointer to zl3073x_dev structure + * @index: synth index to fetch state for + * + * Function fetches state of the given synthesizer from the hardware and + * stores it for later use. + * + * Return: 0 on success, <0 on error + */ +int zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 index) +{ + struct zl3073x_synth *synth = &zldev->synth[index]; + int rc; + + /* Read synth control register */ + rc = zl3073x_read_u8(zldev, ZL_REG_SYNTH_CTRL(index), &synth->ctrl); + if (rc) + return rc; + + guard(mutex)(&zldev->multiop_lock); + + /* Read synth configuration */ + rc = zl3073x_mb_op(zldev, ZL_REG_SYNTH_MB_SEM, ZL_SYNTH_MB_SEM_RD, + ZL_REG_SYNTH_MB_MASK, BIT(index)); + if (rc) + return rc; + + /* The output frequency is determined by the following formula: + * base * multiplier * numerator / denominator + * + * Read registers with these values + */ + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_BASE, &synth->freq_base); + if (rc) + return rc; + + rc = zl3073x_read_u32(zldev, ZL_REG_SYNTH_FREQ_MULT, &synth->freq_mult); + if (rc) + return rc; + + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_M, &synth->freq_m); + if (rc) + return rc; + + rc = zl3073x_read_u16(zldev, ZL_REG_SYNTH_FREQ_N, &synth->freq_n); + if (rc) + return rc; + + /* Check denominator for zero to avoid div by 0 */ + if (!synth->freq_n) { + dev_err(zldev->dev, + "Zero divisor for SYNTH%u retrieved from device\n", + index); + return -EINVAL; + } + + dev_dbg(zldev->dev, "SYNTH%u frequency: %u Hz\n", index, + zl3073x_synth_freq_get(synth)); + + return rc; +} + +/** + * zl3073x_synth_state_get - get current synth state + * @zldev: pointer to zl3073x_dev structure + * @index: synth index to get state for + * + * Return: pointer to given synth state + */ +const struct zl3073x_synth *zl3073x_synth_state_get(struct zl3073x_dev *zldev, + u8 index) +{ + return &zldev->synth[index]; +} diff --git a/drivers/dpll/zl3073x/synth.h b/drivers/dpll/zl3073x/synth.h new file mode 100644 index 0000000000000..6c55eb8a888c2 --- /dev/null +++ b/drivers/dpll/zl3073x/synth.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef _ZL3073X_SYNTH_H +#define _ZL3073X_SYNTH_H + +#include +#include +#include + +#include "regs.h" + +struct zl3073x_dev; + +/** + * struct zl3073x_synth - synthesizer state + * @freq_mult: frequency multiplier + * @freq_base: frequency base + * @freq_m: frequency numerator + * @freq_n: frequency denominator + * @ctrl: synth control + */ +struct zl3073x_synth { + u32 freq_mult; + u16 freq_base; + u16 freq_m; + u16 freq_n; + u8 ctrl; +}; + +int zl3073x_synth_state_fetch(struct zl3073x_dev *zldev, u8 synth_id); + +const struct zl3073x_synth *zl3073x_synth_state_get(struct zl3073x_dev *zldev, + u8 synth_id); + +int zl3073x_synth_state_set(struct zl3073x_dev *zldev, u8 synth_id, + const struct zl3073x_synth *synth); + +/** + * zl3073x_synth_dpll_get - get DPLL ID the synth is driven by + * @synth: pointer to synth state + * + * Return: ID of DPLL the given synthetizer is driven by + */ +static inline u8 zl3073x_synth_dpll_get(const struct zl3073x_synth *synth) +{ + return FIELD_GET(ZL_SYNTH_CTRL_DPLL_SEL, synth->ctrl); +} + +/** + * zl3073x_synth_freq_get - get synth current freq + * @synth: pointer to synth state + * + * Return: frequency of given synthetizer + */ +static inline u32 zl3073x_synth_freq_get(const struct zl3073x_synth *synth) +{ + return mul_u64_u32_div(synth->freq_base * synth->freq_m, + synth->freq_mult, synth->freq_n); +} + +/** + * zl3073x_synth_is_enabled - check if the given synth is enabled + * @synth: pointer to synth state + * + * Return: true if synth is enabled, false otherwise + */ +static inline bool zl3073x_synth_is_enabled(const struct zl3073x_synth *synth) +{ + return FIELD_GET(ZL_SYNTH_CTRL_EN, synth->ctrl); +} + +#endif /* _ZL3073X_SYNTH_H */ diff --git a/drivers/firewire/Kconfig b/drivers/firewire/Kconfig index a5f5e250223a1..8cddc84d4d236 100644 --- a/drivers/firewire/Kconfig +++ b/drivers/firewire/Kconfig @@ -21,7 +21,6 @@ config FIREWIRE config FIREWIRE_KUNIT_UAPI_TEST tristate "KUnit tests for layout of structure in UAPI" if !KUNIT_ALL_TESTS depends on FIREWIRE && KUNIT - default KUNIT_ALL_TESTS help This builds the KUnit tests whether structures exposed to user space have expected layout. @@ -37,7 +36,6 @@ config FIREWIRE_KUNIT_UAPI_TEST config FIREWIRE_KUNIT_DEVICE_ATTRIBUTE_TEST tristate "KUnit tests for device attributes" if !KUNIT_ALL_TESTS depends on FIREWIRE && KUNIT - default KUNIT_ALL_TESTS help This builds the KUnit tests for device attribute for node and unit. @@ -53,7 +51,6 @@ config FIREWIRE_KUNIT_DEVICE_ATTRIBUTE_TEST config FIREWIRE_KUNIT_PACKET_SERDES_TEST tristate "KUnit tests for packet serialization/deserialization" if !KUNIT_ALL_TESTS depends on FIREWIRE && KUNIT - default KUNIT_ALL_TESTS help This builds the KUnit tests for packet serialization and deserialization. @@ -69,7 +66,6 @@ config FIREWIRE_KUNIT_PACKET_SERDES_TEST config FIREWIRE_KUNIT_SELF_ID_SEQUENCE_HELPER_TEST tristate "KUnit tests for helpers of self ID sequence" if !KUNIT_ALL_TESTS depends on FIREWIRE && KUNIT - default KUNIT_ALL_TESTS help This builds the KUnit tests for helpers of self ID sequence. @@ -95,7 +91,6 @@ config FIREWIRE_OHCI config FIREWIRE_KUNIT_OHCI_SERDES_TEST tristate "KUnit tests for serialization/deserialization of data in buffers/registers" if !KUNIT_ALL_TESTS depends on FIREWIRE && KUNIT - default KUNIT_ALL_TESTS help This builds the KUnit tests to check serialization and deserialization of data in buffers and registers defined in 1394 OHCI specification. diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig index e3c2e38b746df..ad7055f7e48d7 100644 --- a/drivers/firmware/cirrus/Kconfig +++ b/drivers/firmware/cirrus/Kconfig @@ -10,7 +10,6 @@ config FW_CS_DSP_KUNIT_TEST_UTILS config FW_CS_DSP_KUNIT_TEST tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS depends on KUNIT && REGMAP && FW_CS_DSP - default KUNIT_ALL_TESTS select FW_CS_DSP_KUNIT_TEST_UTILS help This builds KUnit tests for cs_dsp. diff --git a/drivers/fpga/tests/Kconfig b/drivers/fpga/tests/Kconfig index e4a64815f16d6..e8ded96191df9 100644 --- a/drivers/fpga/tests/Kconfig +++ b/drivers/fpga/tests/Kconfig @@ -1,7 +1,6 @@ config FPGA_KUNIT_TESTS tristate "KUnit test for the FPGA subsystem" if !KUNIT_ALL_TESTS depends on FPGA && FPGA_REGION && FPGA_BRIDGE && KUNIT=y - default KUNIT_ALL_TESTS help This builds unit tests for the FPGA subsystem diff --git a/drivers/gpu/drm/vc4/Kconfig b/drivers/gpu/drm/vc4/Kconfig index 123ab0ce17815..3751163aa3d2d 100644 --- a/drivers/gpu/drm/vc4/Kconfig +++ b/drivers/gpu/drm/vc4/Kconfig @@ -43,7 +43,6 @@ config DRM_VC4_KUNIT_TEST tristate "KUnit tests for VC4" if !KUNIT_ALL_TESTS depends on DRM_VC4 && KUNIT select DRM_KUNIT_TEST_HELPERS - default KUNIT_ALL_TESTS help This builds unit tests for the VC4 DRM/KMS driver. This option is not useful for distributions or general kernels, but only for kernel diff --git a/drivers/gpu/drm/xe/Kconfig.debug b/drivers/gpu/drm/xe/Kconfig.debug index 87902b4bd6d3b..df9ba4d9cdb51 100644 --- a/drivers/gpu/drm/xe/Kconfig.debug +++ b/drivers/gpu/drm/xe/Kconfig.debug @@ -76,7 +76,6 @@ config DRM_XE_DEBUG_MEM config DRM_XE_KUNIT_TEST tristate "KUnit tests for the drm xe driver" if !KUNIT_ALL_TESTS depends on DRM_XE && KUNIT && DEBUG_FS - default KUNIT_ALL_TESTS select DRM_EXPORT_FOR_TESTS if m help Choose this option to allow the driver to perform selftests under diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig index 04420a713be08..24e8018f8a446 100644 --- a/drivers/hid/Kconfig +++ b/drivers/hid/Kconfig @@ -1413,7 +1413,6 @@ config HID_KUNIT_TEST depends on KUNIT depends on HID_BATTERY_STRENGTH depends on HID_UCLOGIC - default KUNIT_ALL_TESTS help This builds unit tests for HID. This option is not useful for distributions or general kernels, but only for kernel diff --git a/drivers/infiniband/hw/erdma/erdma_cm.c b/drivers/infiniband/hw/erdma/erdma_cm.c index e0acc185e7193..ed21ba0037a4a 100644 --- a/drivers/infiniband/hw/erdma/erdma_cm.c +++ b/drivers/infiniband/hw/erdma/erdma_cm.c @@ -993,10 +993,10 @@ static int kernel_bindconnect(struct socket *s, struct sockaddr *laddr, int ret; sock_set_reuseaddr(s->sk); - ret = s->ops->bind(s, laddr, laddrlen); + ret = s->ops->bind(s, (struct sockaddr_unsized *)laddr, laddrlen); if (ret) return ret; - ret = s->ops->connect(s, raddr, raddrlen, flags); + ret = s->ops->connect(s, (struct sockaddr_unsized *)raddr, raddrlen, flags); return ret < 0 ? ret : 0; } @@ -1315,7 +1315,7 @@ int erdma_create_listen(struct iw_cm_id *id, int backlog) if (ipv4_is_zeronet(laddr->sin_addr.s_addr)) s->sk->sk_bound_dev_if = dev->netdev->ifindex; - ret = s->ops->bind(s, (struct sockaddr *)laddr, + ret = s->ops->bind(s, (struct sockaddr_unsized *)laddr, sizeof(struct sockaddr_in)); if (ret) goto error; diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index fc1e86f6c4097..90daa58126f47 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -842,7 +842,7 @@ static int mlx5_query_node_guid(struct mlx5_ib_dev *dev, break; case MLX5_VPORT_ACCESS_METHOD_NIC: - err = mlx5_query_nic_vport_node_guid(dev->mdev, &tmp); + err = mlx5_query_nic_vport_node_guid(dev->mdev, 0, false, &tmp); break; default: diff --git a/drivers/infiniband/sw/siw/siw_cm.c b/drivers/infiniband/sw/siw/siw_cm.c index 708b13993fdfd..eb0bd4f79a855 100644 --- a/drivers/infiniband/sw/siw/siw_cm.c +++ b/drivers/infiniband/sw/siw/siw_cm.c @@ -1340,11 +1340,11 @@ static int kernel_bindconnect(struct socket *s, struct sockaddr *laddr, return rv; } - rv = s->ops->bind(s, laddr, size); + rv = s->ops->bind(s, (struct sockaddr_unsized *)laddr, size); if (rv < 0) return rv; - rv = s->ops->connect(s, raddr, size, flags); + rv = s->ops->connect(s, (struct sockaddr_unsized *)raddr, size, flags); return rv < 0 ? rv : 0; } @@ -1789,7 +1789,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) goto error; } } - rv = s->ops->bind(s, (struct sockaddr *)laddr, + rv = s->ops->bind(s, (struct sockaddr_unsized *)laddr, sizeof(struct sockaddr_in)); } else { struct sockaddr_in6 *laddr = &to_sockaddr_in6(id->local_addr); @@ -1813,7 +1813,7 @@ int siw_create_listen(struct iw_cm_id *id, int backlog) goto error; } } - rv = s->ops->bind(s, (struct sockaddr *)laddr, + rv = s->ops->bind(s, (struct sockaddr_unsized *)laddr, sizeof(struct sockaddr_in6)); } if (rv) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 5b4d76e97437d..300afc27c5612 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1825,6 +1825,31 @@ static int ipoib_ioctl(struct net_device *dev, struct ifreq *ifr, return priv->rn_ops->ndo_eth_ioctl(dev, ifr, cmd); } +static int ipoib_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + if (!priv->rn_ops->ndo_hwtstamp_get) + /* legacy */ + return dev_eth_ioctl(dev, config->ifr, SIOCGHWTSTAMP); + + return priv->rn_ops->ndo_hwtstamp_get(dev, config); +} + +static int ipoib_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct ipoib_dev_priv *priv = ipoib_priv(dev); + + if (!priv->rn_ops->ndo_hwtstamp_set) + /* legacy */ + return dev_eth_ioctl(dev, config->ifr, SIOCSHWTSTAMP); + + return priv->rn_ops->ndo_hwtstamp_set(dev, config, extack); +} + static int ipoib_dev_init(struct net_device *dev) { struct ipoib_dev_priv *priv = ipoib_priv(dev); @@ -2149,6 +2174,8 @@ static const struct net_device_ops ipoib_netdev_ops_pf = { .ndo_set_mac_address = ipoib_set_mac, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, + .ndo_hwtstamp_get = ipoib_hwtstamp_get, + .ndo_hwtstamp_set = ipoib_hwtstamp_set, }; static const struct net_device_ops ipoib_netdev_ops_vf = { @@ -2164,6 +2191,8 @@ static const struct net_device_ops ipoib_netdev_ops_vf = { .ndo_get_iflink = ipoib_get_iflink, .ndo_get_stats64 = ipoib_get_stats, .ndo_eth_ioctl = ipoib_ioctl, + .ndo_hwtstamp_get = ipoib_hwtstamp_get, + .ndo_hwtstamp_set = ipoib_hwtstamp_set, }; static const struct net_device_ops ipoib_netdev_default_pf = { diff --git a/drivers/isdn/capi/kcapi.c b/drivers/isdn/capi/kcapi.c index c5d13bdc239be..e8f7e52354bc2 100644 --- a/drivers/isdn/capi/kcapi.c +++ b/drivers/isdn/capi/kcapi.c @@ -907,7 +907,7 @@ int __init kcapi_init(void) { int err; - kcapi_wq = alloc_workqueue("kcapi", 0, 0); + kcapi_wq = alloc_workqueue("kcapi", WQ_PERCPU, 0); if (!kcapi_wq) return -ENOMEM; diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index f732f6614d370..6ab036e4a35fb 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -676,7 +676,7 @@ l1oip_socket_thread(void *data) hc->sin_remote.sin_port = htons((unsigned short)hc->remoteport); /* bind to incoming port */ - if (socket->ops->bind(socket, (struct sockaddr *)&hc->sin_local, + if (socket->ops->bind(socket, (struct sockaddr_unsized *)&hc->sin_local, sizeof(hc->sin_local))) { printk(KERN_ERR "%s: Failed to bind socket to port %d.\n", __func__, hc->localport); diff --git a/drivers/isdn/mISDN/socket.c b/drivers/isdn/mISDN/socket.c index b215b28cad7b7..77b900db1cac2 100644 --- a/drivers/isdn/mISDN/socket.c +++ b/drivers/isdn/mISDN/socket.c @@ -462,7 +462,7 @@ static int data_sock_getsockopt(struct socket *sock, int level, int optname, } static int -data_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +data_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; @@ -696,7 +696,7 @@ base_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) } static int -base_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +base_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_mISDN *maddr = (struct sockaddr_mISDN *) addr; struct sock *sk = sock->sk; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 5abef8a3b7758..3d56339a8a10d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1468,97 +1468,6 @@ static netdev_features_t bond_fix_features(struct net_device *dev, return features; } -#define BOND_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ - NETIF_F_GSO_ENCAP_ALL | \ - NETIF_F_HIGHDMA | NETIF_F_LRO) - -#define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ - NETIF_F_GSO_PARTIAL) - -#define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_GSO_SOFTWARE) - -#define BOND_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) - - -static void bond_compute_features(struct bonding *bond) -{ - netdev_features_t gso_partial_features = BOND_GSO_PARTIAL_FEATURES; - unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | - IFF_XMIT_DST_RELEASE_PERM; - netdev_features_t vlan_features = BOND_VLAN_FEATURES; - netdev_features_t enc_features = BOND_ENC_FEATURES; -#ifdef CONFIG_XFRM_OFFLOAD - netdev_features_t xfrm_features = BOND_XFRM_FEATURES; -#endif /* CONFIG_XFRM_OFFLOAD */ - netdev_features_t mpls_features = BOND_MPLS_FEATURES; - struct net_device *bond_dev = bond->dev; - struct list_head *iter; - struct slave *slave; - unsigned short max_hard_header_len = ETH_HLEN; - unsigned int tso_max_size = TSO_MAX_SIZE; - u16 tso_max_segs = TSO_MAX_SEGS; - - if (!bond_has_slaves(bond)) - goto done; - - vlan_features = netdev_base_features(vlan_features); - mpls_features = netdev_base_features(mpls_features); - - bond_for_each_slave(bond, slave, iter) { - vlan_features = netdev_increment_features(vlan_features, - slave->dev->vlan_features, BOND_VLAN_FEATURES); - - enc_features = netdev_increment_features(enc_features, - slave->dev->hw_enc_features, - BOND_ENC_FEATURES); - -#ifdef CONFIG_XFRM_OFFLOAD - xfrm_features = netdev_increment_features(xfrm_features, - slave->dev->hw_enc_features, - BOND_XFRM_FEATURES); -#endif /* CONFIG_XFRM_OFFLOAD */ - - gso_partial_features = netdev_increment_features(gso_partial_features, - slave->dev->gso_partial_features, - BOND_GSO_PARTIAL_FEATURES); - - mpls_features = netdev_increment_features(mpls_features, - slave->dev->mpls_features, - BOND_MPLS_FEATURES); - - dst_release_flag &= slave->dev->priv_flags; - if (slave->dev->hard_header_len > max_hard_header_len) - max_hard_header_len = slave->dev->hard_header_len; - - tso_max_size = min(tso_max_size, slave->dev->tso_max_size); - tso_max_segs = min(tso_max_segs, slave->dev->tso_max_segs); - } - bond_dev->hard_header_len = max_hard_header_len; - -done: - bond_dev->gso_partial_features = gso_partial_features; - bond_dev->vlan_features = vlan_features; - bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX; -#ifdef CONFIG_XFRM_OFFLOAD - bond_dev->hw_enc_features |= xfrm_features; -#endif /* CONFIG_XFRM_OFFLOAD */ - bond_dev->mpls_features = mpls_features; - netif_set_tso_max_segs(bond_dev, tso_max_segs); - netif_set_tso_max_size(bond_dev, tso_max_size); - - bond_dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; - if ((bond_dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) && - dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) - bond_dev->priv_flags |= IFF_XMIT_DST_RELEASE; - - netdev_change_features(bond_dev); -} - static void bond_setup_by_slave(struct net_device *bond_dev, struct net_device *slave_dev) { @@ -2273,7 +2182,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev, } bond->slave_cnt++; - bond_compute_features(bond); + netdev_compute_master_upper_features(bond->dev, true); bond_set_carrier(bond); /* Needs to be called before bond_select_active_slave(), which will @@ -2528,7 +2437,7 @@ static int __bond_release_one(struct net_device *bond_dev, call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } - bond_compute_features(bond); + netdev_compute_master_upper_features(bond->dev, true); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n"); @@ -4028,7 +3937,7 @@ static int bond_slave_netdev_event(unsigned long event, case NETDEV_FEAT_CHANGE: if (!bond->notifier_ctx) { bond->notifier_ctx = true; - bond_compute_features(bond); + netdev_compute_master_upper_features(bond->dev, true); bond->notifier_ctx = false; } break; @@ -6011,7 +5920,7 @@ void bond_setup(struct net_device *bond_dev) * capable */ - bond_dev->hw_features = BOND_VLAN_FEATURES | + bond_dev->hw_features = MASTER_UPPER_DEV_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c index 191707d7e3dac..c2a3a4eef5b28 100644 --- a/drivers/net/can/at91_can.c +++ b/drivers/net/can/at91_can.c @@ -948,7 +948,6 @@ static const struct net_device_ops at91_netdev_ops = { .ndo_open = at91_open, .ndo_stop = at91_close, .ndo_start_xmit = at91_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops at91_ethtool_ops = { diff --git a/drivers/net/can/bxcan.c b/drivers/net/can/bxcan.c index 333ad42ea73bc..baf494d20bef4 100644 --- a/drivers/net/can/bxcan.c +++ b/drivers/net/can/bxcan.c @@ -227,7 +227,7 @@ static void bxcan_enable_filters(struct bxcan_priv *priv, enum bxcan_cfg cfg) * mask mode with 32 bits width. */ - /* Enter filter initialization mode and assing filters to CAN + /* Enter filter initialization mode and assign filters to CAN * controllers. */ regmap_update_bits(priv->gcan, BXCAN_FMR_REG, @@ -881,7 +881,6 @@ static const struct net_device_ops bxcan_netdev_ops = { .ndo_open = bxcan_open, .ndo_stop = bxcan_stop, .ndo_start_xmit = bxcan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops bxcan_ethtool_ops = { diff --git a/drivers/net/can/c_can/c_can_main.c b/drivers/net/can/c_can/c_can_main.c index cc371d0c9f3c7..3702cac7fbf0f 100644 --- a/drivers/net/can/c_can/c_can_main.c +++ b/drivers/net/can/c_can/c_can_main.c @@ -1362,7 +1362,6 @@ static const struct net_device_ops c_can_netdev_ops = { .ndo_open = c_can_open, .ndo_stop = c_can_close, .ndo_start_xmit = c_can_start_xmit, - .ndo_change_mtu = can_change_mtu, }; int register_c_can_dev(struct net_device *dev) diff --git a/drivers/net/can/can327.c b/drivers/net/can/can327.c index 24af639610309..b66fc16aedd2c 100644 --- a/drivers/net/can/can327.c +++ b/drivers/net/can/can327.c @@ -849,7 +849,6 @@ static const struct net_device_ops can327_netdev_ops = { .ndo_open = can327_netdev_open, .ndo_stop = can327_netdev_close, .ndo_start_xmit = can327_netdev_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops can327_ethtool_ops = { diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c index 30909f3aab576..8d5abd643c068 100644 --- a/drivers/net/can/cc770/cc770.c +++ b/drivers/net/can/cc770/cc770.c @@ -834,7 +834,6 @@ static const struct net_device_ops cc770_netdev_ops = { .ndo_open = cc770_open, .ndo_stop = cc770_close, .ndo_start_xmit = cc770_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops cc770_ethtool_ops = { diff --git a/drivers/net/can/ctucanfd/ctucanfd_base.c b/drivers/net/can/ctucanfd/ctucanfd_base.c index 8bd3f0fc385c3..1e6b9e3dc2fea 100644 --- a/drivers/net/can/ctucanfd/ctucanfd_base.c +++ b/drivers/net/can/ctucanfd/ctucanfd_base.c @@ -1301,7 +1301,6 @@ static const struct net_device_ops ctucan_netdev_ops = { .ndo_open = ctucan_open, .ndo_stop = ctucan_close, .ndo_start_xmit = ctucan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops ctucan_ethtool_ops = { diff --git a/drivers/net/can/dev/dev.c b/drivers/net/can/dev/dev.c index 15ccedbb3f8dd..80e1ab18de876 100644 --- a/drivers/net/can/dev/dev.c +++ b/drivers/net/can/dev/dev.c @@ -359,44 +359,6 @@ void can_set_default_mtu(struct net_device *dev) } } -/* changing MTU and control mode for CAN/CANFD devices */ -int can_change_mtu(struct net_device *dev, int new_mtu) -{ - struct can_priv *priv = netdev_priv(dev); - u32 ctrlmode_static = can_get_static_ctrlmode(priv); - - /* Do not allow changing the MTU while running */ - if (dev->flags & IFF_UP) - return -EBUSY; - - /* allow change of MTU according to the CANFD ability of the device */ - switch (new_mtu) { - case CAN_MTU: - /* 'CANFD-only' controllers can not switch to CAN_MTU */ - if (ctrlmode_static & CAN_CTRLMODE_FD) - return -EINVAL; - - priv->ctrlmode &= ~CAN_CTRLMODE_FD; - break; - - case CANFD_MTU: - /* check for potential CANFD ability */ - if (!(priv->ctrlmode_supported & CAN_CTRLMODE_FD) && - !(ctrlmode_static & CAN_CTRLMODE_FD)) - return -EINVAL; - - priv->ctrlmode |= CAN_CTRLMODE_FD; - break; - - default: - return -EINVAL; - } - - WRITE_ONCE(dev->mtu, new_mtu); - return 0; -} -EXPORT_SYMBOL_GPL(can_change_mtu); - /* helper to define static CAN controller features at device creation time */ int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) { @@ -417,34 +379,33 @@ int can_set_static_ctrlmode(struct net_device *dev, u32 static_mode) } EXPORT_SYMBOL_GPL(can_set_static_ctrlmode); -/* generic implementation of netdev_ops::ndo_eth_ioctl for CAN devices +/* generic implementation of netdev_ops::ndo_hwtstamp_get for CAN devices * supporting hardware timestamps */ -int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd) +int can_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg) { - struct hwtstamp_config hwts_cfg = { 0 }; - - switch (cmd) { - case SIOCSHWTSTAMP: /* set */ - if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg))) - return -EFAULT; - if (hwts_cfg.tx_type == HWTSTAMP_TX_ON && - hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL) - return 0; - return -ERANGE; - - case SIOCGHWTSTAMP: /* get */ - hwts_cfg.tx_type = HWTSTAMP_TX_ON; - hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL; - if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg))) - return -EFAULT; - return 0; + cfg->tx_type = HWTSTAMP_TX_ON; + cfg->rx_filter = HWTSTAMP_FILTER_ALL; - default: - return -EOPNOTSUPP; - } + return 0; +} +EXPORT_SYMBOL(can_hwtstamp_get); + +/* generic implementation of netdev_ops::ndo_hwtstamp_set for CAN devices + * supporting hardware timestamps + */ +int can_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) +{ + if (cfg->tx_type == HWTSTAMP_TX_ON && + cfg->rx_filter == HWTSTAMP_FILTER_ALL) + return 0; + NL_SET_ERR_MSG_MOD(extack, "Only TX on and RX all packets filter supported"); + return -ERANGE; } -EXPORT_SYMBOL(can_eth_ioctl_hwts); +EXPORT_SYMBOL(can_hwtstamp_set); /* generic implementation of ethtool_ops::get_ts_info for CAN devices * supporting hardware timestamps diff --git a/drivers/net/can/esd/esd_402_pci-core.c b/drivers/net/can/esd/esd_402_pci-core.c index 5d6d2828cd045..c826f00c551b4 100644 --- a/drivers/net/can/esd/esd_402_pci-core.c +++ b/drivers/net/can/esd/esd_402_pci-core.c @@ -86,8 +86,8 @@ static const struct net_device_ops pci402_acc_netdev_ops = { .ndo_open = acc_open, .ndo_stop = acc_close, .ndo_start_xmit = acc_start_xmit, - .ndo_change_mtu = can_change_mtu, - .ndo_eth_ioctl = can_eth_ioctl_hwts, + .ndo_hwtstamp_get = can_hwtstamp_get, + .ndo_hwtstamp_set = can_hwtstamp_set, }; static const struct ethtool_ops pci402_acc_ethtool_ops = { diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c index 06d5d35fc1b55..f5d22c61503fa 100644 --- a/drivers/net/can/flexcan/flexcan-core.c +++ b/drivers/net/can/flexcan/flexcan-core.c @@ -1867,7 +1867,6 @@ static const struct net_device_ops flexcan_netdev_ops = { .ndo_open = flexcan_open, .ndo_stop = flexcan_close, .ndo_start_xmit = flexcan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static int register_flexcandev(struct net_device *dev) diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c index c5784d9779ef5..3b1b09943436f 100644 --- a/drivers/net/can/grcan.c +++ b/drivers/net/can/grcan.c @@ -1561,7 +1561,6 @@ static const struct net_device_ops grcan_netdev_ops = { .ndo_open = grcan_open, .ndo_stop = grcan_close, .ndo_start_xmit = grcan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops grcan_ethtool_ops = { diff --git a/drivers/net/can/ifi_canfd/ifi_canfd.c b/drivers/net/can/ifi_canfd/ifi_canfd.c index 2eeee65f606f3..0f83335e4d075 100644 --- a/drivers/net/can/ifi_canfd/ifi_canfd.c +++ b/drivers/net/can/ifi_canfd/ifi_canfd.c @@ -944,7 +944,6 @@ static const struct net_device_ops ifi_canfd_netdev_ops = { .ndo_open = ifi_canfd_open, .ndo_stop = ifi_canfd_close, .ndo_start_xmit = ifi_canfd_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops ifi_canfd_ethtool_ops = { diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c index bfa5cbe88017d..1efdd1fd8caa4 100644 --- a/drivers/net/can/janz-ican3.c +++ b/drivers/net/can/janz-ican3.c @@ -1752,7 +1752,6 @@ static const struct net_device_ops ican3_netdev_ops = { .ndo_open = ican3_open, .ndo_stop = ican3_stop, .ndo_start_xmit = ican3_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops ican3_ethtool_ops = { diff --git a/drivers/net/can/kvaser_pciefd/kvaser_pciefd_core.c b/drivers/net/can/kvaser_pciefd/kvaser_pciefd_core.c index 0880023611beb..d8c9bfb202304 100644 --- a/drivers/net/can/kvaser_pciefd/kvaser_pciefd_core.c +++ b/drivers/net/can/kvaser_pciefd/kvaser_pciefd_core.c @@ -902,9 +902,9 @@ static void kvaser_pciefd_bec_poll_timer(struct timer_list *data) static const struct net_device_ops kvaser_pciefd_netdev_ops = { .ndo_open = kvaser_pciefd_open, .ndo_stop = kvaser_pciefd_stop, - .ndo_eth_ioctl = can_eth_ioctl_hwts, .ndo_start_xmit = kvaser_pciefd_start_xmit, - .ndo_change_mtu = can_change_mtu, + .ndo_hwtstamp_get = can_hwtstamp_get, + .ndo_hwtstamp_set = can_hwtstamp_set, }; static int kvaser_pciefd_set_phys_id(struct net_device *netdev, diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c index ad4f577c1ef78..eb856547ae7df 100644 --- a/drivers/net/can/m_can/m_can.c +++ b/drivers/net/can/m_can/m_can.c @@ -23,6 +23,7 @@ #include #include #include +#include #include "m_can.h" @@ -386,8 +387,8 @@ static int m_can_cccr_update_bits(struct m_can_classdev *cdev, u32 mask, u32 val size_t tries = 10; if (!(mask & CCCR_INIT) && !(val_before & CCCR_INIT)) { - dev_err(cdev->dev, - "refusing to configure device when in normal mode\n"); + netdev_err(cdev->net, + "refusing to configure device when in normal mode\n"); return -EBUSY; } @@ -451,7 +452,7 @@ static void m_can_interrupt_enable(struct m_can_classdev *cdev, u32 interrupts) { if (cdev->active_interrupts == interrupts) return; - cdev->ops->write_reg(cdev, M_CAN_IE, interrupts); + m_can_write(cdev, M_CAN_IE, interrupts); cdev->active_interrupts = interrupts; } @@ -469,7 +470,7 @@ static void m_can_coalescing_disable(struct m_can_classdev *cdev) static inline void m_can_enable_all_interrupts(struct m_can_classdev *cdev) { if (!cdev->net->irq) { - dev_dbg(cdev->dev, "Start hrtimer\n"); + netdev_dbg(cdev->net, "Start hrtimer\n"); hrtimer_start(&cdev->hrtimer, ms_to_ktime(HRTIMER_POLL_INTERVAL_MS), HRTIMER_MODE_REL_PINNED); @@ -485,7 +486,7 @@ static inline void m_can_disable_all_interrupts(struct m_can_classdev *cdev) m_can_write(cdev, M_CAN_ILE, 0x0); if (!cdev->net->irq) { - dev_dbg(cdev->dev, "Stop hrtimer\n"); + netdev_dbg(cdev->net, "Stop hrtimer\n"); hrtimer_try_to_cancel(&cdev->hrtimer); } } @@ -790,6 +791,10 @@ static int m_can_get_berr_counter(const struct net_device *dev, struct m_can_classdev *cdev = netdev_priv(dev); int err; + /* Avoid waking up the controller if the interface is down */ + if (!(dev->flags & IFF_UP)) + return 0; + err = m_can_clk_start(cdev); if (err) return err; @@ -1379,6 +1384,27 @@ static const struct can_bittiming_const m_can_data_bittiming_const_31X = { .brp_inc = 1, }; +static int m_can_init_ram(struct m_can_classdev *cdev) +{ + int end, i, start; + int err = 0; + + /* initialize the entire Message RAM in use to avoid possible + * ECC/parity checksum errors when reading an uninitialized buffer + */ + start = cdev->mcfg[MRAM_SIDF].off; + end = cdev->mcfg[MRAM_TXB].off + + cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE; + + for (i = start; i < end; i += 4) { + err = m_can_fifo_write_no_off(cdev, i, 0x0); + if (err) + break; + } + + return err; +} + static int m_can_set_bittiming(struct net_device *dev) { struct m_can_classdev *cdev = netdev_priv(dev); @@ -1464,7 +1490,7 @@ static int m_can_chip_config(struct net_device *dev) err = m_can_init_ram(cdev); if (err) { - dev_err(cdev->dev, "Message RAM configuration failed\n"); + netdev_err(dev, "Message RAM configuration failed\n"); return err; } @@ -1694,7 +1720,7 @@ static int m_can_niso_supported(struct m_can_classdev *cdev) /* Then clear the it again. */ ret = m_can_cccr_update_bits(cdev, CCCR_NISO, 0); if (ret) { - dev_err(cdev->dev, "failed to revert the NON-ISO bit in CCCR\n"); + netdev_err(cdev->net, "failed to revert the NON-ISO bit in CCCR\n"); return ret; } @@ -1713,8 +1739,8 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) m_can_version = m_can_check_core_release(cdev); /* return if unsupported version */ if (!m_can_version) { - dev_err(cdev->dev, "Unsupported version number: %2d", - m_can_version); + netdev_err(cdev->net, "Unsupported version number: %2d", + m_can_version); return -EINVAL; } @@ -1772,8 +1798,8 @@ static int m_can_dev_setup(struct m_can_classdev *cdev) cdev->can.ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO; break; default: - dev_err(cdev->dev, "Unsupported version number: %2d", - cdev->version); + netdev_err(cdev->net, "Unsupported version number: %2d", + cdev->version); return -EINVAL; } @@ -1827,6 +1853,7 @@ static int m_can_close(struct net_device *dev) close_candev(dev); + reset_control_assert(cdev->rst); m_can_clk_stop(cdev); phy_power_off(cdev->transceiver); @@ -1950,11 +1977,6 @@ static netdev_tx_t m_can_tx_handler(struct m_can_classdev *cdev, static void m_can_tx_submit(struct m_can_classdev *cdev) { - if (cdev->version == 30) - return; - if (!cdev->is_peripheral) - return; - m_can_write(cdev, M_CAN_TXBAR, cdev->tx_peripheral_submit); cdev->tx_peripheral_submit = 0; } @@ -2035,7 +2057,7 @@ static netdev_tx_t m_can_start_xmit(struct sk_buff *skb, return ret; } -static enum hrtimer_restart hrtimer_callback(struct hrtimer *timer) +static enum hrtimer_restart m_can_polling_timer(struct hrtimer *timer) { struct m_can_classdev *cdev = container_of(timer, struct m_can_classdev, hrtimer); @@ -2069,11 +2091,15 @@ static int m_can_open(struct net_device *dev) if (err) goto out_phy_power_off; + err = reset_control_deassert(cdev->rst); + if (err) + goto exit_disable_clks; + /* open the can device */ err = open_candev(dev); if (err) { netdev_err(dev, "failed to open can device\n"); - goto exit_disable_clks; + goto out_reset_control_assert; } if (cdev->is_peripheral) @@ -2129,6 +2155,8 @@ static int m_can_open(struct net_device *dev) else napi_disable(&cdev->napi); close_candev(dev); +out_reset_control_assert: + reset_control_assert(cdev->rst); exit_disable_clks: m_can_clk_stop(cdev); out_phy_power_off: @@ -2140,7 +2168,6 @@ static const struct net_device_ops m_can_netdev_ops = { .ndo_open = m_can_open, .ndo_stop = m_can_close, .ndo_start_xmit = m_can_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static int m_can_get_coalesce(struct net_device *dev, @@ -2231,6 +2258,55 @@ static int m_can_set_coalesce(struct net_device *dev, return 0; } +static void m_can_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +{ + struct m_can_classdev *cdev = netdev_priv(dev); + + wol->supported = device_can_wakeup(cdev->dev) ? WAKE_PHY : 0; + wol->wolopts = device_may_wakeup(cdev->dev) ? WAKE_PHY : 0; +} + +static int m_can_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) +{ + struct m_can_classdev *cdev = netdev_priv(dev); + bool wol_enable = !!(wol->wolopts & WAKE_PHY); + int ret; + + if (wol->wolopts & ~WAKE_PHY) + return -EINVAL; + + if (wol_enable == device_may_wakeup(cdev->dev)) + return 0; + + ret = device_set_wakeup_enable(cdev->dev, wol_enable); + if (ret) { + netdev_err(cdev->net, "Failed to set wakeup enable %pE\n", + ERR_PTR(ret)); + return ret; + } + + if (!IS_ERR_OR_NULL(cdev->pinctrl_state_wakeup)) { + if (wol_enable) + ret = pinctrl_select_state(cdev->pinctrl, cdev->pinctrl_state_wakeup); + else + ret = pinctrl_pm_select_default_state(cdev->dev); + + if (ret) { + netdev_err(cdev->net, "Failed to select pinctrl state %pE\n", + ERR_PTR(ret)); + goto err_wakeup_enable; + } + } + + return 0; + +err_wakeup_enable: + /* Revert wakeup enable */ + device_set_wakeup_enable(cdev->dev, !wol_enable); + + return ret; +} + static const struct ethtool_ops m_can_ethtool_ops_coalescing = { .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS_IRQ | ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ | @@ -2240,10 +2316,14 @@ static const struct ethtool_ops m_can_ethtool_ops_coalescing = { .get_ts_info = ethtool_op_get_ts_info, .get_coalesce = m_can_get_coalesce, .set_coalesce = m_can_set_coalesce, + .get_wol = m_can_get_wol, + .set_wol = m_can_set_wol, }; static const struct ethtool_ops m_can_ethtool_ops = { .get_ts_info = ethtool_op_get_ts_info, + .get_wol = m_can_get_wol, + .set_wol = m_can_set_wol, }; static int register_m_can_dev(struct m_can_classdev *cdev) @@ -2267,8 +2347,8 @@ int m_can_check_mram_cfg(struct m_can_classdev *cdev, u32 mram_max_size) total_size = cdev->mcfg[MRAM_TXB].off - cdev->mcfg[MRAM_SIDF].off + cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE; if (total_size > mram_max_size) { - dev_err(cdev->dev, "Total size of mram config(%u) exceeds mram(%u)\n", - total_size, mram_max_size); + netdev_err(cdev->net, "Total size of mram config(%u) exceeds mram(%u)\n", + total_size, mram_max_size); return -EINVAL; } @@ -2303,39 +2383,17 @@ static void m_can_of_parse_mram(struct m_can_classdev *cdev, cdev->mcfg[MRAM_TXB].num = mram_config_vals[7] & FIELD_MAX(TXBC_NDTB_MASK); - dev_dbg(cdev->dev, - "sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n", - cdev->mcfg[MRAM_SIDF].off, cdev->mcfg[MRAM_SIDF].num, - cdev->mcfg[MRAM_XIDF].off, cdev->mcfg[MRAM_XIDF].num, - cdev->mcfg[MRAM_RXF0].off, cdev->mcfg[MRAM_RXF0].num, - cdev->mcfg[MRAM_RXF1].off, cdev->mcfg[MRAM_RXF1].num, - cdev->mcfg[MRAM_RXB].off, cdev->mcfg[MRAM_RXB].num, - cdev->mcfg[MRAM_TXE].off, cdev->mcfg[MRAM_TXE].num, - cdev->mcfg[MRAM_TXB].off, cdev->mcfg[MRAM_TXB].num); + netdev_dbg(cdev->net, + "sidf 0x%x %d xidf 0x%x %d rxf0 0x%x %d rxf1 0x%x %d rxb 0x%x %d txe 0x%x %d txb 0x%x %d\n", + cdev->mcfg[MRAM_SIDF].off, cdev->mcfg[MRAM_SIDF].num, + cdev->mcfg[MRAM_XIDF].off, cdev->mcfg[MRAM_XIDF].num, + cdev->mcfg[MRAM_RXF0].off, cdev->mcfg[MRAM_RXF0].num, + cdev->mcfg[MRAM_RXF1].off, cdev->mcfg[MRAM_RXF1].num, + cdev->mcfg[MRAM_RXB].off, cdev->mcfg[MRAM_RXB].num, + cdev->mcfg[MRAM_TXE].off, cdev->mcfg[MRAM_TXE].num, + cdev->mcfg[MRAM_TXB].off, cdev->mcfg[MRAM_TXB].num); } -int m_can_init_ram(struct m_can_classdev *cdev) -{ - int end, i, start; - int err = 0; - - /* initialize the entire Message RAM in use to avoid possible - * ECC/parity checksum errors when reading an uninitialized buffer - */ - start = cdev->mcfg[MRAM_SIDF].off; - end = cdev->mcfg[MRAM_TXB].off + - cdev->mcfg[MRAM_TXB].num * TXB_ELEMENT_SIZE; - - for (i = start; i < end; i += 4) { - err = m_can_fifo_write_no_off(cdev, i, 0x0); - if (err) - break; - } - - return err; -} -EXPORT_SYMBOL_GPL(m_can_init_ram); - int m_can_class_get_clocks(struct m_can_classdev *cdev) { int ret = 0; @@ -2344,7 +2402,7 @@ int m_can_class_get_clocks(struct m_can_classdev *cdev) cdev->cclk = devm_clk_get(cdev->dev, "cclk"); if (IS_ERR(cdev->hclk) || IS_ERR(cdev->cclk)) { - dev_err(cdev->dev, "no clock found\n"); + netdev_err(cdev->net, "no clock found\n"); ret = -ENODEV; } @@ -2352,6 +2410,42 @@ int m_can_class_get_clocks(struct m_can_classdev *cdev) } EXPORT_SYMBOL_GPL(m_can_class_get_clocks); +static bool m_can_class_wakeup_pinctrl_enabled(struct m_can_classdev *class_dev) +{ + return device_may_wakeup(class_dev->dev) && class_dev->pinctrl_state_wakeup; +} + +static int m_can_class_parse_pinctrl(struct m_can_classdev *class_dev) +{ + struct device *dev = class_dev->dev; + int ret; + + class_dev->pinctrl = devm_pinctrl_get(dev); + if (IS_ERR(class_dev->pinctrl)) { + ret = PTR_ERR(class_dev->pinctrl); + class_dev->pinctrl = NULL; + + if (ret == -ENODEV) + return 0; + + return dev_err_probe(dev, ret, "Failed to get pinctrl\n"); + } + + class_dev->pinctrl_state_wakeup = + pinctrl_lookup_state(class_dev->pinctrl, "wakeup"); + if (IS_ERR(class_dev->pinctrl_state_wakeup)) { + ret = PTR_ERR(class_dev->pinctrl_state_wakeup); + class_dev->pinctrl_state_wakeup = NULL; + + if (ret == -ENODEV) + return 0; + + return dev_err_probe(dev, ret, "Failed to lookup pinctrl wakeup state\n"); + } + + return 0; +} + struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, int sizeof_priv) { @@ -2367,9 +2461,12 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, sizeof(mram_config_vals) / 4); if (ret) { dev_err(dev, "Could not get Message RAM configuration."); - goto out; + return ERR_PTR(ret); } + if (dev->of_node && of_property_read_bool(dev->of_node, "wakeup-source")) + device_set_wakeup_capable(dev, true); + /* Get TX FIFO size * Defines the total amount of echo buffers for loopback */ @@ -2379,7 +2476,7 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, net_dev = alloc_candev(sizeof_priv, tx_fifo_size); if (!net_dev) { dev_err(dev, "Failed to allocate CAN device"); - goto out; + return ERR_PTR(-ENOMEM); } class_dev = netdev_priv(net_dev); @@ -2389,8 +2486,16 @@ struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, m_can_of_parse_mram(class_dev, mram_config_vals); spin_lock_init(&class_dev->tx_handling_spinlock); -out: + + ret = m_can_class_parse_pinctrl(class_dev); + if (ret) + goto err_free_candev; + return class_dev; + +err_free_candev: + free_candev(net_dev); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(m_can_class_allocate_dev); @@ -2411,26 +2516,33 @@ int m_can_class_register(struct m_can_classdev *cdev) devm_kzalloc(cdev->dev, cdev->tx_fifo_size * sizeof(*cdev->tx_ops), GFP_KERNEL); - if (!cdev->tx_ops) { - dev_err(cdev->dev, "Failed to allocate tx_ops for workqueue\n"); + if (!cdev->tx_ops) return -ENOMEM; - } } + cdev->rst = devm_reset_control_get_optional_shared(cdev->dev, NULL); + if (IS_ERR(cdev->rst)) + return dev_err_probe(cdev->dev, PTR_ERR(cdev->rst), + "Failed to get reset line\n"); + ret = m_can_clk_start(cdev); if (ret) return ret; + ret = reset_control_deassert(cdev->rst); + if (ret) + goto clk_disable; + if (cdev->is_peripheral) { ret = can_rx_offload_add_manual(cdev->net, &cdev->offload, NAPI_POLL_WEIGHT); if (ret) - goto clk_disable; + goto out_reset_control_assert; } if (!cdev->net->irq) { - dev_dbg(cdev->dev, "Polling enabled, initialize hrtimer"); - hrtimer_setup(&cdev->hrtimer, &hrtimer_callback, CLOCK_MONOTONIC, + netdev_dbg(cdev->net, "Polling enabled, initialize hrtimer"); + hrtimer_setup(&cdev->hrtimer, m_can_polling_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); } else { hrtimer_setup(&cdev->hrtimer, m_can_coalescing_timer, CLOCK_MONOTONIC, @@ -2443,19 +2555,21 @@ int m_can_class_register(struct m_can_classdev *cdev) ret = register_m_can_dev(cdev); if (ret) { - dev_err(cdev->dev, "registering %s failed (err=%d)\n", - cdev->net->name, ret); + netdev_err(cdev->net, "registering %s failed (err=%d)\n", + cdev->net->name, ret); goto rx_offload_del; } of_can_transceiver(cdev->net); - dev_info(cdev->dev, "%s device registered (irq=%d, version=%d)\n", - KBUILD_MODNAME, cdev->net->irq, cdev->version); + netdev_info(cdev->net, "device registered (irq=%d, version=%d)\n", + cdev->net->irq, cdev->version); /* Probe finished - * Stop clocks. They will be reactivated once the M_CAN device is opened + * Assert reset and stop clocks. + * They will be reactivated once the M_CAN device is opened */ + reset_control_assert(cdev->rst); m_can_clk_stop(cdev); return 0; @@ -2463,6 +2577,8 @@ int m_can_class_register(struct m_can_classdev *cdev) rx_offload_del: if (cdev->is_peripheral) can_rx_offload_del(&cdev->offload); +out_reset_control_assert: + reset_control_assert(cdev->rst); clk_disable: m_can_clk_stop(cdev); @@ -2506,7 +2622,8 @@ int m_can_class_suspend(struct device *dev) cdev->can.state = CAN_STATE_SLEEPING; } - pinctrl_pm_select_sleep_state(dev); + if (!m_can_class_wakeup_pinctrl_enabled(cdev)) + pinctrl_pm_select_sleep_state(dev); return ret; } @@ -2518,7 +2635,8 @@ int m_can_class_resume(struct device *dev) struct net_device *ndev = cdev->net; int ret = 0; - pinctrl_pm_select_default_state(dev); + if (!m_can_class_wakeup_pinctrl_enabled(cdev)) + pinctrl_pm_select_default_state(dev); if (netif_running(ndev)) { ret = m_can_clk_start(cdev); diff --git a/drivers/net/can/m_can/m_can.h b/drivers/net/can/m_can/m_can.h index bd4746c63af3f..4743342b2fba3 100644 --- a/drivers/net/can/m_can/m_can.h +++ b/drivers/net/can/m_can/m_can.h @@ -86,6 +86,7 @@ struct m_can_classdev { struct device *dev; struct clk *hclk; struct clk *cclk; + struct reset_control *rst; struct workqueue_struct *tx_wq; struct phy *transceiver; @@ -128,6 +129,9 @@ struct m_can_classdev { struct mram_cfg mcfg[MRAM_CFG_NUM]; struct hrtimer hrtimer; + + struct pinctrl *pinctrl; + struct pinctrl_state *pinctrl_state_wakeup; }; struct m_can_classdev *m_can_class_allocate_dev(struct device *dev, int sizeof_priv); @@ -135,7 +139,6 @@ void m_can_class_free_dev(struct net_device *net); int m_can_class_register(struct m_can_classdev *cdev); void m_can_class_unregister(struct m_can_classdev *cdev); int m_can_class_get_clocks(struct m_can_classdev *cdev); -int m_can_init_ram(struct m_can_classdev *priv); int m_can_check_mram_cfg(struct m_can_classdev *cdev, u32 mram_max_size); int m_can_class_suspend(struct device *dev); diff --git a/drivers/net/can/m_can/m_can_pci.c b/drivers/net/can/m_can/m_can_pci.c index 9ad7419f88f83..eb31ed1f96449 100644 --- a/drivers/net/can/m_can/m_can_pci.c +++ b/drivers/net/can/m_can/m_can_pci.c @@ -111,8 +111,8 @@ static int m_can_pci_probe(struct pci_dev *pci, const struct pci_device_id *id) mcan_class = m_can_class_allocate_dev(&pci->dev, sizeof(struct m_can_pci_priv)); - if (!mcan_class) - return -ENOMEM; + if (IS_ERR(mcan_class)) + return PTR_ERR(mcan_class); priv = cdev_to_priv(mcan_class); diff --git a/drivers/net/can/m_can/m_can_platform.c b/drivers/net/can/m_can/m_can_platform.c index 4a412add2b8d3..56da411878af0 100644 --- a/drivers/net/can/m_can/m_can_platform.c +++ b/drivers/net/can/m_can/m_can_platform.c @@ -87,8 +87,8 @@ static int m_can_plat_probe(struct platform_device *pdev) mcan_class = m_can_class_allocate_dev(&pdev->dev, sizeof(struct m_can_plat_priv)); - if (!mcan_class) - return -ENOMEM; + if (IS_ERR(mcan_class)) + return PTR_ERR(mcan_class); priv = cdev_to_priv(mcan_class); diff --git a/drivers/net/can/m_can/tcan4x5x-core.c b/drivers/net/can/m_can/tcan4x5x-core.c index 39b0b5277b11f..31cc9d0abd453 100644 --- a/drivers/net/can/m_can/tcan4x5x-core.c +++ b/drivers/net/can/m_can/tcan4x5x-core.c @@ -416,8 +416,8 @@ static int tcan4x5x_can_probe(struct spi_device *spi) mcan_class = m_can_class_allocate_dev(&spi->dev, sizeof(struct tcan4x5x_priv)); - if (!mcan_class) - return -ENOMEM; + if (IS_ERR(mcan_class)) + return PTR_ERR(mcan_class); ret = m_can_check_mram_cfg(mcan_class, TCAN4X5X_MRAM_SIZE); if (ret) diff --git a/drivers/net/can/mscan/mscan.c b/drivers/net/can/mscan/mscan.c index 8c2a7bc64d3d7..39c7aa2a0b2f8 100644 --- a/drivers/net/can/mscan/mscan.c +++ b/drivers/net/can/mscan/mscan.c @@ -607,7 +607,6 @@ static const struct net_device_ops mscan_netdev_ops = { .ndo_open = mscan_open, .ndo_stop = mscan_close, .ndo_start_xmit = mscan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops mscan_ethtool_ops = { diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c index b5bc80ac7876a..06cb2629f66ab 100644 --- a/drivers/net/can/peak_canfd/peak_canfd.c +++ b/drivers/net/can/peak_canfd/peak_canfd.c @@ -743,37 +743,33 @@ static netdev_tx_t peak_canfd_start_xmit(struct sk_buff *skb, return NETDEV_TX_OK; } -static int peak_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int peak_eth_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - struct hwtstamp_config hwts_cfg = { 0 }; + config->tx_type = HWTSTAMP_TX_OFF; + config->rx_filter = HWTSTAMP_FILTER_ALL; - switch (cmd) { - case SIOCSHWTSTAMP: /* set */ - if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg))) - return -EFAULT; - if (hwts_cfg.tx_type == HWTSTAMP_TX_OFF && - hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL) - return 0; - return -ERANGE; + return 0; +} - case SIOCGHWTSTAMP: /* get */ - hwts_cfg.tx_type = HWTSTAMP_TX_OFF; - hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL; - if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg))) - return -EFAULT; +static int peak_eth_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + if (config->tx_type == HWTSTAMP_TX_OFF && + config->rx_filter == HWTSTAMP_FILTER_ALL) return 0; - default: - return -EOPNOTSUPP; - } + NL_SET_ERR_MSG_MOD(extack, "Only RX HWTSTAMP_FILTER_ALL is supported"); + return -ERANGE; } static const struct net_device_ops peak_canfd_netdev_ops = { .ndo_open = peak_canfd_open, .ndo_stop = peak_canfd_close, - .ndo_eth_ioctl = peak_eth_ioctl, .ndo_start_xmit = peak_canfd_start_xmit, - .ndo_change_mtu = can_change_mtu, + .ndo_hwtstamp_get = peak_eth_hwtstamp_get, + .ndo_hwtstamp_set = peak_eth_hwtstamp_set, }; static int peak_get_ts_info(struct net_device *dev, diff --git a/drivers/net/can/rcar/rcar_can.c b/drivers/net/can/rcar/rcar_can.c index 5f85f4e272054..fc3df328e877c 100644 --- a/drivers/net/can/rcar/rcar_can.c +++ b/drivers/net/can/rcar/rcar_can.c @@ -635,7 +635,6 @@ static const struct net_device_ops rcar_can_netdev_ops = { .ndo_open = rcar_can_open, .ndo_stop = rcar_can_close, .ndo_start_xmit = rcar_can_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops rcar_can_ethtool_ops = { diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c index 45d36adb51b78..49ab65274b51d 100644 --- a/drivers/net/can/rcar/rcar_canfd.c +++ b/drivers/net/can/rcar/rcar_canfd.c @@ -1818,7 +1818,6 @@ static const struct net_device_ops rcar_canfd_netdev_ops = { .ndo_open = rcar_canfd_open, .ndo_stop = rcar_canfd_close, .ndo_start_xmit = rcar_canfd_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops rcar_canfd_ethtool_ops = { diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c index 046f0a0ae4d4b..29de0c01e4edc 100644 --- a/drivers/net/can/rockchip/rockchip_canfd-core.c +++ b/drivers/net/can/rockchip/rockchip_canfd-core.c @@ -761,7 +761,6 @@ static const struct net_device_ops rkcanfd_netdev_ops = { .ndo_open = rkcanfd_open, .ndo_stop = rkcanfd_stop, .ndo_start_xmit = rkcanfd_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static int __maybe_unused rkcanfd_runtime_suspend(struct device *dev) diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index 4d245857ef1ce..acfa49db3907e 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -697,7 +697,6 @@ static const struct net_device_ops sja1000_netdev_ops = { .ndo_open = sja1000_open, .ndo_stop = sja1000_close, .ndo_start_xmit = sja1000_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops sja1000_ethtool_ops = { diff --git a/drivers/net/can/slcan/slcan-core.c b/drivers/net/can/slcan/slcan-core.c index 58ff2ec1d9757..cd789e178d34b 100644 --- a/drivers/net/can/slcan/slcan-core.c +++ b/drivers/net/can/slcan/slcan-core.c @@ -774,7 +774,6 @@ static const struct net_device_ops slcan_netdev_ops = { .ndo_open = slcan_netdev_open, .ndo_stop = slcan_netdev_close, .ndo_start_xmit = slcan_netdev_xmit, - .ndo_change_mtu = can_change_mtu, }; /****************************************** diff --git a/drivers/net/can/softing/softing_main.c b/drivers/net/can/softing/softing_main.c index 278ee8722770c..79bc64395ac46 100644 --- a/drivers/net/can/softing/softing_main.c +++ b/drivers/net/can/softing/softing_main.c @@ -609,7 +609,6 @@ static const struct net_device_ops softing_netdev_ops = { .ndo_open = softing_netdev_open, .ndo_stop = softing_netdev_stop, .ndo_start_xmit = softing_netdev_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops softing_ethtool_ops = { diff --git a/drivers/net/can/spi/hi311x.c b/drivers/net/can/spi/hi311x.c index 6d4b643e135fd..e00d3dbc4cf43 100644 --- a/drivers/net/can/spi/hi311x.c +++ b/drivers/net/can/spi/hi311x.c @@ -799,7 +799,6 @@ static const struct net_device_ops hi3110_netdev_ops = { .ndo_open = hi3110_open, .ndo_stop = hi3110_stop, .ndo_start_xmit = hi3110_hard_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops hi3110_ethtool_ops = { diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c index b797e08499d70..fa97adf25b734 100644 --- a/drivers/net/can/spi/mcp251x.c +++ b/drivers/net/can/spi/mcp251x.c @@ -1270,7 +1270,6 @@ static const struct net_device_ops mcp251x_netdev_ops = { .ndo_open = mcp251x_open, .ndo_stop = mcp251x_stop, .ndo_start_xmit = mcp251x_hard_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops mcp251x_ethtool_ops = { @@ -1321,7 +1320,7 @@ static int mcp251x_can_probe(struct spi_device *spi) clk = devm_clk_get_optional(&spi->dev, NULL); if (IS_ERR(clk)) - return PTR_ERR(clk); + return dev_err_probe(&spi->dev, PTR_ERR(clk), "Cannot get clock\n"); freq = clk_get_rate(clk); if (freq == 0) @@ -1329,7 +1328,7 @@ static int mcp251x_can_probe(struct spi_device *spi) /* Sanity check */ if (freq < 1000000 || freq > 25000000) - return -ERANGE; + return dev_err_probe(&spi->dev, -ERANGE, "clock frequency out of range\n"); /* Allocate can/net device */ net = alloc_candev(sizeof(struct mcp251x_priv), TX_ECHO_SKB_MAX); @@ -1337,8 +1336,10 @@ static int mcp251x_can_probe(struct spi_device *spi) return -ENOMEM; ret = clk_prepare_enable(clk); - if (ret) + if (ret) { + dev_err_probe(&spi->dev, ret, "Cannot enable clock\n"); goto out_free; + } net->netdev_ops = &mcp251x_netdev_ops; net->ethtool_ops = &mcp251x_ethtool_ops; @@ -1363,20 +1364,25 @@ static int mcp251x_can_probe(struct spi_device *spi) else spi->max_speed_hz = spi->max_speed_hz ? : 10 * 1000 * 1000; ret = spi_setup(spi); - if (ret) + if (ret) { + dev_err_probe(&spi->dev, ret, "Cannot set up spi\n"); goto out_clk; + } priv->power = devm_regulator_get_optional(&spi->dev, "vdd"); priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver"); if ((PTR_ERR(priv->power) == -EPROBE_DEFER) || (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) { ret = -EPROBE_DEFER; + dev_err_probe(&spi->dev, ret, "supply deferred\n"); goto out_clk; } ret = mcp251x_power_enable(priv->power, 1); - if (ret) + if (ret) { + dev_err_probe(&spi->dev, ret, "Cannot enable power\n"); goto out_clk; + } priv->wq = alloc_workqueue("mcp251x_wq", WQ_FREEZABLE | WQ_MEM_RECLAIM | WQ_PERCPU, @@ -1410,21 +1416,24 @@ static int mcp251x_can_probe(struct spi_device *spi) /* Here is OK to not lock the MCP, no one knows about it yet */ ret = mcp251x_hw_probe(spi); if (ret) { - if (ret == -ENODEV) - dev_err(&spi->dev, "Cannot initialize MCP%x. Wrong wiring?\n", - priv->model); + dev_err_probe(&spi->dev, ret, "Cannot initialize MCP%x. Wrong wiring?\n", + priv->model); goto error_probe; } mcp251x_hw_sleep(spi); ret = register_candev(net); - if (ret) + if (ret) { + dev_err_probe(&spi->dev, ret, "Cannot register CAN device\n"); goto error_probe; + } ret = mcp251x_gpio_setup(priv); - if (ret) + if (ret) { + dev_err_probe(&spi->dev, ret, "Cannot set up gpios\n"); goto out_unregister_candev; + } netdev_info(net, "MCP%x successfully initialized.\n", priv->model); return 0; @@ -1443,7 +1452,6 @@ static int mcp251x_can_probe(struct spi_device *spi) out_free: free_candev(net); - dev_err(&spi->dev, "Probe failed, err=%d\n", -ret); return ret; } diff --git a/drivers/net/can/spi/mcp251xfd/Kconfig b/drivers/net/can/spi/mcp251xfd/Kconfig index 877e4356010dd..7c29846e60517 100644 --- a/drivers/net/can/spi/mcp251xfd/Kconfig +++ b/drivers/net/can/spi/mcp251xfd/Kconfig @@ -5,6 +5,7 @@ config CAN_MCP251XFD select CAN_RX_OFFLOAD select REGMAP select WANT_DEV_COREDUMP + select GPIOLIB help Driver for the Microchip MCP251XFD SPI FD-CAN controller family. diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 7450ea42c1ea5..5134ebb85880b 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -608,23 +608,21 @@ static int mcp251xfd_set_bittiming(const struct mcp251xfd_priv *priv) static int mcp251xfd_chip_rx_int_enable(const struct mcp251xfd_priv *priv) { - u32 val; + u32 val, mask; if (!priv->rx_int) return 0; - /* Configure GPIOs: - * - PIN0: GPIO Input - * - PIN1: GPIO Input/RX Interrupt + /* Configure PIN1 as RX Interrupt: * * PIN1 must be Input, otherwise there is a glitch on the * rx-INT line. It happens between setting the PIN as output * (in the first byte of the SPI transfer) and configuring the * PIN as interrupt (in the last byte of the SPI transfer). */ - val = MCP251XFD_REG_IOCON_PM0 | MCP251XFD_REG_IOCON_TRIS1 | - MCP251XFD_REG_IOCON_TRIS0; - return regmap_write(priv->map_reg, MCP251XFD_REG_IOCON, val); + val = MCP251XFD_REG_IOCON_TRIS(1); + mask = MCP251XFD_REG_IOCON_TRIS(1) | MCP251XFD_REG_IOCON_PM(1); + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, mask, val); } static int mcp251xfd_chip_rx_int_disable(const struct mcp251xfd_priv *priv) @@ -634,13 +632,9 @@ static int mcp251xfd_chip_rx_int_disable(const struct mcp251xfd_priv *priv) if (!priv->rx_int) return 0; - /* Configure GPIOs: - * - PIN0: GPIO Input - * - PIN1: GPIO Input - */ - val = MCP251XFD_REG_IOCON_PM1 | MCP251XFD_REG_IOCON_PM0 | - MCP251XFD_REG_IOCON_TRIS1 | MCP251XFD_REG_IOCON_TRIS0; - return regmap_write(priv->map_reg, MCP251XFD_REG_IOCON, val); + /* Configure PIN1 as GPIO Input */ + val = MCP251XFD_REG_IOCON_PM(1) | MCP251XFD_REG_IOCON_TRIS(1); + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, val, val); } static int mcp251xfd_chip_ecc_init(struct mcp251xfd_priv *priv) @@ -767,21 +761,13 @@ static void mcp251xfd_chip_stop(struct mcp251xfd_priv *priv, mcp251xfd_chip_interrupts_disable(priv); mcp251xfd_chip_rx_int_disable(priv); mcp251xfd_timestamp_stop(priv); - mcp251xfd_chip_sleep(priv); + mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_CONFIG); } static int mcp251xfd_chip_start(struct mcp251xfd_priv *priv) { int err; - err = mcp251xfd_chip_softreset(priv); - if (err) - goto out_chip_stop; - - err = mcp251xfd_chip_clock_init(priv); - if (err) - goto out_chip_stop; - err = mcp251xfd_chip_timestamp_init(priv); if (err) goto out_chip_stop; @@ -1625,8 +1611,11 @@ static int mcp251xfd_open(struct net_device *ndev) return err; err = pm_runtime_resume_and_get(ndev->dev.parent); - if (err) + if (err) { + if (err == -ETIMEDOUT || err == -ENODEV) + pm_runtime_set_suspended(ndev->dev.parent); goto out_close_candev; + } err = mcp251xfd_ring_alloc(priv); if (err) @@ -1714,8 +1703,8 @@ static const struct net_device_ops mcp251xfd_netdev_ops = { .ndo_open = mcp251xfd_open, .ndo_stop = mcp251xfd_stop, .ndo_start_xmit = mcp251xfd_start_xmit, - .ndo_eth_ioctl = can_eth_ioctl_hwts, - .ndo_change_mtu = can_change_mtu, + .ndo_hwtstamp_get = can_hwtstamp_get, + .ndo_hwtstamp_set = can_hwtstamp_set, }; static void @@ -1808,6 +1797,160 @@ static int mcp251xfd_register_check_rx_int(struct mcp251xfd_priv *priv) return 0; } +static const char * const mcp251xfd_gpio_names[] = { "GPIO0", "GPIO1" }; + +static int mcp251xfd_gpio_request(struct gpio_chip *chip, unsigned int offset) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 pin_mask = MCP251XFD_REG_IOCON_PM(offset); + int ret; + + if (priv->rx_int && offset == 1) { + netdev_err(priv->ndev, "Can't use GPIO 1 with RX-INT!\n"); + return -EINVAL; + } + + ret = pm_runtime_resume_and_get(priv->ndev->dev.parent); + if (ret) + return ret; + + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, pin_mask, pin_mask); +} + +static void mcp251xfd_gpio_free(struct gpio_chip *chip, unsigned int offset) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + + pm_runtime_put(priv->ndev->dev.parent); +} + +static int mcp251xfd_gpio_get_direction(struct gpio_chip *chip, + unsigned int offset) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 mask = MCP251XFD_REG_IOCON_TRIS(offset); + u32 val; + int ret; + + ret = regmap_read(priv->map_reg, MCP251XFD_REG_IOCON, &val); + if (ret) + return ret; + + if (mask & val) + return GPIO_LINE_DIRECTION_IN; + + return GPIO_LINE_DIRECTION_OUT; +} + +static int mcp251xfd_gpio_get(struct gpio_chip *chip, unsigned int offset) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 mask = MCP251XFD_REG_IOCON_GPIO(offset); + u32 val; + int ret; + + ret = regmap_read(priv->map_reg, MCP251XFD_REG_IOCON, &val); + if (ret) + return ret; + + return !!(mask & val); +} + +static int mcp251xfd_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask, + unsigned long *bit) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 val; + int ret; + + ret = regmap_read(priv->map_reg, MCP251XFD_REG_IOCON, &val); + if (ret) + return ret; + + *bit = FIELD_GET(MCP251XFD_REG_IOCON_GPIO_MASK, val) & *mask; + + return 0; +} + +static int mcp251xfd_gpio_direction_output(struct gpio_chip *chip, + unsigned int offset, int value) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 dir_mask = MCP251XFD_REG_IOCON_TRIS(offset); + u32 val_mask = MCP251XFD_REG_IOCON_LAT(offset); + u32 val; + + if (value) + val = val_mask; + else + val = 0; + + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, + dir_mask | val_mask, val); +} + +static int mcp251xfd_gpio_direction_input(struct gpio_chip *chip, + unsigned int offset) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 dir_mask = MCP251XFD_REG_IOCON_TRIS(offset); + + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, dir_mask, dir_mask); +} + +static int mcp251xfd_gpio_set(struct gpio_chip *chip, unsigned int offset, int value) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 val_mask = MCP251XFD_REG_IOCON_LAT(offset); + u32 val; + + if (value) + val = val_mask; + else + val = 0; + + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, val_mask, val); +} + +static int mcp251xfd_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mask, + unsigned long *bits) +{ + struct mcp251xfd_priv *priv = gpiochip_get_data(chip); + u32 val; + + val = FIELD_PREP(MCP251XFD_REG_IOCON_LAT_MASK, *bits); + + return regmap_update_bits(priv->map_reg, MCP251XFD_REG_IOCON, + MCP251XFD_REG_IOCON_LAT_MASK, val); +} + +static int mcp251fdx_gpio_setup(struct mcp251xfd_priv *priv) +{ + struct gpio_chip *gc = &priv->gc; + + if (!device_property_present(&priv->spi->dev, "gpio-controller")) + return 0; + + gc->label = dev_name(&priv->spi->dev); + gc->parent = &priv->spi->dev; + gc->owner = THIS_MODULE; + gc->request = mcp251xfd_gpio_request; + gc->free = mcp251xfd_gpio_free; + gc->get_direction = mcp251xfd_gpio_get_direction; + gc->direction_output = mcp251xfd_gpio_direction_output; + gc->direction_input = mcp251xfd_gpio_direction_input; + gc->get = mcp251xfd_gpio_get; + gc->get_multiple = mcp251xfd_gpio_get_multiple; + gc->set = mcp251xfd_gpio_set; + gc->set_multiple = mcp251xfd_gpio_set_multiple; + gc->base = -1; + gc->can_sleep = true; + gc->ngpio = ARRAY_SIZE(mcp251xfd_gpio_names); + gc->names = mcp251xfd_gpio_names; + + return devm_gpiochip_add_data(&priv->spi->dev, gc, priv); +} + static int mcp251xfd_register_get_dev_id(const struct mcp251xfd_priv *priv, u32 *dev_id, u32 *effective_speed_hz_slow, @@ -1907,53 +2050,59 @@ static int mcp251xfd_register(struct mcp251xfd_priv *priv) struct net_device *ndev = priv->ndev; int err; + mcp251xfd_register_quirks(priv); + err = mcp251xfd_clks_and_vdd_enable(priv); if (err) return err; - pm_runtime_get_noresume(ndev->dev.parent); - err = pm_runtime_set_active(ndev->dev.parent); - if (err) - goto out_runtime_put_noidle; - pm_runtime_enable(ndev->dev.parent); - - mcp251xfd_register_quirks(priv); - err = mcp251xfd_chip_softreset(priv); if (err == -ENODEV) - goto out_runtime_disable; + goto out_clks_and_vdd_disable; if (err) goto out_chip_sleep; err = mcp251xfd_chip_clock_init(priv); if (err == -ENODEV) - goto out_runtime_disable; + goto out_clks_and_vdd_disable; if (err) goto out_chip_sleep; + pm_runtime_get_noresume(ndev->dev.parent); + err = pm_runtime_set_active(ndev->dev.parent); + if (err) + goto out_runtime_put_noidle; + pm_runtime_enable(ndev->dev.parent); + err = mcp251xfd_register_chip_detect(priv); if (err) - goto out_chip_sleep; + goto out_runtime_disable; err = mcp251xfd_register_check_rx_int(priv); if (err) - goto out_chip_sleep; + goto out_runtime_disable; mcp251xfd_ethtool_init(priv); + err = mcp251fdx_gpio_setup(priv); + if (err) { + dev_err_probe(&priv->spi->dev, err, "Failed to register gpio-controller.\n"); + goto out_runtime_disable; + } + err = register_candev(ndev); if (err) - goto out_chip_sleep; + goto out_runtime_disable; err = mcp251xfd_register_done(priv); if (err) goto out_unregister_candev; - /* Put controller into sleep mode and let pm_runtime_put() - * disable the clocks and vdd. If CONFIG_PM is not enabled, - * the clocks and vdd will stay powered. + /* Put controller into Config mode and let pm_runtime_put() + * put in sleep mode, disable the clocks and vdd. If CONFIG_PM + * is not enabled, the clocks and vdd will stay powered. */ - err = mcp251xfd_chip_sleep(priv); + err = mcp251xfd_chip_set_mode(priv, MCP251XFD_REG_CON_MODE_CONFIG); if (err) goto out_unregister_candev; @@ -1963,12 +2112,13 @@ static int mcp251xfd_register(struct mcp251xfd_priv *priv) out_unregister_candev: unregister_candev(ndev); -out_chip_sleep: - mcp251xfd_chip_sleep(priv); out_runtime_disable: pm_runtime_disable(ndev->dev.parent); out_runtime_put_noidle: pm_runtime_put_noidle(ndev->dev.parent); +out_chip_sleep: + mcp251xfd_chip_sleep(priv); +out_clks_and_vdd_disable: mcp251xfd_clks_and_vdd_disable(priv); return err; @@ -1980,10 +2130,12 @@ static inline void mcp251xfd_unregister(struct mcp251xfd_priv *priv) unregister_candev(ndev); - if (pm_runtime_enabled(ndev->dev.parent)) + if (pm_runtime_enabled(ndev->dev.parent)) { pm_runtime_disable(ndev->dev.parent); - else + } else { + mcp251xfd_chip_sleep(priv); mcp251xfd_clks_and_vdd_disable(priv); + } } static const struct of_device_id mcp251xfd_of_match[] = { @@ -2206,16 +2358,41 @@ static void mcp251xfd_remove(struct spi_device *spi) static int __maybe_unused mcp251xfd_runtime_suspend(struct device *device) { - const struct mcp251xfd_priv *priv = dev_get_drvdata(device); + struct mcp251xfd_priv *priv = dev_get_drvdata(device); + mcp251xfd_chip_sleep(priv); return mcp251xfd_clks_and_vdd_disable(priv); } static int __maybe_unused mcp251xfd_runtime_resume(struct device *device) { - const struct mcp251xfd_priv *priv = dev_get_drvdata(device); + struct mcp251xfd_priv *priv = dev_get_drvdata(device); + int err; + + err = mcp251xfd_clks_and_vdd_enable(priv); + if (err) + return err; - return mcp251xfd_clks_and_vdd_enable(priv); + err = mcp251xfd_chip_softreset(priv); + if (err == -ENODEV) + goto out_clks_and_vdd_disable; + if (err) + goto out_chip_sleep; + + err = mcp251xfd_chip_clock_init(priv); + if (err == -ENODEV) + goto out_clks_and_vdd_disable; + if (err) + goto out_chip_sleep; + + return 0; + +out_chip_sleep: + mcp251xfd_chip_sleep(priv); +out_clks_and_vdd_disable: + mcp251xfd_clks_and_vdd_disable(priv); + + return err; } static const struct dev_pm_ops mcp251xfd_pm_ops = { diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c index 8c5be8d1c5196..70d5ff0ae7acb 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c @@ -13,17 +13,9 @@ static const struct regmap_config mcp251xfd_regmap_crc; static int -mcp251xfd_regmap_nocrc_write(void *context, const void *data, size_t count) -{ - struct spi_device *spi = context; - - return spi_write(spi, data, count); -} - -static int -mcp251xfd_regmap_nocrc_gather_write(void *context, - const void *reg, size_t reg_len, - const void *val, size_t val_len) +_mcp251xfd_regmap_nocrc_gather_write(void *context, + const void *reg, size_t reg_len, + const void *val, size_t val_len) { struct spi_device *spi = context; struct mcp251xfd_priv *priv = spi_get_drvdata(spi); @@ -47,6 +39,54 @@ mcp251xfd_regmap_nocrc_gather_write(void *context, return spi_sync_transfer(spi, xfer, ARRAY_SIZE(xfer)); } +static int +mcp251xfd_regmap_nocrc_gather_write(void *context, + const void *reg_p, size_t reg_len, + const void *val, size_t val_len) +{ + const u16 byte_exclude = MCP251XFD_REG_IOCON + + mcp251xfd_first_byte_set(MCP251XFD_REG_IOCON_GPIO_MASK); + u16 reg = be16_to_cpu(*(__be16 *)reg_p) & MCP251XFD_SPI_ADDRESS_MASK; + int ret; + + /* Never write to bits 16..23 of IOCON register to avoid clearing of LAT0/LAT1 + * + * According to MCP2518FD Errata DS80000789E 5 writing IOCON register using one + * SPI write command clears LAT0/LAT1. + * + * Errata Fix/Work Around suggests to write registers with single byte + * write instructions. However, it seems that the byte at 0xe06(IOCON[23:16]) + * is for read-only access and writing to it causes the clearing of LAT0/LAT1. + */ + if (reg <= byte_exclude && reg + val_len > byte_exclude) { + size_t len = byte_exclude - reg; + + /* Write up to 0xe05 */ + ret = _mcp251xfd_regmap_nocrc_gather_write(context, reg_p, reg_len, val, len); + if (ret) + return ret; + + /* Write from 0xe07 on */ + reg += len + 1; + reg = (__force unsigned short)cpu_to_be16(MCP251XFD_SPI_INSTRUCTION_WRITE | reg); + return _mcp251xfd_regmap_nocrc_gather_write(context, ®, reg_len, + val + len + 1, + val_len - len - 1); + } + + return _mcp251xfd_regmap_nocrc_gather_write(context, reg_p, reg_len, + val, val_len); +} + +static int +mcp251xfd_regmap_nocrc_write(void *context, const void *data, size_t count) +{ + const size_t data_offset = sizeof(__be16); + + return mcp251xfd_regmap_nocrc_gather_write(context, data, data_offset, + data + data_offset, count - data_offset); +} + static inline bool mcp251xfd_update_bits_read_reg(const struct mcp251xfd_priv *priv, unsigned int reg) @@ -64,6 +104,7 @@ mcp251xfd_update_bits_read_reg(const struct mcp251xfd_priv *priv, case MCP251XFD_REG_CON: case MCP251XFD_REG_OSC: case MCP251XFD_REG_ECCCON: + case MCP251XFD_REG_IOCON: return true; default: mcp251xfd_for_each_rx_ring(priv, ring, n) { @@ -139,10 +180,9 @@ mcp251xfd_regmap_nocrc_update_bits(void *context, unsigned int reg, tmp_le32 = orig_le32 & ~mask_le32; tmp_le32 |= val_le32 & mask_le32; - mcp251xfd_spi_cmd_write_nocrc(&buf_tx->cmd, reg + first_byte); - memcpy(buf_tx->data, &tmp_le32, len); - - return spi_write(spi, buf_tx, sizeof(buf_tx->cmd) + len); + reg += first_byte; + mcp251xfd_spi_cmd_write_nocrc(&buf_tx->cmd, reg); + return mcp251xfd_regmap_nocrc_gather_write(context, &buf_tx->cmd, 2, &tmp_le32, len); } static int @@ -196,9 +236,9 @@ mcp251xfd_regmap_nocrc_read(void *context, } static int -mcp251xfd_regmap_crc_gather_write(void *context, - const void *reg_p, size_t reg_len, - const void *val, size_t val_len) +_mcp251xfd_regmap_crc_gather_write(void *context, + const void *reg_p, size_t reg_len, + const void *val, size_t val_len) { struct spi_device *spi = context; struct mcp251xfd_priv *priv = spi_get_drvdata(spi); @@ -229,6 +269,44 @@ mcp251xfd_regmap_crc_gather_write(void *context, return spi_sync_transfer(spi, xfer, ARRAY_SIZE(xfer)); } +static int +mcp251xfd_regmap_crc_gather_write(void *context, + const void *reg_p, size_t reg_len, + const void *val, size_t val_len) +{ + const u16 byte_exclude = MCP251XFD_REG_IOCON + + mcp251xfd_first_byte_set(MCP251XFD_REG_IOCON_GPIO_MASK); + u16 reg = *(u16 *)reg_p; + int ret; + + /* Never write to bits 16..23 of IOCON register to avoid clearing of LAT0/LAT1 + * + * According to MCP2518FD Errata DS80000789E 5 writing IOCON register using one + * SPI write command clears LAT0/LAT1. + * + * Errata Fix/Work Around suggests to write registers with single byte + * write instructions. However, it seems that the byte at 0xe06(IOCON[23:16]) + * is for read-only access and writing to it causes the clearing of LAT0/LAT1. + */ + if (reg <= byte_exclude && reg + val_len > byte_exclude) { + size_t len = byte_exclude - reg; + + /* Write up to 0xe05 */ + ret = _mcp251xfd_regmap_crc_gather_write(context, ®, reg_len, val, len); + if (ret) + return ret; + + /* Write from 0xe07 on */ + reg += len + 1; + return _mcp251xfd_regmap_crc_gather_write(context, ®, reg_len, + val + len + 1, + val_len - len - 1); + } + + return _mcp251xfd_regmap_crc_gather_write(context, reg_p, reg_len, + val, val_len); +} + static int mcp251xfd_regmap_crc_write(void *context, const void *data, size_t count) diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index dcbbd2b2fae82..085d7101e595e 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -15,6 +15,7 @@ #include #include #include +#include #include #include #include @@ -335,13 +336,19 @@ #define MCP251XFD_REG_IOCON_TXCANOD BIT(28) #define MCP251XFD_REG_IOCON_PM1 BIT(25) #define MCP251XFD_REG_IOCON_PM0 BIT(24) +#define MCP251XFD_REG_IOCON_PM(n) (MCP251XFD_REG_IOCON_PM0 << (n)) #define MCP251XFD_REG_IOCON_GPIO1 BIT(17) #define MCP251XFD_REG_IOCON_GPIO0 BIT(16) +#define MCP251XFD_REG_IOCON_GPIO(n) (MCP251XFD_REG_IOCON_GPIO0 << (n)) +#define MCP251XFD_REG_IOCON_GPIO_MASK GENMASK(17, 16) #define MCP251XFD_REG_IOCON_LAT1 BIT(9) #define MCP251XFD_REG_IOCON_LAT0 BIT(8) +#define MCP251XFD_REG_IOCON_LAT(n) (MCP251XFD_REG_IOCON_LAT0 << (n)) +#define MCP251XFD_REG_IOCON_LAT_MASK GENMASK(9, 8) #define MCP251XFD_REG_IOCON_XSTBYEN BIT(6) #define MCP251XFD_REG_IOCON_TRIS1 BIT(1) #define MCP251XFD_REG_IOCON_TRIS0 BIT(0) +#define MCP251XFD_REG_IOCON_TRIS(n) (MCP251XFD_REG_IOCON_TRIS0 << (n)) #define MCP251XFD_REG_CRC 0xe08 #define MCP251XFD_REG_CRC_FERRIE BIT(25) @@ -670,6 +677,7 @@ struct mcp251xfd_priv { struct mcp251xfd_devtype_data devtype_data; struct can_berr_counter bec; + struct gpio_chip gc; }; #define MCP251XFD_IS(_model) \ diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c index 53bfd873de9bd..6fcb301ef611d 100644 --- a/drivers/net/can/sun4i_can.c +++ b/drivers/net/can/sun4i_can.c @@ -768,7 +768,6 @@ static const struct net_device_ops sun4ican_netdev_ops = { .ndo_open = sun4ican_open, .ndo_stop = sun4ican_close, .ndo_start_xmit = sun4ican_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops sun4ican_ethtool_ops = { diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c index e6d6661a908ab..1d3dbf28b1057 100644 --- a/drivers/net/can/ti_hecc.c +++ b/drivers/net/can/ti_hecc.c @@ -829,7 +829,6 @@ static const struct net_device_ops ti_hecc_netdev_ops = { .ndo_open = ti_hecc_open, .ndo_stop = ti_hecc_close, .ndo_start_xmit = ti_hecc_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops ti_hecc_ethtool_ops = { diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c index 5355bac4dccbe..de8e212a1366b 100644 --- a/drivers/net/can/usb/ems_usb.c +++ b/drivers/net/can/usb/ems_usb.c @@ -885,7 +885,6 @@ static const struct net_device_ops ems_usb_netdev_ops = { .ndo_open = ems_usb_open, .ndo_stop = ems_usb_close, .ndo_start_xmit = ems_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops ems_usb_ethtool_ops = { diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c index 9bc1824d7be6a..08da507faef4a 100644 --- a/drivers/net/can/usb/esd_usb.c +++ b/drivers/net/can/usb/esd_usb.c @@ -1011,7 +1011,6 @@ static const struct net_device_ops esd_usb_netdev_ops = { .ndo_open = esd_usb_open, .ndo_stop = esd_usb_close, .ndo_start_xmit = esd_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops esd_usb_ethtool_ops = { diff --git a/drivers/net/can/usb/etas_es58x/es58x_core.c b/drivers/net/can/usb/etas_es58x/es58x_core.c index adc91873c083f..f799233c2b72c 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_core.c +++ b/drivers/net/can/usb/etas_es58x/es58x_core.c @@ -1976,8 +1976,8 @@ static const struct net_device_ops es58x_netdev_ops = { .ndo_open = es58x_open, .ndo_stop = es58x_stop, .ndo_start_xmit = es58x_start_xmit, - .ndo_eth_ioctl = can_eth_ioctl_hwts, - .ndo_change_mtu = can_change_mtu, + .ndo_hwtstamp_get = can_hwtstamp_get, + .ndo_hwtstamp_set = can_hwtstamp_set, }; static const struct ethtool_ops es58x_ethtool_ops = { diff --git a/drivers/net/can/usb/f81604.c b/drivers/net/can/usb/f81604.c index e0cfa1460b0b8..efe61ece79ea2 100644 --- a/drivers/net/can/usb/f81604.c +++ b/drivers/net/can/usb/f81604.c @@ -1052,7 +1052,6 @@ static const struct net_device_ops f81604_netdev_ops = { .ndo_open = f81604_open, .ndo_stop = f81604_close, .ndo_start_xmit = f81604_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct can_bittiming_const f81604_bittiming_const = { diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index 69b8d6da651bf..1321eb5e89ae5 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -1087,12 +1087,25 @@ static int gs_can_close(struct net_device *netdev) return 0; } -static int gs_can_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int gs_can_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg) { const struct gs_can *dev = netdev_priv(netdev); if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) - return can_eth_ioctl_hwts(netdev, ifr, cmd); + return can_hwtstamp_get(netdev, cfg); + + return -EOPNOTSUPP; +} + +static int gs_can_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) +{ + const struct gs_can *dev = netdev_priv(netdev); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + return can_hwtstamp_set(netdev, cfg, extack); return -EOPNOTSUPP; } @@ -1101,8 +1114,8 @@ static const struct net_device_ops gs_usb_netdev_ops = { .ndo_open = gs_can_open, .ndo_stop = gs_can_close, .ndo_start_xmit = gs_can_start_xmit, - .ndo_change_mtu = can_change_mtu, - .ndo_eth_ioctl = gs_can_eth_ioctl, + .ndo_hwtstamp_get = gs_can_hwtstamp_get, + .ndo_hwtstamp_set = gs_can_hwtstamp_set, }; static int gs_usb_set_identify(struct net_device *netdev, bool do_identify) diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c index 90e77fa0ff4a5..62701ec34272d 100644 --- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c +++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c @@ -784,9 +784,9 @@ static int kvaser_usb_set_phys_id(struct net_device *netdev, static const struct net_device_ops kvaser_usb_netdev_ops = { .ndo_open = kvaser_usb_open, .ndo_stop = kvaser_usb_close, - .ndo_eth_ioctl = can_eth_ioctl_hwts, .ndo_start_xmit = kvaser_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, + .ndo_hwtstamp_get = can_hwtstamp_get, + .ndo_hwtstamp_set = can_hwtstamp_set, }; static const struct ethtool_ops kvaser_usb_ethtool_ops = { diff --git a/drivers/net/can/usb/mcba_usb.c b/drivers/net/can/usb/mcba_usb.c index 1f9b915094e64..41c0a1c399bf3 100644 --- a/drivers/net/can/usb/mcba_usb.c +++ b/drivers/net/can/usb/mcba_usb.c @@ -761,7 +761,6 @@ static const struct net_device_ops mcba_netdev_ops = { .ndo_open = mcba_usb_open, .ndo_stop = mcba_usb_close, .ndo_start_xmit = mcba_usb_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops mcba_ethtool_ops = { diff --git a/drivers/net/can/usb/nct6694_canfd.c b/drivers/net/can/usb/nct6694_canfd.c index 8deff16491a1a..dd6df2ec3742e 100644 --- a/drivers/net/can/usb/nct6694_canfd.c +++ b/drivers/net/can/usb/nct6694_canfd.c @@ -690,7 +690,6 @@ static const struct net_device_ops nct6694_canfd_netdev_ops = { .ndo_open = nct6694_canfd_open, .ndo_stop = nct6694_canfd_close, .ndo_start_xmit = nct6694_canfd_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops nct6694_canfd_ethtool_ops = { diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c index c74302ca7cee9..cf48bb26d46d2 100644 --- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c +++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c @@ -784,37 +784,33 @@ static int peak_usb_set_data_bittiming(struct net_device *netdev) return 0; } -static int peak_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int peak_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - struct hwtstamp_config hwts_cfg = { 0 }; - - switch (cmd) { - case SIOCSHWTSTAMP: /* set */ - if (copy_from_user(&hwts_cfg, ifr->ifr_data, sizeof(hwts_cfg))) - return -EFAULT; - if (hwts_cfg.tx_type == HWTSTAMP_TX_OFF && - hwts_cfg.rx_filter == HWTSTAMP_FILTER_ALL) - return 0; - return -ERANGE; - - case SIOCGHWTSTAMP: /* get */ - hwts_cfg.tx_type = HWTSTAMP_TX_OFF; - hwts_cfg.rx_filter = HWTSTAMP_FILTER_ALL; - if (copy_to_user(ifr->ifr_data, &hwts_cfg, sizeof(hwts_cfg))) - return -EFAULT; + config->tx_type = HWTSTAMP_TX_OFF; + config->rx_filter = HWTSTAMP_FILTER_ALL; + + return 0; +} + +static int peak_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + if (config->tx_type == HWTSTAMP_TX_OFF && + config->rx_filter == HWTSTAMP_FILTER_ALL) return 0; - default: - return -EOPNOTSUPP; - } + NL_SET_ERR_MSG_MOD(extack, "Only RX HWTSTAMP_FILTER_ALL is supported"); + return -ERANGE; } static const struct net_device_ops peak_usb_netdev_ops = { .ndo_open = peak_usb_ndo_open, .ndo_stop = peak_usb_ndo_stop, - .ndo_eth_ioctl = peak_eth_ioctl, .ndo_start_xmit = peak_usb_ndo_start_xmit, - .ndo_change_mtu = can_change_mtu, + .ndo_hwtstamp_get = peak_hwtstamp_get, + .ndo_hwtstamp_set = peak_hwtstamp_set, }; /* CAN-USB devices generally handle 32-bit CAN channel IDs. diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c index 07406daf7c88e..de61d9da99e35 100644 --- a/drivers/net/can/usb/ucan.c +++ b/drivers/net/can/usb/ucan.c @@ -1233,7 +1233,6 @@ static const struct net_device_ops ucan_netdev_ops = { .ndo_open = ucan_open, .ndo_stop = ucan_close, .ndo_start_xmit = ucan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops ucan_ethtool_ops = { diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c index 8a5596ce4e463..7449328f7cd72 100644 --- a/drivers/net/can/usb/usb_8dev.c +++ b/drivers/net/can/usb/usb_8dev.c @@ -868,7 +868,6 @@ static const struct net_device_ops usb_8dev_netdev_ops = { .ndo_open = usb_8dev_open, .ndo_stop = usb_8dev_close, .ndo_start_xmit = usb_8dev_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops usb_8dev_ethtool_ops = { diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index a25a3ca62c12e..43d7f22820b88 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -1702,7 +1702,6 @@ static const struct net_device_ops xcan_netdev_ops = { .ndo_open = xcan_open, .ndo_stop = xcan_close, .ndo_start_xmit = xcan_start_xmit, - .ndo_change_mtu = can_change_mtu, }; static const struct ethtool_ops xcan_ethtool_ops = { diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig index 4d9af691b9896..7eb301fd987d1 100644 --- a/drivers/net/dsa/Kconfig +++ b/drivers/net/dsa/Kconfig @@ -154,4 +154,11 @@ config NET_DSA_VITESSE_VSC73XX_PLATFORM This enables support for the Vitesse VSC7385, VSC7388, VSC7395 and VSC7398 SparX integrated ethernet switches, connected over a CPU-attached address bus and work in memory-mapped I/O mode. + +config NET_DSA_YT921X + tristate "Motorcomm YT9215 ethernet switch chip support" + select NET_DSA_TAG_YT921X + help + This enables support for the Motorcomm YT9215 ethernet switch + chip. endmenu diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile index 0f8ff4a1a313b..16de4ba3fa388 100644 --- a/drivers/net/dsa/Makefile +++ b/drivers/net/dsa/Makefile @@ -14,6 +14,7 @@ obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx-core.o obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM) += vitesse-vsc73xx-platform.o obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o +obj-$(CONFIG_NET_DSA_YT921X) += yt921x.o obj-y += b53/ obj-y += hirschmann/ obj-y += lantiq/ diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index eb767edc4c135..72c85cd34a4ee 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -632,6 +632,25 @@ static void b53_port_set_learning(struct b53_device *dev, int port, b53_write16(dev, B53_CTRL_PAGE, B53_DIS_LEARNING, reg); } +static void b53_port_set_isolated(struct b53_device *dev, int port, + bool isolated) +{ + u8 offset; + u16 reg; + + if (is5325(dev)) + offset = B53_PROTECTED_PORT_SEL_25; + else + offset = B53_PROTECTED_PORT_SEL; + + b53_read16(dev, B53_CTRL_PAGE, offset, ®); + if (isolated) + reg |= BIT(port); + else + reg &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, offset, reg); +} + static void b53_eee_enable_set(struct dsa_switch *ds, int port, bool enable) { struct b53_device *dev = ds->priv; @@ -652,6 +671,7 @@ int b53_setup_port(struct dsa_switch *ds, int port) b53_port_set_ucast_flood(dev, port, true); b53_port_set_mcast_flood(dev, port, true); b53_port_set_learning(dev, port, false); + b53_port_set_isolated(dev, port, false); /* Force all traffic to go to the CPU port to prevent the ASIC from * trying to forward to bridged ports on matching FDB entries, then @@ -1830,49 +1850,78 @@ static int b53_arl_rw_op(struct b53_device *dev, unsigned int op) return b53_arl_op_wait(dev); } -static int b53_arl_read(struct b53_device *dev, u64 mac, - u16 vid, struct b53_arl_entry *ent, u8 *idx) +static void b53_arl_read_entry_25(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) { - DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES); - unsigned int i; - int ret; + u64 mac_vid; - ret = b53_arl_op_wait(dev); - if (ret) - return ret; + b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + &mac_vid); + b53_arl_to_entry_25(ent, mac_vid); +} - bitmap_zero(free_bins, dev->num_arl_bins); +static void b53_arl_write_entry_25(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + u64 mac_vid; - /* Read the bins */ - for (i = 0; i < dev->num_arl_bins; i++) { - u64 mac_vid; - u32 fwd_entry; + b53_arl_from_entry_25(&mac_vid, ent); + b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + mac_vid); +} - b53_read64(dev, B53_ARLIO_PAGE, - B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid); - b53_read32(dev, B53_ARLIO_PAGE, - B53_ARLTBL_DATA_ENTRY(i), &fwd_entry); - b53_arl_to_entry(ent, mac_vid, fwd_entry); +static void b53_arl_read_entry_89(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) +{ + u64 mac_vid; + u16 fwd_entry; - if (!(fwd_entry & ARLTBL_VALID)) { - set_bit(i, free_bins); - continue; - } - if ((mac_vid & ARLTBL_MAC_MASK) != mac) - continue; - if (dev->vlan_enabled && - ((mac_vid >> ARLTBL_VID_S) & ARLTBL_VID_MASK) != vid) - continue; - *idx = i; - return 0; - } + b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + &mac_vid); + b53_read16(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), &fwd_entry); + b53_arl_to_entry_89(ent, mac_vid, fwd_entry); +} - *idx = find_first_bit(free_bins, dev->num_arl_bins); - return *idx >= dev->num_arl_bins ? -ENOSPC : -ENOENT; +static void b53_arl_write_entry_89(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_arl_from_entry_89(&mac_vid, &fwd_entry, ent); + b53_write64(dev, B53_ARLIO_PAGE, + B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid); + b53_write16(dev, B53_ARLIO_PAGE, + B53_ARLTBL_DATA_ENTRY(idx), fwd_entry); } -static int b53_arl_read_25(struct b53_device *dev, u64 mac, - u16 vid, struct b53_arl_entry *ent, u8 *idx) +static void b53_arl_read_entry_95(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + &mac_vid); + b53_read32(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), &fwd_entry); + b53_arl_to_entry(ent, mac_vid, fwd_entry); +} + +static void b53_arl_write_entry_95(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_arl_from_entry(&mac_vid, &fwd_entry, ent); + b53_write64(dev, B53_ARLIO_PAGE, B53_ARLTBL_MAC_VID_ENTRY(idx), + mac_vid); + b53_write32(dev, B53_ARLIO_PAGE, B53_ARLTBL_DATA_ENTRY(idx), + fwd_entry); +} + +static int b53_arl_read(struct b53_device *dev, const u8 *mac, + u16 vid, struct b53_arl_entry *ent, u8 *idx) { DECLARE_BITMAP(free_bins, B53_ARLTBL_MAX_BIN_ENTRIES); unsigned int i; @@ -1886,21 +1935,15 @@ static int b53_arl_read_25(struct b53_device *dev, u64 mac, /* Read the bins */ for (i = 0; i < dev->num_arl_bins; i++) { - u64 mac_vid; - - b53_read64(dev, B53_ARLIO_PAGE, - B53_ARLTBL_MAC_VID_ENTRY(i), &mac_vid); + b53_arl_read_entry(dev, ent, i); - b53_arl_to_entry_25(ent, mac_vid); - - if (!(mac_vid & ARLTBL_VALID_25)) { + if (!ent->is_valid) { set_bit(i, free_bins); continue; } - if ((mac_vid & ARLTBL_MAC_MASK) != mac) + if (!ether_addr_equal(ent->mac, mac)) continue; - if (dev->vlan_enabled && - ((mac_vid >> ARLTBL_VID_S_65) & ARLTBL_VID_MASK_25) != vid) + if (dev->vlan_enabled && ent->vid != vid) continue; *idx = i; return 0; @@ -1914,9 +1957,8 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, const unsigned char *addr, u16 vid, bool is_valid) { struct b53_arl_entry ent; - u32 fwd_entry; - u64 mac, mac_vid = 0; u8 idx = 0; + u64 mac; int ret; /* Convert the array into a 64-bit MAC */ @@ -1932,10 +1974,7 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, if (ret) return ret; - if (is5325(dev) || is5365(dev)) - ret = b53_arl_read_25(dev, mac, vid, &ent, &idx); - else - ret = b53_arl_read(dev, mac, vid, &ent, &idx); + ret = b53_arl_read(dev, addr, vid, &ent, &idx); /* If this is a read, just finish now */ if (op) @@ -1952,7 +1991,6 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, /* We could not find a matching MAC, so reset to a new entry */ dev_dbg(dev->dev, "{%pM,%.4d} not found, using idx: %d\n", addr, vid, idx); - fwd_entry = 0; break; default: dev_dbg(dev->dev, "{%pM,%.4d} found, using idx: %d\n", @@ -1979,17 +2017,7 @@ static int b53_arl_op(struct b53_device *dev, int op, int port, ent.is_static = true; ent.is_age = false; memcpy(ent.mac, addr, ETH_ALEN); - if (is5325(dev) || is5365(dev)) - b53_arl_from_entry_25(&mac_vid, &ent); - else - b53_arl_from_entry(&mac_vid, &fwd_entry, &ent); - - b53_write64(dev, B53_ARLIO_PAGE, - B53_ARLTBL_MAC_VID_ENTRY(idx), mac_vid); - - if (!is5325(dev) && !is5365(dev)) - b53_write32(dev, B53_ARLIO_PAGE, - B53_ARLTBL_DATA_ENTRY(idx), fwd_entry); + b53_arl_write_entry(dev, &ent, idx); return b53_arl_rw_op(dev, 0); } @@ -2024,18 +2052,53 @@ int b53_fdb_del(struct dsa_switch *ds, int port, } EXPORT_SYMBOL(b53_fdb_del); -static int b53_arl_search_wait(struct b53_device *dev) +static void b53_read_arl_srch_ctl(struct b53_device *dev, u8 *val) { - unsigned int timeout = 1000; - u8 reg, offset; + u8 offset; + + if (is5325(dev) || is5365(dev)) + offset = B53_ARL_SRCH_CTL_25; + else if (dev->chip_id == BCM5389_DEVICE_ID || is5397_98(dev) || + is63xx(dev)) + offset = B53_ARL_SRCH_CTL_89; + else + offset = B53_ARL_SRCH_CTL; + + if (is63xx(dev)) { + u16 val16; + + b53_read16(dev, B53_ARLIO_PAGE, offset, &val16); + *val = val16 & 0xff; + } else { + b53_read8(dev, B53_ARLIO_PAGE, offset, val); + } +} + +static void b53_write_arl_srch_ctl(struct b53_device *dev, u8 val) +{ + u8 offset; if (is5325(dev) || is5365(dev)) offset = B53_ARL_SRCH_CTL_25; + else if (dev->chip_id == BCM5389_DEVICE_ID || is5397_98(dev) || + is63xx(dev)) + offset = B53_ARL_SRCH_CTL_89; else offset = B53_ARL_SRCH_CTL; + if (is63xx(dev)) + b53_write16(dev, B53_ARLIO_PAGE, offset, val); + else + b53_write8(dev, B53_ARLIO_PAGE, offset, val); +} + +static int b53_arl_search_wait(struct b53_device *dev) +{ + unsigned int timeout = 1000; + u8 reg; + do { - b53_read8(dev, B53_ARLIO_PAGE, offset, ®); + b53_read_arl_srch_ctl(dev, ®); if (!(reg & ARL_SRCH_STDN)) return -ENOENT; @@ -2048,28 +2111,61 @@ static int b53_arl_search_wait(struct b53_device *dev) return -ETIMEDOUT; } -static void b53_arl_search_rd(struct b53_device *dev, u8 idx, - struct b53_arl_entry *ent) +static void b53_arl_search_read_25(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) { u64 mac_vid; - if (is5325(dev)) { - b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_25, - &mac_vid); - b53_arl_to_entry_25(ent, mac_vid); - } else if (is5365(dev)) { - b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_65, - &mac_vid); - b53_arl_to_entry_25(ent, mac_vid); - } else { - u32 fwd_entry; + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_25, + &mac_vid); + b53_arl_to_entry_25(ent, mac_vid); +} - b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_MACVID(idx), - &mac_vid); - b53_read32(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL(idx), - &fwd_entry); - b53_arl_to_entry(ent, mac_vid, fwd_entry); - } +static void b53_arl_search_read_65(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_0_MACVID_65, + &mac_vid); + b53_arl_to_entry_25(ent, mac_vid); +} + +static void b53_arl_search_read_89(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u16 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_MACVID_89, + &mac_vid); + b53_read16(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_89, &fwd_entry); + b53_arl_to_entry_89(ent, mac_vid, fwd_entry); +} + +static void b53_arl_search_read_63xx(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u16 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_MACVID_63XX, + &mac_vid); + b53_read16(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSLT_63XX, &fwd_entry); + b53_arl_search_to_entry_63xx(ent, mac_vid, fwd_entry); +} + +static void b53_arl_search_read_95(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + u32 fwd_entry; + u64 mac_vid; + + b53_read64(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL_MACVID(idx), + &mac_vid); + b53_read32(dev, B53_ARLIO_PAGE, B53_ARL_SRCH_RSTL(idx), + &fwd_entry); + b53_arl_to_entry(ent, mac_vid, fwd_entry); } static int b53_fdb_copy(int port, const struct b53_arl_entry *ent, @@ -2090,36 +2186,28 @@ int b53_fdb_dump(struct dsa_switch *ds, int port, unsigned int count = 0, results_per_hit = 1; struct b53_device *priv = ds->priv; struct b53_arl_entry results[2]; - u8 offset; int ret; - u8 reg; if (priv->num_arl_bins > 2) results_per_hit = 2; mutex_lock(&priv->arl_mutex); - if (is5325(priv) || is5365(priv)) - offset = B53_ARL_SRCH_CTL_25; - else - offset = B53_ARL_SRCH_CTL; - /* Start search operation */ - reg = ARL_SRCH_STDN; - b53_write8(priv, B53_ARLIO_PAGE, offset, reg); + b53_write_arl_srch_ctl(priv, ARL_SRCH_STDN); do { ret = b53_arl_search_wait(priv); if (ret) break; - b53_arl_search_rd(priv, 0, &results[0]); + b53_arl_search_read(priv, 0, &results[0]); ret = b53_fdb_copy(port, &results[0], cb, data); if (ret) break; if (results_per_hit == 2) { - b53_arl_search_rd(priv, 1, &results[1]); + b53_arl_search_read(priv, 1, &results[1]); ret = b53_fdb_copy(port, &results[1], cb, data); if (ret) break; @@ -2340,7 +2428,7 @@ int b53_br_flags_pre(struct dsa_switch *ds, int port, struct netlink_ext_ack *extack) { struct b53_device *dev = ds->priv; - unsigned long mask = (BR_FLOOD | BR_MCAST_FLOOD); + unsigned long mask = (BR_FLOOD | BR_MCAST_FLOOD | BR_ISOLATED); if (!is5325(dev)) mask |= BR_LEARNING; @@ -2365,6 +2453,9 @@ int b53_br_flags(struct dsa_switch *ds, int port, if (flags.mask & BR_LEARNING) b53_port_set_learning(ds->priv, port, !!(flags.val & BR_LEARNING)); + if (flags.mask & BR_ISOLATED) + b53_port_set_isolated(ds->priv, port, + !!(flags.val & BR_ISOLATED)); return 0; } @@ -2645,6 +2736,36 @@ static const struct dsa_switch_ops b53_switch_ops = { .port_change_mtu = b53_change_mtu, }; +static const struct b53_arl_ops b53_arl_ops_25 = { + .arl_read_entry = b53_arl_read_entry_25, + .arl_write_entry = b53_arl_write_entry_25, + .arl_search_read = b53_arl_search_read_25, +}; + +static const struct b53_arl_ops b53_arl_ops_65 = { + .arl_read_entry = b53_arl_read_entry_25, + .arl_write_entry = b53_arl_write_entry_25, + .arl_search_read = b53_arl_search_read_65, +}; + +static const struct b53_arl_ops b53_arl_ops_89 = { + .arl_read_entry = b53_arl_read_entry_89, + .arl_write_entry = b53_arl_write_entry_89, + .arl_search_read = b53_arl_search_read_89, +}; + +static const struct b53_arl_ops b53_arl_ops_63xx = { + .arl_read_entry = b53_arl_read_entry_89, + .arl_write_entry = b53_arl_write_entry_89, + .arl_search_read = b53_arl_search_read_63xx, +}; + +static const struct b53_arl_ops b53_arl_ops_95 = { + .arl_read_entry = b53_arl_read_entry_95, + .arl_write_entry = b53_arl_write_entry_95, + .arl_search_read = b53_arl_search_read_95, +}; + struct b53_chip_data { u32 chip_id; const char *dev_name; @@ -2658,6 +2779,7 @@ struct b53_chip_data { u8 duplex_reg; u8 jumbo_pm_reg; u8 jumbo_size_reg; + const struct b53_arl_ops *arl_ops; }; #define B53_VTA_REGS \ @@ -2677,6 +2799,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_buckets = 1024, .imp_port = 5, .duplex_reg = B53_DUPLEX_STAT_FE, + .arl_ops = &b53_arl_ops_25, }, { .chip_id = BCM5365_DEVICE_ID, @@ -2687,6 +2810,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .arl_buckets = 1024, .imp_port = 5, .duplex_reg = B53_DUPLEX_STAT_FE, + .arl_ops = &b53_arl_ops_65, }, { .chip_id = BCM5389_DEVICE_ID, @@ -2700,6 +2824,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_89, }, { .chip_id = BCM5395_DEVICE_ID, @@ -2713,6 +2838,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM5397_DEVICE_ID, @@ -2726,6 +2852,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_89, }, { .chip_id = BCM5398_DEVICE_ID, @@ -2739,6 +2866,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_89, }, { .chip_id = BCM53101_DEVICE_ID, @@ -2752,6 +2880,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53115_DEVICE_ID, @@ -2765,6 +2894,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53125_DEVICE_ID, @@ -2778,6 +2908,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53128_DEVICE_ID, @@ -2791,19 +2922,21 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM63XX_DEVICE_ID, .dev_name = "BCM63xx", .vlans = 4096, .enabled_ports = 0, /* pdata must provide them */ - .arl_bins = 4, - .arl_buckets = 1024, + .arl_bins = 1, + .arl_buckets = 4096, .imp_port = 8, .vta_regs = B53_VTA_REGS_63XX, .duplex_reg = B53_DUPLEX_STAT_63XX, .jumbo_pm_reg = B53_JUMBO_PORT_MASK_63XX, .jumbo_size_reg = B53_JUMBO_MAX_SIZE_63XX, + .arl_ops = &b53_arl_ops_63xx, }, { .chip_id = BCM53010_DEVICE_ID, @@ -2817,6 +2950,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53011_DEVICE_ID, @@ -2830,6 +2964,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53012_DEVICE_ID, @@ -2843,6 +2978,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53018_DEVICE_ID, @@ -2856,6 +2992,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53019_DEVICE_ID, @@ -2869,6 +3006,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM58XX_DEVICE_ID, @@ -2882,6 +3020,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM583XX_DEVICE_ID, @@ -2895,6 +3034,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, /* Starfighter 2 */ { @@ -2909,6 +3049,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM7445_DEVICE_ID, @@ -2922,6 +3063,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM7278_DEVICE_ID, @@ -2935,6 +3077,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, { .chip_id = BCM53134_DEVICE_ID, @@ -2949,6 +3092,7 @@ static const struct b53_chip_data b53_switch_chips[] = { .duplex_reg = B53_DUPLEX_STAT_GE, .jumbo_pm_reg = B53_JUMBO_PORT_MASK, .jumbo_size_reg = B53_JUMBO_MAX_SIZE, + .arl_ops = &b53_arl_ops_95, }, }; @@ -2977,6 +3121,7 @@ static int b53_switch_init(struct b53_device *dev) dev->num_vlans = chip->vlans; dev->num_arl_bins = chip->arl_bins; dev->num_arl_buckets = chip->arl_buckets; + dev->arl_ops = chip->arl_ops; break; } } diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 458775f951643..2bfd0e7c95c98 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -58,6 +58,17 @@ struct b53_io_ops { bool link_up); }; +struct b53_arl_entry; + +struct b53_arl_ops { + void (*arl_read_entry)(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx); + void (*arl_write_entry)(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx); + void (*arl_search_read)(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent); +}; + #define B53_INVALID_LANE 0xff enum { @@ -127,6 +138,7 @@ struct b53_device { struct mutex stats_mutex; struct mutex arl_mutex; const struct b53_io_ops *ops; + const struct b53_arl_ops *arl_ops; /* chip specific data */ u32 chip_id; @@ -341,6 +353,18 @@ static inline void b53_arl_to_entry_25(struct b53_arl_entry *ent, ent->vid = mac_vid >> ARLTBL_VID_S_65; } +static inline void b53_arl_to_entry_89(struct b53_arl_entry *ent, + u64 mac_vid, u16 fwd_entry) +{ + memset(ent, 0, sizeof(*ent)); + ent->port = fwd_entry & ARLTBL_DATA_PORT_ID_MASK_89; + ent->is_valid = !!(fwd_entry & ARLTBL_VALID_89); + ent->is_age = !!(fwd_entry & ARLTBL_AGE_89); + ent->is_static = !!(fwd_entry & ARLTBL_STATIC_89); + u64_to_ether_addr(mac_vid, ent->mac); + ent->vid = mac_vid >> ARLTBL_VID_S; +} + static inline void b53_arl_from_entry(u64 *mac_vid, u32 *fwd_entry, const struct b53_arl_entry *ent) { @@ -371,6 +395,53 @@ static inline void b53_arl_from_entry_25(u64 *mac_vid, *mac_vid |= ARLTBL_AGE_25; } +static inline void b53_arl_from_entry_89(u64 *mac_vid, u32 *fwd_entry, + const struct b53_arl_entry *ent) +{ + *mac_vid = ether_addr_to_u64(ent->mac); + *mac_vid |= (u64)(ent->vid & ARLTBL_VID_MASK) << ARLTBL_VID_S; + *fwd_entry = ent->port & ARLTBL_DATA_PORT_ID_MASK_89; + if (ent->is_valid) + *fwd_entry |= ARLTBL_VALID_89; + if (ent->is_static) + *fwd_entry |= ARLTBL_STATIC_89; + if (ent->is_age) + *fwd_entry |= ARLTBL_AGE_89; +} + +static inline void b53_arl_search_to_entry_63xx(struct b53_arl_entry *ent, + u64 mac_vid, u16 fwd_entry) +{ + memset(ent, 0, sizeof(*ent)); + u64_to_ether_addr(mac_vid, ent->mac); + ent->vid = mac_vid >> ARLTBL_VID_S; + + ent->port = fwd_entry & ARL_SRST_PORT_ID_MASK_63XX; + ent->port >>= 1; + + ent->is_age = !!(fwd_entry & ARL_SRST_AGE_63XX); + ent->is_static = !!(fwd_entry & ARL_SRST_STATIC_63XX); + ent->is_valid = 1; +} + +static inline void b53_arl_read_entry(struct b53_device *dev, + struct b53_arl_entry *ent, u8 idx) +{ + dev->arl_ops->arl_read_entry(dev, ent, idx); +} + +static inline void b53_arl_write_entry(struct b53_device *dev, + const struct b53_arl_entry *ent, u8 idx) +{ + dev->arl_ops->arl_write_entry(dev, ent, idx); +} + +static inline void b53_arl_search_read(struct b53_device *dev, u8 idx, + struct b53_arl_entry *ent) +{ + dev->arl_ops->arl_search_read(dev, idx, ent); +} + #ifdef CONFIG_BCM47XX #include diff --git a/drivers/net/dsa/b53/b53_regs.h b/drivers/net/dsa/b53/b53_regs.h index 8ce1ce72e9385..69ebbec932f65 100644 --- a/drivers/net/dsa/b53/b53_regs.h +++ b/drivers/net/dsa/b53/b53_regs.h @@ -119,6 +119,10 @@ #define B53_SWITCH_CTRL 0x22 #define B53_MII_DUMB_FWDG_EN BIT(6) +/* Protected Port Selection (16 bit) */ +#define B53_PROTECTED_PORT_SEL 0x24 +#define B53_PROTECTED_PORT_SEL_25 0x26 + /* (16 bit) */ #define B53_UC_FLOOD_MASK 0x32 #define B53_MC_FLOOD_MASK 0x34 @@ -342,12 +346,20 @@ #define ARLTBL_STATIC BIT(15) #define ARLTBL_VALID BIT(16) +/* BCM5389 ARL Table Data Entry N Register format (16 bit) */ +#define ARLTBL_DATA_PORT_ID_MASK_89 GENMASK(8, 0) +#define ARLTBL_TC_MASK_89 GENMASK(12, 10) +#define ARLTBL_AGE_89 BIT(13) +#define ARLTBL_STATIC_89 BIT(14) +#define ARLTBL_VALID_89 BIT(15) + /* Maximum number of bin entries in the ARL for all switches */ #define B53_ARLTBL_MAX_BIN_ENTRIES 4 /* ARL Search Control Register (8 bit) */ #define B53_ARL_SRCH_CTL 0x50 #define B53_ARL_SRCH_CTL_25 0x20 +#define B53_ARL_SRCH_CTL_89 0x30 #define ARL_SRCH_VLID BIT(0) #define ARL_SRCH_STDN BIT(7) @@ -355,10 +367,14 @@ #define B53_ARL_SRCH_ADDR 0x51 #define B53_ARL_SRCH_ADDR_25 0x22 #define B53_ARL_SRCH_ADDR_65 0x24 +#define B53_ARL_SRCH_ADDR_89 0x31 +#define B53_ARL_SRCH_ADDR_63XX 0x32 #define ARL_ADDR_MASK GENMASK(14, 0) /* ARL Search MAC/VID Result (64 bit) */ #define B53_ARL_SRCH_RSTL_0_MACVID 0x60 +#define B53_ARL_SRCH_RSLT_MACVID_89 0x33 +#define B53_ARL_SRCH_RSLT_MACVID_63XX 0x34 /* Single register search result on 5325 */ #define B53_ARL_SRCH_RSTL_0_MACVID_25 0x24 @@ -368,9 +384,19 @@ /* ARL Search Data Result (32 bit) */ #define B53_ARL_SRCH_RSTL_0 0x68 +/* BCM5389 ARL Search Data Result (16 bit) */ +#define B53_ARL_SRCH_RSLT_89 0x3b + #define B53_ARL_SRCH_RSTL_MACVID(x) (B53_ARL_SRCH_RSTL_0_MACVID + ((x) * 0x10)) #define B53_ARL_SRCH_RSTL(x) (B53_ARL_SRCH_RSTL_0 + ((x) * 0x10)) +/* 63XX ARL Search Data Result (16 bit) */ +#define B53_ARL_SRCH_RSLT_63XX 0x3c +#define ARL_SRST_PORT_ID_MASK_63XX GENMASK(9, 1) +#define ARL_SRST_TC_MASK_63XX GENMASK(13, 11) +#define ARL_SRST_AGE_63XX BIT(14) +#define ARL_SRST_STATIC_63XX BIT(15) + /************************************************************************* * IEEE 802.1X Registers *************************************************************************/ diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index 650d93226d9fa..4a416f2717bae 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -441,11 +441,6 @@ static int __init dsa_loop_create_switch_mdiodev(void) static int __init dsa_loop_init(void) { - struct fixed_phy_status status = { - .link = 1, - .speed = SPEED_100, - .duplex = DUPLEX_FULL, - }; unsigned int i; int ret; @@ -454,7 +449,7 @@ static int __init dsa_loop_init(void) return ret; for (i = 0; i < NUM_FIXED_PHYS; i++) - phydevs[i] = fixed_phy_register(&status, NULL); + phydevs[i] = fixed_phy_register_100fd(); ret = mdio_driver_register(&dsa_loop_drv); if (ret) { diff --git a/drivers/net/dsa/hirschmann/hellcreek_ptp.c b/drivers/net/dsa/hirschmann/hellcreek_ptp.c index bfe21f9f7dcd3..cb23bea9c21b8 100644 --- a/drivers/net/dsa/hirschmann/hellcreek_ptp.c +++ b/drivers/net/dsa/hirschmann/hellcreek_ptp.c @@ -376,8 +376,18 @@ static int hellcreek_led_setup(struct hellcreek *hellcreek) hellcreek_set_brightness(hellcreek, STATUS_OUT_IS_GM, 1); /* Register both leds */ - led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); - led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + ret = led_classdev_register(hellcreek->dev, &hellcreek->led_sync_good); + if (ret) { + dev_err(hellcreek->dev, "Failed to register sync_good LED\n"); + goto out; + } + + ret = led_classdev_register(hellcreek->dev, &hellcreek->led_is_gm); + if (ret) { + dev_err(hellcreek->dev, "Failed to register is_gm LED\n"); + led_classdev_unregister(&hellcreek->led_sync_good); + goto out; + } ret = 0; diff --git a/drivers/net/dsa/lantiq/Kconfig b/drivers/net/dsa/lantiq/Kconfig index 1cb053c823f7f..4a9771be5d588 100644 --- a/drivers/net/dsa/lantiq/Kconfig +++ b/drivers/net/dsa/lantiq/Kconfig @@ -1,7 +1,24 @@ +config NET_DSA_LANTIQ_COMMON + tristate + select REGMAP + config NET_DSA_LANTIQ_GSWIP tristate "Lantiq / Intel GSWIP" depends on HAS_IOMEM select NET_DSA_TAG_GSWIP + select NET_DSA_LANTIQ_COMMON help This enables support for the Lantiq / Intel GSWIP 2.1 found in the xrx200 / VR9 SoC. + +config NET_DSA_MXL_GSW1XX + tristate "MaxLinear GSW1xx Ethernet switch support" + select NET_DSA_TAG_MXL_GSW1XX + select NET_DSA_LANTIQ_COMMON + help + This enables support for the MaxLinear GSW1xx family of 1GE switches + GSW120 4 port, 2 PHYs, RGMII & SGMII/2500Base-X + GSW125 4 port, 2 PHYs, RGMII & SGMII/2500Base-X, industrial temperature + GSW140 6 port, 4 PHYs, RGMII & SGMII/2500Base-X + GSW141 6 port, 4 PHYs, RGMII & SGMII + GSW145 6 port, 4 PHYs, RGMII & SGMII/2500Base-X, industrial temperature diff --git a/drivers/net/dsa/lantiq/Makefile b/drivers/net/dsa/lantiq/Makefile index 849f85ebebd6c..85fce605310b3 100644 --- a/drivers/net/dsa/lantiq/Makefile +++ b/drivers/net/dsa/lantiq/Makefile @@ -1 +1,3 @@ obj-$(CONFIG_NET_DSA_LANTIQ_GSWIP) += lantiq_gswip.o +obj-$(CONFIG_NET_DSA_LANTIQ_COMMON) += lantiq_gswip_common.o +obj-$(CONFIG_NET_DSA_MXL_GSW1XX) += mxl-gsw1xx.o diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.c b/drivers/net/dsa/lantiq/lantiq_gswip.c index 2169c0814a48b..57dd063c07403 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq/lantiq_gswip.c @@ -2,1281 +2,32 @@ /* * Lantiq / Intel GSWIP switch driver for VRX200, xRX300 and xRX330 SoCs * - * Copyright (C) 2010 Lantiq Deutschland - * Copyright (C) 2012 John Crispin - * Copyright (C) 2017 - 2019 Hauke Mehrtens - * - * The VLAN and bridge model the GSWIP hardware uses does not directly - * matches the model DSA uses. - * - * The hardware has 64 possible table entries for bridges with one VLAN - * ID, one flow id and a list of ports for each bridge. All entries which - * match the same flow ID are combined in the mac learning table, they - * act as one global bridge. - * The hardware does not support VLAN filter on the port, but on the - * bridge, this driver converts the DSA model to the hardware. - * - * The CPU gets all the exception frames which do not match any forwarding - * rule and the CPU port is also added to all bridges. This makes it possible - * to handle all the special cases easily in software. - * At the initialization the driver allocates one bridge table entry for - * each switch port which is used when the port is used without an - * explicit bridge. This prevents the frames from being forwarded - * between all LAN ports by default. - */ - -#include "lantiq_gswip.h" -#include "lantiq_pce.h" - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -struct xway_gphy_match_data { - char *fe_firmware_name; - char *ge_firmware_name; -}; - -struct gswip_pce_table_entry { - u16 index; // PCE_TBL_ADDR.ADDR = pData->table_index - u16 table; // PCE_TBL_CTRL.ADDR = pData->table - u16 key[8]; - u16 val[5]; - u16 mask; - u8 gmap; - bool type; - bool valid; - bool key_mode; -}; - -struct gswip_rmon_cnt_desc { - unsigned int size; - unsigned int offset; - const char *name; -}; - -#define MIB_DESC(_size, _offset, _name) {.size = _size, .offset = _offset, .name = _name} - -static const struct gswip_rmon_cnt_desc gswip_rmon_cnt[] = { - /** Receive Packet Count (only packets that are accepted and not discarded). */ - MIB_DESC(1, 0x1F, "RxGoodPkts"), - MIB_DESC(1, 0x23, "RxUnicastPkts"), - MIB_DESC(1, 0x22, "RxMulticastPkts"), - MIB_DESC(1, 0x21, "RxFCSErrorPkts"), - MIB_DESC(1, 0x1D, "RxUnderSizeGoodPkts"), - MIB_DESC(1, 0x1E, "RxUnderSizeErrorPkts"), - MIB_DESC(1, 0x1B, "RxOversizeGoodPkts"), - MIB_DESC(1, 0x1C, "RxOversizeErrorPkts"), - MIB_DESC(1, 0x20, "RxGoodPausePkts"), - MIB_DESC(1, 0x1A, "RxAlignErrorPkts"), - MIB_DESC(1, 0x12, "Rx64BytePkts"), - MIB_DESC(1, 0x13, "Rx127BytePkts"), - MIB_DESC(1, 0x14, "Rx255BytePkts"), - MIB_DESC(1, 0x15, "Rx511BytePkts"), - MIB_DESC(1, 0x16, "Rx1023BytePkts"), - /** Receive Size 1024-1522 (or more, if configured) Packet Count. */ - MIB_DESC(1, 0x17, "RxMaxBytePkts"), - MIB_DESC(1, 0x18, "RxDroppedPkts"), - MIB_DESC(1, 0x19, "RxFilteredPkts"), - MIB_DESC(2, 0x24, "RxGoodBytes"), - MIB_DESC(2, 0x26, "RxBadBytes"), - MIB_DESC(1, 0x11, "TxAcmDroppedPkts"), - MIB_DESC(1, 0x0C, "TxGoodPkts"), - MIB_DESC(1, 0x06, "TxUnicastPkts"), - MIB_DESC(1, 0x07, "TxMulticastPkts"), - MIB_DESC(1, 0x00, "Tx64BytePkts"), - MIB_DESC(1, 0x01, "Tx127BytePkts"), - MIB_DESC(1, 0x02, "Tx255BytePkts"), - MIB_DESC(1, 0x03, "Tx511BytePkts"), - MIB_DESC(1, 0x04, "Tx1023BytePkts"), - /** Transmit Size 1024-1522 (or more, if configured) Packet Count. */ - MIB_DESC(1, 0x05, "TxMaxBytePkts"), - MIB_DESC(1, 0x08, "TxSingleCollCount"), - MIB_DESC(1, 0x09, "TxMultCollCount"), - MIB_DESC(1, 0x0A, "TxLateCollCount"), - MIB_DESC(1, 0x0B, "TxExcessCollCount"), - MIB_DESC(1, 0x0D, "TxPauseCount"), - MIB_DESC(1, 0x10, "TxDroppedPkts"), - MIB_DESC(2, 0x0E, "TxGoodBytes"), -}; - -static u32 gswip_switch_r(struct gswip_priv *priv, u32 offset) -{ - return __raw_readl(priv->gswip + (offset * 4)); -} - -static void gswip_switch_w(struct gswip_priv *priv, u32 val, u32 offset) -{ - __raw_writel(val, priv->gswip + (offset * 4)); -} - -static void gswip_switch_mask(struct gswip_priv *priv, u32 clear, u32 set, - u32 offset) -{ - u32 val = gswip_switch_r(priv, offset); - - val &= ~(clear); - val |= set; - gswip_switch_w(priv, val, offset); -} - -static u32 gswip_switch_r_timeout(struct gswip_priv *priv, u32 offset, - u32 cleared) -{ - u32 val; - - return readx_poll_timeout(__raw_readl, priv->gswip + (offset * 4), val, - (val & cleared) == 0, 20, 50000); -} - -static u32 gswip_mdio_r(struct gswip_priv *priv, u32 offset) -{ - return __raw_readl(priv->mdio + (offset * 4)); -} - -static void gswip_mdio_w(struct gswip_priv *priv, u32 val, u32 offset) -{ - __raw_writel(val, priv->mdio + (offset * 4)); -} - -static void gswip_mdio_mask(struct gswip_priv *priv, u32 clear, u32 set, - u32 offset) -{ - u32 val = gswip_mdio_r(priv, offset); - - val &= ~(clear); - val |= set; - gswip_mdio_w(priv, val, offset); -} - -static u32 gswip_mii_r(struct gswip_priv *priv, u32 offset) -{ - return __raw_readl(priv->mii + (offset * 4)); -} - -static void gswip_mii_w(struct gswip_priv *priv, u32 val, u32 offset) -{ - __raw_writel(val, priv->mii + (offset * 4)); -} - -static void gswip_mii_mask(struct gswip_priv *priv, u32 clear, u32 set, - u32 offset) -{ - u32 val = gswip_mii_r(priv, offset); - - val &= ~(clear); - val |= set; - gswip_mii_w(priv, val, offset); -} - -static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 clear, u32 set, - int port) -{ - int reg_port; - - /* MII_CFG register only exists for MII ports */ - if (!(priv->hw_info->mii_ports & BIT(port))) - return; - - reg_port = port + priv->hw_info->mii_port_reg_offset; - - gswip_mii_mask(priv, clear, set, GSWIP_MII_CFGp(reg_port)); -} - -static void gswip_mii_mask_pcdu(struct gswip_priv *priv, u32 clear, u32 set, - int port) -{ - int reg_port; - - /* MII_PCDU register only exists for MII ports */ - if (!(priv->hw_info->mii_ports & BIT(port))) - return; - - reg_port = port + priv->hw_info->mii_port_reg_offset; - - switch (reg_port) { - case 0: - gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU0); - break; - case 1: - gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU1); - break; - case 5: - gswip_mii_mask(priv, clear, set, GSWIP_MII_PCDU5); - break; - } -} - -static int gswip_mdio_poll(struct gswip_priv *priv) -{ - int cnt = 100; - - while (likely(cnt--)) { - u32 ctrl = gswip_mdio_r(priv, GSWIP_MDIO_CTRL); - - if ((ctrl & GSWIP_MDIO_CTRL_BUSY) == 0) - return 0; - usleep_range(20, 40); - } - - return -ETIMEDOUT; -} - -static int gswip_mdio_wr(struct mii_bus *bus, int addr, int reg, u16 val) -{ - struct gswip_priv *priv = bus->priv; - int err; - - err = gswip_mdio_poll(priv); - if (err) { - dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); - return err; - } - - gswip_mdio_w(priv, val, GSWIP_MDIO_WRITE); - gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_WR | - ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | - (reg & GSWIP_MDIO_CTRL_REGAD_MASK), - GSWIP_MDIO_CTRL); - - return 0; -} - -static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg) -{ - struct gswip_priv *priv = bus->priv; - int err; - - err = gswip_mdio_poll(priv); - if (err) { - dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); - return err; - } - - gswip_mdio_w(priv, GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_RD | - ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | - (reg & GSWIP_MDIO_CTRL_REGAD_MASK), - GSWIP_MDIO_CTRL); - - err = gswip_mdio_poll(priv); - if (err) { - dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); - return err; - } - - return gswip_mdio_r(priv, GSWIP_MDIO_READ); -} - -static int gswip_mdio(struct gswip_priv *priv) -{ - struct device_node *mdio_np, *switch_np = priv->dev->of_node; - struct device *dev = priv->dev; - struct mii_bus *bus; - int err = 0; - - mdio_np = of_get_compatible_child(switch_np, "lantiq,xrx200-mdio"); - if (!mdio_np) - mdio_np = of_get_child_by_name(switch_np, "mdio"); - - if (!of_device_is_available(mdio_np)) - goto out_put_node; - - bus = devm_mdiobus_alloc(dev); - if (!bus) { - err = -ENOMEM; - goto out_put_node; - } - - bus->priv = priv; - bus->read = gswip_mdio_rd; - bus->write = gswip_mdio_wr; - bus->name = "lantiq,xrx200-mdio"; - snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev)); - bus->parent = priv->dev; - - err = devm_of_mdiobus_register(dev, bus, mdio_np); - -out_put_node: - of_node_put(mdio_np); - - return err; -} - -static int gswip_pce_table_entry_read(struct gswip_priv *priv, - struct gswip_pce_table_entry *tbl) -{ - int i; - int err; - u16 crtl; - u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSRD : - GSWIP_PCE_TBL_CTRL_OPMOD_ADRD; - - mutex_lock(&priv->pce_table_lock); - - err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, - GSWIP_PCE_TBL_CTRL_BAS); - if (err) { - mutex_unlock(&priv->pce_table_lock); - return err; - } - - gswip_switch_w(priv, tbl->index, GSWIP_PCE_TBL_ADDR); - gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK | - GSWIP_PCE_TBL_CTRL_OPMOD_MASK, - tbl->table | addr_mode | GSWIP_PCE_TBL_CTRL_BAS, - GSWIP_PCE_TBL_CTRL); - - err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, - GSWIP_PCE_TBL_CTRL_BAS); - if (err) { - mutex_unlock(&priv->pce_table_lock); - return err; - } - - for (i = 0; i < ARRAY_SIZE(tbl->key); i++) - tbl->key[i] = gswip_switch_r(priv, GSWIP_PCE_TBL_KEY(i)); - - for (i = 0; i < ARRAY_SIZE(tbl->val); i++) - tbl->val[i] = gswip_switch_r(priv, GSWIP_PCE_TBL_VAL(i)); - - tbl->mask = gswip_switch_r(priv, GSWIP_PCE_TBL_MASK); - - crtl = gswip_switch_r(priv, GSWIP_PCE_TBL_CTRL); - - tbl->type = !!(crtl & GSWIP_PCE_TBL_CTRL_TYPE); - tbl->valid = !!(crtl & GSWIP_PCE_TBL_CTRL_VLD); - tbl->gmap = (crtl & GSWIP_PCE_TBL_CTRL_GMAP_MASK) >> 7; - - mutex_unlock(&priv->pce_table_lock); - - return 0; -} - -static int gswip_pce_table_entry_write(struct gswip_priv *priv, - struct gswip_pce_table_entry *tbl) -{ - int i; - int err; - u16 crtl; - u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSWR : - GSWIP_PCE_TBL_CTRL_OPMOD_ADWR; - - mutex_lock(&priv->pce_table_lock); - - err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, - GSWIP_PCE_TBL_CTRL_BAS); - if (err) { - mutex_unlock(&priv->pce_table_lock); - return err; - } - - gswip_switch_w(priv, tbl->index, GSWIP_PCE_TBL_ADDR); - gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK | - GSWIP_PCE_TBL_CTRL_OPMOD_MASK, - tbl->table | addr_mode, - GSWIP_PCE_TBL_CTRL); - - for (i = 0; i < ARRAY_SIZE(tbl->key); i++) - gswip_switch_w(priv, tbl->key[i], GSWIP_PCE_TBL_KEY(i)); - - for (i = 0; i < ARRAY_SIZE(tbl->val); i++) - gswip_switch_w(priv, tbl->val[i], GSWIP_PCE_TBL_VAL(i)); - - gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK | - GSWIP_PCE_TBL_CTRL_OPMOD_MASK, - tbl->table | addr_mode, - GSWIP_PCE_TBL_CTRL); - - gswip_switch_w(priv, tbl->mask, GSWIP_PCE_TBL_MASK); - - crtl = gswip_switch_r(priv, GSWIP_PCE_TBL_CTRL); - crtl &= ~(GSWIP_PCE_TBL_CTRL_TYPE | GSWIP_PCE_TBL_CTRL_VLD | - GSWIP_PCE_TBL_CTRL_GMAP_MASK); - if (tbl->type) - crtl |= GSWIP_PCE_TBL_CTRL_TYPE; - if (tbl->valid) - crtl |= GSWIP_PCE_TBL_CTRL_VLD; - crtl |= (tbl->gmap << 7) & GSWIP_PCE_TBL_CTRL_GMAP_MASK; - crtl |= GSWIP_PCE_TBL_CTRL_BAS; - gswip_switch_w(priv, crtl, GSWIP_PCE_TBL_CTRL); - - err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, - GSWIP_PCE_TBL_CTRL_BAS); - - mutex_unlock(&priv->pce_table_lock); - - return err; -} - -/* Add the LAN port into a bridge with the CPU port by - * default. This prevents automatic forwarding of - * packages between the LAN ports when no explicit - * bridge is configured. - */ -static int gswip_add_single_port_br(struct gswip_priv *priv, int port, bool add) -{ - struct gswip_pce_table_entry vlan_active = {0,}; - struct gswip_pce_table_entry vlan_mapping = {0,}; - int err; - - vlan_active.index = port + 1; - vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; - vlan_active.key[0] = 0; /* vid */ - vlan_active.val[0] = port + 1 /* fid */; - vlan_active.valid = add; - err = gswip_pce_table_entry_write(priv, &vlan_active); - if (err) { - dev_err(priv->dev, "failed to write active VLAN: %d\n", err); - return err; - } - - if (!add) - return 0; - - vlan_mapping.index = port + 1; - vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; - vlan_mapping.val[0] = 0 /* vid */; - vlan_mapping.val[1] = BIT(port) | dsa_cpu_ports(priv->ds); - vlan_mapping.val[2] = 0; - err = gswip_pce_table_entry_write(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); - return err; - } - - return 0; -} - -static int gswip_port_setup(struct dsa_switch *ds, int port) -{ - struct gswip_priv *priv = ds->priv; - int err; - - if (!dsa_is_cpu_port(ds, port)) { - err = gswip_add_single_port_br(priv, port, true); - if (err) - return err; - } - - return 0; -} - -static int gswip_port_enable(struct dsa_switch *ds, int port, - struct phy_device *phydev) -{ - struct gswip_priv *priv = ds->priv; - - if (!dsa_is_cpu_port(ds, port)) { - u32 mdio_phy = 0; - - if (phydev) - mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK; - - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_ADDR_MASK, mdio_phy, - GSWIP_MDIO_PHYp(port)); - } - - /* RMON Counter Enable for port */ - gswip_switch_w(priv, GSWIP_BM_PCFG_CNTEN, GSWIP_BM_PCFGp(port)); - - /* enable port fetch/store dma & VLAN Modification */ - gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_EN | - GSWIP_FDMA_PCTRL_VLANMOD_BOTH, - GSWIP_FDMA_PCTRLp(port)); - gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN, - GSWIP_SDMA_PCTRLp(port)); - - return 0; -} - -static void gswip_port_disable(struct dsa_switch *ds, int port) -{ - struct gswip_priv *priv = ds->priv; - - gswip_switch_mask(priv, GSWIP_FDMA_PCTRL_EN, 0, - GSWIP_FDMA_PCTRLp(port)); - gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, - GSWIP_SDMA_PCTRLp(port)); -} - -static int gswip_pce_load_microcode(struct gswip_priv *priv) -{ - int i; - int err; - - gswip_switch_mask(priv, GSWIP_PCE_TBL_CTRL_ADDR_MASK | - GSWIP_PCE_TBL_CTRL_OPMOD_MASK, - GSWIP_PCE_TBL_CTRL_OPMOD_ADWR, GSWIP_PCE_TBL_CTRL); - gswip_switch_w(priv, 0, GSWIP_PCE_TBL_MASK); - - for (i = 0; i < priv->hw_info->pce_microcode_size; i++) { - gswip_switch_w(priv, i, GSWIP_PCE_TBL_ADDR); - gswip_switch_w(priv, (*priv->hw_info->pce_microcode)[i].val_0, - GSWIP_PCE_TBL_VAL(0)); - gswip_switch_w(priv, (*priv->hw_info->pce_microcode)[i].val_1, - GSWIP_PCE_TBL_VAL(1)); - gswip_switch_w(priv, (*priv->hw_info->pce_microcode)[i].val_2, - GSWIP_PCE_TBL_VAL(2)); - gswip_switch_w(priv, (*priv->hw_info->pce_microcode)[i].val_3, - GSWIP_PCE_TBL_VAL(3)); - - /* start the table access: */ - gswip_switch_mask(priv, 0, GSWIP_PCE_TBL_CTRL_BAS, - GSWIP_PCE_TBL_CTRL); - err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, - GSWIP_PCE_TBL_CTRL_BAS); - if (err) - return err; - } - - /* tell the switch that the microcode is loaded */ - gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_MC_VALID, - GSWIP_PCE_GCTRL_0); - - return 0; -} - -static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port, - bool vlan_filtering, - struct netlink_ext_ack *extack) -{ - struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); - struct gswip_priv *priv = ds->priv; - - /* Do not allow changing the VLAN filtering options while in bridge */ - if (bridge && !!(priv->port_vlan_filter & BIT(port)) != vlan_filtering) { - NL_SET_ERR_MSG_MOD(extack, - "Dynamic toggling of vlan_filtering not supported"); - return -EIO; - } - - if (vlan_filtering) { - /* Use tag based VLAN */ - gswip_switch_mask(priv, - GSWIP_PCE_VCTRL_VSR, - GSWIP_PCE_VCTRL_UVR | GSWIP_PCE_VCTRL_VIMR | - GSWIP_PCE_VCTRL_VEMR, - GSWIP_PCE_VCTRL(port)); - gswip_switch_mask(priv, GSWIP_PCE_PCTRL_0_TVM, 0, - GSWIP_PCE_PCTRL_0p(port)); - } else { - /* Use port based VLAN */ - gswip_switch_mask(priv, - GSWIP_PCE_VCTRL_UVR | GSWIP_PCE_VCTRL_VIMR | - GSWIP_PCE_VCTRL_VEMR, - GSWIP_PCE_VCTRL_VSR, - GSWIP_PCE_VCTRL(port)); - gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_TVM, - GSWIP_PCE_PCTRL_0p(port)); - } - - return 0; -} - -static int gswip_setup(struct dsa_switch *ds) -{ - unsigned int cpu_ports = dsa_cpu_ports(ds); - struct gswip_priv *priv = ds->priv; - struct dsa_port *cpu_dp; - int err, i; - - gswip_switch_w(priv, GSWIP_SWRES_R0, GSWIP_SWRES); - usleep_range(5000, 10000); - gswip_switch_w(priv, 0, GSWIP_SWRES); - - /* disable port fetch/store dma on all ports */ - for (i = 0; i < priv->hw_info->max_ports; i++) { - gswip_port_disable(ds, i); - gswip_port_vlan_filtering(ds, i, false, NULL); - } - - /* enable Switch */ - gswip_mdio_mask(priv, 0, GSWIP_MDIO_GLOB_ENABLE, GSWIP_MDIO_GLOB); - - err = gswip_pce_load_microcode(priv); - if (err) { - dev_err(priv->dev, "writing PCE microcode failed, %i\n", err); - return err; - } - - /* Default unknown Broadcast/Multicast/Unicast port maps */ - gswip_switch_w(priv, cpu_ports, GSWIP_PCE_PMAP1); - gswip_switch_w(priv, cpu_ports, GSWIP_PCE_PMAP2); - gswip_switch_w(priv, cpu_ports, GSWIP_PCE_PMAP3); - - /* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an - * interoperability problem with this auto polling mechanism because - * their status registers think that the link is in a different state - * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set - * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the - * auto polling state machine consider the link being negotiated with - * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads - * to the switch port being completely dead (RX and TX are both not - * working). - * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F - * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes - * it would work fine for a few minutes to hours and then stop, on - * other device it would no traffic could be sent or received at all. - * Testing shows that when PHY auto polling is disabled these problems - * go away. - */ - gswip_mdio_w(priv, 0x0, GSWIP_MDIO_MDC_CFG0); - - /* Configure the MDIO Clock 2.5 MHz */ - gswip_mdio_mask(priv, 0xff, 0x09, GSWIP_MDIO_MDC_CFG1); - - /* bring up the mdio bus */ - err = gswip_mdio(priv); - if (err) { - dev_err(priv->dev, "mdio bus setup failed\n"); - return err; - } - - /* Disable the xMII interface and clear it's isolation bit */ - for (i = 0; i < priv->hw_info->max_ports; i++) - gswip_mii_mask_cfg(priv, - GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE, - 0, i); - - dsa_switch_for_each_cpu_port(cpu_dp, ds) { - /* enable special tag insertion on cpu port */ - gswip_switch_mask(priv, 0, GSWIP_FDMA_PCTRL_STEN, - GSWIP_FDMA_PCTRLp(cpu_dp->index)); - - /* accept special tag in ingress direction */ - gswip_switch_mask(priv, 0, GSWIP_PCE_PCTRL_0_INGRESS, - GSWIP_PCE_PCTRL_0p(cpu_dp->index)); - } - - gswip_switch_mask(priv, 0, GSWIP_BM_QUEUE_GCTRL_GL_MOD, - GSWIP_BM_QUEUE_GCTRL); - - /* VLAN aware Switching */ - gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_VLAN, GSWIP_PCE_GCTRL_0); - - /* Flush MAC Table */ - gswip_switch_mask(priv, 0, GSWIP_PCE_GCTRL_0_MTFL, GSWIP_PCE_GCTRL_0); - - err = gswip_switch_r_timeout(priv, GSWIP_PCE_GCTRL_0, - GSWIP_PCE_GCTRL_0_MTFL); - if (err) { - dev_err(priv->dev, "MAC flushing didn't finish\n"); - return err; - } - - ds->mtu_enforcement_ingress = true; - - ds->configure_vlan_while_not_filtering = false; - - return 0; -} - -static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds, - int port, - enum dsa_tag_protocol mp) -{ - struct gswip_priv *priv = ds->priv; - - return priv->hw_info->tag_protocol; -} - -static int gswip_vlan_active_create(struct gswip_priv *priv, - struct net_device *bridge, - int fid, u16 vid) -{ - struct gswip_pce_table_entry vlan_active = {0,}; - unsigned int max_ports = priv->hw_info->max_ports; - int idx = -1; - int err; - int i; - - /* Look for a free slot */ - for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { - if (!priv->vlans[i].bridge) { - idx = i; - break; - } - } - - if (idx == -1) - return -ENOSPC; - - if (fid == -1) - fid = idx; - - vlan_active.index = idx; - vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; - vlan_active.key[0] = vid; - vlan_active.val[0] = fid; - vlan_active.valid = true; - - err = gswip_pce_table_entry_write(priv, &vlan_active); - if (err) { - dev_err(priv->dev, "failed to write active VLAN: %d\n", err); - return err; - } - - priv->vlans[idx].bridge = bridge; - priv->vlans[idx].vid = vid; - priv->vlans[idx].fid = fid; - - return idx; -} - -static int gswip_vlan_active_remove(struct gswip_priv *priv, int idx) -{ - struct gswip_pce_table_entry vlan_active = {0,}; - int err; - - vlan_active.index = idx; - vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; - vlan_active.valid = false; - err = gswip_pce_table_entry_write(priv, &vlan_active); - if (err) - dev_err(priv->dev, "failed to delete active VLAN: %d\n", err); - priv->vlans[idx].bridge = NULL; - - return err; -} - -static int gswip_vlan_add_unaware(struct gswip_priv *priv, - struct net_device *bridge, int port) -{ - struct gswip_pce_table_entry vlan_mapping = {0,}; - unsigned int max_ports = priv->hw_info->max_ports; - bool active_vlan_created = false; - int idx = -1; - int i; - int err; - - /* Check if there is already a page for this bridge */ - for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { - if (priv->vlans[i].bridge == bridge) { - idx = i; - break; - } - } - - /* If this bridge is not programmed yet, add a Active VLAN table - * entry in a free slot and prepare the VLAN mapping table entry. - */ - if (idx == -1) { - idx = gswip_vlan_active_create(priv, bridge, -1, 0); - if (idx < 0) - return idx; - active_vlan_created = true; - - vlan_mapping.index = idx; - vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; - /* VLAN ID byte, maps to the VLAN ID of vlan active table */ - vlan_mapping.val[0] = 0; - } else { - /* Read the existing VLAN mapping entry from the switch */ - vlan_mapping.index = idx; - vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; - err = gswip_pce_table_entry_read(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to read VLAN mapping: %d\n", - err); - return err; - } - } - - /* Update the VLAN mapping entry and write it to the switch */ - vlan_mapping.val[1] |= dsa_cpu_ports(priv->ds); - vlan_mapping.val[1] |= BIT(port); - err = gswip_pce_table_entry_write(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); - /* In case an Active VLAN was creaetd delete it again */ - if (active_vlan_created) - gswip_vlan_active_remove(priv, idx); - return err; - } - - gswip_switch_w(priv, 0, GSWIP_PCE_DEFPVID(port)); - return 0; -} - -static int gswip_vlan_add_aware(struct gswip_priv *priv, - struct net_device *bridge, int port, - u16 vid, bool untagged, - bool pvid) -{ - struct gswip_pce_table_entry vlan_mapping = {0,}; - unsigned int max_ports = priv->hw_info->max_ports; - unsigned int cpu_ports = dsa_cpu_ports(priv->ds); - bool active_vlan_created = false; - int idx = -1; - int fid = -1; - int i; - int err; - - /* Check if there is already a page for this bridge */ - for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { - if (priv->vlans[i].bridge == bridge) { - if (fid != -1 && fid != priv->vlans[i].fid) - dev_err(priv->dev, "one bridge with multiple flow ids\n"); - fid = priv->vlans[i].fid; - if (priv->vlans[i].vid == vid) { - idx = i; - break; - } - } - } - - /* If this bridge is not programmed yet, add a Active VLAN table - * entry in a free slot and prepare the VLAN mapping table entry. - */ - if (idx == -1) { - idx = gswip_vlan_active_create(priv, bridge, fid, vid); - if (idx < 0) - return idx; - active_vlan_created = true; - - vlan_mapping.index = idx; - vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; - /* VLAN ID byte, maps to the VLAN ID of vlan active table */ - vlan_mapping.val[0] = vid; - } else { - /* Read the existing VLAN mapping entry from the switch */ - vlan_mapping.index = idx; - vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; - err = gswip_pce_table_entry_read(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to read VLAN mapping: %d\n", - err); - return err; - } - } - - vlan_mapping.val[0] = vid; - /* Update the VLAN mapping entry and write it to the switch */ - vlan_mapping.val[1] |= cpu_ports; - vlan_mapping.val[2] |= cpu_ports; - vlan_mapping.val[1] |= BIT(port); - if (untagged) - vlan_mapping.val[2] &= ~BIT(port); - else - vlan_mapping.val[2] |= BIT(port); - err = gswip_pce_table_entry_write(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); - /* In case an Active VLAN was creaetd delete it again */ - if (active_vlan_created) - gswip_vlan_active_remove(priv, idx); - return err; - } - - if (pvid) - gswip_switch_w(priv, idx, GSWIP_PCE_DEFPVID(port)); - - return 0; -} - -static int gswip_vlan_remove(struct gswip_priv *priv, - struct net_device *bridge, int port, - u16 vid, bool pvid, bool vlan_aware) -{ - struct gswip_pce_table_entry vlan_mapping = {0,}; - unsigned int max_ports = priv->hw_info->max_ports; - int idx = -1; - int i; - int err; - - /* Check if there is already a page for this bridge */ - for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { - if (priv->vlans[i].bridge == bridge && - (!vlan_aware || priv->vlans[i].vid == vid)) { - idx = i; - break; - } - } - - if (idx == -1) { - dev_err(priv->dev, "bridge to leave does not exists\n"); - return -ENOENT; - } - - vlan_mapping.index = idx; - vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; - err = gswip_pce_table_entry_read(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to read VLAN mapping: %d\n", err); - return err; - } - - vlan_mapping.val[1] &= ~BIT(port); - vlan_mapping.val[2] &= ~BIT(port); - err = gswip_pce_table_entry_write(priv, &vlan_mapping); - if (err) { - dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); - return err; - } - - /* In case all ports are removed from the bridge, remove the VLAN */ - if (!(vlan_mapping.val[1] & ~dsa_cpu_ports(priv->ds))) { - err = gswip_vlan_active_remove(priv, idx); - if (err) { - dev_err(priv->dev, "failed to write active VLAN: %d\n", - err); - return err; - } - } - - /* GSWIP 2.2 (GRX300) and later program here the VID directly. */ - if (pvid) - gswip_switch_w(priv, 0, GSWIP_PCE_DEFPVID(port)); - - return 0; -} - -static int gswip_port_bridge_join(struct dsa_switch *ds, int port, - struct dsa_bridge bridge, - bool *tx_fwd_offload, - struct netlink_ext_ack *extack) -{ - struct net_device *br = bridge.dev; - struct gswip_priv *priv = ds->priv; - int err; - - /* When the bridge uses VLAN filtering we have to configure VLAN - * specific bridges. No bridge is configured here. - */ - if (!br_vlan_enabled(br)) { - err = gswip_vlan_add_unaware(priv, br, port); - if (err) - return err; - priv->port_vlan_filter &= ~BIT(port); - } else { - priv->port_vlan_filter |= BIT(port); - } - return gswip_add_single_port_br(priv, port, false); -} - -static void gswip_port_bridge_leave(struct dsa_switch *ds, int port, - struct dsa_bridge bridge) -{ - struct net_device *br = bridge.dev; - struct gswip_priv *priv = ds->priv; - - gswip_add_single_port_br(priv, port, true); - - /* When the bridge uses VLAN filtering we have to configure VLAN - * specific bridges. No bridge is configured here. - */ - if (!br_vlan_enabled(br)) - gswip_vlan_remove(priv, br, port, 0, true, false); -} - -static int gswip_port_vlan_prepare(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan, - struct netlink_ext_ack *extack) -{ - struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); - struct gswip_priv *priv = ds->priv; - unsigned int max_ports = priv->hw_info->max_ports; - int pos = max_ports; - int i, idx = -1; - - /* We only support VLAN filtering on bridges */ - if (!dsa_is_cpu_port(ds, port) && !bridge) - return -EOPNOTSUPP; - - /* Check if there is already a page for this VLAN */ - for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { - if (priv->vlans[i].bridge == bridge && - priv->vlans[i].vid == vlan->vid) { - idx = i; - break; - } - } - - /* If this VLAN is not programmed yet, we have to reserve - * one entry in the VLAN table. Make sure we start at the - * next position round. - */ - if (idx == -1) { - /* Look for a free slot */ - for (; pos < ARRAY_SIZE(priv->vlans); pos++) { - if (!priv->vlans[pos].bridge) { - idx = pos; - pos++; - break; - } - } - - if (idx == -1) { - NL_SET_ERR_MSG_MOD(extack, "No slot in VLAN table"); - return -ENOSPC; - } - } - - return 0; -} - -static int gswip_port_vlan_add(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan, - struct netlink_ext_ack *extack) -{ - struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); - struct gswip_priv *priv = ds->priv; - bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; - bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; - int err; - - err = gswip_port_vlan_prepare(ds, port, vlan, extack); - if (err) - return err; - - /* We have to receive all packets on the CPU port and should not - * do any VLAN filtering here. This is also called with bridge - * NULL and then we do not know for which bridge to configure - * this. - */ - if (dsa_is_cpu_port(ds, port)) - return 0; - - return gswip_vlan_add_aware(priv, bridge, port, vlan->vid, - untagged, pvid); -} - -static int gswip_port_vlan_del(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan) -{ - struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); - struct gswip_priv *priv = ds->priv; - bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; - - /* We have to receive all packets on the CPU port and should not - * do any VLAN filtering here. This is also called with bridge - * NULL and then we do not know for which bridge to configure - * this. - */ - if (dsa_is_cpu_port(ds, port)) - return 0; - - return gswip_vlan_remove(priv, bridge, port, vlan->vid, pvid, true); -} - -static void gswip_port_fast_age(struct dsa_switch *ds, int port) -{ - struct gswip_priv *priv = ds->priv; - struct gswip_pce_table_entry mac_bridge = {0,}; - int i; - int err; - - for (i = 0; i < 2048; i++) { - mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE; - mac_bridge.index = i; - - err = gswip_pce_table_entry_read(priv, &mac_bridge); - if (err) { - dev_err(priv->dev, "failed to read mac bridge: %d\n", - err); - return; - } - - if (!mac_bridge.valid) - continue; - - if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) - continue; - - if (port != FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT, - mac_bridge.val[0])) - continue; - - mac_bridge.valid = false; - err = gswip_pce_table_entry_write(priv, &mac_bridge); - if (err) { - dev_err(priv->dev, "failed to write mac bridge: %d\n", - err); - return; - } - } -} - -static void gswip_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) -{ - struct gswip_priv *priv = ds->priv; - u32 stp_state; - - switch (state) { - case BR_STATE_DISABLED: - gswip_switch_mask(priv, GSWIP_SDMA_PCTRL_EN, 0, - GSWIP_SDMA_PCTRLp(port)); - return; - case BR_STATE_BLOCKING: - case BR_STATE_LISTENING: - stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LISTEN; - break; - case BR_STATE_LEARNING: - stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LEARNING; - break; - case BR_STATE_FORWARDING: - stp_state = GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING; - break; - default: - dev_err(priv->dev, "invalid STP state: %d\n", state); - return; - } - - gswip_switch_mask(priv, 0, GSWIP_SDMA_PCTRL_EN, - GSWIP_SDMA_PCTRLp(port)); - gswip_switch_mask(priv, GSWIP_PCE_PCTRL_0_PSTATE_MASK, stp_state, - GSWIP_PCE_PCTRL_0p(port)); -} - -static int gswip_port_fdb(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, bool add) -{ - struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); - struct gswip_priv *priv = ds->priv; - struct gswip_pce_table_entry mac_bridge = {0,}; - unsigned int max_ports = priv->hw_info->max_ports; - int fid = -1; - int i; - int err; - - /* Operation not supported on the CPU port, don't throw errors */ - if (!bridge) - return 0; - - for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { - if (priv->vlans[i].bridge == bridge) { - fid = priv->vlans[i].fid; - break; - } - } - - if (fid == -1) { - dev_err(priv->dev, "no FID found for bridge %s\n", - bridge->name); - return -EINVAL; - } - - mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE; - mac_bridge.key_mode = true; - mac_bridge.key[0] = addr[5] | (addr[4] << 8); - mac_bridge.key[1] = addr[3] | (addr[2] << 8); - mac_bridge.key[2] = addr[1] | (addr[0] << 8); - mac_bridge.key[3] = FIELD_PREP(GSWIP_TABLE_MAC_BRIDGE_KEY3_FID, fid); - mac_bridge.val[0] = add ? BIT(port) : 0; /* port map */ - mac_bridge.val[1] = GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC; - mac_bridge.valid = add; - - err = gswip_pce_table_entry_write(priv, &mac_bridge); - if (err) - dev_err(priv->dev, "failed to write mac bridge: %d\n", err); - - return err; -} - -static int gswip_port_fdb_add(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, - struct dsa_db db) -{ - return gswip_port_fdb(ds, port, addr, vid, true); -} - -static int gswip_port_fdb_del(struct dsa_switch *ds, int port, - const unsigned char *addr, u16 vid, - struct dsa_db db) -{ - return gswip_port_fdb(ds, port, addr, vid, false); -} - -static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, - dsa_fdb_dump_cb_t *cb, void *data) -{ - struct gswip_priv *priv = ds->priv; - struct gswip_pce_table_entry mac_bridge = {0,}; - unsigned char addr[ETH_ALEN]; - int i; - int err; - - for (i = 0; i < 2048; i++) { - mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE; - mac_bridge.index = i; - - err = gswip_pce_table_entry_read(priv, &mac_bridge); - if (err) { - dev_err(priv->dev, - "failed to read mac bridge entry %d: %d\n", - i, err); - return err; - } - - if (!mac_bridge.valid) - continue; - - addr[5] = mac_bridge.key[0] & 0xff; - addr[4] = (mac_bridge.key[0] >> 8) & 0xff; - addr[3] = mac_bridge.key[1] & 0xff; - addr[2] = (mac_bridge.key[1] >> 8) & 0xff; - addr[1] = mac_bridge.key[2] & 0xff; - addr[0] = (mac_bridge.key[2] >> 8) & 0xff; - if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) { - if (mac_bridge.val[0] & BIT(port)) { - err = cb(addr, 0, true, data); - if (err) - return err; - } - } else { - if (port == FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT, - mac_bridge.val[0])) { - err = cb(addr, 0, false, data); - if (err) - return err; - } - } - } - return 0; -} - -static int gswip_port_max_mtu(struct dsa_switch *ds, int port) -{ - /* Includes 8 bytes for special header. */ - return GSWIP_MAX_PACKET_LENGTH - VLAN_ETH_HLEN - ETH_FCS_LEN; -} + * Copyright (C) 2025 Daniel Golle + * Copyright (C) 2017 - 2019 Hauke Mehrtens + * Copyright (C) 2012 John Crispin + * Copyright (C) 2010 Lantiq Deutschland + */ -static int gswip_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) -{ - struct gswip_priv *priv = ds->priv; +#include "lantiq_gswip.h" +#include "lantiq_pce.h" - /* CPU port always has maximum mtu of user ports, so use it to set - * switch frame size, including 8 byte special header. - */ - if (dsa_is_cpu_port(ds, port)) { - new_mtu += 8; - gswip_switch_w(priv, VLAN_ETH_HLEN + new_mtu + ETH_FCS_LEN, - GSWIP_MAC_FLEN); - } +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include - /* Enable MLEN for ports with non-standard MTUs, including the special - * header on the CPU port added above. - */ - if (new_mtu != ETH_DATA_LEN) - gswip_switch_mask(priv, 0, GSWIP_MAC_CTRL_2_MLEN, - GSWIP_MAC_CTRL_2p(port)); - else - gswip_switch_mask(priv, GSWIP_MAC_CTRL_2_MLEN, 0, - GSWIP_MAC_CTRL_2p(port)); +#include - return 0; -} +struct xway_gphy_match_data { + char *fe_firmware_name; + char *ge_firmware_name; +}; static void gswip_xrx200_phylink_get_caps(struct dsa_switch *ds, int port, struct phylink_config *config) @@ -1346,327 +97,6 @@ static void gswip_xrx300_phylink_get_caps(struct dsa_switch *ds, int port, MAC_10 | MAC_100 | MAC_1000; } -static void gswip_phylink_get_caps(struct dsa_switch *ds, int port, - struct phylink_config *config) -{ - struct gswip_priv *priv = ds->priv; - - priv->hw_info->phylink_get_caps(ds, port, config); -} - -static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link) -{ - u32 mdio_phy; - - if (link) - mdio_phy = GSWIP_MDIO_PHY_LINK_UP; - else - mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN; - - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_LINK_MASK, mdio_phy, - GSWIP_MDIO_PHYp(port)); -} - -static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed, - phy_interface_t interface) -{ - u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0; - - switch (speed) { - case SPEED_10: - mdio_phy = GSWIP_MDIO_PHY_SPEED_M10; - - if (interface == PHY_INTERFACE_MODE_RMII) - mii_cfg = GSWIP_MII_CFG_RATE_M50; - else - mii_cfg = GSWIP_MII_CFG_RATE_M2P5; - - mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; - break; - - case SPEED_100: - mdio_phy = GSWIP_MDIO_PHY_SPEED_M100; - - if (interface == PHY_INTERFACE_MODE_RMII) - mii_cfg = GSWIP_MII_CFG_RATE_M50; - else - mii_cfg = GSWIP_MII_CFG_RATE_M25; - - mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; - break; - - case SPEED_1000: - mdio_phy = GSWIP_MDIO_PHY_SPEED_G1; - - mii_cfg = GSWIP_MII_CFG_RATE_M125; - - mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII; - break; - } - - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy, - GSWIP_MDIO_PHYp(port)); - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port); - gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0, - GSWIP_MAC_CTRL_0p(port)); -} - -static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex) -{ - u32 mac_ctrl_0, mdio_phy; - - if (duplex == DUPLEX_FULL) { - mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN; - mdio_phy = GSWIP_MDIO_PHY_FDUP_EN; - } else { - mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS; - mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS; - } - - gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0, - GSWIP_MAC_CTRL_0p(port)); - gswip_mdio_mask(priv, GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy, - GSWIP_MDIO_PHYp(port)); -} - -static void gswip_port_set_pause(struct gswip_priv *priv, int port, - bool tx_pause, bool rx_pause) -{ - u32 mac_ctrl_0, mdio_phy; - - if (tx_pause && rx_pause) { - mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX; - mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | - GSWIP_MDIO_PHY_FCONRX_EN; - } else if (tx_pause) { - mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX; - mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | - GSWIP_MDIO_PHY_FCONRX_DIS; - } else if (rx_pause) { - mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX; - mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | - GSWIP_MDIO_PHY_FCONRX_EN; - } else { - mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE; - mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | - GSWIP_MDIO_PHY_FCONRX_DIS; - } - - gswip_switch_mask(priv, GSWIP_MAC_CTRL_0_FCON_MASK, - mac_ctrl_0, GSWIP_MAC_CTRL_0p(port)); - gswip_mdio_mask(priv, - GSWIP_MDIO_PHY_FCONTX_MASK | - GSWIP_MDIO_PHY_FCONRX_MASK, - mdio_phy, GSWIP_MDIO_PHYp(port)); -} - -static void gswip_phylink_mac_config(struct phylink_config *config, - unsigned int mode, - const struct phylink_link_state *state) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct gswip_priv *priv = dp->ds->priv; - int port = dp->index; - u32 miicfg = 0; - - miicfg |= GSWIP_MII_CFG_LDCLKDIS; - - switch (state->interface) { - case PHY_INTERFACE_MODE_SGMII: - case PHY_INTERFACE_MODE_1000BASEX: - case PHY_INTERFACE_MODE_2500BASEX: - return; - case PHY_INTERFACE_MODE_MII: - case PHY_INTERFACE_MODE_INTERNAL: - miicfg |= GSWIP_MII_CFG_MODE_MIIM; - break; - case PHY_INTERFACE_MODE_REVMII: - miicfg |= GSWIP_MII_CFG_MODE_MIIP; - break; - case PHY_INTERFACE_MODE_RMII: - miicfg |= GSWIP_MII_CFG_MODE_RMIIM; - break; - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - miicfg |= GSWIP_MII_CFG_MODE_RGMII; - break; - case PHY_INTERFACE_MODE_GMII: - miicfg |= GSWIP_MII_CFG_MODE_GMII; - break; - default: - dev_err(dp->ds->dev, - "Unsupported interface: %d\n", state->interface); - return; - } - - gswip_mii_mask_cfg(priv, - GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK | - GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS, - miicfg, port); - - switch (state->interface) { - case PHY_INTERFACE_MODE_RGMII_ID: - gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK | - GSWIP_MII_PCDU_RXDLY_MASK, 0, port); - break; - case PHY_INTERFACE_MODE_RGMII_RXID: - gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_RXDLY_MASK, 0, port); - break; - case PHY_INTERFACE_MODE_RGMII_TXID: - gswip_mii_mask_pcdu(priv, GSWIP_MII_PCDU_TXDLY_MASK, 0, port); - break; - default: - break; - } -} - -static void gswip_phylink_mac_link_down(struct phylink_config *config, - unsigned int mode, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct gswip_priv *priv = dp->ds->priv; - int port = dp->index; - - gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port); - - if (!dsa_port_is_cpu(dp)) - gswip_port_set_link(priv, port, false); -} - -static void gswip_phylink_mac_link_up(struct phylink_config *config, - struct phy_device *phydev, - unsigned int mode, - phy_interface_t interface, - int speed, int duplex, - bool tx_pause, bool rx_pause) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct gswip_priv *priv = dp->ds->priv; - int port = dp->index; - - if (!dsa_port_is_cpu(dp)) { - gswip_port_set_link(priv, port, true); - gswip_port_set_speed(priv, port, speed, interface); - gswip_port_set_duplex(priv, port, duplex); - gswip_port_set_pause(priv, port, tx_pause, rx_pause); - } - - gswip_mii_mask_cfg(priv, 0, GSWIP_MII_CFG_EN, port); -} - -static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset, - uint8_t *data) -{ - int i; - - if (stringset != ETH_SS_STATS) - return; - - for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) - ethtool_puts(&data, gswip_rmon_cnt[i].name); -} - -static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table, - u32 index) -{ - u32 result; - int err; - - gswip_switch_w(priv, index, GSWIP_BM_RAM_ADDR); - gswip_switch_mask(priv, GSWIP_BM_RAM_CTRL_ADDR_MASK | - GSWIP_BM_RAM_CTRL_OPMOD, - table | GSWIP_BM_RAM_CTRL_BAS, - GSWIP_BM_RAM_CTRL); - - err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL, - GSWIP_BM_RAM_CTRL_BAS); - if (err) { - dev_err(priv->dev, "timeout while reading table: %u, index: %u\n", - table, index); - return 0; - } - - result = gswip_switch_r(priv, GSWIP_BM_RAM_VAL(0)); - result |= gswip_switch_r(priv, GSWIP_BM_RAM_VAL(1)) << 16; - - return result; -} - -static void gswip_get_ethtool_stats(struct dsa_switch *ds, int port, - uint64_t *data) -{ - struct gswip_priv *priv = ds->priv; - const struct gswip_rmon_cnt_desc *rmon_cnt; - int i; - u64 high; - - for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) { - rmon_cnt = &gswip_rmon_cnt[i]; - - data[i] = gswip_bcm_ram_entry_read(priv, port, - rmon_cnt->offset); - if (rmon_cnt->size == 2) { - high = gswip_bcm_ram_entry_read(priv, port, - rmon_cnt->offset + 1); - data[i] |= high << 32; - } - } -} - -static int gswip_get_sset_count(struct dsa_switch *ds, int port, int sset) -{ - if (sset != ETH_SS_STATS) - return 0; - - return ARRAY_SIZE(gswip_rmon_cnt); -} - -static struct phylink_pcs *gswip_phylink_mac_select_pcs(struct phylink_config *config, - phy_interface_t interface) -{ - struct dsa_port *dp = dsa_phylink_to_port(config); - struct gswip_priv *priv = dp->ds->priv; - - if (priv->hw_info->mac_select_pcs) - return priv->hw_info->mac_select_pcs(config, interface); - - return NULL; -} - -static const struct phylink_mac_ops gswip_phylink_mac_ops = { - .mac_config = gswip_phylink_mac_config, - .mac_link_down = gswip_phylink_mac_link_down, - .mac_link_up = gswip_phylink_mac_link_up, - .mac_select_pcs = gswip_phylink_mac_select_pcs, -}; - -static const struct dsa_switch_ops gswip_switch_ops = { - .get_tag_protocol = gswip_get_tag_protocol, - .setup = gswip_setup, - .port_setup = gswip_port_setup, - .port_enable = gswip_port_enable, - .port_disable = gswip_port_disable, - .port_bridge_join = gswip_port_bridge_join, - .port_bridge_leave = gswip_port_bridge_leave, - .port_fast_age = gswip_port_fast_age, - .port_vlan_filtering = gswip_port_vlan_filtering, - .port_vlan_add = gswip_port_vlan_add, - .port_vlan_del = gswip_port_vlan_del, - .port_stp_state_set = gswip_port_stp_state_set, - .port_fdb_add = gswip_port_fdb_add, - .port_fdb_del = gswip_port_fdb_del, - .port_fdb_dump = gswip_port_fdb_dump, - .port_change_mtu = gswip_port_change_mtu, - .port_max_mtu = gswip_port_max_mtu, - .phylink_get_caps = gswip_phylink_get_caps, - .get_strings = gswip_get_strings, - .get_ethtool_stats = gswip_get_ethtool_stats, - .get_sset_count = gswip_get_sset_count, -}; - static const struct xway_gphy_match_data xrx200a1x_gphy_data = { .fe_firmware_name = "lantiq/xrx200_phy22f_a14.bin", .ge_firmware_name = "lantiq/xrx200_phy11g_a14.bin", @@ -1887,33 +317,37 @@ static int gswip_gphy_fw_list(struct gswip_priv *priv, return err; } -static int gswip_validate_cpu_port(struct dsa_switch *ds) -{ - struct gswip_priv *priv = ds->priv; - struct dsa_port *cpu_dp; - int cpu_port = -1; - - dsa_switch_for_each_cpu_port(cpu_dp, ds) { - if (cpu_port != -1) - return dev_err_probe(ds->dev, -EINVAL, - "only a single CPU port is supported\n"); - - cpu_port = cpu_dp->index; - } - - if (cpu_port == -1) - return dev_err_probe(ds->dev, -EINVAL, "no CPU port defined\n"); +static const struct regmap_config sw_regmap_config = { + .name = "switch", + .reg_bits = 32, + .val_bits = 32, + .reg_shift = REGMAP_UPSHIFT(2), + .val_format_endian = REGMAP_ENDIAN_NATIVE, + .max_register = GSWIP_SDMA_PCTRLp(6), +}; - if (BIT(cpu_port) & ~priv->hw_info->allowed_cpu_ports) - return dev_err_probe(ds->dev, -EINVAL, - "unsupported CPU port defined\n"); +static const struct regmap_config mdio_regmap_config = { + .name = "mdio", + .reg_bits = 32, + .val_bits = 32, + .reg_shift = REGMAP_UPSHIFT(2), + .val_format_endian = REGMAP_ENDIAN_NATIVE, + .max_register = GSWIP_MDIO_PHYp(0), +}; - return 0; -} +static const struct regmap_config mii_regmap_config = { + .name = "mii", + .reg_bits = 32, + .val_bits = 32, + .reg_shift = REGMAP_UPSHIFT(2), + .val_format_endian = REGMAP_ENDIAN_NATIVE, + .max_register = GSWIP_MII_CFGp(6), +}; static int gswip_probe(struct platform_device *pdev) { struct device_node *np, *gphy_fw_np; + __iomem void *gswip, *mdio, *mii; struct device *dev = &pdev->dev; struct gswip_priv *priv; int err; @@ -1924,15 +358,27 @@ static int gswip_probe(struct platform_device *pdev) if (!priv) return -ENOMEM; - priv->gswip = devm_platform_ioremap_resource(pdev, 0); + gswip = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(gswip)) + return PTR_ERR(gswip); + + mdio = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(mdio)) + return PTR_ERR(mdio); + + mii = devm_platform_ioremap_resource(pdev, 2); + if (IS_ERR(mii)) + return PTR_ERR(mii); + + priv->gswip = devm_regmap_init_mmio(dev, gswip, &sw_regmap_config); if (IS_ERR(priv->gswip)) return PTR_ERR(priv->gswip); - priv->mdio = devm_platform_ioremap_resource(pdev, 1); + priv->mdio = devm_regmap_init_mmio(dev, mdio, &mdio_regmap_config); if (IS_ERR(priv->mdio)) return PTR_ERR(priv->mdio); - priv->mii = devm_platform_ioremap_resource(pdev, 2); + priv->mii = devm_regmap_init_mmio(dev, mii, &mii_regmap_config); if (IS_ERR(priv->mii)) return PTR_ERR(priv->mii); @@ -1944,24 +390,9 @@ static int gswip_probe(struct platform_device *pdev) if (!priv->ds) return -ENOMEM; - priv->ds->dev = dev; - priv->ds->num_ports = priv->hw_info->max_ports; - priv->ds->priv = priv; - priv->ds->ops = &gswip_switch_ops; - priv->ds->phylink_mac_ops = &gswip_phylink_mac_ops; priv->dev = dev; - mutex_init(&priv->pce_table_lock); - version = gswip_switch_r(priv, GSWIP_VERSION); - - /* The hardware has the 'major/minor' version bytes in the wrong order - * preventing numerical comparisons. Construct a 16-bit unsigned integer - * having the REV field as most significant byte and the MOD field as - * least significant byte. This is effectively swapping the two bytes of - * the version variable, but other than using swab16 it doesn't affect - * the source variable. - */ - priv->version = GSWIP_VERSION_REV(version) << 8 | - GSWIP_VERSION_MOD(version); + + regmap_read(priv->gswip, GSWIP_VERSION, &version); np = dev->of_node; switch (version) { @@ -1991,25 +422,14 @@ static int gswip_probe(struct platform_device *pdev) "gphy fw probe failed\n"); } - err = dsa_register_switch(priv->ds); - if (err) { - dev_err_probe(dev, err, "dsa switch registration failed\n"); - goto gphy_fw_remove; - } - - err = gswip_validate_cpu_port(priv->ds); + err = gswip_probe_common(priv, version); if (err) - goto disable_switch; + goto gphy_fw_remove; platform_set_drvdata(pdev, priv); - dev_info(dev, "probed GSWIP version %lx mod %lx\n", - GSWIP_VERSION_REV(version), GSWIP_VERSION_MOD(version)); return 0; -disable_switch: - gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); - dsa_unregister_switch(priv->ds); gphy_fw_remove: for (i = 0; i < priv->num_gphy_fw; i++) gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); @@ -2025,7 +445,7 @@ static void gswip_remove(struct platform_device *pdev) return; /* disable the switch */ - gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); + gswip_disable_switch(priv); dsa_unregister_switch(priv->ds); diff --git a/drivers/net/dsa/lantiq/lantiq_gswip.h b/drivers/net/dsa/lantiq/lantiq_gswip.h index 2df9c8e8cfd0b..9c38e51a75e80 100644 --- a/drivers/net/dsa/lantiq/lantiq_gswip.h +++ b/drivers/net/dsa/lantiq/lantiq_gswip.h @@ -2,6 +2,7 @@ #ifndef __LANTIQ_GSWIP_H #define __LANTIQ_GSWIP_H +#include #include #include #include @@ -81,6 +82,10 @@ #define GSWIP_MII_PCDU5 0x05 #define GSWIP_MII_PCDU_TXDLY_MASK GENMASK(2, 0) #define GSWIP_MII_PCDU_RXDLY_MASK GENMASK(9, 7) +#define GSWIP_MII_PCDU_TXDLY(x) u16_encode_bits(((x) / 500), GSWIP_MII_PCDU_TXDLY_MASK) +#define GSWIP_MII_PCDU_RXDLY(x) u16_encode_bits(((x) / 500), GSWIP_MII_PCDU_RXDLY_MASK) +#define GSWIP_MII_PCDU_RXDLY_DEFAULT 2000 /* picoseconds */ +#define GSWIP_MII_PCDU_TXDLY_DEFAULT 2000 /* picoseconds */ /* GSWIP Core Registers */ #define GSWIP_SWRES 0x000 @@ -157,8 +162,15 @@ #define GSWIP_PCE_PCTRL_0_PSTATE_LEARNING 0x3 #define GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING 0x7 #define GSWIP_PCE_PCTRL_0_PSTATE_MASK GENMASK(2, 0) +/* Ethernet Switch PCE Port Control Register 3 */ +#define GSWIP_PCE_PCTRL_3p(p) (0x483 + ((p) * 0xA)) +#define GSWIP_PCE_PCTRL_3_LNDIS BIT(15) /* Learning Disable */ #define GSWIP_PCE_VCTRL(p) (0x485 + ((p) * 0xA)) #define GSWIP_PCE_VCTRL_UVR BIT(0) /* Unknown VLAN Rule */ +#define GSWIP_PCE_VCTRL_VINR GENMASK(2, 1) /* VLAN Ingress Tag Rule */ +#define GSWIP_PCE_VCTRL_VINR_ALL 0 /* Admit tagged and untagged packets */ +#define GSWIP_PCE_VCTRL_VINR_TAGGED 1 /* Admit only tagged packets */ +#define GSWIP_PCE_VCTRL_VINR_UNTAGGED 2 /* Admit only untagged packets */ #define GSWIP_PCE_VCTRL_VIMR BIT(3) /* VLAN Ingress Member violation rule */ #define GSWIP_PCE_VCTRL_VEMR BIT(4) /* VLAN Egress Member violation rule */ #define GSWIP_PCE_VCTRL_VSR BIT(5) /* VLAN Security */ @@ -186,6 +198,12 @@ #define GSWIP_MAC_CTRL_2p(p) (0x905 + ((p) * 0xC)) #define GSWIP_MAC_CTRL_2_LCHKL BIT(2) /* Frame Length Check Long Enable */ #define GSWIP_MAC_CTRL_2_MLEN BIT(3) /* Maximum Untagged Frame Lnegth */ +#define GSWIP_MAC_CTRL_4p(p) (0x907 + ((p) * 0xC)) +#define GSWIP_MAC_CTRL_4_LPIEN BIT(7) /* LPI Mode Enable */ +#define GSWIP_MAC_CTRL_4_GWAIT_MASK GENMASK(14, 8) /* LPI Wait Time 1G */ +#define GSWIP_MAC_CTRL_4_GWAIT(t) u16_encode_bits((t), GSWIP_MAC_CTRL_4_GWAIT_MASK) +#define GSWIP_MAC_CTRL_4_WAIT_MASK GENMASK(6, 0) /* LPI Wait Time 100M */ +#define GSWIP_MAC_CTRL_4_WAIT(t) u16_encode_bits((t), GSWIP_MAC_CTRL_4_WAIT_MASK) /* Ethernet Switch Fetch DMA Port Control Register */ #define GSWIP_FDMA_PCTRLp(p) (0xA80 + ((p) * 0x6)) @@ -210,6 +228,7 @@ #define GSWIP_TABLE_MAC_BRIDGE_KEY3_FID GENMASK(5, 0) /* Filtering identifier */ #define GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT GENMASK(7, 4) /* Port on learned entries */ #define GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC BIT(0) /* Static, non-aging entry */ +#define GSWIP_TABLE_MAC_BRIDGE_VAL1_VALID BIT(1) /* Valid bit */ #define XRX200_GPHY_FW_ALIGN (16 * 1024) @@ -222,6 +241,8 @@ */ #define GSWIP_MAX_PACKET_LENGTH 2400 +#define GSWIP_VLAN_UNAWARE_PVID 0 + struct gswip_pce_microcode { u16 val_3; u16 val_2; @@ -234,6 +255,7 @@ struct gswip_hw_info { unsigned int allowed_cpu_ports; unsigned int mii_ports; int mii_port_reg_offset; + bool supports_2500m; const struct gswip_pce_microcode (*pce_microcode)[]; size_t pce_microcode_size; enum dsa_tag_protocol tag_protocol; @@ -257,9 +279,9 @@ struct gswip_vlan { }; struct gswip_priv { - __iomem void *gswip; - __iomem void *mdio; - __iomem void *mii; + struct regmap *gswip; + struct regmap *mdio; + struct regmap *mii; const struct gswip_hw_info *hw_info; const struct xway_gphy_match_data *gphy_fw_name_cfg; struct dsa_switch *ds; @@ -268,9 +290,12 @@ struct gswip_priv { struct gswip_vlan vlans[64]; int num_gphy_fw; struct gswip_gphy_fw *gphy_fw; - u32 port_vlan_filter; struct mutex pce_table_lock; u16 version; }; +void gswip_disable_switch(struct gswip_priv *priv); + +int gswip_probe_common(struct gswip_priv *priv, u32 version); + #endif /* __LANTIQ_GSWIP_H */ diff --git a/drivers/net/dsa/lantiq/lantiq_gswip_common.c b/drivers/net/dsa/lantiq/lantiq_gswip_common.c new file mode 100644 index 0000000000000..122ccea4057bb --- /dev/null +++ b/drivers/net/dsa/lantiq/lantiq_gswip_common.c @@ -0,0 +1,1737 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Lantiq / Intel / MaxLinear GSWIP common function library + * + * Copyright (C) 2025 Daniel Golle + * Copyright (C) 2023 - 2024 MaxLinear Inc. + * Copyright (C) 2022 Snap One, LLC. All rights reserved. + * Copyright (C) 2017 - 2019 Hauke Mehrtens + * Copyright (C) 2012 John Crispin + * Copyright (C) 2010 Lantiq Deutschland + * + * The VLAN and bridge model the GSWIP hardware uses does not directly + * matches the model DSA uses. + * + * The hardware has 64 possible table entries for bridges with one VLAN + * ID, one flow id and a list of ports for each bridge. All entries which + * match the same flow ID are combined in the mac learning table, they + * act as one global bridge. + * The hardware does not support VLAN filter on the port, but on the + * bridge, this driver converts the DSA model to the hardware. + * + * The CPU gets all the exception frames which do not match any forwarding + * rule and the CPU port is also added to all bridges. This makes it possible + * to handle all the special cases easily in software. + * At the initialization the driver allocates one bridge table entry for + * each switch port which is used when the port is used without an + * explicit bridge. This prevents the frames from being forwarded + * between all LAN ports by default. + */ + +#include "lantiq_gswip.h" + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct gswip_pce_table_entry { + u16 index; // PCE_TBL_ADDR.ADDR = pData->table_index + u16 table; // PCE_TBL_CTRL.ADDR = pData->table + u16 key[8]; + u16 val[5]; + u16 mask; + u8 gmap; + bool type; + bool valid; + bool key_mode; +}; + +struct gswip_rmon_cnt_desc { + unsigned int size; + unsigned int offset; + const char *name; +}; + +#define MIB_DESC(_size, _offset, _name) {.size = _size, .offset = _offset, .name = _name} + +static const struct gswip_rmon_cnt_desc gswip_rmon_cnt[] = { + /** Receive Packet Count (only packets that are accepted and not discarded). */ + MIB_DESC(1, 0x1F, "RxGoodPkts"), + MIB_DESC(1, 0x23, "RxUnicastPkts"), + MIB_DESC(1, 0x22, "RxMulticastPkts"), + MIB_DESC(1, 0x21, "RxFCSErrorPkts"), + MIB_DESC(1, 0x1D, "RxUnderSizeGoodPkts"), + MIB_DESC(1, 0x1E, "RxUnderSizeErrorPkts"), + MIB_DESC(1, 0x1B, "RxOversizeGoodPkts"), + MIB_DESC(1, 0x1C, "RxOversizeErrorPkts"), + MIB_DESC(1, 0x20, "RxGoodPausePkts"), + MIB_DESC(1, 0x1A, "RxAlignErrorPkts"), + MIB_DESC(1, 0x12, "Rx64BytePkts"), + MIB_DESC(1, 0x13, "Rx127BytePkts"), + MIB_DESC(1, 0x14, "Rx255BytePkts"), + MIB_DESC(1, 0x15, "Rx511BytePkts"), + MIB_DESC(1, 0x16, "Rx1023BytePkts"), + /** Receive Size 1024-1522 (or more, if configured) Packet Count. */ + MIB_DESC(1, 0x17, "RxMaxBytePkts"), + MIB_DESC(1, 0x18, "RxDroppedPkts"), + MIB_DESC(1, 0x19, "RxFilteredPkts"), + MIB_DESC(2, 0x24, "RxGoodBytes"), + MIB_DESC(2, 0x26, "RxBadBytes"), + MIB_DESC(1, 0x11, "TxAcmDroppedPkts"), + MIB_DESC(1, 0x0C, "TxGoodPkts"), + MIB_DESC(1, 0x06, "TxUnicastPkts"), + MIB_DESC(1, 0x07, "TxMulticastPkts"), + MIB_DESC(1, 0x00, "Tx64BytePkts"), + MIB_DESC(1, 0x01, "Tx127BytePkts"), + MIB_DESC(1, 0x02, "Tx255BytePkts"), + MIB_DESC(1, 0x03, "Tx511BytePkts"), + MIB_DESC(1, 0x04, "Tx1023BytePkts"), + /** Transmit Size 1024-1522 (or more, if configured) Packet Count. */ + MIB_DESC(1, 0x05, "TxMaxBytePkts"), + MIB_DESC(1, 0x08, "TxSingleCollCount"), + MIB_DESC(1, 0x09, "TxMultCollCount"), + MIB_DESC(1, 0x0A, "TxLateCollCount"), + MIB_DESC(1, 0x0B, "TxExcessCollCount"), + MIB_DESC(1, 0x0D, "TxPauseCount"), + MIB_DESC(1, 0x10, "TxDroppedPkts"), + MIB_DESC(2, 0x0E, "TxGoodBytes"), +}; + +static u32 gswip_switch_r_timeout(struct gswip_priv *priv, u32 offset, + u32 cleared) +{ + u32 val; + + return regmap_read_poll_timeout(priv->gswip, offset, val, + !(val & cleared), 20, 50000); +} + +static void gswip_mii_mask_cfg(struct gswip_priv *priv, u32 mask, u32 set, + int port) +{ + int reg_port; + + /* MII_CFG register only exists for MII ports */ + if (!(priv->hw_info->mii_ports & BIT(port))) + return; + + reg_port = port + priv->hw_info->mii_port_reg_offset; + + regmap_write_bits(priv->mii, GSWIP_MII_CFGp(reg_port), mask, + set); +} + +static int gswip_mdio_poll(struct gswip_priv *priv) +{ + u32 ctrl; + + return regmap_read_poll_timeout(priv->mdio, GSWIP_MDIO_CTRL, ctrl, + !(ctrl & GSWIP_MDIO_CTRL_BUSY), 40, 4000); +} + +static int gswip_mdio_wr(struct mii_bus *bus, int addr, int reg, u16 val) +{ + struct gswip_priv *priv = bus->priv; + int err; + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + regmap_write(priv->mdio, GSWIP_MDIO_WRITE, val); + regmap_write(priv->mdio, GSWIP_MDIO_CTRL, + GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_WR | + ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | + (reg & GSWIP_MDIO_CTRL_REGAD_MASK)); + + return 0; +} + +static int gswip_mdio_rd(struct mii_bus *bus, int addr, int reg) +{ + struct gswip_priv *priv = bus->priv; + u32 val; + int err; + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + regmap_write(priv->mdio, GSWIP_MDIO_CTRL, + GSWIP_MDIO_CTRL_BUSY | GSWIP_MDIO_CTRL_RD | + ((addr & GSWIP_MDIO_CTRL_PHYAD_MASK) << GSWIP_MDIO_CTRL_PHYAD_SHIFT) | + (reg & GSWIP_MDIO_CTRL_REGAD_MASK)); + + err = gswip_mdio_poll(priv); + if (err) { + dev_err(&bus->dev, "waiting for MDIO bus busy timed out\n"); + return err; + } + + err = regmap_read(priv->mdio, GSWIP_MDIO_READ, &val); + if (err) + return err; + + return val; +} + +static int gswip_mdio(struct gswip_priv *priv) +{ + struct device_node *mdio_np, *switch_np = priv->dev->of_node; + struct device *dev = priv->dev; + struct mii_bus *bus; + int err = 0; + + mdio_np = of_get_compatible_child(switch_np, "lantiq,xrx200-mdio"); + if (!mdio_np) + mdio_np = of_get_child_by_name(switch_np, "mdio"); + + if (!of_device_is_available(mdio_np)) + goto out_put_node; + + bus = devm_mdiobus_alloc(dev); + if (!bus) { + err = -ENOMEM; + goto out_put_node; + } + + bus->priv = priv; + bus->read = gswip_mdio_rd; + bus->write = gswip_mdio_wr; + bus->name = "lantiq,xrx200-mdio"; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(priv->dev)); + bus->parent = priv->dev; + + err = devm_of_mdiobus_register(dev, bus, mdio_np); + +out_put_node: + of_node_put(mdio_np); + + return err; +} + +static int gswip_pce_table_entry_read(struct gswip_priv *priv, + struct gswip_pce_table_entry *tbl) +{ + int i; + int err; + u32 crtl; + u32 tmp; + u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSRD : + GSWIP_PCE_TBL_CTRL_OPMOD_ADRD; + + mutex_lock(&priv->pce_table_lock); + + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + if (err) + goto out_unlock; + + regmap_write(priv->gswip, GSWIP_PCE_TBL_ADDR, tbl->index); + regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_ADDR_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_MASK | + GSWIP_PCE_TBL_CTRL_BAS, + tbl->table | addr_mode | GSWIP_PCE_TBL_CTRL_BAS); + + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + if (err) + goto out_unlock; + + for (i = 0; i < ARRAY_SIZE(tbl->key); i++) { + err = regmap_read(priv->gswip, GSWIP_PCE_TBL_KEY(i), &tmp); + if (err) + goto out_unlock; + tbl->key[i] = tmp; + } + for (i = 0; i < ARRAY_SIZE(tbl->val); i++) { + err = regmap_read(priv->gswip, GSWIP_PCE_TBL_VAL(i), &tmp); + if (err) + goto out_unlock; + tbl->val[i] = tmp; + } + + err = regmap_read(priv->gswip, GSWIP_PCE_TBL_MASK, &tmp); + if (err) + goto out_unlock; + + tbl->mask = tmp; + err = regmap_read(priv->gswip, GSWIP_PCE_TBL_CTRL, &crtl); + if (err) + goto out_unlock; + + tbl->type = !!(crtl & GSWIP_PCE_TBL_CTRL_TYPE); + tbl->valid = !!(crtl & GSWIP_PCE_TBL_CTRL_VLD); + tbl->gmap = (crtl & GSWIP_PCE_TBL_CTRL_GMAP_MASK) >> 7; + +out_unlock: + mutex_unlock(&priv->pce_table_lock); + + return err; +} + +static int gswip_pce_table_entry_write(struct gswip_priv *priv, + struct gswip_pce_table_entry *tbl) +{ + int i; + int err; + u32 crtl; + u16 addr_mode = tbl->key_mode ? GSWIP_PCE_TBL_CTRL_OPMOD_KSWR : + GSWIP_PCE_TBL_CTRL_OPMOD_ADWR; + + mutex_lock(&priv->pce_table_lock); + + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + if (err) { + mutex_unlock(&priv->pce_table_lock); + return err; + } + + regmap_write(priv->gswip, GSWIP_PCE_TBL_ADDR, tbl->index); + regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_ADDR_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_MASK, + tbl->table | addr_mode); + + for (i = 0; i < ARRAY_SIZE(tbl->key); i++) + regmap_write(priv->gswip, GSWIP_PCE_TBL_KEY(i), tbl->key[i]); + + for (i = 0; i < ARRAY_SIZE(tbl->val); i++) + regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(i), tbl->val[i]); + + regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_ADDR_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_MASK, + tbl->table | addr_mode); + + regmap_write(priv->gswip, GSWIP_PCE_TBL_MASK, tbl->mask); + + regmap_read(priv->gswip, GSWIP_PCE_TBL_CTRL, &crtl); + crtl &= ~(GSWIP_PCE_TBL_CTRL_TYPE | GSWIP_PCE_TBL_CTRL_VLD | + GSWIP_PCE_TBL_CTRL_GMAP_MASK); + if (tbl->type) + crtl |= GSWIP_PCE_TBL_CTRL_TYPE; + if (tbl->valid) + crtl |= GSWIP_PCE_TBL_CTRL_VLD; + crtl |= (tbl->gmap << 7) & GSWIP_PCE_TBL_CTRL_GMAP_MASK; + crtl |= GSWIP_PCE_TBL_CTRL_BAS; + regmap_write(priv->gswip, GSWIP_PCE_TBL_CTRL, crtl); + + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + + mutex_unlock(&priv->pce_table_lock); + + return err; +} + +/* Add the LAN port into a bridge with the CPU port by + * default. This prevents automatic forwarding of + * packages between the LAN ports when no explicit + * bridge is configured. + */ +static int gswip_add_single_port_br(struct gswip_priv *priv, int port, bool add) +{ + struct gswip_pce_table_entry vlan_active = {0,}; + struct gswip_pce_table_entry vlan_mapping = {0,}; + int err; + + vlan_active.index = port + 1; + vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; + vlan_active.key[0] = GSWIP_VLAN_UNAWARE_PVID; + vlan_active.val[0] = port + 1 /* fid */; + vlan_active.valid = add; + err = gswip_pce_table_entry_write(priv, &vlan_active); + if (err) { + dev_err(priv->dev, "failed to write active VLAN: %d\n", err); + return err; + } + + if (!add) + return 0; + + vlan_mapping.index = port + 1; + vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; + vlan_mapping.val[0] = GSWIP_VLAN_UNAWARE_PVID; + vlan_mapping.val[1] = BIT(port) | dsa_cpu_ports(priv->ds); + vlan_mapping.val[2] = 0; + err = gswip_pce_table_entry_write(priv, &vlan_mapping); + if (err) { + dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); + return err; + } + + return 0; +} + +static int gswip_port_set_learning(struct gswip_priv *priv, int port, + bool enable) +{ + if (!GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2)) + return -EOPNOTSUPP; + + /* learning disable bit */ + return regmap_update_bits(priv->gswip, GSWIP_PCE_PCTRL_3p(port), + GSWIP_PCE_PCTRL_3_LNDIS, + enable ? 0 : GSWIP_PCE_PCTRL_3_LNDIS); +} + +static int gswip_port_pre_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + struct gswip_priv *priv = ds->priv; + unsigned long supported = 0; + + if (GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2)) + supported |= BR_LEARNING; + + if (flags.mask & ~supported) + return -EINVAL; + + return 0; +} + +static int gswip_port_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + struct gswip_priv *priv = ds->priv; + + if (flags.mask & BR_LEARNING) + return gswip_port_set_learning(priv, port, + !!(flags.val & BR_LEARNING)); + + return 0; +} + +static int gswip_port_setup(struct dsa_switch *ds, int port) +{ + struct gswip_priv *priv = ds->priv; + int err; + + if (!dsa_is_cpu_port(ds, port)) { + err = gswip_add_single_port_br(priv, port, true); + if (err) + return err; + } + + return 0; +} + +static int gswip_port_enable(struct dsa_switch *ds, int port, + struct phy_device *phydev) +{ + struct gswip_priv *priv = ds->priv; + + if (!dsa_is_cpu_port(ds, port)) { + u32 mdio_phy = 0; + + if (phydev) + mdio_phy = phydev->mdio.addr & GSWIP_MDIO_PHY_ADDR_MASK; + + regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port), + GSWIP_MDIO_PHY_ADDR_MASK, + mdio_phy); + } + + /* RMON Counter Enable for port */ + regmap_write(priv->gswip, GSWIP_BM_PCFGp(port), GSWIP_BM_PCFG_CNTEN); + + /* enable port fetch/store dma & VLAN Modification */ + regmap_set_bits(priv->gswip, GSWIP_FDMA_PCTRLp(port), + GSWIP_FDMA_PCTRL_EN | GSWIP_FDMA_PCTRL_VLANMOD_BOTH); + regmap_set_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port), + GSWIP_SDMA_PCTRL_EN); + + return 0; +} + +static void gswip_port_disable(struct dsa_switch *ds, int port) +{ + struct gswip_priv *priv = ds->priv; + + regmap_clear_bits(priv->gswip, GSWIP_FDMA_PCTRLp(port), + GSWIP_FDMA_PCTRL_EN); + regmap_clear_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port), + GSWIP_SDMA_PCTRL_EN); +} + +static int gswip_pce_load_microcode(struct gswip_priv *priv) +{ + int i; + int err; + + regmap_write_bits(priv->gswip, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_ADDR_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_MASK | + GSWIP_PCE_TBL_CTRL_OPMOD_ADWR, + GSWIP_PCE_TBL_CTRL_OPMOD_ADWR); + regmap_write(priv->gswip, GSWIP_PCE_TBL_MASK, 0); + + for (i = 0; i < priv->hw_info->pce_microcode_size; i++) { + regmap_write(priv->gswip, GSWIP_PCE_TBL_ADDR, i); + regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(0), + (*priv->hw_info->pce_microcode)[i].val_0); + regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(1), + (*priv->hw_info->pce_microcode)[i].val_1); + regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(2), + (*priv->hw_info->pce_microcode)[i].val_2); + regmap_write(priv->gswip, GSWIP_PCE_TBL_VAL(3), + (*priv->hw_info->pce_microcode)[i].val_3); + + /* start the table access: */ + regmap_set_bits(priv->gswip, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + err = gswip_switch_r_timeout(priv, GSWIP_PCE_TBL_CTRL, + GSWIP_PCE_TBL_CTRL_BAS); + if (err) + return err; + } + + /* tell the switch that the microcode is loaded */ + regmap_set_bits(priv->gswip, GSWIP_PCE_GCTRL_0, + GSWIP_PCE_GCTRL_0_MC_VALID); + + return 0; +} + +static void gswip_port_commit_pvid(struct gswip_priv *priv, int port) +{ + struct dsa_port *dp = dsa_to_port(priv->ds, port); + struct net_device *br = dsa_port_bridge_dev_get(dp); + u32 vinr; + int idx; + + if (!dsa_port_is_user(dp)) + return; + + if (br) { + u16 pvid = GSWIP_VLAN_UNAWARE_PVID; + + if (br_vlan_enabled(br)) + br_vlan_get_pvid(br, &pvid); + + /* VLAN-aware bridge ports with no PVID will use Active VLAN + * index 0. The expectation is that this drops all untagged and + * VID-0 tagged ingress traffic. + */ + idx = 0; + for (int i = priv->hw_info->max_ports; + i < ARRAY_SIZE(priv->vlans); i++) { + if (priv->vlans[i].bridge == br && + priv->vlans[i].vid == pvid) { + idx = i; + break; + } + } + } else { + /* The Active VLAN table index as configured by + * gswip_add_single_port_br() + */ + idx = port + 1; + } + + vinr = idx ? GSWIP_PCE_VCTRL_VINR_ALL : GSWIP_PCE_VCTRL_VINR_TAGGED; + regmap_write_bits(priv->gswip, GSWIP_PCE_VCTRL(port), + GSWIP_PCE_VCTRL_VINR, + FIELD_PREP(GSWIP_PCE_VCTRL_VINR, vinr)); + + /* Note that in GSWIP 2.2 VLAN mode the VID needs to be programmed + * directly instead of referencing the index in the Active VLAN Tablet. + * However, without the VLANMD bit (9) in PCE_GCTRL_1 (0x457) even + * GSWIP 2.2 and newer hardware maintain the GSWIP 2.1 behavior. + */ + regmap_write(priv->gswip, GSWIP_PCE_DEFPVID(port), idx); +} + +static int gswip_port_vlan_filtering(struct dsa_switch *ds, int port, + bool vlan_filtering, + struct netlink_ext_ack *extack) +{ + struct gswip_priv *priv = ds->priv; + + if (vlan_filtering) { + /* Use tag based VLAN */ + regmap_write_bits(priv->gswip, GSWIP_PCE_VCTRL(port), + GSWIP_PCE_VCTRL_VSR | + GSWIP_PCE_VCTRL_UVR | + GSWIP_PCE_VCTRL_VIMR | + GSWIP_PCE_VCTRL_VEMR | + GSWIP_PCE_VCTRL_VID0, + GSWIP_PCE_VCTRL_UVR | + GSWIP_PCE_VCTRL_VIMR | + GSWIP_PCE_VCTRL_VEMR | + GSWIP_PCE_VCTRL_VID0); + regmap_clear_bits(priv->gswip, GSWIP_PCE_PCTRL_0p(port), + GSWIP_PCE_PCTRL_0_TVM); + } else { + /* Use port based VLAN */ + regmap_write_bits(priv->gswip, GSWIP_PCE_VCTRL(port), + GSWIP_PCE_VCTRL_UVR | + GSWIP_PCE_VCTRL_VIMR | + GSWIP_PCE_VCTRL_VEMR | + GSWIP_PCE_VCTRL_VID0 | + GSWIP_PCE_VCTRL_VSR, + GSWIP_PCE_VCTRL_VSR); + regmap_set_bits(priv->gswip, GSWIP_PCE_PCTRL_0p(port), + GSWIP_PCE_PCTRL_0_TVM); + } + + gswip_port_commit_pvid(priv, port); + + return 0; +} + +static void gswip_mii_delay_setup(struct gswip_priv *priv, struct dsa_port *dp, + phy_interface_t interface) +{ + u32 tx_delay = GSWIP_MII_PCDU_TXDLY_DEFAULT; + u32 rx_delay = GSWIP_MII_PCDU_RXDLY_DEFAULT; + struct device_node *port_dn = dp->dn; + u16 mii_pcdu_reg; + + /* As MII_PCDU registers only exist for MII ports, silently return + * unless the port is an MII port + */ + if (!(priv->hw_info->mii_ports & BIT(dp->index))) + return; + + switch (dp->index + priv->hw_info->mii_port_reg_offset) { + case 0: + mii_pcdu_reg = GSWIP_MII_PCDU0; + break; + case 1: + mii_pcdu_reg = GSWIP_MII_PCDU1; + break; + case 5: + mii_pcdu_reg = GSWIP_MII_PCDU5; + break; + default: + return; + } + + /* legacy code to set default delays according to the interface mode */ + switch (interface) { + case PHY_INTERFACE_MODE_RGMII_ID: + tx_delay = 0; + rx_delay = 0; + break; + case PHY_INTERFACE_MODE_RGMII_RXID: + rx_delay = 0; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + tx_delay = 0; + break; + default: + break; + } + + /* allow settings delays using device tree properties */ + of_property_read_u32(port_dn, "rx-internal-delay-ps", &rx_delay); + of_property_read_u32(port_dn, "tx-internal-delay-ps", &tx_delay); + + regmap_write_bits(priv->mii, mii_pcdu_reg, + GSWIP_MII_PCDU_TXDLY_MASK | + GSWIP_MII_PCDU_RXDLY_MASK, + GSWIP_MII_PCDU_TXDLY(tx_delay) | + GSWIP_MII_PCDU_RXDLY(rx_delay)); +} + +static int gswip_setup(struct dsa_switch *ds) +{ + unsigned int cpu_ports = dsa_cpu_ports(ds); + struct gswip_priv *priv = ds->priv; + struct dsa_port *cpu_dp; + int err, i; + + regmap_write(priv->gswip, GSWIP_SWRES, GSWIP_SWRES_R0); + usleep_range(5000, 10000); + regmap_write(priv->gswip, GSWIP_SWRES, 0); + + /* disable port fetch/store dma on all ports */ + for (i = 0; i < priv->hw_info->max_ports; i++) { + gswip_port_disable(ds, i); + gswip_port_vlan_filtering(ds, i, false, NULL); + } + + /* enable Switch */ + regmap_set_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE); + + err = gswip_pce_load_microcode(priv); + if (err) { + dev_err(priv->dev, "writing PCE microcode failed, %i\n", err); + return err; + } + + /* Default unknown Broadcast/Multicast/Unicast port maps */ + regmap_write(priv->gswip, GSWIP_PCE_PMAP1, cpu_ports); + regmap_write(priv->gswip, GSWIP_PCE_PMAP2, cpu_ports); + regmap_write(priv->gswip, GSWIP_PCE_PMAP3, cpu_ports); + + /* Deactivate MDIO PHY auto polling. Some PHYs as the AR8030 have an + * interoperability problem with this auto polling mechanism because + * their status registers think that the link is in a different state + * than it actually is. For the AR8030 it has the BMSR_ESTATEN bit set + * as well as ESTATUS_1000_TFULL and ESTATUS_1000_XFULL. This makes the + * auto polling state machine consider the link being negotiated with + * 1Gbit/s. Since the PHY itself is a Fast Ethernet RMII PHY this leads + * to the switch port being completely dead (RX and TX are both not + * working). + * Also with various other PHY / port combinations (PHY11G GPHY, PHY22F + * GPHY, external RGMII PEF7071/7072) any traffic would stop. Sometimes + * it would work fine for a few minutes to hours and then stop, on + * other device it would no traffic could be sent or received at all. + * Testing shows that when PHY auto polling is disabled these problems + * go away. + */ + regmap_write(priv->mdio, GSWIP_MDIO_MDC_CFG0, 0x0); + + /* Configure the MDIO Clock 2.5 MHz */ + regmap_write_bits(priv->mdio, GSWIP_MDIO_MDC_CFG1, 0xff, 0x09); + + /* bring up the mdio bus */ + err = gswip_mdio(priv); + if (err) { + dev_err(priv->dev, "mdio bus setup failed\n"); + return err; + } + + /* Disable the xMII interface and clear it's isolation bit */ + for (i = 0; i < priv->hw_info->max_ports; i++) + gswip_mii_mask_cfg(priv, + GSWIP_MII_CFG_EN | GSWIP_MII_CFG_ISOLATE, + 0, i); + + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + /* enable special tag insertion on cpu port */ + regmap_set_bits(priv->gswip, GSWIP_FDMA_PCTRLp(cpu_dp->index), + GSWIP_FDMA_PCTRL_STEN); + + /* accept special tag in ingress direction */ + regmap_set_bits(priv->gswip, + GSWIP_PCE_PCTRL_0p(cpu_dp->index), + GSWIP_PCE_PCTRL_0_INGRESS); + } + + regmap_set_bits(priv->gswip, GSWIP_BM_QUEUE_GCTRL, + GSWIP_BM_QUEUE_GCTRL_GL_MOD); + + /* VLAN aware Switching */ + regmap_set_bits(priv->gswip, GSWIP_PCE_GCTRL_0, + GSWIP_PCE_GCTRL_0_VLAN); + + /* Flush MAC Table */ + regmap_set_bits(priv->gswip, GSWIP_PCE_GCTRL_0, + GSWIP_PCE_GCTRL_0_MTFL); + + err = gswip_switch_r_timeout(priv, GSWIP_PCE_GCTRL_0, + GSWIP_PCE_GCTRL_0_MTFL); + if (err) { + dev_err(priv->dev, "MAC flushing didn't finish\n"); + return err; + } + + ds->mtu_enforcement_ingress = true; + + return 0; +} + +static enum dsa_tag_protocol gswip_get_tag_protocol(struct dsa_switch *ds, + int port, + enum dsa_tag_protocol mp) +{ + struct gswip_priv *priv = ds->priv; + + return priv->hw_info->tag_protocol; +} + +static int gswip_vlan_active_create(struct gswip_priv *priv, + struct net_device *bridge, + int fid, u16 vid) +{ + struct gswip_pce_table_entry vlan_active = {0,}; + unsigned int max_ports = priv->hw_info->max_ports; + int idx = -1; + int err; + int i; + + /* Look for a free slot */ + for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { + if (!priv->vlans[i].bridge) { + idx = i; + break; + } + } + + if (idx == -1) + return -ENOSPC; + + if (fid == -1) + fid = idx; + + vlan_active.index = idx; + vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; + vlan_active.key[0] = vid; + vlan_active.val[0] = fid; + vlan_active.valid = true; + + err = gswip_pce_table_entry_write(priv, &vlan_active); + if (err) { + dev_err(priv->dev, "failed to write active VLAN: %d\n", err); + return err; + } + + priv->vlans[idx].bridge = bridge; + priv->vlans[idx].vid = vid; + priv->vlans[idx].fid = fid; + + return idx; +} + +static int gswip_vlan_active_remove(struct gswip_priv *priv, int idx) +{ + struct gswip_pce_table_entry vlan_active = {0,}; + int err; + + vlan_active.index = idx; + vlan_active.table = GSWIP_TABLE_ACTIVE_VLAN; + vlan_active.valid = false; + err = gswip_pce_table_entry_write(priv, &vlan_active); + if (err) + dev_err(priv->dev, "failed to delete active VLAN: %d\n", err); + priv->vlans[idx].bridge = NULL; + + return err; +} + +static int gswip_vlan_add(struct gswip_priv *priv, struct net_device *bridge, + int port, u16 vid, bool untagged, bool pvid, + bool vlan_aware) +{ + struct gswip_pce_table_entry vlan_mapping = {0,}; + unsigned int max_ports = priv->hw_info->max_ports; + unsigned int cpu_ports = dsa_cpu_ports(priv->ds); + bool active_vlan_created = false; + int fid = -1, idx = -1; + int i, err; + + /* Check if there is already a page for this bridge */ + for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { + if (priv->vlans[i].bridge == bridge) { + if (vlan_aware) { + if (fid != -1 && fid != priv->vlans[i].fid) + dev_err(priv->dev, "one bridge with multiple flow ids\n"); + fid = priv->vlans[i].fid; + } + if (priv->vlans[i].vid == vid) { + idx = i; + break; + } + } + } + + /* If this bridge is not programmed yet, add a Active VLAN table + * entry in a free slot and prepare the VLAN mapping table entry. + */ + if (idx == -1) { + idx = gswip_vlan_active_create(priv, bridge, fid, vid); + if (idx < 0) + return idx; + active_vlan_created = true; + + vlan_mapping.index = idx; + vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; + } else { + /* Read the existing VLAN mapping entry from the switch */ + vlan_mapping.index = idx; + vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; + err = gswip_pce_table_entry_read(priv, &vlan_mapping); + if (err) { + dev_err(priv->dev, "failed to read VLAN mapping: %d\n", + err); + return err; + } + } + + /* VLAN ID byte, maps to the VLAN ID of vlan active table */ + vlan_mapping.val[0] = vid; + /* Update the VLAN mapping entry and write it to the switch */ + vlan_mapping.val[1] |= cpu_ports; + vlan_mapping.val[1] |= BIT(port); + if (vlan_aware) + vlan_mapping.val[2] |= cpu_ports; + if (untagged) + vlan_mapping.val[2] &= ~BIT(port); + else + vlan_mapping.val[2] |= BIT(port); + err = gswip_pce_table_entry_write(priv, &vlan_mapping); + if (err) { + dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); + /* In case an Active VLAN was creaetd delete it again */ + if (active_vlan_created) + gswip_vlan_active_remove(priv, idx); + return err; + } + + gswip_port_commit_pvid(priv, port); + + return 0; +} + +static int gswip_vlan_remove(struct gswip_priv *priv, + struct net_device *bridge, int port, + u16 vid) +{ + struct gswip_pce_table_entry vlan_mapping = {0,}; + unsigned int max_ports = priv->hw_info->max_ports; + int idx = -1; + int i; + int err; + + /* Check if there is already a page for this bridge */ + for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { + if (priv->vlans[i].bridge == bridge && + priv->vlans[i].vid == vid) { + idx = i; + break; + } + } + + if (idx == -1) { + dev_err(priv->dev, "Port %d cannot find VID %u of bridge %s\n", + port, vid, bridge ? bridge->name : "(null)"); + return -ENOENT; + } + + vlan_mapping.index = idx; + vlan_mapping.table = GSWIP_TABLE_VLAN_MAPPING; + err = gswip_pce_table_entry_read(priv, &vlan_mapping); + if (err) { + dev_err(priv->dev, "failed to read VLAN mapping: %d\n", err); + return err; + } + + vlan_mapping.val[1] &= ~BIT(port); + vlan_mapping.val[2] &= ~BIT(port); + err = gswip_pce_table_entry_write(priv, &vlan_mapping); + if (err) { + dev_err(priv->dev, "failed to write VLAN mapping: %d\n", err); + return err; + } + + /* In case all ports are removed from the bridge, remove the VLAN */ + if (!(vlan_mapping.val[1] & ~dsa_cpu_ports(priv->ds))) { + err = gswip_vlan_active_remove(priv, idx); + if (err) { + dev_err(priv->dev, "failed to write active VLAN: %d\n", + err); + return err; + } + } + + gswip_port_commit_pvid(priv, port); + + return 0; +} + +static int gswip_port_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge, + bool *tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + struct net_device *br = bridge.dev; + struct gswip_priv *priv = ds->priv; + int err; + + /* Set up the VLAN for VLAN-unaware bridging for this port, and remove + * it from the "single-port bridge" through which it was operating as + * standalone. + */ + err = gswip_vlan_add(priv, br, port, GSWIP_VLAN_UNAWARE_PVID, + true, true, false); + if (err) + return err; + + return gswip_add_single_port_br(priv, port, false); +} + +static void gswip_port_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge) +{ + struct net_device *br = bridge.dev; + struct gswip_priv *priv = ds->priv; + + /* Add the port back to the "single-port bridge", and remove it from + * the VLAN-unaware PVID created for this bridge. + */ + gswip_add_single_port_br(priv, port, true); + gswip_vlan_remove(priv, br, port, GSWIP_VLAN_UNAWARE_PVID); +} + +static int gswip_port_vlan_prepare(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); + struct gswip_priv *priv = ds->priv; + unsigned int max_ports = priv->hw_info->max_ports; + int pos = max_ports; + int i, idx = -1; + + /* We only support VLAN filtering on bridges */ + if (!dsa_is_cpu_port(ds, port) && !bridge) + return -EOPNOTSUPP; + + /* Check if there is already a page for this VLAN */ + for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { + if (priv->vlans[i].bridge == bridge && + priv->vlans[i].vid == vlan->vid) { + idx = i; + break; + } + } + + /* If this VLAN is not programmed yet, we have to reserve + * one entry in the VLAN table. Make sure we start at the + * next position round. + */ + if (idx == -1) { + /* Look for a free slot */ + for (; pos < ARRAY_SIZE(priv->vlans); pos++) { + if (!priv->vlans[pos].bridge) { + idx = pos; + pos++; + break; + } + } + + if (idx == -1) { + NL_SET_ERR_MSG_MOD(extack, "No slot in VLAN table"); + return -ENOSPC; + } + } + + return 0; +} + +static int gswip_port_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); + struct gswip_priv *priv = ds->priv; + bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; + bool pvid = vlan->flags & BRIDGE_VLAN_INFO_PVID; + int err; + + if (vlan->vid == GSWIP_VLAN_UNAWARE_PVID) + return 0; + + err = gswip_port_vlan_prepare(ds, port, vlan, extack); + if (err) + return err; + + /* We have to receive all packets on the CPU port and should not + * do any VLAN filtering here. This is also called with bridge + * NULL and then we do not know for which bridge to configure + * this. + */ + if (dsa_is_cpu_port(ds, port)) + return 0; + + return gswip_vlan_add(priv, bridge, port, vlan->vid, untagged, pvid, + true); +} + +static int gswip_port_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct net_device *bridge = dsa_port_bridge_dev_get(dsa_to_port(ds, port)); + struct gswip_priv *priv = ds->priv; + + if (vlan->vid == GSWIP_VLAN_UNAWARE_PVID) + return 0; + + /* We have to receive all packets on the CPU port and should not + * do any VLAN filtering here. This is also called with bridge + * NULL and then we do not know for which bridge to configure + * this. + */ + if (dsa_is_cpu_port(ds, port)) + return 0; + + return gswip_vlan_remove(priv, bridge, port, vlan->vid); +} + +static void gswip_port_fast_age(struct dsa_switch *ds, int port) +{ + struct gswip_priv *priv = ds->priv; + struct gswip_pce_table_entry mac_bridge = {0,}; + int i; + int err; + + for (i = 0; i < 2048; i++) { + mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE; + mac_bridge.index = i; + + err = gswip_pce_table_entry_read(priv, &mac_bridge); + if (err) { + dev_err(priv->dev, "failed to read mac bridge: %d\n", + err); + return; + } + + if (!mac_bridge.valid) + continue; + + if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) + continue; + + if (port != FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT, + mac_bridge.val[0])) + continue; + + mac_bridge.valid = false; + err = gswip_pce_table_entry_write(priv, &mac_bridge); + if (err) { + dev_err(priv->dev, "failed to write mac bridge: %d\n", + err); + return; + } + } +} + +static void gswip_port_stp_state_set(struct dsa_switch *ds, int port, u8 state) +{ + struct gswip_priv *priv = ds->priv; + u32 stp_state; + + switch (state) { + case BR_STATE_DISABLED: + regmap_clear_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port), + GSWIP_SDMA_PCTRL_EN); + return; + case BR_STATE_BLOCKING: + case BR_STATE_LISTENING: + stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LISTEN; + break; + case BR_STATE_LEARNING: + stp_state = GSWIP_PCE_PCTRL_0_PSTATE_LEARNING; + break; + case BR_STATE_FORWARDING: + stp_state = GSWIP_PCE_PCTRL_0_PSTATE_FORWARDING; + break; + default: + dev_err(priv->dev, "invalid STP state: %d\n", state); + return; + } + + regmap_set_bits(priv->gswip, GSWIP_SDMA_PCTRLp(port), + GSWIP_SDMA_PCTRL_EN); + regmap_write_bits(priv->gswip, GSWIP_PCE_PCTRL_0p(port), + GSWIP_PCE_PCTRL_0_PSTATE_MASK, + stp_state); +} + +static int gswip_port_fdb(struct dsa_switch *ds, int port, + struct net_device *bridge, const unsigned char *addr, + u16 vid, bool add) +{ + struct gswip_priv *priv = ds->priv; + struct gswip_pce_table_entry mac_bridge = {0,}; + unsigned int max_ports = priv->hw_info->max_ports; + int fid = -1; + int i; + int err; + + for (i = max_ports; i < ARRAY_SIZE(priv->vlans); i++) { + if (priv->vlans[i].bridge == bridge) { + fid = priv->vlans[i].fid; + break; + } + } + + if (fid == -1) { + dev_err(priv->dev, "no FID found for bridge %s\n", + bridge->name); + return -EINVAL; + } + + mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE; + mac_bridge.key_mode = true; + mac_bridge.key[0] = addr[5] | (addr[4] << 8); + mac_bridge.key[1] = addr[3] | (addr[2] << 8); + mac_bridge.key[2] = addr[1] | (addr[0] << 8); + mac_bridge.key[3] = FIELD_PREP(GSWIP_TABLE_MAC_BRIDGE_KEY3_FID, fid); + mac_bridge.val[0] = add ? BIT(port) : 0; /* port map */ + if (GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2_ETC)) + mac_bridge.val[1] = add ? (GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC | + GSWIP_TABLE_MAC_BRIDGE_VAL1_VALID) : 0; + else + mac_bridge.val[1] = GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC; + + mac_bridge.valid = add; + + err = gswip_pce_table_entry_write(priv, &mac_bridge); + if (err) + dev_err(priv->dev, "failed to write mac bridge: %d\n", err); + + return err; +} + +static int gswip_port_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + if (db.type != DSA_DB_BRIDGE) + return -EOPNOTSUPP; + + return gswip_port_fdb(ds, port, db.bridge.dev, addr, vid, true); +} + +static int gswip_port_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, + struct dsa_db db) +{ + if (db.type != DSA_DB_BRIDGE) + return -EOPNOTSUPP; + + return gswip_port_fdb(ds, port, db.bridge.dev, addr, vid, false); +} + +static int gswip_port_fdb_dump(struct dsa_switch *ds, int port, + dsa_fdb_dump_cb_t *cb, void *data) +{ + struct gswip_priv *priv = ds->priv; + struct gswip_pce_table_entry mac_bridge = {0,}; + unsigned char addr[ETH_ALEN]; + int i; + int err; + + for (i = 0; i < 2048; i++) { + mac_bridge.table = GSWIP_TABLE_MAC_BRIDGE; + mac_bridge.index = i; + + err = gswip_pce_table_entry_read(priv, &mac_bridge); + if (err) { + dev_err(priv->dev, + "failed to read mac bridge entry %d: %d\n", + i, err); + return err; + } + + if (!mac_bridge.valid) + continue; + + addr[5] = mac_bridge.key[0] & 0xff; + addr[4] = (mac_bridge.key[0] >> 8) & 0xff; + addr[3] = mac_bridge.key[1] & 0xff; + addr[2] = (mac_bridge.key[1] >> 8) & 0xff; + addr[1] = mac_bridge.key[2] & 0xff; + addr[0] = (mac_bridge.key[2] >> 8) & 0xff; + if (mac_bridge.val[1] & GSWIP_TABLE_MAC_BRIDGE_VAL1_STATIC) { + if (mac_bridge.val[0] & BIT(port)) { + err = cb(addr, 0, true, data); + if (err) + return err; + } + } else { + if (port == FIELD_GET(GSWIP_TABLE_MAC_BRIDGE_VAL0_PORT, + mac_bridge.val[0])) { + err = cb(addr, 0, false, data); + if (err) + return err; + } + } + } + return 0; +} + +static int gswip_port_max_mtu(struct dsa_switch *ds, int port) +{ + /* Includes 8 bytes for special header. */ + return GSWIP_MAX_PACKET_LENGTH - VLAN_ETH_HLEN - ETH_FCS_LEN; +} + +static int gswip_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) +{ + struct gswip_priv *priv = ds->priv; + + /* CPU port always has maximum mtu of user ports, so use it to set + * switch frame size, including 8 byte special header. + */ + if (dsa_is_cpu_port(ds, port)) { + new_mtu += 8; + regmap_write(priv->gswip, GSWIP_MAC_FLEN, + VLAN_ETH_HLEN + new_mtu + ETH_FCS_LEN); + } + + /* Enable MLEN for ports with non-standard MTUs, including the special + * header on the CPU port added above. + */ + if (new_mtu != ETH_DATA_LEN) + regmap_set_bits(priv->gswip, GSWIP_MAC_CTRL_2p(port), + GSWIP_MAC_CTRL_2_MLEN); + else + regmap_clear_bits(priv->gswip, GSWIP_MAC_CTRL_2p(port), + GSWIP_MAC_CTRL_2_MLEN); + + return 0; +} + +static void gswip_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + struct gswip_priv *priv = ds->priv; + + priv->hw_info->phylink_get_caps(ds, port, config); +} + +static void gswip_port_set_link(struct gswip_priv *priv, int port, bool link) +{ + u32 mdio_phy; + + if (link) + mdio_phy = GSWIP_MDIO_PHY_LINK_UP; + else + mdio_phy = GSWIP_MDIO_PHY_LINK_DOWN; + + regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port), + GSWIP_MDIO_PHY_LINK_MASK, mdio_phy); +} + +static void gswip_port_set_speed(struct gswip_priv *priv, int port, int speed, + phy_interface_t interface) +{ + u32 mdio_phy = 0, mii_cfg = 0, mac_ctrl_0 = 0; + + switch (speed) { + case SPEED_10: + mdio_phy = GSWIP_MDIO_PHY_SPEED_M10; + + if (interface == PHY_INTERFACE_MODE_RMII) + mii_cfg = GSWIP_MII_CFG_RATE_M50; + else + mii_cfg = GSWIP_MII_CFG_RATE_M2P5; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; + break; + + case SPEED_100: + mdio_phy = GSWIP_MDIO_PHY_SPEED_M100; + + if (interface == PHY_INTERFACE_MODE_RMII) + mii_cfg = GSWIP_MII_CFG_RATE_M50; + else + mii_cfg = GSWIP_MII_CFG_RATE_M25; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_MII; + break; + + case SPEED_1000: + mdio_phy = GSWIP_MDIO_PHY_SPEED_G1; + + mii_cfg = GSWIP_MII_CFG_RATE_M125; + + mac_ctrl_0 = GSWIP_MAC_CTRL_0_GMII_RGMII; + break; + } + + regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port), + GSWIP_MDIO_PHY_SPEED_MASK, mdio_phy); + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_RATE_MASK, mii_cfg, port); + regmap_write_bits(priv->gswip, GSWIP_MAC_CTRL_0p(port), + GSWIP_MAC_CTRL_0_GMII_MASK, mac_ctrl_0); +} + +static void gswip_port_set_duplex(struct gswip_priv *priv, int port, int duplex) +{ + u32 mac_ctrl_0, mdio_phy; + + if (duplex == DUPLEX_FULL) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_EN; + mdio_phy = GSWIP_MDIO_PHY_FDUP_EN; + } else { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FDUP_DIS; + mdio_phy = GSWIP_MDIO_PHY_FDUP_DIS; + } + + regmap_write_bits(priv->gswip, GSWIP_MAC_CTRL_0p(port), + GSWIP_MAC_CTRL_0_FDUP_MASK, mac_ctrl_0); + regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port), + GSWIP_MDIO_PHY_FDUP_MASK, mdio_phy); +} + +static void gswip_port_set_pause(struct gswip_priv *priv, int port, + bool tx_pause, bool rx_pause) +{ + u32 mac_ctrl_0, mdio_phy; + + if (tx_pause && rx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RXTX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | + GSWIP_MDIO_PHY_FCONRX_EN; + } else if (tx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_TX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_EN | + GSWIP_MDIO_PHY_FCONRX_DIS; + } else if (rx_pause) { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_RX; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | + GSWIP_MDIO_PHY_FCONRX_EN; + } else { + mac_ctrl_0 = GSWIP_MAC_CTRL_0_FCON_NONE; + mdio_phy = GSWIP_MDIO_PHY_FCONTX_DIS | + GSWIP_MDIO_PHY_FCONRX_DIS; + } + + regmap_write_bits(priv->gswip, GSWIP_MAC_CTRL_0p(port), + GSWIP_MAC_CTRL_0_FCON_MASK, mac_ctrl_0); + regmap_write_bits(priv->mdio, GSWIP_MDIO_PHYp(port), + GSWIP_MDIO_PHY_FCONTX_MASK | GSWIP_MDIO_PHY_FCONRX_MASK, + mdio_phy); +} + +static void gswip_phylink_mac_config(struct phylink_config *config, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *priv = dp->ds->priv; + int port = dp->index; + u32 miicfg = 0; + + miicfg |= GSWIP_MII_CFG_LDCLKDIS; + + switch (state->interface) { + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + return; + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_INTERNAL: + miicfg |= GSWIP_MII_CFG_MODE_MIIM; + break; + case PHY_INTERFACE_MODE_REVMII: + miicfg |= GSWIP_MII_CFG_MODE_MIIP; + break; + case PHY_INTERFACE_MODE_RMII: + miicfg |= GSWIP_MII_CFG_MODE_RMIIM; + if (of_property_read_bool(dp->dn, "maxlinear,rmii-refclk-out")) + miicfg |= GSWIP_MII_CFG_RMII_CLK; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + miicfg |= GSWIP_MII_CFG_MODE_RGMII; + break; + case PHY_INTERFACE_MODE_GMII: + miicfg |= GSWIP_MII_CFG_MODE_GMII; + break; + default: + dev_err(dp->ds->dev, + "Unsupported interface: %d\n", state->interface); + return; + } + + gswip_mii_mask_cfg(priv, + GSWIP_MII_CFG_MODE_MASK | GSWIP_MII_CFG_RMII_CLK | + GSWIP_MII_CFG_RGMII_IBS | GSWIP_MII_CFG_LDCLKDIS, + miicfg, port); + + gswip_mii_delay_setup(priv, dp, state->interface); +} + +static void gswip_phylink_mac_link_down(struct phylink_config *config, + unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *priv = dp->ds->priv; + int port = dp->index; + + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, 0, port); + + if (!dsa_port_is_cpu(dp)) + gswip_port_set_link(priv, port, false); +} + +static void gswip_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, + unsigned int mode, + phy_interface_t interface, + int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *priv = dp->ds->priv; + int port = dp->index; + + if (!dsa_port_is_cpu(dp) || interface != PHY_INTERFACE_MODE_INTERNAL) { + gswip_port_set_link(priv, port, true); + gswip_port_set_speed(priv, port, speed, interface); + gswip_port_set_duplex(priv, port, duplex); + gswip_port_set_pause(priv, port, tx_pause, rx_pause); + } + + gswip_mii_mask_cfg(priv, GSWIP_MII_CFG_EN, GSWIP_MII_CFG_EN, port); +} + +static void gswip_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data) +{ + int i; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) + ethtool_puts(&data, gswip_rmon_cnt[i].name); +} + +static u32 gswip_bcm_ram_entry_read(struct gswip_priv *priv, u32 table, + u32 index) +{ + u32 result, val; + int err; + + regmap_write(priv->gswip, GSWIP_BM_RAM_ADDR, index); + regmap_write_bits(priv->gswip, GSWIP_BM_RAM_CTRL, + GSWIP_BM_RAM_CTRL_ADDR_MASK | GSWIP_BM_RAM_CTRL_OPMOD | + GSWIP_BM_RAM_CTRL_BAS, + table | GSWIP_BM_RAM_CTRL_BAS); + + err = gswip_switch_r_timeout(priv, GSWIP_BM_RAM_CTRL, + GSWIP_BM_RAM_CTRL_BAS); + if (err) { + dev_err(priv->dev, "timeout while reading table: %u, index: %u\n", + table, index); + return 0; + } + + regmap_read(priv->gswip, GSWIP_BM_RAM_VAL(0), &result); + regmap_read(priv->gswip, GSWIP_BM_RAM_VAL(1), &val); + result |= val << 16; + + return result; +} + +static void gswip_get_ethtool_stats(struct dsa_switch *ds, int port, + uint64_t *data) +{ + struct gswip_priv *priv = ds->priv; + const struct gswip_rmon_cnt_desc *rmon_cnt; + int i; + u64 high; + + for (i = 0; i < ARRAY_SIZE(gswip_rmon_cnt); i++) { + rmon_cnt = &gswip_rmon_cnt[i]; + + data[i] = gswip_bcm_ram_entry_read(priv, port, + rmon_cnt->offset); + if (rmon_cnt->size == 2) { + high = gswip_bcm_ram_entry_read(priv, port, + rmon_cnt->offset + 1); + data[i] |= high << 32; + } + } +} + +static int gswip_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + if (sset != ETH_SS_STATS) + return 0; + + return ARRAY_SIZE(gswip_rmon_cnt); +} + +static int gswip_set_mac_eee(struct dsa_switch *ds, int port, + struct ethtool_keee *e) +{ + if (e->tx_lpi_timer > 0x7f) + return -EINVAL; + + return 0; +} + +static void gswip_phylink_mac_disable_tx_lpi(struct phylink_config *config) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *priv = dp->ds->priv; + + regmap_clear_bits(priv->gswip, GSWIP_MAC_CTRL_4p(dp->index), + GSWIP_MAC_CTRL_4_LPIEN); +} + +static int gswip_phylink_mac_enable_tx_lpi(struct phylink_config *config, + u32 timer, bool tx_clock_stop) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *priv = dp->ds->priv; + + return regmap_update_bits(priv->gswip, GSWIP_MAC_CTRL_4p(dp->index), + GSWIP_MAC_CTRL_4_LPIEN | + GSWIP_MAC_CTRL_4_GWAIT_MASK | + GSWIP_MAC_CTRL_4_WAIT_MASK, + GSWIP_MAC_CTRL_4_LPIEN | + GSWIP_MAC_CTRL_4_GWAIT(timer) | + GSWIP_MAC_CTRL_4_WAIT(timer)); +} + +static bool gswip_support_eee(struct dsa_switch *ds, int port) +{ + struct gswip_priv *priv = ds->priv; + + if (GSWIP_VERSION_GE(priv, GSWIP_VERSION_2_2)) + return true; + + return false; +} + +static struct phylink_pcs *gswip_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *priv = dp->ds->priv; + + if (priv->hw_info->mac_select_pcs) + return priv->hw_info->mac_select_pcs(config, interface); + + return NULL; +} + +static const struct phylink_mac_ops gswip_phylink_mac_ops = { + .mac_config = gswip_phylink_mac_config, + .mac_link_down = gswip_phylink_mac_link_down, + .mac_link_up = gswip_phylink_mac_link_up, + .mac_disable_tx_lpi = gswip_phylink_mac_disable_tx_lpi, + .mac_enable_tx_lpi = gswip_phylink_mac_enable_tx_lpi, + .mac_select_pcs = gswip_phylink_mac_select_pcs, +}; + +static const struct dsa_switch_ops gswip_switch_ops = { + .get_tag_protocol = gswip_get_tag_protocol, + .setup = gswip_setup, + .port_setup = gswip_port_setup, + .port_enable = gswip_port_enable, + .port_disable = gswip_port_disable, + .port_pre_bridge_flags = gswip_port_pre_bridge_flags, + .port_bridge_flags = gswip_port_bridge_flags, + .port_bridge_join = gswip_port_bridge_join, + .port_bridge_leave = gswip_port_bridge_leave, + .port_fast_age = gswip_port_fast_age, + .port_vlan_filtering = gswip_port_vlan_filtering, + .port_vlan_add = gswip_port_vlan_add, + .port_vlan_del = gswip_port_vlan_del, + .port_stp_state_set = gswip_port_stp_state_set, + .port_fdb_add = gswip_port_fdb_add, + .port_fdb_del = gswip_port_fdb_del, + .port_fdb_dump = gswip_port_fdb_dump, + .port_change_mtu = gswip_port_change_mtu, + .port_max_mtu = gswip_port_max_mtu, + .phylink_get_caps = gswip_phylink_get_caps, + .get_strings = gswip_get_strings, + .get_ethtool_stats = gswip_get_ethtool_stats, + .get_sset_count = gswip_get_sset_count, + .set_mac_eee = gswip_set_mac_eee, + .support_eee = gswip_support_eee, +}; + +void gswip_disable_switch(struct gswip_priv *priv) +{ + regmap_clear_bits(priv->mdio, GSWIP_MDIO_GLOB, GSWIP_MDIO_GLOB_ENABLE); +} +EXPORT_SYMBOL_GPL(gswip_disable_switch); + +static int gswip_validate_cpu_port(struct dsa_switch *ds) +{ + struct gswip_priv *priv = ds->priv; + struct dsa_port *cpu_dp; + int cpu_port = -1; + + dsa_switch_for_each_cpu_port(cpu_dp, ds) { + if (cpu_port != -1) + return dev_err_probe(ds->dev, -EINVAL, + "only a single CPU port is supported\n"); + + cpu_port = cpu_dp->index; + } + + if (cpu_port == -1) + return dev_err_probe(ds->dev, -EINVAL, "no CPU port defined\n"); + + if (BIT(cpu_port) & ~priv->hw_info->allowed_cpu_ports) + return dev_err_probe(ds->dev, -EINVAL, + "unsupported CPU port defined\n"); + + return 0; +} + +int gswip_probe_common(struct gswip_priv *priv, u32 version) +{ + int err; + + mutex_init(&priv->pce_table_lock); + + priv->ds = devm_kzalloc(priv->dev, sizeof(*priv->ds), GFP_KERNEL); + if (!priv->ds) + return -ENOMEM; + + priv->ds->dev = priv->dev; + priv->ds->num_ports = priv->hw_info->max_ports; + priv->ds->ops = &gswip_switch_ops; + priv->ds->phylink_mac_ops = &gswip_phylink_mac_ops; + priv->ds->priv = priv; + + /* The hardware has the 'major/minor' version bytes in the wrong order + * preventing numerical comparisons. Construct a 16-bit unsigned integer + * having the REV field as most significant byte and the MOD field as + * least significant byte. This is effectively swapping the two bytes of + * the version variable, but other than using swab16 it doesn't affect + * the source variable. + */ + priv->version = GSWIP_VERSION_REV(version) << 8 | + GSWIP_VERSION_MOD(version); + + err = dsa_register_switch(priv->ds); + if (err) + return dev_err_probe(priv->dev, err, "dsa switch registration failed\n"); + + err = gswip_validate_cpu_port(priv->ds); + if (err) + goto disable_switch; + + dev_info(priv->dev, "probed GSWIP version %lx mod %lx\n", + GSWIP_VERSION_REV(version), GSWIP_VERSION_MOD(version)); + + return 0; + +disable_switch: + gswip_disable_switch(priv); + dsa_unregister_switch(priv->ds); + + return err; +} +EXPORT_SYMBOL_GPL(gswip_probe_common); + +MODULE_AUTHOR("Hauke Mehrtens "); +MODULE_AUTHOR("Daniel Golle "); +MODULE_DESCRIPTION("Lantiq / Intel / MaxLinear GSWIP common functions"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx.c b/drivers/net/dsa/lantiq/mxl-gsw1xx.c new file mode 100644 index 0000000000000..0816c61a47f12 --- /dev/null +++ b/drivers/net/dsa/lantiq/mxl-gsw1xx.c @@ -0,0 +1,733 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* DSA Driver for MaxLinear GSW1xx switch devices + * + * Copyright (C) 2025 Daniel Golle + * Copyright (C) 2023 - 2024 MaxLinear Inc. + * Copyright (C) 2022 Snap One, LLC. All rights reserved. + * Copyright (C) 2017 - 2019 Hauke Mehrtens + * Copyright (C) 2012 John Crispin + * Copyright (C) 2010 Lantiq Deutschland + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "lantiq_gswip.h" +#include "mxl-gsw1xx.h" +#include "mxl-gsw1xx_pce.h" + +struct gsw1xx_priv { + struct mdio_device *mdio_dev; + int smdio_badr; + struct regmap *sgmii; + struct regmap *gpio; + struct regmap *clk; + struct regmap *shell; + struct phylink_pcs pcs; + phy_interface_t tbi_interface; + struct gswip_priv gswip; +}; + +static int gsw1xx_config_smdio_badr(struct gsw1xx_priv *priv, + unsigned int reg) +{ + struct mii_bus *bus = priv->mdio_dev->bus; + int sw_addr = priv->mdio_dev->addr; + int smdio_badr = priv->smdio_badr; + int res; + + if (smdio_badr == GSW1XX_SMDIO_BADR_UNKNOWN || + reg - smdio_badr >= GSW1XX_SMDIO_BADR || + smdio_badr > reg) { + /* Configure the Switch Base Address */ + smdio_badr = reg & ~GENMASK(3, 0); + res = __mdiobus_write(bus, sw_addr, GSW1XX_SMDIO_BADR, smdio_badr); + if (res < 0) { + dev_err(&priv->mdio_dev->dev, + "%s: Error %d, configuring switch base\n", + __func__, res); + return res; + } + priv->smdio_badr = smdio_badr; + } + + return smdio_badr; +} + +static int gsw1xx_regmap_read(void *context, unsigned int reg, + unsigned int *val) +{ + struct gsw1xx_priv *priv = context; + struct mii_bus *bus = priv->mdio_dev->bus; + int sw_addr = priv->mdio_dev->addr; + int smdio_badr; + int res; + + smdio_badr = gsw1xx_config_smdio_badr(priv, reg); + if (smdio_badr < 0) + return smdio_badr; + + res = __mdiobus_read(bus, sw_addr, reg - smdio_badr); + if (res < 0) { + dev_err(&priv->mdio_dev->dev, "%s: Error %d reading 0x%x\n", + __func__, res, reg); + return res; + } + + *val = res; + + return 0; +} + +static int gsw1xx_regmap_write(void *context, unsigned int reg, + unsigned int val) +{ + struct gsw1xx_priv *priv = context; + struct mii_bus *bus = priv->mdio_dev->bus; + int sw_addr = priv->mdio_dev->addr; + int smdio_badr; + int res; + + smdio_badr = gsw1xx_config_smdio_badr(priv, reg); + if (smdio_badr < 0) + return smdio_badr; + + res = __mdiobus_write(bus, sw_addr, reg - smdio_badr, val); + if (res < 0) + dev_err(&priv->mdio_dev->dev, + "%s: Error %d, writing 0x%x:0x%x\n", __func__, res, reg, + val); + + return res; +} + +static const struct regmap_bus gsw1xx_regmap_bus = { + .reg_write = gsw1xx_regmap_write, + .reg_read = gsw1xx_regmap_read, +}; + +static void gsw1xx_mdio_regmap_lock(void *mdio_lock) +{ + mutex_lock_nested(mdio_lock, MDIO_MUTEX_NESTED); +} + +static void gsw1xx_mdio_regmap_unlock(void *mdio_lock) +{ + mutex_unlock(mdio_lock); +} + +static unsigned int gsw1xx_pcs_inband_caps(struct phylink_pcs *pcs, + phy_interface_t interface) +{ + return LINK_INBAND_DISABLE | LINK_INBAND_ENABLE; +} + +static struct gsw1xx_priv *pcs_to_gsw1xx(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct gsw1xx_priv, pcs); +} + +static int gsw1xx_pcs_enable(struct phylink_pcs *pcs) +{ + struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + + /* Deassert SGMII shell reset */ + return regmap_clear_bits(priv->shell, GSW1XX_SHELL_RST_REQ, + GSW1XX_RST_REQ_SGMII_SHELL); +} + +static void gsw1xx_pcs_disable(struct phylink_pcs *pcs) +{ + struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + + /* Assert SGMII shell reset */ + regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ, + GSW1XX_RST_REQ_SGMII_SHELL); + + priv->tbi_interface = PHY_INTERFACE_MODE_NA; +} + +static void gsw1xx_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, + struct phylink_link_state *state) +{ + struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + int ret; + u32 val; + + ret = regmap_read(priv->sgmii, GSW1XX_SGMII_TBI_TBISTAT, &val); + if (ret < 0) + return; + + state->link = !!(val & GSW1XX_SGMII_TBI_TBISTAT_LINK); + state->an_complete = !!(val & GSW1XX_SGMII_TBI_TBISTAT_AN_COMPLETE); + + ret = regmap_read(priv->sgmii, GSW1XX_SGMII_TBI_LPSTAT, &val); + if (ret < 0) + return; + + state->duplex = (val & GSW1XX_SGMII_TBI_LPSTAT_DUPLEX) ? + DUPLEX_FULL : DUPLEX_HALF; + if (val & GSW1XX_SGMII_TBI_LPSTAT_PAUSE_RX) + state->pause |= MLO_PAUSE_RX; + + if (val & GSW1XX_SGMII_TBI_LPSTAT_PAUSE_TX) + state->pause |= MLO_PAUSE_TX; + + switch (FIELD_GET(GSW1XX_SGMII_TBI_LPSTAT_SPEED, val)) { + case GSW1XX_SGMII_TBI_LPSTAT_SPEED_10: + state->speed = SPEED_10; + break; + case GSW1XX_SGMII_TBI_LPSTAT_SPEED_100: + state->speed = SPEED_100; + break; + case GSW1XX_SGMII_TBI_LPSTAT_SPEED_1000: + state->speed = SPEED_1000; + break; + case GSW1XX_SGMII_TBI_LPSTAT_SPEED_NOSGMII: + if (state->interface == PHY_INTERFACE_MODE_1000BASEX) + state->speed = SPEED_1000; + else if (state->interface == PHY_INTERFACE_MODE_2500BASEX) + state->speed = SPEED_2500; + else + state->speed = SPEED_UNKNOWN; + break; + } +} + +static int gsw1xx_pcs_phy_xaui_write(struct gsw1xx_priv *priv, u16 addr, + u16 data) +{ + int ret, val; + + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_D, data); + if (ret < 0) + return ret; + + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_A, addr); + if (ret < 0) + return ret; + + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_C, + GSW1XX_SGMII_PHY_WRITE | + GSW1XX_SGMII_PHY_RESET_N); + if (ret < 0) + return ret; + + return regmap_read_poll_timeout(priv->sgmii, GSW1XX_SGMII_PHY_C, + val, val & GSW1XX_SGMII_PHY_STATUS, + 1000, 100000); +} + +static int gsw1xx_pcs_reset(struct gsw1xx_priv *priv) +{ + int ret; + u16 val; + + /* Assert and deassert SGMII shell reset */ + ret = regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ, + GSW1XX_RST_REQ_SGMII_SHELL); + if (ret < 0) + return ret; + + ret = regmap_clear_bits(priv->shell, GSW1XX_SHELL_RST_REQ, + GSW1XX_RST_REQ_SGMII_SHELL); + if (ret < 0) + return ret; + + /* Hardware Bringup FSM Enable */ + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_HWBU_CTRL, + GSW1XX_SGMII_PHY_HWBU_CTRL_EN_HWBU_FSM | + GSW1XX_SGMII_PHY_HWBU_CTRL_HW_FSM_EN); + if (ret < 0) + return ret; + + /* Configure SGMII PHY Receiver */ + val = FIELD_PREP(GSW1XX_SGMII_PHY_RX0_CFG2_EQ, + GSW1XX_SGMII_PHY_RX0_CFG2_EQ_DEF) | + GSW1XX_SGMII_PHY_RX0_CFG2_LOS_EN | + GSW1XX_SGMII_PHY_RX0_CFG2_TERM_EN | + FIELD_PREP(GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT, + GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT_DEF); + + /* TODO: Take care of inverted RX pair once generic property is + * available + */ + + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_RX0_CFG2, val); + if (ret < 0) + return ret; + + val = FIELD_PREP(GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL, + GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL_DEF); + + /* TODO: Take care of inverted TX pair once generic property is + * available + */ + + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_PHY_TX0_CFG3, val); + if (ret < 0) + return ret; + + /* Reset and Release TBI */ + val = GSW1XX_SGMII_TBI_TBICTL_INITTBI | GSW1XX_SGMII_TBI_TBICTL_ENTBI | + GSW1XX_SGMII_TBI_TBICTL_CRSTRR | GSW1XX_SGMII_TBI_TBICTL_CRSOFF; + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TBICTL, val); + if (ret < 0) + return ret; + val &= ~GSW1XX_SGMII_TBI_TBICTL_INITTBI; + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TBICTL, val); + if (ret < 0) + return ret; + + /* Release Tx Data Buffers */ + ret = regmap_set_bits(priv->sgmii, GSW1XX_SGMII_PCS_TXB_CTL, + GSW1XX_SGMII_PCS_TXB_CTL_INIT_TX_TXB); + if (ret < 0) + return ret; + ret = regmap_clear_bits(priv->sgmii, GSW1XX_SGMII_PCS_TXB_CTL, + GSW1XX_SGMII_PCS_TXB_CTL_INIT_TX_TXB); + if (ret < 0) + return ret; + + /* Release Rx Data Buffers */ + ret = regmap_set_bits(priv->sgmii, GSW1XX_SGMII_PCS_RXB_CTL, + GSW1XX_SGMII_PCS_RXB_CTL_INIT_RX_RXB); + if (ret < 0) + return ret; + return regmap_clear_bits(priv->sgmii, GSW1XX_SGMII_PCS_RXB_CTL, + GSW1XX_SGMII_PCS_RXB_CTL_INIT_RX_RXB); +} + +static int gsw1xx_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + u16 txaneg, anegctl, nco_ctrl; + bool reconf = false; + int ret = 0; + + /* do not unnecessarily disrupt link and skip resetting the hardware in + * case the PCS has previously been successfully configured for this + * interface mode + */ + if (priv->tbi_interface == interface) + reconf = true; + + /* mark PCS configuration as incomplete */ + priv->tbi_interface = PHY_INTERFACE_MODE_NA; + + if (!reconf) + ret = gsw1xx_pcs_reset(priv); + + if (ret) + return ret; + + /* override bootstrap pin settings + * OVRANEG sets ANEG Mode, Enable ANEG and restart ANEG to be + * taken from bits ANMODE, ANEGEN, RANEG of the ANEGCTL register. + * OVERABL sets ability bits in tx_config_reg to be taken from + * the TXANEGH and TXANEGL registers. + */ + anegctl = GSW1XX_SGMII_TBI_ANEGCTL_OVRANEG | + GSW1XX_SGMII_TBI_ANEGCTL_OVRABL; + + switch (phylink_get_link_timer_ns(interface)) { + case 10000: + anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT, + GSW1XX_SGMII_TBI_ANEGCTL_LT_10US); + break; + case 1600000: + anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT, + GSW1XX_SGMII_TBI_ANEGCTL_LT_1_6MS); + break; + case 5000000: + anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT, + GSW1XX_SGMII_TBI_ANEGCTL_LT_5MS); + break; + case 10000000: + anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_LT, + GSW1XX_SGMII_TBI_ANEGCTL_LT_10MS); + break; + default: + return -EINVAL; + } + + if (neg_mode & PHYLINK_PCS_NEG_INBAND) + anegctl |= GSW1XX_SGMII_TBI_ANEGCTL_ANEGEN; + + txaneg = phylink_mii_c22_pcs_encode_advertisement(interface, advertising); + + if (interface == PHY_INTERFACE_MODE_SGMII) { + /* lacking a defined reverse-SGMII interface mode this + * driver only supports SGMII (MAC side) for now + */ + anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_ANMODE, + GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_SGMII_MAC); + txaneg |= ADVERTISE_LPACK; + } else if (interface == PHY_INTERFACE_MODE_1000BASEX || + interface == PHY_INTERFACE_MODE_2500BASEX) { + anegctl |= FIELD_PREP(GSW1XX_SGMII_TBI_ANEGCTL_ANMODE, + GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_1000BASEX); + } else { + dev_err(priv->gswip.dev, "%s: wrong interface mode %s\n", + __func__, phy_modes(interface)); + return -EINVAL; + } + + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TXANEGH, + FIELD_GET(GENMASK(15, 8), txaneg)); + if (ret < 0) + return ret; + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_TXANEGL, + FIELD_GET(GENMASK(7, 0), txaneg)); + if (ret < 0) + return ret; + ret = regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL, anegctl); + if (ret < 0) + return ret; + + if (!reconf) { + /* setup SerDes clock speed */ + if (interface == PHY_INTERFACE_MODE_2500BASEX) + nco_ctrl = GSW1XX_SGMII_2G5 | GSW1XX_SGMII_2G5_NCO2; + else + nco_ctrl = GSW1XX_SGMII_1G | GSW1XX_SGMII_1G_NCO1; + + ret = regmap_update_bits(priv->clk, GSW1XX_CLK_NCO_CTRL, + GSW1XX_SGMII_HSP_MASK | + GSW1XX_SGMII_SEL, + nco_ctrl); + if (ret) + return ret; + + ret = gsw1xx_pcs_phy_xaui_write(priv, 0x30, 0x80); + if (ret) + return ret; + } + + /* PCS configuration has now been completed, store mode to prevent + * disrupting the link in case of future calls of this function for the + * same interface mode. + */ + priv->tbi_interface = interface; + + return 0; +} + +static void gsw1xx_pcs_an_restart(struct phylink_pcs *pcs) +{ + struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + + regmap_set_bits(priv->sgmii, GSW1XX_SGMII_TBI_ANEGCTL, + GSW1XX_SGMII_TBI_ANEGCTL_RANEG); +} + +static void gsw1xx_pcs_link_up(struct phylink_pcs *pcs, + unsigned int neg_mode, + phy_interface_t interface, int speed, + int duplex) +{ + struct gsw1xx_priv *priv = pcs_to_gsw1xx(pcs); + u16 lpstat; + + /* When in-band AN is enabled hardware will set lpstat */ + if (neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED) + return; + + /* Force speed and duplex settings */ + if (interface == PHY_INTERFACE_MODE_SGMII) { + if (speed == SPEED_10) + lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED, + GSW1XX_SGMII_TBI_LPSTAT_SPEED_10); + else if (speed == SPEED_100) + lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED, + GSW1XX_SGMII_TBI_LPSTAT_SPEED_100); + else + lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED, + GSW1XX_SGMII_TBI_LPSTAT_SPEED_1000); + } else { + lpstat = FIELD_PREP(GSW1XX_SGMII_TBI_LPSTAT_SPEED, + GSW1XX_SGMII_TBI_LPSTAT_SPEED_NOSGMII); + } + + if (duplex == DUPLEX_FULL) + lpstat |= GSW1XX_SGMII_TBI_LPSTAT_DUPLEX; + + regmap_write(priv->sgmii, GSW1XX_SGMII_TBI_LPSTAT, lpstat); +} + +static const struct phylink_pcs_ops gsw1xx_pcs_ops = { + .pcs_inband_caps = gsw1xx_pcs_inband_caps, + .pcs_enable = gsw1xx_pcs_enable, + .pcs_disable = gsw1xx_pcs_disable, + .pcs_get_state = gsw1xx_pcs_get_state, + .pcs_config = gsw1xx_pcs_config, + .pcs_an_restart = gsw1xx_pcs_an_restart, + .pcs_link_up = gsw1xx_pcs_link_up, +}; + +static void gsw1xx_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + struct gswip_priv *priv = ds->priv; + + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; + + switch (port) { + case 0: + case 1: + case 2: + case 3: + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + break; + case 4: /* port 4: SGMII */ + __set_bit(PHY_INTERFACE_MODE_SGMII, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + config->supported_interfaces); + if (priv->hw_info->supports_2500m) { + __set_bit(PHY_INTERFACE_MODE_2500BASEX, + config->supported_interfaces); + config->mac_capabilities |= MAC_2500FD; + } + return; /* no support for EEE on SGMII port */ + case 5: /* port 5: RGMII or RMII */ + __set_bit(PHY_INTERFACE_MODE_RMII, + config->supported_interfaces); + phy_interface_set_rgmii(config->supported_interfaces); + break; + } + + config->lpi_capabilities = MAC_100FD | MAC_1000FD; + config->lpi_timer_default = 20; + memcpy(config->lpi_interfaces, config->supported_interfaces, + sizeof(config->lpi_interfaces)); +} + +static struct phylink_pcs *gsw1xx_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct gswip_priv *gswip_priv = dp->ds->priv; + struct gsw1xx_priv *gsw1xx_priv = container_of(gswip_priv, + struct gsw1xx_priv, + gswip); + + switch (dp->index) { + case GSW1XX_SGMII_PORT: + return &gsw1xx_priv->pcs; + default: + return NULL; + } +} + +static struct regmap *gsw1xx_regmap_init(struct gsw1xx_priv *priv, + const char *name, + unsigned int reg_base, + unsigned int max_register) +{ + const struct regmap_config config = { + .name = name, + .reg_bits = 16, + .val_bits = 16, + .reg_base = reg_base, + .max_register = max_register, + .lock = gsw1xx_mdio_regmap_lock, + .unlock = gsw1xx_mdio_regmap_unlock, + .lock_arg = &priv->mdio_dev->bus->mdio_lock, + }; + + return devm_regmap_init(&priv->mdio_dev->dev, &gsw1xx_regmap_bus, + priv, &config); +} + +static int gsw1xx_probe(struct mdio_device *mdiodev) +{ + struct device *dev = &mdiodev->dev; + struct gsw1xx_priv *priv; + u32 version; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->mdio_dev = mdiodev; + priv->smdio_badr = GSW1XX_SMDIO_BADR_UNKNOWN; + + priv->gswip.dev = dev; + priv->gswip.hw_info = of_device_get_match_data(dev); + if (!priv->gswip.hw_info) + return -EINVAL; + + priv->gswip.gswip = gsw1xx_regmap_init(priv, "switch", + GSW1XX_SWITCH_BASE, 0xfff); + if (IS_ERR(priv->gswip.gswip)) + return PTR_ERR(priv->gswip.gswip); + + priv->gswip.mdio = gsw1xx_regmap_init(priv, "mdio", GSW1XX_MMDIO_BASE, + 0xff); + if (IS_ERR(priv->gswip.mdio)) + return PTR_ERR(priv->gswip.mdio); + + priv->gswip.mii = gsw1xx_regmap_init(priv, "mii", GSW1XX_RGMII_BASE, + 0xff); + if (IS_ERR(priv->gswip.mii)) + return PTR_ERR(priv->gswip.mii); + + priv->sgmii = gsw1xx_regmap_init(priv, "sgmii", GSW1XX_SGMII_BASE, + 0xfff); + if (IS_ERR(priv->sgmii)) + return PTR_ERR(priv->sgmii); + + priv->gpio = gsw1xx_regmap_init(priv, "gpio", GSW1XX_GPIO_BASE, 0xff); + if (IS_ERR(priv->gpio)) + return PTR_ERR(priv->gpio); + + priv->clk = gsw1xx_regmap_init(priv, "clk", GSW1XX_CLK_BASE, 0xff); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + priv->shell = gsw1xx_regmap_init(priv, "shell", GSW1XX_SHELL_BASE, + 0xff); + if (IS_ERR(priv->shell)) + return PTR_ERR(priv->shell); + + priv->pcs.ops = &gsw1xx_pcs_ops; + priv->pcs.poll = true; + __set_bit(PHY_INTERFACE_MODE_SGMII, + priv->pcs.supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + priv->pcs.supported_interfaces); + if (priv->gswip.hw_info->supports_2500m) + __set_bit(PHY_INTERFACE_MODE_2500BASEX, + priv->pcs.supported_interfaces); + priv->tbi_interface = PHY_INTERFACE_MODE_NA; + + /* assert SGMII reset to power down SGMII unit */ + ret = regmap_set_bits(priv->shell, GSW1XX_SHELL_RST_REQ, + GSW1XX_RST_REQ_SGMII_SHELL); + if (ret < 0) + return ret; + + /* configure GPIO pin-mux for MMDIO in case of external PHY connected to + * SGMII or RGMII as slave interface + */ + regmap_set_bits(priv->gpio, GPIO_ALTSEL0, 3); + regmap_set_bits(priv->gpio, GPIO_ALTSEL1, 3); + + ret = regmap_read(priv->gswip.gswip, GSWIP_VERSION, &version); + if (ret) + return ret; + + ret = gswip_probe_common(&priv->gswip, version); + if (ret) + return ret; + + dev_set_drvdata(dev, &priv->gswip); + + return 0; +} + +static void gsw1xx_remove(struct mdio_device *mdiodev) +{ + struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + gswip_disable_switch(priv); + + dsa_unregister_switch(priv->ds); +} + +static void gsw1xx_shutdown(struct mdio_device *mdiodev) +{ + struct gswip_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dev_set_drvdata(&mdiodev->dev, NULL); + + gswip_disable_switch(priv); +} + +static const struct gswip_hw_info gsw12x_data = { + .max_ports = GSW1XX_PORTS, + .allowed_cpu_ports = BIT(GSW1XX_MII_PORT) | BIT(GSW1XX_SGMII_PORT), + .mii_ports = BIT(GSW1XX_MII_PORT), + .mii_port_reg_offset = -GSW1XX_MII_PORT, + .mac_select_pcs = gsw1xx_phylink_mac_select_pcs, + .phylink_get_caps = &gsw1xx_phylink_get_caps, + .supports_2500m = true, + .pce_microcode = &gsw1xx_pce_microcode, + .pce_microcode_size = ARRAY_SIZE(gsw1xx_pce_microcode), + .tag_protocol = DSA_TAG_PROTO_MXL_GSW1XX, +}; + +static const struct gswip_hw_info gsw140_data = { + .max_ports = GSW1XX_PORTS, + .allowed_cpu_ports = BIT(GSW1XX_MII_PORT) | BIT(GSW1XX_SGMII_PORT), + .mii_ports = BIT(GSW1XX_MII_PORT), + .mii_port_reg_offset = -GSW1XX_MII_PORT, + .mac_select_pcs = gsw1xx_phylink_mac_select_pcs, + .phylink_get_caps = &gsw1xx_phylink_get_caps, + .supports_2500m = true, + .pce_microcode = &gsw1xx_pce_microcode, + .pce_microcode_size = ARRAY_SIZE(gsw1xx_pce_microcode), + .tag_protocol = DSA_TAG_PROTO_MXL_GSW1XX, +}; + +static const struct gswip_hw_info gsw141_data = { + .max_ports = GSW1XX_PORTS, + .allowed_cpu_ports = BIT(GSW1XX_MII_PORT) | BIT(GSW1XX_SGMII_PORT), + .mii_ports = BIT(GSW1XX_MII_PORT), + .mii_port_reg_offset = -GSW1XX_MII_PORT, + .mac_select_pcs = gsw1xx_phylink_mac_select_pcs, + .phylink_get_caps = gsw1xx_phylink_get_caps, + .pce_microcode = &gsw1xx_pce_microcode, + .pce_microcode_size = ARRAY_SIZE(gsw1xx_pce_microcode), + .tag_protocol = DSA_TAG_PROTO_MXL_GSW1XX, +}; + +/* + * GSW125 is the industrial temperature version of GSW120. + * GSW145 is the industrial temperature version of GSW140. + */ +static const struct of_device_id gsw1xx_of_match[] = { + { .compatible = "maxlinear,gsw120", .data = &gsw12x_data }, + { .compatible = "maxlinear,gsw125", .data = &gsw12x_data }, + { .compatible = "maxlinear,gsw140", .data = &gsw140_data }, + { .compatible = "maxlinear,gsw141", .data = &gsw141_data }, + { .compatible = "maxlinear,gsw145", .data = &gsw140_data }, + { /* sentinel */ }, +}; + +MODULE_DEVICE_TABLE(of, gsw1xx_of_match); + +static struct mdio_driver gsw1xx_driver = { + .probe = gsw1xx_probe, + .remove = gsw1xx_remove, + .shutdown = gsw1xx_shutdown, + .mdiodrv.driver = { + .name = "mxl-gsw1xx", + .of_match_table = gsw1xx_of_match, + }, +}; + +mdio_module_driver(gsw1xx_driver); + +MODULE_AUTHOR("Daniel Golle "); +MODULE_DESCRIPTION("Driver for MaxLinear GSW1xx ethernet switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx.h b/drivers/net/dsa/lantiq/mxl-gsw1xx.h new file mode 100644 index 0000000000000..38e03c048a26c --- /dev/null +++ b/drivers/net/dsa/lantiq/mxl-gsw1xx.h @@ -0,0 +1,126 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Register definitions for MaxLinear GSW1xx series switches + * + * Copyright (C) 2025 Daniel Golle + * Copyright (C) 2023 - 2024 MaxLinear Inc. + */ +#ifndef __MXL_GSW1XX_H +#define __MXL_GSW1XX_H + +#include + +#define GSW1XX_PORTS 6 +/* Port used for RGMII or optional RMII */ +#define GSW1XX_MII_PORT 5 +/* Port used for SGMII */ +#define GSW1XX_SGMII_PORT 4 + +#define GSW1XX_SYS_CLK_FREQ 340000000 + +/* SMDIO switch register base address */ +#define GSW1XX_SMDIO_BADR 0x1f +#define GSW1XX_SMDIO_BADR_UNKNOWN -1 + +/* GSW1XX SGMII PCS */ +#define GSW1XX_SGMII_BASE 0xd000 +#define GSW1XX_SGMII_PHY_HWBU_CTRL 0x009 +#define GSW1XX_SGMII_PHY_HWBU_CTRL_EN_HWBU_FSM BIT(0) +#define GSW1XX_SGMII_PHY_HWBU_CTRL_HW_FSM_EN BIT(3) +#define GSW1XX_SGMII_TBI_TXANEGH 0x300 +#define GSW1XX_SGMII_TBI_TXANEGL 0x301 +#define GSW1XX_SGMII_TBI_ANEGCTL 0x304 +#define GSW1XX_SGMII_TBI_ANEGCTL_LT GENMASK(1, 0) +#define GSW1XX_SGMII_TBI_ANEGCTL_LT_10US 0 +#define GSW1XX_SGMII_TBI_ANEGCTL_LT_1_6MS 1 +#define GSW1XX_SGMII_TBI_ANEGCTL_LT_5MS 2 +#define GSW1XX_SGMII_TBI_ANEGCTL_LT_10MS 3 +#define GSW1XX_SGMII_TBI_ANEGCTL_ANEGEN BIT(2) +#define GSW1XX_SGMII_TBI_ANEGCTL_RANEG BIT(3) +#define GSW1XX_SGMII_TBI_ANEGCTL_OVRABL BIT(4) +#define GSW1XX_SGMII_TBI_ANEGCTL_OVRANEG BIT(5) +#define GSW1XX_SGMII_TBI_ANEGCTL_ANMODE GENMASK(7, 6) +#define GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_1000BASEX 1 +#define GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_SGMII_PHY 2 +#define GSW1XX_SGMII_TBI_ANEGCTL_ANMODE_SGMII_MAC 3 +#define GSW1XX_SGMII_TBI_ANEGCTL_BCOMP BIT(15) + +#define GSW1XX_SGMII_TBI_TBICTL 0x305 +#define GSW1XX_SGMII_TBI_TBICTL_INITTBI BIT(0) +#define GSW1XX_SGMII_TBI_TBICTL_ENTBI BIT(1) +#define GSW1XX_SGMII_TBI_TBICTL_CRSTRR BIT(4) +#define GSW1XX_SGMII_TBI_TBICTL_CRSOFF BIT(5) +#define GSW1XX_SGMII_TBI_TBISTAT 0x309 +#define GSW1XX_SGMII_TBI_TBISTAT_LINK BIT(0) +#define GSW1XX_SGMII_TBI_TBISTAT_AN_COMPLETE BIT(1) +#define GSW1XX_SGMII_TBI_LPSTAT 0x30a +#define GSW1XX_SGMII_TBI_LPSTAT_DUPLEX BIT(0) +#define GSW1XX_SGMII_TBI_LPSTAT_PAUSE_RX BIT(1) +#define GSW1XX_SGMII_TBI_LPSTAT_PAUSE_TX BIT(2) +#define GSW1XX_SGMII_TBI_LPSTAT_SPEED GENMASK(6, 5) +#define GSW1XX_SGMII_TBI_LPSTAT_SPEED_10 0 +#define GSW1XX_SGMII_TBI_LPSTAT_SPEED_100 1 +#define GSW1XX_SGMII_TBI_LPSTAT_SPEED_1000 2 +#define GSW1XX_SGMII_TBI_LPSTAT_SPEED_NOSGMII 3 +#define GSW1XX_SGMII_PHY_D 0x100 +#define GSW1XX_SGMII_PHY_A 0x101 +#define GSW1XX_SGMII_PHY_C 0x102 +#define GSW1XX_SGMII_PHY_STATUS BIT(0) +#define GSW1XX_SGMII_PHY_READ BIT(4) +#define GSW1XX_SGMII_PHY_WRITE BIT(8) +#define GSW1XX_SGMII_PHY_RESET_N BIT(12) +#define GSW1XX_SGMII_PCS_RXB_CTL 0x401 +#define GSW1XX_SGMII_PCS_RXB_CTL_INIT_RX_RXB BIT(1) +#define GSW1XX_SGMII_PCS_TXB_CTL 0x404 +#define GSW1XX_SGMII_PCS_TXB_CTL_INIT_TX_TXB BIT(1) + +#define GSW1XX_SGMII_PHY_RX0_CFG2 0x004 +#define GSW1XX_SGMII_PHY_RX0_CFG2_EQ GENMASK(2, 0) +#define GSW1XX_SGMII_PHY_RX0_CFG2_EQ_DEF 2 +#define GSW1XX_SGMII_PHY_RX0_CFG2_INVERT BIT(3) +#define GSW1XX_SGMII_PHY_RX0_CFG2_LOS_EN BIT(4) +#define GSW1XX_SGMII_PHY_RX0_CFG2_TERM_EN BIT(5) +#define GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT GENMASK(12, 6) +#define GSW1XX_SGMII_PHY_RX0_CFG2_FILT_CNT_DEF 20 + +#define GSW1XX_SGMII_PHY_TX0_CFG3 0x007 +#define GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_EN BIT(12) +#define GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL GENMASK(11, 9) +#define GSW1XX_SGMII_PHY_TX0_CFG3_VBOOST_LEVEL_DEF 4 +#define GSW1XX_SGMII_PHY_TX0_CFG3_INVERT BIT(8) + +/* GSW1XX PDI Registers */ +#define GSW1XX_SWITCH_BASE 0xe000 + +/* GSW1XX MII Registers */ +#define GSW1XX_RGMII_BASE 0xf100 + +/* GSW1XX GPIO Registers */ +#define GSW1XX_GPIO_BASE 0xf300 +#define GPIO_ALTSEL0 0x83 +#define GPIO_ALTSEL0_EXTPHY_MUX_VAL 0x03c3 +#define GPIO_ALTSEL1 0x84 +#define GPIO_ALTSEL1_EXTPHY_MUX_VAL 0x003f + +/* MDIO bus controller */ +#define GSW1XX_MMDIO_BASE 0xf400 + +/* generic IC registers */ +#define GSW1XX_SHELL_BASE 0xfa00 +#define GSW1XX_SHELL_RST_REQ 0x01 +#define GSW1XX_RST_REQ_SGMII_SHELL BIT(5) +/* RGMII PAD Slew Control Register */ +#define GSW1XX_SHELL_RGMII_SLEW_CFG 0x78 +#define RGMII_SLEW_CFG_RX_2_5_V BIT(4) +#define RGMII_SLEW_CFG_TX_2_5_V BIT(5) + +/* SGMII clock related settings */ +#define GSW1XX_CLK_BASE 0xf900 +#define GSW1XX_CLK_NCO_CTRL 0x68 +#define GSW1XX_SGMII_HSP_MASK GENMASK(3, 2) +#define GSW1XX_SGMII_SEL BIT(1) +#define GSW1XX_SGMII_1G 0x0 +#define GSW1XX_SGMII_2G5 0xc +#define GSW1XX_SGMII_1G_NCO1 0x0 +#define GSW1XX_SGMII_2G5_NCO2 0x2 + +#endif /* __MXL_GSW1XX_H */ diff --git a/drivers/net/dsa/lantiq/mxl-gsw1xx_pce.h b/drivers/net/dsa/lantiq/mxl-gsw1xx_pce.h new file mode 100644 index 0000000000000..eefcd411a3403 --- /dev/null +++ b/drivers/net/dsa/lantiq/mxl-gsw1xx_pce.h @@ -0,0 +1,154 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCE microcode code update for driver for MaxLinear GSW1xx switch chips + * + * Copyright (C) 2023 - 2024 MaxLinear Inc. + * Copyright (C) 2022 Snap One, LLC. All rights reserved. + * Copyright (C) 2017 - 2019 Hauke Mehrtens + * Copyright (C) 2012 John Crispin + * Copyright (C) 2010 Lantiq Deutschland + */ + +#include "lantiq_gswip.h" + +#define INSTR 0 +#define IPV6 1 +#define LENACCU 2 + +/* GSWIP_2.X */ +enum { + OUT_MAC0 = 0, + OUT_MAC1, + OUT_MAC2, + OUT_MAC3, + OUT_MAC4, + OUT_MAC5, + OUT_ETHTYP, + OUT_VTAG0, + OUT_VTAG1, + OUT_ITAG0, + OUT_ITAG1, /* 10 */ + OUT_ITAG2, + OUT_ITAG3, + OUT_IP0, + OUT_IP1, + OUT_IP2, + OUT_IP3, + OUT_SIP0, + OUT_SIP1, + OUT_SIP2, + OUT_SIP3, /* 20 */ + OUT_SIP4, + OUT_SIP5, + OUT_SIP6, + OUT_SIP7, + OUT_DIP0, + OUT_DIP1, + OUT_DIP2, + OUT_DIP3, + OUT_DIP4, + OUT_DIP5, /* 30 */ + OUT_DIP6, + OUT_DIP7, + OUT_SESID, + OUT_PROT, + OUT_APP0, + OUT_APP1, + OUT_IGMP0, + OUT_IGMP1, + OUT_STAG0 = 61, + OUT_STAG1 = 62, + OUT_NONE = 63, +}; + +/* parser's microcode flag type */ +enum { + FLAG_ITAG = 0, + FLAG_VLAN, + FLAG_SNAP, + FLAG_PPPOE, + FLAG_IPV6, + FLAG_IPV6FL, + FLAG_IPV4, + FLAG_IGMP, + FLAG_TU, + FLAG_HOP, + FLAG_NN1, /* 10 */ + FLAG_NN2, + FLAG_END, + FLAG_NO, /* 13 */ + FLAG_SVLAN, /* 14 */ +}; + +#define PCE_MC_M(val, msk, ns, out, len, type, flags, ipv4_len) \ + { (val), (msk), ((ns) << 10 | (out) << 4 | (len) >> 1),\ + ((len) & 1) << 15 | (type) << 13 | (flags) << 9 | (ipv4_len) << 8 } + +/* V22_2X (IPv6 issue fixed) */ +static const struct gswip_pce_microcode gsw1xx_pce_microcode[] = { + /* value mask ns fields L type flags ipv4_len */ + PCE_MC_M(0x88c3, 0xFFFF, 1, OUT_ITAG0, 4, INSTR, FLAG_ITAG, 0), + PCE_MC_M(0x8100, 0xFFFF, 4, OUT_STAG0, 2, INSTR, FLAG_SVLAN, 0), + PCE_MC_M(0x88A8, 0xFFFF, 4, OUT_STAG0, 2, INSTR, FLAG_SVLAN, 0), + PCE_MC_M(0x9100, 0xFFFF, 4, OUT_STAG0, 2, INSTR, FLAG_SVLAN, 0), + PCE_MC_M(0x8100, 0xFFFF, 5, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + PCE_MC_M(0x88A8, 0xFFFF, 6, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + PCE_MC_M(0x9100, 0xFFFF, 4, OUT_VTAG0, 2, INSTR, FLAG_VLAN, 0), + PCE_MC_M(0x8864, 0xFFFF, 20, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0800, 0xFFFF, 24, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x86DD, 0xFFFF, 25, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x8863, 0xFFFF, 19, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0xF800, 13, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 44, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0600, 0x0600, 44, OUT_ETHTYP, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 15, OUT_NONE, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0xAAAA, 0xFFFF, 17, OUT_NONE, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0300, 0xFF00, 45, OUT_NONE, 0, INSTR, FLAG_SNAP, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_DIP7, 3, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 21, OUT_DIP7, 3, INSTR, FLAG_PPPOE, 0), + PCE_MC_M(0x0021, 0xFFFF, 24, OUT_NONE, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0057, 0xFFFF, 25, OUT_NONE, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x4000, 0xF000, 27, OUT_IP0, 4, INSTR, FLAG_IPV4, 1), + PCE_MC_M(0x6000, 0xF000, 30, OUT_IP0, 3, INSTR, FLAG_IPV6, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 28, OUT_IP3, 2, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 29, OUT_SIP0, 4, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE, 0, LENACCU, FLAG_NO, 0), + PCE_MC_M(0x1100, 0xFF00, 43, OUT_PROT, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0600, 0xFF00, 43, OUT_PROT, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0xFF00, 36, OUT_IP3, 17, INSTR, FLAG_HOP, 0), + PCE_MC_M(0x2B00, 0xFF00, 36, OUT_IP3, 17, INSTR, FLAG_NN1, 0), + PCE_MC_M(0x3C00, 0xFF00, 36, OUT_IP3, 17, INSTR, FLAG_NN2, 0), + PCE_MC_M(0x0000, 0x0000, 43, OUT_PROT, 1, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x00F0, 38, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE, 0, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0xFF00, 36, OUT_NONE, 0, IPV6, FLAG_HOP, 0), + PCE_MC_M(0x2B00, 0xFF00, 36, OUT_NONE, 0, IPV6, FLAG_NN1, 0), + PCE_MC_M(0x3C00, 0xFF00, 36, OUT_NONE, 0, IPV6, FLAG_NN2, 0), + PCE_MC_M(0x0000, 0x00FC, 44, OUT_PROT, 0, IPV6, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 44, OUT_NONE, 0, IPV6, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 44, OUT_SIP0, 16, INSTR, FLAG_NO, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_APP0, 4, INSTR, FLAG_IGMP, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), + PCE_MC_M(0x0000, 0x0000, 45, OUT_NONE, 0, INSTR, FLAG_END, 0), +}; diff --git a/drivers/net/dsa/microchip/ksz9477.c b/drivers/net/dsa/microchip/ksz9477.c index 5df8f153d511b..5facffbb9c9a9 100644 --- a/drivers/net/dsa/microchip/ksz9477.c +++ b/drivers/net/dsa/microchip/ksz9477.c @@ -244,7 +244,7 @@ static int ksz9477_pcs_read(struct mii_bus *bus, int phy, int mmd, int reg) p->phydev.link = 0; } } else if (reg == MII_BMSR) { - p->phydev.link = (val & BMSR_LSTATUS); + p->phydev.link = !!(val & BMSR_LSTATUS); } } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 933ae8dc63378..15d263c3ddb3a 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -2587,8 +2587,8 @@ static int ksz_irq_phy_setup(struct ksz_device *dev) irq = irq_find_mapping(dev->ports[port].pirq.domain, PORT_SRC_PHY_INT); - if (irq < 0) { - ret = irq; + if (!irq) { + ret = -EINVAL; goto out; } ds->user_mii_bus->irq[phy] = irq; @@ -2862,14 +2862,17 @@ static void ksz_irq_free(struct ksz_irq *kirq) { int irq, virq; - free_irq(kirq->irq_num, kirq); + if (kirq->irq_num) + free_irq(kirq->irq_num, kirq); - for (irq = 0; irq < kirq->nirqs; irq++) { - virq = irq_find_mapping(kirq->domain, irq); - irq_dispose_mapping(virq); - } + if (kirq->domain) { + for (irq = 0; irq < kirq->nirqs; irq++) { + virq = irq_find_mapping(kirq->domain, irq); + irq_dispose_mapping(virq); + } - irq_domain_remove(kirq->domain); + irq_domain_remove(kirq->domain); + } } static irqreturn_t ksz_irq_thread_fn(int irq, void *dev_id) @@ -2952,8 +2955,8 @@ static int ksz_pirq_setup(struct ksz_device *dev, u8 p) snprintf(pirq->name, sizeof(pirq->name), "port_irq-%d", p); pirq->irq_num = irq_find_mapping(dev->girq.domain, p); - if (pirq->irq_num < 0) - return pirq->irq_num; + if (!pirq->irq_num) + return -EINVAL; return ksz_irq_common_setup(dev, pirq); } diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c index 35fc21b1ee48a..a8ad99c6ee35f 100644 --- a/drivers/net/dsa/microchip/ksz_ptp.c +++ b/drivers/net/dsa/microchip/ksz_ptp.c @@ -1102,10 +1102,6 @@ static int ksz_ptp_msg_irq_setup(struct ksz_port *port, u8 n) strscpy(ptpmsg_irq->name, name[n]); - ptpmsg_irq->num = irq_find_mapping(port->ptpirq.domain, n); - if (ptpmsg_irq->num < 0) - return ptpmsg_irq->num; - return request_threaded_irq(ptpmsg_irq->num, NULL, ksz_ptp_msg_thread_fn, IRQF_ONESHOT, ptpmsg_irq->name, ptpmsg_irq); @@ -1135,12 +1131,17 @@ int ksz_ptp_irq_setup(struct dsa_switch *ds, u8 p) if (!ptpirq->domain) return -ENOMEM; - for (irq = 0; irq < ptpirq->nirqs; irq++) - irq_create_mapping(ptpirq->domain, irq); + for (irq = 0; irq < ptpirq->nirqs; irq++) { + port->ptpmsg_irq[irq].num = irq_create_mapping(ptpirq->domain, irq); + if (!port->ptpmsg_irq[irq].num) { + ret = -EINVAL; + goto out; + } + } ptpirq->irq_num = irq_find_mapping(port->pirq.domain, PORT_SRC_PTP_INT); - if (ptpirq->irq_num < 0) { - ret = ptpirq->irq_num; + if (!ptpirq->irq_num) { + ret = -EINVAL; goto out; } diff --git a/drivers/net/dsa/microchip/lan937x_main.c b/drivers/net/dsa/microchip/lan937x_main.c index b1ae3b9de3d16..5a1496fff4452 100644 --- a/drivers/net/dsa/microchip/lan937x_main.c +++ b/drivers/net/dsa/microchip/lan937x_main.c @@ -540,6 +540,7 @@ static void lan937x_set_tune_adj(struct ksz_device *dev, int port, ksz_pread16(dev, port, reg, &data16); /* Update tune Adjust */ + data16 &= ~PORT_TUNE_ADJ; data16 |= FIELD_PREP(PORT_TUNE_ADJ, val); ksz_pwrite16(dev, port, reg, data16); diff --git a/drivers/net/dsa/yt921x.c b/drivers/net/dsa/yt921x.c new file mode 100644 index 0000000000000..944988e29127d --- /dev/null +++ b/drivers/net/dsa/yt921x.c @@ -0,0 +1,2891 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Motorcomm YT921x Switch + * + * Should work on YT9213/YT9214/YT9215/YT9218, but only tested on YT9215+SGMII, + * be sure to do your own checks before porting to another chip. + * + * Copyright (c) 2025 David Yang + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include + +#include "yt921x.h" + +struct yt921x_mib_desc { + unsigned int size; + unsigned int offset; + const char *name; +}; + +#define MIB_DESC(_size, _offset, _name) \ + {_size, _offset, _name} + +/* Must agree with yt921x_mib + * + * Unstructured fields (name != NULL) will appear in get_ethtool_stats(), + * structured go to their *_stats() methods, but we need their sizes and offsets + * to perform 32bit MIB overflow wraparound. + */ +static const struct yt921x_mib_desc yt921x_mib_descs[] = { + MIB_DESC(1, 0x00, NULL), /* RxBroadcast */ + MIB_DESC(1, 0x04, NULL), /* RxPause */ + MIB_DESC(1, 0x08, NULL), /* RxMulticast */ + MIB_DESC(1, 0x0c, NULL), /* RxCrcErr */ + + MIB_DESC(1, 0x10, NULL), /* RxAlignErr */ + MIB_DESC(1, 0x14, NULL), /* RxUnderSizeErr */ + MIB_DESC(1, 0x18, NULL), /* RxFragErr */ + MIB_DESC(1, 0x1c, NULL), /* RxPktSz64 */ + + MIB_DESC(1, 0x20, NULL), /* RxPktSz65To127 */ + MIB_DESC(1, 0x24, NULL), /* RxPktSz128To255 */ + MIB_DESC(1, 0x28, NULL), /* RxPktSz256To511 */ + MIB_DESC(1, 0x2c, NULL), /* RxPktSz512To1023 */ + + MIB_DESC(1, 0x30, NULL), /* RxPktSz1024To1518 */ + MIB_DESC(1, 0x34, NULL), /* RxPktSz1519ToMax */ + MIB_DESC(2, 0x38, NULL), /* RxGoodBytes */ + /* 0x3c */ + + MIB_DESC(2, 0x40, "RxBadBytes"), + /* 0x44 */ + MIB_DESC(2, 0x48, NULL), /* RxOverSzErr */ + /* 0x4c */ + + MIB_DESC(1, 0x50, NULL), /* RxDropped */ + MIB_DESC(1, 0x54, NULL), /* TxBroadcast */ + MIB_DESC(1, 0x58, NULL), /* TxPause */ + MIB_DESC(1, 0x5c, NULL), /* TxMulticast */ + + MIB_DESC(1, 0x60, NULL), /* TxUnderSizeErr */ + MIB_DESC(1, 0x64, NULL), /* TxPktSz64 */ + MIB_DESC(1, 0x68, NULL), /* TxPktSz65To127 */ + MIB_DESC(1, 0x6c, NULL), /* TxPktSz128To255 */ + + MIB_DESC(1, 0x70, NULL), /* TxPktSz256To511 */ + MIB_DESC(1, 0x74, NULL), /* TxPktSz512To1023 */ + MIB_DESC(1, 0x78, NULL), /* TxPktSz1024To1518 */ + MIB_DESC(1, 0x7c, NULL), /* TxPktSz1519ToMax */ + + MIB_DESC(2, 0x80, NULL), /* TxGoodBytes */ + /* 0x84 */ + MIB_DESC(2, 0x88, NULL), /* TxCollision */ + /* 0x8c */ + + MIB_DESC(1, 0x90, NULL), /* TxExcessiveCollistion */ + MIB_DESC(1, 0x94, NULL), /* TxMultipleCollision */ + MIB_DESC(1, 0x98, NULL), /* TxSingleCollision */ + MIB_DESC(1, 0x9c, NULL), /* TxPkt */ + + MIB_DESC(1, 0xa0, NULL), /* TxDeferred */ + MIB_DESC(1, 0xa4, NULL), /* TxLateCollision */ + MIB_DESC(1, 0xa8, "RxOAM"), + MIB_DESC(1, 0xac, "TxOAM"), +}; + +struct yt921x_info { + const char *name; + u16 major; + /* Unknown, seems to be plain enumeration */ + u8 mode; + u8 extmode; + /* Ports with integral GbE PHYs, not including MCU Port 10 */ + u16 internal_mask; + /* TODO: see comments in yt921x_dsa_phylink_get_caps() */ + u16 external_mask; +}; + +#define YT921X_PORT_MASK_INTn(port) BIT(port) +#define YT921X_PORT_MASK_INT0_n(n) GENMASK((n) - 1, 0) +#define YT921X_PORT_MASK_EXT0 BIT(8) +#define YT921X_PORT_MASK_EXT1 BIT(9) + +static const struct yt921x_info yt921x_infos[] = { + { + "YT9215SC", YT9215_MAJOR, 1, 0, + YT921X_PORT_MASK_INT0_n(5), + YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1, + }, + { + "YT9215S", YT9215_MAJOR, 2, 0, + YT921X_PORT_MASK_INT0_n(5), + YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1, + }, + { + "YT9215RB", YT9215_MAJOR, 3, 0, + YT921X_PORT_MASK_INT0_n(5), + YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1, + }, + { + "YT9214NB", YT9215_MAJOR, 3, 2, + YT921X_PORT_MASK_INTn(1) | YT921X_PORT_MASK_INTn(3), + YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1, + }, + { + "YT9213NB", YT9215_MAJOR, 3, 3, + YT921X_PORT_MASK_INTn(1) | YT921X_PORT_MASK_INTn(3), + YT921X_PORT_MASK_EXT1, + }, + { + "YT9218N", YT9218_MAJOR, 0, 0, + YT921X_PORT_MASK_INT0_n(8), + 0, + }, + { + "YT9218MB", YT9218_MAJOR, 1, 0, + YT921X_PORT_MASK_INT0_n(8), + YT921X_PORT_MASK_EXT0 | YT921X_PORT_MASK_EXT1, + }, + {} +}; + +#define YT921X_NAME "yt921x" + +#define YT921X_VID_UNWARE 4095 + +#define YT921X_POLL_SLEEP_US 10000 +#define YT921X_POLL_TIMEOUT_US 100000 + +/* The interval should be small enough to avoid overflow of 32bit MIBs. + * + * Until we can read MIBs from stats64 call directly (i.e. sleep + * there), we have to poll stats more frequently then it is actually needed. + * For overflow protection, normally, 100 sec interval should have been OK. + */ +#define YT921X_STATS_INTERVAL_JIFFIES (3 * HZ) + +struct yt921x_reg_mdio { + struct mii_bus *bus; + int addr; + /* SWITCH_ID_1 / SWITCH_ID_0 of the device + * + * This is a way to multiplex multiple devices on the same MII phyaddr + * and should be configurable in DT. However, MDIO core simply doesn't + * allow multiple devices over one reg addr, so this is a fixed value + * for now until a solution is found. + * + * Keep this because we need switchid to form MII regaddrs anyway. + */ + unsigned char switchid; +}; + +/* TODO: SPI/I2C */ + +#define to_yt921x_priv(_ds) container_of_const(_ds, struct yt921x_priv, ds) +#define to_device(priv) ((priv)->ds.dev) + +static int yt921x_reg_read(struct yt921x_priv *priv, u32 reg, u32 *valp) +{ + WARN_ON(!mutex_is_locked(&priv->reg_lock)); + + return priv->reg_ops->read(priv->reg_ctx, reg, valp); +} + +static int yt921x_reg_write(struct yt921x_priv *priv, u32 reg, u32 val) +{ + WARN_ON(!mutex_is_locked(&priv->reg_lock)); + + return priv->reg_ops->write(priv->reg_ctx, reg, val); +} + +static int +yt921x_reg_wait(struct yt921x_priv *priv, u32 reg, u32 mask, u32 *valp) +{ + u32 val; + int res; + int ret; + + ret = read_poll_timeout(yt921x_reg_read, res, + res || (val & mask) == *valp, + YT921X_POLL_SLEEP_US, YT921X_POLL_TIMEOUT_US, + false, priv, reg, &val); + if (ret) + return ret; + if (res) + return res; + + *valp = val; + return 0; +} + +static int +yt921x_reg_update_bits(struct yt921x_priv *priv, u32 reg, u32 mask, u32 val) +{ + int res; + u32 v; + u32 u; + + res = yt921x_reg_read(priv, reg, &v); + if (res) + return res; + + u = v; + u &= ~mask; + u |= val; + if (u == v) + return 0; + + return yt921x_reg_write(priv, reg, u); +} + +static int yt921x_reg_set_bits(struct yt921x_priv *priv, u32 reg, u32 mask) +{ + return yt921x_reg_update_bits(priv, reg, 0, mask); +} + +static int yt921x_reg_clear_bits(struct yt921x_priv *priv, u32 reg, u32 mask) +{ + return yt921x_reg_update_bits(priv, reg, mask, 0); +} + +static int +yt921x_reg_toggle_bits(struct yt921x_priv *priv, u32 reg, u32 mask, bool set) +{ + return yt921x_reg_update_bits(priv, reg, mask, !set ? 0 : mask); +} + +/* Some registers, like VLANn_CTRL, should always be written in 64-bit, even if + * you are to write only the lower / upper 32 bits. + * + * There is no such restriction for reading, but we still provide 64-bit read + * wrappers so that we always handle u64 values. + */ + +static int yt921x_reg64_read(struct yt921x_priv *priv, u32 reg, u64 *valp) +{ + u32 lo; + u32 hi; + int res; + + res = yt921x_reg_read(priv, reg, &lo); + if (res) + return res; + res = yt921x_reg_read(priv, reg + 4, &hi); + if (res) + return res; + + *valp = ((u64)hi << 32) | lo; + return 0; +} + +static int yt921x_reg64_write(struct yt921x_priv *priv, u32 reg, u64 val) +{ + int res; + + res = yt921x_reg_write(priv, reg, (u32)val); + if (res) + return res; + return yt921x_reg_write(priv, reg + 4, (u32)(val >> 32)); +} + +static int +yt921x_reg64_update_bits(struct yt921x_priv *priv, u32 reg, u64 mask, u64 val) +{ + int res; + u64 v; + u64 u; + + res = yt921x_reg64_read(priv, reg, &v); + if (res) + return res; + + u = v; + u &= ~mask; + u |= val; + if (u == v) + return 0; + + return yt921x_reg64_write(priv, reg, u); +} + +static int yt921x_reg64_clear_bits(struct yt921x_priv *priv, u32 reg, u64 mask) +{ + return yt921x_reg64_update_bits(priv, reg, mask, 0); +} + +static int yt921x_reg_mdio_read(void *context, u32 reg, u32 *valp) +{ + struct yt921x_reg_mdio *mdio = context; + struct mii_bus *bus = mdio->bus; + int addr = mdio->addr; + u32 reg_addr; + u32 reg_data; + u32 val; + int res; + + /* Hold the mdio bus lock to avoid (un)locking for 4 times */ + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); + + reg_addr = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_ADDR | + YT921X_SMI_READ; + res = __mdiobus_write(bus, addr, reg_addr, (u16)(reg >> 16)); + if (res) + goto end; + res = __mdiobus_write(bus, addr, reg_addr, (u16)reg); + if (res) + goto end; + + reg_data = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_DATA | + YT921X_SMI_READ; + res = __mdiobus_read(bus, addr, reg_data); + if (res < 0) + goto end; + val = (u16)res; + res = __mdiobus_read(bus, addr, reg_data); + if (res < 0) + goto end; + val = (val << 16) | (u16)res; + + *valp = val; + res = 0; + +end: + mutex_unlock(&bus->mdio_lock); + return res; +} + +static int yt921x_reg_mdio_write(void *context, u32 reg, u32 val) +{ + struct yt921x_reg_mdio *mdio = context; + struct mii_bus *bus = mdio->bus; + int addr = mdio->addr; + u32 reg_addr; + u32 reg_data; + int res; + + mutex_lock_nested(&bus->mdio_lock, MDIO_MUTEX_NESTED); + + reg_addr = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_ADDR | + YT921X_SMI_WRITE; + res = __mdiobus_write(bus, addr, reg_addr, (u16)(reg >> 16)); + if (res) + goto end; + res = __mdiobus_write(bus, addr, reg_addr, (u16)reg); + if (res) + goto end; + + reg_data = YT921X_SMI_SWITCHID(mdio->switchid) | YT921X_SMI_DATA | + YT921X_SMI_WRITE; + res = __mdiobus_write(bus, addr, reg_data, (u16)(val >> 16)); + if (res) + goto end; + res = __mdiobus_write(bus, addr, reg_data, (u16)val); + if (res) + goto end; + + res = 0; + +end: + mutex_unlock(&bus->mdio_lock); + return res; +} + +static const struct yt921x_reg_ops yt921x_reg_ops_mdio = { + .read = yt921x_reg_mdio_read, + .write = yt921x_reg_mdio_write, +}; + +/* TODO: SPI/I2C */ + +static int yt921x_intif_wait(struct yt921x_priv *priv) +{ + u32 val = 0; + + return yt921x_reg_wait(priv, YT921X_INT_MBUS_OP, YT921X_MBUS_OP_START, + &val); +} + +static int +yt921x_intif_read(struct yt921x_priv *priv, int port, int reg, u16 *valp) +{ + struct device *dev = to_device(priv); + u32 mask; + u32 ctrl; + u32 val; + int res; + + res = yt921x_intif_wait(priv); + if (res) + return res; + + mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M | + YT921X_MBUS_CTRL_OP_M; + ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) | + YT921X_MBUS_CTRL_READ; + res = yt921x_reg_update_bits(priv, YT921X_INT_MBUS_CTRL, mask, ctrl); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_INT_MBUS_OP, YT921X_MBUS_OP_START); + if (res) + return res; + + res = yt921x_intif_wait(priv); + if (res) + return res; + res = yt921x_reg_read(priv, YT921X_INT_MBUS_DIN, &val); + if (res) + return res; + + if ((u16)val != val) + dev_info(dev, + "%s: port %d, reg 0x%x: Expected u16, got 0x%08x\n", + __func__, port, reg, val); + *valp = (u16)val; + return 0; +} + +static int +yt921x_intif_write(struct yt921x_priv *priv, int port, int reg, u16 val) +{ + u32 mask; + u32 ctrl; + int res; + + res = yt921x_intif_wait(priv); + if (res) + return res; + + mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M | + YT921X_MBUS_CTRL_OP_M; + ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) | + YT921X_MBUS_CTRL_WRITE; + res = yt921x_reg_update_bits(priv, YT921X_INT_MBUS_CTRL, mask, ctrl); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_INT_MBUS_DOUT, val); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_INT_MBUS_OP, YT921X_MBUS_OP_START); + if (res) + return res; + + return yt921x_intif_wait(priv); +} + +static int yt921x_mbus_int_read(struct mii_bus *mbus, int port, int reg) +{ + struct yt921x_priv *priv = mbus->priv; + u16 val; + int res; + + if (port >= YT921X_PORT_NUM) + return U16_MAX; + + mutex_lock(&priv->reg_lock); + res = yt921x_intif_read(priv, port, reg, &val); + mutex_unlock(&priv->reg_lock); + + if (res) + return res; + return val; +} + +static int +yt921x_mbus_int_write(struct mii_bus *mbus, int port, int reg, u16 data) +{ + struct yt921x_priv *priv = mbus->priv; + int res; + + if (port >= YT921X_PORT_NUM) + return -ENODEV; + + mutex_lock(&priv->reg_lock); + res = yt921x_intif_write(priv, port, reg, data); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_mbus_int_init(struct yt921x_priv *priv, struct device_node *mnp) +{ + struct device *dev = to_device(priv); + struct mii_bus *mbus; + int res; + + mbus = devm_mdiobus_alloc(dev); + if (!mbus) + return -ENOMEM; + + mbus->name = "YT921x internal MDIO bus"; + snprintf(mbus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); + mbus->priv = priv; + mbus->read = yt921x_mbus_int_read; + mbus->write = yt921x_mbus_int_write; + mbus->parent = dev; + mbus->phy_mask = (u32)~GENMASK(YT921X_PORT_NUM - 1, 0); + + res = devm_of_mdiobus_register(dev, mbus, mnp); + if (res) + return res; + + priv->mbus_int = mbus; + + return 0; +} + +static int yt921x_extif_wait(struct yt921x_priv *priv) +{ + u32 val = 0; + + return yt921x_reg_wait(priv, YT921X_EXT_MBUS_OP, YT921X_MBUS_OP_START, + &val); +} + +static int +yt921x_extif_read(struct yt921x_priv *priv, int port, int reg, u16 *valp) +{ + struct device *dev = to_device(priv); + u32 mask; + u32 ctrl; + u32 val; + int res; + + res = yt921x_extif_wait(priv); + if (res) + return res; + + mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M | + YT921X_MBUS_CTRL_TYPE_M | YT921X_MBUS_CTRL_OP_M; + ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) | + YT921X_MBUS_CTRL_TYPE_C22 | YT921X_MBUS_CTRL_READ; + res = yt921x_reg_update_bits(priv, YT921X_EXT_MBUS_CTRL, mask, ctrl); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_EXT_MBUS_OP, YT921X_MBUS_OP_START); + if (res) + return res; + + res = yt921x_extif_wait(priv); + if (res) + return res; + res = yt921x_reg_read(priv, YT921X_EXT_MBUS_DIN, &val); + if (res) + return res; + + if ((u16)val != val) + dev_info(dev, + "%s: port %d, reg 0x%x: Expected u16, got 0x%08x\n", + __func__, port, reg, val); + *valp = (u16)val; + return 0; +} + +static int +yt921x_extif_write(struct yt921x_priv *priv, int port, int reg, u16 val) +{ + u32 mask; + u32 ctrl; + int res; + + res = yt921x_extif_wait(priv); + if (res) + return res; + + mask = YT921X_MBUS_CTRL_PORT_M | YT921X_MBUS_CTRL_REG_M | + YT921X_MBUS_CTRL_TYPE_M | YT921X_MBUS_CTRL_OP_M; + ctrl = YT921X_MBUS_CTRL_PORT(port) | YT921X_MBUS_CTRL_REG(reg) | + YT921X_MBUS_CTRL_TYPE_C22 | YT921X_MBUS_CTRL_WRITE; + res = yt921x_reg_update_bits(priv, YT921X_EXT_MBUS_CTRL, mask, ctrl); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_EXT_MBUS_DOUT, val); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_EXT_MBUS_OP, YT921X_MBUS_OP_START); + if (res) + return res; + + return yt921x_extif_wait(priv); +} + +static int yt921x_mbus_ext_read(struct mii_bus *mbus, int port, int reg) +{ + struct yt921x_priv *priv = mbus->priv; + u16 val; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_extif_read(priv, port, reg, &val); + mutex_unlock(&priv->reg_lock); + + if (res) + return res; + return val; +} + +static int +yt921x_mbus_ext_write(struct mii_bus *mbus, int port, int reg, u16 data) +{ + struct yt921x_priv *priv = mbus->priv; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_extif_write(priv, port, reg, data); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_mbus_ext_init(struct yt921x_priv *priv, struct device_node *mnp) +{ + struct device *dev = to_device(priv); + struct mii_bus *mbus; + int res; + + mbus = devm_mdiobus_alloc(dev); + if (!mbus) + return -ENOMEM; + + mbus->name = "YT921x external MDIO bus"; + snprintf(mbus->id, MII_BUS_ID_SIZE, "%s@ext", dev_name(dev)); + mbus->priv = priv; + /* TODO: c45? */ + mbus->read = yt921x_mbus_ext_read; + mbus->write = yt921x_mbus_ext_write; + mbus->parent = dev; + + res = devm_of_mdiobus_register(dev, mbus, mnp); + if (res) + return res; + + priv->mbus_ext = mbus; + + return 0; +} + +/* Read and handle overflow of 32bit MIBs. MIB buffer must be zeroed before. */ +static int yt921x_read_mib(struct yt921x_priv *priv, int port) +{ + struct yt921x_port *pp = &priv->ports[port]; + struct device *dev = to_device(priv); + struct yt921x_mib *mib = &pp->mib; + int res = 0; + + /* Reading of yt921x_port::mib is not protected by a lock and it's vain + * to keep its consistency, since we have to read registers one by one + * and there is no way to make a snapshot of MIB stats. + * + * Writing (by this function only) is and should be protected by + * reg_lock. + */ + + for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) { + const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i]; + u32 reg = YT921X_MIBn_DATA0(port) + desc->offset; + u64 *valp = &((u64 *)mib)[i]; + u64 val = *valp; + u32 val0; + u32 val1; + + res = yt921x_reg_read(priv, reg, &val0); + if (res) + break; + + if (desc->size <= 1) { + if (val < (u32)val) + /* overflow */ + val += (u64)U32_MAX + 1; + val &= ~U32_MAX; + val |= val0; + } else { + res = yt921x_reg_read(priv, reg + 4, &val1); + if (res) + break; + val = ((u64)val0 << 32) | val1; + } + + WRITE_ONCE(*valp, val); + } + + pp->rx_frames = mib->rx_64byte + mib->rx_65_127byte + + mib->rx_128_255byte + mib->rx_256_511byte + + mib->rx_512_1023byte + mib->rx_1024_1518byte + + mib->rx_jumbo; + pp->tx_frames = mib->tx_64byte + mib->tx_65_127byte + + mib->tx_128_255byte + mib->tx_256_511byte + + mib->tx_512_1023byte + mib->tx_1024_1518byte + + mib->tx_jumbo; + + if (res) + dev_err(dev, "Failed to %s port %d: %i\n", "read stats for", + port, res); + return res; +} + +static void yt921x_poll_mib(struct work_struct *work) +{ + struct yt921x_port *pp = container_of_const(work, struct yt921x_port, + mib_read.work); + struct yt921x_priv *priv = (void *)(pp - pp->index) - + offsetof(struct yt921x_priv, ports); + unsigned long delay = YT921X_STATS_INTERVAL_JIFFIES; + int port = pp->index; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_read_mib(priv, port); + mutex_unlock(&priv->reg_lock); + if (res) + delay *= 4; + + schedule_delayed_work(&pp->mib_read, delay); +} + +static void +yt921x_dsa_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data) +{ + if (stringset != ETH_SS_STATS) + return; + + for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) { + const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i]; + + if (desc->name) + ethtool_puts(&data, desc->name); + } +} + +static void +yt921x_dsa_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct yt921x_port *pp = &priv->ports[port]; + struct yt921x_mib *mib = &pp->mib; + size_t j; + + mutex_lock(&priv->reg_lock); + yt921x_read_mib(priv, port); + mutex_unlock(&priv->reg_lock); + + j = 0; + for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) { + const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i]; + + if (!desc->name) + continue; + + data[j] = ((u64 *)mib)[i]; + j++; + } +} + +static int yt921x_dsa_get_sset_count(struct dsa_switch *ds, int port, int sset) +{ + int cnt = 0; + + if (sset != ETH_SS_STATS) + return 0; + + for (size_t i = 0; i < ARRAY_SIZE(yt921x_mib_descs); i++) { + const struct yt921x_mib_desc *desc = &yt921x_mib_descs[i]; + + if (desc->name) + cnt++; + } + + return cnt; +} + +static void +yt921x_dsa_get_eth_mac_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct yt921x_port *pp = &priv->ports[port]; + struct yt921x_mib *mib = &pp->mib; + + mutex_lock(&priv->reg_lock); + yt921x_read_mib(priv, port); + mutex_unlock(&priv->reg_lock); + + mac_stats->FramesTransmittedOK = pp->tx_frames; + mac_stats->SingleCollisionFrames = mib->tx_single_collisions; + mac_stats->MultipleCollisionFrames = mib->tx_multiple_collisions; + mac_stats->FramesReceivedOK = pp->rx_frames; + mac_stats->FrameCheckSequenceErrors = mib->rx_crc_errors; + mac_stats->AlignmentErrors = mib->rx_alignment_errors; + mac_stats->OctetsTransmittedOK = mib->tx_good_bytes; + mac_stats->FramesWithDeferredXmissions = mib->tx_deferred; + mac_stats->LateCollisions = mib->tx_late_collisions; + mac_stats->FramesAbortedDueToXSColls = mib->tx_aborted_errors; + /* mac_stats->FramesLostDueToIntMACXmitError */ + /* mac_stats->CarrierSenseErrors */ + mac_stats->OctetsReceivedOK = mib->rx_good_bytes; + /* mac_stats->FramesLostDueToIntMACRcvError */ + mac_stats->MulticastFramesXmittedOK = mib->tx_multicast; + mac_stats->BroadcastFramesXmittedOK = mib->tx_broadcast; + /* mac_stats->FramesWithExcessiveDeferral */ + mac_stats->MulticastFramesReceivedOK = mib->rx_multicast; + mac_stats->BroadcastFramesReceivedOK = mib->rx_broadcast; + /* mac_stats->InRangeLengthErrors */ + /* mac_stats->OutOfRangeLengthField */ + mac_stats->FrameTooLongErrors = mib->rx_oversize_errors; +} + +static void +yt921x_dsa_get_eth_ctrl_stats(struct dsa_switch *ds, int port, + struct ethtool_eth_ctrl_stats *ctrl_stats) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct yt921x_port *pp = &priv->ports[port]; + struct yt921x_mib *mib = &pp->mib; + + mutex_lock(&priv->reg_lock); + yt921x_read_mib(priv, port); + mutex_unlock(&priv->reg_lock); + + ctrl_stats->MACControlFramesTransmitted = mib->tx_pause; + ctrl_stats->MACControlFramesReceived = mib->rx_pause; + /* ctrl_stats->UnsupportedOpcodesReceived */ +} + +static const struct ethtool_rmon_hist_range yt921x_rmon_ranges[] = { + { 0, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1518 }, + { 1519, YT921X_FRAME_SIZE_MAX }, + {} +}; + +static void +yt921x_dsa_get_rmon_stats(struct dsa_switch *ds, int port, + struct ethtool_rmon_stats *rmon_stats, + const struct ethtool_rmon_hist_range **ranges) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct yt921x_port *pp = &priv->ports[port]; + struct yt921x_mib *mib = &pp->mib; + + mutex_lock(&priv->reg_lock); + yt921x_read_mib(priv, port); + mutex_unlock(&priv->reg_lock); + + *ranges = yt921x_rmon_ranges; + + rmon_stats->undersize_pkts = mib->rx_undersize_errors; + rmon_stats->oversize_pkts = mib->rx_oversize_errors; + rmon_stats->fragments = mib->rx_alignment_errors; + /* rmon_stats->jabbers */ + + rmon_stats->hist[0] = mib->rx_64byte; + rmon_stats->hist[1] = mib->rx_65_127byte; + rmon_stats->hist[2] = mib->rx_128_255byte; + rmon_stats->hist[3] = mib->rx_256_511byte; + rmon_stats->hist[4] = mib->rx_512_1023byte; + rmon_stats->hist[5] = mib->rx_1024_1518byte; + rmon_stats->hist[6] = mib->rx_jumbo; + + rmon_stats->hist_tx[0] = mib->tx_64byte; + rmon_stats->hist_tx[1] = mib->tx_65_127byte; + rmon_stats->hist_tx[2] = mib->tx_128_255byte; + rmon_stats->hist_tx[3] = mib->tx_256_511byte; + rmon_stats->hist_tx[4] = mib->tx_512_1023byte; + rmon_stats->hist_tx[5] = mib->tx_1024_1518byte; + rmon_stats->hist_tx[6] = mib->tx_jumbo; +} + +static void +yt921x_dsa_get_stats64(struct dsa_switch *ds, int port, + struct rtnl_link_stats64 *stats) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct yt921x_port *pp = &priv->ports[port]; + struct yt921x_mib *mib = &pp->mib; + + stats->rx_length_errors = mib->rx_undersize_errors + + mib->rx_fragment_errors; + stats->rx_over_errors = mib->rx_oversize_errors; + stats->rx_crc_errors = mib->rx_crc_errors; + stats->rx_frame_errors = mib->rx_alignment_errors; + /* stats->rx_fifo_errors */ + /* stats->rx_missed_errors */ + + stats->tx_aborted_errors = mib->tx_aborted_errors; + /* stats->tx_carrier_errors */ + stats->tx_fifo_errors = mib->tx_undersize_errors; + /* stats->tx_heartbeat_errors */ + stats->tx_window_errors = mib->tx_late_collisions; + + stats->rx_packets = pp->rx_frames; + stats->tx_packets = pp->tx_frames; + stats->rx_bytes = mib->rx_good_bytes - ETH_FCS_LEN * stats->rx_packets; + stats->tx_bytes = mib->tx_good_bytes - ETH_FCS_LEN * stats->tx_packets; + stats->rx_errors = stats->rx_length_errors + stats->rx_over_errors + + stats->rx_crc_errors + stats->rx_frame_errors; + stats->tx_errors = stats->tx_aborted_errors + stats->tx_fifo_errors + + stats->tx_window_errors; + stats->rx_dropped = mib->rx_dropped; + /* stats->tx_dropped */ + stats->multicast = mib->rx_multicast; + stats->collisions = mib->tx_collisions; +} + +static void +yt921x_dsa_get_pause_stats(struct dsa_switch *ds, int port, + struct ethtool_pause_stats *pause_stats) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct yt921x_port *pp = &priv->ports[port]; + struct yt921x_mib *mib = &pp->mib; + + mutex_lock(&priv->reg_lock); + yt921x_read_mib(priv, port); + mutex_unlock(&priv->reg_lock); + + pause_stats->tx_pause_frames = mib->tx_pause; + pause_stats->rx_pause_frames = mib->rx_pause; +} + +static int +yt921x_set_eee(struct yt921x_priv *priv, int port, struct ethtool_keee *e) +{ + /* Poor datasheet for EEE operations; don't ask if you are confused */ + + bool enable = e->eee_enabled; + u16 new_mask; + int res; + + /* Enable / disable global EEE */ + new_mask = priv->eee_ports_mask; + new_mask &= ~BIT(port); + new_mask |= !enable ? 0 : BIT(port); + + if (!!new_mask != !!priv->eee_ports_mask) { + res = yt921x_reg_toggle_bits(priv, YT921X_PON_STRAP_FUNC, + YT921X_PON_STRAP_EEE, !!new_mask); + if (res) + return res; + res = yt921x_reg_toggle_bits(priv, YT921X_PON_STRAP_VAL, + YT921X_PON_STRAP_EEE, !!new_mask); + if (res) + return res; + } + + priv->eee_ports_mask = new_mask; + + /* Enable / disable port EEE */ + res = yt921x_reg_toggle_bits(priv, YT921X_EEE_CTRL, + YT921X_EEE_CTRL_ENn(port), enable); + if (res) + return res; + res = yt921x_reg_toggle_bits(priv, YT921X_EEEn_VAL(port), + YT921X_EEE_VAL_DATA, enable); + if (res) + return res; + + return 0; +} + +static int +yt921x_dsa_set_mac_eee(struct dsa_switch *ds, int port, struct ethtool_keee *e) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_set_eee(priv, port, e); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_change_mtu(struct dsa_switch *ds, int port, int new_mtu) +{ + /* Only serves as packet filter, since the frame size is always set to + * maximum after reset + */ + + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct dsa_port *dp = dsa_to_port(ds, port); + int frame_size; + int res; + + frame_size = new_mtu + ETH_HLEN + ETH_FCS_LEN; + if (dsa_port_is_cpu(dp)) + frame_size += YT921X_TAG_LEN; + + mutex_lock(&priv->reg_lock); + res = yt921x_reg_update_bits(priv, YT921X_MACn_FRAME(port), + YT921X_MAC_FRAME_SIZE_M, + YT921X_MAC_FRAME_SIZE(frame_size)); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int yt921x_dsa_port_max_mtu(struct dsa_switch *ds, int port) +{ + /* Only called for user ports, exclude tag len here */ + return YT921X_FRAME_SIZE_MAX - ETH_HLEN - ETH_FCS_LEN - YT921X_TAG_LEN; +} + +static int +yt921x_mirror_del(struct yt921x_priv *priv, int port, bool ingress) +{ + u32 mask; + + if (ingress) + mask = YT921X_MIRROR_IGR_PORTn(port); + else + mask = YT921X_MIRROR_EGR_PORTn(port); + return yt921x_reg_clear_bits(priv, YT921X_MIRROR, mask); +} + +static int +yt921x_mirror_add(struct yt921x_priv *priv, int port, bool ingress, + int to_local_port, struct netlink_ext_ack *extack) +{ + u32 srcs; + u32 ctrl; + u32 val; + u32 dst; + int res; + + if (ingress) + srcs = YT921X_MIRROR_IGR_PORTn(port); + else + srcs = YT921X_MIRROR_EGR_PORTn(port); + dst = YT921X_MIRROR_PORT(to_local_port); + + res = yt921x_reg_read(priv, YT921X_MIRROR, &val); + if (res) + return res; + + /* other mirror tasks & different dst port -> conflict */ + if ((val & ~srcs & (YT921X_MIRROR_EGR_PORTS_M | + YT921X_MIRROR_IGR_PORTS_M)) && + (val & YT921X_MIRROR_PORT_M) != dst) { + NL_SET_ERR_MSG_MOD(extack, + "Sniffer port is already configured, delete existing rules & retry"); + return -EBUSY; + } + + ctrl = val & ~YT921X_MIRROR_PORT_M; + ctrl |= srcs; + ctrl |= dst; + + if (ctrl == val) + return 0; + + return yt921x_reg_write(priv, YT921X_MIRROR, ctrl); +} + +static void +yt921x_dsa_port_mirror_del(struct dsa_switch *ds, int port, + struct dsa_mall_mirror_tc_entry *mirror) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct device *dev = to_device(priv); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_mirror_del(priv, port, mirror->ingress); + mutex_unlock(&priv->reg_lock); + + if (res) + dev_err(dev, "Failed to %s port %d: %i\n", "unmirror", + port, res); +} + +static int +yt921x_dsa_port_mirror_add(struct dsa_switch *ds, int port, + struct dsa_mall_mirror_tc_entry *mirror, + bool ingress, struct netlink_ext_ack *extack) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_mirror_add(priv, port, ingress, + mirror->to_local_port, extack); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int yt921x_fdb_wait(struct yt921x_priv *priv, u32 *valp) +{ + struct device *dev = to_device(priv); + u32 val = YT921X_FDB_RESULT_DONE; + int res; + + res = yt921x_reg_wait(priv, YT921X_FDB_RESULT, YT921X_FDB_RESULT_DONE, + &val); + if (res) { + dev_err(dev, "FDB probably stuck\n"); + return res; + } + + *valp = val; + return 0; +} + +static int +yt921x_fdb_in01(struct yt921x_priv *priv, const unsigned char *addr, + u16 vid, u32 ctrl1) +{ + u32 ctrl; + int res; + + ctrl = (addr[0] << 24) | (addr[1] << 16) | (addr[2] << 8) | addr[3]; + res = yt921x_reg_write(priv, YT921X_FDB_IN0, ctrl); + if (res) + return res; + + ctrl = ctrl1 | YT921X_FDB_IO1_FID(vid) | (addr[4] << 8) | addr[5]; + return yt921x_reg_write(priv, YT921X_FDB_IN1, ctrl); +} + +static int +yt921x_fdb_has(struct yt921x_priv *priv, const unsigned char *addr, u16 vid, + u16 *indexp) +{ + u32 ctrl; + u32 val; + int res; + + res = yt921x_fdb_in01(priv, addr, vid, 0); + if (res) + return res; + + ctrl = 0; + res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl); + if (res) + return res; + + ctrl = YT921X_FDB_OP_OP_GET_ONE | YT921X_FDB_OP_START; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + + res = yt921x_fdb_wait(priv, &val); + if (res) + return res; + if (val & YT921X_FDB_RESULT_NOTFOUND) { + *indexp = YT921X_FDB_NUM; + return 0; + } + + *indexp = FIELD_GET(YT921X_FDB_RESULT_INDEX_M, val); + return 0; +} + +static int +yt921x_fdb_read(struct yt921x_priv *priv, unsigned char *addr, u16 *vidp, + u16 *ports_maskp, u16 *indexp, u8 *statusp) +{ + struct device *dev = to_device(priv); + u16 index; + u32 data0; + u32 data1; + u32 data2; + u32 val; + int res; + + res = yt921x_fdb_wait(priv, &val); + if (res) + return res; + if (val & YT921X_FDB_RESULT_NOTFOUND) { + *ports_maskp = 0; + return 0; + } + index = FIELD_GET(YT921X_FDB_RESULT_INDEX_M, val); + + res = yt921x_reg_read(priv, YT921X_FDB_OUT1, &data1); + if (res) + return res; + if ((data1 & YT921X_FDB_IO1_STATUS_M) == + YT921X_FDB_IO1_STATUS_INVALID) { + *ports_maskp = 0; + return 0; + } + + res = yt921x_reg_read(priv, YT921X_FDB_OUT0, &data0); + if (res) + return res; + res = yt921x_reg_read(priv, YT921X_FDB_OUT2, &data2); + if (res) + return res; + + addr[0] = data0 >> 24; + addr[1] = data0 >> 16; + addr[2] = data0 >> 8; + addr[3] = data0; + addr[4] = data1 >> 8; + addr[5] = data1; + *vidp = FIELD_GET(YT921X_FDB_IO1_FID_M, data1); + *indexp = index; + *ports_maskp = FIELD_GET(YT921X_FDB_IO2_EGR_PORTS_M, data2); + *statusp = FIELD_GET(YT921X_FDB_IO1_STATUS_M, data1); + + dev_dbg(dev, + "%s: index 0x%x, mac %02x:%02x:%02x:%02x:%02x:%02x, vid %d, ports 0x%x, status %d\n", + __func__, *indexp, addr[0], addr[1], addr[2], addr[3], + addr[4], addr[5], *vidp, *ports_maskp, *statusp); + return 0; +} + +static int +yt921x_fdb_dump(struct yt921x_priv *priv, u16 ports_mask, + dsa_fdb_dump_cb_t *cb, void *data) +{ + unsigned char addr[ETH_ALEN]; + u8 status; + u16 pmask; + u16 index; + u32 ctrl; + u16 vid; + int res; + + ctrl = YT921X_FDB_OP_INDEX(0) | YT921X_FDB_OP_MODE_INDEX | + YT921X_FDB_OP_OP_GET_ONE | YT921X_FDB_OP_START; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + res = yt921x_fdb_read(priv, addr, &vid, &pmask, &index, &status); + if (res) + return res; + if ((pmask & ports_mask) && !is_multicast_ether_addr(addr)) { + res = cb(addr, vid, + status == YT921X_FDB_ENTRY_STATUS_STATIC, data); + if (res) + return res; + } + + ctrl = YT921X_FDB_IO2_EGR_PORTS(ports_mask); + res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl); + if (res) + return res; + + index = 0; + do { + ctrl = YT921X_FDB_OP_INDEX(index) | YT921X_FDB_OP_MODE_INDEX | + YT921X_FDB_OP_NEXT_TYPE_UCAST_PORT | + YT921X_FDB_OP_OP_GET_NEXT | YT921X_FDB_OP_START; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + + res = yt921x_fdb_read(priv, addr, &vid, &pmask, &index, + &status); + if (res) + return res; + if (!pmask) + break; + + if ((pmask & ports_mask) && !is_multicast_ether_addr(addr)) { + res = cb(addr, vid, + status == YT921X_FDB_ENTRY_STATUS_STATIC, + data); + if (res) + return res; + } + + /* Never call GET_NEXT with 4095, otherwise it will hang + * forever until a reset! + */ + } while (index < YT921X_FDB_NUM - 1); + + return 0; +} + +static int +yt921x_fdb_flush_raw(struct yt921x_priv *priv, u16 ports_mask, u16 vid, + bool flush_static) +{ + u32 ctrl; + u32 val; + int res; + + if (vid < 4096) { + ctrl = YT921X_FDB_IO1_FID(vid); + res = yt921x_reg_write(priv, YT921X_FDB_IN1, ctrl); + if (res) + return res; + } + + ctrl = YT921X_FDB_IO2_EGR_PORTS(ports_mask); + res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl); + if (res) + return res; + + ctrl = YT921X_FDB_OP_OP_FLUSH | YT921X_FDB_OP_START; + if (vid >= 4096) + ctrl |= YT921X_FDB_OP_FLUSH_PORT; + else + ctrl |= YT921X_FDB_OP_FLUSH_PORT_VID; + if (flush_static) + ctrl |= YT921X_FDB_OP_FLUSH_STATIC; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + + res = yt921x_fdb_wait(priv, &val); + if (res) + return res; + + return 0; +} + +static int +yt921x_fdb_flush_port(struct yt921x_priv *priv, int port, bool flush_static) +{ + return yt921x_fdb_flush_raw(priv, BIT(port), 4096, flush_static); +} + +static int +yt921x_fdb_add_index_in12(struct yt921x_priv *priv, u16 index, u16 ctrl1, + u16 ctrl2) +{ + u32 ctrl; + u32 val; + int res; + + res = yt921x_reg_write(priv, YT921X_FDB_IN1, ctrl1); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl2); + if (res) + return res; + + ctrl = YT921X_FDB_OP_INDEX(index) | YT921X_FDB_OP_MODE_INDEX | + YT921X_FDB_OP_OP_ADD | YT921X_FDB_OP_START; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + + return yt921x_fdb_wait(priv, &val); +} + +static int +yt921x_fdb_add(struct yt921x_priv *priv, const unsigned char *addr, u16 vid, + u16 ports_mask) +{ + u32 ctrl; + u32 val; + int res; + + ctrl = YT921X_FDB_IO1_STATUS_STATIC; + res = yt921x_fdb_in01(priv, addr, vid, ctrl); + if (res) + return res; + + ctrl = YT921X_FDB_IO2_EGR_PORTS(ports_mask); + res = yt921x_reg_write(priv, YT921X_FDB_IN2, ctrl); + if (res) + return res; + + ctrl = YT921X_FDB_OP_OP_ADD | YT921X_FDB_OP_START; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + + return yt921x_fdb_wait(priv, &val); +} + +static int +yt921x_fdb_leave(struct yt921x_priv *priv, const unsigned char *addr, + u16 vid, u16 ports_mask) +{ + u16 index; + u32 ctrl1; + u32 ctrl2; + u32 ctrl; + u32 val2; + u32 val; + int res; + + /* Check for presence */ + res = yt921x_fdb_has(priv, addr, vid, &index); + if (res) + return res; + if (index >= YT921X_FDB_NUM) + return 0; + + /* Check if action required */ + res = yt921x_reg_read(priv, YT921X_FDB_OUT2, &val2); + if (res) + return res; + + ctrl2 = val2 & ~YT921X_FDB_IO2_EGR_PORTS(ports_mask); + if (ctrl2 == val2) + return 0; + if (!(ctrl2 & YT921X_FDB_IO2_EGR_PORTS_M)) { + ctrl = YT921X_FDB_OP_OP_DEL | YT921X_FDB_OP_START; + res = yt921x_reg_write(priv, YT921X_FDB_OP, ctrl); + if (res) + return res; + + return yt921x_fdb_wait(priv, &val); + } + + res = yt921x_reg_read(priv, YT921X_FDB_OUT1, &ctrl1); + if (res) + return res; + + return yt921x_fdb_add_index_in12(priv, index, ctrl1, ctrl2); +} + +static int +yt921x_fdb_join(struct yt921x_priv *priv, const unsigned char *addr, u16 vid, + u16 ports_mask) +{ + u16 index; + u32 ctrl1; + u32 ctrl2; + u32 val1; + u32 val2; + int res; + + /* Check for presence */ + res = yt921x_fdb_has(priv, addr, vid, &index); + if (res) + return res; + if (index >= YT921X_FDB_NUM) + return yt921x_fdb_add(priv, addr, vid, ports_mask); + + /* Check if action required */ + res = yt921x_reg_read(priv, YT921X_FDB_OUT1, &val1); + if (res) + return res; + res = yt921x_reg_read(priv, YT921X_FDB_OUT2, &val2); + if (res) + return res; + + ctrl1 = val1 & ~YT921X_FDB_IO1_STATUS_M; + ctrl1 |= YT921X_FDB_IO1_STATUS_STATIC; + ctrl2 = val2 | YT921X_FDB_IO2_EGR_PORTS(ports_mask); + if (ctrl1 == val1 && ctrl2 == val2) + return 0; + + return yt921x_fdb_add_index_in12(priv, index, ctrl1, ctrl2); +} + +static int +yt921x_dsa_port_fdb_dump(struct dsa_switch *ds, int port, + dsa_fdb_dump_cb_t *cb, void *data) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + mutex_lock(&priv->reg_lock); + /* Hardware FDB is shared for fdb and mdb, "bridge fdb show" + * only wants to see unicast + */ + res = yt921x_fdb_dump(priv, BIT(port), cb, data); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static void yt921x_dsa_port_fast_age(struct dsa_switch *ds, int port) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct device *dev = to_device(priv); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_fdb_flush_port(priv, port, false); + mutex_unlock(&priv->reg_lock); + + if (res) + dev_err(dev, "Failed to %s port %d: %i\n", "clear FDB for", + port, res); +} + +static int +yt921x_dsa_set_ageing_time(struct dsa_switch *ds, unsigned int msecs) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + u32 ctrl; + int res; + + /* AGEING reg is set in 5s step */ + ctrl = clamp(msecs / 5000, 1, U16_MAX); + + mutex_lock(&priv->reg_lock); + res = yt921x_reg_write(priv, YT921X_AGEING, ctrl); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_fdb_del(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, struct dsa_db db) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_fdb_leave(priv, addr, vid, BIT(port)); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_fdb_add(struct dsa_switch *ds, int port, + const unsigned char *addr, u16 vid, struct dsa_db db) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_fdb_join(priv, addr, vid, BIT(port)); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_mdb_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + const unsigned char *addr = mdb->addr; + u16 vid = mdb->vid; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_fdb_leave(priv, addr, vid, BIT(port)); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_mdb_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_mdb *mdb, + struct dsa_db db) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + const unsigned char *addr = mdb->addr; + u16 vid = mdb->vid; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_fdb_join(priv, addr, vid, BIT(port)); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_port_set_pvid(struct yt921x_priv *priv, int port, u16 vid) +{ + u32 mask; + u32 ctrl; + + mask = YT921X_PORT_VLAN_CTRL_CVID_M; + ctrl = YT921X_PORT_VLAN_CTRL_CVID(vid); + return yt921x_reg_update_bits(priv, YT921X_PORTn_VLAN_CTRL(port), + mask, ctrl); +} + +static int +yt921x_vlan_filtering(struct yt921x_priv *priv, int port, bool vlan_filtering) +{ + struct dsa_port *dp = dsa_to_port(&priv->ds, port); + struct net_device *bdev; + u16 pvid; + u32 mask; + u32 ctrl; + int res; + + bdev = dsa_port_bridge_dev_get(dp); + + if (!bdev || !vlan_filtering) + pvid = YT921X_VID_UNWARE; + else + br_vlan_get_pvid(bdev, &pvid); + res = yt921x_port_set_pvid(priv, port, pvid); + if (res) + return res; + + mask = YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_TAGGED | + YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED; + ctrl = 0; + /* Do not drop tagged frames here; let VLAN_IGR_FILTER do it */ + if (vlan_filtering && !pvid) + ctrl |= YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED; + res = yt921x_reg_update_bits(priv, YT921X_PORTn_VLAN_CTRL1(port), + mask, ctrl); + if (res) + return res; + + res = yt921x_reg_toggle_bits(priv, YT921X_VLAN_IGR_FILTER, + YT921X_VLAN_IGR_FILTER_PORTn(port), + vlan_filtering); + if (res) + return res; + + /* Turn on / off VLAN awareness */ + mask = YT921X_PORT_IGR_TPIDn_CTAG_M; + if (!vlan_filtering) + ctrl = 0; + else + ctrl = YT921X_PORT_IGR_TPIDn_CTAG(0); + res = yt921x_reg_update_bits(priv, YT921X_PORTn_IGR_TPID(port), + mask, ctrl); + if (res) + return res; + + return 0; +} + +static int +yt921x_vlan_del(struct yt921x_priv *priv, int port, u16 vid) +{ + u64 mask64; + + mask64 = YT921X_VLAN_CTRL_PORTS(port) | + YT921X_VLAN_CTRL_UNTAG_PORTn(port); + + return yt921x_reg64_clear_bits(priv, YT921X_VLANn_CTRL(vid), mask64); +} + +static int +yt921x_vlan_add(struct yt921x_priv *priv, int port, u16 vid, bool untagged) +{ + u64 mask64; + u64 ctrl64; + + mask64 = YT921X_VLAN_CTRL_PORTn(port) | + YT921X_VLAN_CTRL_PORTS(priv->cpu_ports_mask); + ctrl64 = mask64; + + mask64 |= YT921X_VLAN_CTRL_UNTAG_PORTn(port); + if (untagged) + ctrl64 |= YT921X_VLAN_CTRL_UNTAG_PORTn(port); + + return yt921x_reg64_update_bits(priv, YT921X_VLANn_CTRL(vid), + mask64, ctrl64); +} + +static int +yt921x_pvid_clear(struct yt921x_priv *priv, int port) +{ + struct dsa_port *dp = dsa_to_port(&priv->ds, port); + bool vlan_filtering; + u32 mask; + int res; + + vlan_filtering = dsa_port_is_vlan_filtering(dp); + + res = yt921x_port_set_pvid(priv, port, + vlan_filtering ? 0 : YT921X_VID_UNWARE); + if (res) + return res; + + if (vlan_filtering) { + mask = YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED; + res = yt921x_reg_set_bits(priv, YT921X_PORTn_VLAN_CTRL1(port), + mask); + if (res) + return res; + } + + return 0; +} + +static int +yt921x_pvid_set(struct yt921x_priv *priv, int port, u16 vid) +{ + struct dsa_port *dp = dsa_to_port(&priv->ds, port); + bool vlan_filtering; + u32 mask; + int res; + + vlan_filtering = dsa_port_is_vlan_filtering(dp); + + if (vlan_filtering) { + res = yt921x_port_set_pvid(priv, port, vid); + if (res) + return res; + } + + mask = YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED; + res = yt921x_reg_clear_bits(priv, YT921X_PORTn_VLAN_CTRL1(port), mask); + if (res) + return res; + + return 0; +} + +static int +yt921x_dsa_port_vlan_filtering(struct dsa_switch *ds, int port, + bool vlan_filtering, + struct netlink_ext_ack *extack) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + if (dsa_is_cpu_port(ds, port)) + return 0; + + mutex_lock(&priv->reg_lock); + res = yt921x_vlan_filtering(priv, port, vlan_filtering); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_vlan_del(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + u16 vid = vlan->vid; + u16 pvid; + int res; + + if (dsa_is_cpu_port(ds, port)) + return 0; + + mutex_lock(&priv->reg_lock); + do { + struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *bdev; + + res = yt921x_vlan_del(priv, port, vid); + if (res) + break; + + bdev = dsa_port_bridge_dev_get(dp); + if (bdev) { + br_vlan_get_pvid(bdev, &pvid); + if (pvid == vid) + res = yt921x_pvid_clear(priv, port); + } + } while (0); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int +yt921x_dsa_port_vlan_add(struct dsa_switch *ds, int port, + const struct switchdev_obj_port_vlan *vlan, + struct netlink_ext_ack *extack) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + u16 vid = vlan->vid; + u16 pvid; + int res; + + /* CPU port is supposed to be a member of every VLAN; see + * yt921x_vlan_add() and yt921x_port_setup() + */ + if (dsa_is_cpu_port(ds, port)) + return 0; + + mutex_lock(&priv->reg_lock); + do { + struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *bdev; + + res = yt921x_vlan_add(priv, port, vid, + vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED); + if (res) + break; + + bdev = dsa_port_bridge_dev_get(dp); + if (bdev) { + if (vlan->flags & BRIDGE_VLAN_INFO_PVID) { + res = yt921x_pvid_set(priv, port, vid); + } else { + br_vlan_get_pvid(bdev, &pvid); + if (pvid == vid) + res = yt921x_pvid_clear(priv, port); + } + } + } while (0); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int yt921x_userport_standalone(struct yt921x_priv *priv, int port) +{ + u32 mask; + u32 ctrl; + int res; + + ctrl = ~priv->cpu_ports_mask; + res = yt921x_reg_write(priv, YT921X_PORTn_ISOLATION(port), ctrl); + if (res) + return res; + + /* Turn off FDB learning to prevent FDB pollution */ + mask = YT921X_PORT_LEARN_DIS; + res = yt921x_reg_set_bits(priv, YT921X_PORTn_LEARN(port), mask); + if (res) + return res; + + /* Turn off VLAN awareness */ + mask = YT921X_PORT_IGR_TPIDn_CTAG_M; + res = yt921x_reg_clear_bits(priv, YT921X_PORTn_IGR_TPID(port), mask); + if (res) + return res; + + /* Unrelated since learning is off and all packets are trapped; + * set it anyway + */ + res = yt921x_port_set_pvid(priv, port, YT921X_VID_UNWARE); + if (res) + return res; + + return 0; +} + +static int yt921x_userport_bridge(struct yt921x_priv *priv, int port) +{ + u32 mask; + int res; + + mask = YT921X_PORT_LEARN_DIS; + res = yt921x_reg_clear_bits(priv, YT921X_PORTn_LEARN(port), mask); + if (res) + return res; + + return 0; +} + +static int yt921x_isolate(struct yt921x_priv *priv, int port) +{ + u32 mask; + int res; + + mask = BIT(port); + for (int i = 0; i < YT921X_PORT_NUM; i++) { + if ((BIT(i) & priv->cpu_ports_mask) || i == port) + continue; + + res = yt921x_reg_set_bits(priv, YT921X_PORTn_ISOLATION(i), + mask); + if (res) + return res; + } + + return 0; +} + +/* Make sure to include the CPU port in ports_mask, or your bridge will + * not have it. + */ +static int yt921x_bridge(struct yt921x_priv *priv, u16 ports_mask) +{ + unsigned long targets_mask = ports_mask & ~priv->cpu_ports_mask; + u32 isolated_mask; + u32 ctrl; + int port; + int res; + + isolated_mask = 0; + for_each_set_bit(port, &targets_mask, YT921X_PORT_NUM) { + struct yt921x_port *pp = &priv->ports[port]; + + if (pp->isolated) + isolated_mask |= BIT(port); + } + + /* Block from non-cpu bridge ports ... */ + for_each_set_bit(port, &targets_mask, YT921X_PORT_NUM) { + struct yt921x_port *pp = &priv->ports[port]; + + /* to non-bridge ports */ + ctrl = ~ports_mask; + /* to isolated ports when isolated */ + if (pp->isolated) + ctrl |= isolated_mask; + /* to itself when non-hairpin */ + if (!pp->hairpin) + ctrl |= BIT(port); + else + ctrl &= ~BIT(port); + + res = yt921x_reg_write(priv, YT921X_PORTn_ISOLATION(port), + ctrl); + if (res) + return res; + } + + return 0; +} + +static int yt921x_bridge_leave(struct yt921x_priv *priv, int port) +{ + int res; + + res = yt921x_userport_standalone(priv, port); + if (res) + return res; + + res = yt921x_isolate(priv, port); + if (res) + return res; + + return 0; +} + +static int +yt921x_bridge_join(struct yt921x_priv *priv, int port, u16 ports_mask) +{ + int res; + + res = yt921x_userport_bridge(priv, port); + if (res) + return res; + + res = yt921x_bridge(priv, ports_mask); + if (res) + return res; + + return 0; +} + +static u32 +dsa_bridge_ports(struct dsa_switch *ds, const struct net_device *bdev) +{ + struct dsa_port *dp; + u32 mask = 0; + + dsa_switch_for_each_user_port(dp, ds) + if (dsa_port_offloads_bridge_dev(dp, bdev)) + mask |= BIT(dp->index); + + return mask; +} + +static int +yt921x_bridge_flags(struct yt921x_priv *priv, int port, + struct switchdev_brport_flags flags) +{ + struct yt921x_port *pp = &priv->ports[port]; + bool do_flush; + u32 mask; + int res; + + if (flags.mask & BR_LEARNING) { + bool learning = flags.val & BR_LEARNING; + + mask = YT921X_PORT_LEARN_DIS; + res = yt921x_reg_toggle_bits(priv, YT921X_PORTn_LEARN(port), + mask, !learning); + if (res) + return res; + } + + /* BR_FLOOD, BR_MCAST_FLOOD: see the comment where ACT_UNK_ACTn_TRAP + * is set + */ + + /* BR_BCAST_FLOOD: we can filter bcast, but cannot trap them */ + + do_flush = false; + if (flags.mask & BR_HAIRPIN_MODE) { + pp->hairpin = flags.val & BR_HAIRPIN_MODE; + do_flush = true; + } + if (flags.mask & BR_ISOLATED) { + pp->isolated = flags.val & BR_ISOLATED; + do_flush = true; + } + if (do_flush) { + struct dsa_switch *ds = &priv->ds; + struct dsa_port *dp = dsa_to_port(ds, port); + struct net_device *bdev; + + bdev = dsa_port_bridge_dev_get(dp); + if (bdev) { + u32 ports_mask; + + ports_mask = dsa_bridge_ports(ds, bdev); + ports_mask |= priv->cpu_ports_mask; + res = yt921x_bridge(priv, ports_mask); + if (res) + return res; + } + } + + return 0; +} + +static int +yt921x_dsa_port_pre_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + if (flags.mask & ~(BR_HAIRPIN_MODE | BR_LEARNING | BR_FLOOD | + BR_MCAST_FLOOD | BR_ISOLATED)) + return -EINVAL; + return 0; +} + +static int +yt921x_dsa_port_bridge_flags(struct dsa_switch *ds, int port, + struct switchdev_brport_flags flags, + struct netlink_ext_ack *extack) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + if (dsa_is_cpu_port(ds, port)) + return 0; + + mutex_lock(&priv->reg_lock); + res = yt921x_bridge_flags(priv, port, flags); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static void +yt921x_dsa_port_bridge_leave(struct dsa_switch *ds, int port, + struct dsa_bridge bridge) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct device *dev = to_device(priv); + int res; + + if (dsa_is_cpu_port(ds, port)) + return; + + mutex_lock(&priv->reg_lock); + res = yt921x_bridge_leave(priv, port); + mutex_unlock(&priv->reg_lock); + + if (res) + dev_err(dev, "Failed to %s port %d: %i\n", "unbridge", + port, res); +} + +static int +yt921x_dsa_port_bridge_join(struct dsa_switch *ds, int port, + struct dsa_bridge bridge, bool *tx_fwd_offload, + struct netlink_ext_ack *extack) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + u16 ports_mask; + int res; + + if (dsa_is_cpu_port(ds, port)) + return 0; + + ports_mask = dsa_bridge_ports(ds, bridge.dev); + ports_mask |= priv->cpu_ports_mask; + + mutex_lock(&priv->reg_lock); + res = yt921x_bridge_join(priv, port, ports_mask); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int yt921x_port_down(struct yt921x_priv *priv, int port) +{ + u32 mask; + int res; + + mask = YT921X_PORT_LINK | YT921X_PORT_RX_MAC_EN | YT921X_PORT_TX_MAC_EN; + res = yt921x_reg_clear_bits(priv, YT921X_PORTn_CTRL(port), mask); + if (res) + return res; + + if (yt921x_port_is_external(port)) { + mask = YT921X_SERDES_LINK; + res = yt921x_reg_clear_bits(priv, YT921X_SERDESn(port), mask); + if (res) + return res; + + mask = YT921X_XMII_LINK; + res = yt921x_reg_clear_bits(priv, YT921X_XMIIn(port), mask); + if (res) + return res; + } + + return 0; +} + +static int +yt921x_port_up(struct yt921x_priv *priv, int port, unsigned int mode, + phy_interface_t interface, int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + u32 mask; + u32 ctrl; + int res; + + switch (speed) { + case SPEED_10: + ctrl = YT921X_PORT_SPEED_10; + break; + case SPEED_100: + ctrl = YT921X_PORT_SPEED_100; + break; + case SPEED_1000: + ctrl = YT921X_PORT_SPEED_1000; + break; + case SPEED_2500: + ctrl = YT921X_PORT_SPEED_2500; + break; + case SPEED_10000: + ctrl = YT921X_PORT_SPEED_10000; + break; + default: + return -EINVAL; + } + if (duplex == DUPLEX_FULL) + ctrl |= YT921X_PORT_DUPLEX_FULL; + if (tx_pause) + ctrl |= YT921X_PORT_TX_PAUSE; + if (rx_pause) + ctrl |= YT921X_PORT_RX_PAUSE; + ctrl |= YT921X_PORT_RX_MAC_EN | YT921X_PORT_TX_MAC_EN; + res = yt921x_reg_write(priv, YT921X_PORTn_CTRL(port), ctrl); + if (res) + return res; + + if (yt921x_port_is_external(port)) { + mask = YT921X_SERDES_SPEED_M; + switch (speed) { + case SPEED_10: + ctrl = YT921X_SERDES_SPEED_10; + break; + case SPEED_100: + ctrl = YT921X_SERDES_SPEED_100; + break; + case SPEED_1000: + ctrl = YT921X_SERDES_SPEED_1000; + break; + case SPEED_2500: + ctrl = YT921X_SERDES_SPEED_2500; + break; + case SPEED_10000: + ctrl = YT921X_SERDES_SPEED_10000; + break; + default: + return -EINVAL; + } + mask |= YT921X_SERDES_DUPLEX_FULL; + if (duplex == DUPLEX_FULL) + ctrl |= YT921X_SERDES_DUPLEX_FULL; + mask |= YT921X_SERDES_TX_PAUSE; + if (tx_pause) + ctrl |= YT921X_SERDES_TX_PAUSE; + mask |= YT921X_SERDES_RX_PAUSE; + if (rx_pause) + ctrl |= YT921X_SERDES_RX_PAUSE; + mask |= YT921X_SERDES_LINK; + ctrl |= YT921X_SERDES_LINK; + res = yt921x_reg_update_bits(priv, YT921X_SERDESn(port), + mask, ctrl); + if (res) + return res; + + mask = YT921X_XMII_LINK; + res = yt921x_reg_set_bits(priv, YT921X_XMIIn(port), mask); + if (res) + return res; + + switch (speed) { + case SPEED_10: + ctrl = YT921X_MDIO_POLLING_SPEED_10; + break; + case SPEED_100: + ctrl = YT921X_MDIO_POLLING_SPEED_100; + break; + case SPEED_1000: + ctrl = YT921X_MDIO_POLLING_SPEED_1000; + break; + case SPEED_2500: + ctrl = YT921X_MDIO_POLLING_SPEED_2500; + break; + case SPEED_10000: + ctrl = YT921X_MDIO_POLLING_SPEED_10000; + break; + default: + return -EINVAL; + } + if (duplex == DUPLEX_FULL) + ctrl |= YT921X_MDIO_POLLING_DUPLEX_FULL; + ctrl |= YT921X_MDIO_POLLING_LINK; + res = yt921x_reg_write(priv, YT921X_MDIO_POLLINGn(port), ctrl); + if (res) + return res; + } + + return 0; +} + +static int +yt921x_port_config(struct yt921x_priv *priv, int port, unsigned int mode, + phy_interface_t interface) +{ + struct device *dev = to_device(priv); + u32 mask; + u32 ctrl; + int res; + + if (!yt921x_port_is_external(port)) { + if (interface != PHY_INTERFACE_MODE_INTERNAL) { + dev_err(dev, "Wrong mode %d on port %d\n", + interface, port); + return -EINVAL; + } + return 0; + } + + switch (interface) { + /* SERDES */ + case PHY_INTERFACE_MODE_SGMII: + case PHY_INTERFACE_MODE_100BASEX: + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + mask = YT921X_SERDES_CTRL_PORTn(port); + res = yt921x_reg_set_bits(priv, YT921X_SERDES_CTRL, mask); + if (res) + return res; + + mask = YT921X_XMII_CTRL_PORTn(port); + res = yt921x_reg_clear_bits(priv, YT921X_XMII_CTRL, mask); + if (res) + return res; + + mask = YT921X_SERDES_MODE_M; + switch (interface) { + case PHY_INTERFACE_MODE_SGMII: + ctrl = YT921X_SERDES_MODE_SGMII; + break; + case PHY_INTERFACE_MODE_100BASEX: + ctrl = YT921X_SERDES_MODE_100BASEX; + break; + case PHY_INTERFACE_MODE_1000BASEX: + ctrl = YT921X_SERDES_MODE_1000BASEX; + break; + case PHY_INTERFACE_MODE_2500BASEX: + ctrl = YT921X_SERDES_MODE_2500BASEX; + break; + default: + return -EINVAL; + } + res = yt921x_reg_update_bits(priv, YT921X_SERDESn(port), + mask, ctrl); + if (res) + return res; + + break; + /* add XMII support here */ + default: + return -EINVAL; + } + + return 0; +} + +static void +yt921x_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct yt921x_priv *priv = to_yt921x_priv(dp->ds); + int port = dp->index; + int res; + + /* No need to sync; port control block is hold until device remove */ + cancel_delayed_work(&priv->ports[port].mib_read); + + mutex_lock(&priv->reg_lock); + res = yt921x_port_down(priv, port); + mutex_unlock(&priv->reg_lock); + + if (res) + dev_err(dp->ds->dev, "Failed to %s port %d: %i\n", "bring down", + port, res); +} + +static void +yt921x_phylink_mac_link_up(struct phylink_config *config, + struct phy_device *phydev, unsigned int mode, + phy_interface_t interface, int speed, int duplex, + bool tx_pause, bool rx_pause) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct yt921x_priv *priv = to_yt921x_priv(dp->ds); + int port = dp->index; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_port_up(priv, port, mode, interface, speed, duplex, + tx_pause, rx_pause); + mutex_unlock(&priv->reg_lock); + + if (res) + dev_err(dp->ds->dev, "Failed to %s port %d: %i\n", "bring up", + port, res); + + schedule_delayed_work(&priv->ports[port].mib_read, 0); +} + +static void +yt921x_phylink_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_phylink_to_port(config); + struct yt921x_priv *priv = to_yt921x_priv(dp->ds); + int port = dp->index; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_port_config(priv, port, mode, state->interface); + mutex_unlock(&priv->reg_lock); + + if (res) + dev_err(dp->ds->dev, "Failed to %s port %d: %i\n", "config", + port, res); +} + +static void +yt921x_dsa_phylink_get_caps(struct dsa_switch *ds, int port, + struct phylink_config *config) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + const struct yt921x_info *info = priv->info; + + config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE | + MAC_10 | MAC_100 | MAC_1000; + + if (info->internal_mask & BIT(port)) { + /* Port 10 for MCU should probably go here too. But since that + * is untested yet, turn it down for the moment by letting it + * fall to the default branch. + */ + __set_bit(PHY_INTERFACE_MODE_INTERNAL, + config->supported_interfaces); + } else if (info->external_mask & BIT(port)) { + /* TODO: external ports may support SERDES only, XMII only, or + * SERDES + XMII depending on the chip. However, we can't get + * the accurate config table due to lack of document, thus + * we simply declare SERDES + XMII and rely on the correctness + * of devicetree for now. + */ + + /* SERDES */ + __set_bit(PHY_INTERFACE_MODE_SGMII, + config->supported_interfaces); + /* REVSGMII (SGMII in PHY role) should go here, once + * PHY_INTERFACE_MODE_REVSGMII is introduced. + */ + __set_bit(PHY_INTERFACE_MODE_100BASEX, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, + config->supported_interfaces); + __set_bit(PHY_INTERFACE_MODE_2500BASEX, + config->supported_interfaces); + config->mac_capabilities |= MAC_2500FD; + + /* XMII */ + + /* Not tested. To add support for XMII: + * - Add proper interface modes below + * - Handle them in yt921x_port_config() + */ + } + /* no such port: empty supported_interfaces causes phylink to turn it + * down + */ +} + +static int yt921x_port_setup(struct yt921x_priv *priv, int port) +{ + struct dsa_switch *ds = &priv->ds; + u32 ctrl; + int res; + + res = yt921x_userport_standalone(priv, port); + if (res) + return res; + + if (dsa_is_cpu_port(ds, port)) { + /* Egress of CPU port is supposed to be completely controlled + * via tagging, so set to oneway isolated (drop all packets + * without tag). + */ + ctrl = ~(u32)0; + res = yt921x_reg_write(priv, YT921X_PORTn_ISOLATION(port), + ctrl); + if (res) + return res; + + /* To simplify FDB "isolation" simulation, we also disable + * learning on the CPU port, and let software identify packets + * towarding CPU (either trapped or a static FDB entry is + * matched, no matter which bridge that entry is for), which is + * already done by yt921x_userport_standalone(). As a result, + * VLAN-awareness becomes unrelated on the CPU port (set to + * VLAN-unaware by the way). + */ + } + + return 0; +} + +static enum dsa_tag_protocol +yt921x_dsa_get_tag_protocol(struct dsa_switch *ds, int port, + enum dsa_tag_protocol m) +{ + return DSA_TAG_PROTO_YT921X; +} + +static int yt921x_dsa_port_setup(struct dsa_switch *ds, int port) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_port_setup(priv, port); + mutex_unlock(&priv->reg_lock); + + return res; +} + +static int yt921x_edata_wait(struct yt921x_priv *priv, u32 *valp) +{ + u32 val = YT921X_EDATA_DATA_IDLE; + int res; + + res = yt921x_reg_wait(priv, YT921X_EDATA_DATA, + YT921X_EDATA_DATA_STATUS_M, &val); + if (res) + return res; + + *valp = val; + return 0; +} + +static int +yt921x_edata_read_cont(struct yt921x_priv *priv, u8 addr, u8 *valp) +{ + u32 ctrl; + u32 val; + int res; + + ctrl = YT921X_EDATA_CTRL_ADDR(addr) | YT921X_EDATA_CTRL_READ; + res = yt921x_reg_write(priv, YT921X_EDATA_CTRL, ctrl); + if (res) + return res; + res = yt921x_edata_wait(priv, &val); + if (res) + return res; + + *valp = FIELD_GET(YT921X_EDATA_DATA_DATA_M, val); + return 0; +} + +static int yt921x_edata_read(struct yt921x_priv *priv, u8 addr, u8 *valp) +{ + u32 val; + int res; + + res = yt921x_edata_wait(priv, &val); + if (res) + return res; + return yt921x_edata_read_cont(priv, addr, valp); +} + +static int yt921x_chip_detect(struct yt921x_priv *priv) +{ + struct device *dev = to_device(priv); + const struct yt921x_info *info; + u8 extmode; + u32 chipid; + u32 major; + u32 mode; + int res; + + res = yt921x_reg_read(priv, YT921X_CHIP_ID, &chipid); + if (res) + return res; + + major = FIELD_GET(YT921X_CHIP_ID_MAJOR, chipid); + + for (info = yt921x_infos; info->name; info++) + if (info->major == major) + break; + if (!info->name) { + dev_err(dev, "Unexpected chipid 0x%x\n", chipid); + return -ENODEV; + } + + res = yt921x_reg_read(priv, YT921X_CHIP_MODE, &mode); + if (res) + return res; + res = yt921x_edata_read(priv, YT921X_EDATA_EXTMODE, &extmode); + if (res) + return res; + + for (; info->name; info++) + if (info->major == major && info->mode == mode && + info->extmode == extmode) + break; + if (!info->name) { + dev_err(dev, + "Unsupported chipid 0x%x with chipmode 0x%x 0x%x\n", + chipid, mode, extmode); + return -ENODEV; + } + + /* Print chipid here since we are interested in lower 16 bits */ + dev_info(dev, + "Motorcomm %s ethernet switch, chipid: 0x%x, chipmode: 0x%x 0x%x\n", + info->name, chipid, mode, extmode); + + priv->info = info; + return 0; +} + +static int yt921x_chip_reset(struct yt921x_priv *priv) +{ + struct device *dev = to_device(priv); + u16 eth_p_tag; + u32 val; + int res; + + res = yt921x_chip_detect(priv); + if (res) + return res; + + /* Reset */ + res = yt921x_reg_write(priv, YT921X_RST, YT921X_RST_HW); + if (res) + return res; + + /* RST_HW is almost same as GPIO hard reset, so we need this delay. */ + fsleep(YT921X_RST_DELAY_US); + + val = 0; + res = yt921x_reg_wait(priv, YT921X_RST, ~0, &val); + if (res) + return res; + + /* Check for tag EtherType; do it after reset in case you messed it up + * before. + */ + res = yt921x_reg_read(priv, YT921X_CPU_TAG_TPID, &val); + if (res) + return res; + eth_p_tag = FIELD_GET(YT921X_CPU_TAG_TPID_TPID_M, val); + if (eth_p_tag != ETH_P_YT921X) { + dev_err(dev, "Tag type 0x%x != 0x%x\n", eth_p_tag, + ETH_P_YT921X); + /* Despite being possible, we choose not to set CPU_TAG_TPID, + * since there is no way it can be different unless you have the + * wrong chip. + */ + return -EINVAL; + } + + return 0; +} + +static int yt921x_chip_setup(struct yt921x_priv *priv) +{ + struct dsa_switch *ds = &priv->ds; + unsigned long cpu_ports_mask; + u64 ctrl64; + u32 ctrl; + int port; + int res; + + /* Enable DSA */ + priv->cpu_ports_mask = dsa_cpu_ports(ds); + + ctrl = YT921X_EXT_CPU_PORT_TAG_EN | YT921X_EXT_CPU_PORT_PORT_EN | + YT921X_EXT_CPU_PORT_PORT(__ffs(priv->cpu_ports_mask)); + res = yt921x_reg_write(priv, YT921X_EXT_CPU_PORT, ctrl); + if (res) + return res; + + /* Enable and clear MIB */ + res = yt921x_reg_set_bits(priv, YT921X_FUNC, YT921X_FUNC_MIB); + if (res) + return res; + + ctrl = YT921X_MIB_CTRL_CLEAN | YT921X_MIB_CTRL_ALL_PORT; + res = yt921x_reg_write(priv, YT921X_MIB_CTRL, ctrl); + if (res) + return res; + + /* Setup software switch */ + ctrl = YT921X_CPU_COPY_TO_EXT_CPU; + res = yt921x_reg_write(priv, YT921X_CPU_COPY, ctrl); + if (res) + return res; + + ctrl = GENMASK(10, 0); + res = yt921x_reg_write(priv, YT921X_FILTER_UNK_UCAST, ctrl); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_FILTER_UNK_MCAST, ctrl); + if (res) + return res; + + /* YT921x does not support native DSA port bridging, so we use port + * isolation to emulate it. However, be especially careful that port + * isolation takes _after_ FDB lookups, i.e. if an FDB entry (from + * another bridge) is matched and the destination port (in another + * bridge) is blocked, the packet will be dropped instead of flooding to + * the "bridged" ports, thus we need to trap and handle those packets by + * software. + * + * If there is no more than one bridge, we might be able to drop them + * directly given some conditions are met, but we trap them in all cases + * for now. + */ + ctrl = 0; + for (int i = 0; i < YT921X_PORT_NUM; i++) + ctrl |= YT921X_ACT_UNK_ACTn_TRAP(i); + /* Except for CPU ports, if any packets are sent via CPU ports without + * tag, they should be dropped. + */ + cpu_ports_mask = priv->cpu_ports_mask; + for_each_set_bit(port, &cpu_ports_mask, YT921X_PORT_NUM) { + ctrl &= ~YT921X_ACT_UNK_ACTn_M(port); + ctrl |= YT921X_ACT_UNK_ACTn_DROP(port); + } + res = yt921x_reg_write(priv, YT921X_ACT_UNK_UCAST, ctrl); + if (res) + return res; + res = yt921x_reg_write(priv, YT921X_ACT_UNK_MCAST, ctrl); + if (res) + return res; + + /* Tagged VID 0 should be treated as untagged, which confuses the + * hardware a lot + */ + ctrl64 = YT921X_VLAN_CTRL_LEARN_DIS | YT921X_VLAN_CTRL_PORTS_M; + res = yt921x_reg64_write(priv, YT921X_VLANn_CTRL(0), ctrl64); + if (res) + return res; + + /* Miscellaneous */ + res = yt921x_reg_set_bits(priv, YT921X_SENSOR, YT921X_SENSOR_TEMP); + if (res) + return res; + + return 0; +} + +static int yt921x_dsa_setup(struct dsa_switch *ds) +{ + struct yt921x_priv *priv = to_yt921x_priv(ds); + struct device *dev = to_device(priv); + struct device_node *np = dev->of_node; + struct device_node *child; + int res; + + mutex_lock(&priv->reg_lock); + res = yt921x_chip_reset(priv); + mutex_unlock(&priv->reg_lock); + + if (res) + return res; + + /* Register the internal mdio bus. Nodes for internal ports should have + * proper phy-handle pointing to their PHYs. Not enabling the internal + * bus is possible, though pretty wired, if internal ports are not used. + */ + child = of_get_child_by_name(np, "mdio"); + if (child) { + res = yt921x_mbus_int_init(priv, child); + of_node_put(child); + if (res) + return res; + } + + /* External mdio bus is optional */ + child = of_get_child_by_name(np, "mdio-external"); + if (child) { + res = yt921x_mbus_ext_init(priv, child); + of_node_put(child); + if (res) + return res; + + dev_err(dev, "Untested external mdio bus\n"); + return -ENODEV; + } + + mutex_lock(&priv->reg_lock); + res = yt921x_chip_setup(priv); + mutex_unlock(&priv->reg_lock); + + if (res) + return res; + + return 0; +} + +static const struct phylink_mac_ops yt921x_phylink_mac_ops = { + .mac_link_down = yt921x_phylink_mac_link_down, + .mac_link_up = yt921x_phylink_mac_link_up, + .mac_config = yt921x_phylink_mac_config, +}; + +static const struct dsa_switch_ops yt921x_dsa_switch_ops = { + /* mib */ + .get_strings = yt921x_dsa_get_strings, + .get_ethtool_stats = yt921x_dsa_get_ethtool_stats, + .get_sset_count = yt921x_dsa_get_sset_count, + .get_eth_mac_stats = yt921x_dsa_get_eth_mac_stats, + .get_eth_ctrl_stats = yt921x_dsa_get_eth_ctrl_stats, + .get_rmon_stats = yt921x_dsa_get_rmon_stats, + .get_stats64 = yt921x_dsa_get_stats64, + .get_pause_stats = yt921x_dsa_get_pause_stats, + /* eee */ + .support_eee = dsa_supports_eee, + .set_mac_eee = yt921x_dsa_set_mac_eee, + /* mtu */ + .port_change_mtu = yt921x_dsa_port_change_mtu, + .port_max_mtu = yt921x_dsa_port_max_mtu, + /* mirror */ + .port_mirror_del = yt921x_dsa_port_mirror_del, + .port_mirror_add = yt921x_dsa_port_mirror_add, + /* fdb */ + .port_fdb_dump = yt921x_dsa_port_fdb_dump, + .port_fast_age = yt921x_dsa_port_fast_age, + .set_ageing_time = yt921x_dsa_set_ageing_time, + .port_fdb_del = yt921x_dsa_port_fdb_del, + .port_fdb_add = yt921x_dsa_port_fdb_add, + .port_mdb_del = yt921x_dsa_port_mdb_del, + .port_mdb_add = yt921x_dsa_port_mdb_add, + /* vlan */ + .port_vlan_filtering = yt921x_dsa_port_vlan_filtering, + .port_vlan_del = yt921x_dsa_port_vlan_del, + .port_vlan_add = yt921x_dsa_port_vlan_add, + /* bridge */ + .port_pre_bridge_flags = yt921x_dsa_port_pre_bridge_flags, + .port_bridge_flags = yt921x_dsa_port_bridge_flags, + .port_bridge_leave = yt921x_dsa_port_bridge_leave, + .port_bridge_join = yt921x_dsa_port_bridge_join, + /* port */ + .get_tag_protocol = yt921x_dsa_get_tag_protocol, + .phylink_get_caps = yt921x_dsa_phylink_get_caps, + .port_setup = yt921x_dsa_port_setup, + /* chip */ + .setup = yt921x_dsa_setup, +}; + +static void yt921x_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct yt921x_priv *priv = mdiodev_get_drvdata(mdiodev); + + if (!priv) + return; + + dsa_switch_shutdown(&priv->ds); +} + +static void yt921x_mdio_remove(struct mdio_device *mdiodev) +{ + struct yt921x_priv *priv = mdiodev_get_drvdata(mdiodev); + + if (!priv) + return; + + for (size_t i = ARRAY_SIZE(priv->ports); i-- > 0; ) { + struct yt921x_port *pp = &priv->ports[i]; + + disable_delayed_work_sync(&pp->mib_read); + } + + dsa_unregister_switch(&priv->ds); + + mutex_destroy(&priv->reg_lock); +} + +static int yt921x_mdio_probe(struct mdio_device *mdiodev) +{ + struct device *dev = &mdiodev->dev; + struct yt921x_reg_mdio *mdio; + struct yt921x_priv *priv; + struct dsa_switch *ds; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + mdio = devm_kzalloc(dev, sizeof(*mdio), GFP_KERNEL); + if (!mdio) + return -ENOMEM; + + mdio->bus = mdiodev->bus; + mdio->addr = mdiodev->addr; + mdio->switchid = 0; + + mutex_init(&priv->reg_lock); + + priv->reg_ops = &yt921x_reg_ops_mdio; + priv->reg_ctx = mdio; + + for (size_t i = 0; i < ARRAY_SIZE(priv->ports); i++) { + struct yt921x_port *pp = &priv->ports[i]; + + pp->index = i; + INIT_DELAYED_WORK(&pp->mib_read, yt921x_poll_mib); + } + + ds = &priv->ds; + ds->dev = dev; + ds->assisted_learning_on_cpu_port = true; + ds->priv = priv; + ds->ops = &yt921x_dsa_switch_ops; + ds->phylink_mac_ops = &yt921x_phylink_mac_ops; + ds->num_ports = YT921X_PORT_NUM; + + mdiodev_set_drvdata(mdiodev, priv); + + return dsa_register_switch(ds); +} + +static const struct of_device_id yt921x_of_match[] = { + { .compatible = "motorcomm,yt9215" }, + {} +}; +MODULE_DEVICE_TABLE(of, yt921x_of_match); + +static struct mdio_driver yt921x_mdio_driver = { + .probe = yt921x_mdio_probe, + .remove = yt921x_mdio_remove, + .shutdown = yt921x_mdio_shutdown, + .mdiodrv.driver = { + .name = YT921X_NAME, + .of_match_table = yt921x_of_match, + }, +}; + +mdio_module_driver(yt921x_mdio_driver); + +MODULE_AUTHOR("David Yang "); +MODULE_DESCRIPTION("Driver for Motorcomm YT921x Switch"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/dsa/yt921x.h b/drivers/net/dsa/yt921x.h new file mode 100644 index 0000000000000..3e85d90826fb5 --- /dev/null +++ b/drivers/net/dsa/yt921x.h @@ -0,0 +1,504 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2025 David Yang + */ + +#ifndef __YT921X_H +#define __YT921X_H + +#include + +#define YT921X_SMI_SWITCHID_M GENMASK(3, 2) +#define YT921X_SMI_SWITCHID(x) FIELD_PREP(YT921X_SMI_SWITCHID_M, (x)) +#define YT921X_SMI_AD BIT(1) +#define YT921X_SMI_ADDR 0 +#define YT921X_SMI_DATA YT921X_SMI_AD +#define YT921X_SMI_RW BIT(0) +#define YT921X_SMI_WRITE 0 +#define YT921X_SMI_READ YT921X_SMI_RW + +#define YT921X_SWITCHID_NUM 4 + +#define YT921X_RST 0x80000 +#define YT921X_RST_HW BIT(31) +#define YT921X_RST_SW BIT(1) +#define YT921X_FUNC 0x80004 +#define YT921X_FUNC_MIB BIT(1) +#define YT921X_CHIP_ID 0x80008 +#define YT921X_CHIP_ID_MAJOR GENMASK(31, 16) +#define YT921X_EXT_CPU_PORT 0x8000c +#define YT921X_EXT_CPU_PORT_TAG_EN BIT(15) +#define YT921X_EXT_CPU_PORT_PORT_EN BIT(14) +#define YT921X_EXT_CPU_PORT_PORT_M GENMASK(3, 0) +#define YT921X_EXT_CPU_PORT_PORT(x) FIELD_PREP(YT921X_EXT_CPU_PORT_PORT_M, (x)) +#define YT921X_CPU_TAG_TPID 0x80010 +#define YT921X_CPU_TAG_TPID_TPID_M GENMASK(15, 0) +/* Same as ETH_P_YT921X, but this represents the true HW default, while the + * former is a local convention chosen by us. + */ +#define YT921X_CPU_TAG_TPID_TPID_DEFAULT 0x9988 +#define YT921X_PVID_SEL 0x80014 +#define YT921X_PVID_SEL_SVID_PORTn(port) BIT(port) +#define YT921X_SERDES_CTRL 0x80028 +#define YT921X_SERDES_CTRL_PORTn_TEST(port) BIT((port) - 3) +#define YT921X_SERDES_CTRL_PORTn(port) BIT((port) - 8) +#define YT921X_IO_LEVEL 0x80030 +#define YT9215_IO_LEVEL_NORMAL_M GENMASK(5, 4) +#define YT9215_IO_LEVEL_NORMAL(x) FIELD_PREP(YT9215_IO_LEVEL_NORMAL_M, (x)) +#define YT9215_IO_LEVEL_NORMAL_3V3 YT9215_IO_LEVEL_NORMAL(0) +#define YT9215_IO_LEVEL_NORMAL_1V8 YT9215_IO_LEVEL_NORMAL(3) +#define YT9215_IO_LEVEL_RGMII1_M GENMASK(3, 2) +#define YT9215_IO_LEVEL_RGMII1(x) FIELD_PREP(YT9215_IO_LEVEL_RGMII1_M, (x)) +#define YT9215_IO_LEVEL_RGMII1_3V3 YT9215_IO_LEVEL_RGMII1(0) +#define YT9215_IO_LEVEL_RGMII1_2V5 YT9215_IO_LEVEL_RGMII1(1) +#define YT9215_IO_LEVEL_RGMII1_1V8 YT9215_IO_LEVEL_RGMII1(2) +#define YT9215_IO_LEVEL_RGMII0_M GENMASK(1, 0) +#define YT9215_IO_LEVEL_RGMII0(x) FIELD_PREP(YT9215_IO_LEVEL_RGMII0_M, (x)) +#define YT9215_IO_LEVEL_RGMII0_3V3 YT9215_IO_LEVEL_RGMII0(0) +#define YT9215_IO_LEVEL_RGMII0_2V5 YT9215_IO_LEVEL_RGMII0(1) +#define YT9215_IO_LEVEL_RGMII0_1V8 YT9215_IO_LEVEL_RGMII0(2) +#define YT9218_IO_LEVEL_RGMII1_M GENMASK(5, 4) +#define YT9218_IO_LEVEL_RGMII1(x) FIELD_PREP(YT9218_IO_LEVEL_RGMII1_M, (x)) +#define YT9218_IO_LEVEL_RGMII1_3V3 YT9218_IO_LEVEL_RGMII1(0) +#define YT9218_IO_LEVEL_RGMII1_2V5 YT9218_IO_LEVEL_RGMII1(1) +#define YT9218_IO_LEVEL_RGMII1_1V8 YT9218_IO_LEVEL_RGMII1(2) +#define YT9218_IO_LEVEL_RGMII0_M GENMASK(3, 2) +#define YT9218_IO_LEVEL_RGMII0(x) FIELD_PREP(YT9218_IO_LEVEL_RGMII0_M, (x)) +#define YT9218_IO_LEVEL_RGMII0_3V3 YT9218_IO_LEVEL_RGMII0(0) +#define YT9218_IO_LEVEL_RGMII0_2V5 YT9218_IO_LEVEL_RGMII0(1) +#define YT9218_IO_LEVEL_RGMII0_1V8 YT9218_IO_LEVEL_RGMII0(2) +#define YT9218_IO_LEVEL_NORMAL_M GENMASK(1, 0) +#define YT9218_IO_LEVEL_NORMAL(x) FIELD_PREP(YT9218_IO_LEVEL_NORMAL_M, (x)) +#define YT9218_IO_LEVEL_NORMAL_3V3 YT9218_IO_LEVEL_NORMAL(0) +#define YT9218_IO_LEVEL_NORMAL_1V8 YT9218_IO_LEVEL_NORMAL(3) +#define YT921X_MAC_ADDR_HI2 0x80080 +#define YT921X_MAC_ADDR_LO4 0x80084 +#define YT921X_SERDESn(port) (0x8008c + 4 * ((port) - 8)) +#define YT921X_SERDES_MODE_M GENMASK(9, 7) +#define YT921X_SERDES_MODE(x) FIELD_PREP(YT921X_SERDES_MODE_M, (x)) +#define YT921X_SERDES_MODE_SGMII YT921X_SERDES_MODE(0) +#define YT921X_SERDES_MODE_REVSGMII YT921X_SERDES_MODE(1) +#define YT921X_SERDES_MODE_1000BASEX YT921X_SERDES_MODE(2) +#define YT921X_SERDES_MODE_100BASEX YT921X_SERDES_MODE(3) +#define YT921X_SERDES_MODE_2500BASEX YT921X_SERDES_MODE(4) +#define YT921X_SERDES_RX_PAUSE BIT(6) +#define YT921X_SERDES_TX_PAUSE BIT(5) +#define YT921X_SERDES_LINK BIT(4) /* force link */ +#define YT921X_SERDES_DUPLEX_FULL BIT(3) +#define YT921X_SERDES_SPEED_M GENMASK(2, 0) +#define YT921X_SERDES_SPEED(x) FIELD_PREP(YT921X_SERDES_SPEED_M, (x)) +#define YT921X_SERDES_SPEED_10 YT921X_SERDES_SPEED(0) +#define YT921X_SERDES_SPEED_100 YT921X_SERDES_SPEED(1) +#define YT921X_SERDES_SPEED_1000 YT921X_SERDES_SPEED(2) +#define YT921X_SERDES_SPEED_10000 YT921X_SERDES_SPEED(3) +#define YT921X_SERDES_SPEED_2500 YT921X_SERDES_SPEED(4) +#define YT921X_PORTn_CTRL(port) (0x80100 + 4 * (port)) +#define YT921X_PORT_CTRL_PAUSE_AN BIT(10) +#define YT921X_PORTn_STATUS(port) (0x80200 + 4 * (port)) +#define YT921X_PORT_LINK BIT(9) /* CTRL: auto negotiation */ +#define YT921X_PORT_HALF_PAUSE BIT(8) /* Half-duplex back pressure mode */ +#define YT921X_PORT_DUPLEX_FULL BIT(7) +#define YT921X_PORT_RX_PAUSE BIT(6) +#define YT921X_PORT_TX_PAUSE BIT(5) +#define YT921X_PORT_RX_MAC_EN BIT(4) +#define YT921X_PORT_TX_MAC_EN BIT(3) +#define YT921X_PORT_SPEED_M GENMASK(2, 0) +#define YT921X_PORT_SPEED(x) FIELD_PREP(YT921X_PORT_SPEED_M, (x)) +#define YT921X_PORT_SPEED_10 YT921X_PORT_SPEED(0) +#define YT921X_PORT_SPEED_100 YT921X_PORT_SPEED(1) +#define YT921X_PORT_SPEED_1000 YT921X_PORT_SPEED(2) +#define YT921X_PORT_SPEED_10000 YT921X_PORT_SPEED(3) +#define YT921X_PORT_SPEED_2500 YT921X_PORT_SPEED(4) +#define YT921X_PON_STRAP_FUNC 0x80320 +#define YT921X_PON_STRAP_VAL 0x80324 +#define YT921X_PON_STRAP_CAP 0x80328 +#define YT921X_PON_STRAP_EEE BIT(16) +#define YT921X_PON_STRAP_LOOP_DETECT BIT(7) +#define YT921X_MDIO_POLLINGn(port) (0x80364 + 4 * ((port) - 8)) +#define YT921X_MDIO_POLLING_DUPLEX_FULL BIT(4) +#define YT921X_MDIO_POLLING_LINK BIT(3) +#define YT921X_MDIO_POLLING_SPEED_M GENMASK(2, 0) +#define YT921X_MDIO_POLLING_SPEED(x) FIELD_PREP(YT921X_MDIO_POLLING_SPEED_M, (x)) +#define YT921X_MDIO_POLLING_SPEED_10 YT921X_MDIO_POLLING_SPEED(0) +#define YT921X_MDIO_POLLING_SPEED_100 YT921X_MDIO_POLLING_SPEED(1) +#define YT921X_MDIO_POLLING_SPEED_1000 YT921X_MDIO_POLLING_SPEED(2) +#define YT921X_MDIO_POLLING_SPEED_10000 YT921X_MDIO_POLLING_SPEED(3) +#define YT921X_MDIO_POLLING_SPEED_2500 YT921X_MDIO_POLLING_SPEED(4) +#define YT921X_SENSOR 0x8036c +#define YT921X_SENSOR_TEMP BIT(18) +#define YT921X_TEMP 0x80374 +#define YT921X_CHIP_MODE 0x80388 +#define YT921X_CHIP_MODE_MODE GENMASK(1, 0) +#define YT921X_XMII_CTRL 0x80394 +#define YT921X_XMII_CTRL_PORTn(port) BIT(9 - (port)) /* Yes, it's reversed */ +#define YT921X_XMIIn(port) (0x80400 + 8 * ((port) - 8)) +#define YT921X_XMII_MODE_M GENMASK(31, 29) +#define YT921X_XMII_MODE(x) FIELD_PREP(YT921X_XMII_MODE_M, (x)) +#define YT921X_XMII_MODE_MII YT921X_XMII_MODE(0) +#define YT921X_XMII_MODE_REVMII YT921X_XMII_MODE(1) +#define YT921X_XMII_MODE_RMII YT921X_XMII_MODE(2) +#define YT921X_XMII_MODE_REVRMII YT921X_XMII_MODE(3) +#define YT921X_XMII_MODE_RGMII YT921X_XMII_MODE(4) +#define YT921X_XMII_MODE_DISABLE YT921X_XMII_MODE(5) +#define YT921X_XMII_LINK BIT(19) /* force link */ +#define YT921X_XMII_EN BIT(18) +#define YT921X_XMII_SOFT_RST BIT(17) +#define YT921X_XMII_RGMII_TX_DELAY_150PS_M GENMASK(16, 13) +#define YT921X_XMII_RGMII_TX_DELAY_150PS(x) FIELD_PREP(YT921X_XMII_RGMII_TX_DELAY_150PS_M, (x)) +#define YT921X_XMII_TX_CLK_IN BIT(11) +#define YT921X_XMII_RX_CLK_IN BIT(10) +#define YT921X_XMII_RGMII_TX_DELAY_2NS BIT(8) +#define YT921X_XMII_RGMII_TX_CLK_OUT BIT(7) +#define YT921X_XMII_RGMII_RX_DELAY_150PS_M GENMASK(6, 3) +#define YT921X_XMII_RGMII_RX_DELAY_150PS(x) FIELD_PREP(YT921X_XMII_RGMII_RX_DELAY_150PS_M, (x)) +#define YT921X_XMII_RMII_PHY_TX_CLK_OUT BIT(2) +#define YT921X_XMII_REVMII_TX_CLK_OUT BIT(1) +#define YT921X_XMII_REVMII_RX_CLK_OUT BIT(0) + +#define YT921X_MACn_FRAME(port) (0x81008 + 0x1000 * (port)) +#define YT921X_MAC_FRAME_SIZE_M GENMASK(21, 8) +#define YT921X_MAC_FRAME_SIZE(x) FIELD_PREP(YT921X_MAC_FRAME_SIZE_M, (x)) + +#define YT921X_EEEn_VAL(port) (0xa0000 + 0x40 * (port)) +#define YT921X_EEE_VAL_DATA BIT(1) + +#define YT921X_EEE_CTRL 0xb0000 +#define YT921X_EEE_CTRL_ENn(port) BIT(port) + +#define YT921X_MIB_CTRL 0xc0004 +#define YT921X_MIB_CTRL_CLEAN BIT(30) +#define YT921X_MIB_CTRL_PORT_M GENMASK(6, 3) +#define YT921X_MIB_CTRL_PORT(x) FIELD_PREP(YT921X_MIB_CTRL_PORT_M, (x)) +#define YT921X_MIB_CTRL_ONE_PORT BIT(1) +#define YT921X_MIB_CTRL_ALL_PORT BIT(0) +#define YT921X_MIBn_DATA0(port) (0xc0100 + 0x100 * (port)) +#define YT921X_MIBn_DATAm(port, x) (YT921X_MIBn_DATA0(port) + 4 * (x)) + +#define YT921X_EDATA_CTRL 0xe0000 +#define YT921X_EDATA_CTRL_ADDR_M GENMASK(15, 8) +#define YT921X_EDATA_CTRL_ADDR(x) FIELD_PREP(YT921X_EDATA_CTRL_ADDR_M, (x)) +#define YT921X_EDATA_CTRL_OP_M GENMASK(3, 0) +#define YT921X_EDATA_CTRL_OP(x) FIELD_PREP(YT921X_EDATA_CTRL_OP_M, (x)) +#define YT921X_EDATA_CTRL_READ YT921X_EDATA_CTRL_OP(5) +#define YT921X_EDATA_DATA 0xe0004 +#define YT921X_EDATA_DATA_DATA_M GENMASK(31, 24) +#define YT921X_EDATA_DATA_STATUS_M GENMASK(3, 0) +#define YT921X_EDATA_DATA_STATUS(x) FIELD_PREP(YT921X_EDATA_DATA_STATUS_M, (x)) +#define YT921X_EDATA_DATA_IDLE YT921X_EDATA_DATA_STATUS(3) + +#define YT921X_EXT_MBUS_OP 0x6a000 +#define YT921X_INT_MBUS_OP 0xf0000 +#define YT921X_MBUS_OP_START BIT(0) +#define YT921X_EXT_MBUS_CTRL 0x6a004 +#define YT921X_INT_MBUS_CTRL 0xf0004 +#define YT921X_MBUS_CTRL_PORT_M GENMASK(25, 21) +#define YT921X_MBUS_CTRL_PORT(x) FIELD_PREP(YT921X_MBUS_CTRL_PORT_M, (x)) +#define YT921X_MBUS_CTRL_REG_M GENMASK(20, 16) +#define YT921X_MBUS_CTRL_REG(x) FIELD_PREP(YT921X_MBUS_CTRL_REG_M, (x)) +#define YT921X_MBUS_CTRL_TYPE_M GENMASK(11, 8) /* wild guess */ +#define YT921X_MBUS_CTRL_TYPE(x) FIELD_PREP(YT921X_MBUS_CTRL_TYPE_M, (x)) +#define YT921X_MBUS_CTRL_TYPE_C22 YT921X_MBUS_CTRL_TYPE(4) +#define YT921X_MBUS_CTRL_OP_M GENMASK(3, 2) /* wild guess */ +#define YT921X_MBUS_CTRL_OP(x) FIELD_PREP(YT921X_MBUS_CTRL_OP_M, (x)) +#define YT921X_MBUS_CTRL_WRITE YT921X_MBUS_CTRL_OP(1) +#define YT921X_MBUS_CTRL_READ YT921X_MBUS_CTRL_OP(2) +#define YT921X_EXT_MBUS_DOUT 0x6a008 +#define YT921X_INT_MBUS_DOUT 0xf0008 +#define YT921X_EXT_MBUS_DIN 0x6a00c +#define YT921X_INT_MBUS_DIN 0xf000c + +#define YT921X_PORTn_EGR(port) (0x100000 + 4 * (port)) +#define YT921X_PORT_EGR_TPID_CTAG_M GENMASK(5, 4) +#define YT921X_PORT_EGR_TPID_CTAG(x) FIELD_PREP(YT921X_PORT_EGR_TPID_CTAG_M, (x)) +#define YT921X_PORT_EGR_TPID_STAG_M GENMASK(3, 2) +#define YT921X_PORT_EGR_TPID_STAG(x) FIELD_PREP(YT921X_PORT_EGR_TPID_STAG_M, (x)) +#define YT921X_TPID_EGRn(x) (0x100300 + 4 * (x)) /* [0, 3] */ +#define YT921X_TPID_EGR_TPID_M GENMASK(15, 0) + +#define YT921X_VLAN_IGR_FILTER 0x180280 +#define YT921X_VLAN_IGR_FILTER_PORTn_BYPASS_IGMP(port) BIT((port) + 11) +#define YT921X_VLAN_IGR_FILTER_PORTn(port) BIT(port) +#define YT921X_PORTn_ISOLATION(port) (0x180294 + 4 * (port)) +#define YT921X_PORT_ISOLATION_BLOCKn(port) BIT(port) +#define YT921X_PORTn_LEARN(port) (0x1803d0 + 4 * (port)) +#define YT921X_PORT_LEARN_VID_LEARN_MULTI_EN BIT(22) +#define YT921X_PORT_LEARN_VID_LEARN_MODE BIT(21) +#define YT921X_PORT_LEARN_VID_LEARN_EN BIT(20) +#define YT921X_PORT_LEARN_SUSPEND_COPY_EN BIT(19) +#define YT921X_PORT_LEARN_SUSPEND_DROP_EN BIT(18) +#define YT921X_PORT_LEARN_DIS BIT(17) +#define YT921X_PORT_LEARN_LIMIT_EN BIT(16) +#define YT921X_PORT_LEARN_LIMIT_M GENMASK(15, 8) +#define YT921X_PORT_LEARN_LIMIT(x) FIELD_PREP(YT921X_PORT_LEARN_LIMIT_M, (x)) +#define YT921X_PORT_LEARN_DROP_ON_EXCEEDED BIT(2) +#define YT921X_PORT_LEARN_MODE_M GENMASK(1, 0) +#define YT921X_PORT_LEARN_MODE(x) FIELD_PREP(YT921X_PORT_LEARN_MODE_M, (x)) +#define YT921X_PORT_LEARN_MODE_AUTO YT921X_PORT_LEARN_MODE(0) +#define YT921X_PORT_LEARN_MODE_AUTO_AND_COPY YT921X_PORT_LEARN_MODE(1) +#define YT921X_PORT_LEARN_MODE_CPU_CONTROL YT921X_PORT_LEARN_MODE(2) +#define YT921X_AGEING 0x180440 +#define YT921X_AGEING_INTERVAL_M GENMASK(15, 0) +#define YT921X_FDB_IN0 0x180454 +#define YT921X_FDB_IN1 0x180458 +#define YT921X_FDB_IN2 0x18045c +#define YT921X_FDB_OP 0x180460 +#define YT921X_FDB_OP_INDEX_M GENMASK(22, 11) +#define YT921X_FDB_OP_INDEX(x) FIELD_PREP(YT921X_FDB_OP_INDEX_M, (x)) +#define YT921X_FDB_OP_MODE_INDEX BIT(10) /* mac+fid / index */ +#define YT921X_FDB_OP_FLUSH_MCAST BIT(9) /* ucast / mcast */ +#define YT921X_FDB_OP_FLUSH_M GENMASK(8, 7) +#define YT921X_FDB_OP_FLUSH(x) FIELD_PREP(YT921X_FDB_OP_FLUSH_M, (x)) +#define YT921X_FDB_OP_FLUSH_ALL YT921X_FDB_OP_FLUSH(0) +#define YT921X_FDB_OP_FLUSH_PORT YT921X_FDB_OP_FLUSH(1) +#define YT921X_FDB_OP_FLUSH_PORT_VID YT921X_FDB_OP_FLUSH(2) +#define YT921X_FDB_OP_FLUSH_VID YT921X_FDB_OP_FLUSH(3) +#define YT921X_FDB_OP_FLUSH_STATIC BIT(6) +#define YT921X_FDB_OP_NEXT_TYPE_M GENMASK(5, 4) +#define YT921X_FDB_OP_NEXT_TYPE(x) FIELD_PREP(YT921X_FDB_OP_NEXT_TYPE_M, (x)) +#define YT921X_FDB_OP_NEXT_TYPE_UCAST_PORT YT921X_FDB_OP_NEXT_TYPE(0) +#define YT921X_FDB_OP_NEXT_TYPE_UCAST_VID YT921X_FDB_OP_NEXT_TYPE(1) +#define YT921X_FDB_OP_NEXT_TYPE_UCAST YT921X_FDB_OP_NEXT_TYPE(2) +#define YT921X_FDB_OP_NEXT_TYPE_MCAST YT921X_FDB_OP_NEXT_TYPE(3) +#define YT921X_FDB_OP_OP_M GENMASK(3, 1) +#define YT921X_FDB_OP_OP(x) FIELD_PREP(YT921X_FDB_OP_OP_M, (x)) +#define YT921X_FDB_OP_OP_ADD YT921X_FDB_OP_OP(0) +#define YT921X_FDB_OP_OP_DEL YT921X_FDB_OP_OP(1) +#define YT921X_FDB_OP_OP_GET_ONE YT921X_FDB_OP_OP(2) +#define YT921X_FDB_OP_OP_GET_NEXT YT921X_FDB_OP_OP(3) +#define YT921X_FDB_OP_OP_FLUSH YT921X_FDB_OP_OP(4) +#define YT921X_FDB_OP_START BIT(0) +#define YT921X_FDB_RESULT 0x180464 +#define YT921X_FDB_RESULT_DONE BIT(15) +#define YT921X_FDB_RESULT_NOTFOUND BIT(14) +#define YT921X_FDB_RESULT_OVERWRITED BIT(13) +#define YT921X_FDB_RESULT_INDEX_M GENMASK(11, 0) +#define YT921X_FDB_RESULT_INDEX(x) FIELD_PREP(YT921X_FDB_RESULT_INDEX_M, (x)) +#define YT921X_FDB_OUT0 0x1804b0 +#define YT921X_FDB_IO0_ADDR_HI4_M GENMASK(31, 0) +#define YT921X_FDB_OUT1 0x1804b4 +#define YT921X_FDB_IO1_EGR_INT_PRI_EN BIT(31) +#define YT921X_FDB_IO1_STATUS_M GENMASK(30, 28) +#define YT921X_FDB_IO1_STATUS(x) FIELD_PREP(YT921X_FDB_IO1_STATUS_M, (x)) +#define YT921X_FDB_IO1_STATUS_INVALID YT921X_FDB_IO1_STATUS(0) +#define YT921X_FDB_IO1_STATUS_MIN_TIME YT921X_FDB_IO1_STATUS(1) +#define YT921X_FDB_IO1_STATUS_MOVE_AGING_MAX_TIME YT921X_FDB_IO1_STATUS(3) +#define YT921X_FDB_IO1_STATUS_MAX_TIME YT921X_FDB_IO1_STATUS(5) +#define YT921X_FDB_IO1_STATUS_PENDING YT921X_FDB_IO1_STATUS(6) +#define YT921X_FDB_IO1_STATUS_STATIC YT921X_FDB_IO1_STATUS(7) +#define YT921X_FDB_IO1_FID_M GENMASK(27, 16) /* filtering ID (VID) */ +#define YT921X_FDB_IO1_FID(x) FIELD_PREP(YT921X_FDB_IO1_FID_M, (x)) +#define YT921X_FDB_IO1_ADDR_LO2_M GENMASK(15, 0) +#define YT921X_FDB_OUT2 0x1804b8 +#define YT921X_FDB_IO2_MOVE_AGING_STATUS_M GENMASK(31, 30) +#define YT921X_FDB_IO2_IGR_DROP BIT(29) +#define YT921X_FDB_IO2_EGR_PORTS_M GENMASK(28, 18) +#define YT921X_FDB_IO2_EGR_PORTS(x) FIELD_PREP(YT921X_FDB_IO2_EGR_PORTS_M, (x)) +#define YT921X_FDB_IO2_EGR_DROP BIT(17) +#define YT921X_FDB_IO2_COPY_TO_CPU BIT(16) +#define YT921X_FDB_IO2_IGR_INT_PRI_EN BIT(15) +#define YT921X_FDB_IO2_INT_PRI_M GENMASK(14, 12) +#define YT921X_FDB_IO2_INT_PRI(x) FIELD_PREP(YT921X_FDB_IO2_INT_PRI_M, (x)) +#define YT921X_FDB_IO2_NEW_VID_M GENMASK(11, 0) +#define YT921X_FDB_IO2_NEW_VID(x) FIELD_PREP(YT921X_FDB_IO2_NEW_VID_M, (x)) +#define YT921X_FILTER_UNK_UCAST 0x180508 +#define YT921X_FILTER_UNK_MCAST 0x18050c +#define YT921X_FILTER_MCAST 0x180510 +#define YT921X_FILTER_BCAST 0x180514 +#define YT921X_FILTER_PORTS_M GENMASK(10, 0) +#define YT921X_FILTER_PORTS(x) FIELD_PREP(YT921X_FILTER_PORTS_M, (x)) +#define YT921X_FILTER_PORTn(port) BIT(port) +#define YT921X_VLAN_EGR_FILTER 0x180598 +#define YT921X_VLAN_EGR_FILTER_PORTn(port) BIT(port) +#define YT921X_CPU_COPY 0x180690 +#define YT921X_CPU_COPY_FORCE_INT_PORT BIT(2) +#define YT921X_CPU_COPY_TO_INT_CPU BIT(1) +#define YT921X_CPU_COPY_TO_EXT_CPU BIT(0) +#define YT921X_ACT_UNK_UCAST 0x180734 +#define YT921X_ACT_UNK_MCAST 0x180738 +#define YT921X_ACT_UNK_MCAST_BYPASS_DROP_RMA BIT(23) +#define YT921X_ACT_UNK_MCAST_BYPASS_DROP_IGMP BIT(22) +#define YT921X_ACT_UNK_ACTn_M(port) GENMASK(2 * (port) + 1, 2 * (port)) +#define YT921X_ACT_UNK_ACTn(port, x) ((x) << (2 * (port))) +#define YT921X_ACT_UNK_ACTn_FORWARD(port) YT921X_ACT_UNK_ACTn(port, 0) /* flood */ +#define YT921X_ACT_UNK_ACTn_TRAP(port) YT921X_ACT_UNK_ACTn(port, 1) /* steer to CPU */ +#define YT921X_ACT_UNK_ACTn_DROP(port) YT921X_ACT_UNK_ACTn(port, 2) /* discard */ +/* NEVER use this action; see comments in the tag driver */ +#define YT921X_ACT_UNK_ACTn_COPY(port) YT921X_ACT_UNK_ACTn(port, 3) /* flood and copy */ +#define YT921X_FDB_HW_FLUSH 0x180958 +#define YT921X_FDB_HW_FLUSH_ON_LINKDOWN BIT(0) + +#define YT921X_VLANn_CTRL(vlan) (0x188000 + 8 * (vlan)) +#define YT921X_VLAN_CTRL_UNTAG_PORTS_M GENMASK(50, 40) +#define YT921X_VLAN_CTRL_UNTAG_PORTS(x) FIELD_PREP(YT921X_VLAN_CTRL_UNTAG_PORTS_M, (x)) +#define YT921X_VLAN_CTRL_UNTAG_PORTn(port) BIT((port) + 40) +#define YT921X_VLAN_CTRL_STP_ID_M GENMASK(39, 36) +#define YT921X_VLAN_CTRL_STP_ID(x) FIELD_PREP(YT921X_VLAN_CTRL_STP_ID_M, (x)) +#define YT921X_VLAN_CTRL_SVLAN_EN BIT(35) +#define YT921X_VLAN_CTRL_FID_M GENMASK(34, 23) +#define YT921X_VLAN_CTRL_FID(x) FIELD_PREP(YT921X_VLAN_CTRL_FID_M, (x)) +#define YT921X_VLAN_CTRL_LEARN_DIS BIT(22) +#define YT921X_VLAN_CTRL_INT_PRI_EN BIT(21) +#define YT921X_VLAN_CTRL_INT_PRI_M GENMASK(20, 18) +#define YT921X_VLAN_CTRL_PORTS_M GENMASK(17, 7) +#define YT921X_VLAN_CTRL_PORTS(x) FIELD_PREP(YT921X_VLAN_CTRL_PORTS_M, (x)) +#define YT921X_VLAN_CTRL_PORTn(port) BIT((port) + 7) +#define YT921X_VLAN_CTRL_BYPASS_1X_AC BIT(6) +#define YT921X_VLAN_CTRL_METER_EN BIT(5) +#define YT921X_VLAN_CTRL_METER_ID_M GENMASK(4, 0) + +#define YT921X_TPID_IGRn(x) (0x210000 + 4 * (x)) /* [0, 3] */ +#define YT921X_TPID_IGR_TPID_M GENMASK(15, 0) +#define YT921X_PORTn_IGR_TPID(port) (0x210010 + 4 * (port)) +#define YT921X_PORT_IGR_TPIDn_STAG_M GENMASK(7, 4) +#define YT921X_PORT_IGR_TPIDn_STAG(x) BIT((x) + 4) +#define YT921X_PORT_IGR_TPIDn_CTAG_M GENMASK(3, 0) +#define YT921X_PORT_IGR_TPIDn_CTAG(x) BIT(x) + +#define YT921X_PORTn_VLAN_CTRL(port) (0x230010 + 4 * (port)) +#define YT921X_PORT_VLAN_CTRL_SVLAN_PRI_EN BIT(31) +#define YT921X_PORT_VLAN_CTRL_CVLAN_PRI_EN BIT(30) +#define YT921X_PORT_VLAN_CTRL_SVID_M GENMASK(29, 18) +#define YT921X_PORT_VLAN_CTRL_SVID(x) FIELD_PREP(YT921X_PORT_VLAN_CTRL_SVID_M, (x)) +#define YT921X_PORT_VLAN_CTRL_CVID_M GENMASK(17, 6) +#define YT921X_PORT_VLAN_CTRL_CVID(x) FIELD_PREP(YT921X_PORT_VLAN_CTRL_CVID_M, (x)) +#define YT921X_PORT_VLAN_CTRL_SVLAN_PRI_M GENMASK(5, 3) +#define YT921X_PORT_VLAN_CTRL_CVLAN_PRI_M GENMASK(2, 0) +#define YT921X_PORTn_VLAN_CTRL1(port) (0x230080 + 4 * (port)) +#define YT921X_PORT_VLAN_CTRL1_VLAN_RANGE_EN BIT(8) +#define YT921X_PORT_VLAN_CTRL1_VLAN_RANGE_PROFILE_ID_M GENMASK(7, 4) +#define YT921X_PORT_VLAN_CTRL1_SVLAN_DROP_TAGGED BIT(3) +#define YT921X_PORT_VLAN_CTRL1_SVLAN_DROP_UNTAGGED BIT(2) +#define YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_TAGGED BIT(1) +#define YT921X_PORT_VLAN_CTRL1_CVLAN_DROP_UNTAGGED BIT(0) + +#define YT921X_MIRROR 0x300300 +#define YT921X_MIRROR_IGR_PORTS_M GENMASK(26, 16) +#define YT921X_MIRROR_IGR_PORTS(x) FIELD_PREP(YT921X_MIRROR_IGR_PORTS_M, (x)) +#define YT921X_MIRROR_IGR_PORTn(port) BIT((port) + 16) +#define YT921X_MIRROR_EGR_PORTS_M GENMASK(14, 4) +#define YT921X_MIRROR_EGR_PORTS(x) FIELD_PREP(YT921X_MIRROR_EGR_PORTS_M, (x)) +#define YT921X_MIRROR_EGR_PORTn(port) BIT((port) + 4) +#define YT921X_MIRROR_PORT_M GENMASK(3, 0) +#define YT921X_MIRROR_PORT(x) FIELD_PREP(YT921X_MIRROR_PORT_M, (x)) + +#define YT921X_EDATA_EXTMODE 0xfb +#define YT921X_EDATA_LEN 0x100 + +#define YT921X_FDB_NUM 4096 + +enum yt921x_fdb_entry_status { + YT921X_FDB_ENTRY_STATUS_INVALID = 0, + YT921X_FDB_ENTRY_STATUS_MIN_TIME = 1, + YT921X_FDB_ENTRY_STATUS_MOVE_AGING_MAX_TIME = 3, + YT921X_FDB_ENTRY_STATUS_MAX_TIME = 5, + YT921X_FDB_ENTRY_STATUS_PENDING = 6, + YT921X_FDB_ENTRY_STATUS_STATIC = 7, +}; + +#define YT9215_MAJOR 0x9002 +#define YT9218_MAJOR 0x9001 + +/* required for a hard reset */ +#define YT921X_RST_DELAY_US 10000 + +#define YT921X_FRAME_SIZE_MAX 0x2400 /* 9216 */ + +#define YT921X_TAG_LEN 8 + +/* 8 internal + 2 external + 1 mcu */ +#define YT921X_PORT_NUM 11 + +#define yt921x_port_is_internal(port) ((port) < 8) +#define yt921x_port_is_external(port) (8 <= (port) && (port) < 9) + +struct yt921x_mib { + u64 rx_broadcast; + u64 rx_pause; + u64 rx_multicast; + u64 rx_crc_errors; + + u64 rx_alignment_errors; + u64 rx_undersize_errors; + u64 rx_fragment_errors; + u64 rx_64byte; + + u64 rx_65_127byte; + u64 rx_128_255byte; + u64 rx_256_511byte; + u64 rx_512_1023byte; + + u64 rx_1024_1518byte; + u64 rx_jumbo; + u64 rx_good_bytes; + + u64 rx_bad_bytes; + u64 rx_oversize_errors; + + u64 rx_dropped; + u64 tx_broadcast; + u64 tx_pause; + u64 tx_multicast; + + u64 tx_undersize_errors; + u64 tx_64byte; + u64 tx_65_127byte; + u64 tx_128_255byte; + + u64 tx_256_511byte; + u64 tx_512_1023byte; + u64 tx_1024_1518byte; + u64 tx_jumbo; + + u64 tx_good_bytes; + u64 tx_collisions; + + u64 tx_aborted_errors; + u64 tx_multiple_collisions; + u64 tx_single_collisions; + u64 tx_good; + + u64 tx_deferred; + u64 tx_late_collisions; + u64 rx_oam; + u64 tx_oam; +}; + +struct yt921x_port { + unsigned char index; + + bool hairpin; + bool isolated; + + struct delayed_work mib_read; + struct yt921x_mib mib; + u64 rx_frames; + u64 tx_frames; +}; + +struct yt921x_reg_ops { + int (*read)(void *context, u32 reg, u32 *valp); + int (*write)(void *context, u32 reg, u32 val); +}; + +struct yt921x_priv { + struct dsa_switch ds; + + const struct yt921x_info *info; + /* cache of dsa_cpu_ports(ds) */ + u16 cpu_ports_mask; + + /* protect the access to the switch registers */ + struct mutex reg_lock; + const struct yt921x_reg_ops *reg_ops; + void *reg_ctx; + + /* mdio master bus */ + struct mii_bus *mbus_int; + struct mii_bus *mbus_ext; + + struct yt921x_port ports[YT921X_PORT_NUM]; + + u16 eee_ports_mask; +}; + +#endif diff --git a/drivers/net/ethernet/3com/3c515.c b/drivers/net/ethernet/3com/3c515.c index ecdea58e6a21f..2227c83a48622 100644 --- a/drivers/net/ethernet/3com/3c515.c +++ b/drivers/net/ethernet/3com/3c515.c @@ -1547,9 +1547,8 @@ static const struct ethtool_ops netdev_ethtool_ops = { .set_msglevel = netdev_set_msglevel, }; - #ifdef MODULE -void cleanup_module(void) +static void __exit corkscrew_exit_module(void) { while (!list_empty(&root_corkscrew_dev)) { struct net_device *dev; @@ -1563,4 +1562,5 @@ void cleanup_module(void) free_netdev(dev); } } +module_exit(corkscrew_exit_module); #endif /* MODULE */ diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index aead145dd91d1..429310dfc686f 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -22,6 +22,7 @@ source "drivers/net/ethernet/aeroflex/Kconfig" source "drivers/net/ethernet/agere/Kconfig" source "drivers/net/ethernet/airoha/Kconfig" source "drivers/net/ethernet/alacritech/Kconfig" +source "drivers/net/ethernet/alibaba/Kconfig" source "drivers/net/ethernet/allwinner/Kconfig" source "drivers/net/ethernet/alteon/Kconfig" source "drivers/net/ethernet/altera/Kconfig" @@ -129,6 +130,7 @@ source "drivers/net/ethernet/microchip/Kconfig" source "drivers/net/ethernet/mscc/Kconfig" source "drivers/net/ethernet/microsoft/Kconfig" source "drivers/net/ethernet/moxa/Kconfig" +source "drivers/net/ethernet/mucse/Kconfig" source "drivers/net/ethernet/myricom/Kconfig" config FEALNX diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 998dd628b202c..2347f87a5808e 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -12,6 +12,7 @@ obj-$(CONFIG_NET_VENDOR_ADI) += adi/ obj-$(CONFIG_NET_VENDOR_AGERE) += agere/ obj-$(CONFIG_NET_VENDOR_AIROHA) += airoha/ obj-$(CONFIG_NET_VENDOR_ALACRITECH) += alacritech/ +obj-$(CONFIG_NET_VENDOR_ALIBABA) += alibaba/ obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/ obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/ obj-$(CONFIG_ALTERA_TSE) += altera/ @@ -65,6 +66,7 @@ obj-$(CONFIG_NET_VENDOR_MICREL) += micrel/ obj-$(CONFIG_NET_VENDOR_MICROCHIP) += microchip/ obj-$(CONFIG_NET_VENDOR_MICROSEMI) += mscc/ obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/ +obj-$(CONFIG_NET_VENDOR_MUCSE) += mucse/ obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/ obj-$(CONFIG_FEALNX) += fealnx.o obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/ diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c index 433a646e98317..75893c90a0a17 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.c +++ b/drivers/net/ethernet/airoha/airoha_eth.c @@ -137,11 +137,11 @@ static void airoha_fe_maccr_init(struct airoha_eth *eth) for (p = 1; p <= ARRAY_SIZE(eth->ports); p++) airoha_fe_set(eth, REG_GDM_FWD_CFG(p), - GDM_TCP_CKSUM | GDM_UDP_CKSUM | GDM_IP4_CKSUM | - GDM_DROP_CRC_ERR); + GDM_TCP_CKSUM_MASK | GDM_UDP_CKSUM_MASK | + GDM_IP4_CKSUM_MASK | GDM_DROP_CRC_ERR_MASK); - airoha_fe_rmw(eth, REG_CDM1_VLAN_CTRL, CDM1_VLAN_MASK, - FIELD_PREP(CDM1_VLAN_MASK, 0x8100)); + airoha_fe_rmw(eth, REG_CDM_VLAN_CTRL(1), CDM_VLAN_MASK, + FIELD_PREP(CDM_VLAN_MASK, 0x8100)); airoha_fe_set(eth, REG_FE_CPORT_CFG, FE_CPORT_PAD); } @@ -297,8 +297,11 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth) int q; all_rsv = airoha_fe_get_pse_all_rsv(eth); - /* hw misses PPE2 oq rsv */ - all_rsv += PSE_RSV_PAGES * pse_port_num_queues[FE_PSE_PORT_PPE2]; + if (airoha_ppe_is_enabled(eth, 1)) { + /* hw misses PPE2 oq rsv */ + all_rsv += PSE_RSV_PAGES * + pse_port_num_queues[FE_PSE_PORT_PPE2]; + } airoha_fe_set(eth, REG_FE_PSE_BUF_SET, all_rsv); /* CMD1 */ @@ -335,13 +338,17 @@ static void airoha_fe_pse_ports_init(struct airoha_eth *eth) for (q = 4; q < pse_port_num_queues[FE_PSE_PORT_CDM4]; q++) airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_CDM4, q, PSE_QUEUE_RSV_PAGES); - /* PPE2 */ - for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE2]; q++) { - if (q < pse_port_num_queues[FE_PSE_PORT_PPE2] / 2) - airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, q, - PSE_QUEUE_RSV_PAGES); - else - airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, q, 0); + if (airoha_ppe_is_enabled(eth, 1)) { + /* PPE2 */ + for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_PPE2]; q++) { + if (q < pse_port_num_queues[FE_PSE_PORT_PPE2] / 2) + airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, + q, + PSE_QUEUE_RSV_PAGES); + else + airoha_fe_set_pse_oq_rsv(eth, FE_PSE_PORT_PPE2, + q, 0); + } } /* GMD4 */ for (q = 0; q < pse_port_num_queues[FE_PSE_PORT_GDM4]; q++) @@ -396,46 +403,46 @@ static int airoha_fe_mc_vlan_clear(struct airoha_eth *eth) static void airoha_fe_crsn_qsel_init(struct airoha_eth *eth) { /* CDM1_CRSN_QSEL */ - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_22 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_22), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_22), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_22 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_22), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_22), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_08 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_08), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_08), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_08 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_08), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_08), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_21 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_21), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_21), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_21 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_21), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_21), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_24 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_24), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_24), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_24 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_24), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_24), CDM_CRSN_QSEL_Q6)); - airoha_fe_rmw(eth, REG_CDM1_CRSN_QSEL(CRSN_25 >> 2), - CDM1_CRSN_QSEL_REASON_MASK(CRSN_25), - FIELD_PREP(CDM1_CRSN_QSEL_REASON_MASK(CRSN_25), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(1, CRSN_25 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_25), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_25), CDM_CRSN_QSEL_Q1)); /* CDM2_CRSN_QSEL */ - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_08 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_08), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_08), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_08 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_08), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_08), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_21 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_21), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_21), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_21 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_21), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_21), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_22 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_22), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_22), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_22 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_22), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_22), CDM_CRSN_QSEL_Q1)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_24 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_24), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_24), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_24 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_24), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_24), CDM_CRSN_QSEL_Q6)); - airoha_fe_rmw(eth, REG_CDM2_CRSN_QSEL(CRSN_25 >> 2), - CDM2_CRSN_QSEL_REASON_MASK(CRSN_25), - FIELD_PREP(CDM2_CRSN_QSEL_REASON_MASK(CRSN_25), + airoha_fe_rmw(eth, REG_CDM_CRSN_QSEL(2, CRSN_25 >> 2), + CDM_CRSN_QSEL_REASON_MASK(CRSN_25), + FIELD_PREP(CDM_CRSN_QSEL_REASON_MASK(CRSN_25), CDM_CRSN_QSEL_Q1)); } @@ -455,18 +462,18 @@ static int airoha_fe_init(struct airoha_eth *eth) airoha_fe_wr(eth, REG_FE_PCE_CFG, PCE_DPI_EN_MASK | PCE_KA_EN_MASK | PCE_MC_EN_MASK); /* set vip queue selection to ring 1 */ - airoha_fe_rmw(eth, REG_CDM1_FWD_CFG, CDM1_VIP_QSEL_MASK, - FIELD_PREP(CDM1_VIP_QSEL_MASK, 0x4)); - airoha_fe_rmw(eth, REG_CDM2_FWD_CFG, CDM2_VIP_QSEL_MASK, - FIELD_PREP(CDM2_VIP_QSEL_MASK, 0x4)); + airoha_fe_rmw(eth, REG_CDM_FWD_CFG(1), CDM_VIP_QSEL_MASK, + FIELD_PREP(CDM_VIP_QSEL_MASK, 0x4)); + airoha_fe_rmw(eth, REG_CDM_FWD_CFG(2), CDM_VIP_QSEL_MASK, + FIELD_PREP(CDM_VIP_QSEL_MASK, 0x4)); /* set GDM4 source interface offset to 8 */ - airoha_fe_rmw(eth, REG_GDM4_SRC_PORT_SET, - GDM4_SPORT_OFF2_MASK | - GDM4_SPORT_OFF1_MASK | - GDM4_SPORT_OFF0_MASK, - FIELD_PREP(GDM4_SPORT_OFF2_MASK, 8) | - FIELD_PREP(GDM4_SPORT_OFF1_MASK, 8) | - FIELD_PREP(GDM4_SPORT_OFF0_MASK, 8)); + airoha_fe_rmw(eth, REG_GDM_SRC_PORT_SET(4), + GDM_SPORT_OFF2_MASK | + GDM_SPORT_OFF1_MASK | + GDM_SPORT_OFF0_MASK, + FIELD_PREP(GDM_SPORT_OFF2_MASK, 8) | + FIELD_PREP(GDM_SPORT_OFF1_MASK, 8) | + FIELD_PREP(GDM_SPORT_OFF0_MASK, 8)); /* set PSE Page as 128B */ airoha_fe_rmw(eth, REG_FE_DMA_GLO_CFG, @@ -492,8 +499,8 @@ static int airoha_fe_init(struct airoha_eth *eth) airoha_fe_set(eth, REG_GDM_MISC_CFG, GDM2_RDM_ACK_WAIT_PREF_MASK | GDM2_CHN_VLD_MODE_MASK); - airoha_fe_rmw(eth, REG_CDM2_FWD_CFG, CDM2_OAM_QSEL_MASK, - FIELD_PREP(CDM2_OAM_QSEL_MASK, 15)); + airoha_fe_rmw(eth, REG_CDM_FWD_CFG(2), CDM_OAM_QSEL_MASK, + FIELD_PREP(CDM_OAM_QSEL_MASK, 15)); /* init fragment and assemble Force Port */ /* NPU Core-3, NPU Bridge Channel-3 */ @@ -507,8 +514,8 @@ static int airoha_fe_init(struct airoha_eth *eth) FIELD_PREP(IP_ASSEMBLE_PORT_MASK, 0) | FIELD_PREP(IP_ASSEMBLE_NBQ_MASK, 22)); - airoha_fe_set(eth, REG_GDM3_FWD_CFG, GDM3_PAD_EN_MASK); - airoha_fe_set(eth, REG_GDM4_FWD_CFG, GDM4_PAD_EN_MASK); + airoha_fe_set(eth, REG_GDM_FWD_CFG(3), GDM_PAD_EN_MASK); + airoha_fe_set(eth, REG_GDM_FWD_CFG(4), GDM_PAD_EN_MASK); airoha_fe_crsn_qsel_init(eth); @@ -516,7 +523,7 @@ static int airoha_fe_init(struct airoha_eth *eth) airoha_fe_set(eth, REG_FE_CPORT_CFG, FE_CPORT_PORT_XFC_MASK); /* default aging mode for mbi unlock issue */ - airoha_fe_rmw(eth, REG_GDM2_CHN_RLS, + airoha_fe_rmw(eth, REG_GDM_CHN_RLS(2), MBI_RX_AGE_SEL_MASK | MBI_TX_AGE_SEL_MASK, FIELD_PREP(MBI_RX_AGE_SEL_MASK, 3) | FIELD_PREP(MBI_TX_AGE_SEL_MASK, 3)); @@ -524,25 +531,6 @@ static int airoha_fe_init(struct airoha_eth *eth) /* disable IFC by default */ airoha_fe_clear(eth, REG_FE_CSR_IFC_CFG, FE_IFC_EN_MASK); - airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(0), - FIELD_PREP(DFT_CPORT_MASK(7), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(6), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(5), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(4), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(3), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(2), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(1), FE_PSE_PORT_CDM1) | - FIELD_PREP(DFT_CPORT_MASK(0), FE_PSE_PORT_CDM1)); - airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(1), - FIELD_PREP(DFT_CPORT_MASK(7), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(6), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(5), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(4), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(3), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(2), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(1), FE_PSE_PORT_CDM2) | - FIELD_PREP(DFT_CPORT_MASK(0), FE_PSE_PORT_CDM2)); - /* enable 1:N vlan action, init vlan table */ airoha_fe_set(eth, REG_MC_VLAN_EN, MC_VLAN_EN_MASK); @@ -904,19 +892,13 @@ static int airoha_qdma_tx_napi_poll(struct napi_struct *napi, int budget) dma_unmap_single(eth->dev, e->dma_addr, e->dma_len, DMA_TO_DEVICE); - memset(e, 0, sizeof(*e)); + e->dma_addr = 0; + list_add_tail(&e->list, &q->tx_list); + WRITE_ONCE(desc->msg0, 0); WRITE_ONCE(desc->msg1, 0); q->queued--; - /* completion ring can report out-of-order indexes if hw QoS - * is enabled and packets with different priority are queued - * to same DMA ring. Take into account possible out-of-order - * reports incrementing DMA ring tail pointer - */ - while (q->tail != q->head && !q->entry[q->tail].dma_addr) - q->tail = (q->tail + 1) % q->ndesc; - if (skb) { u16 queue = skb_get_queue_mapping(skb); struct netdev_queue *txq; @@ -961,6 +943,7 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, q->ndesc = size; q->qdma = qdma; q->free_thr = 1 + MAX_SKB_FRAGS; + INIT_LIST_HEAD(&q->tx_list); q->entry = devm_kzalloc(eth->dev, q->ndesc * sizeof(*q->entry), GFP_KERNEL); @@ -973,9 +956,9 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, return -ENOMEM; for (i = 0; i < q->ndesc; i++) { - u32 val; + u32 val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1); - val = FIELD_PREP(QDMA_DESC_DONE_MASK, 1); + list_add_tail(&q->entry[i].list, &q->tx_list); WRITE_ONCE(q->desc[i].ctrl, cpu_to_le32(val)); } @@ -985,9 +968,9 @@ static int airoha_qdma_init_tx_queue(struct airoha_queue *q, airoha_qdma_wr(qdma, REG_TX_RING_BASE(qid), dma_addr); airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, - FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); + FIELD_PREP(TX_RING_CPU_IDX_MASK, 0)); airoha_qdma_rmw(qdma, REG_TX_DMA_IDX(qid), TX_RING_DMA_IDX_MASK, - FIELD_PREP(TX_RING_DMA_IDX_MASK, q->head)); + FIELD_PREP(TX_RING_DMA_IDX_MASK, 0)); return 0; } @@ -1043,17 +1026,21 @@ static int airoha_qdma_init_tx(struct airoha_qdma *qdma) static void airoha_qdma_cleanup_tx_queue(struct airoha_queue *q) { struct airoha_eth *eth = q->qdma->eth; + int i; spin_lock_bh(&q->lock); - while (q->queued) { - struct airoha_queue_entry *e = &q->entry[q->tail]; + for (i = 0; i < q->ndesc; i++) { + struct airoha_queue_entry *e = &q->entry[i]; + + if (!e->dma_addr) + continue; dma_unmap_single(eth->dev, e->dma_addr, e->dma_len, DMA_TO_DEVICE); dev_kfree_skb_any(e->skb); + e->dma_addr = 0; e->skb = NULL; - - q->tail = (q->tail + 1) % q->ndesc; + list_add_tail(&e->list, &q->tx_list); q->queued--; } spin_unlock_bh(&q->lock); @@ -1387,8 +1374,7 @@ static int airoha_hw_init(struct platform_device *pdev, int err, i; /* disable xsi */ - err = reset_control_bulk_assert(ARRAY_SIZE(eth->xsi_rsts), - eth->xsi_rsts); + err = reset_control_bulk_assert(eth->soc->num_xsi_rsts, eth->xsi_rsts); if (err) return err; @@ -1695,19 +1681,23 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p) return 0; } -static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) +static int airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) { - u32 pse_port = port->id == 3 ? FE_PSE_PORT_GDM3 : FE_PSE_PORT_GDM4; struct airoha_eth *eth = port->qdma->eth; - u32 chan = port->id == 3 ? 4 : 0; + u32 val, pse_port, chan, nbq; + int src_port; /* Forward the traffic to the proper GDM port */ + pse_port = port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 + : FE_PSE_PORT_GDM4; airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port); - airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC); + airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC_MASK); /* Enable GDM2 loopback */ airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff); airoha_fe_wr(eth, REG_GDM_RXCHN_EN(2), 0xffff); + + chan = port->id == AIROHA_GDM3_IDX ? airoha_is_7581(eth) ? 4 : 3 : 0; airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(2), LPBK_CHAN_MASK | LPBK_MODE_MASK | LPBK_EN_MASK, FIELD_PREP(LPBK_CHAN_MASK, chan) | @@ -1722,36 +1712,36 @@ static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port) airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2)); airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2)); - if (port->id == 3) { - /* FIXME: handle XSI_PCE1_PORT */ - airoha_fe_rmw(eth, REG_FE_WAN_PORT, - WAN1_EN_MASK | WAN1_MASK | WAN0_MASK, - FIELD_PREP(WAN0_MASK, HSGMII_LAN_PCIE0_SRCPORT)); - airoha_fe_rmw(eth, - REG_SP_DFT_CPORT(HSGMII_LAN_PCIE0_SRCPORT >> 3), - SP_CPORT_PCIE0_MASK, - FIELD_PREP(SP_CPORT_PCIE0_MASK, - FE_PSE_PORT_CDM2)); - } else { - /* FIXME: handle XSI_USB_PORT */ + /* XXX: handle XSI_USB_PORT and XSI_PCE1_PORT */ + nbq = port->id == AIROHA_GDM3_IDX && airoha_is_7581(eth) ? 4 : 0; + src_port = eth->soc->ops.get_src_port_id(port, nbq); + if (src_port < 0) + return src_port; + + airoha_fe_rmw(eth, REG_FE_WAN_PORT, + WAN1_EN_MASK | WAN1_MASK | WAN0_MASK, + FIELD_PREP(WAN0_MASK, src_port)); + val = src_port & SP_CPORT_DFT_MASK; + airoha_fe_rmw(eth, + REG_SP_DFT_CPORT(src_port >> fls(SP_CPORT_DFT_MASK)), + SP_CPORT_MASK(val), + FE_PSE_PORT_CDM2 << __ffs(SP_CPORT_MASK(val))); + + if (port->id != AIROHA_GDM3_IDX && airoha_is_7581(eth)) airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6, FC_ID_OF_SRC_PORT24_MASK, FIELD_PREP(FC_ID_OF_SRC_PORT24_MASK, 2)); - airoha_fe_rmw(eth, REG_FE_WAN_PORT, - WAN1_EN_MASK | WAN1_MASK | WAN0_MASK, - FIELD_PREP(WAN0_MASK, HSGMII_LAN_ETH_SRCPORT)); - airoha_fe_rmw(eth, - REG_SP_DFT_CPORT(HSGMII_LAN_ETH_SRCPORT >> 3), - SP_CPORT_ETH_MASK, - FIELD_PREP(SP_CPORT_ETH_MASK, FE_PSE_PORT_CDM2)); - } + + return 0; } static int airoha_dev_init(struct net_device *dev) { struct airoha_gdm_port *port = netdev_priv(dev); - struct airoha_eth *eth = port->qdma->eth; - u32 pse_port; + struct airoha_qdma *qdma = port->qdma; + struct airoha_eth *eth = qdma->eth; + u32 pse_port, fe_cpu_port; + u8 ppe_id; airoha_set_macaddr(port, dev->dev_addr); @@ -1759,18 +1749,37 @@ static int airoha_dev_init(struct net_device *dev) case 3: case 4: /* If GDM2 is active we can't enable loopback */ - if (!eth->ports[1]) - airhoha_set_gdm2_loopback(port); + if (!eth->ports[1]) { + int err; + + err = airhoha_set_gdm2_loopback(port); + if (err) + return err; + } fallthrough; case 2: - pse_port = FE_PSE_PORT_PPE2; - break; - default: + if (airoha_ppe_is_enabled(eth, 1)) { + /* For PPE2 always use secondary cpu port. */ + fe_cpu_port = FE_PSE_PORT_CDM2; + pse_port = FE_PSE_PORT_PPE2; + break; + } + fallthrough; + default: { + u8 qdma_id = qdma - ð->qdma[0]; + + /* For PPE1 select cpu port according to the running QDMA. */ + fe_cpu_port = qdma_id ? FE_PSE_PORT_CDM2 : FE_PSE_PORT_CDM1; pse_port = FE_PSE_PORT_PPE1; break; } + } airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(port->id), pse_port); + ppe_id = pse_port == FE_PSE_PORT_PPE2 ? 1 : 0; + airoha_fe_rmw(eth, REG_PPE_DFT_CPORT0(ppe_id), + DFT_CPORT_MASK(port->id), + fe_cpu_port << __ffs(DFT_CPORT_MASK(port->id))); return 0; } @@ -1873,18 +1882,20 @@ static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev) #endif } -static bool airoha_dev_tx_queue_busy(struct airoha_queue *q, u32 nr_frags) +static int airoha_get_fe_port(struct airoha_gdm_port *port) { - u32 tail = q->tail <= q->head ? q->tail + q->ndesc : q->tail; - u32 index = q->head + nr_frags; + struct airoha_qdma *qdma = port->qdma; + struct airoha_eth *eth = qdma->eth; - /* completion napi can free out-of-order tx descriptors if hw QoS is - * enabled and packets with different priorities are queued to the same - * DMA ring. Take into account possible out-of-order reports checking - * if the tx queue is full using circular buffer head/tail pointers - * instead of the number of queued packets. - */ - return index >= tail; + switch (eth->soc->version) { + case 0x7583: + return port->id == AIROHA_GDM3_IDX ? FE_PSE_PORT_GDM3 + : port->id; + case 0x7581: + default: + return port->id == AIROHA_GDM4_IDX ? FE_PSE_PORT_GDM4 + : port->id; + } } static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, @@ -1893,8 +1904,10 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, struct airoha_gdm_port *port = netdev_priv(dev); struct airoha_qdma *qdma = port->qdma; u32 nr_frags, tag, msg0, msg1, len; + struct airoha_queue_entry *e; struct netdev_queue *txq; struct airoha_queue *q; + LIST_HEAD(tx_list); void *data; int i, qid; u16 index; @@ -1927,7 +1940,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, } } - fport = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id; + fport = airoha_get_fe_port(port); msg1 = FIELD_PREP(QDMA_ETH_TXMSG_FPORT_MASK, fport) | FIELD_PREP(QDMA_ETH_TXMSG_METER_MASK, 0x7f); @@ -1940,7 +1953,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, txq = netdev_get_tx_queue(dev, qid); nr_frags = 1 + skb_shinfo(skb)->nr_frags; - if (airoha_dev_tx_queue_busy(q, nr_frags)) { + if (q->queued + nr_frags >= q->ndesc) { /* not enough space in the queue */ netif_tx_stop_queue(txq); spin_unlock_bh(&q->lock); @@ -1949,11 +1962,13 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, len = skb_headlen(skb); data = skb->data; - index = q->head; + + e = list_first_entry(&q->tx_list, struct airoha_queue_entry, + list); + index = e - q->entry; for (i = 0; i < nr_frags; i++) { struct airoha_qdma_desc *desc = &q->desc[index]; - struct airoha_queue_entry *e = &q->entry[index]; skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; dma_addr_t addr; u32 val; @@ -1963,7 +1978,14 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, if (unlikely(dma_mapping_error(dev->dev.parent, addr))) goto error_unmap; - index = (index + 1) % q->ndesc; + list_move_tail(&e->list, &tx_list); + e->skb = i ? NULL : skb; + e->dma_addr = addr; + e->dma_len = len; + + e = list_first_entry(&q->tx_list, struct airoha_queue_entry, + list); + index = e - q->entry; val = FIELD_PREP(QDMA_DESC_LEN_MASK, len); if (i < nr_frags - 1) @@ -1976,15 +1998,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, WRITE_ONCE(desc->msg1, cpu_to_le32(msg1)); WRITE_ONCE(desc->msg2, cpu_to_le32(0xffff)); - e->skb = i ? NULL : skb; - e->dma_addr = addr; - e->dma_len = len; - data = skb_frag_address(frag); len = skb_frag_size(frag); } - - q->head = index; q->queued += i; skb_tx_timestamp(skb); @@ -1993,7 +2009,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, if (netif_xmit_stopped(txq) || !netdev_xmit_more()) airoha_qdma_rmw(qdma, REG_TX_CPU_IDX(qid), TX_RING_CPU_IDX_MASK, - FIELD_PREP(TX_RING_CPU_IDX_MASK, q->head)); + FIELD_PREP(TX_RING_CPU_IDX_MASK, index)); if (q->ndesc - q->queued < q->free_thr) netif_tx_stop_queue(txq); @@ -2003,10 +2019,13 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb, return NETDEV_TX_OK; error_unmap: - for (i--; i >= 0; i--) { - index = (q->head + i) % q->ndesc; - dma_unmap_single(dev->dev.parent, q->entry[index].dma_addr, - q->entry[index].dma_len, DMA_TO_DEVICE); + while (!list_empty(&tx_list)) { + e = list_first_entry(&tx_list, struct airoha_queue_entry, + list); + dma_unmap_single(dev->dev.parent, e->dma_addr, e->dma_len, + DMA_TO_DEVICE); + e->dma_addr = 0; + list_move_tail(&e->list, &q->tx_list); } spin_unlock_bh(&q->lock); @@ -2036,8 +2055,12 @@ static void airoha_ethtool_get_mac_stats(struct net_device *dev, airoha_update_hw_stats(port); do { start = u64_stats_fetch_begin(&port->stats.syncp); + stats->FramesTransmittedOK = port->stats.tx_ok_pkts; + stats->OctetsTransmittedOK = port->stats.tx_ok_bytes; stats->MulticastFramesXmittedOK = port->stats.tx_multicast; stats->BroadcastFramesXmittedOK = port->stats.tx_broadcast; + stats->FramesReceivedOK = port->stats.rx_ok_pkts; + stats->OctetsReceivedOK = port->stats.rx_ok_bytes; stats->BroadcastFramesReceivedOK = port->stats.rx_broadcast; } while (u64_stats_fetch_retry(&port->stats.syncp, start)); } @@ -2780,6 +2803,7 @@ static const struct ethtool_ops airoha_ethtool_ops = { .get_drvinfo = airoha_ethtool_get_drvinfo, .get_eth_mac_stats = airoha_ethtool_get_mac_stats, .get_rmon_stats = airoha_ethtool_get_rmon_stats, + .get_link = ethtool_op_get_link, }; static int airoha_metadata_dst_alloc(struct airoha_gdm_port *port) @@ -2917,6 +2941,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, static int airoha_probe(struct platform_device *pdev) { + struct reset_control_bulk_data *xsi_rsts; struct device_node *np; struct airoha_eth *eth; int i, err; @@ -2925,6 +2950,10 @@ static int airoha_probe(struct platform_device *pdev) if (!eth) return -ENOMEM; + eth->soc = of_device_get_match_data(&pdev->dev); + if (!eth->soc) + return -EINVAL; + eth->dev = &pdev->dev; err = dma_set_mask_and_coherent(eth->dev, DMA_BIT_MASK(32)); @@ -2949,13 +2978,18 @@ static int airoha_probe(struct platform_device *pdev) return err; } - eth->xsi_rsts[0].id = "xsi-mac"; - eth->xsi_rsts[1].id = "hsi0-mac"; - eth->xsi_rsts[2].id = "hsi1-mac"; - eth->xsi_rsts[3].id = "hsi-mac"; - eth->xsi_rsts[4].id = "xfp-mac"; + xsi_rsts = devm_kcalloc(eth->dev, + eth->soc->num_xsi_rsts, sizeof(*xsi_rsts), + GFP_KERNEL); + if (!xsi_rsts) + return -ENOMEM; + + eth->xsi_rsts = xsi_rsts; + for (i = 0; i < eth->soc->num_xsi_rsts; i++) + eth->xsi_rsts[i].id = eth->soc->xsi_rsts_names[i]; + err = devm_reset_control_bulk_get_exclusive(eth->dev, - ARRAY_SIZE(eth->xsi_rsts), + eth->soc->num_xsi_rsts, eth->xsi_rsts); if (err) { dev_err(eth->dev, "failed to get bulk xsi reset lines\n"); @@ -3043,8 +3077,90 @@ static void airoha_remove(struct platform_device *pdev) platform_set_drvdata(pdev, NULL); } +static const char * const en7581_xsi_rsts_names[] = { + "xsi-mac", + "hsi0-mac", + "hsi1-mac", + "hsi-mac", + "xfp-mac", +}; + +static int airoha_en7581_get_src_port_id(struct airoha_gdm_port *port, int nbq) +{ + switch (port->id) { + case 3: + /* 7581 SoC supports PCIe serdes on GDM3 port */ + if (nbq == 4) + return HSGMII_LAN_7581_PCIE0_SRCPORT; + if (nbq == 5) + return HSGMII_LAN_7581_PCIE1_SRCPORT; + break; + case 4: + /* 7581 SoC supports eth and usb serdes on GDM4 port */ + if (!nbq) + return HSGMII_LAN_7581_ETH_SRCPORT; + if (nbq == 1) + return HSGMII_LAN_7581_USB_SRCPORT; + break; + default: + break; + } + + return -EINVAL; +} + +static const char * const an7583_xsi_rsts_names[] = { + "xsi-mac", + "hsi0-mac", + "hsi1-mac", + "xfp-mac", +}; + +static int airoha_an7583_get_src_port_id(struct airoha_gdm_port *port, int nbq) +{ + switch (port->id) { + case 3: + /* 7583 SoC supports eth serdes on GDM3 port */ + if (!nbq) + return HSGMII_LAN_7583_ETH_SRCPORT; + break; + case 4: + /* 7583 SoC supports PCIe and USB serdes on GDM4 port */ + if (!nbq) + return HSGMII_LAN_7583_PCIE_SRCPORT; + if (nbq == 1) + return HSGMII_LAN_7583_USB_SRCPORT; + break; + default: + break; + } + + return -EINVAL; +} + +static const struct airoha_eth_soc_data en7581_soc_data = { + .version = 0x7581, + .xsi_rsts_names = en7581_xsi_rsts_names, + .num_xsi_rsts = ARRAY_SIZE(en7581_xsi_rsts_names), + .num_ppe = 2, + .ops = { + .get_src_port_id = airoha_en7581_get_src_port_id, + }, +}; + +static const struct airoha_eth_soc_data an7583_soc_data = { + .version = 0x7583, + .xsi_rsts_names = an7583_xsi_rsts_names, + .num_xsi_rsts = ARRAY_SIZE(an7583_xsi_rsts_names), + .num_ppe = 1, + .ops = { + .get_src_port_id = airoha_an7583_get_src_port_id, + }, +}; + static const struct of_device_id of_airoha_match[] = { - { .compatible = "airoha,en7581-eth" }, + { .compatible = "airoha,en7581-eth", .data = &en7581_soc_data }, + { .compatible = "airoha,an7583-eth", .data = &an7583_soc_data }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, of_airoha_match); diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h index cd13c1c1224f6..fbbc58133364b 100644 --- a/drivers/net/ethernet/airoha/airoha_eth.h +++ b/drivers/net/ethernet/airoha/airoha_eth.h @@ -21,7 +21,6 @@ #define AIROHA_MAX_NUM_IRQ_BANKS 4 #define AIROHA_MAX_DSA_PORTS 7 #define AIROHA_MAX_NUM_RSTS 3 -#define AIROHA_MAX_NUM_XSI_RSTS 5 #define AIROHA_MAX_MTU 9216 #define AIROHA_MAX_PACKET_SIZE 2048 #define AIROHA_NUM_QOS_CHANNELS 4 @@ -48,20 +47,9 @@ #define QDMA_METER_IDX(_n) ((_n) & 0xff) #define QDMA_METER_GROUP(_n) (((_n) >> 8) & 0x3) -#define PPE_NUM 2 -#define PPE1_SRAM_NUM_ENTRIES (8 * 1024) -#define PPE_SRAM_NUM_ENTRIES (2 * PPE1_SRAM_NUM_ENTRIES) -#ifdef CONFIG_NET_AIROHA_FLOW_STATS -#define PPE1_STATS_NUM_ENTRIES (4 * 1024) -#else -#define PPE1_STATS_NUM_ENTRIES 0 -#endif /* CONFIG_NET_AIROHA_FLOW_STATS */ -#define PPE_STATS_NUM_ENTRIES (2 * PPE1_STATS_NUM_ENTRIES) -#define PPE1_SRAM_NUM_DATA_ENTRIES (PPE1_SRAM_NUM_ENTRIES - PPE1_STATS_NUM_ENTRIES) -#define PPE_SRAM_NUM_DATA_ENTRIES (2 * PPE1_SRAM_NUM_DATA_ENTRIES) +#define PPE_SRAM_NUM_ENTRIES (8 * 1024) +#define PPE_STATS_NUM_ENTRIES (4 * 1024) #define PPE_DRAM_NUM_ENTRIES (16 * 1024) -#define PPE_NUM_ENTRIES (PPE_SRAM_NUM_ENTRIES + PPE_DRAM_NUM_ENTRIES) -#define PPE_HASH_MASK (PPE_NUM_ENTRIES - 1) #define PPE_ENTRY_SIZE 80 #define PPE_RAM_NUM_ENTRIES_SHIFT(_n) (__ffs((_n) >> 10)) @@ -79,10 +67,16 @@ enum { }; enum { - HSGMII_LAN_PCIE0_SRCPORT = 0x16, - HSGMII_LAN_PCIE1_SRCPORT, - HSGMII_LAN_ETH_SRCPORT, - HSGMII_LAN_USB_SRCPORT, + HSGMII_LAN_7581_PCIE0_SRCPORT = 0x16, + HSGMII_LAN_7581_PCIE1_SRCPORT, + HSGMII_LAN_7581_ETH_SRCPORT, + HSGMII_LAN_7581_USB_SRCPORT, +}; + +enum { + HSGMII_LAN_7583_ETH_SRCPORT = 0x16, + HSGMII_LAN_7583_PCIE_SRCPORT = 0x18, + HSGMII_LAN_7583_USB_SRCPORT, }; enum { @@ -111,6 +105,13 @@ enum { CRSN_25 = 0x19, }; +enum airoha_gdm_index { + AIROHA_GDM1_IDX = 1, + AIROHA_GDM2_IDX = 2, + AIROHA_GDM3_IDX = 3, + AIROHA_GDM4_IDX = 4, +}; + enum { FE_PSE_PORT_CDM1, FE_PSE_PORT_GDM1, @@ -168,7 +169,10 @@ enum trtcm_param { struct airoha_queue_entry { union { void *buf; - struct sk_buff *skb; + struct { + struct list_head list; + struct sk_buff *skb; + }; }; dma_addr_t dma_addr; u16 dma_len; @@ -192,6 +196,8 @@ struct airoha_queue { struct napi_struct napi; struct page_pool *page_pool; struct sk_buff *skb; + + struct list_head tx_list; }; struct airoha_tx_irq_queue { @@ -554,7 +560,7 @@ struct airoha_ppe { struct rhashtable l2_flows; struct hlist_head *foe_flow; - u16 foe_check_time[PPE_NUM_ENTRIES]; + u16 *foe_check_time; struct airoha_foe_stats *foe_stats; dma_addr_t foe_stats_dma; @@ -562,9 +568,21 @@ struct airoha_ppe { struct dentry *debugfs_dir; }; +struct airoha_eth_soc_data { + u16 version; + const char * const *xsi_rsts_names; + int num_xsi_rsts; + int num_ppe; + struct { + int (*get_src_port_id)(struct airoha_gdm_port *port, int nbq); + } ops; +}; + struct airoha_eth { struct device *dev; + const struct airoha_eth_soc_data *soc; + unsigned long state; void __iomem *fe_regs; @@ -574,7 +592,7 @@ struct airoha_eth { struct rhashtable flow_table; struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS]; - struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS]; + struct reset_control_bulk_data *xsi_rsts; struct net_device *napi_dev; @@ -617,15 +635,27 @@ static inline bool airhoa_is_lan_gdm_port(struct airoha_gdm_port *port) return port->id == 1; } +static inline bool airoha_is_7581(struct airoha_eth *eth) +{ + return eth->soc->version == 0x7581; +} + +static inline bool airoha_is_7583(struct airoha_eth *eth) +{ + return eth->soc->version == 0x7583; +} + bool airoha_is_valid_gdm_port(struct airoha_eth *eth, struct airoha_gdm_port *port); +bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index); void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb, u16 hash, bool rx_wlan); int airoha_ppe_setup_tc_block_cb(struct airoha_ppe_dev *dev, void *type_data); int airoha_ppe_init(struct airoha_eth *eth); void airoha_ppe_deinit(struct airoha_eth *eth); void airoha_ppe_init_upd_mem(struct airoha_gdm_port *port); +u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe); struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe, u32 hash); void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash, diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c index 8c883f2b2d36b..68b7f9684dc7f 100644 --- a/drivers/net/ethernet/airoha/airoha_npu.c +++ b/drivers/net/ethernet/airoha/airoha_npu.c @@ -16,6 +16,8 @@ #define NPU_EN7581_FIRMWARE_DATA "airoha/en7581_npu_data.bin" #define NPU_EN7581_FIRMWARE_RV32 "airoha/en7581_npu_rv32.bin" +#define NPU_AN7583_FIRMWARE_DATA "airoha/an7583_npu_data.bin" +#define NPU_AN7583_FIRMWARE_RV32 "airoha/an7583_npu_rv32.bin" #define NPU_EN7581_FIRMWARE_RV32_MAX_SIZE 0x200000 #define NPU_EN7581_FIRMWARE_DATA_MAX_SIZE 0x10000 #define NPU_DUMP_SIZE 512 @@ -103,6 +105,16 @@ enum { QDMA_WAN_PON_XDSL, }; +struct airoha_npu_fw { + const char *name; + int max_size; +}; + +struct airoha_npu_soc_data { + struct airoha_npu_fw fw_rv32; + struct airoha_npu_fw fw_data; +}; + #define MBOX_MSG_FUNC_ID GENMASK(14, 11) #define MBOX_MSG_STATIC_BUF BIT(5) #define MBOX_MSG_STATUS GENMASK(4, 2) @@ -182,49 +194,53 @@ static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id, return ret; } -static int airoha_npu_run_firmware(struct device *dev, void __iomem *base, - struct resource *res) +static int airoha_npu_load_firmware(struct device *dev, void __iomem *addr, + const struct airoha_npu_fw *fw_info) { const struct firmware *fw; - void __iomem *addr; int ret; - ret = request_firmware(&fw, NPU_EN7581_FIRMWARE_RV32, dev); + ret = request_firmware(&fw, fw_info->name, dev); if (ret) return ret == -ENOENT ? -EPROBE_DEFER : ret; - if (fw->size > NPU_EN7581_FIRMWARE_RV32_MAX_SIZE) { + if (fw->size > fw_info->max_size) { dev_err(dev, "%s: fw size too overlimit (%zu)\n", - NPU_EN7581_FIRMWARE_RV32, fw->size); + fw_info->name, fw->size); ret = -E2BIG; goto out; } - addr = devm_ioremap_resource(dev, res); - if (IS_ERR(addr)) { - ret = PTR_ERR(addr); - goto out; - } - memcpy_toio(addr, fw->data, fw->size); +out: release_firmware(fw); - ret = request_firmware(&fw, NPU_EN7581_FIRMWARE_DATA, dev); - if (ret) - return ret == -ENOENT ? -EPROBE_DEFER : ret; + return ret; +} - if (fw->size > NPU_EN7581_FIRMWARE_DATA_MAX_SIZE) { - dev_err(dev, "%s: fw size too overlimit (%zu)\n", - NPU_EN7581_FIRMWARE_DATA, fw->size); - ret = -E2BIG; - goto out; - } +static int airoha_npu_run_firmware(struct device *dev, void __iomem *base, + struct resource *res) +{ + const struct airoha_npu_soc_data *soc; + void __iomem *addr; + int ret; - memcpy_toio(base + REG_NPU_LOCAL_SRAM, fw->data, fw->size); -out: - release_firmware(fw); + soc = of_device_get_match_data(dev); + if (!soc) + return -EINVAL; - return ret; + addr = devm_ioremap_resource(dev, res); + if (IS_ERR(addr)) + return PTR_ERR(addr); + + /* Load rv32 npu firmware */ + ret = airoha_npu_load_firmware(dev, addr, &soc->fw_rv32); + if (ret) + return ret; + + /* Load data npu firmware */ + return airoha_npu_load_firmware(dev, base + REG_NPU_LOCAL_SRAM, + &soc->fw_data); } static irqreturn_t airoha_npu_mbox_handler(int irq, void *npu_instance) @@ -597,8 +613,31 @@ void airoha_npu_put(struct airoha_npu *npu) } EXPORT_SYMBOL_GPL(airoha_npu_put); +static const struct airoha_npu_soc_data en7581_npu_soc_data = { + .fw_rv32 = { + .name = NPU_EN7581_FIRMWARE_RV32, + .max_size = NPU_EN7581_FIRMWARE_RV32_MAX_SIZE, + }, + .fw_data = { + .name = NPU_EN7581_FIRMWARE_DATA, + .max_size = NPU_EN7581_FIRMWARE_DATA_MAX_SIZE, + }, +}; + +static const struct airoha_npu_soc_data an7583_npu_soc_data = { + .fw_rv32 = { + .name = NPU_AN7583_FIRMWARE_RV32, + .max_size = NPU_EN7581_FIRMWARE_RV32_MAX_SIZE, + }, + .fw_data = { + .name = NPU_AN7583_FIRMWARE_DATA, + .max_size = NPU_EN7581_FIRMWARE_DATA_MAX_SIZE, + }, +}; + static const struct of_device_id of_airoha_npu_match[] = { - { .compatible = "airoha,en7581-npu" }, + { .compatible = "airoha,en7581-npu", .data = &en7581_npu_soc_data }, + { .compatible = "airoha,an7583-npu", .data = &an7583_npu_soc_data }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, of_airoha_npu_match); @@ -737,6 +776,8 @@ module_platform_driver(airoha_npu_driver); MODULE_FIRMWARE(NPU_EN7581_FIRMWARE_DATA); MODULE_FIRMWARE(NPU_EN7581_FIRMWARE_RV32); +MODULE_FIRMWARE(NPU_AN7583_FIRMWARE_DATA); +MODULE_FIRMWARE(NPU_AN7583_FIRMWARE_RV32); MODULE_LICENSE("GPL"); MODULE_AUTHOR("Lorenzo Bianconi "); MODULE_DESCRIPTION("Airoha Network Processor Unit driver"); diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c index 691361b254075..0caabb0c3aa06 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe.c +++ b/drivers/net/ethernet/airoha/airoha_ppe.c @@ -32,9 +32,50 @@ static const struct rhashtable_params airoha_l2_flow_table_params = { .automatic_shrinking = true, }; -static bool airoha_ppe2_is_enabled(struct airoha_eth *eth) +static int airoha_ppe_get_num_stats_entries(struct airoha_ppe *ppe) { - return airoha_fe_rr(eth, REG_PPE_GLO_CFG(1)) & PPE_GLO_CFG_EN_MASK; + if (!IS_ENABLED(CONFIG_NET_AIROHA_FLOW_STATS)) + return -EOPNOTSUPP; + + if (airoha_is_7583(ppe->eth)) + return -EOPNOTSUPP; + + return PPE_STATS_NUM_ENTRIES; +} + +static int airoha_ppe_get_total_num_stats_entries(struct airoha_ppe *ppe) +{ + int num_stats = airoha_ppe_get_num_stats_entries(ppe); + + if (num_stats > 0) { + struct airoha_eth *eth = ppe->eth; + + num_stats = num_stats * eth->soc->num_ppe; + } + + return num_stats; +} + +static u32 airoha_ppe_get_total_sram_num_entries(struct airoha_ppe *ppe) +{ + struct airoha_eth *eth = ppe->eth; + + return PPE_SRAM_NUM_ENTRIES * eth->soc->num_ppe; +} + +u32 airoha_ppe_get_total_num_entries(struct airoha_ppe *ppe) +{ + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); + + return sram_num_entries + PPE_DRAM_NUM_ENTRIES; +} + +bool airoha_ppe_is_enabled(struct airoha_eth *eth, int index) +{ + if (index >= eth->soc->num_ppe) + return false; + + return airoha_fe_rr(eth, REG_PPE_GLO_CFG(index)) & PPE_GLO_CFG_EN_MASK; } static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe) @@ -46,14 +87,22 @@ static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe) static void airoha_ppe_hw_init(struct airoha_ppe *ppe) { - u32 sram_tb_size, sram_num_entries, dram_num_entries; + u32 sram_ppe_num_data_entries = PPE_SRAM_NUM_ENTRIES, sram_num_entries; + u32 sram_tb_size, dram_num_entries; struct airoha_eth *eth = ppe->eth; - int i; + int i, sram_num_stats_entries; - sram_tb_size = PPE_SRAM_NUM_ENTRIES * sizeof(struct airoha_foe_entry); + sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); + sram_tb_size = sram_num_entries * sizeof(struct airoha_foe_entry); dram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(PPE_DRAM_NUM_ENTRIES); - for (i = 0; i < PPE_NUM; i++) { + sram_num_stats_entries = airoha_ppe_get_num_stats_entries(ppe); + if (sram_num_stats_entries > 0) + sram_ppe_num_data_entries -= sram_num_stats_entries; + sram_ppe_num_data_entries = + PPE_RAM_NUM_ENTRIES_SHIFT(sram_ppe_num_data_entries); + + for (i = 0; i < eth->soc->num_ppe; i++) { int p; airoha_fe_wr(eth, REG_PPE_TB_BASE(i), @@ -85,10 +134,16 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) airoha_fe_rmw(eth, REG_PPE_TB_CFG(i), PPE_TB_CFG_SEARCH_MISS_MASK | + PPE_SRAM_TB_NUM_ENTRY_MASK | + PPE_DRAM_TB_NUM_ENTRY_MASK | PPE_TB_CFG_KEEPALIVE_MASK | PPE_TB_ENTRY_SIZE_MASK, FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) | - FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0)); + FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0) | + FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, + sram_ppe_num_data_entries) | + FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, + dram_num_entries)); airoha_fe_wr(eth, REG_PPE_HASH_SEED(i), PPE_HASH_SEED); @@ -101,35 +156,6 @@ static void airoha_ppe_hw_init(struct airoha_ppe *ppe) FIELD_PREP(FP1_EGRESS_MTU_MASK, AIROHA_MAX_MTU)); } - - if (airoha_ppe2_is_enabled(eth)) { - sram_num_entries = - PPE_RAM_NUM_ENTRIES_SHIFT(PPE1_SRAM_NUM_DATA_ENTRIES); - airoha_fe_rmw(eth, REG_PPE_TB_CFG(0), - PPE_SRAM_TB_NUM_ENTRY_MASK | - PPE_DRAM_TB_NUM_ENTRY_MASK, - FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, - sram_num_entries) | - FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, - dram_num_entries)); - airoha_fe_rmw(eth, REG_PPE_TB_CFG(1), - PPE_SRAM_TB_NUM_ENTRY_MASK | - PPE_DRAM_TB_NUM_ENTRY_MASK, - FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, - sram_num_entries) | - FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, - dram_num_entries)); - } else { - sram_num_entries = - PPE_RAM_NUM_ENTRIES_SHIFT(PPE_SRAM_NUM_DATA_ENTRIES); - airoha_fe_rmw(eth, REG_PPE_TB_CFG(0), - PPE_SRAM_TB_NUM_ENTRY_MASK | - PPE_DRAM_TB_NUM_ENTRY_MASK, - FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK, - sram_num_entries) | - FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK, - dram_num_entries)); - } } static void airoha_ppe_flow_mangle_eth(const struct flow_action_entry *act, void *eth) @@ -282,7 +308,7 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth, if (!airoha_is_valid_gdm_port(eth, port)) return -EINVAL; - if (dsa_port >= 0) + if (dsa_port >= 0 || eth->ports[1]) pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id; else @@ -428,9 +454,11 @@ static int airoha_ppe_foe_entry_set_ipv6_tuple(struct airoha_foe_entry *hwe, return 0; } -static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe) +static u32 airoha_ppe_foe_get_entry_hash(struct airoha_ppe *ppe, + struct airoha_foe_entry *hwe) { int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1); + u32 ppe_hash_mask = airoha_ppe_get_total_num_entries(ppe) - 1; u32 hash, hv1, hv2, hv3; switch (type) { @@ -468,25 +496,31 @@ static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe) case PPE_PKT_TYPE_IPV6_6RD: default: WARN_ON_ONCE(1); - return PPE_HASH_MASK; + return ppe_hash_mask; } hash = (hv1 & hv2) | ((~hv1) & hv3); hash = (hash >> 24) | ((hash & 0xffffff) << 8); hash ^= hv1 ^ hv2 ^ hv3; hash ^= hash >> 16; - hash &= PPE_NUM_ENTRIES - 1; + hash &= ppe_hash_mask; return hash; } -static u32 airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, u32 hash) +static int airoha_ppe_foe_get_flow_stats_index(struct airoha_ppe *ppe, + u32 hash, u32 *index) { - if (!airoha_ppe2_is_enabled(ppe->eth)) - return hash; + int ppe_num_stats_entries; - return hash >= PPE_STATS_NUM_ENTRIES ? hash - PPE1_STATS_NUM_ENTRIES - : hash; + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return ppe_num_stats_entries; + + *index = hash >= ppe_num_stats_entries ? hash - PPE_STATS_NUM_ENTRIES + : hash; + + return 0; } static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe, @@ -500,9 +534,13 @@ static void airoha_ppe_foe_flow_stat_entry_reset(struct airoha_ppe *ppe, static void airoha_ppe_foe_flow_stats_reset(struct airoha_ppe *ppe, struct airoha_npu *npu) { - int i; + int i, ppe_num_stats_entries; + + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return; - for (i = 0; i < PPE_STATS_NUM_ENTRIES; i++) + for (i = 0; i < ppe_num_stats_entries; i++) airoha_ppe_foe_flow_stat_entry_reset(ppe, npu, i); } @@ -513,10 +551,17 @@ static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe, { int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1); u32 index, pse_port, val, *data, *ib2, *meter; + int ppe_num_stats_entries; u8 nbq; - index = airoha_ppe_foe_get_flow_stats_index(ppe, hash); - if (index >= PPE_STATS_NUM_ENTRIES) + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return; + + if (airoha_ppe_foe_get_flow_stats_index(ppe, hash, &index)) + return; + + if (index >= ppe_num_stats_entries) return; if (type == PPE_PKT_TYPE_BRIDGE) { @@ -557,17 +602,17 @@ static void airoha_ppe_foe_flow_stats_update(struct airoha_ppe *ppe, static struct airoha_foe_entry * airoha_ppe_foe_get_entry_locked(struct airoha_ppe *ppe, u32 hash) { + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); + lockdep_assert_held(&ppe_lock); - if (hash < PPE_SRAM_NUM_ENTRIES) { + if (hash < sram_num_entries) { u32 *hwe = ppe->foe + hash * sizeof(struct airoha_foe_entry); + bool ppe2 = hash >= PPE_SRAM_NUM_ENTRIES; struct airoha_eth *eth = ppe->eth; - bool ppe2; u32 val; int i; - ppe2 = airoha_ppe2_is_enabled(ppe->eth) && - hash >= PPE1_SRAM_NUM_ENTRIES; airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2), FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) | PPE_SRAM_CTRL_REQ_MASK); @@ -577,7 +622,8 @@ airoha_ppe_foe_get_entry_locked(struct airoha_ppe *ppe, u32 hash) REG_PPE_RAM_CTRL(ppe2))) return NULL; - for (i = 0; i < sizeof(struct airoha_foe_entry) / 4; i++) + for (i = 0; i < sizeof(struct airoha_foe_entry) / sizeof(*hwe); + i++) hwe[i] = airoha_fe_rr(eth, REG_PPE_RAM_ENTRY(ppe2, i)); } @@ -614,10 +660,32 @@ static bool airoha_ppe_foe_compare_entry(struct airoha_flow_table_entry *e, return !memcmp(&e->data.d, &hwe->d, len - sizeof(hwe->ib1)); } +static int airoha_ppe_foe_commit_sram_entry(struct airoha_ppe *ppe, u32 hash) +{ + struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe); + bool ppe2 = hash >= PPE_SRAM_NUM_ENTRIES; + u32 *ptr = (u32 *)hwe, val; + int i; + + for (i = 0; i < sizeof(*hwe) / sizeof(*ptr); i++) + airoha_fe_wr(ppe->eth, REG_PPE_RAM_ENTRY(ppe2, i), ptr[i]); + + wmb(); + airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2), + FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) | + PPE_SRAM_CTRL_WR_MASK | PPE_SRAM_CTRL_REQ_MASK); + + return read_poll_timeout_atomic(airoha_fe_rr, val, + val & PPE_SRAM_CTRL_ACK_MASK, + 10, 100, false, ppe->eth, + REG_PPE_RAM_CTRL(ppe2)); +} + static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe, struct airoha_foe_entry *e, u32 hash, bool rx_wlan) { + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe); u32 ts = airoha_ppe_get_timestamp(ppe); struct airoha_eth *eth = ppe->eth; @@ -642,14 +710,8 @@ static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe, if (!rx_wlan) airoha_ppe_foe_flow_stats_update(ppe, npu, hwe, hash); - if (hash < PPE_SRAM_NUM_ENTRIES) { - dma_addr_t addr = ppe->foe_dma + hash * sizeof(*hwe); - bool ppe2 = airoha_ppe2_is_enabled(eth) && - hash >= PPE1_SRAM_NUM_ENTRIES; - - err = npu->ops.ppe_foe_commit_entry(npu, addr, sizeof(*hwe), - hash, ppe2); - } + if (hash < sram_num_entries) + err = airoha_ppe_foe_commit_sram_entry(ppe, hash); unlock: rcu_read_unlock(); @@ -772,7 +834,7 @@ static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, if (state == AIROHA_FOE_STATE_BIND) goto unlock; - index = airoha_ppe_foe_get_entry_hash(hwe); + index = airoha_ppe_foe_get_entry_hash(ppe, hwe); hlist_for_each_entry_safe(e, n, &ppe->foe_flow[index], list) { if (e->type == FLOW_TYPE_L2_SUBFLOW) { state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1); @@ -832,7 +894,7 @@ static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe, if (type == PPE_PKT_TYPE_BRIDGE) return airoha_ppe_foe_l2_flow_commit_entry(ppe, e); - hash = airoha_ppe_foe_get_entry_hash(&e->data); + hash = airoha_ppe_foe_get_entry_hash(ppe, &e->data); e->type = FLOW_TYPE_L4; e->hash = 0xffff; @@ -1158,11 +1220,19 @@ static int airoha_ppe_flow_offload_destroy(struct airoha_eth *eth, void airoha_ppe_foe_entry_get_stats(struct airoha_ppe *ppe, u32 hash, struct airoha_foe_stats64 *stats) { - u32 index = airoha_ppe_foe_get_flow_stats_index(ppe, hash); struct airoha_eth *eth = ppe->eth; + int ppe_num_stats_entries; struct airoha_npu *npu; + u32 index; + + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries < 0) + return; - if (index >= PPE_STATS_NUM_ENTRIES) + if (airoha_ppe_foe_get_flow_stats_index(ppe, hash, &index)) + return; + + if (index >= ppe_num_stats_entries) return; rcu_read_lock(); @@ -1225,20 +1295,22 @@ static int airoha_ppe_flow_offload_cmd(struct airoha_eth *eth, return -EOPNOTSUPP; } -static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe, - struct airoha_npu *npu) +static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe) { - int i, sram_num_entries = PPE_SRAM_NUM_ENTRIES; + u32 sram_num_entries = airoha_ppe_get_total_sram_num_entries(ppe); struct airoha_foe_entry *hwe = ppe->foe; + int i, err = 0; - if (airoha_ppe2_is_enabled(ppe->eth)) - sram_num_entries = sram_num_entries / 2; + for (i = 0; i < sram_num_entries; i++) { + int err; - for (i = 0; i < sram_num_entries; i++) memset(&hwe[i], 0, sizeof(*hwe)); + err = airoha_ppe_foe_commit_sram_entry(ppe, i); + if (err) + break; + } - return npu->ops.ppe_flush_sram_entries(npu, ppe->foe_dma, - PPE_SRAM_NUM_ENTRIES); + return err; } static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth) @@ -1257,7 +1329,7 @@ static int airoha_ppe_offload_setup(struct airoha_eth *eth) { struct airoha_npu *npu = airoha_ppe_npu_get(eth); struct airoha_ppe *ppe = eth->ppe; - int err; + int err, ppe_num_stats_entries; if (IS_ERR(npu)) return PTR_ERR(npu); @@ -1266,18 +1338,15 @@ static int airoha_ppe_offload_setup(struct airoha_eth *eth) if (err) goto error_npu_put; - if (PPE_STATS_NUM_ENTRIES) { + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries > 0) { err = npu->ops.ppe_init_stats(npu, ppe->foe_stats_dma, - PPE_STATS_NUM_ENTRIES); + ppe_num_stats_entries); if (err) goto error_npu_put; } airoha_ppe_hw_init(ppe); - err = airoha_ppe_flush_sram_entries(ppe, npu); - if (err) - goto error_npu_put; - airoha_ppe_foe_flow_stats_reset(ppe, npu); rcu_assign_pointer(eth->npu, npu); @@ -1313,9 +1382,10 @@ void airoha_ppe_check_skb(struct airoha_ppe_dev *dev, struct sk_buff *skb, u16 hash, bool rx_wlan) { struct airoha_ppe *ppe = dev->priv; + u32 ppe_hash_mask = airoha_ppe_get_total_num_entries(ppe) - 1; u16 now, diff; - if (hash > PPE_HASH_MASK) + if (hash > ppe_hash_mask) return; now = (u16)jiffies; @@ -1405,8 +1475,9 @@ EXPORT_SYMBOL_GPL(airoha_ppe_put_dev); int airoha_ppe_init(struct airoha_eth *eth) { + int foe_size, err, ppe_num_stats_entries; + u32 ppe_num_entries; struct airoha_ppe *ppe; - int foe_size, err; ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL); if (!ppe) @@ -1415,24 +1486,25 @@ int airoha_ppe_init(struct airoha_eth *eth) ppe->dev.ops.setup_tc_block_cb = airoha_ppe_setup_tc_block_cb; ppe->dev.ops.check_skb = airoha_ppe_check_skb; ppe->dev.priv = ppe; + ppe->eth = eth; + eth->ppe = ppe; - foe_size = PPE_NUM_ENTRIES * sizeof(struct airoha_foe_entry); + ppe_num_entries = airoha_ppe_get_total_num_entries(ppe); + foe_size = ppe_num_entries * sizeof(struct airoha_foe_entry); ppe->foe = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_dma, GFP_KERNEL); if (!ppe->foe) return -ENOMEM; - ppe->eth = eth; - eth->ppe = ppe; - ppe->foe_flow = devm_kzalloc(eth->dev, - PPE_NUM_ENTRIES * sizeof(*ppe->foe_flow), + ppe_num_entries * sizeof(*ppe->foe_flow), GFP_KERNEL); if (!ppe->foe_flow) return -ENOMEM; - foe_size = PPE_STATS_NUM_ENTRIES * sizeof(*ppe->foe_stats); - if (foe_size) { + ppe_num_stats_entries = airoha_ppe_get_total_num_stats_entries(ppe); + if (ppe_num_stats_entries > 0) { + foe_size = ppe_num_stats_entries * sizeof(*ppe->foe_stats); ppe->foe_stats = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_stats_dma, GFP_KERNEL); @@ -1440,6 +1512,15 @@ int airoha_ppe_init(struct airoha_eth *eth) return -ENOMEM; } + ppe->foe_check_time = devm_kzalloc(eth->dev, ppe_num_entries, + GFP_KERNEL); + if (!ppe->foe_check_time) + return -ENOMEM; + + err = airoha_ppe_flush_sram_entries(ppe); + if (err) + return err; + err = rhashtable_init(ð->flow_table, &airoha_flow_table_params); if (err) return err; diff --git a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c index 05a756233f6a4..0112c41150bb0 100644 --- a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c +++ b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c @@ -53,9 +53,10 @@ static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private, [AIROHA_FOE_STATE_FIN] = "FIN", }; struct airoha_ppe *ppe = m->private; + u32 ppe_num_entries = airoha_ppe_get_total_num_entries(ppe); int i; - for (i = 0; i < PPE_NUM_ENTRIES; i++) { + for (i = 0; i < ppe_num_entries; i++) { const char *state_str, *type_str = "UNKNOWN"; void *src_addr = NULL, *dest_addr = NULL; u16 *src_port = NULL, *dest_port = NULL; diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h index 69c5a143db8c0..ed4e3407f4a0e 100644 --- a/drivers/net/ethernet/airoha/airoha_regs.h +++ b/drivers/net/ethernet/airoha/airoha_regs.h @@ -23,6 +23,8 @@ #define GDM3_BASE 0x1100 #define GDM4_BASE 0x2500 +#define CDM_BASE(_n) \ + ((_n) == 2 ? CDM2_BASE : CDM1_BASE) #define GDM_BASE(_n) \ ((_n) == 4 ? GDM4_BASE : \ (_n) == 3 ? GDM3_BASE : \ @@ -109,30 +111,24 @@ #define PATN_DP_MASK GENMASK(31, 16) #define PATN_SP_MASK GENMASK(15, 0) -#define REG_CDM1_VLAN_CTRL CDM1_BASE -#define CDM1_VLAN_MASK GENMASK(31, 16) +#define REG_CDM_VLAN_CTRL(_n) CDM_BASE(_n) +#define CDM_VLAN_MASK GENMASK(31, 16) -#define REG_CDM1_FWD_CFG (CDM1_BASE + 0x08) -#define CDM1_VIP_QSEL_MASK GENMASK(24, 20) +#define REG_CDM_FWD_CFG(_n) (CDM_BASE(_n) + 0x08) +#define CDM_OAM_QSEL_MASK GENMASK(31, 27) +#define CDM_VIP_QSEL_MASK GENMASK(24, 20) -#define REG_CDM1_CRSN_QSEL(_n) (CDM1_BASE + 0x10 + ((_n) << 2)) -#define CDM1_CRSN_QSEL_REASON_MASK(_n) \ - GENMASK(4 + (((_n) % 4) << 3), (((_n) % 4) << 3)) - -#define REG_CDM2_FWD_CFG (CDM2_BASE + 0x08) -#define CDM2_OAM_QSEL_MASK GENMASK(31, 27) -#define CDM2_VIP_QSEL_MASK GENMASK(24, 20) - -#define REG_CDM2_CRSN_QSEL(_n) (CDM2_BASE + 0x10 + ((_n) << 2)) -#define CDM2_CRSN_QSEL_REASON_MASK(_n) \ +#define REG_CDM_CRSN_QSEL(_n, _m) (CDM_BASE(_n) + 0x10 + ((_m) << 2)) +#define CDM_CRSN_QSEL_REASON_MASK(_n) \ GENMASK(4 + (((_n) % 4) << 3), (((_n) % 4) << 3)) #define REG_GDM_FWD_CFG(_n) GDM_BASE(_n) -#define GDM_DROP_CRC_ERR BIT(23) -#define GDM_IP4_CKSUM BIT(22) -#define GDM_TCP_CKSUM BIT(21) -#define GDM_UDP_CKSUM BIT(20) -#define GDM_STRIP_CRC BIT(16) +#define GDM_PAD_EN_MASK BIT(28) +#define GDM_DROP_CRC_ERR_MASK BIT(23) +#define GDM_IP4_CKSUM_MASK BIT(22) +#define GDM_TCP_CKSUM_MASK BIT(21) +#define GDM_UDP_CKSUM_MASK BIT(20) +#define GDM_STRIP_CRC_MASK BIT(16) #define GDM_UCFQ_MASK GENMASK(15, 12) #define GDM_BCFQ_MASK GENMASK(11, 8) #define GDM_MCFQ_MASK GENMASK(7, 4) @@ -156,6 +152,10 @@ #define LBK_CHAN_MODE_MASK BIT(1) #define LPBK_EN_MASK BIT(0) +#define REG_GDM_CHN_RLS(_n) (GDM_BASE(_n) + 0x20) +#define MBI_RX_AGE_SEL_MASK GENMASK(26, 25) +#define MBI_TX_AGE_SEL_MASK GENMASK(18, 17) + #define REG_GDM_TXCHN_EN(_n) (GDM_BASE(_n) + 0x24) #define REG_GDM_RXCHN_EN(_n) (GDM_BASE(_n) + 0x28) @@ -168,10 +168,10 @@ #define FE_GDM_MIB_RX_CLEAR_MASK BIT(1) #define FE_GDM_MIB_TX_CLEAR_MASK BIT(0) -#define REG_FE_GDM1_MIB_CFG (GDM1_BASE + 0xf4) +#define REG_FE_GDM_MIB_CFG(_n) (GDM_BASE(_n) + 0xf4) #define FE_STRICT_RFC2819_MODE_MASK BIT(31) -#define FE_GDM1_TX_MIB_SPLIT_EN_MASK BIT(17) -#define FE_GDM1_RX_MIB_SPLIT_EN_MASK BIT(16) +#define FE_GDM_TX_MIB_SPLIT_EN_MASK BIT(17) +#define FE_GDM_RX_MIB_SPLIT_EN_MASK BIT(16) #define FE_TX_MIB_ID_MASK GENMASK(15, 8) #define FE_RX_MIB_ID_MASK GENMASK(7, 0) @@ -214,6 +214,33 @@ #define REG_FE_GDM_RX_ETH_L511_CNT_L(_n) (GDM_BASE(_n) + 0x198) #define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n) (GDM_BASE(_n) + 0x19c) +#define REG_GDM_SRC_PORT_SET(_n) (GDM_BASE(_n) + 0x23c) +#define GDM_SPORT_OFF2_MASK GENMASK(19, 16) +#define GDM_SPORT_OFF1_MASK GENMASK(15, 12) +#define GDM_SPORT_OFF0_MASK GENMASK(11, 8) + +#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x280) +#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x284) +#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x288) +#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x28c) + +#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x290) +#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x294) +#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x298) +#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x29c) +#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2b8) +#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2bc) +#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2c0) +#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2c4) +#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2c8) +#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2cc) +#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2e8) +#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2ec) +#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2f0) +#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2f4) +#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2f8) +#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2fc) + #define REG_PPE_GLO_CFG(_n) (((_n) ? PPE2_BASE : PPE1_BASE) + 0x200) #define PPE_GLO_CFG_BUSY_MASK BIT(31) #define PPE_GLO_CFG_FLOW_DROP_UPDATE_MASK BIT(9) @@ -326,44 +353,6 @@ #define REG_UPDMEM_DATA(_n) (((_n) ? PPE2_BASE : PPE1_BASE) + 0x374) -#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x280) -#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x284) -#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x288) -#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x28c) - -#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x290) -#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x294) -#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n) (GDM_BASE(_n) + 0x298) -#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n) (GDM_BASE(_n) + 0x29c) -#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2b8) -#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2bc) -#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2c0) -#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2c4) -#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2c8) -#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2cc) -#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n) (GDM_BASE(_n) + 0x2e8) -#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n) (GDM_BASE(_n) + 0x2ec) -#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n) (GDM_BASE(_n) + 0x2f0) -#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n) (GDM_BASE(_n) + 0x2f4) -#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n) (GDM_BASE(_n) + 0x2f8) -#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n) (GDM_BASE(_n) + 0x2fc) - -#define REG_GDM2_CHN_RLS (GDM2_BASE + 0x20) -#define MBI_RX_AGE_SEL_MASK GENMASK(26, 25) -#define MBI_TX_AGE_SEL_MASK GENMASK(18, 17) - -#define REG_GDM3_FWD_CFG GDM3_BASE -#define GDM3_PAD_EN_MASK BIT(28) - -#define REG_GDM4_FWD_CFG GDM4_BASE -#define GDM4_PAD_EN_MASK BIT(28) -#define GDM4_SPORT_OFFSET0_MASK GENMASK(11, 8) - -#define REG_GDM4_SRC_PORT_SET (GDM4_BASE + 0x23c) -#define GDM4_SPORT_OFF2_MASK GENMASK(19, 16) -#define GDM4_SPORT_OFF1_MASK GENMASK(15, 12) -#define GDM4_SPORT_OFF0_MASK GENMASK(11, 8) - #define REG_IP_FRAG_FP 0x2010 #define IP_ASSEMBLE_PORT_MASK GENMASK(24, 21) #define IP_ASSEMBLE_NBQ_MASK GENMASK(20, 16) @@ -383,10 +372,8 @@ #define REG_MC_VLAN_DATA 0x2108 #define REG_SP_DFT_CPORT(_n) (0x20e0 + ((_n) << 2)) -#define SP_CPORT_PCIE1_MASK GENMASK(31, 28) -#define SP_CPORT_PCIE0_MASK GENMASK(27, 24) -#define SP_CPORT_USB_MASK GENMASK(7, 4) -#define SP_CPORT_ETH_MASK GENMASK(7, 4) +#define SP_CPORT_DFT_MASK GENMASK(2, 0) +#define SP_CPORT_MASK(_n) GENMASK(3 + ((_n) << 2), ((_n) << 2)) #define REG_SRC_PORT_FC_MAP6 0x2298 #define FC_ID_OF_SRC_PORT27_MASK GENMASK(28, 24) diff --git a/drivers/net/ethernet/alibaba/Kconfig b/drivers/net/ethernet/alibaba/Kconfig new file mode 100644 index 0000000000000..820a9a7aa1f18 --- /dev/null +++ b/drivers/net/ethernet/alibaba/Kconfig @@ -0,0 +1,29 @@ +# +# Alibaba network device configuration +# + +config NET_VENDOR_ALIBABA + bool "Alibaba Devices" + default y + help + If you have a network (Ethernet) device belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Alibaba devices. If you say Y, you will be asked + for your specific device in the following questions. + +if NET_VENDOR_ALIBABA + +config EEA + tristate "Alibaba Elastic Ethernet Adapter support" + depends on PCI_MSI + depends on 64BIT + select PAGE_POOL + default m + help + This driver supports Alibaba Elastic Ethernet Adapter" + + To compile this driver as a module, choose M here. + +endif #NET_VENDOR_ALIBABA diff --git a/drivers/net/ethernet/alibaba/Makefile b/drivers/net/ethernet/alibaba/Makefile new file mode 100644 index 0000000000000..7980525cb0860 --- /dev/null +++ b/drivers/net/ethernet/alibaba/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for the Alibaba network device drivers. +# + +obj-$(CONFIG_EEA) += eea/ diff --git a/drivers/net/ethernet/alibaba/eea/Makefile b/drivers/net/ethernet/alibaba/eea/Makefile new file mode 100644 index 0000000000000..8f8fbb8d2d9a2 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/Makefile @@ -0,0 +1,9 @@ + +obj-$(CONFIG_EEA) += eea.o +eea-y := eea_ring.o \ + eea_net.o \ + eea_pci.o \ + eea_adminq.o \ + eea_ethtool.o \ + eea_tx.o \ + eea_rx.o diff --git a/drivers/net/ethernet/alibaba/eea/eea_adminq.c b/drivers/net/ethernet/alibaba/eea/eea_adminq.c new file mode 100644 index 0000000000000..99b05357649eb --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_adminq.c @@ -0,0 +1,421 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include +#include +#include +#include + +#include "eea_adminq.h" +#include "eea_net.h" +#include "eea_pci.h" +#include "eea_ring.h" + +#define EEA_AQ_CMD_CFG_QUERY ((0 << 8) | 0) + +#define EEA_AQ_CMD_QUEUE_CREATE ((1 << 8) | 0) +#define EEA_AQ_CMD_QUEUE_DESTROY_ALL ((1 << 8) | 1) + +#define EEA_AQ_CMD_HOST_INFO ((2 << 8) | 0) + +#define EEA_AQ_CMD_DEV_STATUS ((3 << 8) | 0) + +#define EEA_RING_DESC_F_AQ_PHASE (BIT(15) | BIT(7)) + +#define EEA_QUEUE_FLAGS_HW_SPLIT_HDR BIT(0) +#define EEA_QUEUE_FLAGS_SQCQ BIT(1) +#define EEA_QUEUE_FLAGS_HWTS BIT(2) + +struct eea_aq_create { + __le32 flags; + /* queue index. + * rx: 0 == qidx % 2 + * tx: 1 == qidx % 2 + */ + __le16 qidx; + /* the depth of the queue */ + __le16 depth; + /* 0: without SPLIT HDR + * 1: 128B + * 2: 256B + * 3: 512B + */ + u8 hdr_buf_size; + u8 sq_desc_size; + u8 cq_desc_size; + u8 reserve0; + /* The vector for the irq. rx,tx share the same vector */ + __le16 msix_vector; + __le16 reserve; + /* sq ring cfg. */ + __le32 sq_addr_low; + __le32 sq_addr_high; + /* cq ring cfg. Just valid when flags include EEA_QUEUE_FLAGS_SQCQ. */ + __le32 cq_addr_low; + __le32 cq_addr_high; +}; + +struct eea_aq_queue_drv_status { + __le16 qidx; + + __le16 sq_head; + __le16 cq_head; + __le16 reserved; +}; + +#define EEA_OS_DISTRO 0 +#define EEA_DRV_TYPE 0 +#define EEA_OS_LINUX 1 +#define EEA_SPEC_VER_MAJOR 1 +#define EEA_SPEC_VER_MINOR 0 + +struct eea_aq_host_info_cfg { + __le16 os_type; + __le16 os_dist; + __le16 drv_type; + + __le16 kern_ver_major; + __le16 kern_ver_minor; + __le16 kern_ver_sub_minor; + + __le16 drv_ver_major; + __le16 drv_ver_minor; + __le16 drv_ver_sub_minor; + + __le16 spec_ver_major; + __le16 spec_ver_minor; + __le16 pci_bdf; + __le32 pci_domain; + + u8 os_ver_str[64]; + u8 isa_str[64]; +}; + +#define EEA_HINFO_MAX_REP_LEN 1024 +#define EEA_HINFO_REP_REJECT 2 + +struct eea_aq_host_info_rep { + u8 op_code; + u8 has_reply; + u8 reply_str[EEA_HINFO_MAX_REP_LEN]; +}; + +static struct eea_ring *qid_to_ering(struct eea_net *enet, u32 qid) +{ + struct eea_ring *ering; + + if (qid % 2 == 0) + ering = enet->rx[qid / 2]->ering; + else + ering = enet->tx[qid / 2].ering; + + return ering; +} + +#define EEA_AQ_TIMEOUT_US (60 * 1000 * 1000) + +static int eea_adminq_submit(struct eea_net *enet, u16 cmd, + dma_addr_t req_addr, dma_addr_t res_addr, + u32 req_size, u32 res_size) +{ + struct eea_aq_cdesc *cdesc; + struct eea_aq_desc *desc; + int ret; + + desc = ering_aq_alloc_desc(enet->adminq.ring); + + desc->classid = cmd >> 8; + desc->command = cmd & 0xff; + + desc->data_addr = cpu_to_le64(req_addr); + desc->data_len = cpu_to_le32(req_size); + + desc->reply_addr = cpu_to_le64(res_addr); + desc->reply_len = cpu_to_le32(res_size); + + /* for update flags */ + wmb(); + + desc->flags = cpu_to_le16(enet->adminq.phase); + + ering_sq_commit_desc(enet->adminq.ring); + + ering_kick(enet->adminq.ring); + + ++enet->adminq.num; + + if ((enet->adminq.num % enet->adminq.ring->num) == 0) + enet->adminq.phase ^= EEA_RING_DESC_F_AQ_PHASE; + + ret = read_poll_timeout(ering_cq_get_desc, cdesc, cdesc, 0, + EEA_AQ_TIMEOUT_US, false, enet->adminq.ring); + if (ret) + return ret; + + ret = le32_to_cpu(cdesc->status); + + ering_cq_ack_desc(enet->adminq.ring, 1); + + if (ret) + netdev_err(enet->netdev, + "adminq exec failed. cmd: %d ret %d\n", cmd, ret); + + return ret; +} + +static int eea_adminq_exec(struct eea_net *enet, u16 cmd, + void *req, u32 req_size, void *res, u32 res_size) +{ + dma_addr_t req_addr = 0, res_addr = 0; + struct device *dma; + int ret; + + dma = enet->edev->dma_dev; + + if (req) { + req_addr = dma_map_single(dma, req, req_size, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(dma, req_addr))) + return -ENOMEM; + } + + if (res) { + res_addr = dma_map_single(dma, res, res_size, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(dma, res_addr))) { + ret = -ENOMEM; + goto err_unmap_req; + } + } + + ret = eea_adminq_submit(enet, cmd, req_addr, res_addr, + req_size, res_size); + if (res) + dma_unmap_single(dma, res_addr, res_size, DMA_FROM_DEVICE); + +err_unmap_req: + if (req) + dma_unmap_single(dma, req_addr, req_size, DMA_TO_DEVICE); + + return ret; +} + +void eea_destroy_adminq(struct eea_net *enet) +{ + if (enet->adminq.ring) { + ering_free(enet->adminq.ring); + enet->adminq.ring = NULL; + enet->adminq.phase = 0; + } +} + +int eea_create_adminq(struct eea_net *enet, u32 qid) +{ + struct eea_ring *ering; + + ering = ering_alloc(qid, 64, enet->edev, sizeof(struct eea_aq_desc), + sizeof(struct eea_aq_desc), "adminq"); + if (!ering) + return -ENOMEM; + + eea_pci_active_aq(ering); + + enet->adminq.ring = ering; + enet->adminq.phase = BIT(7); + enet->adminq.num = 0; + + /* set device ready to active adminq */ + eea_device_ready(enet->edev); + + return 0; +} + +int eea_adminq_query_cfg(struct eea_net *enet, struct eea_aq_cfg *cfg) +{ + return eea_adminq_exec(enet, EEA_AQ_CMD_CFG_QUERY, NULL, 0, cfg, + sizeof(*cfg)); +} + +static void qcfg_fill(struct eea_aq_create *qcfg, struct eea_ring *ering, + u32 flags) +{ + qcfg->flags = cpu_to_le32(flags); + qcfg->qidx = cpu_to_le16(ering->index); + qcfg->depth = cpu_to_le16(ering->num); + + qcfg->hdr_buf_size = flags & EEA_QUEUE_FLAGS_HW_SPLIT_HDR ? 1 : 0; + qcfg->sq_desc_size = ering->sq.desc_size; + qcfg->cq_desc_size = ering->cq.desc_size; + qcfg->msix_vector = cpu_to_le16(ering->msix_vec); + + qcfg->sq_addr_low = cpu_to_le32(ering->sq.dma_addr); + qcfg->sq_addr_high = cpu_to_le32(ering->sq.dma_addr >> 32); + + qcfg->cq_addr_low = cpu_to_le32(ering->cq.dma_addr); + qcfg->cq_addr_high = cpu_to_le32(ering->cq.dma_addr >> 32); +} + +int eea_adminq_create_q(struct eea_net *enet, u32 qidx, u32 num, u32 flags) +{ + int i, db_size, q_size, qid, err = -ENOMEM; + struct device *dev = enet->edev->dma_dev; + struct eea_aq_create *q_buf; + dma_addr_t db_dma, q_dma; + struct eea_net_cfg *cfg; + struct eea_ring *ering; + __le32 *db_buf; + + cfg = &enet->cfg; + + if (cfg->split_hdr) + flags |= EEA_QUEUE_FLAGS_HW_SPLIT_HDR; + + flags |= EEA_QUEUE_FLAGS_SQCQ; + flags |= EEA_QUEUE_FLAGS_HWTS; + + db_size = sizeof(int) * num; + q_size = sizeof(struct eea_aq_create) * num; + + db_buf = dma_alloc_coherent(dev, db_size, &db_dma, GFP_KERNEL); + if (!db_buf) + return err; + + q_buf = dma_alloc_coherent(dev, q_size, &q_dma, GFP_KERNEL); + if (!q_buf) + goto err_free_db_buf; + + qid = qidx; + for (i = 0; i < num; i++, qid++) + qcfg_fill(q_buf + i, qid_to_ering(enet, qid), flags); + + err = eea_adminq_exec(enet, EEA_AQ_CMD_QUEUE_CREATE, + q_buf, q_size, db_buf, db_size); + if (err) + goto err_free_q_buf; + + qid = qidx; + for (i = 0; i < num; i++, qid++) { + ering = qid_to_ering(enet, qid); + ering->db = eea_pci_db_addr(ering->edev, + le32_to_cpu(db_buf[i])); + } + +err_free_q_buf: + dma_free_coherent(dev, q_size, q_buf, q_dma); + +err_free_db_buf: + dma_free_coherent(dev, db_size, db_buf, db_dma); + + return err; +} + +int eea_adminq_destroy_all_q(struct eea_net *enet) +{ + return eea_adminq_exec(enet, EEA_AQ_CMD_QUEUE_DESTROY_ALL, NULL, 0, + NULL, 0); +} + +struct eea_aq_dev_status *eea_adminq_dev_status(struct eea_net *enet) +{ + struct eea_aq_queue_drv_status *drv_status; + struct eea_aq_dev_status *dev_status; + struct eea_ring *ering; + int err, i, num, size; + void *rep, *req; + + num = enet->cfg.tx_ring_num * 2 + 1; + + req = kcalloc(num, sizeof(struct eea_aq_queue_drv_status), GFP_KERNEL); + if (!req) + return NULL; + + size = struct_size(dev_status, q_status, num); + + rep = kmalloc(size, GFP_KERNEL); + if (!rep) { + kfree(req); + return NULL; + } + + drv_status = req; + for (i = 0; i < enet->cfg.rx_ring_num * 2; ++i, ++drv_status) { + ering = qid_to_ering(enet, i); + drv_status->qidx = cpu_to_le16(i); + drv_status->cq_head = cpu_to_le16(ering->cq.head); + drv_status->sq_head = cpu_to_le16(ering->sq.head); + } + + drv_status->qidx = cpu_to_le16(i); + drv_status->cq_head = cpu_to_le16(enet->adminq.ring->cq.head); + drv_status->sq_head = cpu_to_le16(enet->adminq.ring->sq.head); + + err = eea_adminq_exec(enet, EEA_AQ_CMD_DEV_STATUS, + req, num * sizeof(struct eea_aq_queue_drv_status), + rep, size); + kfree(req); + if (err) { + kfree(rep); + return NULL; + } + + return rep; +} + +int eea_adminq_config_host_info(struct eea_net *enet) +{ + struct device *dev = enet->edev->dma_dev; + struct eea_aq_host_info_cfg *cfg; + struct eea_aq_host_info_rep *rep; + int rc = -ENOMEM; + + cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return rc; + + rep = kzalloc(sizeof(*rep), GFP_KERNEL); + if (!rep) + goto err_free_cfg; + + cfg->os_type = cpu_to_le16(EEA_OS_LINUX); + cfg->os_dist = cpu_to_le16(EEA_OS_DISTRO); + cfg->drv_type = cpu_to_le16(EEA_DRV_TYPE); + + cfg->kern_ver_major = cpu_to_le16(LINUX_VERSION_MAJOR); + cfg->kern_ver_minor = cpu_to_le16(LINUX_VERSION_PATCHLEVEL); + cfg->kern_ver_sub_minor = cpu_to_le16(LINUX_VERSION_SUBLEVEL); + + cfg->drv_ver_major = cpu_to_le16(EEA_VER_MAJOR); + cfg->drv_ver_minor = cpu_to_le16(EEA_VER_MINOR); + cfg->drv_ver_sub_minor = cpu_to_le16(EEA_VER_SUB_MINOR); + + cfg->spec_ver_major = cpu_to_le16(EEA_SPEC_VER_MAJOR); + cfg->spec_ver_minor = cpu_to_le16(EEA_SPEC_VER_MINOR); + + cfg->pci_bdf = cpu_to_le16(eea_pci_dev_id(enet->edev)); + cfg->pci_domain = cpu_to_le32(eea_pci_domain_nr(enet->edev)); + + strscpy(cfg->os_ver_str, utsname()->release, sizeof(cfg->os_ver_str)); + strscpy(cfg->isa_str, utsname()->machine, sizeof(cfg->isa_str)); + + rc = eea_adminq_exec(enet, EEA_AQ_CMD_HOST_INFO, + cfg, sizeof(*cfg), rep, sizeof(*rep)); + + if (!rc) { + if (rep->op_code == EEA_HINFO_REP_REJECT) { + dev_err(dev, "Device has refused the initialization due to provided host information\n"); + rc = -ENODEV; + } + if (rep->has_reply) { + rep->reply_str[EEA_HINFO_MAX_REP_LEN - 1] = '\0'; + dev_warn(dev, "Device replied: %s\n", + rep->reply_str); + } + } + + kfree(rep); +err_free_cfg: + kfree(cfg); + return rc; +} diff --git a/drivers/net/ethernet/alibaba/eea/eea_adminq.h b/drivers/net/ethernet/alibaba/eea/eea_adminq.h new file mode 100644 index 0000000000000..dce65967cc17b --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_adminq.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include "eea_pci.h" + +#ifndef __EEA_ADMINQ_H__ +#define __EEA_ADMINQ_H__ + +struct eea_aq_cfg { + __le32 rx_depth_max; + __le32 rx_depth_def; + + __le32 tx_depth_max; + __le32 tx_depth_def; + + __le32 max_tso_size; + __le32 max_tso_segs; + + u8 mac[ETH_ALEN]; + __le16 status; + + __le16 mtu; + __le16 reserved0; + __le16 reserved1; + u8 reserved2; + u8 reserved3; + + __le16 reserved4; + __le16 reserved5; + __le16 reserved6; +}; + +struct eea_aq_queue_status { + __le16 qidx; +#define EEA_QUEUE_STATUS_OK 0 +#define EEA_QUEUE_STATUS_NEED_RESET 1 + __le16 status; +}; + +struct eea_aq_dev_status { +#define EEA_LINK_DOWN_STATUS 0 +#define EEA_LINK_UP_STATUS 1 + __le16 link_status; + __le16 reserved; + + struct eea_aq_queue_status q_status[]; +}; + +struct eea_aq { + struct eea_ring *ring; + u32 num; + u16 phase; +}; + +struct eea_net; + +int eea_create_adminq(struct eea_net *enet, u32 qid); +void eea_destroy_adminq(struct eea_net *enet); + +int eea_adminq_query_cfg(struct eea_net *enet, struct eea_aq_cfg *cfg); + +int eea_adminq_create_q(struct eea_net *enet, u32 qidx, u32 num, u32 flags); +int eea_adminq_destroy_all_q(struct eea_net *enet); +struct eea_aq_dev_status *eea_adminq_dev_status(struct eea_net *enet); +int eea_adminq_config_host_info(struct eea_net *enet); +#endif diff --git a/drivers/net/ethernet/alibaba/eea/eea_desc.h b/drivers/net/ethernet/alibaba/eea/eea_desc.h new file mode 100644 index 0000000000000..541346a033754 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_desc.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#ifndef __EEA_DESC_H__ +#define __EEA_DESC_H__ + +#define EEA_DESC_TS_MASK GENMASK(47, 0) +#define EEA_DESC_TS(desc) (le64_to_cpu((desc)->ts) & EEA_DESC_TS_MASK) + +struct eea_aq_desc { + __le16 flags; + __le16 id; + __le16 reserved; + u8 classid; + u8 command; + __le64 data_addr; + __le64 reply_addr; + __le32 data_len; + __le32 reply_len; +}; + +struct eea_aq_cdesc { + __le16 flags; + __le16 id; +#define EEA_OK 0 +#define EEA_ERR 0xffffffff + __le32 status; + __le32 reply_len; + __le32 reserved1; + + __le64 reserved2; + __le64 reserved3; +}; + +struct eea_rx_desc { + __le16 flags; + __le16 id; + __le16 len; + __le16 reserved1; + + __le64 addr; + + __le64 hdr_addr; + __le32 reserved2; + __le32 reserved3; +}; + +#define EEA_RX_CDESC_HDR_LEN_MASK GENMASK(9, 0) + +struct eea_rx_cdesc { +#define EEA_DESC_F_DATA_VALID BIT(6) +#define EEA_DESC_F_SPLIT_HDR BIT(5) + __le16 flags; + __le16 id; + __le16 len; +#define EEA_NET_PT_NONE 0 +#define EEA_NET_PT_IPv4 1 +#define EEA_NET_PT_TCPv4 2 +#define EEA_NET_PT_UDPv4 3 +#define EEA_NET_PT_IPv6 4 +#define EEA_NET_PT_TCPv6 5 +#define EEA_NET_PT_UDPv6 6 +#define EEA_NET_PT_IPv6_EX 7 +#define EEA_NET_PT_TCPv6_EX 8 +#define EEA_NET_PT_UDPv6_EX 9 + /* [9:0] is packet type. */ + __le16 type; + + /* hw timestamp [0:47]: ts */ + __le64 ts; + + __le32 hash; + + /* 0-9: hdr_len split header + * 10-15: reserved1 + */ + __le16 len_ex; + __le16 reserved2; + + __le32 reserved3; + __le32 reserved4; +}; + +#define EEA_TX_GSO_NONE 0 +#define EEA_TX_GSO_TCPV4 1 +#define EEA_TX_GSO_TCPV6 4 +#define EEA_TX_GSO_UDP_L4 5 +#define EEA_TX_GSO_ECN 0x80 + +struct eea_tx_desc { +#define EEA_DESC_F_DO_CSUM BIT(6) + __le16 flags; + __le16 id; + __le16 len; + __le16 reserved1; + + __le64 addr; + + __le16 csum_start; + __le16 csum_offset; + u8 gso_type; + u8 reserved2; + __le16 gso_size; + __le64 reserved3; +}; + +struct eea_tx_cdesc { + __le16 flags; + __le16 id; + __le16 len; + __le16 reserved1; + + /* hw timestamp [0:47]: ts */ + __le64 ts; + __le64 reserved2; + __le64 reserved3; +}; + +struct eea_db { +#define EEA_IDX_PRESENT BIT(0) +#define EEA_IRQ_MASK BIT(1) +#define EEA_IRQ_UNMASK BIT(2) +#define EEA_DIRECT_INLINE BIT(3) +#define EEA_DIRECT_DESC BIT(4) + u8 kick_flags; + u8 reserved; + __le16 idx; + + __le16 tx_cq_head; + __le16 rx_cq_head; +}; + +struct eea_db_direct { + u8 kick_flags; + u8 reserved; + __le16 idx; + + __le16 tx_cq_head; + __le16 rx_cq_head; + + u8 desc[24]; +}; + +static_assert(sizeof(struct eea_rx_desc) == 32, "rx desc size does not match"); +static_assert(sizeof(struct eea_rx_cdesc) == 32, + "rx cdesc size does not match"); +static_assert(sizeof(struct eea_tx_desc) == 32, "tx desc size does not match"); +static_assert(sizeof(struct eea_tx_cdesc) == 32, + "tx cdesc size does not match"); +static_assert(sizeof(struct eea_db_direct) == 32, + "db direct size does not match"); +#endif diff --git a/drivers/net/ethernet/alibaba/eea/eea_ethtool.c b/drivers/net/ethernet/alibaba/eea/eea_ethtool.c new file mode 100644 index 0000000000000..16621c1bec2de --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_ethtool.c @@ -0,0 +1,276 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include +#include + +#include "eea_adminq.h" + +struct eea_stat_desc { + char desc[ETH_GSTRING_LEN]; + size_t offset; +}; + +#define EEA_TX_STAT(m) {#m, offsetof(struct eea_tx_stats, m)} +#define EEA_RX_STAT(m) {#m, offsetof(struct eea_rx_stats, m)} + +static const struct eea_stat_desc eea_rx_stats_desc[] = { + EEA_RX_STAT(descs), + EEA_RX_STAT(kicks), +}; + +static const struct eea_stat_desc eea_tx_stats_desc[] = { + EEA_TX_STAT(descs), + EEA_TX_STAT(kicks), +}; + +#define EEA_TX_STATS_LEN ARRAY_SIZE(eea_tx_stats_desc) +#define EEA_RX_STATS_LEN ARRAY_SIZE(eea_rx_stats_desc) + +static void eea_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *info) +{ + struct eea_net *enet = netdev_priv(netdev); + struct eea_device *edev = enet->edev; + + strscpy(info->driver, KBUILD_MODNAME, sizeof(info->driver)); + strscpy(info->bus_info, eea_pci_name(edev), sizeof(info->bus_info)); +} + +static void eea_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct eea_net *enet = netdev_priv(netdev); + + ring->rx_max_pending = enet->cfg_hw.rx_ring_depth; + ring->tx_max_pending = enet->cfg_hw.tx_ring_depth; + ring->rx_pending = enet->cfg.rx_ring_depth; + ring->tx_pending = enet->cfg.tx_ring_depth; + + kernel_ring->tcp_data_split = enet->cfg.split_hdr ? + ETHTOOL_TCP_DATA_SPLIT_ENABLED : + ETHTOOL_TCP_DATA_SPLIT_DISABLED; +} + +static int eea_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring, + struct kernel_ethtool_ringparam *kernel_ring, + struct netlink_ext_ack *extack) +{ + struct eea_net *enet = netdev_priv(netdev); + struct eea_net_init_ctx ctx; + bool need_update = false; + struct eea_net_cfg *cfg; + bool sh; + + enet_init_ctx(enet, &ctx); + + cfg = &ctx.cfg; + + if (ring->rx_pending != cfg->rx_ring_depth) + need_update = true; + + if (ring->tx_pending != cfg->tx_ring_depth) + need_update = true; + + sh = kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED; + if (sh != !!(cfg->split_hdr)) + need_update = true; + + if (!need_update) + return 0; + + cfg->rx_ring_depth = ring->rx_pending; + cfg->tx_ring_depth = ring->tx_pending; + + cfg->split_hdr = sh ? enet->cfg_hw.split_hdr : 0; + + return eea_reset_hw_resources(enet, &ctx); +} + +static int eea_set_channels(struct net_device *netdev, + struct ethtool_channels *channels) +{ + struct eea_net *enet = netdev_priv(netdev); + u16 queue_pairs = channels->combined_count; + struct eea_net_init_ctx ctx; + struct eea_net_cfg *cfg; + + enet_init_ctx(enet, &ctx); + + cfg = &ctx.cfg; + + cfg->rx_ring_num = queue_pairs; + cfg->tx_ring_num = queue_pairs; + + return eea_reset_hw_resources(enet, &ctx); +} + +static void eea_get_channels(struct net_device *netdev, + struct ethtool_channels *channels) +{ + struct eea_net *enet = netdev_priv(netdev); + + channels->combined_count = enet->cfg.rx_ring_num; + channels->max_combined = enet->cfg_hw.rx_ring_num; +} + +static void eea_get_strings(struct net_device *netdev, u32 stringset, u8 *data) +{ + struct eea_net *enet = netdev_priv(netdev); + u8 *p = data; + u32 i, j; + + if (stringset != ETH_SS_STATS) + return; + + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + for (j = 0; j < EEA_RX_STATS_LEN; j++) + ethtool_sprintf(&p, "rx%u_%s", i, + eea_rx_stats_desc[j].desc); + } + + for (i = 0; i < enet->cfg.tx_ring_num; i++) { + for (j = 0; j < EEA_TX_STATS_LEN; j++) + ethtool_sprintf(&p, "tx%u_%s", i, + eea_tx_stats_desc[j].desc); + } +} + +static int eea_get_sset_count(struct net_device *netdev, int sset) +{ + struct eea_net *enet = netdev_priv(netdev); + + if (sset != ETH_SS_STATS) + return -EOPNOTSUPP; + + return enet->cfg.rx_ring_num * EEA_RX_STATS_LEN + + enet->cfg.tx_ring_num * EEA_TX_STATS_LEN; +} + +static void eea_stats_fill_for_q(struct u64_stats_sync *syncp, u32 num, + const struct eea_stat_desc *desc, + u64 *data, u32 idx) +{ + void *stats_base = syncp; + u32 start, i; + + do { + start = u64_stats_fetch_begin(syncp); + for (i = 0; i < num; i++) + data[idx + i] = + u64_stats_read(stats_base + desc[i].offset); + + } while (u64_stats_fetch_retry(syncp, start)); +} + +static void eea_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct eea_net *enet = netdev_priv(netdev); + u32 i, idx = 0; + + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + struct eea_net_rx *rx = enet->rx[i]; + + eea_stats_fill_for_q(&rx->stats.syncp, EEA_RX_STATS_LEN, + eea_rx_stats_desc, data, idx); + + idx += EEA_RX_STATS_LEN; + } + + for (i = 0; i < enet->cfg.tx_ring_num; i++) { + struct eea_net_tx *tx = &enet->tx[i]; + + eea_stats_fill_for_q(&tx->stats.syncp, EEA_TX_STATS_LEN, + eea_tx_stats_desc, data, idx); + + idx += EEA_TX_STATS_LEN; + } +} + +void eea_update_rx_stats(struct eea_rx_stats *rx_stats, + struct eea_rx_ctx_stats *stats) +{ + u64_stats_update_begin(&rx_stats->syncp); + u64_stats_add(&rx_stats->descs, stats->descs); + u64_stats_add(&rx_stats->packets, stats->packets); + u64_stats_add(&rx_stats->bytes, stats->bytes); + u64_stats_add(&rx_stats->drops, stats->drops); + u64_stats_add(&rx_stats->split_hdr_bytes, stats->split_hdr_bytes); + u64_stats_add(&rx_stats->split_hdr_packets, stats->split_hdr_packets); + u64_stats_add(&rx_stats->length_errors, stats->length_errors); + u64_stats_update_end(&rx_stats->syncp); +} + +void eea_stats(struct net_device *netdev, struct rtnl_link_stats64 *tot) +{ + struct eea_net *enet = netdev_priv(netdev); + u64 packets, bytes; + u32 start; + int i; + + if (enet->rx) { + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + struct eea_net_rx *rx = enet->rx[i]; + + do { + start = u64_stats_fetch_begin(&rx->stats.syncp); + packets = u64_stats_read(&rx->stats.packets); + bytes = u64_stats_read(&rx->stats.bytes); + } while (u64_stats_fetch_retry(&rx->stats.syncp, + start)); + + tot->rx_packets += packets; + tot->rx_bytes += bytes; + } + } + + if (enet->tx) { + for (i = 0; i < enet->cfg.tx_ring_num; i++) { + struct eea_net_tx *tx = &enet->tx[i]; + + do { + start = u64_stats_fetch_begin(&tx->stats.syncp); + packets = u64_stats_read(&tx->stats.packets); + bytes = u64_stats_read(&tx->stats.bytes); + } while (u64_stats_fetch_retry(&tx->stats.syncp, + start)); + + tot->tx_packets += packets; + tot->tx_bytes += bytes; + } + } +} + +static int eea_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct eea_net *enet = netdev_priv(netdev); + + cmd->base.speed = enet->speed; + cmd->base.duplex = enet->duplex; + cmd->base.port = PORT_OTHER; + + return 0; +} + +const struct ethtool_ops eea_ethtool_ops = { + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, + .get_drvinfo = eea_get_drvinfo, + .get_link = ethtool_op_get_link, + .get_ringparam = eea_get_ringparam, + .set_ringparam = eea_set_ringparam, + .set_channels = eea_set_channels, + .get_channels = eea_get_channels, + .get_strings = eea_get_strings, + .get_sset_count = eea_get_sset_count, + .get_ethtool_stats = eea_get_ethtool_stats, + .get_link_ksettings = eea_get_link_ksettings, +}; diff --git a/drivers/net/ethernet/alibaba/eea/eea_ethtool.h b/drivers/net/ethernet/alibaba/eea/eea_ethtool.h new file mode 100644 index 0000000000000..1ee89b49addd2 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_ethtool.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#ifndef __EEA_ETHTOOL_H__ +#define __EEA_ETHTOOL_H__ + +struct eea_tx_stats { + struct u64_stats_sync syncp; + u64_stats_t descs; + u64_stats_t packets; + u64_stats_t bytes; + u64_stats_t drops; + u64_stats_t kicks; +}; + +struct eea_rx_ctx_stats { + u64 descs; + u64 packets; + u64 bytes; + u64 drops; + u64 split_hdr_bytes; + u64 split_hdr_packets; + + u64 length_errors; +}; + +struct eea_rx_stats { + struct u64_stats_sync syncp; + u64_stats_t descs; + u64_stats_t packets; + u64_stats_t bytes; + u64_stats_t drops; + u64_stats_t kicks; + u64_stats_t split_hdr_bytes; + u64_stats_t split_hdr_packets; + + u64_stats_t length_errors; +}; + +void eea_update_rx_stats(struct eea_rx_stats *rx_stats, + struct eea_rx_ctx_stats *stats); +void eea_stats(struct net_device *netdev, struct rtnl_link_stats64 *tot); + +extern const struct ethtool_ops eea_ethtool_ops; + +#endif diff --git a/drivers/net/ethernet/alibaba/eea/eea_net.c b/drivers/net/ethernet/alibaba/eea/eea_net.c new file mode 100644 index 0000000000000..9bf0d823d6100 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_net.c @@ -0,0 +1,576 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include +#include +#include +#include +#include + +#include "eea_adminq.h" +#include "eea_net.h" +#include "eea_pci.h" +#include "eea_ring.h" + +#define EEA_SPLIT_HDR_SIZE 128 + +static void enet_bind_new_q_and_cfg(struct eea_net *enet, + struct eea_net_init_ctx *ctx) +{ + struct eea_net_rx *rx; + struct eea_net_tx *tx; + int i; + + enet->cfg = ctx->cfg; + + enet->rx = ctx->rx; + enet->tx = ctx->tx; + + for (i = 0; i < ctx->cfg.rx_ring_num; i++) { + rx = ctx->rx[i]; + tx = &ctx->tx[i]; + + rx->enet = enet; + tx->enet = enet; + } +} + +void enet_init_ctx(struct eea_net *enet, struct eea_net_init_ctx *ctx) +{ + memset(ctx, 0, sizeof(*ctx)); + + ctx->netdev = enet->netdev; + ctx->edev = enet->edev; + ctx->cfg = enet->cfg; +} + +static void eea_free_rxtx_q_mem(struct eea_net *enet) +{ + struct eea_net_rx *rx; + struct eea_net_tx *tx; + int i; + + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + rx = enet->rx[i]; + tx = &enet->tx[i]; + + eea_free_rx(rx); + eea_free_tx(tx); + } + + /* We called __netif_napi_del(), + * we need to respect an RCU grace period before freeing enet->rx + */ + synchronize_net(); + + kvfree(enet->rx); + kvfree(enet->tx); + + enet->rx = NULL; + enet->tx = NULL; +} + +/* alloc tx/rx: struct, ring, meta, pp, napi */ +static int eea_alloc_rxtx_q_mem(struct eea_net_init_ctx *ctx) +{ + struct eea_net_rx *rx; + struct eea_net_tx *tx; + int err, i; + + ctx->tx = kvcalloc(ctx->cfg.tx_ring_num, sizeof(*ctx->tx), GFP_KERNEL); + if (!ctx->tx) + return -ENOMEM; + + ctx->rx = kvcalloc(ctx->cfg.rx_ring_num, sizeof(*ctx->rx), GFP_KERNEL); + if (!ctx->rx) + goto err_free_tx; + + ctx->cfg.rx_sq_desc_size = sizeof(struct eea_rx_desc); + ctx->cfg.rx_cq_desc_size = sizeof(struct eea_rx_cdesc); + ctx->cfg.tx_sq_desc_size = sizeof(struct eea_tx_desc); + ctx->cfg.tx_cq_desc_size = sizeof(struct eea_tx_cdesc); + + ctx->cfg.tx_cq_desc_size /= 2; + + if (!ctx->cfg.split_hdr) + ctx->cfg.rx_sq_desc_size /= 2; + + for (i = 0; i < ctx->cfg.rx_ring_num; i++) { + rx = eea_alloc_rx(ctx, i); + if (!rx) + goto err_free; + + ctx->rx[i] = rx; + + tx = ctx->tx + i; + err = eea_alloc_tx(ctx, tx, i); + if (err) + goto err_free; + } + + return 0; + +err_free: + for (i = 0; i < ctx->cfg.rx_ring_num; i++) { + rx = ctx->rx[i]; + tx = ctx->tx + i; + + eea_free_rx(rx); + eea_free_tx(tx); + } + + kvfree(ctx->rx); + +err_free_tx: + kvfree(ctx->tx); + return -ENOMEM; +} + +static int eea_active_ring_and_irq(struct eea_net *enet) +{ + int err; + + err = eea_adminq_create_q(enet, /* qidx = */ 0, + enet->cfg.rx_ring_num + + enet->cfg.tx_ring_num, 0); + if (err) + return err; + + err = enet_rxtx_irq_setup(enet, 0, enet->cfg.rx_ring_num); + if (err) { + eea_adminq_destroy_all_q(enet); + return err; + } + + return 0; +} + +static int eea_unactive_ring_and_irq(struct eea_net *enet) +{ + struct eea_net_rx *rx; + int err, i; + + err = eea_adminq_destroy_all_q(enet); + if (err) + netdev_warn(enet->netdev, "unactive rxtx ring failed.\n"); + + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + rx = enet->rx[i]; + eea_irq_free(rx); + } + + return err; +} + +/* stop rx napi, stop tx queue. */ +static int eea_stop_rxtx(struct net_device *netdev) +{ + struct eea_net *enet = netdev_priv(netdev); + int i; + + netif_tx_disable(netdev); + + for (i = 0; i < enet->cfg.rx_ring_num; i++) + enet_rx_stop(enet->rx[i]); + + netif_carrier_off(netdev); + + return 0; +} + +static int eea_start_rxtx(struct net_device *netdev) +{ + struct eea_net *enet = netdev_priv(netdev); + int i, err; + + err = netif_set_real_num_queues(netdev, enet->cfg.tx_ring_num, + enet->cfg.rx_ring_num); + if (err) + return err; + + for (i = 0; i < enet->cfg.rx_ring_num; i++) + enet_rx_start(enet->rx[i]); + + netif_tx_start_all_queues(netdev); + netif_carrier_on(netdev); + + enet->started = true; + + return 0; +} + +static int eea_netdev_stop(struct net_device *netdev) +{ + struct eea_net *enet = netdev_priv(netdev); + + /* This function can be called during device anomaly recovery. To + * prevent duplicate stop operations, the `started` flag is introduced + * for checking. + */ + + if (!enet->started) { + netdev_warn(netdev, "eea netdev stop: but dev is not started.\n"); + return 0; + } + + eea_stop_rxtx(netdev); + eea_unactive_ring_and_irq(enet); + eea_free_rxtx_q_mem(enet); + + enet->started = false; + + return 0; +} + +static int eea_netdev_open(struct net_device *netdev) +{ + struct eea_net *enet = netdev_priv(netdev); + struct eea_net_init_ctx ctx; + int err; + + if (enet->link_err) { + netdev_err(netdev, "netdev open err, because link error: %d\n", + enet->link_err); + return -EBUSY; + } + + enet_init_ctx(enet, &ctx); + + err = eea_alloc_rxtx_q_mem(&ctx); + if (err) + return err; + + enet_bind_new_q_and_cfg(enet, &ctx); + + err = eea_active_ring_and_irq(enet); + if (err) + return err; + + return eea_start_rxtx(netdev); +} + +/* resources: ring, buffers, irq */ +int eea_reset_hw_resources(struct eea_net *enet, struct eea_net_init_ctx *ctx) +{ + int err; + + if (!netif_running(enet->netdev)) { + enet->cfg = ctx->cfg; + return 0; + } + + err = eea_alloc_rxtx_q_mem(ctx); + if (err) { + netdev_warn(enet->netdev, + "eea reset: alloc q failed. stop reset. err %d\n", + err); + return err; + } + + eea_netdev_stop(enet->netdev); + + enet_bind_new_q_and_cfg(enet, ctx); + + err = eea_active_ring_and_irq(enet); + if (err) { + netdev_warn(enet->netdev, + "eea reset: active new ring and irq failed. err %d\n", + err); + return err; + } + + err = eea_start_rxtx(enet->netdev); + if (err) + netdev_warn(enet->netdev, + "eea reset: start queue failed. err %d\n", err); + + return err; +} + +int eea_queues_check_and_reset(struct eea_device *edev) +{ + struct eea_aq_queue_status *qstatus; + struct eea_aq_dev_status *dstatus; + struct eea_aq_queue_status *qs; + struct eea_net_init_ctx ctx; + bool need_reset = false; + int num, i, err = 0; + + rtnl_lock(); + + num = edev->enet->cfg.tx_ring_num * 2 + 1; + + dstatus = eea_adminq_dev_status(edev->enet); + if (!dstatus) { + netdev_warn(edev->enet->netdev, "query queue status failed.\n"); + err = -ENOMEM; + goto err_unlock; + } + + if (le16_to_cpu(dstatus->link_status) == EEA_LINK_DOWN_STATUS) { + eea_netdev_stop(edev->enet->netdev); + edev->enet->link_err = EEA_LINK_ERR_LINK_DOWN; + netdev_warn(edev->enet->netdev, "device link is down. stop device.\n"); + goto err_free; + } + + qstatus = dstatus->q_status; + + for (i = 0; i < num; ++i) { + qs = &qstatus[i]; + + if (le16_to_cpu(qs->status) == EEA_QUEUE_STATUS_NEED_RESET) { + netdev_warn(edev->enet->netdev, + "queue status: queue %u needs to reset\n", + le16_to_cpu(qs->qidx)); + need_reset = true; + } + } + + if (need_reset) { + enet_init_ctx(edev->enet, &ctx); + err = eea_reset_hw_resources(edev->enet, &ctx); + } + +err_free: + kfree(dstatus); + +err_unlock: + rtnl_unlock(); + return err; +} + +static void eea_update_cfg(struct eea_net *enet, + struct eea_device *edev, + struct eea_aq_cfg *hwcfg) +{ + enet->cfg_hw.rx_ring_depth = le32_to_cpu(hwcfg->rx_depth_max); + enet->cfg_hw.tx_ring_depth = le32_to_cpu(hwcfg->tx_depth_max); + + enet->cfg_hw.rx_ring_num = edev->rx_num; + enet->cfg_hw.tx_ring_num = edev->tx_num; + + enet->cfg.rx_ring_depth = le32_to_cpu(hwcfg->rx_depth_def); + enet->cfg.tx_ring_depth = le32_to_cpu(hwcfg->tx_depth_def); + + enet->cfg.rx_ring_num = edev->rx_num; + enet->cfg.tx_ring_num = edev->tx_num; + + enet->cfg_hw.split_hdr = EEA_SPLIT_HDR_SIZE; +} + +static int eea_netdev_init_features(struct net_device *netdev, + struct eea_net *enet, + struct eea_device *edev) +{ + struct eea_aq_cfg *cfg; + int err; + u32 mtu; + + cfg = kmalloc(sizeof(*cfg), GFP_KERNEL); + if (!cfg) + return -ENOMEM; + + err = eea_adminq_query_cfg(enet, cfg); + if (err) + goto err_free; + + mtu = le16_to_cpu(cfg->mtu); + if (mtu < ETH_MIN_MTU) { + dev_err(edev->dma_dev, "The device gave us an invalid MTU. Here we can only exit the initialization. %u < %u\n", + mtu, ETH_MIN_MTU); + err = -EINVAL; + goto err_free; + } + + eea_update_cfg(enet, edev, cfg); + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + + netdev->hw_features |= NETIF_F_HW_CSUM; + netdev->hw_features |= NETIF_F_GRO_HW; + netdev->hw_features |= NETIF_F_SG; + netdev->hw_features |= NETIF_F_TSO; + netdev->hw_features |= NETIF_F_TSO_ECN; + netdev->hw_features |= NETIF_F_TSO6; + netdev->hw_features |= NETIF_F_GSO_UDP_L4; + + netdev->features |= NETIF_F_HIGHDMA; + netdev->features |= NETIF_F_HW_CSUM; + netdev->features |= NETIF_F_SG; + netdev->features |= NETIF_F_GSO_ROBUST; + netdev->features |= netdev->hw_features & NETIF_F_ALL_TSO; + netdev->features |= NETIF_F_RXCSUM; + netdev->features |= NETIF_F_GRO_HW; + + netdev->vlan_features = netdev->features; + + eth_hw_addr_set(netdev, cfg->mac); + + enet->speed = SPEED_UNKNOWN; + enet->duplex = DUPLEX_UNKNOWN; + + netdev->min_mtu = ETH_MIN_MTU; + + netdev->mtu = mtu; + + /* If jumbo frames are already enabled, then the returned MTU will be a + * jumbo MTU, and the driver will automatically enable jumbo frame + * support by default. + */ + netdev->max_mtu = mtu; + + netif_carrier_on(netdev); + +err_free: + kfree(cfg); + return err; +} + +static const struct net_device_ops eea_netdev = { + .ndo_open = eea_netdev_open, + .ndo_stop = eea_netdev_stop, + .ndo_start_xmit = eea_tx_xmit, + .ndo_validate_addr = eth_validate_addr, + .ndo_get_stats64 = eea_stats, + .ndo_features_check = passthru_features_check, + .ndo_tx_timeout = eea_tx_timeout, +}; + +static struct eea_net *eea_netdev_alloc(struct eea_device *edev, u32 pairs) +{ + struct net_device *netdev; + struct eea_net *enet; + + netdev = alloc_etherdev_mq(sizeof(struct eea_net), pairs); + if (!netdev) { + dev_err(edev->dma_dev, + "alloc_etherdev_mq failed with pairs %d\n", pairs); + return NULL; + } + + netdev->netdev_ops = &eea_netdev; + netdev->ethtool_ops = &eea_ethtool_ops; + SET_NETDEV_DEV(netdev, edev->dma_dev); + + enet = netdev_priv(netdev); + enet->netdev = netdev; + enet->edev = edev; + edev->enet = enet; + + return enet; +} + +static void eea_update_ts_off(struct eea_device *edev, struct eea_net *enet) +{ + u64 ts; + + ts = eea_pci_device_ts(edev); + + enet->hw_ts_offset = ktime_get_real() - ts; +} + +static int eea_net_reprobe(struct eea_device *edev) +{ + struct eea_net *enet = edev->enet; + int err = 0; + + enet->edev = edev; + + if (!enet->adminq.ring) { + err = eea_create_adminq(enet, edev->rx_num + edev->tx_num); + if (err) + return err; + } + + eea_update_ts_off(edev, enet); + + if (edev->ha_reset_netdev_running) { + rtnl_lock(); + enet->link_err = 0; + err = eea_netdev_open(enet->netdev); + rtnl_unlock(); + } + + return err; +} + +int eea_net_probe(struct eea_device *edev) +{ + struct eea_net *enet; + int err = -ENOMEM; + + if (edev->ha_reset) + return eea_net_reprobe(edev); + + enet = eea_netdev_alloc(edev, edev->rx_num); + if (!enet) + return -ENOMEM; + + err = eea_create_adminq(enet, edev->rx_num + edev->tx_num); + if (err) + goto err_free_netdev; + + err = eea_adminq_config_host_info(enet); + if (err) + goto err_reset_dev; + + err = eea_netdev_init_features(enet->netdev, enet, edev); + if (err) + goto err_reset_dev; + + err = register_netdev(enet->netdev); + if (err) + goto err_reset_dev; + + eea_update_ts_off(edev, enet); + netif_carrier_off(enet->netdev); + + netdev_dbg(enet->netdev, "eea probe success.\n"); + + return 0; + +err_reset_dev: + eea_device_reset(edev); + eea_destroy_adminq(enet); + +err_free_netdev: + free_netdev(enet->netdev); + return err; +} + +void eea_net_remove(struct eea_device *edev) +{ + struct net_device *netdev; + struct eea_net *enet; + + enet = edev->enet; + netdev = enet->netdev; + + if (edev->ha_reset) { + edev->ha_reset_netdev_running = false; + if (netif_running(enet->netdev)) { + rtnl_lock(); + eea_netdev_stop(enet->netdev); + enet->link_err = EEA_LINK_ERR_HA_RESET_DEV; + enet->edev = NULL; + rtnl_unlock(); + edev->ha_reset_netdev_running = true; + } + } else { + unregister_netdev(netdev); + netdev_dbg(enet->netdev, "eea removed.\n"); + } + + eea_device_reset(edev); + + eea_destroy_adminq(enet); + + if (!edev->ha_reset) + free_netdev(netdev); +} diff --git a/drivers/net/ethernet/alibaba/eea/eea_net.h b/drivers/net/ethernet/alibaba/eea/eea_net.h new file mode 100644 index 0000000000000..d98a1a94d86e5 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_net.h @@ -0,0 +1,196 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#ifndef __EEA_NET_H__ +#define __EEA_NET_H__ + +#include +#include + +#include "eea_adminq.h" +#include "eea_ethtool.h" +#include "eea_ring.h" + +#define EEA_VER_MAJOR 1 +#define EEA_VER_MINOR 0 +#define EEA_VER_SUB_MINOR 0 + +struct eea_tx_meta; + +struct eea_reprobe { + struct eea_net *enet; + bool running_before_reprobe; +}; + +struct eea_net_tx { + struct eea_net *enet; + + struct eea_ring *ering; + + struct eea_tx_meta *meta; + struct eea_tx_meta *free; + + struct device *dma_dev; + + u32 index; + + char name[16]; + + struct eea_tx_stats stats; +}; + +struct eea_rx_meta { + struct eea_rx_meta *next; + + struct page *page; + dma_addr_t dma; + u32 offset; + u32 frags; + + struct page *hdr_page; + void *hdr_addr; + dma_addr_t hdr_dma; + + u32 id; + + u32 truesize; + u32 headroom; + u32 tailroom; + u32 room; + + u32 len; +}; + +struct eea_net_rx_pkt_ctx { + u16 idx; + + bool data_valid; + bool do_drop; + + struct sk_buff *head_skb; + struct sk_buff *curr_skb; +}; + +struct eea_net_rx { + struct eea_net *enet; + + struct eea_ring *ering; + + struct eea_rx_meta *meta; + struct eea_rx_meta *free; + + struct device *dma_dev; + + u32 index; + + u32 flags; + + u32 headroom; + + struct napi_struct napi; + + struct eea_rx_stats stats; + + u16 irq_n; + + char name[16]; + + struct eea_net_rx_pkt_ctx pkt; + + struct page_pool *pp; +}; + +struct eea_net_cfg { + u32 rx_ring_depth; + u32 tx_ring_depth; + u32 rx_ring_num; + u32 tx_ring_num; + + u8 rx_sq_desc_size; + u8 rx_cq_desc_size; + u8 tx_sq_desc_size; + u8 tx_cq_desc_size; + + u32 split_hdr; + + struct hwtstamp_config ts_cfg; +}; + +struct eea_net_init_ctx { + struct eea_net_cfg cfg; + + struct eea_net_tx *tx; + struct eea_net_rx **rx; + + struct net_device *netdev; + struct eea_device *edev; +}; + +enum { + EEA_LINK_ERR_NONE, + EEA_LINK_ERR_HA_RESET_DEV, + EEA_LINK_ERR_LINK_DOWN, +}; + +struct eea_net { + struct eea_device *edev; + struct net_device *netdev; + + struct eea_aq adminq; + + struct eea_net_tx *tx; + struct eea_net_rx **rx; + + struct eea_net_cfg cfg; + struct eea_net_cfg cfg_hw; + + u32 link_err; + + bool started; + bool cpu_aff_set; + + u8 duplex; + u32 speed; + + u64 hw_ts_offset; +}; + +int eea_tx_resize(struct eea_net *enet, struct eea_net_tx *tx, u32 ring_num); + +int eea_net_probe(struct eea_device *edev); +void eea_net_remove(struct eea_device *edev); +int eea_net_freeze(struct eea_device *edev); +int eea_net_restore(struct eea_device *edev); + +int eea_reset_hw_resources(struct eea_net *enet, struct eea_net_init_ctx *ctx); +void enet_init_ctx(struct eea_net *enet, struct eea_net_init_ctx *ctx); +int eea_queues_check_and_reset(struct eea_device *edev); + +/* rx apis */ +int eea_poll(struct napi_struct *napi, int budget); + +void enet_rx_stop(struct eea_net_rx *rx); +void enet_rx_start(struct eea_net_rx *rx); + +void eea_free_rx(struct eea_net_rx *rx); +struct eea_net_rx *eea_alloc_rx(struct eea_net_init_ctx *ctx, u32 idx); + +void eea_irq_free(struct eea_net_rx *rx); + +int enet_rxtx_irq_setup(struct eea_net *enet, u32 qid, u32 num); + +/* tx apis */ +int eea_poll_tx(struct eea_net_tx *tx, int budget); +void eea_poll_cleantx(struct eea_net_rx *rx); +netdev_tx_t eea_tx_xmit(struct sk_buff *skb, struct net_device *netdev); + +void eea_tx_timeout(struct net_device *netdev, u32 txqueue); + +void eea_free_tx(struct eea_net_tx *tx); +int eea_alloc_tx(struct eea_net_init_ctx *ctx, struct eea_net_tx *tx, u32 idx); + +#endif diff --git a/drivers/net/ethernet/alibaba/eea/eea_pci.c b/drivers/net/ethernet/alibaba/eea/eea_pci.c new file mode 100644 index 0000000000000..06f733147f8d5 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_pci.c @@ -0,0 +1,585 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include +#include + +#include "eea_net.h" +#include "eea_pci.h" + +#define EEA_PCI_DB_OFFSET 4096 + +#define EEA_PCI_CAP_RESET_DEVICE 0xFA +#define EEA_PCI_CAP_RESET_FLAG BIT(1) + +struct eea_pci_cfg { + __le32 reserve0; + __le32 reserve1; + __le32 drv_f_idx; + __le32 drv_f; + +#define EEA_S_OK BIT(2) +#define EEA_S_FEATURE_DONE BIT(3) +#define EEA_S_FAILED BIT(7) + u8 device_status; + u8 reserved[7]; + + __le32 rx_num_max; + __le32 tx_num_max; + __le32 db_blk_size; + + /* admin queue cfg */ + __le16 aq_size; + __le16 aq_msix_vector; + __le32 aq_db_off; + + __le32 aq_sq_addr; + __le32 aq_sq_addr_hi; + __le32 aq_cq_addr; + __le32 aq_cq_addr_hi; + + __le64 hw_ts; +}; + +struct eea_pci_device { + struct eea_device edev; + struct pci_dev *pci_dev; + + u32 msix_vec_n; + + void __iomem *reg; + void __iomem *db_base; + + struct work_struct ha_handle_work; + char ha_irq_name[32]; + u8 reset_pos; +}; + +#define cfg_pointer(reg, item) \ + ((void __iomem *)((reg) + offsetof(struct eea_pci_cfg, item))) + +#define cfg_write8(reg, item, val) iowrite8(val, cfg_pointer(reg, item)) +#define cfg_write16(reg, item, val) iowrite16(val, cfg_pointer(reg, item)) +#define cfg_write32(reg, item, val) iowrite32(val, cfg_pointer(reg, item)) +#define cfg_write64(reg, item, val) iowrite64_lo_hi(val, cfg_pointer(reg, item)) + +#define cfg_read8(reg, item) ioread8(cfg_pointer(reg, item)) +#define cfg_read32(reg, item) ioread32(cfg_pointer(reg, item)) +#define cfg_readq(reg, item) readq(cfg_pointer(reg, item)) + +/* Due to circular references, we have to add function definitions here. */ +static int __eea_pci_probe(struct pci_dev *pci_dev, + struct eea_pci_device *ep_dev); +static void __eea_pci_remove(struct pci_dev *pci_dev, bool flush_ha_work); + +const char *eea_pci_name(struct eea_device *edev) +{ + return pci_name(edev->ep_dev->pci_dev); +} + +int eea_pci_domain_nr(struct eea_device *edev) +{ + return pci_domain_nr(edev->ep_dev->pci_dev->bus); +} + +u16 eea_pci_dev_id(struct eea_device *edev) +{ + return pci_dev_id(edev->ep_dev->pci_dev); +} + +static void eea_pci_io_set_status(struct eea_device *edev, u8 status) +{ + struct eea_pci_device *ep_dev = edev->ep_dev; + + cfg_write8(ep_dev->reg, device_status, status); +} + +static u8 eea_pci_io_get_status(struct eea_device *edev) +{ + struct eea_pci_device *ep_dev = edev->ep_dev; + + return cfg_read8(ep_dev->reg, device_status); +} + +static void eea_add_status(struct eea_device *dev, u32 status) +{ + eea_pci_io_set_status(dev, eea_pci_io_get_status(dev) | status); +} + +#define EEA_RESET_TIMEOUT_US (1000 * 1000 * 1000) + +int eea_device_reset(struct eea_device *edev) +{ + struct eea_pci_device *ep_dev = edev->ep_dev; + int i, err; + u8 val; + + eea_pci_io_set_status(edev, 0); + + err = read_poll_timeout(cfg_read8, val, !val, 20, EEA_RESET_TIMEOUT_US, + false, ep_dev->reg, device_status); + if (err) + return -EBUSY; + + for (i = 0; i < ep_dev->msix_vec_n; ++i) + synchronize_irq(pci_irq_vector(ep_dev->pci_dev, i)); + + return 0; +} + +void eea_device_ready(struct eea_device *dev) +{ + u8 status = eea_pci_io_get_status(dev); + + WARN_ON(status & EEA_S_OK); + + eea_pci_io_set_status(dev, status | EEA_S_OK); +} + +static int eea_negotiate(struct eea_device *edev) +{ + struct eea_pci_device *ep_dev; + u32 status; + + ep_dev = edev->ep_dev; + + edev->features = 0; + + cfg_write32(ep_dev->reg, drv_f_idx, 0); + cfg_write32(ep_dev->reg, drv_f, (u32)edev->features); + cfg_write32(ep_dev->reg, drv_f_idx, 1); + cfg_write32(ep_dev->reg, drv_f, edev->features >> 32); + + eea_add_status(edev, EEA_S_FEATURE_DONE); + status = eea_pci_io_get_status(edev); + if (!(status & EEA_S_FEATURE_DONE)) + return -ENODEV; + + return 0; +} + +static void eea_pci_release_resource(struct eea_pci_device *ep_dev) +{ + struct pci_dev *pci_dev = ep_dev->pci_dev; + + if (ep_dev->reg) { + pci_iounmap(pci_dev, ep_dev->reg); + ep_dev->reg = NULL; + } + + if (ep_dev->msix_vec_n) { + ep_dev->msix_vec_n = 0; + pci_free_irq_vectors(ep_dev->pci_dev); + } + + pci_release_regions(pci_dev); + pci_disable_device(pci_dev); +} + +static int eea_pci_setup(struct pci_dev *pci_dev, struct eea_pci_device *ep_dev) +{ + int err, n; + + ep_dev->pci_dev = pci_dev; + + err = pci_enable_device(pci_dev); + if (err) + return err; + + err = pci_request_regions(pci_dev, "EEA"); + if (err) + goto err_disable_dev; + + pci_set_master(pci_dev); + + err = dma_set_mask_and_coherent(&pci_dev->dev, DMA_BIT_MASK(64)); + if (err) { + dev_warn(&pci_dev->dev, "Failed to enable 64-bit DMA.\n"); + goto err_release_regions; + } + + ep_dev->reg = pci_iomap(pci_dev, 0, 0); + if (!ep_dev->reg) { + dev_err(&pci_dev->dev, "Failed to map pci bar!\n"); + err = -ENOMEM; + goto err_release_regions; + } + + ep_dev->edev.rx_num = cfg_read32(ep_dev->reg, rx_num_max); + ep_dev->edev.tx_num = cfg_read32(ep_dev->reg, tx_num_max); + + /* 2: adminq, error handle*/ + n = ep_dev->edev.rx_num + ep_dev->edev.tx_num + 2; + err = pci_alloc_irq_vectors(ep_dev->pci_dev, n, n, PCI_IRQ_MSIX); + if (err < 0) + goto err_unmap_reg; + + ep_dev->msix_vec_n = n; + + ep_dev->db_base = ep_dev->reg + EEA_PCI_DB_OFFSET; + ep_dev->edev.db_blk_size = cfg_read32(ep_dev->reg, db_blk_size); + + return 0; + +err_unmap_reg: + pci_iounmap(pci_dev, ep_dev->reg); + ep_dev->reg = NULL; + +err_release_regions: + pci_release_regions(pci_dev); + +err_disable_dev: + pci_disable_device(pci_dev); + + return err; +} + +void __iomem *eea_pci_db_addr(struct eea_device *edev, u32 off) +{ + return edev->ep_dev->db_base + off; +} + +void eea_pci_active_aq(struct eea_ring *ering) +{ + struct eea_pci_device *ep_dev = ering->edev->ep_dev; + + cfg_write16(ep_dev->reg, aq_size, ering->num); + cfg_write16(ep_dev->reg, aq_msix_vector, ering->msix_vec); + + cfg_write64(ep_dev->reg, aq_sq_addr, ering->sq.dma_addr); + cfg_write64(ep_dev->reg, aq_cq_addr, ering->cq.dma_addr); + + ering->db = eea_pci_db_addr(ering->edev, + cfg_read32(ep_dev->reg, aq_db_off)); +} + +void eea_pci_free_irq(struct eea_ring *ering, void *data) +{ + struct eea_pci_device *ep_dev = ering->edev->ep_dev; + int irq; + + irq = pci_irq_vector(ep_dev->pci_dev, ering->msix_vec); + irq_update_affinity_hint(irq, NULL); + free_irq(irq, data); +} + +int eea_pci_request_irq(struct eea_ring *ering, + irqreturn_t (*callback)(int irq, void *data), + void *data) +{ + struct eea_pci_device *ep_dev = ering->edev->ep_dev; + int irq; + + snprintf(ering->irq_name, sizeof(ering->irq_name), "eea-q%d@%s", + ering->index / 2, pci_name(ep_dev->pci_dev)); + + irq = pci_irq_vector(ep_dev->pci_dev, ering->msix_vec); + + return request_irq(irq, callback, 0, ering->irq_name, data); +} + +static int eea_ha_handle_reset(struct eea_pci_device *ep_dev) +{ + struct eea_device *edev; + struct pci_dev *pci_dev; + u16 reset; + + if (!ep_dev->reset_pos) + return 0; + + edev = &ep_dev->edev; + + pci_read_config_word(ep_dev->pci_dev, ep_dev->reset_pos, &reset); + + /* clear bit */ + pci_write_config_word(ep_dev->pci_dev, ep_dev->reset_pos, 0xFFFF); + + if (reset & EEA_PCI_CAP_RESET_FLAG) { + dev_warn(&ep_dev->pci_dev->dev, "recv device reset request.\n"); + + pci_dev = ep_dev->pci_dev; + + /* The pci remove callback may hold this lock. If the + * pci remove callback is called, then we can ignore the + * ha interrupt. + */ + if (mutex_trylock(&edev->ha_lock)) { + edev->ha_reset = true; + + __eea_pci_remove(pci_dev, false); + __eea_pci_probe(pci_dev, ep_dev); + + edev->ha_reset = false; + mutex_unlock(&edev->ha_lock); + } else { + dev_warn(&ep_dev->pci_dev->dev, + "ha device reset: trylock failed.\n"); + } + + return 1; + } + + return 0; +} + +/* ha handle code */ +static void eea_ha_handle_work(struct work_struct *work) +{ + struct eea_pci_device *ep_dev; + int done; + + ep_dev = container_of(work, struct eea_pci_device, ha_handle_work); + + /* Ha interrupt is triggered, so there maybe some error, we may need to + * reset the device or reset some queues. + */ + dev_warn(&ep_dev->pci_dev->dev, "recv ha interrupt.\n"); + + done = eea_ha_handle_reset(ep_dev); + if (done) + return; + + eea_queues_check_and_reset(&ep_dev->edev); +} + +static irqreturn_t eea_pci_ha_handle(int irq, void *data) +{ + struct eea_device *edev = data; + + schedule_work(&edev->ep_dev->ha_handle_work); + + return IRQ_HANDLED; +} + +static void eea_pci_free_ha_irq(struct eea_device *edev) +{ + struct eea_pci_device *ep_dev = edev->ep_dev; + int irq = pci_irq_vector(ep_dev->pci_dev, 0); + + free_irq(irq, edev); +} + +static int eea_pci_ha_init(struct eea_device *edev, struct pci_dev *pci_dev) +{ + u8 pos, cfg_type_off, type, cfg_drv_off, cfg_dev_off; + struct eea_pci_device *ep_dev = edev->ep_dev; + int irq; + + cfg_type_off = offsetof(struct eea_pci_cap, cfg_type); + cfg_drv_off = offsetof(struct eea_pci_reset_reg, driver); + cfg_dev_off = offsetof(struct eea_pci_reset_reg, device); + + for (pos = pci_find_capability(pci_dev, PCI_CAP_ID_VNDR); + pos > 0; + pos = pci_find_next_capability(pci_dev, pos, PCI_CAP_ID_VNDR)) { + pci_read_config_byte(pci_dev, pos + cfg_type_off, &type); + + if (type == EEA_PCI_CAP_RESET_DEVICE) { + /* notify device, driver support this feature. */ + pci_write_config_word(pci_dev, pos + cfg_drv_off, + EEA_PCI_CAP_RESET_FLAG); + pci_write_config_word(pci_dev, pos + cfg_dev_off, + 0xFFFF); + + edev->ep_dev->reset_pos = pos + cfg_dev_off; + goto found; + } + } + + dev_warn(&edev->ep_dev->pci_dev->dev, "Not Found reset cap.\n"); + +found: + snprintf(ep_dev->ha_irq_name, sizeof(ep_dev->ha_irq_name), "eea-ha@%s", + pci_name(ep_dev->pci_dev)); + + irq = pci_irq_vector(ep_dev->pci_dev, 0); + + INIT_WORK(&ep_dev->ha_handle_work, eea_ha_handle_work); + + return request_irq(irq, eea_pci_ha_handle, 0, + ep_dev->ha_irq_name, edev); +} + +u64 eea_pci_device_ts(struct eea_device *edev) +{ + struct eea_pci_device *ep_dev = edev->ep_dev; + + return cfg_readq(ep_dev->reg, hw_ts); +} + +static int eea_init_device(struct eea_device *edev) +{ + int err; + + err = eea_device_reset(edev); + if (err) + return err; + + eea_pci_io_set_status(edev, BIT(0) | BIT(1)); + + err = eea_negotiate(edev); + if (err) + goto err; + + err = eea_net_probe(edev); + if (err) + goto err; + + return 0; +err: + eea_add_status(edev, EEA_S_FAILED); + return err; +} + +static int __eea_pci_probe(struct pci_dev *pci_dev, + struct eea_pci_device *ep_dev) +{ + struct eea_device *edev; + int err; + + pci_set_drvdata(pci_dev, ep_dev); + + edev = &ep_dev->edev; + + err = eea_pci_setup(pci_dev, ep_dev); + if (err) + return err; + + err = eea_init_device(&ep_dev->edev); + if (err) + goto err_pci_rel; + + err = eea_pci_ha_init(edev, pci_dev); + if (err) + goto err_net_rm; + + return 0; + +err_net_rm: + eea_net_remove(edev); + +err_pci_rel: + eea_pci_release_resource(ep_dev); + return err; +} + +static void __eea_pci_remove(struct pci_dev *pci_dev, bool flush_ha_work) +{ + struct eea_pci_device *ep_dev = pci_get_drvdata(pci_dev); + struct device *dev = get_device(&ep_dev->pci_dev->dev); + struct eea_device *edev = &ep_dev->edev; + + eea_pci_free_ha_irq(edev); + + if (flush_ha_work) + flush_work(&ep_dev->ha_handle_work); + + eea_net_remove(edev); + + pci_disable_sriov(pci_dev); + + eea_pci_release_resource(ep_dev); + + put_device(dev); +} + +static int eea_pci_probe(struct pci_dev *pci_dev, + const struct pci_device_id *id) +{ + struct eea_pci_device *ep_dev; + struct eea_device *edev; + int err; + + ep_dev = kzalloc(sizeof(*ep_dev), GFP_KERNEL); + if (!ep_dev) + return -ENOMEM; + + edev = &ep_dev->edev; + + edev->ep_dev = ep_dev; + edev->dma_dev = &pci_dev->dev; + + ep_dev->pci_dev = pci_dev; + + mutex_init(&edev->ha_lock); + + err = __eea_pci_probe(pci_dev, ep_dev); + if (err) + kfree(ep_dev); + + return err; +} + +static void eea_pci_remove(struct pci_dev *pci_dev) +{ + struct eea_pci_device *ep_dev = pci_get_drvdata(pci_dev); + struct eea_device *edev; + + edev = &ep_dev->edev; + + mutex_lock(&edev->ha_lock); + __eea_pci_remove(pci_dev, true); + mutex_unlock(&edev->ha_lock); + + kfree(ep_dev); +} + +static int eea_pci_sriov_configure(struct pci_dev *pci_dev, int num_vfs) +{ + struct eea_pci_device *ep_dev = pci_get_drvdata(pci_dev); + struct eea_device *edev = &ep_dev->edev; + int ret; + + if (!(eea_pci_io_get_status(edev) & EEA_S_OK)) + return -EBUSY; + + if (pci_vfs_assigned(pci_dev)) + return -EPERM; + + if (num_vfs == 0) { + pci_disable_sriov(pci_dev); + return 0; + } + + ret = pci_enable_sriov(pci_dev, num_vfs); + if (ret < 0) + return ret; + + return num_vfs; +} + +static const struct pci_device_id eea_pci_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_ALIBABA, 0x500B) }, + { 0 } +}; + +MODULE_DEVICE_TABLE(pci, eea_pci_id_table); + +static struct pci_driver eea_pci_driver = { + .name = "eea", + .id_table = eea_pci_id_table, + .probe = eea_pci_probe, + .remove = eea_pci_remove, + .sriov_configure = eea_pci_sriov_configure, +}; + +static __init int eea_pci_init(void) +{ + return pci_register_driver(&eea_pci_driver); +} + +static __exit void eea_pci_exit(void) +{ + pci_unregister_driver(&eea_pci_driver); +} + +module_init(eea_pci_init); +module_exit(eea_pci_exit); + +MODULE_DESCRIPTION("Driver for Alibaba Elastic Ethernet Adapter"); +MODULE_AUTHOR("Xuan Zhuo "); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/alibaba/eea/eea_pci.h b/drivers/net/ethernet/alibaba/eea/eea_pci.h new file mode 100644 index 0000000000000..cdddb465d9564 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_pci.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#ifndef __EEA_PCI_H__ +#define __EEA_PCI_H__ + +#include + +#include "eea_net.h" +#include "eea_ring.h" + +struct eea_pci_cap { + __u8 cap_vndr; + __u8 cap_next; + __u8 cap_len; + __u8 cfg_type; +}; + +struct eea_pci_reset_reg { + struct eea_pci_cap cap; + __le16 driver; + __le16 device; +}; + +struct eea_pci_device; + +struct eea_device { + struct eea_pci_device *ep_dev; + struct device *dma_dev; + struct eea_net *enet; + + u64 features; + + bool ha_reset; + bool ha_reset_netdev_running; + + /* ha lock for the race between ha work and pci remove */ + struct mutex ha_lock; + + u32 rx_num; + u32 tx_num; + u32 db_blk_size; +}; + +const char *eea_pci_name(struct eea_device *edev); +int eea_pci_domain_nr(struct eea_device *edev); +u16 eea_pci_dev_id(struct eea_device *edev); + +int eea_device_reset(struct eea_device *dev); +void eea_device_ready(struct eea_device *dev); +void eea_pci_active_aq(struct eea_ring *ering); + +int eea_pci_request_irq(struct eea_ring *ering, + irqreturn_t (*callback)(int irq, void *data), + void *data); +void eea_pci_free_irq(struct eea_ring *ering, void *data); + +u64 eea_pci_device_ts(struct eea_device *edev); + +int eea_pci_set_affinity(struct eea_ring *ering, + const struct cpumask *cpu_mask); +void __iomem *eea_pci_db_addr(struct eea_device *edev, u32 off); +#endif diff --git a/drivers/net/ethernet/alibaba/eea/eea_ring.c b/drivers/net/ethernet/alibaba/eea/eea_ring.c new file mode 100644 index 0000000000000..f05745474ecfb --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_ring.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include "eea_pci.h" +#include "eea_ring.h" + +void ering_irq_unactive(struct eea_ring *ering) +{ + union { + u64 data; + struct eea_db db; + } val; + + if (ering->mask == EEA_IRQ_MASK) + return; + + ering->mask = EEA_IRQ_MASK; + + val.db.kick_flags = EEA_IRQ_MASK; + + writeq(val.data, (void __iomem *)ering->db); +} + +void ering_irq_active(struct eea_ring *ering, struct eea_ring *tx_ering) +{ + union { + u64 data; + struct eea_db db; + } val; + + if (ering->mask == EEA_IRQ_UNMASK) + return; + + ering->mask = EEA_IRQ_UNMASK; + + val.db.kick_flags = EEA_IRQ_UNMASK; + + val.db.tx_cq_head = cpu_to_le16(tx_ering->cq.hw_idx); + val.db.rx_cq_head = cpu_to_le16(ering->cq.hw_idx); + + writeq(val.data, ering->db); +} + +void *ering_cq_get_desc(const struct eea_ring *ering) +{ + u8 phase; + u8 *desc; + + desc = ering->cq.desc + (ering->cq.head << ering->cq.desc_size_shift); + + phase = *(u8 *)(desc + ering->cq.desc_size - 1); + + if ((phase & EEA_RING_DESC_F_CQ_PHASE) == ering->cq.phase) { + dma_rmb(); + return desc; + } + + return NULL; +} + +/* sq api */ +void *ering_sq_alloc_desc(struct eea_ring *ering, u16 id, bool is_last, + u16 flags) +{ + struct eea_ring_sq *sq = &ering->sq; + struct eea_common_desc *desc; + + if (!sq->shadow_num) { + sq->shadow_idx = sq->head; + sq->shadow_id = cpu_to_le16(id); + } + + if (!is_last) + flags |= EEA_RING_DESC_F_MORE; + + desc = sq->desc + (sq->shadow_idx << sq->desc_size_shift); + + desc->flags = cpu_to_le16(flags); + desc->id = sq->shadow_id; + + if (unlikely(++sq->shadow_idx >= ering->num)) + sq->shadow_idx = 0; + + ++sq->shadow_num; + + return desc; +} + +/* alloc desc for adminq */ +void *ering_aq_alloc_desc(struct eea_ring *ering) +{ + struct eea_ring_sq *sq = &ering->sq; + struct eea_common_desc *desc; + + sq->shadow_idx = sq->head; + + desc = sq->desc + (sq->shadow_idx << sq->desc_size_shift); + + if (unlikely(++sq->shadow_idx >= ering->num)) + sq->shadow_idx = 0; + + ++sq->shadow_num; + + return desc; +} + +void ering_sq_commit_desc(struct eea_ring *ering) +{ + struct eea_ring_sq *sq = &ering->sq; + int num; + + num = sq->shadow_num; + + ering->num_free -= num; + + sq->head = sq->shadow_idx; + sq->hw_idx += num; + sq->shadow_num = 0; +} + +void ering_sq_cancel(struct eea_ring *ering) +{ + ering->sq.shadow_num = 0; +} + +/* cq api */ +void ering_cq_ack_desc(struct eea_ring *ering, u32 num) +{ + struct eea_ring_cq *cq = &ering->cq; + + cq->head += num; + cq->hw_idx += num; + + if (unlikely(cq->head >= ering->num)) { + cq->head -= ering->num; + cq->phase ^= EEA_RING_DESC_F_CQ_PHASE; + } + + ering->num_free += num; +} + +/* notify */ +bool ering_kick(struct eea_ring *ering) +{ + union { + struct eea_db db; + u64 data; + } val; + + val.db.kick_flags = EEA_IDX_PRESENT; + val.db.idx = cpu_to_le16(ering->sq.hw_idx); + + writeq(val.data, ering->db); + + return true; +} + +/* ering alloc/free */ +static void ering_free_queue(struct eea_device *edev, size_t size, + void *queue, dma_addr_t dma_handle) +{ + dma_free_coherent(edev->dma_dev, size, queue, dma_handle); +} + +static void *ering_alloc_queue(struct eea_device *edev, size_t size, + dma_addr_t *dma_handle) +{ + gfp_t flags = GFP_KERNEL | __GFP_NOWARN; + + return dma_alloc_coherent(edev->dma_dev, size, dma_handle, flags); +} + +static int ering_alloc_queues(struct eea_ring *ering, struct eea_device *edev, + u32 num, u8 sq_desc_size, u8 cq_desc_size) +{ + dma_addr_t addr; + size_t size; + void *ring; + + size = num * sq_desc_size; + + ring = ering_alloc_queue(edev, size, &addr); + if (!ring) + return -ENOMEM; + + ering->sq.desc = ring; + ering->sq.dma_addr = addr; + ering->sq.dma_size = size; + ering->sq.desc_size = sq_desc_size; + ering->sq.desc_size_shift = fls(sq_desc_size) - 1; + + size = num * cq_desc_size; + + ring = ering_alloc_queue(edev, size, &addr); + if (!ring) + goto err_free_sq; + + ering->cq.desc = ring; + ering->cq.dma_addr = addr; + ering->cq.dma_size = size; + ering->cq.desc_size = cq_desc_size; + ering->cq.desc_size_shift = fls(cq_desc_size) - 1; + + ering->num = num; + + return 0; + +err_free_sq: + ering_free_queue(ering->edev, ering->sq.dma_size, + ering->sq.desc, ering->sq.dma_addr); + return -ENOMEM; +} + +static void ering_init(struct eea_ring *ering) +{ + ering->cq.phase = EEA_RING_DESC_F_CQ_PHASE; + ering->num_free = ering->num; +} + +struct eea_ring *ering_alloc(u32 index, u32 num, struct eea_device *edev, + u8 sq_desc_size, u8 cq_desc_size, + const char *name) +{ + struct eea_ring *ering; + + ering = kzalloc(sizeof(*ering), GFP_KERNEL); + if (!ering) + return NULL; + + ering->edev = edev; + ering->name = name; + ering->index = index; + ering->msix_vec = index / 2 + 1; /* vec 0 is for error notify. */ + + if (ering_alloc_queues(ering, edev, num, sq_desc_size, cq_desc_size)) + goto err_free; + + ering_init(ering); + + return ering; + +err_free: + kfree(ering); + return NULL; +} + +void ering_free(struct eea_ring *ering) +{ + ering_free_queue(ering->edev, ering->cq.dma_size, + ering->cq.desc, ering->cq.dma_addr); + + ering_free_queue(ering->edev, ering->sq.dma_size, + ering->sq.desc, ering->sq.dma_addr); + + kfree(ering); +} diff --git a/drivers/net/ethernet/alibaba/eea/eea_ring.h b/drivers/net/ethernet/alibaba/eea/eea_ring.h new file mode 100644 index 0000000000000..ea7adc32bb23c --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_ring.h @@ -0,0 +1,91 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#ifndef __EEA_RING_H__ +#define __EEA_RING_H__ + +#include +#include "eea_desc.h" + +#define EEA_RING_DESC_F_MORE BIT(0) +#define EEA_RING_DESC_F_CQ_PHASE BIT(7) + +struct eea_common_desc { + __le16 flags; + __le16 id; +}; + +struct eea_device; + +struct eea_ring_sq { + void *desc; + + u16 head; + u16 hw_idx; + + u16 shadow_idx; + __le16 shadow_id; + u16 shadow_num; + + u8 desc_size; + u8 desc_size_shift; + + dma_addr_t dma_addr; + u32 dma_size; +}; + +struct eea_ring_cq { + void *desc; + + u16 head; + u16 hw_idx; + + u8 phase; + u8 desc_size_shift; + u8 desc_size; + + dma_addr_t dma_addr; + u32 dma_size; +}; + +struct eea_ring { + const char *name; + struct eea_device *edev; + u32 index; + void __iomem *db; + u16 msix_vec; + + u8 mask; + + u32 num; + + u32 num_free; + + struct eea_ring_sq sq; + struct eea_ring_cq cq; + + char irq_name[32]; +}; + +struct eea_ring *ering_alloc(u32 index, u32 num, struct eea_device *edev, + u8 sq_desc_size, u8 cq_desc_size, + const char *name); +void ering_free(struct eea_ring *ering); +bool ering_kick(struct eea_ring *ering); + +void *ering_sq_alloc_desc(struct eea_ring *ering, u16 id, + bool is_last, u16 flags); +void *ering_aq_alloc_desc(struct eea_ring *ering); +void ering_sq_commit_desc(struct eea_ring *ering); +void ering_sq_cancel(struct eea_ring *ering); + +void ering_cq_ack_desc(struct eea_ring *ering, u32 num); + +void ering_irq_unactive(struct eea_ring *ering); +void ering_irq_active(struct eea_ring *ering, struct eea_ring *tx_ering); +void *ering_cq_get_desc(const struct eea_ring *ering); +#endif diff --git a/drivers/net/ethernet/alibaba/eea/eea_rx.c b/drivers/net/ethernet/alibaba/eea/eea_rx.c new file mode 100644 index 0000000000000..e0a0a9e29e991 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_rx.c @@ -0,0 +1,787 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include +#include + +#include "eea_adminq.h" +#include "eea_net.h" +#include "eea_ring.h" + +#define EEA_SETUP_F_NAPI BIT(0) +#define EEA_SETUP_F_IRQ BIT(1) +#define EEA_ENABLE_F_NAPI BIT(2) + +#define EEA_PAGE_FRAGS_NUM 1024 + +#define EEA_RX_BUF_ALIGN 128 + +struct eea_rx_ctx { + void *buf; + + u32 len; + u32 hdr_len; + + u16 flags; + bool more; + + u32 frame_sz; + + struct eea_rx_meta *meta; + + struct eea_rx_ctx_stats stats; +}; + +static struct eea_rx_meta *eea_rx_meta_get(struct eea_net_rx *rx) +{ + struct eea_rx_meta *meta; + + if (!rx->free) + return NULL; + + meta = rx->free; + rx->free = meta->next; + + return meta; +} + +static void eea_rx_meta_put(struct eea_net_rx *rx, struct eea_rx_meta *meta) +{ + meta->next = rx->free; + rx->free = meta; +} + +static void eea_free_rx_buffer(struct eea_net_rx *rx, struct eea_rx_meta *meta) +{ + u32 drain_count; + + drain_count = EEA_PAGE_FRAGS_NUM - meta->frags; + + if (page_pool_unref_page(meta->page, drain_count) == 0) + page_pool_put_unrefed_page(rx->pp, meta->page, -1, true); + + meta->page = NULL; +} + +static void meta_align_offset(struct eea_net_rx *rx, struct eea_rx_meta *meta) +{ + int h, b; + + h = rx->headroom; + b = meta->offset + h; + + /* For better performance, we align the buffer address to + * EEA_RX_BUF_ALIGN, as required by the device design. + */ + b = ALIGN(b, EEA_RX_BUF_ALIGN); + + meta->offset = b - h; +} + +static int eea_alloc_rx_buffer(struct eea_net_rx *rx, struct eea_rx_meta *meta) +{ + struct page *page; + + if (meta->page) + return 0; + + page = page_pool_dev_alloc_pages(rx->pp); + if (!page) + return -ENOMEM; + + page_pool_fragment_page(page, EEA_PAGE_FRAGS_NUM); + + meta->page = page; + meta->dma = page_pool_get_dma_addr(page); + meta->offset = 0; + meta->frags = 0; + + meta_align_offset(rx, meta); + + return 0; +} + +static void eea_consume_rx_buffer(struct eea_net_rx *rx, + struct eea_rx_meta *meta, + u32 consumed) +{ + int min; + + meta->offset += consumed; + ++meta->frags; + + min = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + min += rx->headroom; + min += ETH_DATA_LEN; + + meta_align_offset(rx, meta); + + if (min + meta->offset > PAGE_SIZE) + eea_free_rx_buffer(rx, meta); +} + +static void eea_free_rx_hdr(struct eea_net_rx *rx) +{ + struct eea_net *enet = rx->enet; + struct eea_rx_meta *meta; + int i; + + for (i = 0; i < enet->cfg.rx_ring_depth; ++i) { + meta = &rx->meta[i]; + meta->hdr_addr = NULL; + + if (!meta->hdr_page) + continue; + + dma_unmap_page(enet->edev->dma_dev, meta->hdr_dma, + PAGE_SIZE, DMA_FROM_DEVICE); + put_page(meta->hdr_page); + + meta->hdr_page = NULL; + } +} + +static int eea_alloc_rx_hdr(struct eea_net_init_ctx *ctx, struct eea_net_rx *rx) +{ + struct page *hdr_page = NULL; + struct eea_rx_meta *meta; + u32 offset = 0, hdrsize; + struct device *dmadev; + dma_addr_t dma; + int i; + + dmadev = ctx->edev->dma_dev; + hdrsize = ctx->cfg.split_hdr; + + for (i = 0; i < ctx->cfg.rx_ring_depth; ++i) { + meta = &rx->meta[i]; + + if (!hdr_page || offset + hdrsize > PAGE_SIZE) { + hdr_page = dev_alloc_page(); + if (!hdr_page) + return -ENOMEM; + + dma = dma_map_page(dmadev, hdr_page, 0, PAGE_SIZE, + DMA_FROM_DEVICE); + + if (unlikely(dma_mapping_error(dmadev, dma))) { + put_page(hdr_page); + return -ENOMEM; + } + + offset = 0; + meta->hdr_page = hdr_page; + meta->dma = dma; + } + + meta->hdr_dma = dma + offset; + meta->hdr_addr = page_address(hdr_page) + offset; + offset += hdrsize; + } + + return 0; +} + +static void eea_rx_meta_dma_sync_for_cpu(struct eea_net_rx *rx, + struct eea_rx_meta *meta, u32 len) +{ + dma_sync_single_for_cpu(rx->enet->edev->dma_dev, + meta->dma + meta->offset + meta->headroom, + len, DMA_FROM_DEVICE); +} + +static int eea_harden_check_overflow(struct eea_rx_ctx *ctx, + struct eea_net *enet) +{ + if (unlikely(ctx->len > ctx->meta->truesize - ctx->meta->room)) { + pr_debug("%s: rx error: len %u exceeds truesize %u\n", + enet->netdev->name, ctx->len, + ctx->meta->truesize - ctx->meta->room); + ++ctx->stats.length_errors; + return -EINVAL; + } + + return 0; +} + +static int eea_harden_check_size(struct eea_rx_ctx *ctx, struct eea_net *enet) +{ + int err; + + err = eea_harden_check_overflow(ctx, enet); + if (err) + return err; + + if (unlikely(ctx->hdr_len + ctx->len < ETH_HLEN)) { + pr_debug("%s: short packet %u\n", enet->netdev->name, ctx->len); + ++ctx->stats.length_errors; + return -EINVAL; + } + + return 0; +} + +static struct sk_buff *eea_build_skb(void *buf, u32 buflen, u32 headroom, + u32 len) +{ + struct sk_buff *skb; + + skb = build_skb(buf, buflen); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, headroom); + skb_put(skb, len); + + return skb; +} + +static struct sk_buff *eea_rx_build_split_hdr_skb(struct eea_net_rx *rx, + struct eea_rx_ctx *ctx) +{ + struct eea_rx_meta *meta = ctx->meta; + struct sk_buff *skb; + u32 truesize; + + dma_sync_single_for_cpu(rx->enet->edev->dma_dev, meta->hdr_dma, + ctx->hdr_len, DMA_FROM_DEVICE); + + skb = napi_alloc_skb(&rx->napi, ctx->hdr_len); + if (unlikely(!skb)) + return NULL; + + truesize = meta->headroom + ctx->len; + + skb_put_data(skb, ctx->meta->hdr_addr, ctx->hdr_len); + + if (ctx->len) { + skb_add_rx_frag(skb, 0, meta->page, + meta->offset + meta->headroom, + ctx->len, truesize); + + eea_consume_rx_buffer(rx, meta, truesize); + } + + skb_mark_for_recycle(skb); + + return skb; +} + +static struct sk_buff *eea_rx_build_skb(struct eea_net_rx *rx, + struct eea_rx_ctx *ctx) +{ + struct eea_rx_meta *meta = ctx->meta; + u32 len, shinfo_size, truesize; + struct sk_buff *skb; + struct page *page; + void *buf, *pkt; + + page = meta->page; + if (!page) + return NULL; + + shinfo_size = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + + buf = page_address(page) + meta->offset; + pkt = buf + meta->headroom; + len = ctx->len; + truesize = meta->headroom + ctx->len + shinfo_size; + + skb = eea_build_skb(buf, truesize, pkt - buf, len); + if (unlikely(!skb)) + return NULL; + + eea_consume_rx_buffer(rx, meta, truesize); + skb_mark_for_recycle(skb); + + return skb; +} + +static int eea_skb_append_buf(struct eea_net_rx *rx, struct eea_rx_ctx *ctx) +{ + struct sk_buff *curr_skb = rx->pkt.curr_skb; + struct sk_buff *head_skb = rx->pkt.head_skb; + int num_skb_frags; + int offset; + + if (!curr_skb) + curr_skb = head_skb; + + num_skb_frags = skb_shinfo(curr_skb)->nr_frags; + if (unlikely(num_skb_frags == MAX_SKB_FRAGS)) { + struct sk_buff *nskb = alloc_skb(0, GFP_ATOMIC); + + if (unlikely(!nskb)) + return -ENOMEM; + + if (curr_skb == head_skb) + skb_shinfo(curr_skb)->frag_list = nskb; + else + curr_skb->next = nskb; + + curr_skb = nskb; + head_skb->truesize += nskb->truesize; + num_skb_frags = 0; + + rx->pkt.curr_skb = curr_skb; + } + + if (curr_skb != head_skb) { + head_skb->data_len += ctx->len; + head_skb->len += ctx->len; + head_skb->truesize += ctx->meta->truesize; + } + + offset = ctx->meta->offset + ctx->meta->headroom; + + skb_add_rx_frag(curr_skb, num_skb_frags, ctx->meta->page, + offset, ctx->len, ctx->meta->truesize); + + eea_consume_rx_buffer(rx, ctx->meta, ctx->meta->headroom + ctx->len); + + return 0; +} + +static int process_remain_buf(struct eea_net_rx *rx, struct eea_rx_ctx *ctx) +{ + struct eea_net *enet = rx->enet; + + if (eea_harden_check_overflow(ctx, enet)) + goto err; + + if (eea_skb_append_buf(rx, ctx)) + goto err; + + return 0; + +err: + dev_kfree_skb(rx->pkt.head_skb); + ++ctx->stats.drops; + rx->pkt.do_drop = true; + rx->pkt.head_skb = NULL; + return 0; +} + +static int process_first_buf(struct eea_net_rx *rx, struct eea_rx_ctx *ctx) +{ + struct eea_net *enet = rx->enet; + struct sk_buff *skb = NULL; + + if (eea_harden_check_size(ctx, enet)) + goto err; + + rx->pkt.data_valid = ctx->flags & EEA_DESC_F_DATA_VALID; + + if (ctx->hdr_len) + skb = eea_rx_build_split_hdr_skb(rx, ctx); + else + skb = eea_rx_build_skb(rx, ctx); + + if (unlikely(!skb)) + goto err; + + rx->pkt.head_skb = skb; + + return 0; + +err: + ++ctx->stats.drops; + rx->pkt.do_drop = true; + return 0; +} + +static void eea_submit_skb(struct eea_net_rx *rx, struct sk_buff *skb, + struct eea_rx_cdesc *desc) +{ + struct eea_net *enet = rx->enet; + + if (rx->pkt.data_valid) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (enet->cfg.ts_cfg.rx_filter == HWTSTAMP_FILTER_ALL) + skb_hwtstamps(skb)->hwtstamp = EEA_DESC_TS(desc) + + enet->hw_ts_offset; + + skb_record_rx_queue(skb, rx->index); + skb->protocol = eth_type_trans(skb, enet->netdev); + + napi_gro_receive(&rx->napi, skb); +} + +static void eea_rx_desc_to_ctx(struct eea_net_rx *rx, + struct eea_rx_ctx *ctx, + struct eea_rx_cdesc *desc) +{ + ctx->meta = &rx->meta[le16_to_cpu(desc->id)]; + ctx->len = le16_to_cpu(desc->len); + ctx->flags = le16_to_cpu(desc->flags); + + ctx->hdr_len = 0; + if (ctx->flags & EEA_DESC_F_SPLIT_HDR) { + ctx->hdr_len = le16_to_cpu(desc->len_ex) & + EEA_RX_CDESC_HDR_LEN_MASK; + ctx->stats.split_hdr_bytes += ctx->hdr_len; + ++ctx->stats.split_hdr_packets; + } + + ctx->more = ctx->flags & EEA_RING_DESC_F_MORE; +} + +static int eea_cleanrx(struct eea_net_rx *rx, int budget, + struct eea_rx_ctx *ctx) +{ + struct eea_rx_cdesc *desc; + struct eea_rx_meta *meta; + int packets; + + for (packets = 0; packets < budget; ) { + desc = ering_cq_get_desc(rx->ering); + if (!desc) + break; + + eea_rx_desc_to_ctx(rx, ctx, desc); + + meta = ctx->meta; + ctx->buf = page_address(meta->page) + meta->offset + + meta->headroom; + + if (unlikely(rx->pkt.do_drop)) + goto skip; + + eea_rx_meta_dma_sync_for_cpu(rx, meta, ctx->len); + + ctx->stats.bytes += ctx->len; + + if (!rx->pkt.idx) + process_first_buf(rx, ctx); + else + process_remain_buf(rx, ctx); + + ++rx->pkt.idx; + + if (!ctx->more) { + if (likely(rx->pkt.head_skb)) + eea_submit_skb(rx, rx->pkt.head_skb, desc); + + ++packets; + } + +skip: + eea_rx_meta_put(rx, meta); + ering_cq_ack_desc(rx->ering, 1); + ++ctx->stats.descs; + + if (!ctx->more) + memset(&rx->pkt, 0, sizeof(rx->pkt)); + } + + ctx->stats.packets = packets; + + return packets; +} + +static bool eea_rx_post(struct eea_net *enet, struct eea_net_rx *rx) +{ + u32 tailroom, headroom, room, flags, len; + struct eea_rx_meta *meta; + struct eea_rx_desc *desc; + int err = 0, num = 0; + dma_addr_t addr; + + tailroom = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + headroom = rx->headroom; + room = headroom + tailroom; + + while (true) { + meta = eea_rx_meta_get(rx); + if (!meta) + break; + + err = eea_alloc_rx_buffer(rx, meta); + if (err) { + eea_rx_meta_put(rx, meta); + break; + } + + len = PAGE_SIZE - meta->offset - room; + addr = meta->dma + meta->offset + headroom; + + desc = ering_sq_alloc_desc(rx->ering, meta->id, true, 0); + desc->addr = cpu_to_le64(addr); + desc->len = cpu_to_le16(len); + + if (meta->hdr_addr) + desc->hdr_addr = cpu_to_le64(meta->hdr_dma); + + ering_sq_commit_desc(rx->ering); + + meta->truesize = len + room; + meta->headroom = headroom; + meta->tailroom = tailroom; + meta->len = len; + ++num; + } + + if (num) { + ering_kick(rx->ering); + + flags = u64_stats_update_begin_irqsave(&rx->stats.syncp); + u64_stats_inc(&rx->stats.kicks); + u64_stats_update_end_irqrestore(&rx->stats.syncp, flags); + } + + /* true means busy, napi should be called again. */ + return !!err; +} + +int eea_poll(struct napi_struct *napi, int budget) +{ + struct eea_net_rx *rx = container_of(napi, struct eea_net_rx, napi); + struct eea_net_tx *tx = &rx->enet->tx[rx->index]; + struct eea_net *enet = rx->enet; + struct eea_rx_ctx ctx = {}; + bool busy = false; + u32 received; + + eea_poll_tx(tx, budget); + + received = eea_cleanrx(rx, budget, &ctx); + + if (rx->ering->num_free > budget) + busy |= eea_rx_post(enet, rx); + + eea_update_rx_stats(&rx->stats, &ctx.stats); + + busy |= received >= budget; + + if (!busy) { + if (napi_complete_done(napi, received)) + ering_irq_active(rx->ering, tx->ering); + } + + if (busy) + return budget; + + return budget - 1; +} + +static void eea_free_rx_buffers(struct eea_net_rx *rx) +{ + struct eea_rx_meta *meta; + u32 i; + + for (i = 0; i < rx->enet->cfg.rx_ring_depth; ++i) { + meta = &rx->meta[i]; + if (!meta->page) + continue; + + eea_free_rx_buffer(rx, meta); + } +} + +static struct page_pool *eea_create_pp(struct eea_net_rx *rx, + struct eea_net_init_ctx *ctx, u32 idx) +{ + struct page_pool_params pp_params = {0}; + + pp_params.order = 0; + pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV; + pp_params.pool_size = ctx->cfg.rx_ring_depth; + pp_params.nid = dev_to_node(ctx->edev->dma_dev); + pp_params.dev = ctx->edev->dma_dev; + pp_params.napi = &rx->napi; + pp_params.netdev = ctx->netdev; + pp_params.dma_dir = DMA_FROM_DEVICE; + pp_params.max_len = PAGE_SIZE; + + return page_pool_create(&pp_params); +} + +static void eea_destroy_page_pool(struct eea_net_rx *rx) +{ + if (rx->pp) + page_pool_destroy(rx->pp); +} + +static irqreturn_t irq_handler(int irq, void *data) +{ + struct eea_net_rx *rx = data; + + rx->irq_n++; + + napi_schedule_irqoff(&rx->napi); + + return IRQ_HANDLED; +} + +void enet_rx_stop(struct eea_net_rx *rx) +{ + if (rx->flags & EEA_ENABLE_F_NAPI) { + rx->flags &= ~EEA_ENABLE_F_NAPI; + napi_disable(&rx->napi); + } +} + +void enet_rx_start(struct eea_net_rx *rx) +{ + napi_enable(&rx->napi); + rx->flags |= EEA_ENABLE_F_NAPI; + + local_bh_disable(); + napi_schedule(&rx->napi); + local_bh_enable(); +} + +static int enet_irq_setup_for_q(struct eea_net_rx *rx) +{ + int err; + + ering_irq_unactive(rx->ering); + + err = eea_pci_request_irq(rx->ering, irq_handler, rx); + if (err) + return err; + + rx->flags |= EEA_SETUP_F_IRQ; + + return 0; +} + +void eea_irq_free(struct eea_net_rx *rx) +{ + if (rx->flags & EEA_SETUP_F_IRQ) { + eea_pci_free_irq(rx->ering, rx); + rx->flags &= ~EEA_SETUP_F_IRQ; + } +} + +int enet_rxtx_irq_setup(struct eea_net *enet, u32 qid, u32 num) +{ + struct eea_net_rx *rx; + int err, i; + + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + rx = enet->rx[i]; + + err = enet_irq_setup_for_q(rx); + if (err) + goto err_free_irq; + } + + return 0; + +err_free_irq: + for (i = 0; i < enet->cfg.rx_ring_num; i++) { + rx = enet->rx[i]; + + eea_irq_free(rx); + } + return err; +} + +void eea_free_rx(struct eea_net_rx *rx) +{ + if (!rx) + return; + + if (rx->ering) { + ering_free(rx->ering); + rx->ering = NULL; + } + + if (rx->meta) { + eea_free_rx_buffers(rx); + eea_free_rx_hdr(rx); + kvfree(rx->meta); + rx->meta = NULL; + } + + if (rx->pp) { + eea_destroy_page_pool(rx); + rx->pp = NULL; + } + + if (rx->flags & EEA_SETUP_F_NAPI) { + rx->flags &= ~EEA_SETUP_F_NAPI; + netif_napi_del(&rx->napi); + } + + kfree(rx); +} + +static void eea_rx_meta_init(struct eea_net_rx *rx, u32 num) +{ + struct eea_rx_meta *meta; + int i; + + rx->free = NULL; + + for (i = 0; i < num; ++i) { + meta = &rx->meta[i]; + meta->id = i; + meta->next = rx->free; + rx->free = meta; + } +} + +struct eea_net_rx *eea_alloc_rx(struct eea_net_init_ctx *ctx, u32 idx) +{ + struct eea_ring *ering; + struct eea_net_rx *rx; + int err; + + rx = kzalloc(sizeof(*rx), GFP_KERNEL); + if (!rx) + return rx; + + rx->index = idx; + sprintf(rx->name, "rx.%u", idx); + + u64_stats_init(&rx->stats.syncp); + + /* ering */ + ering = ering_alloc(idx * 2, ctx->cfg.rx_ring_depth, ctx->edev, + ctx->cfg.rx_sq_desc_size, + ctx->cfg.rx_cq_desc_size, + rx->name); + if (!ering) + goto err_free_rx; + + rx->ering = ering; + + rx->dma_dev = ctx->edev->dma_dev; + + /* meta */ + rx->meta = kvcalloc(ctx->cfg.rx_ring_depth, + sizeof(*rx->meta), GFP_KERNEL); + if (!rx->meta) + goto err_free_rx; + + eea_rx_meta_init(rx, ctx->cfg.rx_ring_depth); + + if (ctx->cfg.split_hdr) { + err = eea_alloc_rx_hdr(ctx, rx); + if (err) + goto err_free_rx; + } + + rx->pp = eea_create_pp(rx, ctx, idx); + if (IS_ERR(rx->pp)) { + err = PTR_ERR(rx->pp); + rx->pp = NULL; + goto err_free_rx; + } + + netif_napi_add(ctx->netdev, &rx->napi, eea_poll); + rx->flags |= EEA_SETUP_F_NAPI; + + return rx; + +err_free_rx: + eea_free_rx(rx); + return NULL; +} diff --git a/drivers/net/ethernet/alibaba/eea/eea_tx.c b/drivers/net/ethernet/alibaba/eea/eea_tx.c new file mode 100644 index 0000000000000..fa1be337a1717 --- /dev/null +++ b/drivers/net/ethernet/alibaba/eea/eea_tx.c @@ -0,0 +1,402 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Driver for Alibaba Elastic Ethernet Adapter. + * + * Copyright (C) 2025 Alibaba Inc. + */ + +#include + +#include "eea_net.h" +#include "eea_pci.h" +#include "eea_ring.h" + +struct eea_sq_free_stats { + u64 packets; + u64 bytes; +}; + +struct eea_tx_meta { + struct eea_tx_meta *next; + + u32 id; + + union { + struct sk_buff *skb; + void *data; + }; + + u32 num; + + dma_addr_t dma_addr; + struct eea_tx_desc *desc; + u16 dma_len; +}; + +static struct eea_tx_meta *eea_tx_meta_get(struct eea_net_tx *tx) +{ + struct eea_tx_meta *meta; + + if (!tx->free) + return NULL; + + meta = tx->free; + tx->free = meta->next; + + return meta; +} + +static void eea_tx_meta_put_and_unmap(struct eea_net_tx *tx, + struct eea_tx_meta *meta) +{ + struct eea_tx_meta *head; + + head = meta; + + while (true) { + dma_unmap_single(tx->dma_dev, meta->dma_addr, + meta->dma_len, DMA_TO_DEVICE); + + meta->data = NULL; + + if (meta->next) { + meta = meta->next; + continue; + } + + break; + } + + meta->next = tx->free; + tx->free = head; +} + +static void eea_meta_free_xmit(struct eea_net_tx *tx, + struct eea_tx_meta *meta, + bool in_napi, + struct eea_tx_cdesc *desc, + struct eea_sq_free_stats *stats) +{ + struct sk_buff *skb = meta->skb; + + if (!skb) { + netdev_err(tx->enet->netdev, + "tx meta->skb is null. id %d num: %d\n", + meta->id, meta->num); + return; + } + + if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && desc)) { + struct skb_shared_hwtstamps ts = {}; + + ts.hwtstamp = EEA_DESC_TS(desc) + tx->enet->hw_ts_offset; + skb_tstamp_tx(skb, &ts); + } + + stats->bytes += meta->skb->len; + napi_consume_skb(meta->skb, in_napi); +} + +static u32 eea_clean_tx(struct eea_net_tx *tx) +{ + struct eea_sq_free_stats stats = {0}; + struct eea_tx_cdesc *desc; + struct eea_tx_meta *meta; + + while ((desc = ering_cq_get_desc(tx->ering))) { + ++stats.packets; + + meta = &tx->meta[le16_to_cpu(desc->id)]; + + eea_meta_free_xmit(tx, meta, true, desc, &stats); + + ering_cq_ack_desc(tx->ering, meta->num); + eea_tx_meta_put_and_unmap(tx, meta); + } + + if (stats.packets) { + u64_stats_update_begin(&tx->stats.syncp); + u64_stats_add(&tx->stats.bytes, stats.bytes); + u64_stats_add(&tx->stats.packets, stats.packets); + u64_stats_update_end(&tx->stats.syncp); + } + + return stats.packets; +} + +int eea_poll_tx(struct eea_net_tx *tx, int budget) +{ + struct eea_net *enet = tx->enet; + u32 index = tx - enet->tx; + struct netdev_queue *txq; + u32 cleaned; + + txq = netdev_get_tx_queue(enet->netdev, index); + + __netif_tx_lock(txq, smp_processor_id()); + + cleaned = eea_clean_tx(tx); + + if (netif_tx_queue_stopped(txq) && cleaned > 0) + netif_tx_wake_queue(txq); + + __netif_tx_unlock(txq); + + return 0; +} + +static int eea_fill_desc_from_skb(const struct sk_buff *skb, + struct eea_ring *ering, + struct eea_tx_desc *desc) +{ + if (skb_is_gso(skb)) { + struct skb_shared_info *sinfo = skb_shinfo(skb); + + desc->gso_size = cpu_to_le16(sinfo->gso_size); + if (sinfo->gso_type & SKB_GSO_TCPV4) + desc->gso_type = EEA_TX_GSO_TCPV4; + + else if (sinfo->gso_type & SKB_GSO_TCPV6) + desc->gso_type = EEA_TX_GSO_TCPV6; + + else if (sinfo->gso_type & SKB_GSO_UDP_L4) + desc->gso_type = EEA_TX_GSO_UDP_L4; + + else + return -EINVAL; + + if (sinfo->gso_type & SKB_GSO_TCP_ECN) + desc->gso_type |= EEA_TX_GSO_ECN; + } else { + desc->gso_type = EEA_TX_GSO_NONE; + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + desc->csum_start = cpu_to_le16(skb_checksum_start_offset(skb)); + desc->csum_offset = cpu_to_le16(skb->csum_offset); + } + + return 0; +} + +static struct eea_tx_meta *eea_tx_desc_fill(struct eea_net_tx *tx, + dma_addr_t addr, u32 len, + bool is_last, void *data, u16 flags) +{ + struct eea_tx_meta *meta; + struct eea_tx_desc *desc; + + meta = eea_tx_meta_get(tx); + + desc = ering_sq_alloc_desc(tx->ering, meta->id, is_last, flags); + desc->addr = cpu_to_le64(addr); + desc->len = cpu_to_le16(len); + + meta->next = NULL; + meta->dma_len = len; + meta->dma_addr = addr; + meta->data = data; + meta->num = 1; + meta->desc = desc; + + return meta; +} + +static int eea_tx_add_skb_frag(struct eea_net_tx *tx, + struct eea_tx_meta *head_meta, + const skb_frag_t *frag, bool is_last) +{ + u32 len = skb_frag_size(frag); + struct eea_tx_meta *meta; + dma_addr_t addr; + + addr = skb_frag_dma_map(tx->dma_dev, frag, 0, len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx->dma_dev, addr))) + return -ENOMEM; + + meta = eea_tx_desc_fill(tx, addr, len, is_last, NULL, 0); + + meta->next = head_meta->next; + head_meta->next = meta; + + return 0; +} + +static int eea_tx_post_skb(struct eea_net_tx *tx, struct sk_buff *skb) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + u32 hlen = skb_headlen(skb); + struct eea_tx_meta *meta; + dma_addr_t addr; + int i, err; + u16 flags; + + addr = dma_map_single(tx->dma_dev, skb->data, hlen, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx->dma_dev, addr))) + return -ENOMEM; + + flags = skb->ip_summed == CHECKSUM_PARTIAL ? EEA_DESC_F_DO_CSUM : 0; + + meta = eea_tx_desc_fill(tx, addr, hlen, !shinfo->nr_frags, skb, flags); + + if (eea_fill_desc_from_skb(skb, tx->ering, meta->desc)) + goto err_cancel; + + for (i = 0; i < shinfo->nr_frags; i++) { + const skb_frag_t *frag = &shinfo->frags[i]; + bool is_last = i == (shinfo->nr_frags - 1); + + err = eea_tx_add_skb_frag(tx, meta, frag, is_last); + if (err) + goto err_cancel; + } + + meta->num = shinfo->nr_frags + 1; + ering_sq_commit_desc(tx->ering); + + u64_stats_update_begin(&tx->stats.syncp); + u64_stats_add(&tx->stats.descs, meta->num); + u64_stats_update_end(&tx->stats.syncp); + + return 0; + +err_cancel: + ering_sq_cancel(tx->ering); + eea_tx_meta_put_and_unmap(tx, meta); + return -ENOMEM; +} + +static void eea_tx_kick(struct eea_net_tx *tx) +{ + ering_kick(tx->ering); + + u64_stats_update_begin(&tx->stats.syncp); + u64_stats_inc(&tx->stats.kicks); + u64_stats_update_end(&tx->stats.syncp); +} + +netdev_tx_t eea_tx_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + const struct skb_shared_info *shinfo = skb_shinfo(skb); + struct eea_net *enet = netdev_priv(netdev); + int qnum = skb_get_queue_mapping(skb); + struct eea_net_tx *tx = &enet->tx[qnum]; + struct netdev_queue *txq; + int err, n; + + txq = netdev_get_tx_queue(netdev, qnum); + + n = shinfo->nr_frags + 1; + + if (!netif_txq_maybe_stop(txq, tx->ering->num_free, n, n)) { + /* maybe the previous skbs was xmitted without kick. */ + eea_tx_kick(tx); + return NETDEV_TX_BUSY; + } + + skb_tx_timestamp(skb); + + err = eea_tx_post_skb(tx, skb); + if (unlikely(err)) { + u64_stats_update_begin(&tx->stats.syncp); + u64_stats_inc(&tx->stats.drops); + u64_stats_update_end(&tx->stats.syncp); + + dev_kfree_skb_any(skb); + } + + if (!netdev_xmit_more() || netif_xmit_stopped(txq)) + eea_tx_kick(tx); + + return NETDEV_TX_OK; +} + +static void eea_free_meta(struct eea_net_tx *tx) +{ + struct eea_sq_free_stats stats; + struct eea_tx_meta *meta; + int i; + + while ((meta = eea_tx_meta_get(tx))) + meta->skb = NULL; + + for (i = 0; i < tx->enet->cfg.tx_ring_num; i++) { + meta = &tx->meta[i]; + + if (!meta->skb) + continue; + + eea_meta_free_xmit(tx, meta, false, NULL, &stats); + + meta->skb = NULL; + } + + kvfree(tx->meta); + tx->meta = NULL; +} + +void eea_tx_timeout(struct net_device *netdev, unsigned int txqueue) +{ + struct netdev_queue *txq = netdev_get_tx_queue(netdev, txqueue); + struct eea_net *priv = netdev_priv(netdev); + struct eea_net_tx *tx = &priv->tx[txqueue]; + + netdev_err(netdev, "TX timeout on queue: %u, tx: %s, ering: 0x%x, %u usecs ago\n", + txqueue, tx->name, tx->ering->index, + jiffies_to_usecs(jiffies - READ_ONCE(txq->trans_start))); +} + +void eea_free_tx(struct eea_net_tx *tx) +{ + if (!tx) + return; + + if (tx->ering) { + ering_free(tx->ering); + tx->ering = NULL; + } + + if (tx->meta) + eea_free_meta(tx); +} + +int eea_alloc_tx(struct eea_net_init_ctx *ctx, struct eea_net_tx *tx, u32 idx) +{ + struct eea_tx_meta *meta; + struct eea_ring *ering; + u32 i; + + u64_stats_init(&tx->stats.syncp); + + sprintf(tx->name, "tx.%u", idx); + + ering = ering_alloc(idx * 2 + 1, ctx->cfg.tx_ring_depth, ctx->edev, + ctx->cfg.tx_sq_desc_size, + ctx->cfg.tx_cq_desc_size, + tx->name); + if (!ering) + goto err_free_tx; + + tx->ering = ering; + tx->index = idx; + tx->dma_dev = ctx->edev->dma_dev; + + /* meta */ + tx->meta = kvcalloc(ctx->cfg.tx_ring_depth, + sizeof(*tx->meta), GFP_KERNEL); + if (!tx->meta) + goto err_free_tx; + + for (i = 0; i < ctx->cfg.tx_ring_depth; ++i) { + meta = &tx->meta[i]; + meta->id = i; + meta->next = tx->free; + tx->free = meta; + } + + return 0; + +err_free_tx: + eea_free_tx(tx); + return -ENOMEM; +} diff --git a/drivers/net/ethernet/altera/altera_tse.h b/drivers/net/ethernet/altera/altera_tse.h index 82f2363a45cd0..e5a56bb989daf 100644 --- a/drivers/net/ethernet/altera/altera_tse.h +++ b/drivers/net/ethernet/altera/altera_tse.h @@ -401,9 +401,6 @@ struct altera_tse_private { /* MAC address space */ struct altera_tse_mac __iomem *mac_dev; - /* TSE Revision */ - u32 revision; - /* mSGDMA Rx Dispatcher address space */ void __iomem *rx_dma_csr; void __iomem *rx_dma_desc; diff --git a/drivers/net/ethernet/altera/altera_tse_main.c b/drivers/net/ethernet/altera/altera_tse_main.c index 3f6204de9e6b8..ca55c5fd11dfd 100644 --- a/drivers/net/ethernet/altera/altera_tse_main.c +++ b/drivers/net/ethernet/altera/altera_tse_main.c @@ -892,9 +892,6 @@ static int tse_open(struct net_device *dev) netdev_warn(dev, "device MAC address %pM\n", dev->dev_addr); - if ((priv->revision < 0xd00) || (priv->revision > 0xe00)) - netdev_warn(dev, "TSE revision %x\n", priv->revision); - spin_lock(&priv->mac_cfg_lock); ret = reset_mac(priv); @@ -1142,6 +1139,7 @@ static int altera_tse_probe(struct platform_device *pdev) struct net_device *ndev; void __iomem *descmap; int ret = -ENODEV; + u32 revision; ndev = alloc_etherdev(sizeof(struct altera_tse_private)); if (!ndev) { @@ -1150,6 +1148,7 @@ static int altera_tse_probe(struct platform_device *pdev) } SET_NETDEV_DEV(ndev, &pdev->dev); + platform_set_drvdata(pdev, ndev); priv = netdev_priv(ndev); priv->device = &pdev->dev; @@ -1387,25 +1386,7 @@ static int altera_tse_probe(struct platform_device *pdev) spin_lock_init(&priv->tx_lock); spin_lock_init(&priv->rxdma_irq_lock); - netif_carrier_off(ndev); - ret = register_netdev(ndev); - if (ret) { - dev_err(&pdev->dev, "failed to register TSE net device\n"); - goto err_register_netdev; - } - - platform_set_drvdata(pdev, ndev); - - priv->revision = ioread32(&priv->mac_dev->megacore_revision); - - if (netif_msg_probe(priv)) - dev_info(&pdev->dev, "Altera TSE MAC version %d.%d at 0x%08lx irq %d/%d\n", - (priv->revision >> 8) & 0xff, - priv->revision & 0xff, - (unsigned long) control_port->start, priv->rx_irq, - priv->tx_irq); - - snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", ndev->name); + snprintf(mrc.name, MII_BUS_ID_SIZE, "%s-pcs-mii", dev_name(&pdev->dev)); pcs_bus = devm_mdio_regmap_register(&pdev->dev, &mrc); if (IS_ERR(pcs_bus)) { ret = PTR_ERR(pcs_bus); @@ -1442,12 +1423,30 @@ static int altera_tse_probe(struct platform_device *pdev) goto err_init_phylink; } + ret = register_netdev(ndev); + if (ret) { + dev_err(&pdev->dev, "failed to register TSE net device\n"); + goto err_register_netdev; + } + + revision = ioread32(&priv->mac_dev->megacore_revision); + + if (revision < 0xd00 || revision > 0xe00) + netdev_warn(ndev, "TSE revision %x\n", revision); + + if (netif_msg_probe(priv)) + dev_info(&pdev->dev, "Altera TSE MAC version %d.%d at 0x%08lx irq %d/%d\n", + (revision >> 8) & 0xff, revision & 0xff, + (unsigned long)control_port->start, priv->rx_irq, + priv->tx_irq); + return 0; + +err_register_netdev: + phylink_destroy(priv->phylink); err_init_phylink: lynx_pcs_destroy(priv->pcs); err_init_pcs: - unregister_netdev(ndev); -err_register_netdev: netif_napi_del(&priv->napi); altera_tse_mdio_destroy(ndev); err_free_netdev: diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig index b39c6f3e1edaa..d54dca3074eb6 100644 --- a/drivers/net/ethernet/amd/Kconfig +++ b/drivers/net/ethernet/amd/Kconfig @@ -165,6 +165,7 @@ config AMD_XGBE select CRC32 select PHYLIB select AMD_XGBE_HAVE_ECC if X86 + select NET_SELFTESTS help This driver supports the AMD 10GbE Ethernet device found on an AMD SoC. diff --git a/drivers/net/ethernet/amd/xgbe/Makefile b/drivers/net/ethernet/amd/xgbe/Makefile index 980e276522377..5992f7fd4d9b7 100644 --- a/drivers/net/ethernet/amd/xgbe/Makefile +++ b/drivers/net/ethernet/amd/xgbe/Makefile @@ -5,7 +5,7 @@ amd-xgbe-objs := xgbe-main.o xgbe-drv.o xgbe-dev.o \ xgbe-desc.o xgbe-ethtool.o xgbe-mdio.o \ xgbe-hwtstamp.o xgbe-ptp.o xgbe-pps.o \ xgbe-i2c.o xgbe-phy-v1.o xgbe-phy-v2.o \ - xgbe-platform.o + xgbe-platform.o xgbe-selftest.o amd-xgbe-$(CONFIG_PCI) += xgbe-pci.o amd-xgbe-$(CONFIG_AMD_XGBE_DCB) += xgbe-dcb.o diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c index e5391a2eca51d..b646ae575e6a1 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c @@ -211,6 +211,7 @@ static void xgbe_config_sph_mode(struct xgbe_prv_data *pdata) } XGMAC_IOWRITE_BITS(pdata, MAC_RCR, HDSMS, XGBE_SPH_HDSMS_SIZE); + pdata->sph = true; } static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata) @@ -223,6 +224,7 @@ static void xgbe_disable_sph_mode(struct xgbe_prv_data *pdata) XGMAC_DMA_IOWRITE_BITS(pdata->channel[i], DMA_CH_CR, SPH, 0); } + pdata->sph = false; } static int xgbe_write_rss_reg(struct xgbe_prv_data *pdata, unsigned int type, @@ -3578,3 +3580,20 @@ void xgbe_init_function_ptrs_dev(struct xgbe_hw_if *hw_if) DBGPR("<--xgbe_init_function_ptrs\n"); } + +int xgbe_enable_mac_loopback(struct xgbe_prv_data *pdata) +{ + /* Enable MAC loopback mode */ + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, LM, 1); + + /* Wait for loopback to stabilize */ + usleep_range(10, 15); + + return 0; +} + +void xgbe_disable_mac_loopback(struct xgbe_prv_data *pdata) +{ + /* Disable MAC loopback mode */ + XGMAC_IOWRITE_BITS(pdata, MAC_RCR, LM, 0); +} diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 4dc631af79332..f3adf29b222bf 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1754,27 +1754,6 @@ static int xgbe_set_mac_address(struct net_device *netdev, void *addr) return 0; } -static int xgbe_ioctl(struct net_device *netdev, struct ifreq *ifreq, int cmd) -{ - struct xgbe_prv_data *pdata = netdev_priv(netdev); - int ret; - - switch (cmd) { - case SIOCGHWTSTAMP: - ret = xgbe_get_hwtstamp_settings(pdata, ifreq); - break; - - case SIOCSHWTSTAMP: - ret = xgbe_set_hwtstamp_settings(pdata, ifreq); - break; - - default: - ret = -EOPNOTSUPP; - } - - return ret; -} - static int xgbe_change_mtu(struct net_device *netdev, int mtu) { struct xgbe_prv_data *pdata = netdev_priv(netdev); @@ -2020,7 +1999,6 @@ static const struct net_device_ops xgbe_netdev_ops = { .ndo_set_rx_mode = xgbe_set_rx_mode, .ndo_set_mac_address = xgbe_set_mac_address, .ndo_validate_addr = eth_validate_addr, - .ndo_eth_ioctl = xgbe_ioctl, .ndo_change_mtu = xgbe_change_mtu, .ndo_tx_timeout = xgbe_tx_timeout, .ndo_get_stats64 = xgbe_get_stats64, @@ -2033,6 +2011,8 @@ static const struct net_device_ops xgbe_netdev_ops = { .ndo_fix_features = xgbe_fix_features, .ndo_set_features = xgbe_set_features, .ndo_features_check = xgbe_features_check, + .ndo_hwtstamp_get = xgbe_get_hwtstamp_settings, + .ndo_hwtstamp_set = xgbe_set_hwtstamp_settings, }; const struct net_device_ops *xgbe_get_netdev_ops(void) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c index b6e1b67a2d0e3..0d19b09497a0f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-ethtool.c @@ -85,6 +85,9 @@ static void xgbe_get_strings(struct net_device *netdev, u32 stringset, u8 *data) int i; switch (stringset) { + case ETH_SS_TEST: + xgbe_selftest_get_strings(pdata, data); + break; case ETH_SS_STATS: for (i = 0; i < XGBE_STATS_COUNT; i++) ethtool_puts(&data, xgbe_gstring_stats[i].stat_string); @@ -131,6 +134,9 @@ static int xgbe_get_sset_count(struct net_device *netdev, int stringset) int ret; switch (stringset) { + case ETH_SS_TEST: + ret = xgbe_selftest_get_count(pdata); + break; case ETH_SS_STATS: ret = XGBE_STATS_COUNT + (pdata->tx_ring_count * 2) + @@ -760,6 +766,7 @@ static const struct ethtool_ops xgbe_ethtool_ops = { .set_ringparam = xgbe_set_ringparam, .get_channels = xgbe_get_channels, .set_channels = xgbe_set_channels, + .self_test = xgbe_selftest_run, }; const struct ethtool_ops *xgbe_get_ethtool_ops(void) diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c b/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c index bc52e5ec64205..0127988e10bee 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-hwtstamp.c @@ -157,26 +157,24 @@ void xgbe_tx_tstamp(struct work_struct *work) spin_unlock_irqrestore(&pdata->tstamp_lock, flags); } -int xgbe_get_hwtstamp_settings(struct xgbe_prv_data *pdata, struct ifreq *ifreq) +int xgbe_get_hwtstamp_settings(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - if (copy_to_user(ifreq->ifr_data, &pdata->tstamp_config, - sizeof(pdata->tstamp_config))) - return -EFAULT; + struct xgbe_prv_data *pdata = netdev_priv(netdev); + + *config = pdata->tstamp_config; return 0; } -int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, struct ifreq *ifreq) +int xgbe_set_hwtstamp_settings(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config config; - unsigned int mac_tscr; - - if (copy_from_user(&config, ifreq->ifr_data, sizeof(config))) - return -EFAULT; - - mac_tscr = 0; + struct xgbe_prv_data *pdata = netdev_priv(netdev); + unsigned int mac_tscr = 0; - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: break; @@ -188,7 +186,7 @@ int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, struct ifreq *ifreq) return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: break; @@ -290,7 +288,7 @@ int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, struct ifreq *ifreq) xgbe_config_tstamp(pdata, mac_tscr); - memcpy(&pdata->tstamp_config, &config, sizeof(config)); + pdata->tstamp_config = *config; return 0; } diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c index a56efc1bee339..35a381a83647d 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-phy-v2.c @@ -668,7 +668,7 @@ static int xgbe_phy_mii_read_c45(struct mii_bus *mii, int addr, int devad, else if (phy_data->conn_type & XGBE_CONN_TYPE_MDIO) ret = xgbe_phy_mdio_mii_read_c45(pdata, addr, devad, reg); else - ret = -ENOTSUPP; + ret = -EOPNOTSUPP; xgbe_phy_put_comm_ownership(pdata); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-selftest.c b/drivers/net/ethernet/amd/xgbe/xgbe-selftest.c new file mode 100644 index 0000000000000..55e5e467facd7 --- /dev/null +++ b/drivers/net/ethernet/amd/xgbe/xgbe-selftest.c @@ -0,0 +1,346 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-3-Clause) +/* + * Copyright (c) 2014-2025, Advanced Micro Devices, Inc. + * Copyright (c) 2014, Synopsys, Inc. + * All rights reserved + * + * Author: Raju Rangoju + */ +#include +#include +#include +#include +#include +#include +#include + +#include "xgbe.h" +#include "xgbe-common.h" + +#define XGBE_LOOPBACK_NONE 0 +#define XGBE_LOOPBACK_MAC 1 +#define XGBE_LOOPBACK_PHY 2 + +struct xgbe_test { + char name[ETH_GSTRING_LEN]; + int lb; + int (*fn)(struct xgbe_prv_data *pdata); +}; + +static u8 xgbe_test_id; + +static int xgbe_test_loopback_validate(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt, + struct net_device *orig_ndev) +{ + struct net_test_priv *tdata = pt->af_packet_priv; + const unsigned char *dst = tdata->packet->dst; + const unsigned char *src = tdata->packet->src; + struct netsfhdr *hdr; + struct ethhdr *eh; + struct tcphdr *th; + struct udphdr *uh; + struct iphdr *ih; + int eat; + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + goto out; + + eat = (skb->tail + skb->data_len) - skb->end; + if (eat > 0 && skb_shared(skb)) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (!skb) + goto out; + } + + if (skb_linearize(skb)) + goto out; + + if (skb_headlen(skb) < (NET_TEST_PKT_SIZE - ETH_HLEN)) + goto out; + + eh = (struct ethhdr *)skb_mac_header(skb); + if (dst) { + if (!ether_addr_equal_unaligned(eh->h_dest, dst)) + goto out; + } + if (src) { + if (!ether_addr_equal_unaligned(eh->h_source, src)) + goto out; + } + + ih = ip_hdr(skb); + + if (tdata->packet->tcp) { + if (ih->protocol != IPPROTO_TCP) + goto out; + + th = (struct tcphdr *)((u8 *)ih + 4 * ih->ihl); + if (th->dest != htons(tdata->packet->dport)) + goto out; + + hdr = (struct netsfhdr *)((u8 *)th + sizeof(*th)); + } else { + if (ih->protocol != IPPROTO_UDP) + goto out; + + uh = (struct udphdr *)((u8 *)ih + 4 * ih->ihl); + if (uh->dest != htons(tdata->packet->dport)) + goto out; + + hdr = (struct netsfhdr *)((u8 *)uh + sizeof(*uh)); + } + + if (hdr->magic != cpu_to_be64(NET_TEST_PKT_MAGIC)) + goto out; + if (tdata->packet->id != hdr->id) + goto out; + + tdata->ok = true; + complete(&tdata->comp); +out: + kfree_skb(skb); + return 0; +} + +static int __xgbe_test_loopback(struct xgbe_prv_data *pdata, + struct net_packet_attrs *attr) +{ + struct net_test_priv *tdata; + struct sk_buff *skb = NULL; + int ret = 0; + + tdata = kzalloc(sizeof(*tdata), GFP_KERNEL); + if (!tdata) + return -ENOMEM; + + tdata->ok = false; + init_completion(&tdata->comp); + + tdata->pt.type = htons(ETH_P_IP); + tdata->pt.func = xgbe_test_loopback_validate; + tdata->pt.dev = pdata->netdev; + tdata->pt.af_packet_priv = tdata; + tdata->packet = attr; + + dev_add_pack(&tdata->pt); + + skb = net_test_get_skb(pdata->netdev, xgbe_test_id, attr); + if (!skb) { + ret = -ENOMEM; + goto cleanup; + } + + xgbe_test_id++; + ret = dev_direct_xmit(skb, attr->queue_mapping); + if (ret) + goto cleanup; + + if (!attr->timeout) + attr->timeout = NET_LB_TIMEOUT; + + wait_for_completion_timeout(&tdata->comp, attr->timeout); + ret = tdata->ok ? 0 : -ETIMEDOUT; + + if (ret) + netdev_err(pdata->netdev, "Response timedout: ret %d\n", ret); +cleanup: + dev_remove_pack(&tdata->pt); + kfree(tdata); + return ret; +} + +static int xgbe_test_mac_loopback(struct xgbe_prv_data *pdata) +{ + struct net_packet_attrs attr = {}; + + attr.dst = pdata->netdev->dev_addr; + return __xgbe_test_loopback(pdata, &attr); +} + +static int xgbe_test_phy_loopback(struct xgbe_prv_data *pdata) +{ + struct net_packet_attrs attr = {}; + int ret; + + if (!pdata->netdev->phydev) { + netdev_err(pdata->netdev, "phydev not found: cannot start PHY loopback test\n"); + return -EOPNOTSUPP; + } + + ret = phy_loopback(pdata->netdev->phydev, true, 0); + if (ret) + return ret; + + attr.dst = pdata->netdev->dev_addr; + ret = __xgbe_test_loopback(pdata, &attr); + + phy_loopback(pdata->netdev->phydev, false, 0); + return ret; +} + +static int xgbe_test_sph(struct xgbe_prv_data *pdata) +{ + struct net_packet_attrs attr = {}; + unsigned long cnt_end, cnt_start; + int ret; + + cnt_start = pdata->ext_stats.rx_split_header_packets; + + if (!pdata->sph) { + netdev_err(pdata->netdev, "Split Header not enabled\n"); + return -EOPNOTSUPP; + } + + /* UDP test */ + attr.dst = pdata->netdev->dev_addr; + attr.tcp = false; + + ret = __xgbe_test_loopback(pdata, &attr); + if (ret) + return ret; + + cnt_end = pdata->ext_stats.rx_split_header_packets; + if (cnt_end <= cnt_start) + return -EINVAL; + + /* TCP test */ + cnt_start = cnt_end; + + attr.dst = pdata->netdev->dev_addr; + attr.tcp = true; + + ret = __xgbe_test_loopback(pdata, &attr); + if (ret) + return ret; + + cnt_end = pdata->ext_stats.rx_split_header_packets; + if (cnt_end <= cnt_start) + return -EINVAL; + + return 0; +} + +static int xgbe_test_jumbo(struct xgbe_prv_data *pdata) +{ + struct net_packet_attrs attr = {}; + int size = pdata->rx_buf_size; + + attr.dst = pdata->netdev->dev_addr; + attr.max_size = size - ETH_FCS_LEN; + + return __xgbe_test_loopback(pdata, &attr); +} + +static const struct xgbe_test xgbe_selftests[] = { + { + .name = "MAC Loopback ", + .lb = XGBE_LOOPBACK_MAC, + .fn = xgbe_test_mac_loopback, + }, { + .name = "PHY Loopback ", + .lb = XGBE_LOOPBACK_NONE, + .fn = xgbe_test_phy_loopback, + }, { + .name = "Split Header ", + .lb = XGBE_LOOPBACK_PHY, + .fn = xgbe_test_sph, + }, { + .name = "Jumbo Frame ", + .lb = XGBE_LOOPBACK_PHY, + .fn = xgbe_test_jumbo, + }, +}; + +void xgbe_selftest_run(struct net_device *dev, + struct ethtool_test *etest, u64 *buf) +{ + struct xgbe_prv_data *pdata = netdev_priv(dev); + int count = xgbe_selftest_get_count(pdata); + int i, ret; + + memset(buf, 0, sizeof(*buf) * count); + xgbe_test_id = 0; + + if (etest->flags != ETH_TEST_FL_OFFLINE) { + netdev_err(pdata->netdev, "Only offline tests are supported\n"); + etest->flags |= ETH_TEST_FL_FAILED; + return; + } else if (!netif_carrier_ok(dev)) { + netdev_err(pdata->netdev, + "Invalid link, cannot execute tests\n"); + etest->flags |= ETH_TEST_FL_FAILED; + return; + } + + /* Wait for queues drain */ + msleep(200); + + for (i = 0; i < count; i++) { + ret = 0; + + switch (xgbe_selftests[i].lb) { + case XGBE_LOOPBACK_PHY: + ret = -EOPNOTSUPP; + if (dev->phydev) + ret = phy_loopback(dev->phydev, true, 0); + if (!ret) + break; + fallthrough; + case XGBE_LOOPBACK_MAC: + ret = xgbe_enable_mac_loopback(pdata); + break; + case XGBE_LOOPBACK_NONE: + break; + default: + ret = -EOPNOTSUPP; + break; + } + + /* + * First tests will always be MAC / PHY loopback. + * If any of them is not supported we abort earlier. + */ + if (ret) { + netdev_err(pdata->netdev, "Loopback not supported\n"); + etest->flags |= ETH_TEST_FL_FAILED; + break; + } + + ret = xgbe_selftests[i].fn(pdata); + if (ret && (ret != -EOPNOTSUPP)) + etest->flags |= ETH_TEST_FL_FAILED; + buf[i] = ret; + + switch (xgbe_selftests[i].lb) { + case XGBE_LOOPBACK_PHY: + ret = -EOPNOTSUPP; + if (dev->phydev) + ret = phy_loopback(dev->phydev, false, 0); + if (!ret) + break; + fallthrough; + case XGBE_LOOPBACK_MAC: + xgbe_disable_mac_loopback(pdata); + break; + default: + break; + } + } +} + +void xgbe_selftest_get_strings(struct xgbe_prv_data *pdata, u8 *data) +{ + u8 *p = data; + int i; + + for (i = 0; i < xgbe_selftest_get_count(pdata); i++) + ethtool_puts(&p, xgbe_selftests[i].name); +} + +int xgbe_selftest_get_count(struct xgbe_prv_data *pdata) +{ + return ARRAY_SIZE(xgbe_selftests); +} diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h index e8bbb68059013..03ef0f5484830 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe.h +++ b/drivers/net/ethernet/amd/xgbe/xgbe.h @@ -1146,7 +1146,7 @@ struct xgbe_prv_data { spinlock_t tstamp_lock; struct ptp_clock_info ptp_clock_info; struct ptp_clock *ptp_clock; - struct hwtstamp_config tstamp_config; + struct kernel_hwtstamp_config tstamp_config; unsigned int tstamp_addend; struct work_struct tx_tstamp_work; struct sk_buff *tx_tstamp_skb; @@ -1246,6 +1246,7 @@ struct xgbe_prv_data { int rx_adapt_retries; bool rx_adapt_done; bool mode_set; + bool sph; }; /* Function prototypes*/ @@ -1307,10 +1308,11 @@ void xgbe_update_tstamp_addend(struct xgbe_prv_data *pdata, void xgbe_set_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec, unsigned int nsec); void xgbe_tx_tstamp(struct work_struct *work); -int xgbe_get_hwtstamp_settings(struct xgbe_prv_data *pdata, - struct ifreq *ifreq); -int xgbe_set_hwtstamp_settings(struct xgbe_prv_data *pdata, - struct ifreq *ifreq); +int xgbe_get_hwtstamp_settings(struct net_device *netdev, + struct kernel_hwtstamp_config *config); +int xgbe_set_hwtstamp_settings(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); void xgbe_prep_tx_tstamp(struct xgbe_prv_data *pdata, struct sk_buff *skb, struct xgbe_packet_data *packet); @@ -1321,6 +1323,16 @@ void xgbe_update_tstamp_time(struct xgbe_prv_data *pdata, unsigned int sec, int xgbe_pps_config(struct xgbe_prv_data *pdata, struct xgbe_pps_config *cfg, int index, bool on); +/* Selftest functions */ +void xgbe_selftest_run(struct net_device *dev, + struct ethtool_test *etest, u64 *buf); +void xgbe_selftest_get_strings(struct xgbe_prv_data *pdata, u8 *data); +int xgbe_selftest_get_count(struct xgbe_prv_data *pdata); + +/* Loopback control */ +int xgbe_enable_mac_loopback(struct xgbe_prv_data *pdata); +void xgbe_disable_mac_loopback(struct xgbe_prv_data *pdata); + #ifdef CONFIG_DEBUG_FS void xgbe_debugfs_init(struct xgbe_prv_data *); void xgbe_debugfs_exit(struct xgbe_prv_data *); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_main.c b/drivers/net/ethernet/aquantia/atlantic/aq_main.c index b565189e59139..4ef4fe64b8ac1 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_main.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_main.c @@ -258,10 +258,15 @@ static void aq_ndev_set_multicast_settings(struct net_device *ndev) (void)aq_nic_set_multicast_list(aq_nic, ndev); } -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) -static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic, - struct hwtstamp_config *config) +static int aq_ndev_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { + struct aq_nic_s *aq_nic = netdev_priv(netdev); + + if (!IS_REACHABLE(CONFIG_PTP_1588_CLOCK) || !aq_nic->aq_ptp) + return -EOPNOTSUPP; + switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: @@ -290,59 +295,17 @@ static int aq_ndev_config_hwtstamp(struct aq_nic_s *aq_nic, return aq_ptp_hwtstamp_config_set(aq_nic->aq_ptp, config); } -#endif - -static int aq_ndev_hwtstamp_set(struct aq_nic_s *aq_nic, struct ifreq *ifr) -{ - struct hwtstamp_config config; -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) - int ret_val; -#endif - - if (!aq_nic->aq_ptp) - return -EOPNOTSUPP; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) - ret_val = aq_ndev_config_hwtstamp(aq_nic, &config); - if (ret_val) - return ret_val; -#endif - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) -static int aq_ndev_hwtstamp_get(struct aq_nic_s *aq_nic, struct ifreq *ifr) +static int aq_ndev_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - struct hwtstamp_config config; + struct aq_nic_s *aq_nic = netdev_priv(netdev); if (!aq_nic->aq_ptp) return -EOPNOTSUPP; - aq_ptp_hwtstamp_config_get(aq_nic->aq_ptp, &config); - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} -#endif - -static int aq_ndev_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) -{ - struct aq_nic_s *aq_nic = netdev_priv(netdev); - - switch (cmd) { - case SIOCSHWTSTAMP: - return aq_ndev_hwtstamp_set(aq_nic, ifr); - -#if IS_REACHABLE(CONFIG_PTP_1588_CLOCK) - case SIOCGHWTSTAMP: - return aq_ndev_hwtstamp_get(aq_nic, ifr); -#endif - } - - return -EOPNOTSUPP; + aq_ptp_hwtstamp_config_get(aq_nic->aq_ptp, config); + return 0; } static int aq_ndo_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, @@ -500,12 +463,13 @@ static const struct net_device_ops aq_ndev_ops = { .ndo_set_mac_address = aq_ndev_set_mac_address, .ndo_set_features = aq_ndev_set_features, .ndo_fix_features = aq_ndev_fix_features, - .ndo_eth_ioctl = aq_ndev_ioctl, .ndo_vlan_rx_add_vid = aq_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = aq_ndo_vlan_rx_kill_vid, .ndo_setup_tc = aq_ndo_setup_tc, .ndo_bpf = aq_xdp, .ndo_xdp_xmit = aq_xdp_xmit, + .ndo_hwtstamp_get = aq_ndev_hwtstamp_get, + .ndo_hwtstamp_set = aq_ndev_hwtstamp_set, }; static int __init aq_ndev_init_module(void) diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c index 5acb3e16b5677..0fa0f891c0e03 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.c @@ -51,7 +51,7 @@ struct ptp_tx_timeout { struct aq_ptp_s { struct aq_nic_s *aq_nic; - struct hwtstamp_config hwtstamp_config; + struct kernel_hwtstamp_config hwtstamp_config; spinlock_t ptp_lock; spinlock_t ptp_ring_lock; struct ptp_clock *ptp_clock; @@ -567,7 +567,7 @@ static void aq_ptp_rx_hwtstamp(struct aq_ptp_s *aq_ptp, struct skb_shared_hwtsta } void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp, - struct hwtstamp_config *config) + struct kernel_hwtstamp_config *config) { *config = aq_ptp->hwtstamp_config; } @@ -588,7 +588,7 @@ static void aq_ptp_prepare_filters(struct aq_ptp_s *aq_ptp) } int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp, - struct hwtstamp_config *config) + struct kernel_hwtstamp_config *config) { struct aq_nic_s *aq_nic = aq_ptp->aq_nic; const struct aq_hw_ops *hw_ops; diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h index 210b723f22072..5e643ec7cc06a 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ptp.h @@ -60,9 +60,9 @@ void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp); /* Must be to check available of PTP before call */ void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp, - struct hwtstamp_config *config); + struct kernel_hwtstamp_config *config); int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp, - struct hwtstamp_config *config); + struct kernel_hwtstamp_config *config); /* Return either ring is belong to PTP or not*/ bool aq_ptp_ring(struct aq_nic_s *aq_nic, struct aq_ring_s *ring); @@ -130,9 +130,9 @@ static inline int aq_ptp_xmit(struct aq_nic_s *aq_nic, struct sk_buff *skb) static inline void aq_ptp_tx_hwtstamp(struct aq_nic_s *aq_nic, u64 timestamp) {} static inline void aq_ptp_hwtstamp_config_get(struct aq_ptp_s *aq_ptp, - struct hwtstamp_config *config) {} + struct kernel_hwtstamp_config *config) {} static inline int aq_ptp_hwtstamp_config_set(struct aq_ptp_s *aq_ptp, - struct hwtstamp_config *config) + struct kernel_hwtstamp_config *config) { return 0; } diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig index 9fdef874f5ca3..666522d647751 100644 --- a/drivers/net/ethernet/broadcom/Kconfig +++ b/drivers/net/ethernet/broadcom/Kconfig @@ -25,6 +25,7 @@ config B44 select SSB select MII select PHYLIB + select FIXED_PHY if BCM47XX help If you have a network (Ethernet) controller of this type, say Y or M here. diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c index 63f1a8c3a7fbe..dd80ccfca19d5 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_ethtool.c @@ -163,11 +163,30 @@ static void bcmasp_set_msglevel(struct net_device *dev, u32 level) static void bcmasp_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct bcmasp_intf *intf = netdev_priv(dev); + struct bcmasp_priv *priv = intf->parent; + struct device *kdev = &priv->pdev->dev; + u32 phy_wolopts = 0; + + if (dev->phydev) { + phy_ethtool_get_wol(dev->phydev, wol); + phy_wolopts = wol->wolopts; + } + + /* MAC is not wake-up capable, return what the PHY does */ + if (!device_can_wakeup(kdev)) + return; + + /* Overlay MAC capabilities with that of the PHY queried before */ + wol->supported |= BCMASP_SUPPORTED_WAKE; + wol->wolopts |= intf->wolopts; + + /* Return the PHY configured magic password */ + if (phy_wolopts & WAKE_MAGICSECURE) + return; - wol->supported = BCMASP_SUPPORTED_WAKE; - wol->wolopts = intf->wolopts; memset(wol->sopass, 0, sizeof(wol->sopass)); + /* Otherwise the MAC one */ if (wol->wolopts & WAKE_MAGICSECURE) memcpy(wol->sopass, intf->sopass, sizeof(intf->sopass)); } @@ -177,10 +196,21 @@ static int bcmasp_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) struct bcmasp_intf *intf = netdev_priv(dev); struct bcmasp_priv *priv = intf->parent; struct device *kdev = &priv->pdev->dev; + int ret = 0; + + /* Try Wake-on-LAN from the PHY first */ + if (dev->phydev) { + ret = phy_ethtool_set_wol(dev->phydev, wol); + if (ret != -EOPNOTSUPP && wol->wolopts) + return ret; + } if (!device_can_wakeup(kdev)) return -EOPNOTSUPP; + if (wol->wolopts & ~BCMASP_SUPPORTED_WAKE) + return -EINVAL; + /* Interface Specific */ intf->wolopts = wol->wolopts; if (intf->wolopts & WAKE_MAGICSECURE) diff --git a/drivers/net/ethernet/broadcom/b44.c b/drivers/net/ethernet/broadcom/b44.c index 0353359c3fe96..888f28f11406f 100644 --- a/drivers/net/ethernet/broadcom/b44.c +++ b/drivers/net/ethernet/broadcom/b44.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -2233,7 +2234,6 @@ static int b44_register_phy_one(struct b44 *bp) struct mii_bus *mii_bus; struct ssb_device *sdev = bp->sdev; struct phy_device *phydev; - char bus_id[MII_BUS_ID_SIZE + 3]; struct ssb_sprom *sprom = &sdev->bus->sprom; int err; @@ -2260,27 +2260,26 @@ static int b44_register_phy_one(struct b44 *bp) goto err_out_mdiobus; } - if (!mdiobus_is_registered_device(bp->mii_bus, bp->phy_addr) && - (sprom->boardflags_lo & (B44_BOARDFLAG_ROBO | B44_BOARDFLAG_ADM))) { - + phydev = mdiobus_get_phy(bp->mii_bus, bp->phy_addr); + if (!phydev && + sprom->boardflags_lo & (B44_BOARDFLAG_ROBO | B44_BOARDFLAG_ADM)) { dev_info(sdev->dev, "could not find PHY at %i, use fixed one\n", bp->phy_addr); - bp->phy_addr = 0; - snprintf(bus_id, sizeof(bus_id), PHY_ID_FMT, "fixed-0", - bp->phy_addr); - } else { - snprintf(bus_id, sizeof(bus_id), PHY_ID_FMT, mii_bus->id, - bp->phy_addr); + phydev = fixed_phy_register_100fd(); + if (!IS_ERR(phydev)) + bp->phy_addr = phydev->mdio.addr; } - phydev = phy_connect(bp->dev, bus_id, &b44_adjust_link, - PHY_INTERFACE_MODE_MII); - if (IS_ERR(phydev)) { + if (IS_ERR_OR_NULL(phydev)) + err = -ENODEV; + else + err = phy_connect_direct(bp->dev, phydev, &b44_adjust_link, + PHY_INTERFACE_MODE_MII); + if (err) { dev_err(sdev->dev, "could not attach PHY at %i\n", bp->phy_addr); - err = PTR_ERR(phydev); goto err_out_mdiobus_unregister; } @@ -2293,7 +2292,6 @@ static int b44_register_phy_one(struct b44 *bp) linkmode_copy(phydev->advertising, phydev->supported); bp->old_link = 0; - bp->phy_addr = phydev->mdio.addr; phy_attached_info(phydev); @@ -2311,10 +2309,15 @@ static int b44_register_phy_one(struct b44 *bp) static void b44_unregister_phy_one(struct b44 *bp) { - struct net_device *dev = bp->dev; struct mii_bus *mii_bus = bp->mii_bus; + struct net_device *dev = bp->dev; + struct phy_device *phydev; + + phydev = dev->phydev; - phy_disconnect(dev->phydev); + phy_disconnect(phydev); + if (phy_is_pseudo_fixed_link(phydev)) + fixed_phy_unregister(phydev); mdiobus_unregister(mii_bus); mdiobus_free(mii_bus); } diff --git a/drivers/net/ethernet/broadcom/bnge/Makefile b/drivers/net/ethernet/broadcom/bnge/Makefile index 6142d9c57f492..1fedd7a0f14d3 100644 --- a/drivers/net/ethernet/broadcom/bnge/Makefile +++ b/drivers/net/ethernet/broadcom/bnge/Makefile @@ -9,4 +9,6 @@ bng_en-y := bnge_core.o \ bnge_rmem.o \ bnge_resc.o \ bnge_netdev.o \ - bnge_ethtool.o + bnge_ethtool.o \ + bnge_link.o \ + bnge_txrx.o diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h index 7aed5f81cd51e..88b904246f580 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge.h @@ -9,8 +9,10 @@ #include #include +#include #include "bnge_rmem.h" #include "bnge_resc.h" +#include "bnge_link.h" #define DRV_VER_MAJ 1 #define DRV_VER_MIN 15 @@ -134,6 +136,7 @@ struct bnge_dev { unsigned long state; #define BNGE_STATE_DRV_REGISTERED 0 #define BNGE_STATE_OPEN 1 +#define BNGE_STATE_IN_SP_TASK 2 u64 fw_cap; @@ -141,6 +144,17 @@ struct bnge_dev { struct bnge_ctx_mem_info *ctx; u64 flags; +#define BNGE_PF(bd) (1) +#define BNGE_VF(bd) (0) +#define BNGE_NPAR(bd) (0) +#define BNGE_MH(bd) (0) +#define BNGE_SINGLE_PF(bd) (BNGE_PF(bd) && !BNGE_NPAR(bd) && !BNGE_MH(bn)) +#define BNGE_SH_PORT_CFG_OK(bd) \ + (BNGE_PF(bd) && ((bd)->phy_flags & BNGE_PHY_FL_SHARED_PORT_CFG)) +#define BNGE_PHY_CFG_ABLE(bd) \ + ((BNGE_SINGLE_PF(bd) || \ + BNGE_SH_PORT_CFG_OK(bd)) && \ + (bd)->link_info.phy_state == BNGE_PHY_STATE_ENABLED) struct bnge_hw_resc hw_resc; @@ -195,8 +209,35 @@ struct bnge_dev { u8 max_q; u8 port_count; + unsigned int current_interval; +#define BNGE_TIMER_INTERVAL HZ + + struct timer_list timer; struct bnge_irq *irq_tbl; u16 irqs_acquired; + + struct workqueue_struct *bnge_pf_wq; + struct work_struct sp_task; + unsigned long sp_event; +#define BNGE_PERIODIC_STATS_SP_EVENT 0 + + /* To protect link related settings during link changes and + * ethtool settings changes. + */ + struct mutex link_lock; + struct bnge_link_info link_info; + + /* copied from flags and flags2 in hwrm_port_phy_qcaps_output */ + u32 phy_flags; +#define BNGE_PHY_FL_SHARED_PORT_CFG \ + PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED +#define BNGE_PHY_FL_NO_FCS PORT_PHY_QCAPS_RESP_FLAGS_NO_FCS +#define BNGE_PHY_FL_SPEEDS2 \ + (PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED << 8) +#define BNGE_PHY_FL_NO_PAUSE \ + (PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED << 8) + + u32 msg_enable; }; static inline bool bnge_is_roce_en(struct bnge_dev *bd) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_core.c b/drivers/net/ethernet/broadcom/bnge/bnge_core.c index 2c72dd34d50d0..dfa501f912ada 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_core.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_core.c @@ -238,6 +238,23 @@ static int bnge_map_db_bar(struct bnge_dev *bd) return 0; } +static struct workqueue_struct * +bnge_create_workqueue_thread(struct bnge_dev *bd, char thread_name[]) +{ + struct workqueue_struct *wq; + char *wq_name; + + wq_name = kasprintf(GFP_KERNEL, "%s-%s", thread_name, + dev_name(bd->dev)); + if (!wq_name) + return NULL; + + wq = create_singlethread_workqueue(wq_name); + + kfree(wq_name); + return wq; +} + static int bnge_probe_one(struct pci_dev *pdev, const struct pci_device_id *ent) { unsigned int max_irqs; @@ -277,6 +294,10 @@ static int bnge_probe_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_devl_free; } + INIT_WORK(&bd->sp_task, bnge_sp_task); + timer_setup(&bd->timer, bnge_timer, 0); + bd->current_interval = BNGE_TIMER_INTERVAL; + rc = bnge_init_hwrm_resources(bd); if (rc) goto err_bar_unmap; @@ -318,14 +339,24 @@ static int bnge_probe_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_config_uninit; } + bd->bnge_pf_wq = bnge_create_workqueue_thread(bd, "bnge_pf_wq"); + if (!bd->bnge_pf_wq) { + dev_err(&pdev->dev, "Unable to create workqueue.\n"); + rc = -ENOMEM; + goto err_free_irq; + } + rc = bnge_netdev_alloc(bd, max_irqs); if (rc) - goto err_free_irq; + goto err_free_workq; pci_save_state(pdev); return 0; +err_free_workq: + destroy_workqueue(bd->bnge_pf_wq); + err_free_irq: bnge_free_irqs(bd); @@ -356,6 +387,8 @@ static void bnge_remove_one(struct pci_dev *pdev) bnge_netdev_free(bd); + destroy_workqueue(bd->bnge_pf_wq); + bnge_free_irqs(bd); bnge_net_uninit_dflt_config(bd); diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c index 569371c1b4f26..a82271492d7d4 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_ethtool.c @@ -11,6 +11,394 @@ #include "bnge.h" #include "bnge_ethtool.h" +#include "bnge_hwrm_lib.h" + +static int bnge_nway_reset(struct net_device *dev) +{ + struct bnge_net *bn = netdev_priv(dev); + struct bnge_dev *bd = bn->bd; + int rc = 0; + + if (!BNGE_PHY_CFG_ABLE(bd)) + return -EOPNOTSUPP; + + if (!(bn->eth_link_info.autoneg & BNGE_AUTONEG_SPEED)) + return -EINVAL; + + if (netif_running(dev)) + rc = bnge_hwrm_set_link_setting(bn, true); + + return rc; +} + + +static const char * const bnge_ring_rx_stats_str[] = { + "rx_ucast_packets", + "rx_mcast_packets", + "rx_bcast_packets", + "rx_discards", + "rx_errors", + "rx_ucast_bytes", + "rx_mcast_bytes", + "rx_bcast_bytes", +}; + +static const char * const bnge_ring_tx_stats_str[] = { + "tx_ucast_packets", + "tx_mcast_packets", + "tx_bcast_packets", + "tx_errors", + "tx_discards", + "tx_ucast_bytes", + "tx_mcast_bytes", + "tx_bcast_bytes", +}; + +static const char * const bnge_ring_tpa_stats_str[] = { + "tpa_packets", + "tpa_bytes", + "tpa_events", + "tpa_aborts", +}; + +static const char * const bnge_ring_tpa2_stats_str[] = { + "rx_tpa_eligible_pkt", + "rx_tpa_eligible_bytes", + "rx_tpa_pkt", + "rx_tpa_bytes", + "rx_tpa_errors", + "rx_tpa_events", +}; + +static const char * const bnge_rx_sw_stats_str[] = { + "rx_l4_csum_errors", + "rx_resets", + "rx_buf_errors", +}; + +#define BNGE_RX_STATS_ENTRY(counter) \ + { BNGE_RX_STATS_OFFSET(counter), __stringify(counter) } + +#define BNGE_TX_STATS_ENTRY(counter) \ + { BNGE_TX_STATS_OFFSET(counter), __stringify(counter) } + +#define BNGE_RX_STATS_EXT_ENTRY(counter) \ + { BNGE_RX_STATS_EXT_OFFSET(counter), __stringify(counter) } + +#define BNGE_TX_STATS_EXT_ENTRY(counter) \ + { BNGE_TX_STATS_EXT_OFFSET(counter), __stringify(counter) } + +#define BNGE_RX_STATS_EXT_PFC_ENTRY(n) \ + BNGE_RX_STATS_EXT_ENTRY(pfc_pri##n##_rx_duration_us), \ + BNGE_RX_STATS_EXT_ENTRY(pfc_pri##n##_rx_transitions) + +#define BNGE_TX_STATS_EXT_PFC_ENTRY(n) \ + BNGE_TX_STATS_EXT_ENTRY(pfc_pri##n##_tx_duration_us), \ + BNGE_TX_STATS_EXT_ENTRY(pfc_pri##n##_tx_transitions) + +#define BNGE_RX_STATS_EXT_PFC_ENTRIES \ + BNGE_RX_STATS_EXT_PFC_ENTRY(0), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(1), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(2), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(3), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(4), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(5), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(6), \ + BNGE_RX_STATS_EXT_PFC_ENTRY(7) + +#define BNGE_TX_STATS_EXT_PFC_ENTRIES \ + BNGE_TX_STATS_EXT_PFC_ENTRY(0), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(1), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(2), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(3), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(4), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(5), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(6), \ + BNGE_TX_STATS_EXT_PFC_ENTRY(7) + +#define BNGE_RX_STATS_EXT_COS_ENTRY(n) \ + BNGE_RX_STATS_EXT_ENTRY(rx_bytes_cos##n), \ + BNGE_RX_STATS_EXT_ENTRY(rx_packets_cos##n) + +#define BNGE_TX_STATS_EXT_COS_ENTRY(n) \ + BNGE_TX_STATS_EXT_ENTRY(tx_bytes_cos##n), \ + BNGE_TX_STATS_EXT_ENTRY(tx_packets_cos##n) + +#define BNGE_RX_STATS_EXT_COS_ENTRIES \ + BNGE_RX_STATS_EXT_COS_ENTRY(0), \ + BNGE_RX_STATS_EXT_COS_ENTRY(1), \ + BNGE_RX_STATS_EXT_COS_ENTRY(2), \ + BNGE_RX_STATS_EXT_COS_ENTRY(3), \ + BNGE_RX_STATS_EXT_COS_ENTRY(4), \ + BNGE_RX_STATS_EXT_COS_ENTRY(5), \ + BNGE_RX_STATS_EXT_COS_ENTRY(6), \ + BNGE_RX_STATS_EXT_COS_ENTRY(7) \ + +#define BNGE_TX_STATS_EXT_COS_ENTRIES \ + BNGE_TX_STATS_EXT_COS_ENTRY(0), \ + BNGE_TX_STATS_EXT_COS_ENTRY(1), \ + BNGE_TX_STATS_EXT_COS_ENTRY(2), \ + BNGE_TX_STATS_EXT_COS_ENTRY(3), \ + BNGE_TX_STATS_EXT_COS_ENTRY(4), \ + BNGE_TX_STATS_EXT_COS_ENTRY(5), \ + BNGE_TX_STATS_EXT_COS_ENTRY(6), \ + BNGE_TX_STATS_EXT_COS_ENTRY(7) \ + +#define BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(n) \ + BNGE_RX_STATS_EXT_ENTRY(rx_discard_bytes_cos##n), \ + BNGE_RX_STATS_EXT_ENTRY(rx_discard_packets_cos##n) + +#define BNGE_RX_STATS_EXT_DISCARD_COS_ENTRIES \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(0), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(1), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(2), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(3), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(4), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(5), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(6), \ + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRY(7) + +#define BNGE_RX_STATS_PRI_ENTRY(counter, n) \ + { BNGE_RX_STATS_EXT_OFFSET(counter##_cos0), \ + __stringify(counter##_pri##n) } + +#define BNGE_TX_STATS_PRI_ENTRY(counter, n) \ + { BNGE_TX_STATS_EXT_OFFSET(counter##_cos0), \ + __stringify(counter##_pri##n) } + +#define BNGE_RX_STATS_PRI_ENTRIES(counter) \ + BNGE_RX_STATS_PRI_ENTRY(counter, 0), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 1), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 2), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 3), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 4), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 5), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 6), \ + BNGE_RX_STATS_PRI_ENTRY(counter, 7) + +#define BNGE_TX_STATS_PRI_ENTRIES(counter) \ + BNGE_TX_STATS_PRI_ENTRY(counter, 0), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 1), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 2), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 3), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 4), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 5), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 6), \ + BNGE_TX_STATS_PRI_ENTRY(counter, 7) + +enum { + RX_TOTAL_DISCARDS, + TX_TOTAL_DISCARDS, + RX_NETPOLL_DISCARDS, +}; + +static const char *const bnge_ring_err_stats_arr[] = { + "rx_total_l4_csum_errors", + "rx_total_resets", + "rx_total_buf_errors", + "rx_total_oom_discards", + "rx_total_netpoll_discards", + "rx_total_ring_discards", + "tx_total_resets", + "tx_total_ring_discards", +}; + +#define NUM_RING_RX_SW_STATS ARRAY_SIZE(bnge_rx_sw_stats_str) +#define NUM_RING_RX_HW_STATS ARRAY_SIZE(bnge_ring_rx_stats_str) +#define NUM_RING_TX_HW_STATS ARRAY_SIZE(bnge_ring_tx_stats_str) + +static const struct { + long offset; + char string[ETH_GSTRING_LEN]; +} bnge_tx_port_stats_ext_arr[] = { + BNGE_TX_STATS_EXT_COS_ENTRIES, + BNGE_TX_STATS_EXT_PFC_ENTRIES, +}; + +static const struct { + long base_off; + char string[ETH_GSTRING_LEN]; +} bnge_rx_bytes_pri_arr[] = { + BNGE_RX_STATS_PRI_ENTRIES(rx_bytes), +}; + +static const struct { + long base_off; + char string[ETH_GSTRING_LEN]; +} bnge_rx_pkts_pri_arr[] = { + BNGE_RX_STATS_PRI_ENTRIES(rx_packets), +}; + +static const struct { + long base_off; + char string[ETH_GSTRING_LEN]; +} bnge_tx_bytes_pri_arr[] = { + BNGE_TX_STATS_PRI_ENTRIES(tx_bytes), +}; + +static const struct { + long base_off; + char string[ETH_GSTRING_LEN]; +} bnge_tx_pkts_pri_arr[] = { + BNGE_TX_STATS_PRI_ENTRIES(tx_packets), +}; + +static const struct { + long offset; + char string[ETH_GSTRING_LEN]; +} bnge_port_stats_arr[] = { + BNGE_RX_STATS_ENTRY(rx_64b_frames), + BNGE_RX_STATS_ENTRY(rx_65b_127b_frames), + BNGE_RX_STATS_ENTRY(rx_128b_255b_frames), + BNGE_RX_STATS_ENTRY(rx_256b_511b_frames), + BNGE_RX_STATS_ENTRY(rx_512b_1023b_frames), + BNGE_RX_STATS_ENTRY(rx_1024b_1518b_frames), + BNGE_RX_STATS_ENTRY(rx_good_vlan_frames), + BNGE_RX_STATS_ENTRY(rx_1519b_2047b_frames), + BNGE_RX_STATS_ENTRY(rx_2048b_4095b_frames), + BNGE_RX_STATS_ENTRY(rx_4096b_9216b_frames), + BNGE_RX_STATS_ENTRY(rx_9217b_16383b_frames), + BNGE_RX_STATS_ENTRY(rx_total_frames), + BNGE_RX_STATS_ENTRY(rx_ucast_frames), + BNGE_RX_STATS_ENTRY(rx_mcast_frames), + BNGE_RX_STATS_ENTRY(rx_bcast_frames), + BNGE_RX_STATS_ENTRY(rx_fcs_err_frames), + BNGE_RX_STATS_ENTRY(rx_ctrl_frames), + BNGE_RX_STATS_ENTRY(rx_pause_frames), + BNGE_RX_STATS_ENTRY(rx_pfc_frames), + BNGE_RX_STATS_ENTRY(rx_align_err_frames), + BNGE_RX_STATS_ENTRY(rx_ovrsz_frames), + BNGE_RX_STATS_ENTRY(rx_jbr_frames), + BNGE_RX_STATS_ENTRY(rx_mtu_err_frames), + BNGE_RX_STATS_ENTRY(rx_tagged_frames), + BNGE_RX_STATS_ENTRY(rx_double_tagged_frames), + BNGE_RX_STATS_ENTRY(rx_good_frames), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri0), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri1), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri2), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri3), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri4), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri5), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri6), + BNGE_RX_STATS_ENTRY(rx_pfc_ena_frames_pri7), + BNGE_RX_STATS_ENTRY(rx_undrsz_frames), + BNGE_RX_STATS_ENTRY(rx_eee_lpi_events), + BNGE_RX_STATS_ENTRY(rx_eee_lpi_duration), + BNGE_RX_STATS_ENTRY(rx_bytes), + BNGE_RX_STATS_ENTRY(rx_runt_bytes), + BNGE_RX_STATS_ENTRY(rx_runt_frames), + BNGE_RX_STATS_ENTRY(rx_stat_discard), + BNGE_RX_STATS_ENTRY(rx_stat_err), + + BNGE_TX_STATS_ENTRY(tx_64b_frames), + BNGE_TX_STATS_ENTRY(tx_65b_127b_frames), + BNGE_TX_STATS_ENTRY(tx_128b_255b_frames), + BNGE_TX_STATS_ENTRY(tx_256b_511b_frames), + BNGE_TX_STATS_ENTRY(tx_512b_1023b_frames), + BNGE_TX_STATS_ENTRY(tx_1024b_1518b_frames), + BNGE_TX_STATS_ENTRY(tx_good_vlan_frames), + BNGE_TX_STATS_ENTRY(tx_1519b_2047b_frames), + BNGE_TX_STATS_ENTRY(tx_2048b_4095b_frames), + BNGE_TX_STATS_ENTRY(tx_4096b_9216b_frames), + BNGE_TX_STATS_ENTRY(tx_9217b_16383b_frames), + BNGE_TX_STATS_ENTRY(tx_good_frames), + BNGE_TX_STATS_ENTRY(tx_total_frames), + BNGE_TX_STATS_ENTRY(tx_ucast_frames), + BNGE_TX_STATS_ENTRY(tx_mcast_frames), + BNGE_TX_STATS_ENTRY(tx_bcast_frames), + BNGE_TX_STATS_ENTRY(tx_pause_frames), + BNGE_TX_STATS_ENTRY(tx_pfc_frames), + BNGE_TX_STATS_ENTRY(tx_jabber_frames), + BNGE_TX_STATS_ENTRY(tx_fcs_err_frames), + BNGE_TX_STATS_ENTRY(tx_err), + BNGE_TX_STATS_ENTRY(tx_fifo_underruns), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri0), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri1), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri2), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri3), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri4), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri5), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri6), + BNGE_TX_STATS_ENTRY(tx_pfc_ena_frames_pri7), + BNGE_TX_STATS_ENTRY(tx_eee_lpi_events), + BNGE_TX_STATS_ENTRY(tx_eee_lpi_duration), + BNGE_TX_STATS_ENTRY(tx_total_collisions), + BNGE_TX_STATS_ENTRY(tx_bytes), + BNGE_TX_STATS_ENTRY(tx_xthol_frames), + BNGE_TX_STATS_ENTRY(tx_stat_discard), + BNGE_TX_STATS_ENTRY(tx_stat_error), +}; + +static const struct { + long offset; + char string[ETH_GSTRING_LEN]; +} bnge_port_stats_ext_arr[] = { + BNGE_RX_STATS_EXT_ENTRY(link_down_events), + BNGE_RX_STATS_EXT_ENTRY(continuous_pause_events), + BNGE_RX_STATS_EXT_ENTRY(resume_pause_events), + BNGE_RX_STATS_EXT_ENTRY(continuous_roce_pause_events), + BNGE_RX_STATS_EXT_ENTRY(resume_roce_pause_events), + BNGE_RX_STATS_EXT_COS_ENTRIES, + BNGE_RX_STATS_EXT_PFC_ENTRIES, + BNGE_RX_STATS_EXT_ENTRY(rx_bits), + BNGE_RX_STATS_EXT_ENTRY(rx_buffer_passed_threshold), + BNGE_RX_STATS_EXT_ENTRY(rx_pcs_symbol_err), + BNGE_RX_STATS_EXT_ENTRY(rx_corrected_bits), + BNGE_RX_STATS_EXT_DISCARD_COS_ENTRIES, + BNGE_RX_STATS_EXT_ENTRY(rx_fec_corrected_blocks), + BNGE_RX_STATS_EXT_ENTRY(rx_fec_uncorrectable_blocks), + BNGE_RX_STATS_EXT_ENTRY(rx_filter_miss), +}; + +static int bnge_get_num_tpa_ring_stats(struct bnge_dev *bd) +{ + if (BNGE_SUPPORTS_TPA(bd)) + return BNGE_NUM_TPA_RING_STATS; + return 0; +} + +#define BNGE_NUM_RING_ERR_STATS ARRAY_SIZE(bnge_ring_err_stats_arr) +#define BNGE_NUM_PORT_STATS ARRAY_SIZE(bnge_port_stats_arr) +#define BNGE_NUM_STATS_PRI \ + (ARRAY_SIZE(bnge_rx_bytes_pri_arr) + \ + ARRAY_SIZE(bnge_rx_pkts_pri_arr) + \ + ARRAY_SIZE(bnge_tx_bytes_pri_arr) + \ + ARRAY_SIZE(bnge_tx_pkts_pri_arr)) + +static int bnge_get_num_ring_stats(struct bnge_dev *bd) +{ + int rx, tx; + + rx = NUM_RING_RX_HW_STATS + NUM_RING_RX_SW_STATS + + bnge_get_num_tpa_ring_stats(bd); + tx = NUM_RING_TX_HW_STATS; + return rx * bd->rx_nr_rings + + tx * bd->tx_nr_rings_per_tc; +} + +static int bnge_get_num_stats(struct bnge_net *bn) +{ + int num_stats = bnge_get_num_ring_stats(bn->bd); + int len; + + num_stats += BNGE_NUM_RING_ERR_STATS; + + if (bn->flags & BNGE_FLAG_PORT_STATS) + num_stats += BNGE_NUM_PORT_STATS; + + if (bn->flags & BNGE_FLAG_PORT_STATS_EXT) { + len = min_t(int, bn->fw_rx_stats_ext_size, + ARRAY_SIZE(bnge_port_stats_ext_arr)); + num_stats += len; + len = min_t(int, bn->fw_tx_stats_ext_size, + ARRAY_SIZE(bnge_tx_port_stats_ext_arr)); + num_stats += len; + if (bn->pri2cos_valid) + num_stats += BNGE_NUM_STATS_PRI; + } + + return num_stats; +} static void bnge_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) @@ -21,10 +409,259 @@ static void bnge_get_drvinfo(struct net_device *dev, strscpy(info->driver, DRV_NAME, sizeof(info->driver)); strscpy(info->fw_version, bd->fw_ver_str, sizeof(info->fw_version)); strscpy(info->bus_info, pci_name(bd->pdev), sizeof(info->bus_info)); + info->n_stats = bnge_get_num_stats(bn); +} + +static int bnge_get_sset_count(struct net_device *dev, int sset) +{ + struct bnge_net *bn = netdev_priv(dev); + + switch (sset) { + case ETH_SS_STATS: + return bnge_get_num_stats(bn); + default: + return -EOPNOTSUPP; + } +} + +static bool is_rx_ring(struct bnge_dev *bd, u16 ring_num) +{ + return ring_num < bd->rx_nr_rings; +} + +static bool is_tx_ring(struct bnge_dev *bd, u16 ring_num) +{ + u16 tx_base = 0; + + if (!(bd->flags & BNGE_EN_SHARED_CHNL)) + tx_base = bd->rx_nr_rings; + + if (ring_num >= tx_base && ring_num < (tx_base + bd->tx_nr_rings)) + return true; + return false; +} + +static void bnge_get_ethtool_stats(struct net_device *dev, + struct ethtool_stats *stats, u64 *buf) +{ + struct bnge_total_ring_err_stats ring_err_stats = {0}; + struct bnge_net *bn = netdev_priv(dev); + struct bnge_dev *bd = bn->bd; + u64 *curr, *prev; + u32 tpa_stats; + u32 i, j = 0; + + if (!bn->bnapi) { + j += bnge_get_num_ring_stats(bd); + goto skip_ring_stats; + } + + tpa_stats = bnge_get_num_tpa_ring_stats(bd); + for (i = 0; i < bd->nq_nr_rings; i++) { + struct bnge_napi *bnapi = bn->bnapi[i]; + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + u64 *sw_stats = nqr->stats.sw_stats; + u64 *sw; + int k; + + if (is_rx_ring(bd, i)) { + for (k = 0; k < NUM_RING_RX_HW_STATS; j++, k++) + buf[j] = sw_stats[k]; + } + if (is_tx_ring(bd, i)) { + k = NUM_RING_RX_HW_STATS; + for (; k < NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS; + j++, k++) + buf[j] = sw_stats[k]; + } + if (!tpa_stats || !is_rx_ring(bd, i)) + goto skip_tpa_ring_stats; + + k = NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS; + for (; k < NUM_RING_RX_HW_STATS + NUM_RING_TX_HW_STATS + + tpa_stats; j++, k++) + buf[j] = sw_stats[k]; + +skip_tpa_ring_stats: + sw = (u64 *)&nqr->sw_stats->rx; + if (is_rx_ring(bd, i)) { + for (k = 0; k < NUM_RING_RX_SW_STATS; j++, k++) + buf[j] = sw[k]; + } + } + + bnge_get_ring_err_stats(bn, &ring_err_stats); + +skip_ring_stats: + curr = &ring_err_stats.rx_total_l4_csum_errors; + prev = &bn->ring_err_stats_prev.rx_total_l4_csum_errors; + for (i = 0; i < BNGE_NUM_RING_ERR_STATS; i++, j++, curr++, prev++) + buf[j] = *curr + *prev; + + if (bn->flags & BNGE_FLAG_PORT_STATS) { + u64 *port_stats = bn->port_stats.sw_stats; + + for (i = 0; i < BNGE_NUM_PORT_STATS; i++, j++) + buf[j] = *(port_stats + bnge_port_stats_arr[i].offset); + } + if (bn->flags & BNGE_FLAG_PORT_STATS_EXT) { + u64 *rx_port_stats_ext = bn->rx_port_stats_ext.sw_stats; + u64 *tx_port_stats_ext = bn->tx_port_stats_ext.sw_stats; + u32 len; + + len = min_t(u32, bn->fw_rx_stats_ext_size, + ARRAY_SIZE(bnge_port_stats_ext_arr)); + for (i = 0; i < len; i++, j++) { + buf[j] = *(rx_port_stats_ext + + bnge_port_stats_ext_arr[i].offset); + } + len = min_t(u32, bn->fw_tx_stats_ext_size, + ARRAY_SIZE(bnge_tx_port_stats_ext_arr)); + for (i = 0; i < len; i++, j++) { + buf[j] = *(tx_port_stats_ext + + bnge_tx_port_stats_ext_arr[i].offset); + } + if (bn->pri2cos_valid) { + for (i = 0; i < 8; i++, j++) { + long n = bnge_rx_bytes_pri_arr[i].base_off + + bn->pri2cos_idx[i]; + + buf[j] = *(rx_port_stats_ext + n); + } + for (i = 0; i < 8; i++, j++) { + long n = bnge_rx_pkts_pri_arr[i].base_off + + bn->pri2cos_idx[i]; + + buf[j] = *(rx_port_stats_ext + n); + } + for (i = 0; i < 8; i++, j++) { + long n = bnge_tx_bytes_pri_arr[i].base_off + + bn->pri2cos_idx[i]; + + buf[j] = *(tx_port_stats_ext + n); + } + for (i = 0; i < 8; i++, j++) { + long n = bnge_tx_pkts_pri_arr[i].base_off + + bn->pri2cos_idx[i]; + + buf[j] = *(tx_port_stats_ext + n); + } + } + } +} + +static void bnge_get_strings(struct net_device *dev, u32 stringset, u8 *buf) +{ + struct bnge_net *bn = netdev_priv(dev); + struct bnge_dev *bd = bn->bd; + u32 i, j, num_str; + const char *str; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < bd->nq_nr_rings; i++) { + if (is_rx_ring(bd, i)) + for (j = 0; j < NUM_RING_RX_HW_STATS; j++) { + str = bnge_ring_rx_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } + if (is_tx_ring(bd, i)) + for (j = 0; j < NUM_RING_TX_HW_STATS; j++) { + str = bnge_ring_tx_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } + num_str = bnge_get_num_tpa_ring_stats(bd); + if (!num_str || !is_rx_ring(bd, i)) + goto skip_tpa_stats; + + if (bd->max_tpa_v2) + for (j = 0; j < num_str; j++) { + str = bnge_ring_tpa2_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } + else + for (j = 0; j < num_str; j++) { + str = bnge_ring_tpa_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } +skip_tpa_stats: + if (is_rx_ring(bd, i)) + for (j = 0; j < NUM_RING_RX_SW_STATS; j++) { + str = bnge_rx_sw_stats_str[j]; + ethtool_sprintf(&buf, "[%d]: %s", i, + str); + } + } + for (i = 0; i < BNGE_NUM_RING_ERR_STATS; i++) + ethtool_puts(&buf, bnge_ring_err_stats_arr[i]); + + if (bn->flags & BNGE_FLAG_PORT_STATS) + for (i = 0; i < BNGE_NUM_PORT_STATS; i++) { + str = bnge_port_stats_arr[i].string; + ethtool_puts(&buf, str); + } + + if (bn->flags & BNGE_FLAG_PORT_STATS_EXT) { + u32 len; + + len = min_t(u32, bn->fw_rx_stats_ext_size, + ARRAY_SIZE(bnge_port_stats_ext_arr)); + for (i = 0; i < len; i++) { + str = bnge_port_stats_ext_arr[i].string; + ethtool_puts(&buf, str); + } + + len = min_t(u32, bn->fw_tx_stats_ext_size, + ARRAY_SIZE(bnge_tx_port_stats_ext_arr)); + for (i = 0; i < len; i++) { + str = bnge_tx_port_stats_ext_arr[i].string; + ethtool_puts(&buf, str); + } + + if (bn->pri2cos_valid) { + for (i = 0; i < 8; i++) { + str = bnge_rx_bytes_pri_arr[i].string; + ethtool_puts(&buf, str); + } + + for (i = 0; i < 8; i++) { + str = bnge_rx_pkts_pri_arr[i].string; + ethtool_puts(&buf, str); + } + + for (i = 0; i < 8; i++) { + str = bnge_tx_bytes_pri_arr[i].string; + ethtool_puts(&buf, str); + } + + for (i = 0; i < 8; i++) { + str = bnge_tx_pkts_pri_arr[i].string; + ethtool_puts(&buf, str); + } + } + } + break; + default: + netdev_err(bd->netdev, "%s invalid request %x\n", + __func__, stringset); + break; + } } static const struct ethtool_ops bnge_ethtool_ops = { + .cap_link_lanes_supported = 1, + .get_link_ksettings = bnge_get_link_ksettings, + .set_link_ksettings = bnge_set_link_ksettings, .get_drvinfo = bnge_get_drvinfo, + .get_link = bnge_get_link, + .nway_reset = bnge_nway_reset, + .get_sset_count = bnge_get_sset_count, + .get_strings = bnge_get_strings, + .get_ethtool_stats = bnge_get_ethtool_stats, }; void bnge_set_ethtool_ops(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hw_def.h b/drivers/net/ethernet/broadcom/bnge/bnge_hw_def.h new file mode 100644 index 0000000000000..a41f4b000032a --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hw_def.h @@ -0,0 +1,214 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Broadcom */ + +#ifndef _BNGE_HW_DEF_H_ +#define _BNGE_HW_DEF_H_ + +struct rx_agg_cmp { + __le32 rx_agg_cmp_len_flags_type; + #define RX_AGG_CMP_TYPE (0x3f << 0) + #define RX_AGG_CMP_LEN (0xffff << 16) + #define RX_AGG_CMP_LEN_SHIFT 16 + u32 rx_agg_cmp_opaque; + __le32 rx_agg_cmp_v; + #define RX_AGG_CMP_V (1 << 0) + #define RX_AGG_CMP_AGG_ID (0xffff << 16) + #define RX_AGG_CMP_AGG_ID_SHIFT 16 + __le32 rx_agg_cmp_unused; +}; + +struct tx_bd_ext { + __le32 tx_bd_hsize_lflags; + #define TX_BD_FLAGS_TCP_UDP_CHKSUM (1 << 0) + #define TX_BD_FLAGS_IP_CKSUM (1 << 1) + #define TX_BD_FLAGS_NO_CRC (1 << 2) + #define TX_BD_FLAGS_STAMP (1 << 3) + #define TX_BD_FLAGS_T_IP_CHKSUM (1 << 4) + #define TX_BD_FLAGS_LSO (1 << 5) + #define TX_BD_FLAGS_IPID_FMT (1 << 6) + #define TX_BD_FLAGS_T_IPID (1 << 7) + #define TX_BD_HSIZE (0xff << 16) + #define TX_BD_HSIZE_SHIFT 16 + + __le32 tx_bd_mss; + __le32 tx_bd_cfa_action; + #define TX_BD_CFA_ACTION (0xffff << 16) + #define TX_BD_CFA_ACTION_SHIFT 16 + + __le32 tx_bd_cfa_meta; + #define TX_BD_CFA_META_MASK 0xfffffff + #define TX_BD_CFA_META_VID_MASK 0xfff + #define TX_BD_CFA_META_PRI_MASK (0xf << 12) + #define TX_BD_CFA_META_PRI_SHIFT 12 + #define TX_BD_CFA_META_TPID_MASK (3 << 16) + #define TX_BD_CFA_META_TPID_SHIFT 16 + #define TX_BD_CFA_META_KEY (0xf << 28) + #define TX_BD_CFA_META_KEY_SHIFT 28 + #define TX_BD_CFA_META_KEY_VLAN (1 << 28) +}; + +#define TX_CMP_SQ_CONS_IDX(txcmp) \ + (le32_to_cpu((txcmp)->sq_cons_idx) & TX_CMP_SQ_CONS_IDX_MASK) + +struct rx_cmp { + __le32 rx_cmp_len_flags_type; + #define RX_CMP_CMP_TYPE (0x3f << 0) + #define RX_CMP_FLAGS_ERROR (1 << 6) + #define RX_CMP_FLAGS_PLACEMENT (7 << 7) + #define RX_CMP_FLAGS_RSS_VALID (1 << 10) + #define RX_CMP_FLAGS_PKT_METADATA_PRESENT (1 << 11) + #define RX_CMP_FLAGS_ITYPES_SHIFT 12 + #define RX_CMP_FLAGS_ITYPES_MASK 0xf000 + #define RX_CMP_FLAGS_ITYPE_UNKNOWN (0 << 12) + #define RX_CMP_FLAGS_ITYPE_IP (1 << 12) + #define RX_CMP_FLAGS_ITYPE_TCP (2 << 12) + #define RX_CMP_FLAGS_ITYPE_UDP (3 << 12) + #define RX_CMP_FLAGS_ITYPE_FCOE (4 << 12) + #define RX_CMP_FLAGS_ITYPE_ROCE (5 << 12) + #define RX_CMP_FLAGS_ITYPE_PTP_WO_TS (8 << 12) + #define RX_CMP_FLAGS_ITYPE_PTP_W_TS (9 << 12) + #define RX_CMP_LEN (0xffff << 16) + #define RX_CMP_LEN_SHIFT 16 + + u32 rx_cmp_opaque; + __le32 rx_cmp_misc_v1; + #define RX_CMP_V1 (1 << 0) + #define RX_CMP_AGG_BUFS (0x1f << 1) + #define RX_CMP_AGG_BUFS_SHIFT 1 + #define RX_CMP_RSS_HASH_TYPE (0x7f << 9) + #define RX_CMP_RSS_HASH_TYPE_SHIFT 9 + #define RX_CMP_V3_RSS_EXT_OP_LEGACY (0xf << 12) + #define RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT 12 + #define RX_CMP_V3_RSS_EXT_OP_NEW (0xf << 8) + #define RX_CMP_V3_RSS_EXT_OP_NEW_SHIFT 8 + #define RX_CMP_PAYLOAD_OFFSET (0xff << 16) + #define RX_CMP_PAYLOAD_OFFSET_SHIFT 16 + #define RX_CMP_SUB_NS_TS (0xf << 16) + #define RX_CMP_SUB_NS_TS_SHIFT 16 + #define RX_CMP_METADATA1 (0xf << 28) + #define RX_CMP_METADATA1_SHIFT 28 + #define RX_CMP_METADATA1_TPID_SEL (0x7 << 28) + #define RX_CMP_METADATA1_TPID_8021Q (0x1 << 28) + #define RX_CMP_METADATA1_TPID_8021AD (0x0 << 28) + #define RX_CMP_METADATA1_VALID (0x8 << 28) + + __le32 rx_cmp_rss_hash; +}; + +struct rx_cmp_ext { + __le32 rx_cmp_flags2; + #define RX_CMP_FLAGS2_IP_CS_CALC 0x1 + #define RX_CMP_FLAGS2_L4_CS_CALC (0x1 << 1) + #define RX_CMP_FLAGS2_T_IP_CS_CALC (0x1 << 2) + #define RX_CMP_FLAGS2_T_L4_CS_CALC (0x1 << 3) + #define RX_CMP_FLAGS2_META_FORMAT_VLAN (0x1 << 4) + __le32 rx_cmp_meta_data; + #define RX_CMP_FLAGS2_METADATA_TCI_MASK 0xffff + #define RX_CMP_FLAGS2_METADATA_VID_MASK 0xfff + #define RX_CMP_FLAGS2_METADATA_TPID_MASK 0xffff0000 + #define RX_CMP_FLAGS2_METADATA_TPID_SFT 16 + __le32 rx_cmp_cfa_code_errors_v2; + #define RX_CMP_V (1 << 0) + #define RX_CMPL_ERRORS_MASK (0x7fff << 1) + #define RX_CMPL_ERRORS_SFT 1 + #define RX_CMPL_ERRORS_BUFFER_ERROR_MASK (0x7 << 1) + #define RX_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT (0x1 << 1) + #define RX_CMPL_ERRORS_BUFFER_ERROR_NOT_ON_CHIP (0x2 << 1) + #define RX_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_CMPL_ERRORS_IP_CS_ERROR (0x1 << 4) + #define RX_CMPL_ERRORS_L4_CS_ERROR (0x1 << 5) + #define RX_CMPL_ERRORS_T_IP_CS_ERROR (0x1 << 6) + #define RX_CMPL_ERRORS_T_L4_CS_ERROR (0x1 << 7) + #define RX_CMPL_ERRORS_CRC_ERROR (0x1 << 8) + #define RX_CMPL_ERRORS_T_PKT_ERROR_MASK (0x7 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_NO_ERROR (0x0 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_T_L3_BAD_VERSION (0x1 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_T_L3_BAD_HDR_LEN (0x2 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_TUNNEL_TOTAL_ERROR (0x3 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_T_IP_TOTAL_ERROR (0x4 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_T_UDP_TOTAL_ERROR (0x5 << 9) + #define RX_CMPL_ERRORS_T_PKT_ERROR_T_L3_BAD_TTL (0x6 << 9) + #define RX_CMPL_ERRORS_PKT_ERROR_MASK (0xf << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_NO_ERROR (0x0 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_L3_BAD_VERSION (0x1 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_L3_BAD_HDR_LEN (0x2 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_L3_BAD_TTL (0x3 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_IP_TOTAL_ERROR (0x4 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_UDP_TOTAL_ERROR (0x5 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN (0x6 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_L4_BAD_HDR_LEN_TOO_SMALL (0x7 << 12) + #define RX_CMPL_ERRORS_PKT_ERROR_L4_BAD_OPT_LEN (0x8 << 12) + + #define RX_CMPL_CFA_CODE_MASK (0xffff << 16) + #define RX_CMPL_CFA_CODE_SFT 16 + #define RX_CMPL_METADATA0_TCI_MASK (0xffff << 16) + #define RX_CMPL_METADATA0_VID_MASK (0x0fff << 16) + #define RX_CMPL_METADATA0_SFT 16 + + __le32 rx_cmp_timestamp; +}; + +#define RX_CMP_L2_ERRORS \ + cpu_to_le32(RX_CMPL_ERRORS_BUFFER_ERROR_MASK | RX_CMPL_ERRORS_CRC_ERROR) + +#define RX_CMP_L4_CS_BITS \ + (cpu_to_le32(RX_CMP_FLAGS2_L4_CS_CALC | RX_CMP_FLAGS2_T_L4_CS_CALC)) + +#define RX_CMP_L4_CS_ERR_BITS \ + (cpu_to_le32(RX_CMPL_ERRORS_L4_CS_ERROR | RX_CMPL_ERRORS_T_L4_CS_ERROR)) + +#define RX_CMP_L4_CS_OK(rxcmp1) \ + (((rxcmp1)->rx_cmp_flags2 & RX_CMP_L4_CS_BITS) && \ + !((rxcmp1)->rx_cmp_cfa_code_errors_v2 & RX_CMP_L4_CS_ERR_BITS)) + +#define RX_CMP_METADATA0_TCI(rxcmp1) \ + ((le32_to_cpu((rxcmp1)->rx_cmp_cfa_code_errors_v2) & \ + RX_CMPL_METADATA0_TCI_MASK) >> RX_CMPL_METADATA0_SFT) + +#define RX_CMP_ENCAP(rxcmp1) \ + ((le32_to_cpu((rxcmp1)->rx_cmp_flags2) & \ + RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3) + +#define RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp) \ + ((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & \ + RX_CMP_V3_RSS_EXT_OP_LEGACY) >> RX_CMP_V3_RSS_EXT_OP_LEGACY_SHIFT) + +#define RX_CMP_V3_HASH_TYPE_NEW(rxcmp) \ + ((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_V3_RSS_EXT_OP_NEW) >>\ + RX_CMP_V3_RSS_EXT_OP_NEW_SHIFT) + +#define RX_CMP_V3_HASH_TYPE(bd, rxcmp) \ + (((bd)->rss_cap & BNGE_RSS_CAP_RSS_TCAM) ? \ + RX_CMP_V3_HASH_TYPE_NEW(rxcmp) : \ + RX_CMP_V3_HASH_TYPE_LEGACY(rxcmp)) + +#define EXT_OP_INNER_4 0x0 +#define EXT_OP_OUTER_4 0x2 +#define EXT_OP_INNFL_3 0x8 +#define EXT_OP_OUTFL_3 0xa + +#define RX_CMP_VLAN_VALID(rxcmp) \ + ((rxcmp)->rx_cmp_misc_v1 & cpu_to_le32(RX_CMP_METADATA1_VALID)) + +#define RX_CMP_VLAN_TPID_SEL(rxcmp) \ + (le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_METADATA1_TPID_SEL) + +#define RSS_PROFILE_ID_MASK 0x1f + +#define RX_CMP_HASH_TYPE(rxcmp) \ + (((le32_to_cpu((rxcmp)->rx_cmp_misc_v1) & RX_CMP_RSS_HASH_TYPE) >>\ + RX_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK) + +#define RX_CMP_L2_ERRORS \ + cpu_to_le32(RX_CMPL_ERRORS_BUFFER_ERROR_MASK | RX_CMPL_ERRORS_CRC_ERROR) + +#define RX_CMP_HASH_VALID(rxcmp) \ + ((rxcmp)->rx_cmp_len_flags_type & cpu_to_le32(RX_CMP_FLAGS_RSS_VALID)) + +#define HWRM_RING_ALLOC_TX 0x1 +#define HWRM_RING_ALLOC_RX 0x2 +#define HWRM_RING_ALLOC_AGG 0x4 +#define HWRM_RING_ALLOC_CMPL 0x8 +#define HWRM_RING_ALLOC_NQ 0x10 +#endif /* _BNGE_HW_DEF_H_ */ diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c index 198f49b40dbf0..144d9467b14f8 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c @@ -14,6 +14,8 @@ #include "bnge_hwrm_lib.h" #include "bnge_rmem.h" #include "bnge_resc.h" +#include "bnge_netdev.h" +#include "bnge_link.h" int bnge_hwrm_ver_get(struct bnge_dev *bd) { @@ -595,6 +597,10 @@ int bnge_hwrm_func_qcaps(struct bnge_dev *bd) bd->flags |= BNGE_EN_ROCE_V1; if (flags & FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED) bd->flags |= BNGE_EN_ROCE_V2; + if (flags & FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED) + bd->fw_cap |= BNGE_FW_CAP_EXT_STATS_SUPPORTED; + if (flags & FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED) + bd->fw_cap |= BNGE_FW_CAP_PCIE_STATS_SUPPORTED; pf->fw_fid = le16_to_cpu(resp->fid); pf->port_id = le16_to_cpu(resp->port_id); @@ -981,6 +987,192 @@ void bnge_hwrm_vnic_ctx_free_one(struct bnge_dev *bd, vnic->fw_rss_cos_lb_ctx[ctx_idx] = INVALID_HW_RING_ID; } +int bnge_hwrm_phy_qcaps(struct bnge_dev *bd) +{ + struct bnge_link_info *link_info = &bd->link_info; + struct hwrm_port_phy_qcaps_output *resp; + struct hwrm_port_phy_qcaps_input *req; + int rc = 0; + + rc = bnge_hwrm_req_init(bd, req, HWRM_PORT_PHY_QCAPS); + if (rc) + return rc; + + resp = bnge_hwrm_req_hold(bd, req); + rc = bnge_hwrm_req_send(bd, req); + if (rc) + goto hwrm_phy_qcaps_exit; + + bd->phy_flags = resp->flags | (le16_to_cpu(resp->flags2) << 8); + + if (bnge_phy_qcaps_no_speed(resp)) { + link_info->phy_state = BNGE_PHY_STATE_DISABLED; + netdev_warn(bd->netdev, "Ethernet link disabled\n"); + } else if (link_info->phy_state == BNGE_PHY_STATE_DISABLED) { + link_info->phy_state = BNGE_PHY_STATE_ENABLED; + netdev_info(bd->netdev, "Ethernet link enabled\n"); + /* Phy re-enabled, reprobe the speeds */ + link_info->support_auto_speeds = 0; + link_info->support_pam4_auto_speeds = 0; + link_info->support_auto_speeds2 = 0; + } + if (resp->supported_speeds_auto_mode) + link_info->support_auto_speeds = + le16_to_cpu(resp->supported_speeds_auto_mode); + if (resp->supported_pam4_speeds_auto_mode) + link_info->support_pam4_auto_speeds = + le16_to_cpu(resp->supported_pam4_speeds_auto_mode); + if (resp->supported_speeds2_auto_mode) + link_info->support_auto_speeds2 = + le16_to_cpu(resp->supported_speeds2_auto_mode); + + bd->port_count = resp->port_cnt; + +hwrm_phy_qcaps_exit: + bnge_hwrm_req_drop(bd, req); + return rc; +} + +int bnge_hwrm_set_link_setting(struct bnge_net *bn, bool set_pause) +{ + struct hwrm_port_phy_cfg_input *req; + struct bnge_dev *bd = bn->bd; + int rc; + + rc = bnge_hwrm_req_init(bd, req, HWRM_PORT_PHY_CFG); + if (rc) + return rc; + + if (set_pause) + bnge_hwrm_set_pause_common(bn, req); + + bnge_hwrm_set_link_common(bn, req); + + return bnge_hwrm_req_send(bd, req); +} + +int bnge_update_link(struct bnge_net *bn, bool chng_link_state) +{ + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + struct hwrm_port_phy_qcfg_output *resp; + u8 link_state = link_info->link_state; + struct hwrm_port_phy_qcfg_input *req; + bool support_changed; + int rc; + + rc = bnge_hwrm_req_init(bd, req, HWRM_PORT_PHY_QCFG); + if (rc) + return rc; + + resp = bnge_hwrm_req_hold(bd, req); + rc = bnge_hwrm_req_send(bd, req); + if (rc) { + bnge_hwrm_req_drop(bd, req); + return rc; + } + + memcpy(&link_info->phy_qcfg_resp, resp, sizeof(*resp)); + link_info->phy_link_status = resp->link; + link_info->duplex = resp->duplex_state; + link_info->pause = resp->pause; + link_info->auto_mode = resp->auto_mode; + link_info->auto_pause_setting = resp->auto_pause; + link_info->lp_pause = resp->link_partner_adv_pause; + link_info->force_pause_setting = resp->force_pause; + link_info->duplex_setting = resp->duplex_cfg; + if (link_info->phy_link_status == BNGE_LINK_LINK) { + link_info->link_speed = le16_to_cpu(resp->link_speed); + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) + link_info->active_lanes = resp->active_lanes; + } else { + link_info->link_speed = 0; + link_info->active_lanes = 0; + } + link_info->force_link_speed = le16_to_cpu(resp->force_link_speed); + link_info->force_pam4_link_speed = + le16_to_cpu(resp->force_pam4_link_speed); + link_info->force_link_speed2 = le16_to_cpu(resp->force_link_speeds2); + link_info->support_speeds = le16_to_cpu(resp->support_speeds); + link_info->support_pam4_speeds = le16_to_cpu(resp->support_pam4_speeds); + link_info->support_speeds2 = le16_to_cpu(resp->support_speeds2); + link_info->auto_link_speeds = le16_to_cpu(resp->auto_link_speed_mask); + link_info->auto_pam4_link_speeds = + le16_to_cpu(resp->auto_pam4_link_speed_mask); + link_info->auto_link_speeds2 = le16_to_cpu(resp->auto_link_speeds2); + link_info->lp_auto_link_speeds = + le16_to_cpu(resp->link_partner_adv_speeds); + link_info->lp_auto_pam4_link_speeds = + resp->link_partner_pam4_adv_speeds; + link_info->preemphasis = le32_to_cpu(resp->preemphasis); + link_info->phy_ver[0] = resp->phy_maj; + link_info->phy_ver[1] = resp->phy_min; + link_info->phy_ver[2] = resp->phy_bld; + link_info->media_type = resp->media_type; + link_info->phy_type = resp->phy_type; + link_info->transceiver = resp->xcvr_pkg_type; + link_info->phy_addr = resp->eee_config_phy_addr & + PORT_PHY_QCFG_RESP_PHY_ADDR_MASK; + link_info->module_status = resp->module_status; + + link_info->fec_cfg = PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED; + link_info->fec_cfg = le16_to_cpu(resp->fec_cfg); + link_info->active_fec_sig_mode = resp->active_fec_signal_mode; + /* TODO: need to add more logic to report VF link */ + if (chng_link_state) { + if (link_info->phy_link_status == BNGE_LINK_LINK) + link_info->link_state = BNGE_LINK_STATE_UP; + else + link_info->link_state = BNGE_LINK_STATE_DOWN; + if (link_state != link_info->link_state) + bnge_report_link(bd); + } else { + /* always link down if not require to update link state */ + link_info->link_state = BNGE_LINK_STATE_DOWN; + } + bnge_hwrm_req_drop(bd, req); + + if (!BNGE_PHY_CFG_ABLE(bd)) + return 0; + + support_changed = bnge_support_speed_dropped(bn); + if (support_changed && (bn->eth_link_info.autoneg & BNGE_AUTONEG_SPEED)) + bnge_hwrm_set_link_setting(bn, true); + return 0; +} + +int bnge_hwrm_set_pause(struct bnge_net *bn) +{ + struct hwrm_port_phy_cfg_input *req; + struct bnge_dev *bd = bn->bd; + int rc; + + rc = bnge_hwrm_req_init(bd, req, HWRM_PORT_PHY_CFG); + if (rc) + return rc; + + bnge_hwrm_set_pause_common(bn, req); + + if ((bn->eth_link_info.autoneg & BNGE_AUTONEG_FLOW_CTRL) || + bn->eth_link_info.force_link_chng) + bnge_hwrm_set_link_common(bn, req); + + rc = bnge_hwrm_req_send(bd, req); + if (!rc && !(bn->eth_link_info.autoneg & BNGE_AUTONEG_FLOW_CTRL)) { + /* since changing of pause setting doesn't trigger any link + * change event, the driver needs to update the current pause + * result upon successfully return of the phy_cfg command + */ + bd->link_info.force_pause_setting = + bd->link_info.pause = bn->eth_link_info.req_flow_ctrl; + bd->link_info.auto_pause_setting = 0; + if (!bn->eth_link_info.force_link_chng) + bnge_report_link(bd); + } + bn->eth_link_info.force_link_chng = false; + return rc; +} + void bnge_hwrm_stat_ctx_free(struct bnge_net *bn) { struct hwrm_stat_ctx_free_input *req; @@ -1183,3 +1375,206 @@ int bnge_hwrm_set_async_event_cr(struct bnge_dev *bd, int idx) req->async_event_cr = cpu_to_le16(idx); return bnge_hwrm_req_send(bd, req); } + +#define BNGE_DFLT_TUNL_TPA_BMAP \ + (VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE | \ + VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4 | \ + VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6) + +static void bnge_hwrm_vnic_update_tunl_tpa(struct bnge_dev *bd, + struct hwrm_vnic_tpa_cfg_input *req) +{ + struct bnge_net *bn = netdev_priv(bd->netdev); + u32 tunl_tpa_bmap = BNGE_DFLT_TUNL_TPA_BMAP; + + if (!(bd->fw_cap & BNGE_FW_CAP_VNIC_TUNNEL_TPA)) + return; + + if (bn->vxlan_port) + tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN; + if (bn->vxlan_gpe_port) + tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE; + if (bn->nge_port) + tunl_tpa_bmap |= VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE; + + req->enables |= cpu_to_le32(VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN); + req->tnl_tpa_en_bitmap = cpu_to_le32(tunl_tpa_bmap); +} + +int bnge_hwrm_vnic_set_tpa(struct bnge_dev *bd, struct bnge_vnic_info *vnic, + u32 tpa_flags) +{ + struct bnge_net *bn = netdev_priv(bd->netdev); + struct hwrm_vnic_tpa_cfg_input *req; + int rc; + + if (vnic->fw_vnic_id == INVALID_HW_RING_ID) + return 0; + + rc = bnge_hwrm_req_init(bd, req, HWRM_VNIC_TPA_CFG); + if (rc) + return rc; + + if (tpa_flags) { + u32 flags; + + flags = VNIC_TPA_CFG_REQ_FLAGS_TPA | + VNIC_TPA_CFG_REQ_FLAGS_ENCAP_TPA | + VNIC_TPA_CFG_REQ_FLAGS_RSC_WND_UPDATE | + VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_ECN | + VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_SAME_GRE_SEQ; + if (tpa_flags & BNGE_NET_EN_GRO) + flags |= VNIC_TPA_CFG_REQ_FLAGS_GRO; + + req->flags = cpu_to_le32(flags); + req->enables = + cpu_to_le32(VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS | + VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS | + VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN); + req->max_agg_segs = cpu_to_le16(MAX_TPA_SEGS); + req->max_aggs = cpu_to_le16(bn->max_tpa); + req->min_agg_len = cpu_to_le32(512); + bnge_hwrm_vnic_update_tunl_tpa(bd, req); + } + req->vnic_id = cpu_to_le16(vnic->fw_vnic_id); + + return bnge_hwrm_req_send(bd, req); +} + +int bnge_hwrm_func_qstat_ext(struct bnge_dev *bd, struct bnge_stats_mem *stats) +{ + struct hwrm_func_qstats_ext_output *resp; + struct hwrm_func_qstats_ext_input *req; + __le64 *hw_masks; + int rc; + + rc = bnge_hwrm_req_init(bd, req, HWRM_FUNC_QSTATS_EXT); + if (rc) + return rc; + + req->fid = cpu_to_le16(0xffff); + req->flags = FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; + + resp = bnge_hwrm_req_hold(bd, req); + rc = bnge_hwrm_req_send(bd, req); + if (!rc) { + hw_masks = &resp->rx_ucast_pkts; + bnge_copy_hw_masks(stats->hw_masks, hw_masks, stats->len / 8); + } + bnge_hwrm_req_drop(bd, req); + return rc; +} + +int bnge_hwrm_port_qstats_ext(struct bnge_dev *bd, u8 flags) +{ + struct hwrm_queue_pri2cos_qcfg_output *resp_qc; + struct bnge_net *bn = netdev_priv(bd->netdev); + struct hwrm_queue_pri2cos_qcfg_input *req_qc; + struct hwrm_port_qstats_ext_output *resp_qs; + struct hwrm_port_qstats_ext_input *req_qs; + struct bnge_pf_info *pf = &bd->pf; + u32 tx_stat_size; + int rc; + + if (!(bn->flags & BNGE_FLAG_PORT_STATS_EXT)) + return 0; + + if (flags && !(bd->fw_cap & BNGE_FW_CAP_EXT_HW_STATS_SUPPORTED)) + return -EOPNOTSUPP; + + rc = bnge_hwrm_req_init(bd, req_qs, HWRM_PORT_QSTATS_EXT); + if (rc) + return rc; + + req_qs->flags = flags; + req_qs->port_id = cpu_to_le16(pf->port_id); + req_qs->rx_stat_size = cpu_to_le16(sizeof(struct rx_port_stats_ext)); + req_qs->rx_stat_host_addr = + cpu_to_le64(bn->rx_port_stats_ext.hw_stats_map); + tx_stat_size = bn->tx_port_stats_ext.hw_stats ? + sizeof(struct tx_port_stats_ext) : 0; + req_qs->tx_stat_size = cpu_to_le16(tx_stat_size); + req_qs->tx_stat_host_addr = + cpu_to_le64(bn->tx_port_stats_ext.hw_stats_map); + resp_qs = bnge_hwrm_req_hold(bd, req_qs); + rc = bnge_hwrm_req_send(bd, req_qs); + if (!rc) { + bn->fw_rx_stats_ext_size = + le16_to_cpu(resp_qs->rx_stat_size) / 8; + bn->fw_tx_stats_ext_size = tx_stat_size ? + le16_to_cpu(resp_qs->tx_stat_size) / 8 : 0; + } else { + bn->fw_rx_stats_ext_size = 0; + bn->fw_tx_stats_ext_size = 0; + } + bnge_hwrm_req_drop(bd, req_qs); + + if (flags) + return rc; + + if (bn->fw_tx_stats_ext_size <= + offsetof(struct tx_port_stats_ext, pfc_pri0_tx_duration_us) / 8) { + bn->pri2cos_valid = 0; + return rc; + } + + rc = bnge_hwrm_req_init(bd, req_qc, HWRM_QUEUE_PRI2COS_QCFG); + if (rc) + return rc; + + req_qc->flags = cpu_to_le32(QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN); + + resp_qc = bnge_hwrm_req_hold(bd, req_qc); + rc = bnge_hwrm_req_send(bd, req_qc); + if (!rc) { + u8 *pri2cos; + int i, j; + + pri2cos = &resp_qc->pri0_cos_queue_id; + for (i = 0; i < 8; i++) { + u8 queue_id = pri2cos[i]; + u8 queue_idx; + + /* Per port queue IDs start from 0, 10, 20, etc */ + queue_idx = queue_id % 10; + if (queue_idx > BNGE_MAX_QUEUE) { + bn->pri2cos_valid = false; + bnge_hwrm_req_drop(bd, req_qc); + return rc; + } + for (j = 0; j < bd->max_q; j++) { + if (bd->q_ids[j] == queue_id) + bn->pri2cos_idx[i] = queue_idx; + } + } + bn->pri2cos_valid = true; + } + bnge_hwrm_req_drop(bd, req_qc); + + return rc; +} + +int bnge_hwrm_port_qstats(struct bnge_dev *bd, u8 flags) +{ + struct bnge_net *bn = netdev_priv(bd->netdev); + struct hwrm_port_qstats_input *req; + struct bnge_pf_info *pf = &bd->pf; + int rc; + + if (!(bn->flags & BNGE_FLAG_PORT_STATS)) + return 0; + + if (flags && !(bd->fw_cap & BNGE_FW_CAP_EXT_HW_STATS_SUPPORTED)) + return -EOPNOTSUPP; + + rc = bnge_hwrm_req_init(bd, req, HWRM_PORT_QSTATS); + if (rc) + return rc; + + req->flags = flags; + req->port_id = cpu_to_le16(pf->port_id); + req->tx_stat_host_addr = cpu_to_le64(bn->port_stats.hw_stats_map + + BNGE_TX_PORT_STATS_BYTE_OFFSET); + req->rx_stat_host_addr = cpu_to_le64(bn->port_stats.hw_stats_map); + return bnge_hwrm_req_send(bd, req); +} diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h index 042f28e84a05b..d43ccd4c7b372 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.h @@ -55,4 +55,13 @@ int hwrm_ring_alloc_send_msg(struct bnge_net *bn, struct bnge_ring_struct *ring, u32 ring_type, u32 map_index); int bnge_hwrm_set_async_event_cr(struct bnge_dev *bd, int idx); +int bnge_update_link(struct bnge_net *bn, bool chng_link_state); +int bnge_hwrm_phy_qcaps(struct bnge_dev *bd); +int bnge_hwrm_set_link_setting(struct bnge_net *bn, bool set_pause); +int bnge_hwrm_set_pause(struct bnge_net *bn); +int bnge_hwrm_vnic_set_tpa(struct bnge_dev *bd, struct bnge_vnic_info *vnic, + u32 tpa_flags); +int bnge_hwrm_port_qstats(struct bnge_dev *bd, u8 flags); +int bnge_hwrm_port_qstats_ext(struct bnge_dev *bd, u8 flags); +int bnge_hwrm_func_qstat_ext(struct bnge_dev *bd, struct bnge_stats_mem *stats); #endif /* _BNGE_HWRM_LIB_H_ */ diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_link.c b/drivers/net/ethernet/broadcom/bnge/bnge_link.c new file mode 100644 index 0000000000000..8e18b2476505a --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnge/bnge_link.c @@ -0,0 +1,1289 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2025 Broadcom. + +#include + +#include "bnge.h" +#include "bnge_link.h" +#include "bnge_hwrm_lib.h" + +enum bnge_media_type { + BNGE_MEDIA_UNKNOWN = 0, + BNGE_MEDIA_TP, + BNGE_MEDIA_CR, + BNGE_MEDIA_SR, + BNGE_MEDIA_LR_ER_FR, + BNGE_MEDIA_KR, + BNGE_MEDIA_KX, + BNGE_MEDIA_X, + __BNGE_MEDIA_END, +}; + +static const enum bnge_media_type bnge_phy_types[] = { + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASECR] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR4] = BNGE_MEDIA_KR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASELR] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASESR] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR2] = BNGE_MEDIA_KR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKX] = BNGE_MEDIA_KX, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR] = BNGE_MEDIA_KR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASET] = BNGE_MEDIA_TP, + [PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE] = BNGE_MEDIA_TP, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR4] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR4] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR4] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER4] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR10] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR4] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4] = BNGE_MEDIA_CR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4] = BNGE_MEDIA_SR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4] = BNGE_MEDIA_LR_ER_FR, + [PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4] = BNGE_MEDIA_LR_ER_FR, +}; + +u32 bnge_fw_to_ethtool_speed(u16 fw_link_speed) +{ + switch (fw_link_speed) { + case BNGE_LINK_SPEED_50GB: + case BNGE_LINK_SPEED_50GB_PAM4: + return SPEED_50000; + case BNGE_LINK_SPEED_100GB: + case BNGE_LINK_SPEED_100GB_PAM4: + case BNGE_LINK_SPEED_100GB_PAM4_112: + return SPEED_100000; + case BNGE_LINK_SPEED_200GB: + case BNGE_LINK_SPEED_200GB_PAM4: + case BNGE_LINK_SPEED_200GB_PAM4_112: + return SPEED_200000; + case BNGE_LINK_SPEED_400GB: + case BNGE_LINK_SPEED_400GB_PAM4: + case BNGE_LINK_SPEED_400GB_PAM4_112: + return SPEED_400000; + case BNGE_LINK_SPEED_800GB: + case BNGE_LINK_SPEED_800GB_PAM4_112: + return SPEED_800000; + default: + return SPEED_UNKNOWN; + } +} + +bool bnge_phy_qcaps_no_speed(struct hwrm_port_phy_qcaps_output *resp) +{ + if (!resp->supported_speeds_auto_mode && + !resp->supported_speeds_force_mode && + !resp->supported_pam4_speeds_auto_mode && + !resp->supported_pam4_speeds_force_mode && + !resp->supported_speeds2_auto_mode && + !resp->supported_speeds2_force_mode) + return true; + return false; +} + +static void bnge_set_auto_speed(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + elink_info->advertising = link_info->auto_link_speeds2; + return; + } + elink_info->advertising = link_info->auto_link_speeds; + elink_info->advertising_pam4 = link_info->auto_pam4_link_speeds; +} + +static void bnge_set_force_speed(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + elink_info->req_link_speed = link_info->force_link_speed2; + elink_info->req_signal_mode = BNGE_SIG_MODE_NRZ; + switch (elink_info->req_link_speed) { + case BNGE_LINK_SPEED_50GB_PAM4: + case BNGE_LINK_SPEED_100GB_PAM4: + case BNGE_LINK_SPEED_200GB_PAM4: + case BNGE_LINK_SPEED_400GB_PAM4: + elink_info->req_signal_mode = BNGE_SIG_MODE_PAM4; + break; + case BNGE_LINK_SPEED_100GB_PAM4_112: + case BNGE_LINK_SPEED_200GB_PAM4_112: + case BNGE_LINK_SPEED_400GB_PAM4_112: + case BNGE_LINK_SPEED_800GB_PAM4_112: + elink_info->req_signal_mode = BNGE_SIG_MODE_PAM4_112; + break; + default: + elink_info->req_signal_mode = BNGE_SIG_MODE_NRZ; + } + return; + } + elink_info->req_link_speed = link_info->force_link_speed; + elink_info->req_signal_mode = BNGE_SIG_MODE_NRZ; + if (link_info->force_pam4_link_speed) { + elink_info->req_link_speed = link_info->force_pam4_link_speed; + elink_info->req_signal_mode = BNGE_SIG_MODE_PAM4; + } +} + +void bnge_init_ethtool_link_settings(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + + if (BNGE_AUTO_MODE(link_info->auto_mode)) { + elink_info->autoneg = BNGE_AUTONEG_SPEED; + if (link_info->auto_pause_setting & + PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE) + elink_info->autoneg |= BNGE_AUTONEG_FLOW_CTRL; + bnge_set_auto_speed(bn); + } else { + bnge_set_force_speed(bn); + elink_info->req_duplex = link_info->duplex_setting; + } + if (elink_info->autoneg & BNGE_AUTONEG_FLOW_CTRL) + elink_info->req_flow_ctrl = + link_info->auto_pause_setting & BNGE_LINK_PAUSE_BOTH; + else + elink_info->req_flow_ctrl = link_info->force_pause_setting; +} + +int bnge_probe_phy(struct bnge_net *bn, bool fw_dflt) +{ + struct bnge_dev *bd = bn->bd; + int rc = 0; + + bd->phy_flags = 0; + rc = bnge_hwrm_phy_qcaps(bd); + if (rc) { + netdev_err(bd->netdev, + "Probe phy can't get phy qcaps (rc: %d)\n", rc); + return rc; + } + if (bd->phy_flags & BNGE_PHY_FL_NO_FCS) + bd->netdev->priv_flags |= IFF_SUPP_NOFCS; + else + bd->netdev->priv_flags &= ~IFF_SUPP_NOFCS; + if (!fw_dflt) + return 0; + + mutex_lock(&bd->link_lock); + rc = bnge_update_link(bn, false); + if (rc) { + mutex_unlock(&bd->link_lock); + netdev_err(bd->netdev, "Probe phy can't update link (rc: %d)\n", + rc); + return rc; + } + + bnge_init_ethtool_link_settings(bn); + mutex_unlock(&bd->link_lock); + return 0; +} + +void bnge_hwrm_set_link_common(struct bnge_net *bn, + struct hwrm_port_phy_cfg_input *req) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + + if (elink_info->autoneg & BNGE_AUTONEG_SPEED) { + req->auto_mode |= PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK; + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + req->enables |= cpu_to_le32(BNGE_PHY_AUTO_SPEEDS2_MASK); + req->auto_link_speeds2_mask = + cpu_to_le16(elink_info->advertising); + } else if (elink_info->advertising) { + req->enables |= cpu_to_le32(BNGE_PHY_AUTO_SPEED_MASK); + req->auto_link_speed_mask = + cpu_to_le16(elink_info->advertising); + } + if (elink_info->advertising_pam4) { + req->enables |= + cpu_to_le32(BNGE_PHY_AUTO_PAM4_SPEED_MASK); + req->auto_link_pam4_speed_mask = + cpu_to_le16(elink_info->advertising_pam4); + } + req->enables |= cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE); + req->flags |= cpu_to_le32(BNGE_PHY_FLAGS_RESTART_AUTO); + } else { + req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_FORCE); + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + req->force_link_speeds2 = + cpu_to_le16(elink_info->req_link_speed); + req->enables |= + cpu_to_le32(BNGE_PHY_FLAGS_ENA_FORCE_SPEEDS2); + netif_info(bd, link, bd->netdev, + "Forcing FW speed2: %d\n", + (u32)elink_info->req_link_speed); + } else if (elink_info->req_signal_mode == BNGE_SIG_MODE_PAM4) { + req->force_pam4_link_speed = + cpu_to_le16(elink_info->req_link_speed); + req->enables |= + cpu_to_le32(BNGE_PHY_FLAGS_ENA_FORCE_PM4_SPEED); + } else { + req->force_link_speed = + cpu_to_le16(elink_info->req_link_speed); + } + } + + /* tell FW that the setting takes effect immediately */ + req->flags |= cpu_to_le32(PORT_PHY_CFG_REQ_FLAGS_RESET_PHY); +} + +static bool bnge_auto_speed_updated(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + if (elink_info->advertising != link_info->auto_link_speeds2) + return true; + return false; + } + if (elink_info->advertising != link_info->auto_link_speeds || + elink_info->advertising_pam4 != link_info->auto_pam4_link_speeds) + return true; + return false; +} + +void bnge_hwrm_set_pause_common(struct bnge_net *bn, + struct hwrm_port_phy_cfg_input *req) +{ + if (bn->eth_link_info.autoneg & BNGE_AUTONEG_FLOW_CTRL) { + req->auto_pause = PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE; + if (bn->eth_link_info.req_flow_ctrl & BNGE_LINK_PAUSE_RX) + req->auto_pause |= PORT_PHY_CFG_REQ_AUTO_PAUSE_RX; + if (bn->eth_link_info.req_flow_ctrl & BNGE_LINK_PAUSE_TX) + req->auto_pause |= PORT_PHY_CFG_REQ_AUTO_PAUSE_TX; + req->enables |= + cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE); + } else { + if (bn->eth_link_info.req_flow_ctrl & BNGE_LINK_PAUSE_RX) + req->force_pause |= PORT_PHY_CFG_REQ_FORCE_PAUSE_RX; + if (bn->eth_link_info.req_flow_ctrl & BNGE_LINK_PAUSE_TX) + req->force_pause |= PORT_PHY_CFG_REQ_FORCE_PAUSE_TX; + req->enables |= + cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE); + req->auto_pause = req->force_pause; + req->enables |= + cpu_to_le32(PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE); + } +} + +static bool bnge_force_speed_updated(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + if (elink_info->req_link_speed != link_info->force_link_speed2) + return true; + return false; + } + if (elink_info->req_signal_mode == BNGE_SIG_MODE_NRZ && + elink_info->req_link_speed != link_info->force_link_speed) + return true; + if (elink_info->req_signal_mode == BNGE_SIG_MODE_PAM4 && + elink_info->req_link_speed != link_info->force_pam4_link_speed) + return true; + return false; +} + +int bnge_update_phy_setting(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info; + struct bnge_link_info *link_info; + struct bnge_dev *bd = bn->bd; + bool update_pause = false; + bool update_link = false; + int rc; + + link_info = &bd->link_info; + elink_info = &bn->eth_link_info; + rc = bnge_update_link(bn, true); + if (rc) { + netdev_err(bd->netdev, "failed to update link (rc: %d)\n", + rc); + return rc; + } + if (!BNGE_SINGLE_PF(bd)) + return 0; + + if ((elink_info->autoneg & BNGE_AUTONEG_FLOW_CTRL) && + (link_info->auto_pause_setting & BNGE_LINK_PAUSE_BOTH) != + elink_info->req_flow_ctrl) + update_pause = true; + if (!(elink_info->autoneg & BNGE_AUTONEG_FLOW_CTRL) && + link_info->force_pause_setting != elink_info->req_flow_ctrl) + update_pause = true; + if (!(elink_info->autoneg & BNGE_AUTONEG_SPEED)) { + if (BNGE_AUTO_MODE(link_info->auto_mode)) + update_link = true; + if (bnge_force_speed_updated(bn)) + update_link = true; + if (elink_info->req_duplex != link_info->duplex_setting) + update_link = true; + } else { + if (link_info->auto_mode == BNGE_LINK_AUTO_NONE) + update_link = true; + if (bnge_auto_speed_updated(bn)) + update_link = true; + } + + /* The last close may have shutdown the link, so need to call + * PHY_CFG to bring it back up. + */ + if (!BNGE_LINK_IS_UP(bd)) + update_link = true; + + if (update_link) + rc = bnge_hwrm_set_link_setting(bn, update_pause); + else if (update_pause) + rc = bnge_hwrm_set_pause(bn); + if (rc) { + netdev_err(bd->netdev, + "failed to update phy setting (rc: %d)\n", rc); + return rc; + } + + return rc; +} + +void bnge_get_port_module_status(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + struct hwrm_port_phy_qcfg_output *resp = &link_info->phy_qcfg_resp; + u8 module_status; + + if (bnge_update_link(bn, true)) + return; + + module_status = link_info->module_status; + switch (module_status) { + case PORT_PHY_QCFG_RESP_MODULE_STATUS_DISABLETX: + case PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN: + case PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG: + netdev_warn(bd->netdev, + "Unqualified SFP+ module detected on port %d\n", + bd->pf.port_id); + netdev_warn(bd->netdev, "Module part number %s\n", + resp->phy_vendor_partnumber); + if (module_status == PORT_PHY_QCFG_RESP_MODULE_STATUS_DISABLETX) + netdev_warn(bd->netdev, "TX is disabled\n"); + if (module_status == PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN) + netdev_warn(bd->netdev, "SFP+ module is shutdown\n"); + } +} + +static bool bnge_support_dropped(u16 advertising, u16 supported) +{ + u16 diff = advertising ^ supported; + + return ((supported | diff) != supported); +} + +bool bnge_support_speed_dropped(struct bnge_net *bn) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + + /* Check if any advertised speeds are no longer supported. The caller + * holds the link_lock mutex, so we can modify link_info settings. + */ + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + if (bnge_support_dropped(elink_info->advertising, + link_info->support_auto_speeds2)) { + elink_info->advertising = + link_info->support_auto_speeds2; + return true; + } + return false; + } + if (bnge_support_dropped(elink_info->advertising, + link_info->support_auto_speeds)) { + elink_info->advertising = link_info->support_auto_speeds; + return true; + } + if (bnge_support_dropped(elink_info->advertising_pam4, + link_info->support_pam4_auto_speeds)) { + elink_info->advertising_pam4 = + link_info->support_pam4_auto_speeds; + return true; + } + return false; +} + +static char *bnge_report_fec(struct bnge_link_info *link_info) +{ + u8 active_fec = link_info->active_fec_sig_mode & + PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK; + + switch (active_fec) { + default: + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE: + return "None"; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE: + return "Clause 74 BaseR"; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE: + return "Clause 91 RS(528,514)"; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE: + return "Clause 91 RS544_1XN"; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE: + return "Clause 91 RS(544,514)"; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE: + return "Clause 91 RS272_1XN"; + case PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE: + return "Clause 91 RS(272,257)"; + } +} + +void bnge_report_link(struct bnge_dev *bd) +{ + if (BNGE_LINK_IS_UP(bd)) { + const char *signal = ""; + const char *flow_ctrl; + const char *duplex; + u32 speed; + u16 fec; + + netif_carrier_on(bd->netdev); + speed = bnge_fw_to_ethtool_speed(bd->link_info.link_speed); + if (speed == SPEED_UNKNOWN) { + netdev_info(bd->netdev, + "NIC Link is Up, speed unknown\n"); + return; + } + if (bd->link_info.duplex == BNGE_LINK_DUPLEX_FULL) + duplex = "full"; + else + duplex = "half"; + if (bd->link_info.pause == BNGE_LINK_PAUSE_BOTH) + flow_ctrl = "ON - receive & transmit"; + else if (bd->link_info.pause == BNGE_LINK_PAUSE_TX) + flow_ctrl = "ON - transmit"; + else if (bd->link_info.pause == BNGE_LINK_PAUSE_RX) + flow_ctrl = "ON - receive"; + else + flow_ctrl = "none"; + if (bd->link_info.phy_qcfg_resp.option_flags & + PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN) { + u8 sig_mode = bd->link_info.active_fec_sig_mode & + PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK; + switch (sig_mode) { + case PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ: + signal = "(NRZ) "; + break; + case PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4: + signal = "(PAM4 56Gbps) "; + break; + case PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112: + signal = "(PAM4 112Gbps) "; + break; + default: + break; + } + } + netdev_info(bd->netdev, "NIC Link is Up, %u Mbps %s%s duplex, Flow control: %s\n", + speed, signal, duplex, flow_ctrl); + fec = bd->link_info.fec_cfg; + if (!(fec & PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED)) + netdev_info(bd->netdev, "FEC autoneg %s encoding: %s\n", + (fec & BNGE_FEC_AUTONEG) ? "on" : "off", + bnge_report_fec(&bd->link_info)); + } else { + netif_carrier_off(bd->netdev); + netdev_err(bd->netdev, "NIC Link is Down\n"); + } +} + +static void bnge_get_ethtool_modes(struct bnge_net *bn, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnge_dev *bd = bn->bd; + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_link_info *link_info = &bd->link_info; + + if (!(bd->phy_flags & BNGE_PHY_FL_NO_PAUSE)) { + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + lk_ksettings->link_modes.supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + lk_ksettings->link_modes.supported); + } + + if (link_info->support_auto_speeds || link_info->support_auto_speeds2 || + link_info->support_pam4_auto_speeds) + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lk_ksettings->link_modes.supported); + + if (~elink_info->autoneg & BNGE_AUTONEG_FLOW_CTRL) + return; + + if (link_info->auto_pause_setting & BNGE_LINK_PAUSE_RX) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + lk_ksettings->link_modes.advertising); + if (hweight8(link_info->auto_pause_setting & BNGE_LINK_PAUSE_BOTH) == 1) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + lk_ksettings->link_modes.advertising); + if (link_info->lp_pause & BNGE_LINK_PAUSE_RX) + linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, + lk_ksettings->link_modes.lp_advertising); + if (hweight8(link_info->lp_pause & BNGE_LINK_PAUSE_BOTH) == 1) + linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, + lk_ksettings->link_modes.lp_advertising); +} + +u32 bnge_get_link(struct net_device *dev) +{ + struct bnge_net *bn = netdev_priv(dev); + + /* TODO: handle MF, VF, driver close case */ + return BNGE_LINK_IS_UP(bn->bd); +} + +static enum bnge_media_type +bnge_get_media(struct bnge_link_info *link_info) +{ + switch (link_info->media_type) { + case PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP: + return BNGE_MEDIA_TP; + case PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC: + return BNGE_MEDIA_CR; + default: + if (link_info->phy_type < ARRAY_SIZE(bnge_phy_types)) + return bnge_phy_types[link_info->phy_type]; + return BNGE_MEDIA_UNKNOWN; + } +} + +enum bnge_link_speed_indices { + BNGE_LINK_SPEED_UNKNOWN = 0, + BNGE_LINK_SPEED_50GB_IDX, + BNGE_LINK_SPEED_100GB_IDX, + BNGE_LINK_SPEED_200GB_IDX, + BNGE_LINK_SPEED_400GB_IDX, + BNGE_LINK_SPEED_800GB_IDX, + __BNGE_LINK_SPEED_END +}; + +static enum bnge_link_speed_indices bnge_fw_speed_idx(u16 speed) +{ + switch (speed) { + case BNGE_LINK_SPEED_50GB: + case BNGE_LINK_SPEED_50GB_PAM4: + return BNGE_LINK_SPEED_50GB_IDX; + case BNGE_LINK_SPEED_100GB: + case BNGE_LINK_SPEED_100GB_PAM4: + case BNGE_LINK_SPEED_100GB_PAM4_112: + return BNGE_LINK_SPEED_100GB_IDX; + case BNGE_LINK_SPEED_200GB: + case BNGE_LINK_SPEED_200GB_PAM4: + case BNGE_LINK_SPEED_200GB_PAM4_112: + return BNGE_LINK_SPEED_200GB_IDX; + case BNGE_LINK_SPEED_400GB: + case BNGE_LINK_SPEED_400GB_PAM4: + case BNGE_LINK_SPEED_400GB_PAM4_112: + return BNGE_LINK_SPEED_400GB_IDX; + case BNGE_LINK_SPEED_800GB: + case BNGE_LINK_SPEED_800GB_PAM4_112: + return BNGE_LINK_SPEED_800GB_IDX; + default: return BNGE_LINK_SPEED_UNKNOWN; + } +} + +static const enum ethtool_link_mode_bit_indices +bnge_link_modes[__BNGE_LINK_SPEED_END][BNGE_SIG_MODE_MAX][__BNGE_MEDIA_END] = { + [BNGE_LINK_SPEED_50GB_IDX] = { + [BNGE_SIG_MODE_PAM4] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + }, + }, + [BNGE_LINK_SPEED_100GB_IDX] = { + [BNGE_SIG_MODE_NRZ] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, + }, + [BNGE_SIG_MODE_PAM4] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, + }, + [BNGE_SIG_MODE_PAM4_112] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_100000baseCR_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_100000baseSR_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_100000baseKR_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT, + }, + }, + [BNGE_LINK_SPEED_200GB_IDX] = { + [BNGE_SIG_MODE_PAM4] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, + }, + [BNGE_SIG_MODE_PAM4_112] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT, + }, + }, + [BNGE_LINK_SPEED_400GB_IDX] = { + [BNGE_SIG_MODE_PAM4] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT, + }, + [BNGE_SIG_MODE_PAM4_112] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT, + [BNGE_MEDIA_LR_ER_FR] = ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT, + }, + }, + [BNGE_LINK_SPEED_800GB_IDX] = { + [BNGE_SIG_MODE_PAM4_112] = { + [BNGE_MEDIA_CR] = ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT, + [BNGE_MEDIA_KR] = ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT, + [BNGE_MEDIA_SR] = ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT, + }, + }, +}; + +#define BNGE_LINK_MODE_UNKNOWN -1 + +static enum ethtool_link_mode_bit_indices +bnge_get_link_mode(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_link_info *link_info = &bd->link_info; + enum ethtool_link_mode_bit_indices link_mode; + enum bnge_link_speed_indices speed; + enum bnge_media_type media; + u8 sig_mode; + + if (link_info->phy_link_status != BNGE_LINK_LINK) + return BNGE_LINK_MODE_UNKNOWN; + + media = bnge_get_media(link_info); + if (BNGE_AUTO_MODE(link_info->auto_mode)) { + speed = bnge_fw_speed_idx(link_info->link_speed); + sig_mode = link_info->active_fec_sig_mode & + PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK; + } else { + speed = bnge_fw_speed_idx(elink_info->req_link_speed); + sig_mode = elink_info->req_signal_mode; + } + if (sig_mode >= BNGE_SIG_MODE_MAX) + return BNGE_LINK_MODE_UNKNOWN; + + /* Note ETHTOOL_LINK_MODE_10baseT_Half_BIT == 0 is a legal Linux + * link mode, but since no such devices exist, the zeroes in the + * map can be conveniently used to represent unknown link modes. + */ + link_mode = bnge_link_modes[speed][sig_mode][media]; + if (!link_mode) + return BNGE_LINK_MODE_UNKNOWN; + + switch (link_mode) { + case ETHTOOL_LINK_MODE_100baseT_Full_BIT: + if (~link_info->duplex & BNGE_LINK_DUPLEX_FULL) + link_mode = ETHTOOL_LINK_MODE_100baseT_Half_BIT; + break; + case ETHTOOL_LINK_MODE_1000baseT_Full_BIT: + if (~link_info->duplex & BNGE_LINK_DUPLEX_FULL) + link_mode = ETHTOOL_LINK_MODE_1000baseT_Half_BIT; + break; + default: + break; + } + + return link_mode; +} + +static const u16 bnge_nrz_speed_masks[] = { + [BNGE_LINK_SPEED_100GB_IDX] = BNGE_LINK_SPEED_MSK_100GB, + [__BNGE_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */ +}; + +static const u16 bnge_pam4_speed_masks[] = { + [BNGE_LINK_SPEED_50GB_IDX] = BNGE_LINK_PAM4_SPEED_MSK_50GB, + [BNGE_LINK_SPEED_100GB_IDX] = BNGE_LINK_PAM4_SPEED_MSK_100GB, + [BNGE_LINK_SPEED_200GB_IDX] = BNGE_LINK_PAM4_SPEED_MSK_200GB, + [__BNGE_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */ +}; + +static const u16 bnge_nrz_speeds2_masks[] = { + [BNGE_LINK_SPEED_100GB_IDX] = BNGE_LINK_SPEEDS2_MSK_100GB, + [__BNGE_LINK_SPEED_END - 1] = 0 /* make any legal speed a valid index */ +}; + +static const u16 bnge_pam4_speeds2_masks[] = { + [BNGE_LINK_SPEED_50GB_IDX] = BNGE_LINK_SPEEDS2_MSK_50GB_PAM4, + [BNGE_LINK_SPEED_100GB_IDX] = BNGE_LINK_SPEEDS2_MSK_100GB_PAM4, + [BNGE_LINK_SPEED_200GB_IDX] = BNGE_LINK_SPEEDS2_MSK_200GB_PAM4, + [BNGE_LINK_SPEED_400GB_IDX] = BNGE_LINK_SPEEDS2_MSK_400GB_PAM4, +}; + +static const u16 bnge_pam4_112_speeds2_masks[] = { + [BNGE_LINK_SPEED_100GB_IDX] = BNGE_LINK_SPEEDS2_MSK_100GB_PAM4_112, + [BNGE_LINK_SPEED_200GB_IDX] = BNGE_LINK_SPEEDS2_MSK_200GB_PAM4_112, + [BNGE_LINK_SPEED_400GB_IDX] = BNGE_LINK_SPEEDS2_MSK_400GB_PAM4_112, + [BNGE_LINK_SPEED_800GB_IDX] = BNGE_LINK_SPEEDS2_MSK_800GB_PAM4_112, +}; + +static enum bnge_link_speed_indices +bnge_encoding_speed_idx(u8 sig_mode, u16 phy_flags, u16 speed_msk) +{ + const u16 *speeds; + int idx, len; + + switch (sig_mode) { + case BNGE_SIG_MODE_NRZ: + if (phy_flags & BNGE_PHY_FL_SPEEDS2) { + speeds = bnge_nrz_speeds2_masks; + len = ARRAY_SIZE(bnge_nrz_speeds2_masks); + } else { + speeds = bnge_nrz_speed_masks; + len = ARRAY_SIZE(bnge_nrz_speed_masks); + } + break; + case BNGE_SIG_MODE_PAM4: + if (phy_flags & BNGE_PHY_FL_SPEEDS2) { + speeds = bnge_pam4_speeds2_masks; + len = ARRAY_SIZE(bnge_pam4_speeds2_masks); + } else { + speeds = bnge_pam4_speed_masks; + len = ARRAY_SIZE(bnge_pam4_speed_masks); + } + break; + case BNGE_SIG_MODE_PAM4_112: + speeds = bnge_pam4_112_speeds2_masks; + len = ARRAY_SIZE(bnge_pam4_112_speeds2_masks); + break; + default: + return BNGE_LINK_SPEED_UNKNOWN; + } + + for (idx = 0; idx < len; idx++) { + if (speeds[idx] == speed_msk) + return idx; + } + + return BNGE_LINK_SPEED_UNKNOWN; +} + +#define BNGE_FW_SPEED_MSK_BITS 16 + +static void +__bnge_get_ethtool_speeds(unsigned long fw_mask, enum bnge_media_type media, + u8 sig_mode, u16 phy_flags, unsigned long *et_mask) +{ + enum ethtool_link_mode_bit_indices link_mode; + enum bnge_link_speed_indices speed; + u8 bit; + + for_each_set_bit(bit, &fw_mask, BNGE_FW_SPEED_MSK_BITS) { + speed = bnge_encoding_speed_idx(sig_mode, phy_flags, 1 << bit); + if (!speed) + continue; + + link_mode = bnge_link_modes[speed][sig_mode][media]; + if (!link_mode) + continue; + + linkmode_set_bit(link_mode, et_mask); + } +} + +static void +bnge_get_ethtool_speeds(unsigned long fw_mask, enum bnge_media_type media, + u8 sig_mode, u16 phy_flags, unsigned long *et_mask) +{ + if (media) { + __bnge_get_ethtool_speeds(fw_mask, media, sig_mode, phy_flags, + et_mask); + return; + } + + /* list speeds for all media if unknown */ + for (media = 1; media < __BNGE_MEDIA_END; media++) + __bnge_get_ethtool_speeds(fw_mask, media, sig_mode, phy_flags, + et_mask); +} + +static void +bnge_get_all_ethtool_support_speeds(struct bnge_dev *bd, + enum bnge_media_type media, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnge_link_info *link_info = &bd->link_info; + u16 sp_nrz, sp_pam4, sp_pam4_112 = 0; + u16 phy_flags = bd->phy_flags; + + if (phy_flags & BNGE_PHY_FL_SPEEDS2) { + sp_nrz = link_info->support_speeds2; + sp_pam4 = link_info->support_speeds2; + sp_pam4_112 = link_info->support_speeds2; + } else { + sp_nrz = link_info->support_speeds; + sp_pam4 = link_info->support_pam4_speeds; + } + bnge_get_ethtool_speeds(sp_nrz, media, BNGE_SIG_MODE_NRZ, phy_flags, + lk_ksettings->link_modes.supported); + bnge_get_ethtool_speeds(sp_pam4, media, BNGE_SIG_MODE_PAM4, phy_flags, + lk_ksettings->link_modes.supported); + bnge_get_ethtool_speeds(sp_pam4_112, media, BNGE_SIG_MODE_PAM4_112, + phy_flags, lk_ksettings->link_modes.supported); +} + +static void +bnge_get_all_ethtool_adv_speeds(struct bnge_net *bn, + enum bnge_media_type media, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnge_dev *bd = bn->bd; + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + u16 sp_nrz, sp_pam4, sp_pam4_112 = 0; + u16 phy_flags = bd->phy_flags; + + sp_nrz = elink_info->advertising; + if (phy_flags & BNGE_PHY_FL_SPEEDS2) { + sp_pam4 = elink_info->advertising; + sp_pam4_112 = elink_info->advertising; + } else { + sp_pam4 = elink_info->advertising_pam4; + } + bnge_get_ethtool_speeds(sp_nrz, media, BNGE_SIG_MODE_NRZ, phy_flags, + lk_ksettings->link_modes.advertising); + bnge_get_ethtool_speeds(sp_pam4, media, BNGE_SIG_MODE_PAM4, phy_flags, + lk_ksettings->link_modes.advertising); + bnge_get_ethtool_speeds(sp_pam4_112, media, BNGE_SIG_MODE_PAM4_112, + phy_flags, lk_ksettings->link_modes.advertising); +} + +static void +bnge_get_all_ethtool_lp_speeds(struct bnge_dev *bd, + enum bnge_media_type media, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnge_link_info *link_info = &bd->link_info; + u16 phy_flags = bd->phy_flags; + + bnge_get_ethtool_speeds(link_info->lp_auto_link_speeds, media, + BNGE_SIG_MODE_NRZ, phy_flags, + lk_ksettings->link_modes.lp_advertising); + bnge_get_ethtool_speeds(link_info->lp_auto_pam4_link_speeds, media, + BNGE_SIG_MODE_PAM4, phy_flags, + lk_ksettings->link_modes.lp_advertising); +} + +static void bnge_update_speed(u32 *delta, bool installed_media, u16 *speeds, + u16 speed_msk, const unsigned long *et_mask, + enum ethtool_link_mode_bit_indices mode) +{ + bool mode_desired = linkmode_test_bit(mode, et_mask); + + if (!mode) + return; + + /* enabled speeds for installed media should override */ + if (installed_media && mode_desired) { + *speeds |= speed_msk; + *delta |= speed_msk; + return; + } + + /* many to one mapping, only allow one change per fw_speed bit */ + if (!(*delta & speed_msk) && (mode_desired == !(*speeds & speed_msk))) { + *speeds ^= speed_msk; + *delta |= speed_msk; + } +} + +static void bnge_set_ethtool_speeds(struct bnge_net *bn, + const unsigned long *et_mask) +{ + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + u16 const *sp_msks, *sp_pam4_msks, *sp_pam4_112_msks; + struct bnge_dev *bd = bn->bd; + struct bnge_link_info *link_info = &bd->link_info; + enum bnge_media_type media = bnge_get_media(link_info); + u16 *adv, *adv_pam4, *adv_pam4_112 = NULL; + u32 delta_pam4_112 = 0; + u32 delta_pam4 = 0; + u32 delta_nrz = 0; + int i, m; + + adv = &elink_info->advertising; + if (bd->phy_flags & BNGE_PHY_FL_SPEEDS2) { + adv_pam4 = &elink_info->advertising; + adv_pam4_112 = &elink_info->advertising; + sp_msks = bnge_nrz_speeds2_masks; + sp_pam4_msks = bnge_pam4_speeds2_masks; + sp_pam4_112_msks = bnge_pam4_112_speeds2_masks; + } else { + adv_pam4 = &elink_info->advertising_pam4; + sp_msks = bnge_nrz_speed_masks; + sp_pam4_msks = bnge_pam4_speed_masks; + } + for (i = 1; i < __BNGE_LINK_SPEED_END; i++) { + /* accept any legal media from user */ + for (m = 1; m < __BNGE_MEDIA_END; m++) { + bnge_update_speed(&delta_nrz, m == media, + adv, sp_msks[i], et_mask, + bnge_link_modes[i][BNGE_SIG_MODE_NRZ][m]); + bnge_update_speed(&delta_pam4, m == media, + adv_pam4, sp_pam4_msks[i], et_mask, + bnge_link_modes[i][BNGE_SIG_MODE_PAM4][m]); + if (!adv_pam4_112) + continue; + + bnge_update_speed(&delta_pam4_112, m == media, + adv_pam4_112, sp_pam4_112_msks[i], et_mask, + bnge_link_modes[i][BNGE_SIG_MODE_PAM4_112][m]); + } + } +} + +static void +bnge_fw_to_ethtool_advertised_fec(struct bnge_link_info *link_info, + struct ethtool_link_ksettings *lk_ksettings) +{ + u16 fec_cfg = link_info->fec_cfg; + + if ((fec_cfg & BNGE_FEC_NONE) || !(fec_cfg & BNGE_FEC_AUTONEG)) { + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, + lk_ksettings->link_modes.advertising); + return; + } + if (fec_cfg & BNGE_FEC_ENC_BASE_R) + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, + lk_ksettings->link_modes.advertising); + if (fec_cfg & BNGE_FEC_ENC_RS) + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, + lk_ksettings->link_modes.advertising); + if (fec_cfg & BNGE_FEC_ENC_LLRS) + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, + lk_ksettings->link_modes.advertising); +} + +static void +bnge_fw_to_ethtool_support_fec(struct bnge_link_info *link_info, + struct ethtool_link_ksettings *lk_ksettings) +{ + u16 fec_cfg = link_info->fec_cfg; + + if (fec_cfg & BNGE_FEC_NONE) { + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_NONE_BIT, + lk_ksettings->link_modes.supported); + return; + } + if (fec_cfg & BNGE_FEC_ENC_BASE_R_CAP) + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_BASER_BIT, + lk_ksettings->link_modes.supported); + if (fec_cfg & BNGE_FEC_ENC_RS_CAP) + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_RS_BIT, + lk_ksettings->link_modes.supported); + if (fec_cfg & BNGE_FEC_ENC_LLRS_CAP) + linkmode_set_bit(ETHTOOL_LINK_MODE_FEC_LLRS_BIT, + lk_ksettings->link_modes.supported); +} + +static void bnge_get_default_speeds(struct bnge_net *bn, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnge_dev *bd = bn->bd; + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct ethtool_link_settings *base = &lk_ksettings->base; + struct bnge_link_info *link_info = &bd->link_info; + + if (link_info->link_state == BNGE_LINK_STATE_UP) { + base->speed = bnge_fw_to_ethtool_speed(link_info->link_speed); + base->duplex = DUPLEX_HALF; + if (link_info->duplex & BNGE_LINK_DUPLEX_FULL) + base->duplex = DUPLEX_FULL; + lk_ksettings->lanes = link_info->active_lanes; + } else if (!elink_info->autoneg) { + base->speed = bnge_fw_to_ethtool_speed(elink_info->req_link_speed); + base->duplex = DUPLEX_HALF; + if (elink_info->req_duplex == BNGE_LINK_DUPLEX_FULL) + base->duplex = DUPLEX_FULL; + } +} + +int bnge_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *lk_ksettings) +{ + struct bnge_net *bn = netdev_priv(dev); + struct ethtool_link_settings *base = &lk_ksettings->base; + enum ethtool_link_mode_bit_indices link_mode; + struct bnge_link_info *link_info; + struct bnge_dev *bd = bn->bd; + enum bnge_media_type media; + + ethtool_link_ksettings_zero_link_mode(lk_ksettings, lp_advertising); + ethtool_link_ksettings_zero_link_mode(lk_ksettings, advertising); + ethtool_link_ksettings_zero_link_mode(lk_ksettings, supported); + base->duplex = DUPLEX_UNKNOWN; + base->speed = SPEED_UNKNOWN; + link_info = &bd->link_info; + + mutex_lock(&bd->link_lock); + bnge_get_ethtool_modes(bn, lk_ksettings); + media = bnge_get_media(link_info); + bnge_get_all_ethtool_support_speeds(bd, media, lk_ksettings); + bnge_fw_to_ethtool_support_fec(link_info, lk_ksettings); + link_mode = bnge_get_link_mode(bn); + if (link_mode != BNGE_LINK_MODE_UNKNOWN) + ethtool_params_from_link_mode(lk_ksettings, link_mode); + else + bnge_get_default_speeds(bn, lk_ksettings); + + if (bn->eth_link_info.autoneg) { + bnge_fw_to_ethtool_advertised_fec(link_info, lk_ksettings); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, + lk_ksettings->link_modes.advertising); + base->autoneg = AUTONEG_ENABLE; + bnge_get_all_ethtool_adv_speeds(bn, media, lk_ksettings); + if (link_info->phy_link_status == BNGE_LINK_LINK) + bnge_get_all_ethtool_lp_speeds(bd, media, lk_ksettings); + } else { + base->autoneg = AUTONEG_DISABLE; + } + + base->port = PORT_NONE; + if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) { + base->port = PORT_TP; + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, + lk_ksettings->link_modes.supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_TP_BIT, + lk_ksettings->link_modes.advertising); + } else { + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + lk_ksettings->link_modes.supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, + lk_ksettings->link_modes.advertising); + + if (link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC) + base->port = PORT_DA; + else + base->port = PORT_FIBRE; + } + base->phy_address = link_info->phy_addr; + mutex_unlock(&bd->link_lock); + + return 0; +} + +static int +bnge_force_link_speed(struct net_device *dev, u32 ethtool_speed, u32 lanes) +{ + struct bnge_net *bn = netdev_priv(dev); + struct bnge_dev *bd = bn->bd; + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_link_info *link_info = &bd->link_info; + u16 support_pam4_spds = link_info->support_pam4_speeds; + u16 support_spds2 = link_info->support_speeds2; + u16 support_spds = link_info->support_speeds; + u8 sig_mode = BNGE_SIG_MODE_NRZ; + u32 lanes_needed = 1; + u16 fw_speed = 0; + + switch (ethtool_speed) { + case SPEED_50000: + if (((support_spds & BNGE_LINK_SPEED_MSK_50GB) || + (support_spds2 & BNGE_LINK_SPEEDS2_MSK_50GB)) && + lanes != 1) { + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB; + lanes_needed = 2; + } else if (support_pam4_spds & BNGE_LINK_PAM4_SPEED_MSK_50GB) { + fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB; + sig_mode = BNGE_SIG_MODE_PAM4; + } else if (support_spds2 & BNGE_LINK_SPEEDS2_MSK_50GB_PAM4) { + fw_speed = BNGE_LINK_SPEED_50GB_PAM4; + sig_mode = BNGE_SIG_MODE_PAM4; + } + break; + case SPEED_100000: + if (((support_spds & BNGE_LINK_SPEED_MSK_100GB) || + (support_spds2 & BNGE_LINK_SPEEDS2_MSK_100GB)) && + lanes != 2 && lanes != 1) { + fw_speed = PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB; + lanes_needed = 4; + } else if (support_pam4_spds & BNGE_LINK_PAM4_SPEED_MSK_100GB) { + fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB; + sig_mode = BNGE_SIG_MODE_PAM4; + lanes_needed = 2; + } else if ((support_spds2 & BNGE_LINK_SPEEDS2_MSK_100GB_PAM4) && + lanes != 1) { + fw_speed = BNGE_LINK_SPEED_100GB_PAM4; + sig_mode = BNGE_SIG_MODE_PAM4; + lanes_needed = 2; + } else if (support_spds2 & BNGE_LINK_SPEEDS2_MSK_100GB_PAM4_112) { + fw_speed = BNGE_LINK_SPEED_100GB_PAM4_112; + sig_mode = BNGE_SIG_MODE_PAM4_112; + } + break; + case SPEED_200000: + if (support_pam4_spds & BNGE_LINK_PAM4_SPEED_MSK_200GB) { + fw_speed = PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB; + sig_mode = BNGE_SIG_MODE_PAM4; + lanes_needed = 4; + } else if ((support_spds2 & BNGE_LINK_SPEEDS2_MSK_200GB_PAM4) && + lanes != 2) { + fw_speed = BNGE_LINK_SPEED_200GB_PAM4; + sig_mode = BNGE_SIG_MODE_PAM4; + lanes_needed = 4; + } else if (support_spds2 & BNGE_LINK_SPEEDS2_MSK_200GB_PAM4_112) { + fw_speed = BNGE_LINK_SPEED_200GB_PAM4_112; + sig_mode = BNGE_SIG_MODE_PAM4_112; + lanes_needed = 2; + } + break; + case SPEED_400000: + if ((support_spds2 & BNGE_LINK_SPEEDS2_MSK_400GB_PAM4) && + lanes != 4) { + fw_speed = BNGE_LINK_SPEED_400GB_PAM4; + sig_mode = BNGE_SIG_MODE_PAM4; + lanes_needed = 8; + } else if (support_spds2 & BNGE_LINK_SPEEDS2_MSK_400GB_PAM4_112) { + fw_speed = BNGE_LINK_SPEED_400GB_PAM4_112; + sig_mode = BNGE_SIG_MODE_PAM4_112; + lanes_needed = 4; + } + break; + case SPEED_800000: + if (support_spds2 & BNGE_LINK_SPEEDS2_MSK_800GB_PAM4_112) { + fw_speed = BNGE_LINK_SPEED_800GB_PAM4_112; + sig_mode = BNGE_SIG_MODE_PAM4_112; + lanes_needed = 8; + } + } + + if (!fw_speed) { + netdev_err(dev, "unsupported speed!\n"); + return -EINVAL; + } + + if (lanes && lanes != lanes_needed) { + netdev_err(dev, "unsupported number of lanes for speed\n"); + return -EINVAL; + } + + if (elink_info->req_link_speed == fw_speed && + elink_info->req_signal_mode == sig_mode && + elink_info->autoneg == 0) + return -EALREADY; + + elink_info->req_link_speed = fw_speed; + elink_info->req_signal_mode = sig_mode; + elink_info->req_duplex = BNGE_LINK_DUPLEX_FULL; + elink_info->autoneg = 0; + elink_info->advertising = 0; + elink_info->advertising_pam4 = 0; + + return 0; +} + +int bnge_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *lk_ksettings) +{ + const struct ethtool_link_settings *base = &lk_ksettings->base; + struct bnge_net *bn = netdev_priv(dev); + struct bnge_dev *bd = bn->bd; + struct bnge_ethtool_link_info *elink_info = &bn->eth_link_info; + struct bnge_link_info *link_info = &bd->link_info; + bool set_pause = false; + u32 speed, lanes = 0; + int rc = 0; + + if (!BNGE_PHY_CFG_ABLE(bd)) + return -EOPNOTSUPP; + + mutex_lock(&bd->link_lock); + if (base->autoneg == AUTONEG_ENABLE) { + bnge_set_ethtool_speeds(bn, + lk_ksettings->link_modes.advertising); + elink_info->autoneg |= BNGE_AUTONEG_SPEED; + if (!elink_info->advertising && !elink_info->advertising_pam4) { + elink_info->advertising = link_info->support_auto_speeds; + elink_info->advertising_pam4 = + link_info->support_pam4_auto_speeds; + } + /* any change to autoneg will cause link change, therefore the + * driver should put back the original pause setting in autoneg + */ + if (!(bd->phy_flags & BNGE_PHY_FL_NO_PAUSE)) + set_pause = true; + } else { + u8 phy_type = link_info->phy_type; + + if (phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASET || + phy_type == PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE || + link_info->media_type == PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP) { + netdev_err(dev, "10GBase-T devices must autoneg\n"); + rc = -EINVAL; + goto set_setting_exit; + } + if (base->duplex == DUPLEX_HALF) { + netdev_err(dev, "HALF DUPLEX is not supported!\n"); + rc = -EINVAL; + goto set_setting_exit; + } + speed = base->speed; + lanes = lk_ksettings->lanes; + rc = bnge_force_link_speed(dev, speed, lanes); + if (rc) { + if (rc == -EALREADY) + rc = 0; + goto set_setting_exit; + } + } + + if (netif_running(dev)) + rc = bnge_hwrm_set_link_setting(bn, set_pause); + +set_setting_exit: + mutex_unlock(&bd->link_lock); + return rc; +} diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_link.h b/drivers/net/ethernet/broadcom/bnge/bnge_link.h new file mode 100644 index 0000000000000..995ca7318799a --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnge/bnge_link.h @@ -0,0 +1,191 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Broadcom */ + +#ifndef _BNGE_LINK_H_ +#define _BNGE_LINK_H_ + +#define BNGE_PHY_AUTO_SPEEDS2_MASK \ + PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK +#define BNGE_PHY_AUTO_SPEED_MASK \ + PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK +#define BNGE_PHY_AUTO_PAM4_SPEED_MASK \ + PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK +#define BNGE_PHY_FLAGS_RESTART_AUTO \ + PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG +#define BNGE_PHY_FLAGS_ENA_FORCE_SPEEDS2 \ + PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2 +#define BNGE_PHY_FLAGS_ENA_FORCE_PM4_SPEED \ + PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED + +struct bnge_link_info { + u8 phy_type; + u8 media_type; + u8 transceiver; + u8 phy_addr; + u8 phy_link_status; +#define BNGE_LINK_LINK PORT_PHY_QCFG_RESP_LINK_LINK + u8 phy_state; +#define BNGE_PHY_STATE_ENABLED 0 +#define BNGE_PHY_STATE_DISABLED 1 + + u8 link_state; +#define BNGE_LINK_STATE_UNKNOWN 0 +#define BNGE_LINK_STATE_DOWN 1 +#define BNGE_LINK_STATE_UP 2 +#define BNGE_LINK_IS_UP(bd) \ + ((bd)->link_info.link_state == BNGE_LINK_STATE_UP) + u8 active_lanes; + u8 duplex; +#define BNGE_LINK_DUPLEX_FULL PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL + u8 pause; +#define BNGE_LINK_PAUSE_TX PORT_PHY_QCFG_RESP_PAUSE_TX +#define BNGE_LINK_PAUSE_RX PORT_PHY_QCFG_RESP_PAUSE_RX +#define BNGE_LINK_PAUSE_BOTH (PORT_PHY_QCFG_RESP_PAUSE_RX | \ + PORT_PHY_QCFG_RESP_PAUSE_TX) + u8 lp_pause; + u8 auto_pause_setting; + u8 force_pause_setting; + u8 duplex_setting; + u8 auto_mode; +#define BNGE_AUTO_MODE(mode) ((mode) > BNGE_LINK_AUTO_NONE && \ + (mode) <= BNGE_LINK_AUTO_MSK) +#define BNGE_LINK_AUTO_NONE PORT_PHY_QCFG_RESP_AUTO_MODE_NONE +#define BNGE_LINK_AUTO_MSK PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK +#define PHY_VER_LEN 3 + u8 phy_ver[PHY_VER_LEN]; + u16 link_speed; +#define BNGE_LINK_SPEED_50GB PORT_PHY_QCFG_RESP_LINK_SPEED_50GB +#define BNGE_LINK_SPEED_100GB PORT_PHY_QCFG_RESP_LINK_SPEED_100GB +#define BNGE_LINK_SPEED_200GB PORT_PHY_QCFG_RESP_LINK_SPEED_200GB +#define BNGE_LINK_SPEED_400GB PORT_PHY_QCFG_RESP_LINK_SPEED_400GB +#define BNGE_LINK_SPEED_800GB PORT_PHY_QCFG_RESP_LINK_SPEED_800GB + u16 support_speeds; + u16 support_pam4_speeds; + u16 support_speeds2; + + u16 auto_link_speeds; /* fw adv setting */ +#define BNGE_LINK_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB +#define BNGE_LINK_SPEED_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB + u16 auto_pam4_link_speeds; +#define BNGE_LINK_PAM4_SPEED_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G +#define BNGE_LINK_PAM4_SPEED_MSK_100GB \ + PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G +#define BNGE_LINK_PAM4_SPEED_MSK_200GB \ + PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G + u16 auto_link_speeds2; +#define BNGE_LINK_SPEEDS2_MSK_50GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB +#define BNGE_LINK_SPEEDS2_MSK_100GB PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB +#define BNGE_LINK_SPEEDS2_MSK_50GB_PAM4 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56 +#define BNGE_LINK_SPEEDS2_MSK_100GB_PAM4 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56 +#define BNGE_LINK_SPEEDS2_MSK_200GB_PAM4 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56 +#define BNGE_LINK_SPEEDS2_MSK_400GB_PAM4 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56 +#define BNGE_LINK_SPEEDS2_MSK_100GB_PAM4_112 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112 +#define BNGE_LINK_SPEEDS2_MSK_200GB_PAM4_112 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112 +#define BNGE_LINK_SPEEDS2_MSK_400GB_PAM4_112 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112 +#define BNGE_LINK_SPEEDS2_MSK_800GB_PAM4_112 \ + PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112 + + u16 support_auto_speeds; + u16 support_pam4_auto_speeds; + u16 support_auto_speeds2; + + u16 lp_auto_link_speeds; + u16 lp_auto_pam4_link_speeds; + u16 force_link_speed; + u16 force_pam4_link_speed; + u16 force_link_speed2; +#define BNGE_LINK_SPEED_50GB_PAM4 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56 +#define BNGE_LINK_SPEED_100GB_PAM4 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56 +#define BNGE_LINK_SPEED_200GB_PAM4 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56 +#define BNGE_LINK_SPEED_400GB_PAM4 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56 +#define BNGE_LINK_SPEED_100GB_PAM4_112 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 +#define BNGE_LINK_SPEED_200GB_PAM4_112 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 +#define BNGE_LINK_SPEED_400GB_PAM4_112 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 +#define BNGE_LINK_SPEED_800GB_PAM4_112 \ + PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 + + u32 preemphasis; + u8 module_status; + u8 active_fec_sig_mode; + u16 fec_cfg; +#define BNGE_FEC_NONE PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED +#define BNGE_FEC_AUTONEG_CAP PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED +#define BNGE_FEC_AUTONEG PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED +#define BNGE_FEC_ENC_BASE_R_CAP \ + PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED +#define BNGE_FEC_ENC_BASE_R PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED +#define BNGE_FEC_ENC_RS_CAP \ + PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED +#define BNGE_FEC_ENC_LLRS_CAP \ + (PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED | \ + PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED) +#define BNGE_FEC_ENC_RS \ + (PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED | \ + PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED | \ + PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED) +#define BNGE_FEC_ENC_LLRS \ + (PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED | \ + PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED) + + bool phy_retry; + unsigned long phy_retry_expires; + + /* a copy of phy_qcfg output used to report link + * info to VF + */ + struct hwrm_port_phy_qcfg_output phy_qcfg_resp; +}; + +struct bnge_ethtool_link_info { + /* copy of requested setting from ethtool cmd */ + u8 autoneg; +#define BNGE_AUTONEG_SPEED 1 +#define BNGE_AUTONEG_FLOW_CTRL 2 + u8 req_signal_mode; +#define BNGE_SIG_MODE_NRZ PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ +#define BNGE_SIG_MODE_PAM4 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4 +#define BNGE_SIG_MODE_PAM4_112 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112 +#define BNGE_SIG_MODE_MAX (PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST + 1) + u8 req_duplex; + u8 req_flow_ctrl; + u16 req_link_speed; + u16 advertising; /* user adv setting */ + u16 advertising_pam4; + bool force_link_chng; +}; + +void bnge_hwrm_set_eee(struct bnge_dev *bd, + struct hwrm_port_phy_cfg_input *req); +void bnge_hwrm_set_link_common(struct bnge_net *bn, + struct hwrm_port_phy_cfg_input *req); +void bnge_hwrm_set_pause_common(struct bnge_net *bn, + struct hwrm_port_phy_cfg_input *req); +int bnge_update_phy_setting(struct bnge_net *bn); +void bnge_get_port_module_status(struct bnge_net *bn); +void bnge_report_link(struct bnge_dev *bd); +bool bnge_support_speed_dropped(struct bnge_net *bn); +void bnge_init_ethtool_link_settings(struct bnge_net *bn); +u32 bnge_fw_to_ethtool_speed(u16 fw_link_speed); +int bnge_probe_phy(struct bnge_net *bd, bool fw_dflt); +bool bnge_phy_qcaps_no_speed(struct hwrm_port_phy_qcaps_output *resp); +int bnge_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *lk_ksettings); +int bnge_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *lk_ksettings); +u32 bnge_get_link(struct net_device *dev); +u16 bnge_get_force_speed(struct bnge_link_info *link_info); +#endif /* _BNGE_LINK_H_ */ diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c index 832eeb960bd2d..dbca011db33ee 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c @@ -10,16 +10,22 @@ #include #include #include +#include +#include +#include #include #include #include +#include #include #include #include "bnge.h" +#include "bnge_hwrm.h" #include "bnge_hwrm_lib.h" #include "bnge_ethtool.h" #include "bnge_rmem.h" +#include "bnge_txrx.h" #define BNGE_RING_TO_TC_OFF(bd, tx) \ ((tx) % (bd)->tx_nr_rings_per_tc) @@ -35,6 +41,10 @@ static void bnge_free_stats_mem(struct bnge_net *bn, { struct bnge_dev *bd = bn->bd; + kfree(stats->hw_masks); + stats->hw_masks = NULL; + kfree(stats->sw_stats); + stats->sw_stats = NULL; if (stats->hw_stats) { dma_free_coherent(bd->dev, stats->len, stats->hw_stats, stats->hw_stats_map); @@ -43,7 +53,7 @@ static void bnge_free_stats_mem(struct bnge_net *bn, } static int bnge_alloc_stats_mem(struct bnge_net *bn, - struct bnge_stats_mem *stats) + struct bnge_stats_mem *stats, bool alloc_masks) { struct bnge_dev *bd = bn->bd; @@ -52,7 +62,20 @@ static int bnge_alloc_stats_mem(struct bnge_net *bn, if (!stats->hw_stats) return -ENOMEM; + stats->sw_stats = kzalloc(stats->len, GFP_KERNEL); + if (!stats->sw_stats) + goto stats_mem_err; + + if (alloc_masks) { + stats->hw_masks = kzalloc(stats->len, GFP_KERNEL); + if (!stats->hw_masks) + goto stats_mem_err; + } return 0; + +stats_mem_err: + bnge_free_stats_mem(bn, stats); + return -ENOMEM; } static void bnge_free_ring_stats(struct bnge_net *bn) @@ -68,7 +91,105 @@ static void bnge_free_ring_stats(struct bnge_net *bn) struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; bnge_free_stats_mem(bn, &nqr->stats); + + kfree(nqr->sw_stats); + nqr->sw_stats = NULL; + } +} + +static void bnge_fill_masks(u64 *mask_arr, u64 mask, int count) +{ + int i; + + for (i = 0; i < count; i++) + mask_arr[i] = mask; +} + +void bnge_copy_hw_masks(u64 *mask_arr, __le64 *hw_mask_arr, int count) +{ + int i; + + for (i = 0; i < count; i++) + mask_arr[i] = le64_to_cpu(hw_mask_arr[i]); +} + +static void bnge_init_stats(struct bnge_net *bn) +{ + struct bnge_napi *bnapi = bn->bnapi[0]; + struct bnge_nq_ring_info *nqr; + struct bnge_stats_mem *stats; + struct bnge_dev *bd = bn->bd; + __le64 *rx_stats, *tx_stats; + int rc, rx_count, tx_count; + u64 *rx_masks, *tx_masks; + u8 flags; + + nqr = &bnapi->nq_ring; + stats = &nqr->stats; + rc = bnge_hwrm_func_qstat_ext(bd, stats); + if (rc) { + u64 mask = (1ULL << 48) - 1; + + bnge_fill_masks(stats->hw_masks, mask, stats->len / 8); } + if (bn->flags & BNGE_FLAG_PORT_STATS) { + stats = &bn->port_stats; + rx_stats = stats->hw_stats; + rx_masks = stats->hw_masks; + rx_count = sizeof(struct rx_port_stats) / 8; + tx_stats = rx_stats + BNGE_TX_PORT_STATS_BYTE_OFFSET / 8; + tx_masks = rx_masks + BNGE_TX_PORT_STATS_BYTE_OFFSET / 8; + tx_count = sizeof(struct tx_port_stats) / 8; + + flags = PORT_QSTATS_REQ_FLAGS_COUNTER_MASK; + rc = bnge_hwrm_port_qstats(bd, flags); + if (rc) { + u64 mask = (1ULL << 40) - 1; + + bnge_fill_masks(rx_masks, mask, rx_count); + bnge_fill_masks(tx_masks, mask, tx_count); + } else { + bnge_copy_hw_masks(rx_masks, rx_stats, rx_count); + bnge_copy_hw_masks(tx_masks, tx_stats, tx_count); + bnge_hwrm_port_qstats(bd, 0); + } + } + if (bn->flags & BNGE_FLAG_PORT_STATS_EXT) { + stats = &bn->rx_port_stats_ext; + rx_stats = stats->hw_stats; + rx_masks = stats->hw_masks; + rx_count = sizeof(struct rx_port_stats_ext) / 8; + stats = &bn->tx_port_stats_ext; + tx_stats = stats->hw_stats; + tx_masks = stats->hw_masks; + tx_count = sizeof(struct tx_port_stats_ext) / 8; + + flags = PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK; + rc = bnge_hwrm_port_qstats_ext(bd, flags); + if (rc) { + u64 mask = (1ULL << 40) - 1; + + bnge_fill_masks(rx_masks, mask, rx_count); + if (tx_stats) + bnge_fill_masks(tx_masks, mask, tx_count); + } else { + bnge_copy_hw_masks(rx_masks, rx_stats, rx_count); + if (tx_stats) + bnge_copy_hw_masks(tx_masks, tx_stats, + tx_count); + bnge_hwrm_port_qstats_ext(bd, 0); + } + } +} + +static void bnge_free_port_stats(struct bnge_net *bn) +{ + bn->flags &= ~BNGE_FLAG_PORT_STATS; + bn->flags &= ~BNGE_FLAG_PORT_STATS_EXT; + + bnge_free_stats_mem(bn, &bn->port_stats); + bnge_free_stats_mem(bn, &bn->rx_port_stats_ext); + bnge_free_stats_mem(bn, &bn->tx_port_stats_ext); } static int bnge_alloc_ring_stats(struct bnge_net *bn) @@ -83,13 +204,48 @@ static int bnge_alloc_ring_stats(struct bnge_net *bn) struct bnge_napi *bnapi = bn->bnapi[i]; struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + nqr->sw_stats = kzalloc(sizeof(*nqr->sw_stats), GFP_KERNEL); + if (!nqr->sw_stats) { + rc = -ENOMEM; + goto err_free_ring_stats; + } + nqr->stats.len = size; - rc = bnge_alloc_stats_mem(bn, &nqr->stats); + rc = bnge_alloc_stats_mem(bn, &nqr->stats, !i); if (rc) goto err_free_ring_stats; nqr->hw_stats_ctx_id = INVALID_STATS_CTX_ID; } + + if (!bn->port_stats.hw_stats) { + bn->port_stats.len = BNGE_PORT_STATS_SIZE; + rc = bnge_alloc_stats_mem(bn, &bn->port_stats, true); + if (rc) + goto err_free_ring_stats; + + bn->flags |= BNGE_FLAG_PORT_STATS; + } + + if (!(bd->fw_cap & BNGE_FW_CAP_EXT_STATS_SUPPORTED)) + return 0; + + if (!bn->rx_port_stats_ext.hw_stats) { + bn->rx_port_stats_ext.len = sizeof(struct rx_port_stats_ext); + /* Extended stats are optional */ + rc = bnge_alloc_stats_mem(bn, &bn->rx_port_stats_ext, true); + if (!rc) + return 0; + } + + if (!bn->tx_port_stats_ext.hw_stats) { + bn->tx_port_stats_ext.len = sizeof(struct tx_port_stats_ext); + /* Extended stats are optional */ + rc = bnge_alloc_stats_mem(bn, &bn->tx_port_stats_ext, true); + if (!rc) + return 0; + } + bn->flags |= BNGE_FLAG_PORT_STATS_EXT; return 0; err_free_ring_stats: @@ -97,6 +253,128 @@ static int bnge_alloc_ring_stats(struct bnge_net *bn) return rc; } +static void __bnge_queue_sp_work(struct bnge_dev *bd) +{ + queue_work(bd->bnge_pf_wq, &bd->sp_task); +} + +static void bnge_queue_sp_work(struct bnge_dev *bd, unsigned int event) +{ + set_bit(event, &bd->sp_event); + __bnge_queue_sp_work(bd); +} + +void bnge_timer(struct timer_list *t) +{ + struct bnge_dev *bd = timer_container_of(bd, t, timer); + struct bnge_net *bn = netdev_priv(bd->netdev); + struct net_device *dev = bd->netdev; + + if (!netif_running(dev) || !test_bit(BNGE_STATE_OPEN, &bd->state)) + return; + + if (atomic_read(&bn->intr_sem) != 0) + goto bnge_restart_timer; + + if (BNGE_LINK_IS_UP(bd) && bn->stats_coal_ticks) + bnge_queue_sp_work(bd, BNGE_PERIODIC_STATS_SP_EVENT); + +bnge_restart_timer: + mod_timer(&bd->timer, jiffies + bd->current_interval); +} + +static void bnge_add_one_ctr(u64 hw, u64 *sw, u64 mask) +{ + u64 sw_tmp; + + hw &= mask; + sw_tmp = (*sw & ~mask) | hw; + if (hw < (*sw & mask)) + sw_tmp += mask + 1; + WRITE_ONCE(*sw, sw_tmp); +} + +static void __bnge_accumulate_stats(__le64 *hw_stats, u64 *sw_stats, u64 *masks, + int count) +{ + int i; + + for (i = 0; i < count; i++) { + u64 hw = le64_to_cpu(READ_ONCE(hw_stats[i])); + + if (masks[i] == -1ULL) + sw_stats[i] = hw; + else + bnge_add_one_ctr(hw, &sw_stats[i], masks[i]); + } +} + +static void bnge_accumulate_stats(struct bnge_stats_mem *stats) +{ + if (!stats->hw_stats) + return; + + __bnge_accumulate_stats(stats->hw_stats, stats->sw_stats, + stats->hw_masks, stats->len / 8); +} + +static void bnge_accumulate_all_stats(struct bnge_dev *bd) +{ + struct bnge_net *bn = netdev_priv(bd->netdev); + struct bnge_stats_mem *ring0_stats; + int i; + + for (i = 0; i < bd->nq_nr_rings; i++) { + struct bnge_napi *bnapi = bn->bnapi[i]; + struct bnge_nq_ring_info *nqr; + struct bnge_stats_mem *stats; + + nqr = &bnapi->nq_ring; + stats = &nqr->stats; + if (!i) + ring0_stats = stats; + __bnge_accumulate_stats(stats->hw_stats, stats->sw_stats, + ring0_stats->hw_masks, + ring0_stats->len / 8); + } + if (bn->flags & BNGE_FLAG_PORT_STATS) { + struct bnge_stats_mem *stats = &bn->port_stats; + __le64 *hw_stats = stats->hw_stats; + u64 *sw_stats = stats->sw_stats; + u64 *masks = stats->hw_masks; + int cnt; + + cnt = sizeof(struct rx_port_stats) / 8; + __bnge_accumulate_stats(hw_stats, sw_stats, masks, cnt); + + hw_stats += BNGE_TX_PORT_STATS_BYTE_OFFSET / 8; + sw_stats += BNGE_TX_PORT_STATS_BYTE_OFFSET / 8; + masks += BNGE_TX_PORT_STATS_BYTE_OFFSET / 8; + cnt = sizeof(struct tx_port_stats) / 8; + __bnge_accumulate_stats(hw_stats, sw_stats, masks, cnt); + } + if (bn->flags & BNGE_FLAG_PORT_STATS_EXT) { + bnge_accumulate_stats(&bn->rx_port_stats_ext); + bnge_accumulate_stats(&bn->tx_port_stats_ext); + } +} + +void bnge_sp_task(struct work_struct *work) +{ + struct bnge_dev *bd = container_of(work, struct bnge_dev, sp_task); + + set_bit(BNGE_STATE_IN_SP_TASK, &bd->state); + smp_mb__after_atomic(); + if (test_and_clear_bit(BNGE_PERIODIC_STATS_SP_EVENT, &bd->sp_event)) { + bnge_hwrm_port_qstats(bd, 0); + bnge_hwrm_port_qstats_ext(bd, 0); + bnge_accumulate_all_stats(bd); + } + + smp_mb__before_atomic(); + clear_bit(BNGE_STATE_IN_SP_TASK, &bd->state); +} + static void bnge_free_nq_desc_arr(struct bnge_nq_ring_info *nqr) { struct bnge_ring_struct *ring = &nqr->ring_struct; @@ -372,11 +650,37 @@ static void bnge_free_one_agg_ring_bufs(struct bnge_net *bn, } } +static void bnge_free_one_tpa_info_data(struct bnge_net *bn, + struct bnge_rx_ring_info *rxr) +{ + int i; + + for (i = 0; i < bn->max_tpa; i++) { + struct bnge_tpa_info *tpa_info = &rxr->rx_tpa[i]; + u8 *data = tpa_info->data; + + if (!data) + continue; + + tpa_info->data = NULL; + page_pool_free_va(rxr->head_pool, data, false); + } +} + static void bnge_free_one_rx_ring_pair_bufs(struct bnge_net *bn, struct bnge_rx_ring_info *rxr) { + struct bnge_tpa_idx_map *map; + + if (rxr->rx_tpa) + bnge_free_one_tpa_info_data(bn, rxr); + bnge_free_one_rx_ring_bufs(bn, rxr); bnge_free_one_agg_ring_bufs(bn, rxr); + + map = rxr->rx_tpa_idx_map; + if (map) + memset(map->agg_idx_bmap, 0, sizeof(map->agg_idx_bmap)); } static void bnge_free_rx_ring_pair_bufs(struct bnge_net *bn) @@ -391,9 +695,118 @@ static void bnge_free_rx_ring_pair_bufs(struct bnge_net *bn) bnge_free_one_rx_ring_pair_bufs(bn, &bn->rx_ring[i]); } +static void bnge_free_tx_skbs(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + u16 max_idx; + int i; + + max_idx = bn->tx_nr_pages * TX_DESC_CNT; + for (i = 0; i < bd->tx_nr_rings; i++) { + struct bnge_tx_ring_info *txr = &bn->tx_ring[i]; + int j; + + if (!txr->tx_buf_ring) + continue; + + for (j = 0; j < max_idx;) { + struct bnge_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j]; + struct sk_buff *skb; + int k, last; + + skb = tx_buf->skb; + if (!skb) { + j++; + continue; + } + + tx_buf->skb = NULL; + + dma_unmap_single(bd->dev, + dma_unmap_addr(tx_buf, mapping), + skb_headlen(skb), + DMA_TO_DEVICE); + + last = tx_buf->nr_frags; + j += 2; + for (k = 0; k < last; k++, j++) { + int ring_idx = j & bn->tx_ring_mask; + skb_frag_t *frag = &skb_shinfo(skb)->frags[k]; + + tx_buf = &txr->tx_buf_ring[ring_idx]; + dma_unmap_page(bd->dev, + dma_unmap_addr(tx_buf, mapping), + skb_frag_size(frag), + DMA_TO_DEVICE); + } + dev_kfree_skb(skb); + } + netdev_tx_reset_queue(netdev_get_tx_queue(bd->netdev, i)); + } +} + static void bnge_free_all_rings_bufs(struct bnge_net *bn) { bnge_free_rx_ring_pair_bufs(bn); + bnge_free_tx_skbs(bn); +} + +static void bnge_free_tpa_info(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i, j; + + for (i = 0; i < bd->rx_nr_rings; i++) { + struct bnge_rx_ring_info *rxr = &bn->rx_ring[i]; + + kfree(rxr->rx_tpa_idx_map); + rxr->rx_tpa_idx_map = NULL; + if (rxr->rx_tpa) { + for (j = 0; j < bn->max_tpa; j++) { + kfree(rxr->rx_tpa[j].agg_arr); + rxr->rx_tpa[j].agg_arr = NULL; + } + } + kfree(rxr->rx_tpa); + rxr->rx_tpa = NULL; + } +} + +static int bnge_alloc_tpa_info(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i, j; + + if (!bd->max_tpa_v2) + return 0; + + bn->max_tpa = max_t(u16, bd->max_tpa_v2, MAX_TPA); + for (i = 0; i < bd->rx_nr_rings; i++) { + struct bnge_rx_ring_info *rxr = &bn->rx_ring[i]; + + rxr->rx_tpa = kcalloc(bn->max_tpa, sizeof(struct bnge_tpa_info), + GFP_KERNEL); + if (!rxr->rx_tpa) + goto err_free_tpa_info; + + for (j = 0; j < bn->max_tpa; j++) { + struct rx_agg_cmp *agg; + + agg = kcalloc(MAX_SKB_FRAGS, sizeof(*agg), GFP_KERNEL); + if (!agg) + goto err_free_tpa_info; + rxr->rx_tpa[j].agg_arr = agg; + } + rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map), + GFP_KERNEL); + if (!rxr->rx_tpa_idx_map) + goto err_free_tpa_info; + } + return 0; + +err_free_tpa_info: + bnge_free_tpa_info(bn); + return -ENOMEM; } static void bnge_free_rx_rings(struct bnge_net *bn) @@ -401,6 +814,7 @@ static void bnge_free_rx_rings(struct bnge_net *bn) struct bnge_dev *bd = bn->bd; int i; + bnge_free_tpa_info(bn); for (i = 0; i < bd->rx_nr_rings; i++) { struct bnge_rx_ring_info *rxr = &bn->rx_ring[i]; struct bnge_ring_struct *ring; @@ -525,6 +939,12 @@ static int bnge_alloc_rx_rings(struct bnge_net *bn) goto err_free_rx_rings; } } + + if (bn->priv_flags & BNGE_NET_EN_TPA) { + rc = bnge_alloc_tpa_info(bn); + if (rc) + goto err_free_rx_rings; + } return rc; err_free_rx_rings: @@ -720,6 +1140,7 @@ static void bnge_free_core(struct bnge_net *bn) bnge_free_nq_arrays(bn); bnge_free_ring_stats(bn); bnge_free_ring_grps(bn); + bnge_free_port_stats(bn); bnge_free_vnics(bn); kfree(bn->tx_ring_map); bn->tx_ring_map = NULL; @@ -811,6 +1232,8 @@ static int bnge_alloc_core(struct bnge_net *bn) if (rc) goto err_free_core; + bnge_init_stats(bn); + rc = bnge_alloc_vnics(bn); if (rc) goto err_free_core; @@ -856,6 +1279,13 @@ u16 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr) return txr->tx_cpr->ring_struct.fw_ring_id; } +static void bnge_db_nq_arm(struct bnge_net *bn, + struct bnge_db_info *db, u32 idx) +{ + bnge_writeq(bn->bd, db->db_key64 | DBR_TYPE_NQ_ARM | + DB_RING_IDX(db, idx), db->doorbell); +} + static void bnge_db_nq(struct bnge_net *bn, struct bnge_db_info *db, u32 idx) { bnge_writeq(bn->bd, db->db_key64 | DBR_TYPE_NQ_MASK | @@ -878,12 +1308,6 @@ static int bnge_cp_num_to_irq_num(struct bnge_net *bn, int n) return nqr->ring_struct.map_idx; } -static irqreturn_t bnge_msix(int irq, void *dev_instance) -{ - /* NAPI scheduling to be added in a future patch */ - return IRQ_HANDLED; -} - static void bnge_init_nq_tree(struct bnge_net *bn) { struct bnge_dev *bd = bn->bd; @@ -925,9 +1349,9 @@ static netmem_ref __bnge_alloc_rx_netmem(struct bnge_net *bn, return netmem; } -static u8 *__bnge_alloc_rx_frag(struct bnge_net *bn, dma_addr_t *mapping, - struct bnge_rx_ring_info *rxr, - gfp_t gfp) +u8 *__bnge_alloc_rx_frag(struct bnge_net *bn, dma_addr_t *mapping, + struct bnge_rx_ring_info *rxr, + gfp_t gfp) { unsigned int offset; struct page *page; @@ -941,9 +1365,8 @@ static u8 *__bnge_alloc_rx_frag(struct bnge_net *bn, dma_addr_t *mapping, return page_address(page) + offset; } -static int bnge_alloc_rx_data(struct bnge_net *bn, - struct bnge_rx_ring_info *rxr, - u16 prod, gfp_t gfp) +int bnge_alloc_rx_data(struct bnge_net *bn, struct bnge_rx_ring_info *rxr, + u16 prod, gfp_t gfp) { struct bnge_sw_rx_bd *rx_buf = &rxr->rx_buf_ring[RING_RX(bn, prod)]; struct rx_bd *rxbd; @@ -995,7 +1418,7 @@ static int bnge_alloc_one_rx_ring_bufs(struct bnge_net *bn, return 0; } -static u16 bnge_find_next_agg_idx(struct bnge_rx_ring_info *rxr, u16 idx) +u16 bnge_find_next_agg_idx(struct bnge_rx_ring_info *rxr, u16 idx) { u16 next, max = rxr->rx_agg_bmap_size; @@ -1005,9 +1428,9 @@ static u16 bnge_find_next_agg_idx(struct bnge_rx_ring_info *rxr, u16 idx) return next; } -static int bnge_alloc_rx_netmem(struct bnge_net *bn, - struct bnge_rx_ring_info *rxr, - u16 prod, gfp_t gfp) +int bnge_alloc_rx_netmem(struct bnge_net *bn, + struct bnge_rx_ring_info *rxr, + u16 prod, gfp_t gfp) { struct bnge_sw_rx_agg_bd *rx_agg_buf; u16 sw_prod = rxr->rx_sw_agg_prod; @@ -1070,6 +1493,29 @@ static int bnge_alloc_one_agg_ring_bufs(struct bnge_net *bn, return -ENOMEM; } +static int bnge_alloc_one_tpa_info_data(struct bnge_net *bn, + struct bnge_rx_ring_info *rxr) +{ + dma_addr_t mapping; + u8 *data; + int i; + + for (i = 0; i < bn->max_tpa; i++) { + data = __bnge_alloc_rx_frag(bn, &mapping, rxr, + GFP_KERNEL); + if (!data) + goto err_free_tpa_info_data; + + rxr->rx_tpa[i].data = data; + rxr->rx_tpa[i].data_ptr = data + bn->rx_offset; + rxr->rx_tpa[i].mapping = mapping; + } + return 0; +err_free_tpa_info_data: + bnge_free_one_tpa_info_data(bn, rxr); + return -ENOMEM; +} + static int bnge_alloc_one_rx_ring_pair_bufs(struct bnge_net *bn, int ring_nr) { struct bnge_rx_ring_info *rxr = &bn->rx_ring[ring_nr]; @@ -1084,8 +1530,17 @@ static int bnge_alloc_one_rx_ring_pair_bufs(struct bnge_net *bn, int ring_nr) if (rc) goto err_free_one_rx_ring_bufs; } + + if (rxr->rx_tpa) { + rc = bnge_alloc_one_tpa_info_data(bn, rxr); + if (rc) + goto err_free_one_agg_ring_bufs; + } + return 0; +err_free_one_agg_ring_bufs: + bnge_free_one_agg_ring_bufs(bn, rxr); err_free_one_rx_ring_bufs: bnge_free_one_rx_ring_bufs(bn, rxr); return rc; @@ -1755,6 +2210,80 @@ static int bnge_cfg_def_vnic(struct bnge_net *bn) return rc; } +static void bnge_disable_int(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i; + + if (!bn->bnapi) + return; + + for (i = 0; i < bd->nq_nr_rings; i++) { + struct bnge_napi *bnapi = bn->bnapi[i]; + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + struct bnge_ring_struct *ring = &nqr->ring_struct; + + if (ring->fw_ring_id != INVALID_HW_RING_ID) + bnge_db_nq(bn, &nqr->nq_db, nqr->nq_raw_cons); + } +} + +static void bnge_disable_int_sync(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i; + + atomic_inc(&bn->intr_sem); + bnge_disable_int(bn); + for (i = 0; i < bd->nq_nr_rings; i++) { + int map_idx = bnge_cp_num_to_irq_num(bn, i); + + synchronize_irq(bd->irq_tbl[map_idx].vector); + } +} + +static void bnge_enable_int(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i; + + atomic_set(&bn->intr_sem, 0); + for (i = 0; i < bd->nq_nr_rings; i++) { + struct bnge_napi *bnapi = bn->bnapi[i]; + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + + bnge_db_nq_arm(bn, &nqr->nq_db, nqr->nq_raw_cons); + } +} + +static void bnge_disable_napi(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i; + + if (test_and_set_bit(BNGE_STATE_NAPI_DISABLED, &bn->state)) + return; + + for (i = 0; i < bd->nq_nr_rings; i++) { + struct bnge_napi *bnapi = bn->bnapi[i]; + + napi_disable_locked(&bnapi->napi); + } +} + +static void bnge_enable_napi(struct bnge_net *bn) +{ + struct bnge_dev *bd = bn->bd; + int i; + + clear_bit(BNGE_STATE_NAPI_DISABLED, &bn->state); + for (i = 0; i < bd->nq_nr_rings; i++) { + struct bnge_napi *bnapi = bn->bnapi[i]; + + napi_enable_locked(&bnapi->napi); + } +} + static void bnge_hwrm_vnic_free(struct bnge_net *bn) { int i; @@ -1886,6 +2415,12 @@ static void bnge_hwrm_ring_free(struct bnge_net *bn, bool close_path) bnge_hwrm_rx_agg_ring_free(bn, &bn->rx_ring[i], close_path); } + /* The completion rings are about to be freed. After that the + * IRQ doorbell will not work anymore. So we need to disable + * IRQ here. + */ + bnge_disable_int_sync(bn); + for (i = 0; i < bd->nq_nr_rings; i++) { struct bnge_napi *bnapi = bn->bnapi[i]; struct bnge_nq_ring_info *nqr; @@ -2015,6 +2550,27 @@ static int bnge_request_irq(struct bnge_net *bn) return rc; } +static int bnge_set_tpa(struct bnge_net *bn, bool set_tpa) +{ + u32 tpa_flags = 0; + int rc, i; + + if (set_tpa) + tpa_flags = bn->priv_flags & BNGE_NET_EN_TPA; + else if (BNGE_NO_FW_ACCESS(bn->bd)) + return 0; + for (i = 0; i < bn->nr_vnics; i++) { + rc = bnge_hwrm_vnic_set_tpa(bn->bd, &bn->vnic_info[i], + tpa_flags); + if (rc) { + netdev_err(bn->netdev, "hwrm vnic set tpa failure rc for vnic %d: %x\n", + i, rc); + return rc; + } + } + return 0; +} + static int bnge_init_chip(struct bnge_net *bn) { struct bnge_vnic_info *vnic = &bn->vnic_info[BNGE_VNIC_DEFAULT]; @@ -2049,6 +2605,12 @@ static int bnge_init_chip(struct bnge_net *bn) if (bd->rss_cap & BNGE_RSS_CAP_RSS_HASH_TYPE_DELTA) bnge_hwrm_update_rss_hash_cfg(bn); + if (bn->priv_flags & BNGE_NET_EN_TPA) { + rc = bnge_set_tpa(bn, true); + if (rc) + goto err_out; + } + /* Filter for default vnic 0 */ rc = bnge_hwrm_set_vnic_filter(bn, 0, 0, bn->netdev->dev_addr); if (rc) { @@ -2085,16 +2647,6 @@ static int bnge_init_chip(struct bnge_net *bn) return rc; } -static int bnge_napi_poll(struct napi_struct *napi, int budget) -{ - int work_done = 0; - - /* defer NAPI implementation to next patch series */ - napi_complete_done(napi, work_done); - - return work_done; -} - static void bnge_init_napi(struct bnge_net *bn) { struct bnge_dev *bd = bn->bd; @@ -2161,6 +2713,44 @@ static int bnge_init_nic(struct bnge_net *bn) return rc; } +static void bnge_tx_disable(struct bnge_net *bn) +{ + struct bnge_tx_ring_info *txr; + int i; + + if (bn->tx_ring) { + for (i = 0; i < bn->bd->tx_nr_rings; i++) { + txr = &bn->tx_ring[i]; + WRITE_ONCE(txr->dev_state, BNGE_DEV_STATE_CLOSING); + } + } + /* Make sure napi polls see @dev_state change */ + synchronize_net(); + + if (!bn->netdev) + return; + /* Drop carrier first to prevent TX timeout */ + netif_carrier_off(bn->netdev); + /* Stop all TX queues */ + netif_tx_disable(bn->netdev); +} + +static void bnge_tx_enable(struct bnge_net *bn) +{ + struct bnge_tx_ring_info *txr; + int i; + + for (i = 0; i < bn->bd->tx_nr_rings; i++) { + txr = &bn->tx_ring[i]; + WRITE_ONCE(txr->dev_state, 0); + } + /* Make sure napi polls see @dev_state change */ + synchronize_net(); + netif_tx_wake_all_queues(bn->netdev); + if (BNGE_LINK_IS_UP(bn->bd)) + netif_carrier_on(bn->netdev); +} + static int bnge_open_core(struct bnge_net *bn) { struct bnge_dev *bd = bn->bd; @@ -2192,7 +2782,30 @@ static int bnge_open_core(struct bnge_net *bn) netdev_err(bn->netdev, "bnge_init_nic err: %d\n", rc); goto err_free_irq; } + + bnge_enable_napi(bn); + + mutex_lock(&bd->link_lock); + rc = bnge_update_phy_setting(bn); + mutex_unlock(&bd->link_lock); + if (rc) { + netdev_warn(bn->netdev, "failed to update phy settings\n"); + if (BNGE_SINGLE_PF(bd)) { + bd->link_info.phy_retry = true; + bd->link_info.phy_retry_expires = + jiffies + 5 * HZ; + } + } + set_bit(BNGE_STATE_OPEN, &bd->state); + + bnge_enable_int(bn); + bnge_tx_enable(bn); + mod_timer(&bd->timer, jiffies + bd->current_interval); + /* Poll link status and check for SFP+ module status */ + mutex_lock(&bd->link_lock); + bnge_get_port_module_status(bn); + mutex_unlock(&bd->link_lock); return 0; err_free_irq: @@ -2203,13 +2816,6 @@ static int bnge_open_core(struct bnge_net *bn) return rc; } -static netdev_tx_t bnge_start_xmit(struct sk_buff *skb, struct net_device *dev) -{ - dev_kfree_skb_any(skb); - - return NETDEV_TX_OK; -} - static int bnge_open(struct net_device *dev) { struct bnge_net *bn = netdev_priv(dev); @@ -2224,8 +2830,7 @@ static int bnge_open(struct net_device *dev) static int bnge_shutdown_nic(struct bnge_net *bn) { - /* TODO: close_path = 0 until we make NAPI functional */ - bnge_hwrm_resource_free(bn, 0); + bnge_hwrm_resource_free(bn, 1); return 0; } @@ -2233,8 +2838,12 @@ static void bnge_close_core(struct bnge_net *bn) { struct bnge_dev *bd = bn->bd; + bnge_tx_disable(bn); + clear_bit(BNGE_STATE_OPEN, &bd->state); bnge_shutdown_nic(bn); + bnge_disable_napi(bn); + timer_delete_sync(&bd->timer); bnge_free_all_rings_bufs(bn); bnge_free_irq(bn); bnge_del_napi(bn); @@ -2251,6 +2860,35 @@ static int bnge_close(struct net_device *dev) return 0; } +static void bnge_get_one_ring_err_stats(struct bnge_dev *bd, + struct bnge_total_ring_err_stats *stats, + struct bnge_nq_ring_info *nqr) +{ + struct bnge_sw_stats *sw_stats = nqr->sw_stats; + u64 *hw_stats = nqr->stats.sw_stats; + + stats->rx_total_l4_csum_errors += sw_stats->rx.rx_l4_csum_errors; + stats->rx_total_resets += sw_stats->rx.rx_resets; + stats->rx_total_buf_errors += sw_stats->rx.rx_buf_errors; + stats->rx_total_oom_discards += sw_stats->rx.rx_oom_discards; + stats->rx_total_netpoll_discards += sw_stats->rx.rx_netpoll_discards; + stats->rx_total_ring_discards += + BNGE_GET_RING_STATS64(hw_stats, rx_discard_pkts); + stats->tx_total_resets += sw_stats->tx.tx_resets; + stats->tx_total_ring_discards += + BNGE_GET_RING_STATS64(hw_stats, tx_discard_pkts); +} + +void bnge_get_ring_err_stats(struct bnge_net *bn, + struct bnge_total_ring_err_stats *stats) +{ + int i; + + for (i = 0; i < bn->bd->nq_nr_rings; i++) + bnge_get_one_ring_err_stats(bn->bd, stats, + &bn->bnapi[i]->nq_ring); +} + static const struct net_device_ops bnge_netdev_ops = { .ndo_open = bnge_open, .ndo_stop = bnge_close, @@ -2295,7 +2933,6 @@ void bnge_set_ring_params(struct bnge_dev *bd) rx_space = rx_size + ALIGN(NET_SKB_PAD, 8) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - bn->rx_copy_thresh = BNGE_RX_COPY_THRESH; ring_size = bn->rx_ring_size; bn->rx_agg_ring_size = 0; bn->rx_agg_nr_pages = 0; @@ -2334,7 +2971,10 @@ void bnge_set_ring_params(struct bnge_dev *bd) bn->rx_agg_ring_size = agg_ring_size; bn->rx_agg_ring_mask = (bn->rx_agg_nr_pages * RX_DESC_CNT) - 1; - rx_size = SKB_DATA_ALIGN(BNGE_RX_COPY_THRESH + NET_IP_ALIGN); + rx_size = max3(BNGE_DEFAULT_RX_COPYBREAK, + bn->rx_copybreak, + bn->netdev->cfg_pending->hds_thresh); + rx_size = SKB_DATA_ALIGN(rx_size + NET_IP_ALIGN); rx_space = rx_size + NET_SKB_PAD + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); } @@ -2367,6 +3007,17 @@ void bnge_set_ring_params(struct bnge_dev *bd) bn->cp_ring_mask = bn->cp_bit - 1; } +static void bnge_init_ring_params(struct bnge_net *bn) +{ + unsigned int rx_size; + + bn->rx_copybreak = BNGE_DEFAULT_RX_COPYBREAK; + /* Try to fit 4 chunks into a 4k page */ + rx_size = SZ_1K - + NET_SKB_PAD - SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); + bn->netdev->cfg->hds_thresh = max(BNGE_DEFAULT_RX_COPYBREAK, rx_size); +} + int bnge_netdev_alloc(struct bnge_dev *bd, int max_irqs) { struct net_device *netdev; @@ -2456,11 +3107,16 @@ int bnge_netdev_alloc(struct bnge_dev *bd, int max_irqs) bn->rx_dir = DMA_FROM_DEVICE; bnge_set_tpa_flags(bd); + bnge_init_ring_params(bn); bnge_set_ring_params(bd); bnge_init_l2_fltr_tbl(bn); bnge_init_mac_addr(bd); + rc = bnge_probe_phy(bn, true); + if (rc) + goto err_netdev; + netdev->request_ops_lock = true; rc = register_netdev(netdev); if (rc) { diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h index fb3b961536ba7..ad1cfd4e6f0b8 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h @@ -8,6 +8,8 @@ #include #include #include "bnge_db.h" +#include "bnge_link.h" +#include "bnge_hw_def.h" struct tx_bd { __le32 tx_bd_len_flags_type; @@ -76,6 +78,7 @@ struct tx_cmp { #define CMPL_BASE_TYPE_HWRM_FWD_REQ 0x22UL #define CMPL_BASE_TYPE_HWRM_FWD_RESP 0x24UL #define CMPL_BASE_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define CMPL_BA_TY_HWRM_ASY_EVT CMPL_BASE_TYPE_HWRM_ASYNC_EVENT #define TX_CMP_FLAGS_ERROR (1 << 6) #define TX_CMP_FLAGS_PUSH (1 << 7) u32 tx_cmp_opaque; @@ -135,7 +138,8 @@ struct bnge_ring_grp_info { u16 nq_fw_ring_id; }; -#define BNGE_RX_COPY_THRESH 256 +#define BNGE_DEFAULT_RX_COPYBREAK 256 +#define BNGE_MAX_RX_COPYBREAK 1024 #define BNGE_HW_FEATURE_VLAN_ALL_RX \ (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX) @@ -150,6 +154,46 @@ enum { #define BNGE_NET_EN_TPA (BNGE_NET_EN_GRO | BNGE_NET_EN_LRO) +#define BNGE_NO_FW_ACCESS(bd) (pci_channel_offline((bd)->pdev)) + +#define MAX_TPA 256 +#define MAX_TPA_MASK (MAX_TPA - 1) +#define MAX_TPA_SEGS 0x3f + +#define BNGE_AGG_IDX_BMAP_SIZE (MAX_TPA / BITS_PER_LONG) +struct bnge_tpa_idx_map { + u16 agg_id_tbl[1024]; + unsigned long agg_idx_bmap[BNGE_AGG_IDX_BMAP_SIZE]; +}; + +struct bnge_tpa_info { + void *data; + u8 *data_ptr; + dma_addr_t mapping; + u16 len; + unsigned short gso_type; + u32 flags2; + u32 metadata; + enum pkt_hash_types hash_type; + u32 rss_hash; + u32 hdr_info; + +#define BNGE_TPA_INNER_L3_OFF(hdr_info) \ + (((hdr_info) >> 18) & 0x1ff) + +#define BNGE_TPA_INNER_L2_OFF(hdr_info) \ + (((hdr_info) >> 9) & 0x1ff) + +#define BNGE_TPA_OUTER_L3_OFF(hdr_info) \ + ((hdr_info) & 0x1ff) + + u16 cfa_code; /* cfa_code in TPA start compl */ + u8 agg_count; + u8 vlan_valid:1; + u8 cfa_code_valid:1; + struct rx_agg_cmp *agg_arr; +}; + /* Minimum TX BDs for a TX packet with MAX_SKB_FRAGS + 1. We need one extra * BD because the first TX BD is always a long BD. */ @@ -172,10 +216,82 @@ enum { #define RING_RX_AGG(bn, idx) ((idx) & (bn)->rx_agg_ring_mask) #define NEXT_RX_AGG(idx) ((idx) + 1) +#define BNGE_NQ_HDL_IDX_MASK 0x00ffffff +#define BNGE_NQ_HDL_TYPE_MASK 0xff000000 #define BNGE_NQ_HDL_TYPE_SHIFT 24 #define BNGE_NQ_HDL_TYPE_RX 0x00 #define BNGE_NQ_HDL_TYPE_TX 0x01 +#define BNGE_NQ_HDL_IDX(hdl) ((hdl) & BNGE_NQ_HDL_IDX_MASK) +#define BNGE_NQ_HDL_TYPE(hdl) (((hdl) & BNGE_NQ_HDL_TYPE_MASK) >> \ + BNGE_NQ_HDL_TYPE_SHIFT) +#define BNGE_GET_RING_STATS64(sw, counter) \ + (*((sw) + offsetof(struct ctx_hw_stats, counter) / 8)) + +#define BNGE_GET_RX_PORT_STATS64(sw, counter) \ + (*((sw) + offsetof(struct rx_port_stats, counter) / 8)) + +#define BNGE_GET_TX_PORT_STATS64(sw, counter) \ + (*((sw) + offsetof(struct tx_port_stats, counter) / 8)) + +#define BNGE_PORT_STATS_SIZE \ + (sizeof(struct rx_port_stats) + sizeof(struct tx_port_stats) + 1024) + +#define BNGE_TX_PORT_STATS_BYTE_OFFSET \ + (sizeof(struct rx_port_stats) + 512) + +#define BNGE_RX_STATS_OFFSET(counter) \ + (offsetof(struct rx_port_stats, counter) / 8) + +#define BNGE_TX_STATS_OFFSET(counter) \ + ((offsetof(struct tx_port_stats, counter) + \ + BNGE_TX_PORT_STATS_BYTE_OFFSET) / 8) + +#define BNGE_RX_STATS_EXT_OFFSET(counter) \ + (offsetof(struct rx_port_stats_ext, counter) / 8) + +#define BNGE_RX_STATS_EXT_NUM_LEGACY \ + BNGE_RX_STATS_EXT_OFFSET(rx_fec_corrected_blocks) + +#define BNGE_TX_STATS_EXT_OFFSET(counter) \ + (offsetof(struct tx_port_stats_ext, counter) / 8) + +struct bnge_total_ring_err_stats { + u64 rx_total_l4_csum_errors; + u64 rx_total_resets; + u64 rx_total_buf_errors; + u64 rx_total_oom_discards; + u64 rx_total_netpoll_discards; + u64 rx_total_ring_discards; + u64 tx_total_resets; + u64 tx_total_ring_discards; +}; + +struct bnge_rx_sw_stats { + u64 rx_l4_csum_errors; + u64 rx_resets; + u64 rx_buf_errors; + u64 rx_oom_discards; + u64 rx_netpoll_discards; +}; + +struct bnge_tx_sw_stats { + u64 tx_resets; +}; + +struct bnge_stats_mem { + u64 *sw_stats; + u64 *hw_masks; + void *hw_stats; + dma_addr_t hw_stats_map; + int len; +}; + +struct bnge_sw_stats { + struct bnge_rx_sw_stats rx; + struct bnge_tx_sw_stats tx; +}; + struct bnge_net { struct bnge_dev *bd; struct net_device *netdev; @@ -186,7 +302,7 @@ struct bnge_net { u32 rx_buf_size; u32 rx_buf_use_size; /* usable size */ u32 rx_agg_ring_size; - u32 rx_copy_thresh; + u32 rx_copybreak; u32 rx_ring_mask; u32 rx_agg_ring_mask; u16 rx_nr_pages; @@ -231,6 +347,35 @@ struct bnge_net { u8 rss_hash_key_updated:1; int rsscos_nr_ctxs; u32 stats_coal_ticks; + + struct bnge_ethtool_link_info eth_link_info; + + atomic_t intr_sem; + + unsigned long state; +#define BNGE_STATE_NAPI_DISABLED 0 + + u32 msg_enable; + u16 max_tpa; + __be16 vxlan_port; + __be16 nge_port; + __be16 vxlan_gpe_port; + + u64 flags; +#define BNGE_FLAG_PORT_STATS 0x1 +#define BNGE_FLAG_PORT_STATS_EXT 0x2 + + struct bnge_total_ring_err_stats ring_err_stats_prev; + + struct bnge_stats_mem port_stats; + struct bnge_stats_mem rx_port_stats_ext; + struct bnge_stats_mem tx_port_stats_ext; + u16 fw_rx_stats_ext_size; + u16 fw_tx_stats_ext_size; + + u8 pri2cos_idx[8]; + u8 pri2cos_valid; + }; #define BNGE_DEFAULT_RX_RING_SIZE 511 @@ -277,17 +422,292 @@ void bnge_set_ring_params(struct bnge_dev *bd); txr = (iter < BNGE_MAX_TXR_PER_NAPI - 1) ? \ (bnapi)->tx_ring[++iter] : NULL) +#define DB_EPOCH(db, idx) (((idx) & (db)->db_epoch_mask) << \ + ((db)->db_epoch_shift)) + +#define DB_TOGGLE(tgl) ((tgl) << DBR_TOGGLE_SFT) + +#define DB_RING_IDX(db, idx) (((idx) & (db)->db_ring_mask) | \ + DB_EPOCH(db, idx)) + #define BNGE_SET_NQ_HDL(cpr) \ (((cpr)->cp_ring_type << BNGE_NQ_HDL_TYPE_SHIFT) | (cpr)->cp_idx) -struct bnge_stats_mem { - u64 *sw_stats; - u64 *hw_masks; - void *hw_stats; - dma_addr_t hw_stats_map; - int len; +#define BNGE_DB_NQ(db, idx) \ + bnge_writeq(bd, (db)->db_key64 | DBR_TYPE_NQ | DB_RING_IDX(db, idx),\ + (db)->doorbell) + +#define BNGE_DB_NQ_ARM(db, idx) \ + bnge_writeq(bd, (db)->db_key64 | DBR_TYPE_NQ_ARM | \ + DB_RING_IDX(db, idx), (db)->doorbell) + +#define TPA_AGG_AGG_ID(rx_agg) \ + ((le32_to_cpu((rx_agg)->rx_agg_cmp_v) & \ + RX_AGG_CMP_AGG_ID) >> RX_AGG_CMP_AGG_ID_SHIFT) + +struct rx_tpa_start_cmp { + __le32 rx_tpa_start_cmp_len_flags_type; + #define RX_TPA_START_CMP_TYPE (0x3f << 0) + #define RX_TPA_START_CMP_FLAGS (0x3ff << 6) + #define RX_TPA_START_CMP_FLAGS_SHIFT 6 + #define RX_TPA_START_CMP_FLAGS_ERROR (0x1 << 6) + #define RX_TPA_START_CMP_FLAGS_PLACEMENT (0x7 << 7) + #define RX_TPA_START_CMP_FLAGS_PLACEMENT_SHIFT 7 + #define RX_TPA_START_CMP_FLAGS_PLACEMENT_JUMBO (0x1 << 7) + #define RX_TPA_START_CMP_FLAGS_PLACEMENT_HDS (0x2 << 7) + #define RX_TPA_START_CMP_FLAGS_PLACEMENT_GRO_JUMBO (0x5 << 7) + #define RX_TPA_START_CMP_FLAGS_PLACEMENT_GRO_HDS (0x6 << 7) + #define RX_TPA_START_CMP_FLAGS_RSS_VALID (0x1 << 10) + #define RX_TPA_START_CMP_FLAGS_TIMESTAMP (0x1 << 11) + #define RX_TPA_START_CMP_FLAGS_ITYPES (0xf << 12) + #define RX_TPA_START_CMP_FLAGS_ITYPES_SHIFT 12 + #define RX_TPA_START_CMP_FLAGS_ITYPE_TCP (0x2 << 12) + #define RX_TPA_START_CMP_LEN (0xffff << 16) + #define RX_TPA_START_CMP_LEN_SHIFT 16 + + u32 rx_tpa_start_cmp_opaque; + __le32 rx_tpa_start_cmp_misc_v1; + #define RX_TPA_START_CMP_V1 (0x1 << 0) + #define RX_TPA_START_CMP_RSS_HASH_TYPE (0x7f << 9) + #define RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT 9 + #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE (0x1ff << 7) + #define RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT 7 + #define RX_TPA_START_CMP_AGG_ID (0x7f << 25) + #define RX_TPA_START_CMP_AGG_ID_SHIFT 25 + #define RX_TPA_START_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5 16 + #define RX_TPA_START_CMP_METADATA1 (0xf << 28) + #define RX_TPA_START_CMP_METADATA1_SHIFT 28 + #define RX_TPA_START_METADATA1_TPID_SEL (0x7 << 28) + #define RX_TPA_START_METADATA1_TPID_8021Q (0x1 << 28) + #define RX_TPA_START_METADATA1_TPID_8021AD (0x0 << 28) + #define RX_TPA_START_METADATA1_VALID (0x8 << 28) + + __le32 rx_tpa_start_cmp_rss_hash; +}; + +#define TPA_START_HASH_VALID(rx_tpa_start) \ + ((rx_tpa_start)->rx_tpa_start_cmp_len_flags_type & \ + cpu_to_le32(RX_TPA_START_CMP_FLAGS_RSS_VALID)) + +#define TPA_START_HASH_TYPE(rx_tpa_start) \ + (((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ + RX_TPA_START_CMP_RSS_HASH_TYPE) >> \ + RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK) + +#define TPA_START_V3_HASH_TYPE(rx_tpa_start) \ + (((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ + RX_TPA_START_CMP_V3_RSS_HASH_TYPE) >> \ + RX_TPA_START_CMP_V3_RSS_HASH_TYPE_SHIFT) & RSS_PROFILE_ID_MASK) + +#define TPA_START_AGG_ID(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ + RX_TPA_START_CMP_AGG_ID_P5) >> RX_TPA_START_CMP_AGG_ID_SHIFT_P5) + +#define TPA_START_ERROR(rx_tpa_start) \ + ((rx_tpa_start)->rx_tpa_start_cmp_len_flags_type & \ + cpu_to_le32(RX_TPA_START_CMP_FLAGS_ERROR)) + +#define TPA_START_VLAN_VALID(rx_tpa_start) \ + ((rx_tpa_start)->rx_tpa_start_cmp_misc_v1 & \ + cpu_to_le32(RX_TPA_START_METADATA1_VALID)) + +#define TPA_START_VLAN_TPID_SEL(rx_tpa_start) \ + (le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ + RX_TPA_START_METADATA1_TPID_SEL) + +struct rx_tpa_start_cmp_ext { + __le32 rx_tpa_start_cmp_flags2; + #define RX_TPA_START_CMP_FLAGS2_IP_CS_CALC (0x1 << 0) + #define RX_TPA_START_CMP_FLAGS2_L4_CS_CALC (0x1 << 1) + #define RX_TPA_START_CMP_FLAGS2_T_IP_CS_CALC (0x1 << 2) + #define RX_TPA_START_CMP_FLAGS2_T_L4_CS_CALC (0x1 << 3) + #define RX_TPA_START_CMP_FLAGS2_IP_TYPE (0x1 << 8) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_VALID (0x1 << 9) + #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT (0x3 << 10) + #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT_SHIFT 10 + #define RX_TPA_START_CMP_V3_FLAGS2_T_IP_TYPE (0x1 << 10) + #define RX_TPA_START_CMP_V3_FLAGS2_AGG_GRO (0x1 << 11) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL (0xffff << 16) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_SHIFT 16 + + __le32 rx_tpa_start_cmp_metadata; + __le32 rx_tpa_start_cmp_cfa_code_v2; + #define RX_TPA_START_CMP_V2 (0x1 << 0) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK (0x7 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT 1 + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_FLUSH (0x5 << 1) + #define RX_TPA_START_CMP_CFA_CODE (0xffff << 16) + #define RX_TPA_START_CMPL_CFA_CODE_SHIFT 16 + #define RX_TPA_START_CMP_METADATA0_TCI_MASK (0xffff << 16) + #define RX_TPA_START_CMP_METADATA0_VID_MASK (0x0fff << 16) + #define RX_TPA_START_CMP_METADATA0_SFT 16 + __le32 rx_tpa_start_cmp_hdr_info; }; +#define TPA_START_CFA_CODE(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ + RX_TPA_START_CMP_CFA_CODE) >> RX_TPA_START_CMPL_CFA_CODE_SHIFT) + +#define TPA_START_IS_IPV6(rx_tpa_start) \ + (!!((rx_tpa_start)->rx_tpa_start_cmp_flags2 & \ + cpu_to_le32(RX_TPA_START_CMP_FLAGS2_IP_TYPE))) + +#define TPA_START_ERROR_CODE(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ + RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK) >> \ + RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT) + +#define TPA_START_METADATA0_TCI(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ + RX_TPA_START_CMP_METADATA0_TCI_MASK) >> \ + RX_TPA_START_CMP_METADATA0_SFT) + +struct rx_tpa_end_cmp { + __le32 rx_tpa_end_cmp_len_flags_type; + #define RX_TPA_END_CMP_TYPE (0x3f << 0) + #define RX_TPA_END_CMP_FLAGS (0x3ff << 6) + #define RX_TPA_END_CMP_FLAGS_SHIFT 6 + #define RX_TPA_END_CMP_FLAGS_PLACEMENT (0x7 << 7) + #define RX_TPA_END_CMP_FLAGS_PLACEMENT_SHIFT 7 + #define RX_TPA_END_CMP_FLAGS_PLACEMENT_JUMBO (0x1 << 7) + #define RX_TPA_END_CMP_FLAGS_PLACEMENT_HDS (0x2 << 7) + #define RX_TPA_END_CMP_FLAGS_PLACEMENT_GRO_JUMBO (0x5 << 7) + #define RX_TPA_END_CMP_FLAGS_PLACEMENT_GRO_HDS (0x6 << 7) + #define RX_TPA_END_CMP_FLAGS_RSS_VALID (0x1 << 10) + #define RX_TPA_END_CMP_FLAGS_ITYPES (0xf << 12) + #define RX_TPA_END_CMP_FLAGS_ITYPES_SHIFT 12 + #define RX_TPA_END_CMP_FLAGS_ITYPE_TCP (0x2 << 12) + #define RX_TPA_END_CMP_LEN (0xffff << 16) + #define RX_TPA_END_CMP_LEN_SHIFT 16 + + u32 rx_tpa_end_cmp_opaque; + __le32 rx_tpa_end_cmp_misc_v1; + #define RX_TPA_END_CMP_V1 (0x1 << 0) + #define RX_TPA_END_CMP_AGG_BUFS (0x3f << 1) + #define RX_TPA_END_CMP_AGG_BUFS_SHIFT 1 + #define RX_TPA_END_CMP_TPA_SEGS (0xff << 8) + #define RX_TPA_END_CMP_TPA_SEGS_SHIFT 8 + #define RX_TPA_END_CMP_PAYLOAD_OFFSET (0xff << 16) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT 16 + #define RX_TPA_END_CMP_AGG_ID (0xffff << 16) + #define RX_TPA_END_CMP_AGG_ID_SHIFT 16 + + __le32 rx_tpa_end_cmp_tsdelta; + #define RX_TPA_END_GRO_TS (0x1 << 31) +}; + +#define TPA_END_AGG_ID(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_AGG_ID) >> RX_TPA_END_CMP_AGG_ID_SHIFT) + +#define TPA_END_TPA_SEGS(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_TPA_SEGS) >> RX_TPA_END_CMP_TPA_SEGS_SHIFT) + +#define RX_TPA_END_CMP_FLAGS_PLACEMENT_ANY_GRO \ + cpu_to_le32(RX_TPA_END_CMP_FLAGS_PLACEMENT_GRO_JUMBO & \ + RX_TPA_END_CMP_FLAGS_PLACEMENT_GRO_HDS) + +#define TPA_END_GRO(rx_tpa_end) \ + ((rx_tpa_end)->rx_tpa_end_cmp_len_flags_type & \ + RX_TPA_END_CMP_FLAGS_PLACEMENT_ANY_GRO) + +#define TPA_END_GRO_TS(rx_tpa_end) \ + (!!((rx_tpa_end)->rx_tpa_end_cmp_tsdelta & \ + cpu_to_le32(RX_TPA_END_GRO_TS))) + +struct rx_tpa_end_cmp_ext { + __le32 rx_tpa_end_cmp_dup_acks; + #define RX_TPA_END_CMP_TPA_DUP_ACKS (0xf << 0) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_P5 (0xff << 16) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT_P5 16 + #define RX_TPA_END_CMP_AGG_BUFS_P5 (0xff << 24) + #define RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5 24 + + __le32 rx_tpa_end_cmp_seg_len; + #define RX_TPA_END_CMP_TPA_SEG_LEN (0xffff << 0) + + __le32 rx_tpa_end_cmp_errors_v2; + #define RX_TPA_END_CMP_V2 (0x1 << 0) + #define RX_TPA_END_CMP_ERRORS (0x3 << 1) + #define RX_TPA_END_CMP_ERRORS_P5 (0x7 << 1) + #define RX_TPA_END_CMPL_ERRORS_SHIFT 1 + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_NOT_ON_CHIP (0x2 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_RSV_ERROR (0x4 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_FLUSH (0x5 << 1) + + u32 rx_tpa_end_cmp_start_opaque; +}; + +#define TPA_END_ERRORS(rx_tpa_end_ext) \ + ((rx_tpa_end_ext)->rx_tpa_end_cmp_errors_v2 & \ + cpu_to_le32(RX_TPA_END_CMP_ERRORS)) + +#define TPA_END_PAYLOAD_OFF(rx_tpa_end_ext) \ + ((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) & \ + RX_TPA_END_CMP_PAYLOAD_OFFSET_P5) >> \ + RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT_P5) + +#define TPA_END_AGG_BUFS(rx_tpa_end_ext) \ + ((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) & \ + RX_TPA_END_CMP_AGG_BUFS_P5) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5) + +#define EVENT_DATA1_RESET_NOTIFY_FATAL(data1) \ + (((data1) & \ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK) ==\ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL) + +#define EVENT_DATA1_RESET_NOTIFY_FW_ACTIVATION(data1) \ + (((data1) & \ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK) ==\ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION) + +#define EVENT_DATA2_RESET_NOTIFY_FW_STATUS_CODE(data2) \ + ((data2) & \ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_MASK) + +#define EVENT_DATA1_RECOVERY_MASTER_FUNC(data1) \ + (!!((data1) & \ + ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC)) + +#define EVENT_DATA1_RECOVERY_ENABLED(data1) \ + (!!((data1) & \ + ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED)) + +#define BNGE_EVENT_ERROR_REPORT_TYPE(data1) \ + (((data1) & \ + ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK) >>\ + ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT) + +#define BNGE_EVENT_INVALID_SIGNAL_DATA(data2) \ + (((data2) & \ + ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK) >>\ + ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT) + +struct nqe_cn { + __le16 type; + #define NQ_CN_TYPE_MASK 0x3fUL + #define NQ_CN_TYPE_SFT 0 + #define NQ_CN_TYPE_CQ_NOTIFICATION 0x30UL + #define NQ_CN_TYPE_LAST NQ_CN_TYPE_CQ_NOTIFICATION + #define NQ_CN_TOGGLE_MASK 0xc0UL + #define NQ_CN_TOGGLE_SFT 6 + __le16 reserved16; + __le32 cq_handle_low; + __le32 v; + #define NQ_CN_V 0x1UL + __le32 cq_handle_high; +}; + +#define NQE_CN_TYPE(type) ((type) & NQ_CN_TYPE_MASK) +#define NQE_CN_TOGGLE(type) (((type) & NQ_CN_TOGGLE_MASK) >> \ + NQ_CN_TOGGLE_SFT) + struct bnge_cp_ring_info { struct bnge_napi *bnapi; dma_addr_t *desc_mapping; @@ -297,6 +717,10 @@ struct bnge_cp_ring_info { u8 cp_idx; u32 cp_raw_cons; struct bnge_db_info cp_db; + u8 had_work_done:1; + u8 has_more_work:1; + u8 had_nqe_notify:1; + u8 toggle; }; struct bnge_nq_ring_info { @@ -308,9 +732,11 @@ struct bnge_nq_ring_info { struct bnge_db_info nq_db; struct bnge_stats_mem stats; + struct bnge_sw_stats *sw_stats; u32 hw_stats_ctx_id; + u8 has_more_work:1; - int cp_ring_count; + u16 cp_ring_count; struct bnge_cp_ring_info *cp_ring_arr; }; @@ -336,6 +762,9 @@ struct bnge_rx_ring_info { dma_addr_t rx_desc_mapping[MAX_RX_PAGES]; dma_addr_t rx_agg_desc_mapping[MAX_RX_AGG_PAGES]; + struct bnge_tpa_info *rx_tpa; + struct bnge_tpa_idx_map *rx_tpa_idx_map; + struct bnge_ring_struct rx_ring_struct; struct bnge_ring_struct rx_agg_ring_struct; struct page_pool *page_pool; @@ -373,6 +802,12 @@ struct bnge_napi { struct bnge_nq_ring_info nq_ring; struct bnge_rx_ring_info *rx_ring; struct bnge_tx_ring_info *tx_ring[BNGE_MAX_TXR_PER_NAPI]; + u8 events; +#define BNGE_RX_EVENT 1 +#define BNGE_AGG_EVENT 2 +#define BNGE_TX_EVENT 4 +#define BNGE_REDIRECT_EVENT 8 +#define BNGE_TX_CMP_EVENT 0x10 }; #define INVALID_STATS_CTX_ID -1 @@ -451,4 +886,16 @@ struct bnge_l2_filter { u16 bnge_cp_ring_for_rx(struct bnge_rx_ring_info *rxr); u16 bnge_cp_ring_for_tx(struct bnge_tx_ring_info *txr); void bnge_fill_hw_rss_tbl(struct bnge_net *bn, struct bnge_vnic_info *vnic); +int bnge_alloc_rx_data(struct bnge_net *bn, struct bnge_rx_ring_info *rxr, + u16 prod, gfp_t gfp); +u16 bnge_find_next_agg_idx(struct bnge_rx_ring_info *rxr, u16 idx); +u8 *__bnge_alloc_rx_frag(struct bnge_net *bn, dma_addr_t *mapping, + struct bnge_rx_ring_info *rxr, gfp_t gfp); +int bnge_alloc_rx_netmem(struct bnge_net *bn, struct bnge_rx_ring_info *rxr, + u16 prod, gfp_t gfp); +void bnge_get_ring_err_stats(struct bnge_net *bn, + struct bnge_total_ring_err_stats *stats); +void bnge_copy_hw_masks(u64 *mask_arr, __le64 *hw_mask_arr, int count); +void bnge_timer(struct timer_list *t); +void bnge_sp_task(struct work_struct *work); #endif /* _BNGE_NETDEV_H_ */ diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_txrx.c b/drivers/net/ethernet/broadcom/bnge/bnge_txrx.c new file mode 100644 index 0000000000000..3417cfef92bd4 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnge/bnge_txrx.c @@ -0,0 +1,1604 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2025 Broadcom. + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bnge.h" +#include "bnge_hwrm.h" +#include "bnge_hwrm_lib.h" +#include "bnge_netdev.h" +#include "bnge_rmem.h" +#include "bnge_txrx.h" + +irqreturn_t bnge_msix(int irq, void *dev_instance) +{ + struct bnge_napi *bnapi = dev_instance; + struct bnge_net *bn = bnapi->bn; + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + u32 cons = RING_CMP(bn, nqr->nq_raw_cons); + + prefetch(&nqr->desc_ring[CP_RING(cons)][CP_IDX(cons)]); + napi_schedule(&bnapi->napi); + return IRQ_HANDLED; +} + +static struct rx_agg_cmp *bnge_get_tpa_agg(struct bnge_net *bn, + struct bnge_rx_ring_info *rxr, + u16 agg_id, u16 curr) +{ + struct bnge_tpa_info *tpa_info = &rxr->rx_tpa[agg_id]; + + return &tpa_info->agg_arr[curr]; +} + +static struct rx_agg_cmp *bnge_get_agg(struct bnge_net *bn, + struct bnge_cp_ring_info *cpr, + u16 cp_cons, u16 curr) +{ + struct rx_agg_cmp *agg; + + cp_cons = RING_CMP(bn, ADV_RAW_CMP(cp_cons, curr)); + agg = (struct rx_agg_cmp *) + &cpr->desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + return agg; +} + +static void bnge_reuse_rx_agg_bufs(struct bnge_cp_ring_info *cpr, u16 idx, + u16 start, u32 agg_bufs, bool tpa) +{ + struct bnge_napi *bnapi = cpr->bnapi; + struct bnge_rx_ring_info *rxr = bnapi->rx_ring; + u16 sw_prod = rxr->rx_sw_agg_prod; + struct bnge_net *bn = bnapi->bn; + u16 prod = rxr->rx_agg_prod; + u32 i; + + for (i = 0; i < agg_bufs; i++) { + struct bnge_sw_rx_agg_bd *cons_rx_buf, *prod_rx_buf; + struct rx_agg_cmp *agg; + struct rx_bd *prod_bd; + netmem_ref netmem; + u16 cons; + + if (tpa) + agg = bnge_get_tpa_agg(bn, rxr, idx, start + i); + else + agg = bnge_get_agg(bn, cpr, idx, start + i); + cons = agg->rx_agg_cmp_opaque; + __clear_bit(cons, rxr->rx_agg_bmap); + + if (unlikely(test_bit(sw_prod, rxr->rx_agg_bmap))) + sw_prod = bnge_find_next_agg_idx(rxr, sw_prod); + + __set_bit(sw_prod, rxr->rx_agg_bmap); + prod_rx_buf = &rxr->rx_agg_buf_ring[sw_prod]; + cons_rx_buf = &rxr->rx_agg_buf_ring[cons]; + + /* It is possible for sw_prod to be equal to cons, so + * set cons_rx_buf->netmem to 0 first. + */ + netmem = cons_rx_buf->netmem; + cons_rx_buf->netmem = 0; + prod_rx_buf->netmem = netmem; + + prod_rx_buf->mapping = cons_rx_buf->mapping; + + prod_bd = &rxr->rx_agg_desc_ring[RX_AGG_RING(bn, prod)] + [RX_IDX(prod)]; + + prod_bd->rx_bd_haddr = cpu_to_le64(cons_rx_buf->mapping); + prod_bd->rx_bd_opaque = sw_prod; + + prod = NEXT_RX_AGG(prod); + sw_prod = RING_RX_AGG(bn, NEXT_RX_AGG(sw_prod)); + } + rxr->rx_agg_prod = prod; + rxr->rx_sw_agg_prod = sw_prod; +} + +static int bnge_agg_bufs_valid(struct bnge_net *bn, + struct bnge_cp_ring_info *cpr, + u8 agg_bufs, u32 *raw_cons) +{ + struct rx_agg_cmp *agg; + u16 last; + + *raw_cons = ADV_RAW_CMP(*raw_cons, agg_bufs); + last = RING_CMP(bn, *raw_cons); + agg = (struct rx_agg_cmp *) + &cpr->desc_ring[CP_RING(last)][CP_IDX(last)]; + return RX_AGG_CMP_VALID(agg, *raw_cons); +} + +static int bnge_discard_rx(struct bnge_net *bn, struct bnge_cp_ring_info *cpr, + u32 *raw_cons, void *cmp) +{ + u32 tmp_raw_cons = *raw_cons; + struct rx_cmp *rxcmp = cmp; + u8 cmp_type, agg_bufs = 0; + + cmp_type = RX_CMP_TYPE(rxcmp); + + if (cmp_type == CMP_TYPE_RX_L2_CMP) { + agg_bufs = (le32_to_cpu(rxcmp->rx_cmp_misc_v1) & + RX_CMP_AGG_BUFS) >> + RX_CMP_AGG_BUFS_SHIFT; + } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { + return 0; + } + + if (agg_bufs) { + if (!bnge_agg_bufs_valid(bn, cpr, agg_bufs, &tmp_raw_cons)) + return -EBUSY; + } + *raw_cons = tmp_raw_cons; + return 0; +} + +static u32 __bnge_rx_agg_netmems(struct bnge_net *bn, + struct bnge_cp_ring_info *cpr, + u16 idx, u32 agg_bufs, bool tpa, + struct sk_buff *skb) +{ + struct bnge_napi *bnapi = cpr->bnapi; + struct skb_shared_info *shinfo; + struct bnge_rx_ring_info *rxr; + u32 i, total_frag_len = 0; + u16 prod; + + rxr = bnapi->rx_ring; + prod = rxr->rx_agg_prod; + shinfo = skb_shinfo(skb); + + for (i = 0; i < agg_bufs; i++) { + struct bnge_sw_rx_agg_bd *cons_rx_buf; + struct rx_agg_cmp *agg; + u16 cons, frag_len; + netmem_ref netmem; + + if (tpa) + agg = bnge_get_tpa_agg(bn, rxr, idx, i); + else + agg = bnge_get_agg(bn, cpr, idx, i); + cons = agg->rx_agg_cmp_opaque; + frag_len = (le32_to_cpu(agg->rx_agg_cmp_len_flags_type) & + RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; + + cons_rx_buf = &rxr->rx_agg_buf_ring[cons]; + skb_add_rx_frag_netmem(skb, i, cons_rx_buf->netmem, 0, + frag_len, BNGE_RX_PAGE_SIZE); + __clear_bit(cons, rxr->rx_agg_bmap); + + /* It is possible for bnge_alloc_rx_netmem() to allocate + * a sw_prod index that equals the cons index, so we + * need to clear the cons entry now. + */ + netmem = cons_rx_buf->netmem; + cons_rx_buf->netmem = 0; + + if (bnge_alloc_rx_netmem(bn, rxr, prod, GFP_ATOMIC) != 0) { + skb->len -= frag_len; + skb->data_len -= frag_len; + skb->truesize -= BNGE_RX_PAGE_SIZE; + + --shinfo->nr_frags; + cons_rx_buf->netmem = netmem; + + /* Update prod since possibly some netmems have been + * allocated already. + */ + rxr->rx_agg_prod = prod; + bnge_reuse_rx_agg_bufs(cpr, idx, i, agg_bufs - i, tpa); + return 0; + } + + page_pool_dma_sync_netmem_for_cpu(rxr->page_pool, netmem, 0, + BNGE_RX_PAGE_SIZE); + + total_frag_len += frag_len; + prod = NEXT_RX_AGG(prod); + } + rxr->rx_agg_prod = prod; + return total_frag_len; +} + +static struct sk_buff *bnge_rx_agg_netmems_skb(struct bnge_net *bn, + struct bnge_cp_ring_info *cpr, + struct sk_buff *skb, u16 idx, + u32 agg_bufs, bool tpa) +{ + u32 total_frag_len = 0; + + total_frag_len = __bnge_rx_agg_netmems(bn, cpr, idx, agg_bufs, + tpa, skb); + if (!total_frag_len) { + skb_mark_for_recycle(skb); + dev_kfree_skb(skb); + return NULL; + } + + return skb; +} + +static void bnge_sched_reset_rxr(struct bnge_net *bn, + struct bnge_rx_ring_info *rxr) +{ + rxr->rx_next_cons = 0xffff; +} + +static u16 bnge_tpa_alloc_agg_idx(struct bnge_rx_ring_info *rxr, u16 agg_id) +{ + struct bnge_tpa_idx_map *map = rxr->rx_tpa_idx_map; + u16 idx = agg_id & MAX_TPA_MASK; + + if (test_bit(idx, map->agg_idx_bmap)) + idx = find_first_zero_bit(map->agg_idx_bmap, + BNGE_AGG_IDX_BMAP_SIZE); + __set_bit(idx, map->agg_idx_bmap); + map->agg_id_tbl[agg_id] = idx; + return idx; +} + +static void bnge_free_agg_idx(struct bnge_rx_ring_info *rxr, u16 idx) +{ + struct bnge_tpa_idx_map *map = rxr->rx_tpa_idx_map; + + __clear_bit(idx, map->agg_idx_bmap); +} + +static u16 bnge_lookup_agg_idx(struct bnge_rx_ring_info *rxr, u16 agg_id) +{ + struct bnge_tpa_idx_map *map = rxr->rx_tpa_idx_map; + + return map->agg_id_tbl[agg_id]; +} + +static void bnge_tpa_metadata(struct bnge_tpa_info *tpa_info, + struct rx_tpa_start_cmp *tpa_start, + struct rx_tpa_start_cmp_ext *tpa_start1) +{ + tpa_info->cfa_code_valid = 1; + tpa_info->cfa_code = TPA_START_CFA_CODE(tpa_start1); + tpa_info->vlan_valid = 0; + if (tpa_info->flags2 & RX_CMP_FLAGS2_META_FORMAT_VLAN) { + tpa_info->vlan_valid = 1; + tpa_info->metadata = + le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata); + } +} + +static void bnge_tpa_metadata_v2(struct bnge_tpa_info *tpa_info, + struct rx_tpa_start_cmp *tpa_start, + struct rx_tpa_start_cmp_ext *tpa_start1) +{ + tpa_info->vlan_valid = 0; + if (TPA_START_VLAN_VALID(tpa_start)) { + u32 tpid_sel = TPA_START_VLAN_TPID_SEL(tpa_start); + u32 vlan_proto = ETH_P_8021Q; + + tpa_info->vlan_valid = 1; + if (tpid_sel == RX_TPA_START_METADATA1_TPID_8021AD) + vlan_proto = ETH_P_8021AD; + tpa_info->metadata = vlan_proto << 16 | + TPA_START_METADATA0_TCI(tpa_start1); + } +} + +static void bnge_tpa_start(struct bnge_net *bn, struct bnge_rx_ring_info *rxr, + u8 cmp_type, struct rx_tpa_start_cmp *tpa_start, + struct rx_tpa_start_cmp_ext *tpa_start1) +{ + struct bnge_sw_rx_bd *cons_rx_buf, *prod_rx_buf; + struct bnge_tpa_info *tpa_info; + u16 cons, prod, agg_id; + struct rx_bd *prod_bd; + dma_addr_t mapping; + + agg_id = TPA_START_AGG_ID(tpa_start); + agg_id = bnge_tpa_alloc_agg_idx(rxr, agg_id); + cons = tpa_start->rx_tpa_start_cmp_opaque; + prod = rxr->rx_prod; + cons_rx_buf = &rxr->rx_buf_ring[cons]; + prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bn, prod)]; + tpa_info = &rxr->rx_tpa[agg_id]; + + if (unlikely(cons != rxr->rx_next_cons || + TPA_START_ERROR(tpa_start))) { + netdev_warn(bn->netdev, "TPA cons %x, expected cons %x, error code %x\n", + cons, rxr->rx_next_cons, + TPA_START_ERROR_CODE(tpa_start1)); + bnge_sched_reset_rxr(bn, rxr); + return; + } + prod_rx_buf->data = tpa_info->data; + prod_rx_buf->data_ptr = tpa_info->data_ptr; + + mapping = tpa_info->mapping; + prod_rx_buf->mapping = mapping; + + prod_bd = &rxr->rx_desc_ring[RX_RING(bn, prod)][RX_IDX(prod)]; + + prod_bd->rx_bd_haddr = cpu_to_le64(mapping); + + tpa_info->data = cons_rx_buf->data; + tpa_info->data_ptr = cons_rx_buf->data_ptr; + cons_rx_buf->data = NULL; + tpa_info->mapping = cons_rx_buf->mapping; + + tpa_info->len = + le32_to_cpu(tpa_start->rx_tpa_start_cmp_len_flags_type) >> + RX_TPA_START_CMP_LEN_SHIFT; + if (likely(TPA_START_HASH_VALID(tpa_start))) { + tpa_info->hash_type = PKT_HASH_TYPE_L4; + tpa_info->gso_type = SKB_GSO_TCPV4; + if (TPA_START_IS_IPV6(tpa_start1)) + tpa_info->gso_type = SKB_GSO_TCPV6; + tpa_info->rss_hash = + le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash); + } else { + tpa_info->hash_type = PKT_HASH_TYPE_NONE; + tpa_info->gso_type = 0; + netif_warn(bn, rx_err, bn->netdev, "TPA packet without valid hash\n"); + } + tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2); + tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info); + if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) + bnge_tpa_metadata(tpa_info, tpa_start, tpa_start1); + else + bnge_tpa_metadata_v2(tpa_info, tpa_start, tpa_start1); + tpa_info->agg_count = 0; + + rxr->rx_prod = NEXT_RX(prod); + cons = RING_RX(bn, NEXT_RX(cons)); + rxr->rx_next_cons = RING_RX(bn, NEXT_RX(cons)); + cons_rx_buf = &rxr->rx_buf_ring[cons]; + + bnge_reuse_rx_data(rxr, cons, cons_rx_buf->data); + rxr->rx_prod = NEXT_RX(rxr->rx_prod); + cons_rx_buf->data = NULL; +} + +static void bnge_abort_tpa(struct bnge_cp_ring_info *cpr, u16 idx, u32 agg_bufs) +{ + if (agg_bufs) + bnge_reuse_rx_agg_bufs(cpr, idx, 0, agg_bufs, true); +} + +static void bnge_tpa_agg(struct bnge_net *bn, struct bnge_rx_ring_info *rxr, + struct rx_agg_cmp *rx_agg) +{ + u16 agg_id = TPA_AGG_AGG_ID(rx_agg); + struct bnge_tpa_info *tpa_info; + + agg_id = bnge_lookup_agg_idx(rxr, agg_id); + tpa_info = &rxr->rx_tpa[agg_id]; + BUG_ON(tpa_info->agg_count >= MAX_SKB_FRAGS); + tpa_info->agg_arr[tpa_info->agg_count++] = *rx_agg; +} + +void bnge_reuse_rx_data(struct bnge_rx_ring_info *rxr, u16 cons, void *data) +{ + struct bnge_sw_rx_bd *cons_rx_buf, *prod_rx_buf; + struct bnge_net *bn = rxr->bnapi->bn; + struct rx_bd *cons_bd, *prod_bd; + u16 prod = rxr->rx_prod; + + prod_rx_buf = &rxr->rx_buf_ring[RING_RX(bn, prod)]; + cons_rx_buf = &rxr->rx_buf_ring[cons]; + + prod_rx_buf->data = data; + prod_rx_buf->data_ptr = cons_rx_buf->data_ptr; + + prod_rx_buf->mapping = cons_rx_buf->mapping; + + prod_bd = &rxr->rx_desc_ring[RX_RING(bn, prod)][RX_IDX(prod)]; + cons_bd = &rxr->rx_desc_ring[RX_RING(bn, cons)][RX_IDX(cons)]; + + prod_bd->rx_bd_haddr = cons_bd->rx_bd_haddr; +} + +static void bnge_deliver_skb(struct bnge_net *bn, struct bnge_napi *bnapi, + struct sk_buff *skb) +{ + skb_mark_for_recycle(skb); + skb_record_rx_queue(skb, bnapi->index); + napi_gro_receive(&bnapi->napi, skb); +} + +static struct sk_buff *bnge_copy_skb(struct bnge_napi *bnapi, u8 *data, + unsigned int len, dma_addr_t mapping) +{ + struct bnge_net *bn = bnapi->bn; + struct bnge_dev *bd = bn->bd; + struct sk_buff *skb; + + skb = napi_alloc_skb(&bnapi->napi, len); + if (!skb) + return NULL; + + dma_sync_single_for_cpu(bd->dev, mapping, bn->rx_copybreak, + bn->rx_dir); + + memcpy(skb->data - NET_IP_ALIGN, data - NET_IP_ALIGN, + len + NET_IP_ALIGN); + + dma_sync_single_for_device(bd->dev, mapping, bn->rx_copybreak, + bn->rx_dir); + + skb_put(skb, len); + + return skb; +} + +#ifdef CONFIG_INET +static void bnge_gro_tunnel(struct sk_buff *skb, __be16 ip_proto) +{ + struct udphdr *uh = NULL; + + if (ip_proto == htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + if (iph->protocol == IPPROTO_UDP) + uh = (struct udphdr *)(iph + 1); + } else { + struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; + + if (iph->nexthdr == IPPROTO_UDP) + uh = (struct udphdr *)(iph + 1); + } + if (uh) { + if (uh->check) + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; + } +} + +static struct sk_buff *bnge_gro_func(struct bnge_tpa_info *tpa_info, + int payload_off, int tcp_ts, + struct sk_buff *skb) +{ + u16 outer_ip_off, inner_ip_off, inner_mac_off; + u32 hdr_info = tpa_info->hdr_info; + int iphdr_len, nw_off; + + inner_ip_off = BNGE_TPA_INNER_L3_OFF(hdr_info); + inner_mac_off = BNGE_TPA_INNER_L2_OFF(hdr_info); + outer_ip_off = BNGE_TPA_OUTER_L3_OFF(hdr_info); + + nw_off = inner_ip_off - ETH_HLEN; + skb_set_network_header(skb, nw_off); + iphdr_len = (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) ? + sizeof(struct ipv6hdr) : sizeof(struct iphdr); + skb_set_transport_header(skb, nw_off + iphdr_len); + + if (inner_mac_off) { /* tunnel */ + __be16 proto = *((__be16 *)(skb->data + outer_ip_off - + ETH_HLEN - 2)); + + bnge_gro_tunnel(skb, proto); + } + + return skb; +} + +static inline struct sk_buff *bnge_gro_skb(struct bnge_net *bn, + struct bnge_tpa_info *tpa_info, + struct rx_tpa_end_cmp *tpa_end, + struct rx_tpa_end_cmp_ext *tpa_end1, + struct sk_buff *skb) +{ + int payload_off; + u16 segs; + + segs = TPA_END_TPA_SEGS(tpa_end); + if (segs == 1) + return skb; + + NAPI_GRO_CB(skb)->count = segs; + skb_shinfo(skb)->gso_size = + le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len); + skb_shinfo(skb)->gso_type = tpa_info->gso_type; + payload_off = TPA_END_PAYLOAD_OFF(tpa_end1); + skb = bnge_gro_func(tpa_info, payload_off, + TPA_END_GRO_TS(tpa_end), skb); + if (likely(skb)) + tcp_gro_complete(skb); + + return skb; +} +#endif + +static inline struct sk_buff *bnge_tpa_end(struct bnge_net *bn, + struct bnge_cp_ring_info *cpr, + u32 *raw_cons, + struct rx_tpa_end_cmp *tpa_end, + struct rx_tpa_end_cmp_ext *tpa_end1, + u8 *event) +{ + struct bnge_napi *bnapi = cpr->bnapi; + struct bnge_rx_ring_info *rxr = bnapi->rx_ring; + struct net_device *dev = bn->netdev; + struct bnge_tpa_info *tpa_info; + u8 *data_ptr, agg_bufs; + struct sk_buff *skb; + u16 idx = 0, agg_id; + dma_addr_t mapping; + unsigned int len; + void *data; + bool gro; + + agg_id = TPA_END_AGG_ID(tpa_end); + agg_id = bnge_lookup_agg_idx(rxr, agg_id); + agg_bufs = TPA_END_AGG_BUFS(tpa_end1); + tpa_info = &rxr->rx_tpa[agg_id]; + if (unlikely(agg_bufs != tpa_info->agg_count)) { + netdev_warn(bn->netdev, "TPA end agg_buf %d != expected agg_bufs %d\n", + agg_bufs, tpa_info->agg_count); + agg_bufs = tpa_info->agg_count; + } + tpa_info->agg_count = 0; + *event |= BNGE_AGG_EVENT; + bnge_free_agg_idx(rxr, agg_id); + idx = agg_id; + gro = !!(bn->priv_flags & BNGE_NET_EN_GRO); + data = tpa_info->data; + data_ptr = tpa_info->data_ptr; + prefetch(data_ptr); + len = tpa_info->len; + mapping = tpa_info->mapping; + + if (unlikely(agg_bufs > MAX_SKB_FRAGS || TPA_END_ERRORS(tpa_end1))) { + bnge_abort_tpa(cpr, idx, agg_bufs); + if (agg_bufs > MAX_SKB_FRAGS) + netdev_warn(bn->netdev, "TPA frags %d exceeded MAX_SKB_FRAGS %d\n", + agg_bufs, (int)MAX_SKB_FRAGS); + return NULL; + } + + if (len <= bn->rx_copybreak) { + skb = bnge_copy_skb(bnapi, data_ptr, len, mapping); + if (!skb) { + bnge_abort_tpa(cpr, idx, agg_bufs); + return NULL; + } + } else { + u8 *new_data; + dma_addr_t new_mapping; + + new_data = __bnge_alloc_rx_frag(bn, &new_mapping, rxr, + GFP_ATOMIC); + if (!new_data) { + bnge_abort_tpa(cpr, idx, agg_bufs); + return NULL; + } + + tpa_info->data = new_data; + tpa_info->data_ptr = new_data + bn->rx_offset; + tpa_info->mapping = new_mapping; + + skb = napi_build_skb(data, bn->rx_buf_size); + dma_sync_single_for_cpu(bn->bd->dev, mapping, + bn->rx_buf_use_size, bn->rx_dir); + + if (!skb) { + page_pool_free_va(rxr->head_pool, data, true); + bnge_abort_tpa(cpr, idx, agg_bufs); + return NULL; + } + skb_mark_for_recycle(skb); + skb_reserve(skb, bn->rx_offset); + skb_put(skb, len); + } + + if (agg_bufs) { + skb = bnge_rx_agg_netmems_skb(bn, cpr, skb, idx, agg_bufs, + true); + /* Page reuse already handled by bnge_rx_agg_netmems_skb(). */ + if (!skb) + return NULL; + } + + skb->protocol = eth_type_trans(skb, dev); + + if (tpa_info->hash_type != PKT_HASH_TYPE_NONE) + skb_set_hash(skb, tpa_info->rss_hash, tpa_info->hash_type); + + if (tpa_info->vlan_valid && + (dev->features & BNGE_HW_FEATURE_VLAN_ALL_RX)) { + __be16 vlan_proto = htons(tpa_info->metadata >> + RX_CMP_FLAGS2_METADATA_TPID_SFT); + u16 vtag = tpa_info->metadata & RX_CMP_FLAGS2_METADATA_TCI_MASK; + + if (eth_type_vlan(vlan_proto)) { + __vlan_hwaccel_put_tag(skb, vlan_proto, vtag); + } else { + dev_kfree_skb(skb); + return NULL; + } + } + + skb_checksum_none_assert(skb); + if (likely(tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_L4_CS_CALC)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = + (tpa_info->flags2 & RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3; + } + +#ifdef CONFIG_INET + if (gro) + skb = bnge_gro_skb(bn, tpa_info, tpa_end, tpa_end1, skb); +#endif + + return skb; +} + +static enum pkt_hash_types bnge_rss_ext_op(struct bnge_net *bn, + struct rx_cmp *rxcmp) +{ + u8 ext_op = RX_CMP_V3_HASH_TYPE(bn->bd, rxcmp); + + switch (ext_op) { + case EXT_OP_INNER_4: + case EXT_OP_OUTER_4: + case EXT_OP_INNFL_3: + case EXT_OP_OUTFL_3: + return PKT_HASH_TYPE_L4; + default: + return PKT_HASH_TYPE_L3; + } +} + +static struct sk_buff *bnge_rx_vlan(struct sk_buff *skb, u8 cmp_type, + struct rx_cmp *rxcmp, + struct rx_cmp_ext *rxcmp1) +{ + __be16 vlan_proto; + u16 vtag; + + if (cmp_type == CMP_TYPE_RX_L2_CMP) { + __le32 flags2 = rxcmp1->rx_cmp_flags2; + u32 meta_data; + + if (!(flags2 & cpu_to_le32(RX_CMP_FLAGS2_META_FORMAT_VLAN))) + return skb; + + meta_data = le32_to_cpu(rxcmp1->rx_cmp_meta_data); + vtag = meta_data & RX_CMP_FLAGS2_METADATA_TCI_MASK; + vlan_proto = + htons(meta_data >> RX_CMP_FLAGS2_METADATA_TPID_SFT); + if (eth_type_vlan(vlan_proto)) + __vlan_hwaccel_put_tag(skb, vlan_proto, vtag); + else + goto vlan_err; + } else if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) { + if (RX_CMP_VLAN_VALID(rxcmp)) { + u32 tpid_sel = RX_CMP_VLAN_TPID_SEL(rxcmp); + + if (tpid_sel == RX_CMP_METADATA1_TPID_8021Q) + vlan_proto = htons(ETH_P_8021Q); + else if (tpid_sel == RX_CMP_METADATA1_TPID_8021AD) + vlan_proto = htons(ETH_P_8021AD); + else + goto vlan_err; + vtag = RX_CMP_METADATA0_TCI(rxcmp1); + __vlan_hwaccel_put_tag(skb, vlan_proto, vtag); + } + } + return skb; +vlan_err: + skb_mark_for_recycle(skb); + dev_kfree_skb(skb); + return NULL; +} + +static struct sk_buff *bnge_rx_skb(struct bnge_net *bn, + struct bnge_rx_ring_info *rxr, u16 cons, + void *data, u8 *data_ptr, + dma_addr_t dma_addr, + unsigned int offset_and_len) +{ + struct bnge_dev *bd = bn->bd; + u16 prod = rxr->rx_prod; + struct sk_buff *skb; + int err; + + err = bnge_alloc_rx_data(bn, rxr, prod, GFP_ATOMIC); + if (unlikely(err)) { + bnge_reuse_rx_data(rxr, cons, data); + return NULL; + } + + skb = napi_build_skb(data, bn->rx_buf_size); + dma_sync_single_for_cpu(bd->dev, dma_addr, bn->rx_buf_use_size, + bn->rx_dir); + if (!skb) { + page_pool_free_va(rxr->head_pool, data, true); + return NULL; + } + + skb_mark_for_recycle(skb); + skb_reserve(skb, bn->rx_offset); + skb_put(skb, offset_and_len & 0xffff); + return skb; +} + +/* returns the following: + * 1 - 1 packet successfully received + * 0 - successful TPA_START, packet not completed yet + * -EBUSY - completion ring does not have all the agg buffers yet + * -ENOMEM - packet aborted due to out of memory + * -EIO - packet aborted due to hw error indicated in BD + */ +static int bnge_rx_pkt(struct bnge_net *bn, struct bnge_cp_ring_info *cpr, + u32 *raw_cons, u8 *event) +{ + struct bnge_napi *bnapi = cpr->bnapi; + struct bnge_rx_ring_info *rxr; + u32 tmp_raw_cons, flags, misc; + struct bnge_sw_rx_bd *rx_buf; + struct rx_cmp_ext *rxcmp1; + u16 cons, prod, cp_cons; + u8 *data_ptr, cmp_type; + struct net_device *dev; + struct rx_cmp *rxcmp; + dma_addr_t dma_addr; + struct sk_buff *skb; + unsigned int len; + u8 agg_bufs; + void *data; + int rc = 0; + + dev = bn->netdev; + rxr = bnapi->rx_ring; + + tmp_raw_cons = *raw_cons; + cp_cons = RING_CMP(bn, tmp_raw_cons); + rxcmp = (struct rx_cmp *) + &cpr->desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + cmp_type = RX_CMP_TYPE(rxcmp); + + if (cmp_type == CMP_TYPE_RX_TPA_AGG_CMP) { + bnge_tpa_agg(bn, rxr, (struct rx_agg_cmp *)rxcmp); + goto next_rx_no_prod_no_len; + } + + tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons); + cp_cons = RING_CMP(bn, tmp_raw_cons); + rxcmp1 = (struct rx_cmp_ext *) + &cpr->desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons)) + return -EBUSY; + + /* The valid test of the entry must be done first before + * reading any further. + */ + dma_rmb(); + prod = rxr->rx_prod; + + if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP || + cmp_type == CMP_TYPE_RX_L2_TPA_START_V3_CMP) { + bnge_tpa_start(bn, rxr, cmp_type, + (struct rx_tpa_start_cmp *)rxcmp, + (struct rx_tpa_start_cmp_ext *)rxcmp1); + + *event |= BNGE_RX_EVENT; + goto next_rx_no_prod_no_len; + + } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { + skb = bnge_tpa_end(bn, cpr, &tmp_raw_cons, + (struct rx_tpa_end_cmp *)rxcmp, + (struct rx_tpa_end_cmp_ext *)rxcmp1, event); + + if (IS_ERR(skb)) + return -EBUSY; + + rc = -ENOMEM; + if (likely(skb)) { + bnge_deliver_skb(bn, bnapi, skb); + rc = 1; + } + *event |= BNGE_RX_EVENT; + goto next_rx_no_prod_no_len; + } + + cons = rxcmp->rx_cmp_opaque; + if (unlikely(cons != rxr->rx_next_cons)) { + int rc1 = bnge_discard_rx(bn, cpr, &tmp_raw_cons, rxcmp); + + /* 0xffff is forced error, don't print it */ + if (rxr->rx_next_cons != 0xffff) + netdev_warn(bn->netdev, "RX cons %x != expected cons %x\n", + cons, rxr->rx_next_cons); + bnge_sched_reset_rxr(bn, rxr); + if (rc1) + return rc1; + goto next_rx_no_prod_no_len; + } + rx_buf = &rxr->rx_buf_ring[cons]; + data = rx_buf->data; + data_ptr = rx_buf->data_ptr; + prefetch(data_ptr); + + misc = le32_to_cpu(rxcmp->rx_cmp_misc_v1); + agg_bufs = (misc & RX_CMP_AGG_BUFS) >> RX_CMP_AGG_BUFS_SHIFT; + + if (agg_bufs) { + if (!bnge_agg_bufs_valid(bn, cpr, agg_bufs, &tmp_raw_cons)) + return -EBUSY; + + cp_cons = NEXT_CMP(bn, cp_cons); + *event |= BNGE_AGG_EVENT; + } + *event |= BNGE_RX_EVENT; + + rx_buf->data = NULL; + if (rxcmp1->rx_cmp_cfa_code_errors_v2 & RX_CMP_L2_ERRORS) { + bnge_reuse_rx_data(rxr, cons, data); + if (agg_bufs) + bnge_reuse_rx_agg_bufs(cpr, cp_cons, 0, agg_bufs, + false); + rc = -EIO; + goto next_rx_no_len; + } + + flags = le32_to_cpu(rxcmp->rx_cmp_len_flags_type); + len = flags >> RX_CMP_LEN_SHIFT; + dma_addr = rx_buf->mapping; + + if (len <= bn->rx_copybreak) { + skb = bnge_copy_skb(bnapi, data_ptr, len, dma_addr); + bnge_reuse_rx_data(rxr, cons, data); + if (!skb) { + if (agg_bufs) + bnge_reuse_rx_agg_bufs(cpr, cp_cons, 0, + agg_bufs, false); + goto oom_next_rx; + } + } else { + u32 payload; + + if (rx_buf->data_ptr == data_ptr) + payload = misc & RX_CMP_PAYLOAD_OFFSET; + else + payload = 0; + skb = bnge_rx_skb(bn, rxr, cons, data, data_ptr, dma_addr, + payload | len); + if (!skb) + goto oom_next_rx; + } + + if (agg_bufs) { + skb = bnge_rx_agg_netmems_skb(bn, cpr, skb, cp_cons, + agg_bufs, false); + if (!skb) + goto oom_next_rx; + } + + if (RX_CMP_HASH_VALID(rxcmp)) { + enum pkt_hash_types type; + + if (cmp_type == CMP_TYPE_RX_L2_V3_CMP) { + type = bnge_rss_ext_op(bn, rxcmp); + } else { +#define RX_CMP_ITYPES(rxcmp) \ + (le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_FLAGS_ITYPES_MASK) + + u32 itypes = RX_CMP_ITYPES(rxcmp); + + if (itypes == RX_CMP_FLAGS_ITYPE_TCP || + itypes == RX_CMP_FLAGS_ITYPE_UDP) + type = PKT_HASH_TYPE_L4; + else + type = PKT_HASH_TYPE_L3; + } + skb_set_hash(skb, le32_to_cpu(rxcmp->rx_cmp_rss_hash), type); + } + +#define RX_CMP_CFA_CODE(rxcmpl1) \ + ((le32_to_cpu((rxcmpl1)->rx_cmp_cfa_code_errors_v2) & \ + RX_CMPL_CFA_CODE_MASK) >> RX_CMPL_CFA_CODE_SFT) + + skb->protocol = eth_type_trans(skb, dev); + + if (skb->dev->features & BNGE_HW_FEATURE_VLAN_ALL_RX) { + skb = bnge_rx_vlan(skb, cmp_type, rxcmp, rxcmp1); + if (!skb) + goto next_rx; + } + + skb_checksum_none_assert(skb); + if (RX_CMP_L4_CS_OK(rxcmp1)) { + if (dev->features & NETIF_F_RXCSUM) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = RX_CMP_ENCAP(rxcmp1); + } + } + + bnge_deliver_skb(bn, bnapi, skb); + rc = 1; + +next_rx: + /* Update Stats */ +next_rx_no_len: + rxr->rx_prod = NEXT_RX(prod); + rxr->rx_next_cons = RING_RX(bn, NEXT_RX(cons)); + +next_rx_no_prod_no_len: + *raw_cons = tmp_raw_cons; + return rc; + +oom_next_rx: + rc = -ENOMEM; + goto next_rx; +} + +/* In netpoll mode, if we are using a combined completion ring, we need to + * discard the rx packets and recycle the buffers. + */ +static int bnge_force_rx_discard(struct bnge_net *bn, + struct bnge_cp_ring_info *cpr, + u32 *raw_cons, u8 *event) +{ + u32 tmp_raw_cons = *raw_cons; + struct rx_cmp_ext *rxcmp1; + struct rx_cmp *rxcmp; + u16 cp_cons; + u8 cmp_type; + int rc; + + cp_cons = RING_CMP(bn, tmp_raw_cons); + rxcmp = (struct rx_cmp *) + &cpr->desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons); + cp_cons = RING_CMP(bn, tmp_raw_cons); + rxcmp1 = (struct rx_cmp_ext *) + &cpr->desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + + if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons)) + return -EBUSY; + + /* The valid test of the entry must be done first before + * reading any further. + */ + dma_rmb(); + cmp_type = RX_CMP_TYPE(rxcmp); + if (cmp_type == CMP_TYPE_RX_L2_CMP || + cmp_type == CMP_TYPE_RX_L2_V3_CMP) { + rxcmp1->rx_cmp_cfa_code_errors_v2 |= + cpu_to_le32(RX_CMPL_ERRORS_CRC_ERROR); + } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { + struct rx_tpa_end_cmp_ext *tpa_end1; + + tpa_end1 = (struct rx_tpa_end_cmp_ext *)rxcmp1; + tpa_end1->rx_tpa_end_cmp_errors_v2 |= + cpu_to_le32(RX_TPA_END_CMP_ERRORS); + } + rc = bnge_rx_pkt(bn, cpr, raw_cons, event); + return rc; +} + +static bool __bnge_tx_int(struct bnge_net *bn, struct bnge_tx_ring_info *txr, + int budget) +{ + struct netdev_queue *txq = + netdev_get_tx_queue(bn->netdev, txr->txq_index); + u16 hw_cons = txr->tx_hw_cons; + struct bnge_dev *bd = bn->bd; + unsigned int tx_bytes = 0; + unsigned int tx_pkts = 0; + u16 cons = txr->tx_cons; + skb_frag_t *frag; + bool rc = false; + + while (RING_TX(bn, cons) != hw_cons) { + struct bnge_sw_tx_bd *tx_buf; + struct sk_buff *skb; + int j, last; + + tx_buf = &txr->tx_buf_ring[RING_TX(bn, cons)]; + skb = tx_buf->skb; + + cons = NEXT_TX(cons); + tx_pkts++; + tx_bytes += skb->len; + tx_buf->skb = NULL; + + dma_unmap_single(bd->dev, dma_unmap_addr(tx_buf, mapping), + skb_headlen(skb), DMA_TO_DEVICE); + last = tx_buf->nr_frags; + + for (j = 0; j < last; j++) { + frag = &skb_shinfo(skb)->frags[j]; + cons = NEXT_TX(cons); + tx_buf = &txr->tx_buf_ring[RING_TX(bn, cons)]; + netmem_dma_unmap_page_attrs(bd->dev, + dma_unmap_addr(tx_buf, + mapping), + skb_frag_size(frag), + DMA_TO_DEVICE, 0); + } + + cons = NEXT_TX(cons); + + dev_consume_skb_any(skb); + } + + WRITE_ONCE(txr->tx_cons, cons); + + __netif_txq_completed_wake(txq, tx_pkts, tx_bytes, + bnge_tx_avail(bn, txr), bn->tx_wake_thresh, + (READ_ONCE(txr->dev_state) == + BNGE_DEV_STATE_CLOSING)); + + return rc; +} + +static void bnge_tx_int(struct bnge_net *bn, struct bnge_napi *bnapi, + int budget) +{ + struct bnge_tx_ring_info *txr; + bool more = false; + int i; + + bnge_for_each_napi_tx(i, bnapi, txr) { + if (txr->tx_hw_cons != RING_TX(bn, txr->tx_cons)) + more |= __bnge_tx_int(bn, txr, budget); + } + if (!more) + bnapi->events &= ~BNGE_TX_CMP_EVENT; +} + +static void __bnge_poll_work_done(struct bnge_net *bn, struct bnge_napi *bnapi, + int budget) +{ + if ((bnapi->events & BNGE_TX_CMP_EVENT)) + bnge_tx_int(bn, bnapi, budget); + if ((bnapi->events & BNGE_RX_EVENT)) { + struct bnge_rx_ring_info *rxr = bnapi->rx_ring; + + bnge_db_write(bn->bd, &rxr->rx_db, rxr->rx_prod); + bnapi->events &= ~BNGE_RX_EVENT; + } + if (bnapi->events & BNGE_AGG_EVENT) { + struct bnge_rx_ring_info *rxr = bnapi->rx_ring; + + bnge_db_write(bn->bd, &rxr->rx_agg_db, rxr->rx_agg_prod); + bnapi->events &= ~BNGE_AGG_EVENT; + } +} + +static void +bnge_hwrm_update_token(struct bnge_dev *bd, u16 seq_id, + enum bnge_hwrm_wait_state state) +{ + struct bnge_hwrm_wait_token *token; + + rcu_read_lock(); + hlist_for_each_entry_rcu(token, &bd->hwrm_pending_list, node) { + if (token->seq_id == seq_id) { + WRITE_ONCE(token->state, state); + rcu_read_unlock(); + return; + } + } + rcu_read_unlock(); + dev_err(bd->dev, "Invalid hwrm seq id %d\n", seq_id); +} + +static int bnge_hwrm_handler(struct bnge_dev *bd, struct tx_cmp *txcmp) +{ + struct hwrm_cmpl *h_cmpl = (struct hwrm_cmpl *)txcmp; + u16 cmpl_type = TX_CMP_TYPE(txcmp), seq_id; + + switch (cmpl_type) { + case CMPL_BASE_TYPE_HWRM_DONE: + seq_id = le16_to_cpu(h_cmpl->sequence_id); + bnge_hwrm_update_token(bd, seq_id, BNGE_HWRM_COMPLETE); + break; + + case CMPL_BASE_TYPE_HWRM_ASYNC_EVENT: + default: + break; + } + + return 0; +} + +static int __bnge_poll_work(struct bnge_net *bn, struct bnge_cp_ring_info *cpr, + int budget) +{ + struct bnge_napi *bnapi = cpr->bnapi; + u32 raw_cons = cpr->cp_raw_cons; + struct tx_cmp *txcmp; + int rx_pkts = 0; + u8 event = 0; + u32 cons; + + cpr->has_more_work = 0; + cpr->had_work_done = 1; + while (1) { + u8 cmp_type; + int rc; + + cons = RING_CMP(bn, raw_cons); + txcmp = &cpr->desc_ring[CP_RING(cons)][CP_IDX(cons)]; + + if (!TX_CMP_VALID(txcmp, raw_cons)) + break; + + /* The valid test of the entry must be done first before + * reading any further. + */ + dma_rmb(); + cmp_type = TX_CMP_TYPE(txcmp); + if (cmp_type == CMP_TYPE_TX_L2_CMP || + cmp_type == CMP_TYPE_TX_L2_COAL_CMP) { + u32 opaque = txcmp->tx_cmp_opaque; + struct bnge_tx_ring_info *txr; + u16 tx_freed; + + txr = bnapi->tx_ring[TX_OPAQUE_RING(opaque)]; + event |= BNGE_TX_CMP_EVENT; + if (cmp_type == CMP_TYPE_TX_L2_COAL_CMP) + txr->tx_hw_cons = TX_CMP_SQ_CONS_IDX(txcmp); + else + txr->tx_hw_cons = TX_OPAQUE_PROD(bn, opaque); + tx_freed = ((txr->tx_hw_cons - txr->tx_cons) & + bn->tx_ring_mask); + /* return full budget so NAPI will complete. */ + if (unlikely(tx_freed >= bn->tx_wake_thresh)) { + rx_pkts = budget; + raw_cons = NEXT_RAW_CMP(raw_cons); + if (budget) + cpr->has_more_work = 1; + break; + } + } else if (cmp_type >= CMP_TYPE_RX_L2_CMP && + cmp_type <= CMP_TYPE_RX_L2_TPA_START_V3_CMP) { + if (likely(budget)) + rc = bnge_rx_pkt(bn, cpr, &raw_cons, &event); + else + rc = bnge_force_rx_discard(bn, cpr, &raw_cons, + &event); + if (likely(rc >= 0)) + rx_pkts += rc; + /* Increment rx_pkts when rc is -ENOMEM to count towards + * the NAPI budget. Otherwise, we may potentially loop + * here forever if we consistently cannot allocate + * buffers. + */ + else if (rc == -ENOMEM && budget) + rx_pkts++; + else if (rc == -EBUSY) /* partial completion */ + break; + } else if (unlikely(cmp_type == CMPL_BASE_TYPE_HWRM_DONE || + cmp_type == CMPL_BASE_TYPE_HWRM_FWD_REQ || + cmp_type == CMPL_BA_TY_HWRM_ASY_EVT)) { + bnge_hwrm_handler(bn->bd, txcmp); + } + raw_cons = NEXT_RAW_CMP(raw_cons); + + if (rx_pkts && rx_pkts == budget) { + cpr->has_more_work = 1; + break; + } + } + + cpr->cp_raw_cons = raw_cons; + bnapi->events |= event; + return rx_pkts; +} + +static void __bnge_poll_cqs_done(struct bnge_net *bn, struct bnge_napi *bnapi, + u64 dbr_type, int budget) +{ + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + int i; + + for (i = 0; i < nqr->cp_ring_count; i++) { + struct bnge_cp_ring_info *cpr = &nqr->cp_ring_arr[i]; + struct bnge_db_info *db; + + if (cpr->had_work_done) { + u32 tgl = 0; + + if (dbr_type == DBR_TYPE_CQ_ARMALL) { + cpr->had_nqe_notify = 0; + tgl = cpr->toggle; + } + db = &cpr->cp_db; + bnge_writeq(bn->bd, + db->db_key64 | dbr_type | DB_TOGGLE(tgl) | + DB_RING_IDX(db, cpr->cp_raw_cons), + db->doorbell); + cpr->had_work_done = 0; + } + } + __bnge_poll_work_done(bn, bnapi, budget); +} + +static int __bnge_poll_cqs(struct bnge_net *bn, struct bnge_napi *bnapi, + int budget) +{ + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + int i, work_done = 0; + + for (i = 0; i < nqr->cp_ring_count; i++) { + struct bnge_cp_ring_info *cpr = &nqr->cp_ring_arr[i]; + + if (cpr->had_nqe_notify) { + work_done += __bnge_poll_work(bn, cpr, + budget - work_done); + nqr->has_more_work |= cpr->has_more_work; + } + } + return work_done; +} + +int bnge_napi_poll(struct napi_struct *napi, int budget) +{ + struct bnge_napi *bnapi = container_of(napi, struct bnge_napi, napi); + struct bnge_nq_ring_info *nqr = &bnapi->nq_ring; + u32 raw_cons = nqr->nq_raw_cons; + struct bnge_net *bn = bnapi->bn; + struct bnge_dev *bd = bn->bd; + struct nqe_cn *nqcmp; + int work_done = 0; + u32 cons; + + if (nqr->has_more_work) { + nqr->has_more_work = 0; + work_done = __bnge_poll_cqs(bn, bnapi, budget); + } + + while (1) { + u16 type; + + cons = RING_CMP(bn, raw_cons); + nqcmp = &nqr->desc_ring[CP_RING(cons)][CP_IDX(cons)]; + + if (!NQ_CMP_VALID(nqcmp, raw_cons)) { + if (nqr->has_more_work) + break; + + __bnge_poll_cqs_done(bn, bnapi, DBR_TYPE_CQ_ARMALL, + budget); + nqr->nq_raw_cons = raw_cons; + if (napi_complete_done(napi, work_done)) + BNGE_DB_NQ_ARM(&nqr->nq_db, nqr->nq_raw_cons); + goto poll_done; + } + + /* The valid test of the entry must be done first before + * reading any further. + */ + dma_rmb(); + + type = le16_to_cpu(nqcmp->type); + if (NQE_CN_TYPE(type) == NQ_CN_TYPE_CQ_NOTIFICATION) { + u32 idx = le32_to_cpu(nqcmp->cq_handle_low); + u32 cq_type = BNGE_NQ_HDL_TYPE(idx); + struct bnge_cp_ring_info *cpr; + + /* No more budget for RX work */ + if (budget && work_done >= budget && + cq_type == BNGE_NQ_HDL_TYPE_RX) + break; + + idx = BNGE_NQ_HDL_IDX(idx); + cpr = &nqr->cp_ring_arr[idx]; + cpr->had_nqe_notify = 1; + cpr->toggle = NQE_CN_TOGGLE(type); + work_done += __bnge_poll_work(bn, cpr, + budget - work_done); + nqr->has_more_work |= cpr->has_more_work; + } else { + bnge_hwrm_handler(bn->bd, (struct tx_cmp *)nqcmp); + } + raw_cons = NEXT_RAW_CMP(raw_cons); + } + __bnge_poll_cqs_done(bn, bnapi, DBR_TYPE_CQ, budget); + if (raw_cons != nqr->nq_raw_cons) { + nqr->nq_raw_cons = raw_cons; + BNGE_DB_NQ(&nqr->nq_db, raw_cons); + } +poll_done: + return work_done; +} + +static u16 bnge_xmit_get_cfa_action(struct sk_buff *skb) +{ + struct metadata_dst *md_dst = skb_metadata_dst(skb); + + if (!md_dst || md_dst->type != METADATA_HW_PORT_MUX) + return 0; + + return md_dst->u.port_info.port_id; +} + +static const u16 bnge_lhint_arr[] = { + TX_BD_FLAGS_LHINT_512_AND_SMALLER, + TX_BD_FLAGS_LHINT_512_TO_1023, + TX_BD_FLAGS_LHINT_1024_TO_2047, + TX_BD_FLAGS_LHINT_1024_TO_2047, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, + TX_BD_FLAGS_LHINT_2048_AND_LARGER, +}; + +static void bnge_txr_db_kick(struct bnge_net *bn, struct bnge_tx_ring_info *txr, + u16 prod) +{ + /* Sync BD data before updating doorbell */ + wmb(); + bnge_db_write(bn->bd, &txr->tx_db, prod); + txr->kick_pending = 0; +} + +netdev_tx_t bnge_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + u32 len, free_size, vlan_tag_flags, cfa_action, flags; + struct bnge_net *bn = netdev_priv(dev); + struct bnge_tx_ring_info *txr; + struct bnge_dev *bd = bn->bd; + unsigned int length, pad = 0; + struct bnge_sw_tx_bd *tx_buf; + struct tx_bd *txbd, *txbd0; + struct netdev_queue *txq; + struct tx_bd_ext *txbd1; + u16 prod, last_frag; + dma_addr_t mapping; + __le32 lflags = 0; + skb_frag_t *frag; + int i; + + i = skb_get_queue_mapping(skb); + if (unlikely(i >= bd->tx_nr_rings)) { + dev_kfree_skb_any(skb); + dev_core_stats_tx_dropped_inc(dev); + return NETDEV_TX_OK; + } + + txq = netdev_get_tx_queue(dev, i); + txr = &bn->tx_ring[bn->tx_ring_map[i]]; + prod = txr->tx_prod; + +#if (MAX_SKB_FRAGS > TX_MAX_FRAGS) + if (skb_shinfo(skb)->nr_frags > TX_MAX_FRAGS) { + netdev_warn_once(dev, "SKB has too many (%d) fragments, max supported is %d. SKB will be linearized.\n", + skb_shinfo(skb)->nr_frags, TX_MAX_FRAGS); + if (skb_linearize(skb)) { + dev_kfree_skb_any(skb); + dev_core_stats_tx_dropped_inc(dev); + return NETDEV_TX_OK; + } + } +#endif + free_size = bnge_tx_avail(bn, txr); + if (unlikely(free_size < skb_shinfo(skb)->nr_frags + 2)) { + /* We must have raced with NAPI cleanup */ + if (net_ratelimit() && txr->kick_pending) + netif_warn(bn, tx_err, dev, + "bnxt: ring busy w/ flush pending!\n"); + if (!netif_txq_try_stop(txq, bnge_tx_avail(bn, txr), + bn->tx_wake_thresh)) + return NETDEV_TX_BUSY; + } + + if (unlikely(ipv6_hopopt_jumbo_remove(skb))) + goto tx_free; + + length = skb->len; + len = skb_headlen(skb); + last_frag = skb_shinfo(skb)->nr_frags; + + txbd = &txr->tx_desc_ring[TX_RING(bn, prod)][TX_IDX(prod)]; + + tx_buf = &txr->tx_buf_ring[RING_TX(bn, prod)]; + tx_buf->skb = skb; + tx_buf->nr_frags = last_frag; + + vlan_tag_flags = 0; + cfa_action = bnge_xmit_get_cfa_action(skb); + if (skb_vlan_tag_present(skb)) { + vlan_tag_flags = TX_BD_CFA_META_KEY_VLAN | + skb_vlan_tag_get(skb); + /* Currently supports 8021Q, 8021AD vlan offloads + * QINQ1, QINQ2, QINQ3 vlan headers are deprecated + */ + if (skb->vlan_proto == htons(ETH_P_8021Q)) + vlan_tag_flags |= 1 << TX_BD_CFA_META_TPID_SHIFT; + } + + if (unlikely(skb->no_fcs)) + lflags |= cpu_to_le32(TX_BD_FLAGS_NO_CRC); + + if (length < BNGE_MIN_PKT_SIZE) { + pad = BNGE_MIN_PKT_SIZE - length; + if (skb_pad(skb, pad)) + /* SKB already freed. */ + goto tx_kick_pending; + length = BNGE_MIN_PKT_SIZE; + } + + mapping = dma_map_single(bd->dev, skb->data, len, DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(bd->dev, mapping))) + goto tx_free; + + dma_unmap_addr_set(tx_buf, mapping, mapping); + flags = (len << TX_BD_LEN_SHIFT) | TX_BD_TYPE_LONG_TX_BD | + TX_BD_CNT(last_frag + 2); + + txbd->tx_bd_haddr = cpu_to_le64(mapping); + txbd->tx_bd_opaque = SET_TX_OPAQUE(bn, txr, prod, 2 + last_frag); + + prod = NEXT_TX(prod); + txbd1 = (struct tx_bd_ext *) + &txr->tx_desc_ring[TX_RING(bn, prod)][TX_IDX(prod)]; + + txbd1->tx_bd_hsize_lflags = lflags; + if (skb_is_gso(skb)) { + bool udp_gso = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4); + u32 hdr_len; + + if (skb->encapsulation) { + if (udp_gso) + hdr_len = skb_inner_transport_offset(skb) + + sizeof(struct udphdr); + else + hdr_len = skb_inner_tcp_all_headers(skb); + } else if (udp_gso) { + hdr_len = skb_transport_offset(skb) + + sizeof(struct udphdr); + } else { + hdr_len = skb_tcp_all_headers(skb); + } + + txbd1->tx_bd_hsize_lflags |= cpu_to_le32(TX_BD_FLAGS_LSO | + TX_BD_FLAGS_T_IPID | + (hdr_len << (TX_BD_HSIZE_SHIFT - 1))); + length = skb_shinfo(skb)->gso_size; + txbd1->tx_bd_mss = cpu_to_le32(length); + length += hdr_len; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + txbd1->tx_bd_hsize_lflags |= + cpu_to_le32(TX_BD_FLAGS_TCP_UDP_CHKSUM); + txbd1->tx_bd_mss = 0; + } + + length >>= 9; + if (unlikely(length >= ARRAY_SIZE(bnge_lhint_arr))) { + dev_warn_ratelimited(bd->dev, "Dropped oversize %d bytes TX packet.\n", + skb->len); + i = 0; + goto tx_dma_error; + } + flags |= bnge_lhint_arr[length]; + txbd->tx_bd_len_flags_type = cpu_to_le32(flags); + + txbd1->tx_bd_cfa_meta = cpu_to_le32(vlan_tag_flags); + txbd1->tx_bd_cfa_action = + cpu_to_le32(cfa_action << TX_BD_CFA_ACTION_SHIFT); + txbd0 = txbd; + for (i = 0; i < last_frag; i++) { + frag = &skb_shinfo(skb)->frags[i]; + + prod = NEXT_TX(prod); + txbd = &txr->tx_desc_ring[TX_RING(bn, prod)][TX_IDX(prod)]; + + len = skb_frag_size(frag); + mapping = skb_frag_dma_map(bd->dev, frag, 0, len, + DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(bd->dev, mapping))) + goto tx_dma_error; + + tx_buf = &txr->tx_buf_ring[RING_TX(bn, prod)]; + netmem_dma_unmap_addr_set(skb_frag_netmem(frag), tx_buf, + mapping, mapping); + + txbd->tx_bd_haddr = cpu_to_le64(mapping); + + flags = len << TX_BD_LEN_SHIFT; + txbd->tx_bd_len_flags_type = cpu_to_le32(flags); + } + + flags &= ~TX_BD_LEN; + txbd->tx_bd_len_flags_type = + cpu_to_le32(((len + pad) << TX_BD_LEN_SHIFT) | flags | + TX_BD_FLAGS_PACKET_END); + + netdev_tx_sent_queue(txq, skb->len); + + prod = NEXT_TX(prod); + WRITE_ONCE(txr->tx_prod, prod); + + if (!netdev_xmit_more() || netif_xmit_stopped(txq)) { + bnge_txr_db_kick(bn, txr, prod); + } else { + if (free_size >= bn->tx_wake_thresh) + txbd0->tx_bd_len_flags_type |= + cpu_to_le32(TX_BD_FLAGS_NO_CMPL); + txr->kick_pending = 1; + } + + if (unlikely(bnge_tx_avail(bn, txr) <= MAX_SKB_FRAGS + 1)) { + if (netdev_xmit_more()) { + txbd0->tx_bd_len_flags_type &= + cpu_to_le32(~TX_BD_FLAGS_NO_CMPL); + bnge_txr_db_kick(bn, txr, prod); + } + + netif_txq_try_stop(txq, bnge_tx_avail(bn, txr), + bn->tx_wake_thresh); + } + return NETDEV_TX_OK; + +tx_dma_error: + last_frag = i; + + /* start back at beginning and unmap skb */ + prod = txr->tx_prod; + tx_buf = &txr->tx_buf_ring[RING_TX(bn, prod)]; + dma_unmap_single(bd->dev, dma_unmap_addr(tx_buf, mapping), + skb_headlen(skb), DMA_TO_DEVICE); + prod = NEXT_TX(prod); + + /* unmap remaining mapped pages */ + for (i = 0; i < last_frag; i++) { + prod = NEXT_TX(prod); + tx_buf = &txr->tx_buf_ring[RING_TX(bn, prod)]; + frag = &skb_shinfo(skb)->frags[i]; + netmem_dma_unmap_page_attrs(bd->dev, + dma_unmap_addr(tx_buf, mapping), + skb_frag_size(frag), + DMA_TO_DEVICE, 0); + } + +tx_free: + dev_kfree_skb_any(skb); + +tx_kick_pending: + if (txr->kick_pending) + bnge_txr_db_kick(bn, txr, txr->tx_prod); + txr->tx_buf_ring[RING_TX(bn, txr->tx_prod)].skb = NULL; + dev_core_stats_tx_dropped_inc(dev); + return NETDEV_TX_OK; +} + diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_txrx.h b/drivers/net/ethernet/broadcom/bnge/bnge_txrx.h new file mode 100644 index 0000000000000..d2c9e6f2e7fc0 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnge/bnge_txrx.h @@ -0,0 +1,118 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Broadcom */ + +#ifndef _BNGE_TXRX_H_ +#define _BNGE_TXRX_H_ + +#include +#include "bnge_netdev.h" + +static inline u32 bnge_tx_avail(struct bnge_net *bn, + const struct bnge_tx_ring_info *txr) +{ + u32 used = READ_ONCE(txr->tx_prod) - READ_ONCE(txr->tx_cons); + + return bn->tx_ring_size - (used & bn->tx_ring_mask); +} + +static inline void bnge_writeq_relaxed(struct bnge_dev *bd, u64 val, + volatile void __iomem *addr) +{ +#if BITS_PER_LONG == 32 + spin_lock(&bd->db_lock); + lo_hi_writeq_relaxed(val, addr); + spin_unlock(&bd->db_lock); +#else + writeq_relaxed(val, addr); +#endif +} + +/* For TX and RX ring doorbells with no ordering guarantee*/ +static inline void bnge_db_write_relaxed(struct bnge_net *bn, + struct bnge_db_info *db, u32 idx) +{ + bnge_writeq_relaxed(bn->bd, db->db_key64 | DB_RING_IDX(db, idx), + db->doorbell); +} + +#define BNGE_MIN_PKT_SIZE 52 + +#define TX_OPAQUE_IDX_MASK 0x0000ffff +#define TX_OPAQUE_BDS_MASK 0x00ff0000 +#define TX_OPAQUE_BDS_SHIFT 16 +#define TX_OPAQUE_RING_MASK 0xff000000 +#define TX_OPAQUE_RING_SHIFT 24 + +#define SET_TX_OPAQUE(bn, txr, idx, bds) \ + (((txr)->tx_napi_idx << TX_OPAQUE_RING_SHIFT) | \ + ((bds) << TX_OPAQUE_BDS_SHIFT) | ((idx) & (bn)->tx_ring_mask)) + +#define TX_OPAQUE_IDX(opq) ((opq) & TX_OPAQUE_IDX_MASK) +#define TX_OPAQUE_RING(opq) (((opq) & TX_OPAQUE_RING_MASK) >> \ + TX_OPAQUE_RING_SHIFT) +#define TX_OPAQUE_BDS(opq) (((opq) & TX_OPAQUE_BDS_MASK) >> \ + TX_OPAQUE_BDS_SHIFT) +#define TX_OPAQUE_PROD(bn, opq) ((TX_OPAQUE_IDX(opq) + TX_OPAQUE_BDS(opq)) &\ + (bn)->tx_ring_mask) +#define TX_BD_CNT(n) (((n) << TX_BD_FLAGS_BD_CNT_SHIFT) & TX_BD_FLAGS_BD_CNT) + +#define TX_MAX_BD_CNT 32 + +#define TX_MAX_FRAGS (TX_MAX_BD_CNT - 2) + +/* Minimum TX BDs for a TX packet with MAX_SKB_FRAGS + 1. We need one extra + * BD because the first TX BD is always a long BD. + */ +#define BNGE_MIN_TX_DESC_CNT (MAX_SKB_FRAGS + 2) + +#define RX_RING(bn, x) (((x) & (bn)->rx_ring_mask) >> (BNGE_PAGE_SHIFT - 4)) +#define RX_AGG_RING(bn, x) (((x) & (bn)->rx_agg_ring_mask) >> \ + (BNGE_PAGE_SHIFT - 4)) +#define RX_IDX(x) ((x) & (RX_DESC_CNT - 1)) + +#define TX_RING(bn, x) (((x) & (bn)->tx_ring_mask) >> (BNGE_PAGE_SHIFT - 4)) +#define TX_IDX(x) ((x) & (TX_DESC_CNT - 1)) + +#define CP_RING(x) (((x) & ~(CP_DESC_CNT - 1)) >> (BNGE_PAGE_SHIFT - 4)) +#define CP_IDX(x) ((x) & (CP_DESC_CNT - 1)) + +#define TX_CMP_VALID(txcmp, raw_cons) \ + (!!((txcmp)->tx_cmp_errors_v & cpu_to_le32(TX_CMP_V)) == \ + !((raw_cons) & bn->cp_bit)) + +#define RX_CMP_VALID(rxcmp1, raw_cons) \ + (!!((rxcmp1)->rx_cmp_cfa_code_errors_v2 & cpu_to_le32(RX_CMP_V)) ==\ + !((raw_cons) & bn->cp_bit)) + +#define RX_AGG_CMP_VALID(agg, raw_cons) \ + (!!((agg)->rx_agg_cmp_v & cpu_to_le32(RX_AGG_CMP_V)) == \ + !((raw_cons) & bn->cp_bit)) + +#define NQ_CMP_VALID(nqcmp, raw_cons) \ + (!!((nqcmp)->v & cpu_to_le32(NQ_CN_V)) == !((raw_cons) & bn->cp_bit)) + +#define TX_CMP_TYPE(txcmp) \ + (le32_to_cpu((txcmp)->tx_cmp_flags_type) & CMP_TYPE) + +#define RX_CMP_TYPE(rxcmp) \ + (le32_to_cpu((rxcmp)->rx_cmp_len_flags_type) & RX_CMP_CMP_TYPE) + +#define RING_RX(bn, idx) ((idx) & (bn)->rx_ring_mask) +#define NEXT_RX(idx) ((idx) + 1) + +#define RING_RX_AGG(bn, idx) ((idx) & (bn)->rx_agg_ring_mask) +#define NEXT_RX_AGG(idx) ((idx) + 1) + +#define RING_TX(bn, idx) ((idx) & (bn)->tx_ring_mask) +#define NEXT_TX(idx) ((idx) + 1) + +#define ADV_RAW_CMP(idx, n) ((idx) + (n)) +#define NEXT_RAW_CMP(idx) ADV_RAW_CMP(idx, 1) +#define RING_CMP(bn, idx) ((idx) & (bn)->cp_ring_mask) +#define NEXT_CMP(bn, idx) RING_CMP(bn, ADV_RAW_CMP(idx, 1)) + +irqreturn_t bnge_msix(int irq, void *dev_instance); +netdev_tx_t bnge_start_xmit(struct sk_buff *skb, struct net_device *dev); +void bnge_reuse_rx_data(struct bnge_rx_ring_info *rxr, u16 cons, void *data); +int bnge_napi_poll(struct napi_struct *napi, int budget); +#endif /* _BNGE_TXRX_H_ */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c index fc8dec37a9e48..3d853eeb976f6 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c @@ -3355,19 +3355,11 @@ static int bnx2x_get_rxfh_fields(struct net_device *dev, return 0; } -static int bnx2x_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, - u32 *rules __always_unused) +static u32 bnx2x_get_rx_ring_count(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = BNX2X_NUM_ETH_QUEUES(bp); - return 0; - default: - DP(BNX2X_MSG_ETHTOOL, "Command parameters not supported\n"); - return -EOPNOTSUPP; - } + return BNX2X_NUM_ETH_QUEUES(bp); } static int bnx2x_set_rxfh_fields(struct net_device *dev, @@ -3674,7 +3666,7 @@ static const struct ethtool_ops bnx2x_ethtool_ops = { .get_strings = bnx2x_get_strings, .set_phys_id = bnx2x_set_phys_id, .get_ethtool_stats = bnx2x_get_ethtool_stats, - .get_rxnfc = bnx2x_get_rxnfc, + .get_rx_ring_count = bnx2x_get_rx_ring_count, .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size, .get_rxfh = bnx2x_get_rxfh, .set_rxfh = bnx2x_set_rxfh, @@ -3702,7 +3694,7 @@ static const struct ethtool_ops bnx2x_vf_ethtool_ops = { .get_sset_count = bnx2x_get_sset_count, .get_strings = bnx2x_get_strings, .get_ethtool_stats = bnx2x_get_ethtool_stats, - .get_rxnfc = bnx2x_get_rxnfc, + .get_rx_ring_count = bnx2x_get_rx_ring_count, .get_rxfh_indir_size = bnx2x_get_rxfh_indir_size, .get_rxfh = bnx2x_get_rxfh, .set_rxfh = bnx2x_set_rxfh, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c index 0abaa2bbe3577..a8a74f07bb547 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c @@ -952,7 +952,6 @@ static int bnxt_ptp_pps_init(struct bnxt *bp) snprintf(ptp_info->pin_config[i].name, sizeof(ptp_info->pin_config[i].name), "bnxt_pps%d", i); ptp_info->pin_config[i].index = i; - ptp_info->pin_config[i].chan = i; if (*pin_usg == BNXT_PPS_PIN_PPS_IN) ptp_info->pin_config[i].func = PTP_PF_EXTTS; else if (*pin_usg == BNXT_PPS_PIN_PPS_OUT) @@ -969,6 +968,8 @@ static int bnxt_ptp_pps_init(struct bnxt *bp) ptp_info->n_per_out = 1; ptp_info->pps = 1; ptp_info->verify = bnxt_ptp_verify; + ptp_info->supported_extts_flags = PTP_RISING_EDGE | PTP_STRICT_FLAGS; + ptp_info->supported_perout_flags = PTP_PEROUT_DUTY_CYCLE; return 0; } diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 98971ae4f87df..d99ef92feb82b 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -35,7 +35,6 @@ #include #include #include -#include #include @@ -3926,7 +3925,6 @@ MODULE_DEVICE_TABLE(of, bcmgenet_match); static int bcmgenet_probe(struct platform_device *pdev) { - struct bcmgenet_platform_data *pd = pdev->dev.platform_data; const struct bcmgenet_plat_data *pdata; struct bcmgenet_priv *priv; struct net_device *dev; @@ -4010,9 +4008,6 @@ static int bcmgenet_probe(struct platform_device *pdev) priv->version = pdata->version; priv->dma_max_burst_length = pdata->dma_max_burst_length; priv->flags = pdata->flags; - } else { - priv->version = pd->genet_version; - priv->dma_max_burst_length = DMA_MAX_BURST_LENGTH; } priv->clk = devm_clk_get_optional(&priv->pdev->dev, "enet"); @@ -4062,16 +4057,13 @@ static int bcmgenet_probe(struct platform_device *pdev) if (device_get_phy_mode(&pdev->dev) == PHY_INTERFACE_MODE_INTERNAL) bcmgenet_power_up(priv, GENET_POWER_PASSIVE); - if (pd && !IS_ERR_OR_NULL(pd->mac_address)) - eth_hw_addr_set(dev, pd->mac_address); - else - if (device_get_ethdev_address(&pdev->dev, dev)) - if (has_acpi_companion(&pdev->dev)) { - u8 addr[ETH_ALEN]; + if (device_get_ethdev_address(&pdev->dev, dev)) + if (has_acpi_companion(&pdev->dev)) { + u8 addr[ETH_ALEN]; - bcmgenet_get_hw_addr(priv, addr); - eth_hw_addr_set(dev, addr); - } + bcmgenet_get_hw_addr(priv, addr); + eth_hw_addr_set(dev, addr); + } if (!is_valid_ether_addr(dev->dev_addr)) { dev_warn(&pdev->dev, "using random Ethernet MAC\n"); diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c index 573e8b279e52f..38f854b94a799 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmmii.c +++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include "bcmgenet.h" @@ -436,23 +435,6 @@ static struct device_node *bcmgenet_mii_of_find_mdio(struct bcmgenet_priv *priv) return priv->mdio_dn; } -static void bcmgenet_mii_pdata_init(struct bcmgenet_priv *priv, - struct unimac_mdio_pdata *ppd) -{ - struct device *kdev = &priv->pdev->dev; - struct bcmgenet_platform_data *pd = kdev->platform_data; - - if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) { - /* - * Internal or external PHY with MDIO access - */ - if (pd->phy_address >= 0 && pd->phy_address < PHY_MAX_ADDR) - ppd->phy_mask = 1 << pd->phy_address; - else - ppd->phy_mask = 0; - } -} - static int bcmgenet_mii_wait(void *wait_func_data) { struct bcmgenet_priv *priv = wait_func_data; @@ -467,7 +449,6 @@ static int bcmgenet_mii_wait(void *wait_func_data) static int bcmgenet_mii_register(struct bcmgenet_priv *priv) { struct platform_device *pdev = priv->pdev; - struct bcmgenet_platform_data *pdata = pdev->dev.platform_data; struct device_node *dn = pdev->dev.of_node; struct unimac_mdio_pdata ppd; struct platform_device *ppdev; @@ -511,8 +492,6 @@ static int bcmgenet_mii_register(struct bcmgenet_priv *priv) ppdev->dev.parent = &pdev->dev; if (dn) ppdev->dev.of_node = bcmgenet_mii_of_find_mdio(priv); - else if (pdata) - bcmgenet_mii_pdata_init(priv, &ppd); else ppd.phy_mask = ~0; @@ -594,58 +573,6 @@ static int bcmgenet_mii_of_init(struct bcmgenet_priv *priv) return 0; } -static int bcmgenet_mii_pd_init(struct bcmgenet_priv *priv) -{ - struct device *kdev = &priv->pdev->dev; - struct bcmgenet_platform_data *pd = kdev->platform_data; - char phy_name[MII_BUS_ID_SIZE + 3]; - char mdio_bus_id[MII_BUS_ID_SIZE]; - struct phy_device *phydev; - - snprintf(mdio_bus_id, MII_BUS_ID_SIZE, "%s-%d", - UNIMAC_MDIO_DRV_NAME, priv->pdev->id); - - if (pd->phy_interface != PHY_INTERFACE_MODE_MOCA && pd->mdio_enabled) { - snprintf(phy_name, MII_BUS_ID_SIZE, PHY_ID_FMT, - mdio_bus_id, pd->phy_address); - - /* - * Internal or external PHY with MDIO access - */ - phydev = phy_attach(priv->dev, phy_name, pd->phy_interface); - if (IS_ERR(phydev)) { - dev_err(kdev, "failed to register PHY device\n"); - return PTR_ERR(phydev); - } - } else { - /* - * MoCA port or no MDIO access. - * Use fixed PHY to represent the link layer. - */ - struct fixed_phy_status fphy_status = { - .link = 1, - .speed = pd->phy_speed, - .duplex = pd->phy_duplex, - .pause = 0, - .asym_pause = 0, - }; - - phydev = fixed_phy_register(&fphy_status, NULL); - if (IS_ERR(phydev)) { - dev_err(kdev, "failed to register fixed PHY device\n"); - return PTR_ERR(phydev); - } - - /* Make sure we initialize MoCA PHYs with a link down */ - phydev->link = 0; - - } - - priv->phy_interface = pd->phy_interface; - - return 0; -} - static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) { struct device *kdev = &priv->pdev->dev; @@ -656,7 +583,7 @@ static int bcmgenet_mii_bus_init(struct bcmgenet_priv *priv) else if (has_acpi_companion(kdev)) return bcmgenet_phy_interface_init(priv); else - return bcmgenet_mii_pd_init(priv); + return -EINVAL; } int bcmgenet_mii_init(struct net_device *dev) diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index d78cafdb20949..e21f7c6a6de70 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -12719,29 +12719,17 @@ static int tg3_get_sset_count(struct net_device *dev, int sset) } } -static int tg3_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, - u32 *rules __always_unused) +static u32 tg3_get_rx_ring_count(struct net_device *dev) { struct tg3 *tp = netdev_priv(dev); if (!tg3_flag(tp, SUPPORT_MSIX)) - return -EOPNOTSUPP; + return 1; - switch (info->cmd) { - case ETHTOOL_GRXRINGS: - if (netif_running(tp->dev)) - info->data = tp->rxq_cnt; - else { - info->data = num_online_cpus(); - if (info->data > TG3_RSS_MAX_NUM_QS) - info->data = TG3_RSS_MAX_NUM_QS; - } + if (netif_running(tp->dev)) + return tp->rxq_cnt; - return 0; - - default: - return -EOPNOTSUPP; - } + return min_t(u32, netif_get_num_default_rss_queues(), tp->rxq_max); } static u32 tg3_get_rxfh_indir_size(struct net_device *dev) @@ -14268,7 +14256,7 @@ static const struct ethtool_ops tg3_ethtool_ops = { .get_coalesce = tg3_get_coalesce, .set_coalesce = tg3_set_coalesce, .get_sset_count = tg3_get_sset_count, - .get_rxnfc = tg3_get_rxnfc, + .get_rx_ring_count = tg3_get_rx_ring_count, .get_rxfh_indir_size = tg3_get_rxfh_indir_size, .get_rxfh = tg3_get_rxfh, .set_rxfh = tg3_set_rxfh, diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index 0830c48973aa0..87414a2ddf6e3 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -15,10 +15,6 @@ #include #include -#if defined(CONFIG_ARCH_DMA_ADDR_T_64BIT) || defined(CONFIG_MACB_USE_HWSTAMP) -#define MACB_EXT_DESC -#endif - #define MACB_GREGS_NBR 16 #define MACB_GREGS_VERSION 2 #define MACB_MAX_QUEUES 8 @@ -541,6 +537,8 @@ /* Bitfields in DCFG6. */ #define GEM_PBUF_LSO_OFFSET 27 #define GEM_PBUF_LSO_SIZE 1 +#define GEM_PBUF_RSC_OFFSET 26 +#define GEM_PBUF_RSC_SIZE 1 #define GEM_PBUF_CUTTHRU_OFFSET 25 #define GEM_PBUF_CUTTHRU_SIZE 1 #define GEM_DAW64_OFFSET 23 @@ -756,27 +754,31 @@ #define MACB_MAN_C45_CODE 2 /* Capability mask bits */ -#define MACB_CAPS_ISR_CLEAR_ON_WRITE 0x00000001 -#define MACB_CAPS_USRIO_HAS_CLKEN 0x00000002 -#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII 0x00000004 -#define MACB_CAPS_NO_GIGABIT_HALF 0x00000008 -#define MACB_CAPS_USRIO_DISABLED 0x00000010 -#define MACB_CAPS_JUMBO 0x00000020 -#define MACB_CAPS_GEM_HAS_PTP 0x00000040 -#define MACB_CAPS_BD_RD_PREFETCH 0x00000080 -#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 -#define MACB_CAPS_MIIONRGMII 0x00000200 -#define MACB_CAPS_NEED_TSUCLK 0x00000400 -#define MACB_CAPS_QUEUE_DISABLE 0x00000800 -#define MACB_CAPS_QBV 0x00001000 -#define MACB_CAPS_PCS 0x01000000 -#define MACB_CAPS_HIGH_SPEED 0x02000000 -#define MACB_CAPS_CLK_HW_CHG 0x04000000 -#define MACB_CAPS_MACB_IS_EMAC 0x08000000 -#define MACB_CAPS_FIFO_MODE 0x10000000 -#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 -#define MACB_CAPS_SG_DISABLED 0x40000000 -#define MACB_CAPS_MACB_IS_GEM 0x80000000 +#define MACB_CAPS_ISR_CLEAR_ON_WRITE BIT(0) +#define MACB_CAPS_USRIO_HAS_CLKEN BIT(1) +#define MACB_CAPS_USRIO_DEFAULT_IS_MII_GMII BIT(2) +#define MACB_CAPS_NO_GIGABIT_HALF BIT(3) +#define MACB_CAPS_USRIO_DISABLED BIT(4) +#define MACB_CAPS_JUMBO BIT(5) +#define MACB_CAPS_GEM_HAS_PTP BIT(6) +#define MACB_CAPS_BD_RD_PREFETCH BIT(7) +#define MACB_CAPS_NEEDS_RSTONUBR BIT(8) +#define MACB_CAPS_MIIONRGMII BIT(9) +#define MACB_CAPS_NEED_TSUCLK BIT(10) +#define MACB_CAPS_QUEUE_DISABLE BIT(11) +#define MACB_CAPS_QBV BIT(12) +#define MACB_CAPS_PCS BIT(13) +#define MACB_CAPS_HIGH_SPEED BIT(14) +#define MACB_CAPS_CLK_HW_CHG BIT(15) +#define MACB_CAPS_MACB_IS_EMAC BIT(16) +#define MACB_CAPS_FIFO_MODE BIT(17) +#define MACB_CAPS_GIGABIT_MODE_AVAILABLE BIT(18) +#define MACB_CAPS_SG_DISABLED BIT(19) +#define MACB_CAPS_MACB_IS_GEM BIT(20) +#define MACB_CAPS_DMA_64B BIT(21) +#define MACB_CAPS_DMA_PTP BIT(22) +#define MACB_CAPS_RSC BIT(23) +#define MACB_CAPS_NO_LSO BIT(24) /* LSO settings */ #define MACB_LSO_UFO_ENABLE 0x01 @@ -853,12 +855,6 @@ struct macb_dma_desc { u32 ctrl; }; -#ifdef MACB_EXT_DESC -#define HW_DMA_CAP_32B 0 -#define HW_DMA_CAP_64B (1 << 0) -#define HW_DMA_CAP_PTP (1 << 1) -#define HW_DMA_CAP_64B_PTP (HW_DMA_CAP_64B | HW_DMA_CAP_PTP) - struct macb_dma_desc_64 { u32 addrh; u32 resvd; @@ -868,7 +864,6 @@ struct macb_dma_desc_ptp { u32 ts_1; u32 ts_2; }; -#endif /* DMA descriptor bitfields */ #define MACB_RX_USED_OFFSET 0 @@ -1299,7 +1294,6 @@ struct macb { unsigned int tx_ring_size; unsigned int num_queues; - unsigned int queue_mask; struct macb_queue queues[MACB_MAX_QUEUES]; spinlock_t lock; @@ -1347,11 +1341,8 @@ struct macb { struct macb_ptp_info *ptp_info; /* macb-ptp interface */ - struct phy *sgmii_phy; /* for ZynqMP SGMII mode */ + struct phy *phy; -#ifdef MACB_EXT_DESC - uint8_t hw_dma_cap; -#endif spinlock_t tsu_clk_lock; /* gem tsu clock locking */ unsigned int tsu_rate; struct ptp_clock *ptp_clock; @@ -1443,6 +1434,18 @@ static inline u64 enst_max_hw_interval(u32 speed_mbps) ENST_TIME_GRANULARITY_NS * 1000, (speed_mbps)); } +static inline bool macb_dma64(struct macb *bp) +{ + return IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT) && + bp->caps & MACB_CAPS_DMA_64B; +} + +static inline bool macb_dma_ptp(struct macb *bp) +{ + return IS_ENABLED(CONFIG_MACB_USE_HWSTAMP) && + bp->caps & MACB_CAPS_DMA_PTP; +} + /** * struct macb_platform_data - platform data for MACB Ethernet used for PCI registration * @pclk: platform clock diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index ca2386b834737..e461f5072884e 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -6,36 +6,36 @@ */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include +#include #include +#include #include -#include -#include -#include -#include -#include -#include +#include +#include +#include +#include #include -#include #include +#include +#include +#include +#include +#include +#include #include -#include -#include -#include -#include #include #include #include -#include -#include -#include -#include #include +#include +#include #include #include #include -#include -#include +#include +#include +#include +#include #include #include "macb.h" @@ -121,56 +121,26 @@ struct sifive_fu540_macb_mgmt { */ static unsigned int macb_dma_desc_get_size(struct macb *bp) { -#ifdef MACB_EXT_DESC - unsigned int desc_size; + unsigned int desc_size = sizeof(struct macb_dma_desc); + + if (macb_dma64(bp)) + desc_size += sizeof(struct macb_dma_desc_64); + if (macb_dma_ptp(bp)) + desc_size += sizeof(struct macb_dma_desc_ptp); - switch (bp->hw_dma_cap) { - case HW_DMA_CAP_64B: - desc_size = sizeof(struct macb_dma_desc) - + sizeof(struct macb_dma_desc_64); - break; - case HW_DMA_CAP_PTP: - desc_size = sizeof(struct macb_dma_desc) - + sizeof(struct macb_dma_desc_ptp); - break; - case HW_DMA_CAP_64B_PTP: - desc_size = sizeof(struct macb_dma_desc) - + sizeof(struct macb_dma_desc_64) - + sizeof(struct macb_dma_desc_ptp); - break; - default: - desc_size = sizeof(struct macb_dma_desc); - } return desc_size; -#endif - return sizeof(struct macb_dma_desc); } static unsigned int macb_adj_dma_desc_idx(struct macb *bp, unsigned int desc_idx) { -#ifdef MACB_EXT_DESC - switch (bp->hw_dma_cap) { - case HW_DMA_CAP_64B: - case HW_DMA_CAP_PTP: - desc_idx <<= 1; - break; - case HW_DMA_CAP_64B_PTP: - desc_idx *= 3; - break; - default: - break; - } -#endif - return desc_idx; + return desc_idx * (1 + macb_dma64(bp) + macb_dma_ptp(bp)); } -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT static struct macb_dma_desc_64 *macb_64b_desc(struct macb *bp, struct macb_dma_desc *desc) { return (struct macb_dma_desc_64 *)((void *)desc + sizeof(struct macb_dma_desc)); } -#endif /* Ring buffer accessors */ static unsigned int macb_tx_ring_wrap(struct macb *bp, unsigned int index) @@ -357,7 +327,6 @@ static int macb_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum) status = MACB_BFEXT(DATA, macb_readl(bp, MAN)); mdio_read_exit: - pm_runtime_mark_last_busy(&bp->pdev->dev); pm_runtime_put_autosuspend(&bp->pdev->dev); mdio_pm_exit: return status; @@ -403,7 +372,6 @@ static int macb_mdio_read_c45(struct mii_bus *bus, int mii_id, int devad, status = MACB_BFEXT(DATA, macb_readl(bp, MAN)); mdio_read_exit: - pm_runtime_mark_last_busy(&bp->pdev->dev); pm_runtime_put_autosuspend(&bp->pdev->dev); mdio_pm_exit: return status; @@ -435,7 +403,6 @@ static int macb_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum, goto mdio_write_exit; mdio_write_exit: - pm_runtime_mark_last_busy(&bp->pdev->dev); pm_runtime_put_autosuspend(&bp->pdev->dev); mdio_pm_exit: return status; @@ -481,7 +448,6 @@ static int macb_mdio_write_c45(struct mii_bus *bus, int mii_id, goto mdio_write_exit; mdio_write_exit: - pm_runtime_mark_last_busy(&bp->pdev->dev); pm_runtime_put_autosuspend(&bp->pdev->dev); mdio_pm_exit: return status; @@ -492,15 +458,13 @@ static void macb_init_buffers(struct macb *bp) struct macb_queue *queue; unsigned int q; -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT /* Single register for all queues' high 32 bits. */ - if (bp->hw_dma_cap & HW_DMA_CAP_64B) { + if (macb_dma64(bp)) { macb_writel(bp, RBQPH, upper_32_bits(bp->queues[0].rx_ring_dma)); macb_writel(bp, TBQPH, upper_32_bits(bp->queues[0].tx_ring_dma)); } -#endif for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { queue_writel(queue, RBQP, lower_32_bits(queue->rx_ring_dma)); @@ -1025,10 +989,9 @@ static void macb_tx_unmap(struct macb *bp, struct macb_tx_skb *tx_skb, int budge static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_t addr) { -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - struct macb_dma_desc_64 *desc_64; + if (macb_dma64(bp)) { + struct macb_dma_desc_64 *desc_64; - if (bp->hw_dma_cap & HW_DMA_CAP_64B) { desc_64 = macb_64b_desc(bp, desc); desc_64->addrh = upper_32_bits(addr); /* The low bits of RX address contain the RX_USED bit, clearing @@ -1037,26 +1000,23 @@ static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_ */ dma_wmb(); } -#endif + desc->addr = lower_32_bits(addr); } static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc) { dma_addr_t addr = 0; -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - struct macb_dma_desc_64 *desc_64; - if (bp->hw_dma_cap & HW_DMA_CAP_64B) { + if (macb_dma64(bp)) { + struct macb_dma_desc_64 *desc_64; + desc_64 = macb_64b_desc(bp, desc); addr = ((u64)(desc_64->addrh) << 32); } -#endif addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr)); -#ifdef CONFIG_MACB_USE_HWSTAMP - if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + if (macb_dma_ptp(bp)) addr &= ~GEM_BIT(DMA_RXVALID); -#endif return addr; } @@ -1336,8 +1296,19 @@ static void gem_rx_refill(struct macb_queue *queue) dma_wmb(); macb_set_addr(bp, desc, paddr); - /* properly align Ethernet header */ - skb_reserve(skb, NET_IP_ALIGN); + /* Properly align Ethernet header. + * + * Hardware can add dummy bytes if asked using the RBOF + * field inside the NCFGR register. That feature isn't + * available if hardware is RSC capable. + * + * We cannot fallback to doing the 2-byte shift before + * DMA mapping because the address field does not allow + * setting the low 2/3 bits. + * It is 3 bits if HW_DMA_CAP_PTP, else 2 bits. + */ + if (!(bp->caps & MACB_CAPS_RSC)) + skb_reserve(skb, NET_IP_ALIGN); } else { desc->ctrl = 0; dma_wmb(); @@ -2024,14 +1995,14 @@ static unsigned int macb_tx_map(struct macb *bp, struct sk_buff *skb, unsigned int hdrlen) { - dma_addr_t mapping; - unsigned int len, entry, i, tx_head = queue->tx_head; - struct macb_tx_skb *tx_skb = NULL; - struct macb_dma_desc *desc; - unsigned int offset, size, count = 0; unsigned int f, nr_frags = skb_shinfo(skb)->nr_frags; - unsigned int eof = 1, mss_mfs = 0; + unsigned int len, i, tx_head = queue->tx_head; u32 ctrl, lso_ctrl = 0, seq_ctrl = 0; + unsigned int eof = 1, mss_mfs = 0; + struct macb_tx_skb *tx_skb = NULL; + struct macb_dma_desc *desc; + unsigned int offset, size; + dma_addr_t mapping; /* LSO */ if (skb_shinfo(skb)->gso_size != 0) { @@ -2051,8 +2022,7 @@ static unsigned int macb_tx_map(struct macb *bp, offset = 0; while (len) { - entry = macb_tx_ring_wrap(bp, tx_head); - tx_skb = &queue->tx_skb[entry]; + tx_skb = macb_tx_skb(queue, tx_head); mapping = dma_map_single(&bp->pdev->dev, skb->data + offset, @@ -2068,10 +2038,9 @@ static unsigned int macb_tx_map(struct macb *bp, len -= size; offset += size; - count++; tx_head++; - size = min(len, bp->max_tx_length); + size = umin(len, bp->max_tx_length); } /* Then, map paged data from fragments */ @@ -2081,9 +2050,8 @@ static unsigned int macb_tx_map(struct macb *bp, len = skb_frag_size(frag); offset = 0; while (len) { - size = min(len, bp->max_tx_length); - entry = macb_tx_ring_wrap(bp, tx_head); - tx_skb = &queue->tx_skb[entry]; + size = umin(len, bp->max_tx_length); + tx_skb = macb_tx_skb(queue, tx_head); mapping = skb_frag_dma_map(&bp->pdev->dev, frag, offset, size, DMA_TO_DEVICE); @@ -2098,7 +2066,6 @@ static unsigned int macb_tx_map(struct macb *bp, len -= size; offset += size; - count++; tx_head++; } } @@ -2120,9 +2087,8 @@ static unsigned int macb_tx_map(struct macb *bp, * to set the end of TX queue */ i = tx_head; - entry = macb_tx_ring_wrap(bp, i); ctrl = MACB_BIT(TX_USED); - desc = macb_tx_desc(queue, entry); + desc = macb_tx_desc(queue, i); desc->ctrl = ctrl; if (lso_ctrl) { @@ -2142,16 +2108,15 @@ static unsigned int macb_tx_map(struct macb *bp, do { i--; - entry = macb_tx_ring_wrap(bp, i); - tx_skb = &queue->tx_skb[entry]; - desc = macb_tx_desc(queue, entry); + tx_skb = macb_tx_skb(queue, i); + desc = macb_tx_desc(queue, i); ctrl = (u32)tx_skb->size; if (eof) { ctrl |= MACB_BIT(TX_LAST); eof = 0; } - if (unlikely(entry == (bp->tx_ring_size - 1))) + if (unlikely(macb_tx_ring_wrap(bp, i) == bp->tx_ring_size - 1)) ctrl |= MACB_BIT(TX_WRAP); /* First descriptor is header descriptor */ @@ -2179,7 +2144,7 @@ static unsigned int macb_tx_map(struct macb *bp, queue->tx_head = tx_head; - return count; + return 0; dma_error: netdev_err(bp->dev, "TX DMA map failed\n"); @@ -2190,7 +2155,7 @@ static unsigned int macb_tx_map(struct macb *bp, macb_tx_unmap(bp, tx_skb, 0); } - return 0; + return -ENOMEM; } static netdev_features_t macb_features_check(struct sk_buff *skb, @@ -2318,11 +2283,9 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) return ret; } -#ifdef CONFIG_MACB_USE_HWSTAMP - if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && - (bp->hw_dma_cap & HW_DMA_CAP_PTP)) + if (macb_dma_ptp(bp) && + (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; -#endif is_lso = (skb_shinfo(skb)->gso_size != 0); @@ -2339,7 +2302,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } } else - hdrlen = min(skb_headlen(skb), bp->max_tx_length); + hdrlen = umin(skb_headlen(skb), bp->max_tx_length); #if defined(DEBUG) && defined(VERBOSE_DEBUG) netdev_vdbg(bp->dev, @@ -2378,7 +2341,7 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev) } /* Map socket buffer for DMA transfer */ - if (!macb_tx_map(bp, queue, skb, hdrlen)) { + if (macb_tx_map(bp, queue, skb, hdrlen)) { dev_kfree_skb_any(skb); goto unlock; } @@ -2799,14 +2762,10 @@ static void macb_configure_dma(struct macb *bp) dmacfg &= ~GEM_BIT(TXCOEN); dmacfg &= ~GEM_BIT(ADDR64); -#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT - if (bp->hw_dma_cap & HW_DMA_CAP_64B) + if (macb_dma64(bp)) dmacfg |= GEM_BIT(ADDR64); -#endif -#ifdef CONFIG_MACB_USE_HWSTAMP - if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + if (macb_dma_ptp(bp)) dmacfg |= GEM_BIT(RXEXT) | GEM_BIT(TXEXT); -#endif netdev_dbg(bp->dev, "Cadence configure DMA with 0x%08x\n", dmacfg); gem_writel(bp, DMACFG, dmacfg); @@ -2821,7 +2780,11 @@ static void macb_init_hw(struct macb *bp) macb_set_hwaddr(bp); config = macb_mdc_clk_div(bp); - config |= MACB_BF(RBOF, NET_IP_ALIGN); /* Make eth data aligned */ + /* Make eth data aligned. + * If RSC capable, that offset is ignored by HW. + */ + if (!(bp->caps & MACB_CAPS_RSC)) + config |= MACB_BF(RBOF, NET_IP_ALIGN); config |= MACB_BIT(DRFCS); /* Discard Rx FCS */ if (bp->caps & MACB_CAPS_JUMBO) config |= MACB_BIT(JFRAME); /* Enable jumbo frames */ @@ -2998,7 +2961,11 @@ static int macb_open(struct net_device *dev) macb_init_hw(bp); - err = phy_power_on(bp->sgmii_phy); + err = phy_set_mode_ext(bp->phy, PHY_MODE_ETHERNET, bp->phy_interface); + if (err) + goto reset_hw; + + err = phy_power_on(bp->phy); if (err) goto reset_hw; @@ -3014,7 +2981,7 @@ static int macb_open(struct net_device *dev) return 0; phy_off: - phy_power_off(bp->sgmii_phy); + phy_power_off(bp->phy); reset_hw: macb_reset_hw(bp); @@ -3046,7 +3013,7 @@ static int macb_close(struct net_device *dev) phylink_stop(bp->phylink); phylink_disconnect_phy(bp->phylink); - phy_power_off(bp->sgmii_phy); + phy_power_off(bp->phy); spin_lock_irqsave(&bp->lock, flags); macb_reset_hw(bp); @@ -3582,7 +3549,7 @@ static int gem_get_ts_info(struct net_device *dev, { struct macb *bp = netdev_priv(dev); - if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0) { + if (!macb_dma_ptp(bp)) { ethtool_op_get_ts_info(dev, info); return 0; } @@ -4108,6 +4075,8 @@ static int macb_taprio_setup_replace(struct net_device *ndev, struct macb *bp = netdev_priv(ndev); struct ethtool_link_ksettings kset; struct macb_queue *queue; + u32 queue_mask; + u8 queue_id; size_t i; int err; @@ -4159,8 +4128,9 @@ static int macb_taprio_setup_replace(struct net_device *ndev, goto cleanup; } - /* gate_mask must not select queues outside the valid queue_mask */ - if (entry->gate_mask & ~bp->queue_mask) { + /* gate_mask must not select queues outside the valid queues */ + queue_id = order_base_2(entry->gate_mask); + if (queue_id >= bp->num_queues) { netdev_err(ndev, "Entry %zu: gate_mask 0x%x exceeds queue range (max_queues=%d)\n", i, entry->gate_mask, bp->num_queues); err = -EINVAL; @@ -4194,7 +4164,7 @@ static int macb_taprio_setup_replace(struct net_device *ndev, goto cleanup; } - enst_queue[i].queue_id = order_base_2(entry->gate_mask); + enst_queue[i].queue_id = queue_id; enst_queue[i].start_time_mask = (start_time_sec << GEM_START_TIME_SEC_OFFSET) | start_time_nsec; @@ -4222,8 +4192,9 @@ static int macb_taprio_setup_replace(struct net_device *ndev, /* All validations passed - proceed with hardware configuration */ scoped_guard(spinlock_irqsave, &bp->lock) { /* Disable ENST queues if running before configuring */ + queue_mask = BIT_U32(bp->num_queues) - 1; gem_writel(bp, ENST_CONTROL, - bp->queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET); + queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET); for (i = 0; i < conf->num_entries; i++) { queue = &bp->queues[enst_queue[i].queue_id]; @@ -4252,15 +4223,16 @@ static void macb_taprio_destroy(struct net_device *ndev) { struct macb *bp = netdev_priv(ndev); struct macb_queue *queue; - u32 enst_disable_mask; + u32 queue_mask; unsigned int q; netdev_reset_tc(ndev); - enst_disable_mask = bp->queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET; + queue_mask = BIT_U32(bp->num_queues) - 1; scoped_guard(spinlock_irqsave, &bp->lock) { /* Single disable command for all queues */ - gem_writel(bp, ENST_CONTROL, enst_disable_mask); + gem_writel(bp, ENST_CONTROL, + queue_mask << GEM_ENST_DISABLE_QUEUE_OFFSET); /* Clear all queue ENST registers in batch */ for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) { @@ -4364,13 +4336,15 @@ static void macb_configure_caps(struct macb *bp, dcfg = gem_readl(bp, DCFG2); if ((dcfg & (GEM_BIT(RX_PKT_BUFF) | GEM_BIT(TX_PKT_BUFF))) == 0) bp->caps |= MACB_CAPS_FIFO_MODE; + if (GEM_BFEXT(PBUF_RSC, gem_readl(bp, DCFG6))) + bp->caps |= MACB_CAPS_RSC; if (gem_has_ptp(bp)) { if (!GEM_BFEXT(TSU, gem_readl(bp, DCFG5))) dev_err(&bp->pdev->dev, "GEM doesn't support hardware ptp.\n"); else { #ifdef CONFIG_MACB_USE_HWSTAMP - bp->hw_dma_cap |= HW_DMA_CAP_PTP; + bp->caps |= MACB_CAPS_DMA_PTP; bp->ptp_info = &gem_ptp_info; #endif } @@ -4383,26 +4357,25 @@ static void macb_configure_caps(struct macb *bp, dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps); } -static void macb_probe_queues(void __iomem *mem, - bool native_io, - unsigned int *queue_mask, - unsigned int *num_queues) +static int macb_probe_queues(struct device *dev, void __iomem *mem, bool native_io) { - *queue_mask = 0x1; - *num_queues = 1; + /* BIT(0) is never set but queue 0 always exists. */ + unsigned int queue_mask = 0x1; - /* is it macb or gem ? - * - * We need to read directly from the hardware here because - * we are early in the probe process and don't have the - * MACB_CAPS_MACB_IS_GEM flag positioned - */ - if (!hw_is_gem(mem, native_io)) - return; + /* Use hw_is_gem() as MACB_CAPS_MACB_IS_GEM is not yet positioned. */ + if (hw_is_gem(mem, native_io)) { + if (native_io) + queue_mask |= __raw_readl(mem + GEM_DCFG6) & 0xFF; + else + queue_mask |= readl_relaxed(mem + GEM_DCFG6) & 0xFF; - /* bit 0 is never set but queue 0 always exists */ - *queue_mask |= readl_relaxed(mem + GEM_DCFG6) & 0xff; - *num_queues = hweight32(*queue_mask); + if (fls(queue_mask) != ffz(queue_mask)) { + dev_err(dev, "queue mask %#x has a hole\n", queue_mask); + return -EINVAL; + } + } + + return hweight32(queue_mask); } static void macb_clks_disable(struct clk *pclk, struct clk *hclk, struct clk *tx_clk, @@ -4520,10 +4493,7 @@ static int macb_init(struct platform_device *pdev) * register mapping but we don't want to test the queue index then * compute the corresponding register offset at run time. */ - for (hw_q = 0, q = 0; hw_q < MACB_MAX_QUEUES; ++hw_q) { - if (!(bp->queue_mask & (1 << hw_q))) - continue; - + for (hw_q = 0, q = 0; hw_q < bp->num_queues; ++hw_q) { queue = &bp->queues[q]; queue->bp = bp; spin_lock_init(&queue->tx_ptr_lock); @@ -4594,8 +4564,11 @@ static int macb_init(struct platform_device *pdev) /* Set features */ dev->hw_features = NETIF_F_SG; - /* Check LSO capability */ - if (GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6))) + /* Check LSO capability; runtime detection can be overridden by a cap + * flag if the hardware is known to be buggy + */ + if (!(bp->caps & MACB_CAPS_NO_LSO) && + GEM_BFEXT(PBUF_LSO, gem_readl(bp, DCFG6))) dev->hw_features |= MACB_NETIF_LSO; /* Checksum offload is only available on gem with packet buffer */ @@ -4614,8 +4587,8 @@ static int macb_init(struct platform_device *pdev) * each 4-tuple define requires 1 T2 screener reg + 3 compare regs */ reg = gem_readl(bp, DCFG8); - bp->max_tuples = min((GEM_BFEXT(SCR2CMP, reg) / 3), - GEM_BFEXT(T2SCR, reg)); + bp->max_tuples = umin((GEM_BFEXT(SCR2CMP, reg) / 3), + GEM_BFEXT(T2SCR, reg)); INIT_LIST_HEAD(&bp->rx_fs_list.list); if (bp->max_tuples > 0) { /* also needs one ethtype match to check IPv4 */ @@ -5168,13 +5141,13 @@ static int init_reset_optional(struct platform_device *pdev) if (bp->phy_interface == PHY_INTERFACE_MODE_SGMII) { /* Ensure PHY device used in SGMII mode is ready */ - bp->sgmii_phy = devm_phy_optional_get(&pdev->dev, NULL); + bp->phy = devm_phy_optional_get(&pdev->dev, NULL); - if (IS_ERR(bp->sgmii_phy)) - return dev_err_probe(&pdev->dev, PTR_ERR(bp->sgmii_phy), + if (IS_ERR(bp->phy)) + return dev_err_probe(&pdev->dev, PTR_ERR(bp->phy), "failed to get SGMII PHY\n"); - ret = phy_init(bp->sgmii_phy); + ret = phy_init(bp->phy); if (ret) return dev_err_probe(&pdev->dev, ret, "failed to init SGMII PHY\n"); @@ -5203,7 +5176,7 @@ static int init_reset_optional(struct platform_device *pdev) /* Fully reset controller at hardware level if mapped in device tree */ ret = device_reset_optional(&pdev->dev); if (ret) { - phy_exit(bp->sgmii_phy); + phy_exit(bp->phy); return dev_err_probe(&pdev->dev, ret, "failed to reset controller"); } @@ -5211,8 +5184,30 @@ static int init_reset_optional(struct platform_device *pdev) err_out_phy_exit: if (ret) - phy_exit(bp->sgmii_phy); + phy_exit(bp->phy); + + return ret; +} + +static int eyeq5_init(struct platform_device *pdev) +{ + struct net_device *netdev = platform_get_drvdata(pdev); + struct macb *bp = netdev_priv(netdev); + struct device *dev = &pdev->dev; + int ret; + + bp->phy = devm_phy_get(dev, NULL); + if (IS_ERR(bp->phy)) + return dev_err_probe(dev, PTR_ERR(bp->phy), + "failed to get PHY\n"); + + ret = phy_init(bp->phy); + if (ret) + return dev_err_probe(dev, ret, "failed to init PHY\n"); + ret = macb_init(pdev); + if (ret) + phy_exit(bp->phy); return ret; } @@ -5370,6 +5365,17 @@ static const struct macb_config versal_config = { .usrio = &macb_default_usrio, }; +static const struct macb_config eyeq5_config = { + .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_JUMBO | + MACB_CAPS_GEM_HAS_PTP | MACB_CAPS_QUEUE_DISABLE | + MACB_CAPS_NO_LSO, + .dma_burst_length = 16, + .clk_init = macb_clk_init, + .init = eyeq5_init, + .jumbo_max_len = 10240, + .usrio = &macb_default_usrio, +}; + static const struct macb_config raspberrypi_rp1_config = { .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_CLK_HW_CHG | MACB_CAPS_JUMBO | @@ -5401,6 +5407,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "microchip,mpfs-macb", .data = &mpfs_config }, { .compatible = "microchip,sama7g5-gem", .data = &sama7g5_gem_config }, { .compatible = "microchip,sama7g5-emac", .data = &sama7g5_emac_config }, + { .compatible = "mobileye,eyeq5-gem", .data = &eyeq5_config }, { .compatible = "raspberrypi,rp1-gem", .data = &raspberrypi_rp1_config }, { .compatible = "xlnx,zynqmp-gem", .data = &zynqmp_config}, { .compatible = "xlnx,zynq-gem", .data = &zynq_config }, @@ -5424,21 +5431,17 @@ static const struct macb_config default_gem_config = { static int macb_probe(struct platform_device *pdev) { const struct macb_config *macb_config = &default_gem_config; - int (*clk_init)(struct platform_device *, struct clk **, - struct clk **, struct clk **, struct clk **, - struct clk **) = macb_config->clk_init; - int (*init)(struct platform_device *) = macb_config->init; struct device_node *np = pdev->dev.of_node; struct clk *pclk, *hclk = NULL, *tx_clk = NULL, *rx_clk = NULL; struct clk *tsu_clk = NULL; - unsigned int queue_mask, num_queues; - bool native_io; phy_interface_t interface; struct net_device *dev; struct resource *regs; u32 wtrmrk_rst_val; void __iomem *mem; struct macb *bp; + int num_queues; + bool native_io; int err, val; mem = devm_platform_get_and_ioremap_resource(pdev, 0, ®s); @@ -5449,14 +5452,11 @@ static int macb_probe(struct platform_device *pdev) const struct of_device_id *match; match = of_match_node(macb_dt_ids, np); - if (match && match->data) { + if (match && match->data) macb_config = match->data; - clk_init = macb_config->clk_init; - init = macb_config->init; - } } - err = clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk); + err = macb_config->clk_init(pdev, &pclk, &hclk, &tx_clk, &rx_clk, &tsu_clk); if (err) return err; @@ -5467,7 +5467,12 @@ static int macb_probe(struct platform_device *pdev) pm_runtime_enable(&pdev->dev); native_io = hw_is_native_io(mem); - macb_probe_queues(mem, native_io, &queue_mask, &num_queues); + num_queues = macb_probe_queues(&pdev->dev, mem, native_io); + if (num_queues < 0) { + err = num_queues; + goto err_disable_clocks; + } + dev = alloc_etherdev_mq(sizeof(*bp), num_queues); if (!dev) { err = -ENOMEM; @@ -5491,16 +5496,13 @@ static int macb_probe(struct platform_device *pdev) bp->macb_reg_writel = hw_writel; } bp->num_queues = num_queues; - bp->queue_mask = queue_mask; - if (macb_config) - bp->dma_burst_length = macb_config->dma_burst_length; + bp->dma_burst_length = macb_config->dma_burst_length; bp->pclk = pclk; bp->hclk = hclk; bp->tx_clk = tx_clk; bp->rx_clk = rx_clk; bp->tsu_clk = tsu_clk; - if (macb_config) - bp->jumbo_max_len = macb_config->jumbo_max_len; + bp->jumbo_max_len = macb_config->jumbo_max_len; if (!hw_is_gem(bp->regs, bp->native_io)) bp->max_tx_length = MACB_MAX_TX_LEN; @@ -5546,7 +5548,7 @@ static int macb_probe(struct platform_device *pdev) dev_err(&pdev->dev, "failed to set DMA mask\n"); goto err_out_free_netdev; } - bp->hw_dma_cap |= HW_DMA_CAP_64B; + bp->caps |= MACB_CAPS_DMA_64B; } #endif platform_set_drvdata(pdev, dev); @@ -5594,7 +5596,7 @@ static int macb_probe(struct platform_device *pdev) bp->phy_interface = interface; /* IP specific init */ - err = init(pdev); + err = macb_config->init(pdev); if (err) goto err_out_free_netdev; @@ -5616,7 +5618,6 @@ static int macb_probe(struct platform_device *pdev) macb_is_gem(bp) ? "GEM" : "MACB", macb_readl(bp, MID), dev->base_addr, dev->irq, dev->dev_addr); - pm_runtime_mark_last_busy(&bp->pdev->dev); pm_runtime_put_autosuspend(&bp->pdev->dev); return 0; @@ -5626,7 +5627,7 @@ static int macb_probe(struct platform_device *pdev) mdiobus_free(bp->mii_bus); err_out_phy_exit: - phy_exit(bp->sgmii_phy); + phy_exit(bp->phy); err_out_free_netdev: free_netdev(dev); @@ -5650,7 +5651,7 @@ static void macb_remove(struct platform_device *pdev) if (dev) { bp = netdev_priv(dev); unregister_netdev(dev); - phy_exit(bp->sgmii_phy); + phy_exit(bp->phy); mdiobus_unregister(bp->mii_bus); mdiobus_free(bp->mii_bus); @@ -5677,7 +5678,7 @@ static int __maybe_unused macb_suspend(struct device *dev) u32 tmp; if (!device_may_wakeup(&bp->dev->dev)) - phy_exit(bp->sgmii_phy); + phy_exit(bp->phy); if (!netif_running(netdev)) return 0; @@ -5806,7 +5807,7 @@ static int __maybe_unused macb_resume(struct device *dev) int err; if (!device_may_wakeup(&bp->dev->dev)) - phy_init(bp->sgmii_phy); + phy_init(bp->phy); if (!netif_running(netdev)) return 0; diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index a63bf29c4fa81..c9e77819196e1 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -28,14 +28,16 @@ static struct macb_dma_desc_ptp *macb_ptp_desc(struct macb *bp, struct macb_dma_desc *desc) { - if (bp->hw_dma_cap == HW_DMA_CAP_PTP) - return (struct macb_dma_desc_ptp *) - ((u8 *)desc + sizeof(struct macb_dma_desc)); - if (bp->hw_dma_cap == HW_DMA_CAP_64B_PTP) + if (!macb_dma_ptp(bp)) + return NULL; + + if (macb_dma64(bp)) return (struct macb_dma_desc_ptp *) ((u8 *)desc + sizeof(struct macb_dma_desc) + sizeof(struct macb_dma_desc_64)); - return NULL; + else + return (struct macb_dma_desc_ptp *) + ((u8 *)desc + sizeof(struct macb_dma_desc)); } static int gem_tsu_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts, @@ -380,7 +382,7 @@ int gem_get_hwtst(struct net_device *dev, struct macb *bp = netdev_priv(dev); *tstamp_config = bp->tstamp_config; - if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0) + if (!macb_dma_ptp(bp)) return -EOPNOTSUPP; return 0; @@ -407,7 +409,7 @@ int gem_set_hwtst(struct net_device *dev, struct macb *bp = netdev_priv(dev); u32 regval; - if ((bp->hw_dma_cap & HW_DMA_CAP_PTP) == 0) + if (!macb_dma_ptp(bp)) return -EOPNOTSUPP; switch (tstamp_config->tx_type) { diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 8e2fcec26ea13..0732440eeacd6 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -2107,20 +2107,16 @@ liquidio_get_stats64(struct net_device *netdev, lstats->tx_fifo_errors; } -/** - * hwtstamp_ioctl - Handler for SIOCSHWTSTAMP ioctl - * @netdev: network device - * @ifr: interface request - */ -static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) +static int liquidio_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *conf, + struct netlink_ext_ack *extack) { - struct hwtstamp_config conf; struct lio *lio = GET_LIO(netdev); - if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf))) - return -EFAULT; + if (!lio->oct_dev->ptp_enable) + return -EOPNOTSUPP; - switch (conf.tx_type) { + switch (conf->tx_type) { case HWTSTAMP_TX_ON: case HWTSTAMP_TX_OFF: break; @@ -2128,7 +2124,7 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) return -ERANGE; } - switch (conf.rx_filter) { + switch (conf->rx_filter) { case HWTSTAMP_FILTER_NONE: break; case HWTSTAMP_FILTER_ALL: @@ -2146,39 +2142,32 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - conf.rx_filter = HWTSTAMP_FILTER_ALL; + conf->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } - if (conf.rx_filter == HWTSTAMP_FILTER_ALL) + if (conf->rx_filter == HWTSTAMP_FILTER_ALL) ifstate_set(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED); else ifstate_reset(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED); - return copy_to_user(ifr->ifr_data, &conf, sizeof(conf)) ? -EFAULT : 0; + return 0; } -/** - * liquidio_ioctl - ioctl handler - * @netdev: network device - * @ifr: interface request - * @cmd: command - */ -static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int liquidio_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *conf) { struct lio *lio = GET_LIO(netdev); - switch (cmd) { - case SIOCSHWTSTAMP: - if (lio->oct_dev->ptp_enable) - return hwtstamp_ioctl(netdev, ifr); - fallthrough; - default: - return -EOPNOTSUPP; - } + /* TX timestamping is technically always on */ + conf->tx_type = HWTSTAMP_TX_ON; + conf->rx_filter = ifstate_check(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED) ? + HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; + + return 0; } /** @@ -3227,7 +3216,6 @@ static const struct net_device_ops lionetdevops = { .ndo_vlan_rx_add_vid = liquidio_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = liquidio_vlan_rx_kill_vid, .ndo_change_mtu = liquidio_change_mtu, - .ndo_eth_ioctl = liquidio_ioctl, .ndo_fix_features = liquidio_fix_features, .ndo_set_features = liquidio_set_features, .ndo_set_vf_mac = liquidio_set_vf_mac, @@ -3238,6 +3226,8 @@ static const struct net_device_ops lionetdevops = { .ndo_set_vf_link_state = liquidio_set_vf_link_state, .ndo_get_vf_stats = liquidio_get_vf_stats, .ndo_get_port_parent_id = liquidio_get_port_parent_id, + .ndo_hwtstamp_get = liquidio_hwtstamp_get, + .ndo_hwtstamp_set = liquidio_hwtstamp_set, }; /** diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index 3230dff5ba056..e02942dbbcce5 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -1236,20 +1236,13 @@ liquidio_get_stats64(struct net_device *netdev, lstats->tx_carrier_errors; } -/** - * hwtstamp_ioctl - Handler for SIOCSHWTSTAMP ioctl - * @netdev: network device - * @ifr: interface request - */ -static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) +static int liquidio_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *conf, + struct netlink_ext_ack *extack) { struct lio *lio = GET_LIO(netdev); - struct hwtstamp_config conf; - - if (copy_from_user(&conf, ifr->ifr_data, sizeof(conf))) - return -EFAULT; - switch (conf.tx_type) { + switch (conf->tx_type) { case HWTSTAMP_TX_ON: case HWTSTAMP_TX_OFF: break; @@ -1257,7 +1250,7 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) return -ERANGE; } - switch (conf.rx_filter) { + switch (conf->rx_filter) { case HWTSTAMP_FILTER_NONE: break; case HWTSTAMP_FILTER_ALL: @@ -1275,35 +1268,31 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - conf.rx_filter = HWTSTAMP_FILTER_ALL; + conf->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } - if (conf.rx_filter == HWTSTAMP_FILTER_ALL) + if (conf->rx_filter == HWTSTAMP_FILTER_ALL) ifstate_set(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED); else ifstate_reset(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED); - return copy_to_user(ifr->ifr_data, &conf, sizeof(conf)) ? -EFAULT : 0; + return 0; } -/** - * liquidio_ioctl - ioctl handler - * @netdev: network device - * @ifr: interface request - * @cmd: command - */ -static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int liquidio_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *conf) { - switch (cmd) { - case SIOCSHWTSTAMP: - return hwtstamp_ioctl(netdev, ifr); - default: - return -EOPNOTSUPP; - } + struct lio *lio = GET_LIO(netdev); + + /* TX timestamping is techically always on */ + conf->tx_type = HWTSTAMP_TX_ON; + conf->rx_filter = ifstate_check(lio, LIO_IFSTATE_RX_TIMESTAMP_ENABLED) ? + HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; + return 0; } static void handle_timestamp(struct octeon_device *oct, u32 status, void *buf) @@ -1881,9 +1870,10 @@ static const struct net_device_ops lionetdevops = { .ndo_vlan_rx_add_vid = liquidio_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = liquidio_vlan_rx_kill_vid, .ndo_change_mtu = liquidio_change_mtu, - .ndo_eth_ioctl = liquidio_ioctl, .ndo_fix_features = liquidio_fix_features, .ndo_set_features = liquidio_set_features, + .ndo_hwtstamp_get = liquidio_hwtstamp_get, + .ndo_hwtstamp_set = liquidio_hwtstamp_set, }; static int lio_nic_info(struct octeon_recv_info *recv_info, void *buf) diff --git a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c index 393b9951490a1..c190fc6538d4c 100644 --- a/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c +++ b/drivers/net/ethernet/cavium/octeon/octeon_mgmt.c @@ -690,19 +690,16 @@ static irqreturn_t octeon_mgmt_interrupt(int cpl, void *dev_id) return IRQ_HANDLED; } -static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev, - struct ifreq *rq, int cmd) +static int octeon_mgmt_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct octeon_mgmt *p = netdev_priv(netdev); - struct hwtstamp_config config; - union cvmx_mio_ptp_clock_cfg ptp; union cvmx_agl_gmx_rxx_frm_ctl rxx_frm_ctl; + union cvmx_mio_ptp_clock_cfg ptp; bool have_hw_timestamps = false; - if (copy_from_user(&config, rq->ifr_data, sizeof(config))) - return -EFAULT; - - /* Check the status of hardware for tiemstamps */ + /* Check the status of hardware for timestamps */ if (OCTEON_IS_MODEL(OCTEON_CN6XXX)) { /* Get the current state of the PTP clock */ ptp.u64 = cvmx_read_csr(CVMX_MIO_PTP_CLOCK_CFG); @@ -733,10 +730,12 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev, have_hw_timestamps = true; } - if (!have_hw_timestamps) + if (!have_hw_timestamps) { + NL_SET_ERR_MSG_MOD(extack, "HW doesn't support timestamping"); return -EINVAL; + } - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: break; @@ -744,7 +743,7 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev, return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: p->has_rx_tstamp = false; rxx_frm_ctl.u64 = cvmx_read_csr(p->agl + AGL_GMX_RX_FRM_CTL); @@ -766,33 +765,34 @@ static int octeon_mgmt_ioctl_hwtstamp(struct net_device *netdev, case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - p->has_rx_tstamp = have_hw_timestamps; - config.rx_filter = HWTSTAMP_FILTER_ALL; - if (p->has_rx_tstamp) { - rxx_frm_ctl.u64 = cvmx_read_csr(p->agl + AGL_GMX_RX_FRM_CTL); - rxx_frm_ctl.s.ptp_mode = 1; - cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_CTL, rxx_frm_ctl.u64); - } + p->has_rx_tstamp = true; + config->rx_filter = HWTSTAMP_FILTER_ALL; + rxx_frm_ctl.u64 = cvmx_read_csr(p->agl + AGL_GMX_RX_FRM_CTL); + rxx_frm_ctl.s.ptp_mode = 1; + cvmx_write_csr(p->agl + AGL_GMX_RX_FRM_CTL, rxx_frm_ctl.u64); break; default: return -ERANGE; } - if (copy_to_user(rq->ifr_data, &config, sizeof(config))) - return -EFAULT; - return 0; } -static int octeon_mgmt_ioctl(struct net_device *netdev, - struct ifreq *rq, int cmd) +static int octeon_mgmt_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - switch (cmd) { - case SIOCSHWTSTAMP: - return octeon_mgmt_ioctl_hwtstamp(netdev, rq, cmd); - default: - return phy_do_ioctl(netdev, rq, cmd); - } + struct octeon_mgmt *p = netdev_priv(netdev); + + /* Check the status of hardware for timestamps */ + if (!OCTEON_IS_MODEL(OCTEON_CN6XXX)) + return -EINVAL; + + config->tx_type = HWTSTAMP_TX_ON; + config->rx_filter = p->has_rx_tstamp ? + HWTSTAMP_FILTER_ALL : + HWTSTAMP_FILTER_NONE; + + return 0; } static void octeon_mgmt_disable_link(struct octeon_mgmt *p) @@ -1370,11 +1370,13 @@ static const struct net_device_ops octeon_mgmt_ops = { .ndo_start_xmit = octeon_mgmt_xmit, .ndo_set_rx_mode = octeon_mgmt_set_rx_filtering, .ndo_set_mac_address = octeon_mgmt_set_mac_address, - .ndo_eth_ioctl = octeon_mgmt_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_change_mtu = octeon_mgmt_change_mtu, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = octeon_mgmt_poll_controller, #endif + .ndo_hwtstamp_get = octeon_mgmt_hwtstamp_get, + .ndo_hwtstamp_set = octeon_mgmt_hwtstamp_set, }; static int octeon_mgmt_probe(struct platform_device *pdev) diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 1be2dc40a1a63..0b6e30a8feb07 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -1899,18 +1899,18 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp) } } -static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) +static int nicvf_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config config; struct nicvf *nic = netdev_priv(netdev); - if (!nic->ptp_clock) + if (!nic->ptp_clock) { + NL_SET_ERR_MSG_MOD(extack, "HW timestamping is not supported"); return -ENODEV; + } - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: break; @@ -1918,7 +1918,7 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: nic->hw_rx_tstamp = false; break; @@ -1937,7 +1937,7 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: nic->hw_rx_tstamp = true; - config.rx_filter = HWTSTAMP_FILTER_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; @@ -1946,20 +1946,24 @@ static int nicvf_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) if (netif_running(netdev)) nicvf_config_hw_rx_tstamp(nic, nic->hw_rx_tstamp); - if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) - return -EFAULT; - return 0; } -static int nicvf_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) +static int nicvf_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - switch (cmd) { - case SIOCSHWTSTAMP: - return nicvf_config_hwtstamp(netdev, req); - default: - return -EOPNOTSUPP; - } + struct nicvf *nic = netdev_priv(netdev); + + if (!nic->ptp_clock) + return -ENODEV; + + /* TX timestamping is technically always on */ + config->tx_type = HWTSTAMP_TX_ON; + config->rx_filter = nic->hw_rx_tstamp ? + HWTSTAMP_FILTER_ALL : + HWTSTAMP_FILTER_NONE; + + return 0; } static void __nicvf_set_rx_mode_task(u8 mode, struct xcast_addr_list *mc_addrs, @@ -2081,8 +2085,9 @@ static const struct net_device_ops nicvf_netdev_ops = { .ndo_fix_features = nicvf_fix_features, .ndo_set_features = nicvf_set_features, .ndo_bpf = nicvf_xdp, - .ndo_eth_ioctl = nicvf_ioctl, .ndo_set_rx_mode = nicvf_set_rx_mode, + .ndo_hwtstamp_get = nicvf_hwtstamp_get, + .ndo_hwtstamp_set = nicvf_hwtstamp_set, }; static int nicvf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index 0d85198fb03df..f20f4bc58492b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@ -674,7 +674,7 @@ struct port_info { struct cxgb_fcoe fcoe; #endif /* CONFIG_CHELSIO_T4_FCOE */ bool rxtstamp; /* Enable TS */ - struct hwtstamp_config tstamp_config; + struct kernel_hwtstamp_config tstamp_config; bool ptp_enable; struct sched_table *sched_tbl; u32 eth_flags; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 392723ef14e51..7e2283c95b97d 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -3042,12 +3042,87 @@ static void cxgb_get_stats(struct net_device *dev, ns->rx_length_errors + stats.rx_len_err + ns->rx_fifo_errors; } +static int cxgb_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) +{ + struct port_info *pi = netdev_priv(dev); + + *config = pi->tstamp_config; + return 0; +} + +static int cxgb_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct port_info *pi = netdev_priv(dev); + struct adapter *adapter = pi->adapter; + + if (is_t4(adapter->params.chip)) { + /* For T4 Adapters */ + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + pi->rxtstamp = false; + break; + case HWTSTAMP_FILTER_ALL: + pi->rxtstamp = true; + break; + default: + return -ERANGE; + } + pi->tstamp_config = *config; + return 0; + } + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + pi->rxtstamp = false; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + cxgb4_ptprx_timestamping(pi, pi->port_id, PTP_TS_L4); + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + cxgb4_ptprx_timestamping(pi, pi->port_id, PTP_TS_L2_L4); + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + pi->rxtstamp = true; + break; + default: + return -ERANGE; + } + + if (config->tx_type == HWTSTAMP_TX_OFF && + config->rx_filter == HWTSTAMP_FILTER_NONE) { + if (cxgb4_ptp_txtype(adapter, pi->port_id) >= 0) + pi->ptp_enable = false; + } + + if (config->rx_filter != HWTSTAMP_FILTER_NONE) { + if (cxgb4_ptp_redirect_rx_packet(adapter, pi) >= 0) + pi->ptp_enable = true; + } + pi->tstamp_config = *config; + return 0; +} + static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd) { unsigned int mbox; int ret = 0, prtad, devad; struct port_info *pi = netdev_priv(dev); - struct adapter *adapter = pi->adapter; struct mii_ioctl_data *data = (struct mii_ioctl_data *)&req->ifr_data; switch (cmd) { @@ -3076,81 +3151,6 @@ static int cxgb_ioctl(struct net_device *dev, struct ifreq *req, int cmd) ret = t4_mdio_wr(pi->adapter, mbox, prtad, devad, data->reg_num, data->val_in); break; - case SIOCGHWTSTAMP: - return copy_to_user(req->ifr_data, &pi->tstamp_config, - sizeof(pi->tstamp_config)) ? - -EFAULT : 0; - case SIOCSHWTSTAMP: - if (copy_from_user(&pi->tstamp_config, req->ifr_data, - sizeof(pi->tstamp_config))) - return -EFAULT; - - if (!is_t4(adapter->params.chip)) { - switch (pi->tstamp_config.tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - switch (pi->tstamp_config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - pi->rxtstamp = false; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - cxgb4_ptprx_timestamping(pi, pi->port_id, - PTP_TS_L4); - break; - case HWTSTAMP_FILTER_PTP_V2_EVENT: - cxgb4_ptprx_timestamping(pi, pi->port_id, - PTP_TS_L2_L4); - break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - pi->rxtstamp = true; - break; - default: - pi->tstamp_config.rx_filter = - HWTSTAMP_FILTER_NONE; - return -ERANGE; - } - - if ((pi->tstamp_config.tx_type == HWTSTAMP_TX_OFF) && - (pi->tstamp_config.rx_filter == - HWTSTAMP_FILTER_NONE)) { - if (cxgb4_ptp_txtype(adapter, pi->port_id) >= 0) - pi->ptp_enable = false; - } - - if (pi->tstamp_config.rx_filter != - HWTSTAMP_FILTER_NONE) { - if (cxgb4_ptp_redirect_rx_packet(adapter, - pi) >= 0) - pi->ptp_enable = true; - } - } else { - /* For T4 Adapters */ - switch (pi->tstamp_config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - pi->rxtstamp = false; - break; - case HWTSTAMP_FILTER_ALL: - pi->rxtstamp = true; - break; - default: - pi->tstamp_config.rx_filter = - HWTSTAMP_FILTER_NONE; - return -ERANGE; - } - } - return copy_to_user(req->ifr_data, &pi->tstamp_config, - sizeof(pi->tstamp_config)) ? - -EFAULT : 0; default: return -EOPNOTSUPP; } @@ -3875,6 +3875,8 @@ static const struct net_device_ops cxgb4_netdev_ops = { .ndo_setup_tc = cxgb_setup_tc, .ndo_features_check = cxgb_features_check, .ndo_fix_features = cxgb_fix_features, + .ndo_hwtstamp_get = cxgb_hwtstamp_get, + .ndo_hwtstamp_set = cxgb_hwtstamp_set, }; #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c index 0765d000eaef0..e2b5554531b57 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c @@ -161,20 +161,9 @@ static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap, static void cxgb4_process_flow_match(struct net_device *dev, struct flow_rule *rule, + u16 addr_type, struct ch_filter_specification *fs) { - u16 addr_type = 0; - - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_match_control match; - - flow_rule_match_control(rule, &match); - addr_type = match.key->addr_type; - } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { - addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; - } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { - addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; - } if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { struct flow_match_basic match; @@ -327,9 +316,6 @@ static int cxgb4_validate_flow_match(struct netlink_ext_ack *extack, return -EOPNOTSUPP; } - if (flow_rule_match_has_control_flags(rule, extack)) - return -EOPNOTSUPP; - if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { struct flow_match_basic match; @@ -858,6 +844,7 @@ int cxgb4_flow_rule_replace(struct net_device *dev, struct flow_rule *rule, { struct adapter *adap = netdev2adap(dev); struct filter_ctx ctx; + u16 addr_type = 0; u8 inet_family; int fidx, ret; @@ -867,7 +854,28 @@ int cxgb4_flow_rule_replace(struct net_device *dev, struct flow_rule *rule, if (cxgb4_validate_flow_match(extack, rule)) return -EOPNOTSUPP; - cxgb4_process_flow_match(dev, rule, fs); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; + + if (match.mask->flags & FLOW_DIS_IS_FRAGMENT) { + fs->val.frag = match.key->flags & FLOW_DIS_IS_FRAGMENT; + fs->mask.frag = true; + } + + if (!flow_rule_is_supp_control_flags(FLOW_DIS_IS_FRAGMENT, + match.mask->flags, extack)) + return -EOPNOTSUPP; + + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + } else if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + } + + cxgb4_process_flow_match(dev, rule, addr_type, fs); cxgb4_process_flow_actions(dev, &rule->action, fs); fs->hash = is_filter_exact_match(adap, fs); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c index 4ee970f3bad6e..ee0154337a9c5 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_cm.c @@ -1199,12 +1199,12 @@ static struct sock *chtls_recv_sock(struct sock *lsk, struct ipv6_pinfo *newnp = inet6_sk(newsk); struct ipv6_pinfo *np = inet6_sk(lsk); - inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; + newinet->pinet6 = &newtcp6sk->inet6; + newinet->ipv6_fl_list = NULL; memcpy(newnp, np, sizeof(struct ipv6_pinfo)); newsk->sk_v6_daddr = treq->ir_v6_rmt_addr; newsk->sk_v6_rcv_saddr = treq->ir_v6_loc_addr; inet6_sk(newsk)->saddr = treq->ir_v6_loc_addr; - newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newsk->sk_bound_dev_if = treq->ir_iif; newinet->inet_opt = NULL; diff --git a/drivers/net/ethernet/engleder/tsnep.h b/drivers/net/ethernet/engleder/tsnep.h index f188fba021a62..03e19aea9ea48 100644 --- a/drivers/net/ethernet/engleder/tsnep.h +++ b/drivers/net/ethernet/engleder/tsnep.h @@ -176,7 +176,7 @@ struct tsnep_adapter { struct tsnep_gcl gcl[2]; int next_gcl; - struct hwtstamp_config hwtstamp_config; + struct kernel_hwtstamp_config hwtstamp_config; struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_info; /* ptp clock lock */ @@ -203,7 +203,11 @@ extern const struct ethtool_ops tsnep_ethtool_ops; int tsnep_ptp_init(struct tsnep_adapter *adapter); void tsnep_ptp_cleanup(struct tsnep_adapter *adapter); -int tsnep_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd); +int tsnep_ptp_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config); +int tsnep_ptp_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); int tsnep_tc_init(struct tsnep_adapter *adapter); void tsnep_tc_cleanup(struct tsnep_adapter *adapter); diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c index eba73246f9866..b118407c30e87 100644 --- a/drivers/net/ethernet/engleder/tsnep_main.c +++ b/drivers/net/ethernet/engleder/tsnep_main.c @@ -2168,16 +2168,6 @@ static netdev_tx_t tsnep_netdev_xmit_frame(struct sk_buff *skb, return tsnep_xmit_frame_ring(skb, &adapter->tx[queue_mapping]); } -static int tsnep_netdev_ioctl(struct net_device *netdev, struct ifreq *ifr, - int cmd) -{ - if (!netif_running(netdev)) - return -EINVAL; - if (cmd == SIOCSHWTSTAMP || cmd == SIOCGHWTSTAMP) - return tsnep_ptp_ioctl(netdev, ifr, cmd); - return phy_mii_ioctl(netdev->phydev, ifr, cmd); -} - static void tsnep_netdev_set_multicast(struct net_device *netdev) { struct tsnep_adapter *adapter = netdev_priv(netdev); @@ -2384,7 +2374,7 @@ static const struct net_device_ops tsnep_netdev_ops = { .ndo_open = tsnep_netdev_open, .ndo_stop = tsnep_netdev_close, .ndo_start_xmit = tsnep_netdev_xmit_frame, - .ndo_eth_ioctl = tsnep_netdev_ioctl, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_set_rx_mode = tsnep_netdev_set_multicast, .ndo_get_stats64 = tsnep_netdev_get_stats64, .ndo_set_mac_address = tsnep_netdev_set_mac_address, @@ -2394,6 +2384,8 @@ static const struct net_device_ops tsnep_netdev_ops = { .ndo_bpf = tsnep_netdev_bpf, .ndo_xdp_xmit = tsnep_netdev_xdp_xmit, .ndo_xsk_wakeup = tsnep_netdev_xsk_wakeup, + .ndo_hwtstamp_get = tsnep_ptp_hwtstamp_get, + .ndo_hwtstamp_set = tsnep_ptp_hwtstamp_set, }; static int tsnep_mac_init(struct tsnep_adapter *adapter) diff --git a/drivers/net/ethernet/engleder/tsnep_ptp.c b/drivers/net/ethernet/engleder/tsnep_ptp.c index 54fbf0126815f..ae1308eb813de 100644 --- a/drivers/net/ethernet/engleder/tsnep_ptp.c +++ b/drivers/net/ethernet/engleder/tsnep_ptp.c @@ -19,57 +19,53 @@ void tsnep_get_system_time(struct tsnep_adapter *adapter, u64 *time) *time = (((u64)high) << 32) | ((u64)low); } -int tsnep_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +int tsnep_ptp_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { struct tsnep_adapter *adapter = netdev_priv(netdev); - struct hwtstamp_config config; - - if (!ifr) - return -EINVAL; - - if (cmd == SIOCSHWTSTAMP) { - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - return -ERANGE; - } - - memcpy(&adapter->hwtstamp_config, &config, - sizeof(adapter->hwtstamp_config)); + + *config = adapter->hwtstamp_config; + return 0; +} + +int tsnep_ptp_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct tsnep_adapter *adapter = netdev_priv(netdev); + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; } - if (copy_to_user(ifr->ifr_data, &adapter->hwtstamp_config, - sizeof(adapter->hwtstamp_config))) - return -EFAULT; + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + config->rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + adapter->hwtstamp_config = *config; return 0; } diff --git a/drivers/net/ethernet/fealnx.c b/drivers/net/ethernet/fealnx.c index 6ac8547ef9b8d..3c9961806f756 100644 --- a/drivers/net/ethernet/fealnx.c +++ b/drivers/net/ethernet/fealnx.c @@ -196,7 +196,7 @@ enum intr_status_bits { ERI = 0x00000080, /* receive early int */ CNTOVF = 0x00000040, /* counter overflow */ RBU = 0x00000020, /* receive buffer unavailable */ - TBU = 0x00000010, /* transmit buffer unavilable */ + TBU = 0x00000010, /* transmit buffer unavailable */ TI = 0x00000008, /* transmit interrupt */ RI = 0x00000004, /* receive interrupt */ RxErr = 0x00000002, /* receive error */ @@ -215,7 +215,7 @@ enum rx_mode_bits { CR_W_RXMODEMASK = 0x000000e0, CR_W_PROM = 0x00000080, /* promiscuous mode */ CR_W_AB = 0x00000040, /* accept broadcast */ - CR_W_AM = 0x00000020, /* accept mutlicast */ + CR_W_AM = 0x00000020, /* accept multicast */ CR_W_ARP = 0x00000008, /* receive runt pkt */ CR_W_ALP = 0x00000004, /* receive long pkt */ CR_W_SEP = 0x00000002, /* receive error pkt */ diff --git a/drivers/net/ethernet/freescale/Kconfig b/drivers/net/ethernet/freescale/Kconfig index bbef47c3480c5..e2a591cf9601f 100644 --- a/drivers/net/ethernet/freescale/Kconfig +++ b/drivers/net/ethernet/freescale/Kconfig @@ -28,6 +28,7 @@ config FEC depends on PTP_1588_CLOCK_OPTIONAL select CRC32 select PHYLIB + select FIXED_PHY if M5272 select PAGE_POOL imply PAGE_POOL_STATS imply NET_SELFTESTS diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 0535e92404e3c..d5e5800b84eff 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -14,12 +14,21 @@ u32 enetc_port_mac_rd(struct enetc_si *si, u32 reg) { + /* ENETC with pseudo MAC does not have Ethernet MAC + * port registers. + */ + if (enetc_is_pseudo_mac(si)) + return 0; + return enetc_port_rd(&si->hw, reg); } EXPORT_SYMBOL_GPL(enetc_port_mac_rd); void enetc_port_mac_wr(struct enetc_si *si, u32 reg, u32 val) { + if (enetc_is_pseudo_mac(si)) + return; + enetc_port_wr(&si->hw, reg, val); if (si->hw_features & ENETC_SI_F_QBU) enetc_port_wr(&si->hw, reg + si->drvdata->pmac_offset, val); @@ -3367,7 +3376,8 @@ int enetc_hwtstamp_set(struct net_device *ndev, new_offloads |= ENETC_F_TX_TSTAMP; break; case HWTSTAMP_TX_ONESTEP_SYNC: - if (!enetc_si_is_pf(priv->si)) + if (!enetc_si_is_pf(priv->si) || + enetc_is_pseudo_mac(priv->si)) return -EOPNOTSUPP; new_offloads &= ~ENETC_F_TX_TSTAMP_MASK; @@ -3708,6 +3718,13 @@ static const struct enetc_drvdata enetc4_pf_data = { .eth_ops = &enetc4_pf_ethtool_ops, }; +static const struct enetc_drvdata enetc4_ppm_data = { + .sysclk_freq = ENETC_CLK_333M, + .tx_csum = true, + .max_frags = ENETC4_MAX_SKB_FRAGS, + .eth_ops = &enetc4_ppm_ethtool_ops, +}; + static const struct enetc_drvdata enetc_vf_data = { .sysclk_freq = ENETC_CLK_400M, .max_frags = ENETC_MAX_SKB_FRAGS, @@ -3727,6 +3744,15 @@ static const struct enetc_platform_info enetc_info[] = { .dev_id = ENETC_DEV_ID_VF, .data = &enetc_vf_data, }, + { + .revision = ENETC_REV_4_3, + .dev_id = NXP_ENETC_PPM_DEV_ID, + .data = &enetc4_ppm_data, + }, + { .revision = ENETC_REV_4_3, + .dev_id = NXP_ENETC_PF_DEV_ID, + .data = &enetc4_pf_data, + }, }; int enetc_get_driver_data(struct enetc_si *si) diff --git a/drivers/net/ethernet/freescale/enetc/enetc.h b/drivers/net/ethernet/freescale/enetc/enetc.h index f279fa597991e..dce27bd67a7d1 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.h +++ b/drivers/net/ethernet/freescale/enetc/enetc.h @@ -273,6 +273,7 @@ enum enetc_errata { #define ENETC_SI_F_QBV BIT(1) #define ENETC_SI_F_QBU BIT(2) #define ENETC_SI_F_LSO BIT(3) +#define ENETC_SI_F_PPM BIT(4) /* pseudo MAC */ struct enetc_drvdata { u32 pmac_offset; /* Only valid for PSI which supports 802.1Qbu */ @@ -362,6 +363,11 @@ static inline int enetc_pf_to_port(struct pci_dev *pf_pdev) } } +static inline bool enetc_is_pseudo_mac(struct enetc_si *si) +{ + return si->hw_features & ENETC_SI_F_PPM; +} + #define ENETC_MAX_NUM_TXQS 8 #define ENETC_INT_NAME_MAX (IFNAMSIZ + 8) @@ -534,6 +540,8 @@ int enetc_hwtstamp_set(struct net_device *ndev, extern const struct ethtool_ops enetc_pf_ethtool_ops; extern const struct ethtool_ops enetc4_pf_ethtool_ops; extern const struct ethtool_ops enetc_vf_ethtool_ops; +extern const struct ethtool_ops enetc4_ppm_ethtool_ops; + void enetc_set_ethtool_ops(struct net_device *ndev); void enetc_mm_link_state_update(struct enetc_ndev_priv *priv, bool link); void enetc_mm_commit_preemptible_tcs(struct enetc_ndev_priv *priv); diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h index 19bf0e89cdc25..ebea4298791ce 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc4_hw.h @@ -11,6 +11,7 @@ #define NXP_ENETC_VENDOR_ID 0x1131 #define NXP_ENETC_PF_DEV_ID 0xe101 +#define NXP_ENETC_PPM_DEV_ID 0xe110 /**********************Station interface registers************************/ /* Station interface LSO segmentation flag mask register 0/1 */ @@ -115,6 +116,10 @@ #define PMCAPR_HD BIT(8) #define PMCAPR_FP GENMASK(10, 9) +/* Port capability register */ +#define ENETC4_PCAPR 0x4000 +#define PCAPR_LINK_TYPE BIT(4) + /* Port configuration register */ #define ENETC4_PCR 0x4010 #define PCR_HDR_FMT BIT(0) @@ -193,4 +198,29 @@ #define SSP_1G 2 #define PM_IF_MODE_ENA BIT(15) +/**********************ENETC Pseudo MAC port registers************************/ +/* Port pseudo MAC receive octets counter (64-bit) */ +#define ENETC4_PPMROCR 0x5080 + +/* Port pseudo MAC receive unicast frame counter register (64-bit) */ +#define ENETC4_PPMRUFCR 0x5088 + +/* Port pseudo MAC receive multicast frame counter register (64-bit) */ +#define ENETC4_PPMRMFCR 0x5090 + +/* Port pseudo MAC receive broadcast frame counter register (64-bit) */ +#define ENETC4_PPMRBFCR 0x5098 + +/* Port pseudo MAC transmit octets counter (64-bit) */ +#define ENETC4_PPMTOCR 0x50c0 + +/* Port pseudo MAC transmit unicast frame counter register (64-bit) */ +#define ENETC4_PPMTUFCR 0x50c8 + +/* Port pseudo MAC transmit multicast frame counter register (64-bit) */ +#define ENETC4_PPMTMFCR 0x50d0 + +/* Port pseudo MAC transmit broadcast frame counter register (64-bit) */ +#define ENETC4_PPMTBFCR 0x50d8 + #endif diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c index 82c443b28b154..498346dd996aa 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c @@ -41,6 +41,16 @@ static void enetc4_get_port_caps(struct enetc_pf *pf) pf->caps.mac_filter_num = val & PSIMAFCAPR_NUM_MAC_AFTE; } +static void enetc4_get_psi_hw_features(struct enetc_si *si) +{ + struct enetc_hw *hw = &si->hw; + u32 val; + + val = enetc_port_rd(hw, ENETC4_PCAPR); + if (val & PCAPR_LINK_TYPE) + si->hw_features |= ENETC_SI_F_PPM; +} + static void enetc4_pf_set_si_primary_mac(struct enetc_hw *hw, int si, const u8 *addr) { @@ -277,6 +287,7 @@ static int enetc4_pf_struct_init(struct enetc_si *si) pf->ops = &enetc4_pf_ops; enetc4_get_port_caps(pf); + enetc4_get_psi_hw_features(si); return 0; } @@ -589,6 +600,9 @@ static void enetc4_mac_config(struct enetc_pf *pf, unsigned int mode, struct enetc_si *si = pf->si; u32 val; + if (enetc_is_pseudo_mac(si)) + return; + val = enetc_port_mac_rd(si, ENETC4_PM_IF_MODE(0)); val &= ~(PM_IF_MODE_IFMODE | PM_IF_MODE_ENA); @@ -1071,6 +1085,7 @@ static void enetc4_pf_remove(struct pci_dev *pdev) static const struct pci_device_id enetc4_pf_id_table[] = { { PCI_DEVICE(NXP_ENETC_VENDOR_ID, NXP_ENETC_PF_DEV_ID) }, + { PCI_DEVICE(NXP_ENETC_VENDOR_ID, NXP_ENETC_PPM_DEV_ID) }, { 0, } /* End of table. */ }; MODULE_DEVICE_TABLE(pci, enetc4_pf_id_table); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index 71d052de669ab..3e222321b937c 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -435,6 +435,48 @@ static void enetc_get_eth_mac_stats(struct net_device *ndev, } } +static void enetc_ppm_mac_stats(struct enetc_si *si, + struct ethtool_eth_mac_stats *s) +{ + struct enetc_hw *hw = &si->hw; + u64 rufcr, rmfcr, rbfcr; + u64 tufcr, tmfcr, tbfcr; + + rufcr = enetc_port_rd64(hw, ENETC4_PPMRUFCR); + rmfcr = enetc_port_rd64(hw, ENETC4_PPMRMFCR); + rbfcr = enetc_port_rd64(hw, ENETC4_PPMRBFCR); + + tufcr = enetc_port_rd64(hw, ENETC4_PPMTUFCR); + tmfcr = enetc_port_rd64(hw, ENETC4_PPMTMFCR); + tbfcr = enetc_port_rd64(hw, ENETC4_PPMTBFCR); + + s->FramesTransmittedOK = tufcr + tmfcr + tbfcr; + s->FramesReceivedOK = rufcr + rmfcr + rbfcr; + s->OctetsTransmittedOK = enetc_port_rd64(hw, ENETC4_PPMTOCR); + s->OctetsReceivedOK = enetc_port_rd64(hw, ENETC4_PPMROCR); + s->MulticastFramesXmittedOK = tmfcr; + s->BroadcastFramesXmittedOK = tbfcr; + s->MulticastFramesReceivedOK = rmfcr; + s->BroadcastFramesReceivedOK = rbfcr; +} + +static void enetc_ppm_get_eth_mac_stats(struct net_device *ndev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct enetc_ndev_priv *priv = netdev_priv(ndev); + + switch (mac_stats->src) { + case ETHTOOL_MAC_STATS_SRC_EMAC: + enetc_ppm_mac_stats(priv->si, mac_stats); + break; + case ETHTOOL_MAC_STATS_SRC_PMAC: + break; + case ETHTOOL_MAC_STATS_SRC_AGGREGATE: + ethtool_aggregate_mac_stats(ndev, mac_stats); + break; + } +} + static void enetc_get_eth_ctrl_stats(struct net_device *ndev, struct ethtool_eth_ctrl_stats *ctrl_stats) { @@ -894,6 +936,9 @@ static int enetc_get_phc_index_by_pdev(struct enetc_si *si) case ENETC_REV_4_1: devfn = PCI_DEVFN(24, 0); break; + case ENETC_REV_4_3: + devfn = PCI_DEVFN(0, 1); + break; default: return -1; } @@ -1313,6 +1358,25 @@ const struct ethtool_ops enetc_pf_ethtool_ops = { .get_mm_stats = enetc_get_mm_stats, }; +const struct ethtool_ops enetc4_ppm_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS | + ETHTOOL_COALESCE_MAX_FRAMES | + ETHTOOL_COALESCE_USE_ADAPTIVE_RX, + .get_eth_mac_stats = enetc_ppm_get_eth_mac_stats, + .get_rxnfc = enetc4_get_rxnfc, + .get_rxfh_key_size = enetc_get_rxfh_key_size, + .get_rxfh_indir_size = enetc_get_rxfh_indir_size, + .get_rxfh = enetc_get_rxfh, + .set_rxfh = enetc_set_rxfh, + .get_rxfh_fields = enetc_get_rxfh_fields, + .get_ringparam = enetc_get_ringparam, + .get_coalesce = enetc_get_coalesce, + .set_coalesce = enetc_set_coalesce, + .get_link_ksettings = enetc_get_link_ksettings, + .set_link_ksettings = enetc_set_link_ksettings, + .get_link = ethtool_op_get_link, +}; + const struct ethtool_ops enetc_vf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_MAX_FRAMES | diff --git a/drivers/net/ethernet/freescale/enetc/enetc_hw.h b/drivers/net/ethernet/freescale/enetc/enetc_hw.h index 377c963258147..7b882b8921fe9 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_hw.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_hw.h @@ -378,6 +378,7 @@ enum enetc_bdr_type {TX, RX}; #define EIPBRR0_REVISION GENMASK(15, 0) #define ENETC_REV_1_0 0x0100 #define ENETC_REV_4_1 0X0401 +#define ENETC_REV_4_3 0x0403 #define ENETC_G_EIPBRR1 0x0bfc #define ENETC_G_EPFBLPR(n) (0xd00 + 4 * (n)) diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c index edf14a95cab73..9c634205e2a76 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf_common.c @@ -109,7 +109,7 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->hw_features = NETIF_F_SG | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_LOOPBACK | + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_CSUM | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_L4; ndev->features = NETIF_F_HIGHDMA | NETIF_F_SG | NETIF_F_RXCSUM | @@ -133,6 +133,9 @@ void enetc_pf_netdev_setup(struct enetc_si *si, struct net_device *ndev, ndev->features |= NETIF_F_RXHASH; } + if (!enetc_is_pseudo_mac(si)) + ndev->hw_features |= NETIF_F_LOOPBACK; + /* TODO: currently, i.MX95 ENETC driver does not support advanced features */ if (!is_enetc_rev1(si)) goto end; diff --git a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c index bcb8eefeb93c0..d7aee3c934d3a 100644 --- a/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c +++ b/drivers/net/ethernet/freescale/enetc/netc_blk_ctrl.c @@ -47,6 +47,13 @@ #define PCS_PROT_SFI BIT(4) #define PCS_PROT_10G_SXGMII BIT(6) +#define IMX94_EXT_PIN_CONTROL 0x10 +#define MAC2_MAC3_SEL BIT(1) + +#define IMX94_NETC_LINK_CFG(a) (0x4c + (a) * 4) +#define NETC_LINK_CFG_MII_PROT GENMASK(3, 0) +#define NETC_LINK_CFG_IO_VAR GENMASK(19, 16) + /* NETC privileged register block register */ #define PRB_NETCRR 0x100 #define NETCRR_SR BIT(0) @@ -59,6 +66,7 @@ /* NETC integrated endpoint register block register */ #define IERB_EMDIOFAUXR 0x344 #define IERB_T0FAUXR 0x444 +#define IERB_ETBCR(a) (0x300c + 0x100 * (a)) #define IERB_EFAUXR(a) (0x3044 + 0x100 * (a)) #define IERB_VFAUXR(a) (0x4004 + 0x40 * (a)) #define FAUXR_LDID GENMASK(3, 0) @@ -68,6 +76,19 @@ #define IMX95_ENETC1_BUS_DEVFN 0x40 #define IMX95_ENETC2_BUS_DEVFN 0x80 +#define IMX94_ENETC0_BUS_DEVFN 0x100 +#define IMX94_ENETC1_BUS_DEVFN 0x140 +#define IMX94_ENETC2_BUS_DEVFN 0x180 +#define IMX94_TIMER0_BUS_DEVFN 0x1 +#define IMX94_TIMER1_BUS_DEVFN 0x101 +#define IMX94_TIMER2_BUS_DEVFN 0x181 +#define IMX94_ENETC0_LINK 3 +#define IMX94_ENETC1_LINK 4 +#define IMX94_ENETC2_LINK 5 + +#define NETC_ENETC_ID(a) (a) +#define NETC_TIMER_ID(a) (a) + /* Flags for different platforms */ #define NETC_HAS_NETCMIX BIT(0) @@ -192,6 +213,90 @@ static int imx95_netcmix_init(struct platform_device *pdev) return 0; } +static int imx94_enetc_get_link_id(struct device_node *np) +{ + int bus_devfn = netc_of_pci_get_bus_devfn(np); + + /* Parse ENETC link number */ + switch (bus_devfn) { + case IMX94_ENETC0_BUS_DEVFN: + return IMX94_ENETC0_LINK; + case IMX94_ENETC1_BUS_DEVFN: + return IMX94_ENETC1_LINK; + case IMX94_ENETC2_BUS_DEVFN: + return IMX94_ENETC2_LINK; + default: + return -EINVAL; + } +} + +static int imx94_link_config(struct netc_blk_ctrl *priv, + struct device_node *np, int link_id) +{ + phy_interface_t interface; + int mii_proto; + u32 val; + + /* The node may be disabled and does not have a 'phy-mode' + * or 'phy-connection-type' property. + */ + if (of_get_phy_mode(np, &interface)) + return 0; + + mii_proto = netc_get_link_mii_protocol(interface); + if (mii_proto < 0) + return mii_proto; + + val = mii_proto & NETC_LINK_CFG_MII_PROT; + if (val == MII_PROT_SERIAL) + val = u32_replace_bits(val, IO_VAR_16FF_16G_SERDES, + NETC_LINK_CFG_IO_VAR); + + netc_reg_write(priv->netcmix, IMX94_NETC_LINK_CFG(link_id), val); + + return 0; +} + +static int imx94_enetc_link_config(struct netc_blk_ctrl *priv, + struct device_node *np) +{ + int link_id = imx94_enetc_get_link_id(np); + + if (link_id < 0) + return link_id; + + return imx94_link_config(priv, np, link_id); +} + +static int imx94_netcmix_init(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + struct device_node *np = pdev->dev.of_node; + u32 val; + int err; + + for_each_child_of_node_scoped(np, child) { + for_each_child_of_node_scoped(child, gchild) { + if (!of_device_is_compatible(gchild, "pci1131,e101")) + continue; + + err = imx94_enetc_link_config(priv, gchild); + if (err) + return err; + } + } + + /* ENETC 0 and switch port 2 share the same parallel interface. + * Currently, the switch is not supported, so this interface is + * used by ENETC 0 by default. + */ + val = netc_reg_read(priv->netcmix, IMX94_EXT_PIN_CONTROL); + val |= MAC2_MAC3_SEL; + netc_reg_write(priv->netcmix, IMX94_EXT_PIN_CONTROL, val); + + return 0; +} + static bool netc_ierb_is_locked(struct netc_blk_ctrl *priv) { return !!(netc_reg_read(priv->prb, PRB_NETCRR) & NETCRR_LOCK); @@ -247,6 +352,98 @@ static int imx95_ierb_init(struct platform_device *pdev) return 0; } +static int imx94_get_enetc_id(struct device_node *np) +{ + int bus_devfn = netc_of_pci_get_bus_devfn(np); + + /* Parse ENETC offset */ + switch (bus_devfn) { + case IMX94_ENETC0_BUS_DEVFN: + return NETC_ENETC_ID(0); + case IMX94_ENETC1_BUS_DEVFN: + return NETC_ENETC_ID(1); + case IMX94_ENETC2_BUS_DEVFN: + return NETC_ENETC_ID(2); + default: + return -EINVAL; + } +} + +static int imx94_get_timer_id(struct device_node *np) +{ + int bus_devfn = netc_of_pci_get_bus_devfn(np); + + /* Parse NETC PTP timer ID, the timer0 is on bus 0, + * the timer 1 and timer2 is on bus 1. + */ + switch (bus_devfn) { + case IMX94_TIMER0_BUS_DEVFN: + return NETC_TIMER_ID(0); + case IMX94_TIMER1_BUS_DEVFN: + return NETC_TIMER_ID(1); + case IMX94_TIMER2_BUS_DEVFN: + return NETC_TIMER_ID(2); + default: + return -EINVAL; + } +} + +static int imx94_enetc_update_tid(struct netc_blk_ctrl *priv, + struct device_node *np) +{ + struct device *dev = &priv->pdev->dev; + struct device_node *timer_np; + int eid, tid; + + eid = imx94_get_enetc_id(np); + if (eid < 0) { + dev_err(dev, "Failed to get ENETC ID\n"); + return eid; + } + + timer_np = of_parse_phandle(np, "ptp-timer", 0); + if (!timer_np) { + /* If 'ptp-timer' is not present, the timer1 is the default + * timer of all standalone ENETCs, which is on the same PCIe + * bus as these ENETCs. + */ + tid = NETC_TIMER_ID(1); + goto end; + } + + tid = imx94_get_timer_id(timer_np); + of_node_put(timer_np); + if (tid < 0) { + dev_err(dev, "Failed to get NETC Timer ID\n"); + return tid; + } + +end: + netc_reg_write(priv->ierb, IERB_ETBCR(eid), tid); + + return 0; +} + +static int imx94_ierb_init(struct platform_device *pdev) +{ + struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); + struct device_node *np = pdev->dev.of_node; + int err; + + for_each_child_of_node_scoped(np, child) { + for_each_child_of_node_scoped(child, gchild) { + if (!of_device_is_compatible(gchild, "pci1131,e101")) + continue; + + err = imx94_enetc_update_tid(priv, gchild); + if (err) + return err; + } + } + + return 0; +} + static int netc_ierb_init(struct platform_device *pdev) { struct netc_blk_ctrl *priv = platform_get_drvdata(pdev); @@ -340,8 +537,15 @@ static const struct netc_devinfo imx95_devinfo = { .ierb_init = imx95_ierb_init, }; +static const struct netc_devinfo imx94_devinfo = { + .flags = NETC_HAS_NETCMIX, + .netcmix_init = imx94_netcmix_init, + .ierb_init = imx94_ierb_init, +}; + static const struct of_device_id netc_blk_ctrl_match[] = { { .compatible = "nxp,imx95-netc-blk-ctrl", .data = &imx95_devinfo }, + { .compatible = "nxp,imx94-netc-blk-ctrl", .data = &imx94_devinfo }, {}, }; MODULE_DEVICE_TABLE(of, netc_blk_ctrl_match); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 3222359ac15b7..b6fbb84cfb06d 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -52,6 +52,7 @@ #include #include #include +#include #include #include #include @@ -2233,7 +2234,6 @@ static int fec_enet_mdio_read_c22(struct mii_bus *bus, int mii_id, int regnum) ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); out: - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); return ret; @@ -2282,7 +2282,6 @@ static int fec_enet_mdio_read_c45(struct mii_bus *bus, int mii_id, ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA)); out: - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); return ret; @@ -2314,7 +2313,6 @@ static int fec_enet_mdio_write_c22(struct mii_bus *bus, int mii_id, int regnum, if (ret) netdev_err(fep->netdev, "MDIO write timeout\n"); - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); return ret; @@ -2358,7 +2356,6 @@ static int fec_enet_mdio_write_c45(struct mii_bus *bus, int mii_id, netdev_err(fep->netdev, "MDIO write timeout\n"); out: - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); return ret; @@ -2478,11 +2475,8 @@ static int fec_enet_parse_rgmii_delay(struct fec_enet_private *fep, static int fec_enet_mii_probe(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); - struct phy_device *phy_dev = NULL; - char mdio_bus_id[MII_BUS_ID_SIZE]; - char phy_name[MII_BUS_ID_SIZE + 3]; - int phy_id; - int dev_id = fep->dev_id; + struct phy_device *phy_dev; + int ret; if (fep->phy_node) { phy_dev = of_phy_connect(ndev, fep->phy_node, @@ -2494,30 +2488,28 @@ static int fec_enet_mii_probe(struct net_device *ndev) } } else { /* check for attached phy */ - for (phy_id = 0; (phy_id < PHY_MAX_ADDR); phy_id++) { - if (!mdiobus_is_registered_device(fep->mii_bus, phy_id)) - continue; - if (dev_id--) - continue; - strscpy(mdio_bus_id, fep->mii_bus->id, MII_BUS_ID_SIZE); - break; - } + phy_dev = phy_find_first(fep->mii_bus); + if (fep->dev_id && phy_dev) + phy_dev = phy_find_next(fep->mii_bus, phy_dev); - if (phy_id >= PHY_MAX_ADDR) { + if (!phy_dev) { netdev_info(ndev, "no PHY, assuming direct connection to switch\n"); - strscpy(mdio_bus_id, "fixed-0", MII_BUS_ID_SIZE); - phy_id = 0; + phy_dev = fixed_phy_register_100fd(); + if (IS_ERR(phy_dev)) { + netdev_err(ndev, "could not register fixed PHY\n"); + return PTR_ERR(phy_dev); + } } - snprintf(phy_name, sizeof(phy_name), - PHY_ID_FMT, mdio_bus_id, phy_id); - phy_dev = phy_connect(ndev, phy_name, &fec_enet_adjust_link, - fep->phy_interface); - } + ret = phy_connect_direct(ndev, phy_dev, &fec_enet_adjust_link, + fep->phy_interface); + if (ret) { + if (phy_is_pseudo_fixed_link(phy_dev)) + fixed_phy_unregister(phy_dev); + netdev_err(ndev, "could not attach to PHY\n"); + return ret; + } - if (IS_ERR(phy_dev)) { - netdev_err(ndev, "could not attach to PHY\n"); - return PTR_ERR(phy_dev); } /* mask with MAC supported features */ @@ -2554,7 +2546,6 @@ static int fec_enet_mii_init(struct platform_device *pdev) int err = -ENXIO; u32 mii_speed, holdtime; u32 bus_freq; - int addr; /* * The i.MX28 dual fec interfaces are not equal. @@ -2669,11 +2660,8 @@ static int fec_enet_mii_init(struct platform_device *pdev) of_node_put(node); /* find all the PHY devices on the bus and set mac_managed_pm to true */ - for (addr = 0; addr < PHY_MAX_ADDR; addr++) { - phydev = mdiobus_get_phy(fep->mii_bus, addr); - if (phydev) - phydev->mac_managed_pm = true; - } + mdiobus_for_each_phy(fep->mii_bus, phydev) + phydev->mac_managed_pm = true; mii_cnt++; @@ -2841,7 +2829,6 @@ static void fec_enet_get_regs(struct net_device *ndev, buf[off] = readl(&theregs[off]); } - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); } @@ -3618,7 +3605,6 @@ fec_enet_open(struct net_device *ndev) err_enet_alloc: fec_enet_clk_enable(ndev, false); clk_enable: - pm_runtime_mark_last_busy(&fep->pdev->dev); pm_runtime_put_autosuspend(&fep->pdev->dev); pinctrl_pm_select_sleep_state(&fep->pdev->dev); return ret; @@ -3628,8 +3614,9 @@ static int fec_enet_close(struct net_device *ndev) { struct fec_enet_private *fep = netdev_priv(ndev); + struct phy_device *phy_dev = ndev->phydev; - phy_stop(ndev->phydev); + phy_stop(phy_dev); if (netif_device_present(ndev)) { napi_disable(&fep->napi); @@ -3637,7 +3624,10 @@ fec_enet_close(struct net_device *ndev) fec_stop(ndev); } - phy_disconnect(ndev->phydev); + phy_disconnect(phy_dev); + + if (!fep->phy_node && phy_is_pseudo_fixed_link(phy_dev)) + fixed_phy_unregister(phy_dev); if (fep->quirks & FEC_QUIRK_ERR006687) imx6q_cpuidle_fec_irqs_unused(); @@ -3649,7 +3639,6 @@ fec_enet_close(struct net_device *ndev) cpu_latency_qos_remove_request(&fep->pm_qos_req); pinctrl_pm_select_sleep_state(&fep->pdev->dev); - pm_runtime_mark_last_busy(&fep->pdev->dev); pm_runtime_put_autosuspend(&fep->pdev->dev); fec_enet_free_buffers(ndev); @@ -4618,7 +4607,6 @@ fec_probe(struct platform_device *pdev) INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work); - pm_runtime_mark_last_busy(&pdev->dev); pm_runtime_put_autosuspend(&pdev->dev); return 0; diff --git a/drivers/net/ethernet/fungible/funeth/funeth.h b/drivers/net/ethernet/fungible/funeth/funeth.h index 1250e10d21db2..55e705e239f82 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth.h +++ b/drivers/net/ethernet/fungible/funeth/funeth.h @@ -4,7 +4,7 @@ #define _FUNETH_H #include -#include +#include #include #include #include @@ -121,7 +121,7 @@ struct funeth_priv { u8 rx_coal_usec; u8 rx_coal_count; - struct hwtstamp_config hwtstamp_cfg; + struct kernel_hwtstamp_config hwtstamp_cfg; /* cumulative queue stats from earlier queue instances */ u64 tx_packets; diff --git a/drivers/net/ethernet/fungible/funeth/funeth_main.c b/drivers/net/ethernet/fungible/funeth/funeth_main.c index ac86179a0a817..792cddac6f1b9 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_main.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_main.c @@ -1014,26 +1014,25 @@ static int fun_get_port_attributes(struct net_device *netdev) return 0; } -static int fun_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) +static int fun_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) { const struct funeth_priv *fp = netdev_priv(dev); - return copy_to_user(ifr->ifr_data, &fp->hwtstamp_cfg, - sizeof(fp->hwtstamp_cfg)) ? -EFAULT : 0; + *config = fp->hwtstamp_cfg; + return 0; } -static int fun_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) +static int fun_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct funeth_priv *fp = netdev_priv(dev); - struct hwtstamp_config cfg; - - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; /* no TX HW timestamps */ - cfg.tx_type = HWTSTAMP_TX_OFF; + config->tx_type = HWTSTAMP_TX_OFF; - switch (cfg.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: break; case HWTSTAMP_FILTER_ALL: @@ -1051,26 +1050,14 @@ static int fun_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - cfg.rx_filter = HWTSTAMP_FILTER_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } - fp->hwtstamp_cfg = cfg; - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; -} - -static int fun_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - case SIOCSHWTSTAMP: - return fun_hwtstamp_set(dev, ifr); - case SIOCGHWTSTAMP: - return fun_hwtstamp_get(dev, ifr); - default: - return -EOPNOTSUPP; - } + fp->hwtstamp_cfg = *config; + return 0; } /* Prepare the queues for XDP. */ @@ -1340,7 +1327,6 @@ static const struct net_device_ops fun_netdev_ops = { .ndo_change_mtu = fun_change_mtu, .ndo_set_mac_address = fun_set_macaddr, .ndo_validate_addr = eth_validate_addr, - .ndo_eth_ioctl = fun_ioctl, .ndo_uninit = fun_uninit, .ndo_bpf = fun_xdp, .ndo_xdp_xmit = fun_xdp_xmit_frames, @@ -1348,6 +1334,8 @@ static const struct net_device_ops fun_netdev_ops = { .ndo_set_vf_vlan = fun_set_vf_vlan, .ndo_set_vf_rate = fun_set_vf_rate, .ndo_get_vf_config = fun_get_vf_config, + .ndo_hwtstamp_get = fun_hwtstamp_get, + .ndo_hwtstamp_set = fun_hwtstamp_set, }; #define GSO_ENCAP_FLAGS (NETIF_F_GSO_GRE | NETIF_F_GSO_IPXIP4 | \ diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h index 4cc6dcbfd367b..970d5ca8cddee 100644 --- a/drivers/net/ethernet/google/gve/gve.h +++ b/drivers/net/ethernet/google/gve/gve.h @@ -59,8 +59,6 @@ #define GVE_DEFAULT_RX_BUFFER_SIZE 2048 -#define GVE_MAX_RX_BUFFER_SIZE 4096 - #define GVE_XDP_RX_BUFFER_SIZE_DQO 4096 #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048 @@ -207,6 +205,13 @@ struct gve_rx_buf_state_dqo { s16 next; }; +/* Wrapper for XDP Rx metadata */ +struct gve_xdp_buff { + struct xdp_buff xdp; + struct gve_priv *gve; + const struct gve_rx_compl_desc_dqo *compl_desc; +}; + /* `head` and `tail` are indices into an array, or -1 if empty. */ struct gve_index_list { s16 head; @@ -1169,6 +1174,12 @@ static inline bool gve_is_gqi(struct gve_priv *priv) priv->queue_format == GVE_GQI_QPL_FORMAT; } +static inline bool gve_is_dqo(struct gve_priv *priv) +{ + return priv->queue_format == GVE_DQO_RDA_FORMAT || + priv->queue_format == GVE_DQO_QPL_FORMAT; +} + static inline u32 gve_num_tx_queues(struct gve_priv *priv) { return priv->tx_cfg.num_queues + priv->tx_cfg.num_xdp_queues; @@ -1249,9 +1260,12 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv, struct gve_rx_alloc_rings_cfg *cfg); void gve_rx_start_ring_gqi(struct gve_priv *priv, int idx); void gve_rx_stop_ring_gqi(struct gve_priv *priv, int idx); -u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hplit); bool gve_header_split_supported(const struct gve_priv *priv); -int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split); +int gve_set_rx_buf_len_config(struct gve_priv *priv, u32 rx_buf_len, + struct netlink_ext_ack *extack, + struct gve_rx_alloc_rings_cfg *rx_alloc_cfg); +int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split, + struct gve_rx_alloc_rings_cfg *rx_alloc_cfg); /* rx buffer handling */ int gve_buf_ref_cnt(struct gve_rx_buf_state_dqo *bs); void gve_free_page_dqo(struct gve_priv *priv, struct gve_rx_buf_state_dqo *bs, diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c index 4f33d094a2ef4..b72cc0fa2ba2b 100644 --- a/drivers/net/ethernet/google/gve/gve_adminq.c +++ b/drivers/net/ethernet/google/gve/gve_adminq.c @@ -987,6 +987,10 @@ static void gve_enable_supported_features(struct gve_priv *priv, dev_info(&priv->pdev->dev, "BUFFER SIZES device option enabled with max_rx_buffer_size of %u, header_buf_size of %u.\n", priv->max_rx_buffer_size, priv->header_buf_size); + if (gve_is_dqo(priv) && + priv->max_rx_buffer_size > GVE_DEFAULT_RX_BUFFER_SIZE) + priv->rx_cfg.packet_buffer_size = + priv->max_rx_buffer_size; } /* Read and store ring size ranges given by device */ diff --git a/drivers/net/ethernet/google/gve/gve_dqo.h b/drivers/net/ethernet/google/gve/gve_dqo.h index 6eb442096e02e..5871f773f0c70 100644 --- a/drivers/net/ethernet/google/gve/gve_dqo.h +++ b/drivers/net/ethernet/google/gve/gve_dqo.h @@ -36,6 +36,7 @@ netdev_tx_t gve_tx_dqo(struct sk_buff *skb, struct net_device *dev); netdev_features_t gve_features_check_dqo(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); +int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp); bool gve_tx_poll_dqo(struct gve_notify_block *block, bool do_clean); bool gve_xdp_poll_dqo(struct gve_notify_block *block); bool gve_xsk_tx_poll_dqo(struct gve_notify_block *block, int budget); diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index d0a223250845b..52500ae8348e6 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -529,6 +529,8 @@ static void gve_get_ringparam(struct net_device *netdev, cmd->rx_pending = priv->rx_desc_cnt; cmd->tx_pending = priv->tx_desc_cnt; + kernel_cmd->rx_buf_len = priv->rx_cfg.packet_buffer_size; + if (!gve_header_split_supported(priv)) kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_UNKNOWN; else if (priv->header_split_enabled) @@ -537,34 +539,6 @@ static void gve_get_ringparam(struct net_device *netdev, kernel_cmd->tcp_data_split = ETHTOOL_TCP_DATA_SPLIT_DISABLED; } -static int gve_adjust_ring_sizes(struct gve_priv *priv, - u16 new_tx_desc_cnt, - u16 new_rx_desc_cnt) -{ - struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; - struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; - int err; - - /* get current queue configuration */ - gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); - - /* copy over the new ring_size from ethtool */ - tx_alloc_cfg.ring_size = new_tx_desc_cnt; - rx_alloc_cfg.ring_size = new_rx_desc_cnt; - - if (netif_running(priv->dev)) { - err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); - if (err) - return err; - } - - /* Set new ring_size for the next up */ - priv->tx_desc_cnt = new_tx_desc_cnt; - priv->rx_desc_cnt = new_rx_desc_cnt; - - return 0; -} - static int gve_validate_req_ring_size(struct gve_priv *priv, u16 new_tx_desc_cnt, u16 new_rx_desc_cnt) { @@ -584,34 +558,68 @@ static int gve_validate_req_ring_size(struct gve_priv *priv, u16 new_tx_desc_cnt return 0; } +static int gve_set_ring_sizes_config(struct gve_priv *priv, u16 new_tx_desc_cnt, + u16 new_rx_desc_cnt, + struct gve_tx_alloc_rings_cfg *tx_alloc_cfg, + struct gve_rx_alloc_rings_cfg *rx_alloc_cfg) +{ + if (new_tx_desc_cnt == priv->tx_desc_cnt && + new_rx_desc_cnt == priv->rx_desc_cnt) + return 0; + + if (!priv->modify_ring_size_enabled) { + dev_err(&priv->pdev->dev, "Modify ring size is not supported.\n"); + return -EOPNOTSUPP; + } + + if (gve_validate_req_ring_size(priv, new_tx_desc_cnt, new_rx_desc_cnt)) + return -EINVAL; + + tx_alloc_cfg->ring_size = new_tx_desc_cnt; + rx_alloc_cfg->ring_size = new_rx_desc_cnt; + return 0; +} + static int gve_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *cmd, struct kernel_ethtool_ringparam *kernel_cmd, struct netlink_ext_ack *extack) { + struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; + struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; struct gve_priv *priv = netdev_priv(netdev); - u16 new_tx_cnt, new_rx_cnt; int err; - err = gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split); + gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); + + err = gve_set_rx_buf_len_config(priv, kernel_cmd->rx_buf_len, extack, + &rx_alloc_cfg); if (err) return err; - if (cmd->tx_pending == priv->tx_desc_cnt && cmd->rx_pending == priv->rx_desc_cnt) - return 0; - - if (!priv->modify_ring_size_enabled) { - dev_err(&priv->pdev->dev, "Modify ring size is not supported.\n"); - return -EOPNOTSUPP; - } - - new_tx_cnt = cmd->tx_pending; - new_rx_cnt = cmd->rx_pending; + err = gve_set_hsplit_config(priv, kernel_cmd->tcp_data_split, + &rx_alloc_cfg); + if (err) + return err; - if (gve_validate_req_ring_size(priv, new_tx_cnt, new_rx_cnt)) - return -EINVAL; + err = gve_set_ring_sizes_config(priv, cmd->tx_pending, cmd->rx_pending, + &tx_alloc_cfg, &rx_alloc_cfg); + if (err) + return err; - return gve_adjust_ring_sizes(priv, new_tx_cnt, new_rx_cnt); + if (netif_running(priv->dev)) { + err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); + if (err) + return err; + } else { + /* Set ring params for the next up */ + priv->rx_cfg.packet_buffer_size = + rx_alloc_cfg.packet_buffer_size; + priv->header_split_enabled = rx_alloc_cfg.enable_header_split; + priv->tx_desc_cnt = tx_alloc_cfg.ring_size; + priv->rx_desc_cnt = rx_alloc_cfg.ring_size; + } + return 0; } static int gve_user_reset(struct net_device *netdev, u32 *flags) @@ -946,7 +954,8 @@ static int gve_get_ts_info(struct net_device *netdev, const struct ethtool_ops gve_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS, - .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT | + ETHTOOL_RING_USE_RX_BUF_LEN, .get_drvinfo = gve_get_drvinfo, .get_strings = gve_get_strings, .get_sset_count = gve_get_sset_count, diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 1be1b1ef31ee3..a5a2b18d309b8 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -1707,18 +1707,28 @@ static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) return 0; } -static int verify_xdp_configuration(struct net_device *dev) +static int gve_verify_xdp_configuration(struct net_device *dev, + struct netlink_ext_ack *extack) { struct gve_priv *priv = netdev_priv(dev); u16 max_xdp_mtu; if (dev->features & NETIF_F_LRO) { - netdev_warn(dev, "XDP is not supported when LRO is on.\n"); + NL_SET_ERR_MSG_MOD(extack, + "XDP is not supported when LRO is on."); return -EOPNOTSUPP; } if (priv->header_split_enabled) { - netdev_warn(dev, "XDP is not supported when header-data split is enabled.\n"); + NL_SET_ERR_MSG_MOD(extack, + "XDP is not supported when header-data split is enabled."); + return -EOPNOTSUPP; + } + + if (priv->rx_cfg.packet_buffer_size != SZ_2K) { + NL_SET_ERR_MSG_FMT_MOD(extack, + "XDP is not supported for Rx buf len %d, only %d supported.", + priv->rx_cfg.packet_buffer_size, SZ_2K); return -EOPNOTSUPP; } @@ -1727,17 +1737,20 @@ static int verify_xdp_configuration(struct net_device *dev) max_xdp_mtu -= GVE_RX_PAD; if (dev->mtu > max_xdp_mtu) { - netdev_warn(dev, "XDP is not supported for mtu %d.\n", - dev->mtu); + NL_SET_ERR_MSG_FMT_MOD(extack, + "XDP is not supported for mtu %d.", + dev->mtu); return -EOPNOTSUPP; } if (priv->rx_cfg.num_queues != priv->tx_cfg.num_queues || (2 * priv->tx_cfg.num_queues > priv->tx_cfg.max_queues)) { - netdev_warn(dev, "XDP load failed: The number of configured RX queues %d should be equal to the number of configured TX queues %d and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues %d", - priv->rx_cfg.num_queues, - priv->tx_cfg.num_queues, + netdev_warn(dev, + "XDP load failed: The number of configured RX queues %d should be equal to the number of configured TX queues %d and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues %d.", + priv->rx_cfg.num_queues, priv->tx_cfg.num_queues, priv->tx_cfg.max_queues); + NL_SET_ERR_MSG_MOD(extack, + "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues"); return -EINVAL; } return 0; @@ -1748,7 +1761,7 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp) struct gve_priv *priv = netdev_priv(dev); int err; - err = verify_xdp_configuration(dev); + err = gve_verify_xdp_configuration(dev, xdp->extack); if (err) return err; switch (xdp->command) { @@ -2041,14 +2054,6 @@ static void gve_tx_timeout(struct net_device *dev, unsigned int txqueue) priv->tx_timeo_cnt++; } -u16 gve_get_pkt_buf_size(const struct gve_priv *priv, bool enable_hsplit) -{ - if (enable_hsplit && priv->max_rx_buffer_size >= GVE_MAX_RX_BUFFER_SIZE) - return GVE_MAX_RX_BUFFER_SIZE; - else - return GVE_DEFAULT_RX_BUFFER_SIZE; -} - /* Header split is only supported on DQ RDA queue format. If XDP is enabled, * header split is not allowed. */ @@ -2058,12 +2063,42 @@ bool gve_header_split_supported(const struct gve_priv *priv) priv->queue_format == GVE_DQO_RDA_FORMAT && !priv->xdp_prog; } -int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split) +int gve_set_rx_buf_len_config(struct gve_priv *priv, u32 rx_buf_len, + struct netlink_ext_ack *extack, + struct gve_rx_alloc_rings_cfg *rx_alloc_cfg) +{ + u32 old_rx_buf_len = rx_alloc_cfg->packet_buffer_size; + + if (rx_buf_len == old_rx_buf_len) + return 0; + + /* device options may not always contain support for 4K buffers */ + if (!gve_is_dqo(priv) || priv->max_rx_buffer_size < SZ_4K) { + NL_SET_ERR_MSG_MOD(extack, + "Modifying Rx buf len is not supported"); + return -EOPNOTSUPP; + } + + if (priv->xdp_prog && rx_buf_len != SZ_2K) { + NL_SET_ERR_MSG_MOD(extack, + "Rx buf len can only be 2048 when XDP is on"); + return -EINVAL; + } + + if (rx_buf_len != SZ_2K && rx_buf_len != SZ_4K) { + NL_SET_ERR_MSG_MOD(extack, + "Rx buf len can only be 2048 or 4096"); + return -EINVAL; + } + rx_alloc_cfg->packet_buffer_size = rx_buf_len; + + return 0; +} + +int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split, + struct gve_rx_alloc_rings_cfg *rx_alloc_cfg) { - struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0}; - struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0}; bool enable_hdr_split; - int err = 0; if (tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_UNKNOWN) return 0; @@ -2081,14 +2116,9 @@ int gve_set_hsplit_config(struct gve_priv *priv, u8 tcp_data_split) if (enable_hdr_split == priv->header_split_enabled) return 0; - gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg); - - rx_alloc_cfg.enable_header_split = enable_hdr_split; - rx_alloc_cfg.packet_buffer_size = gve_get_pkt_buf_size(priv, enable_hdr_split); + rx_alloc_cfg->enable_header_split = enable_hdr_split; - if (netif_running(priv->dev)) - err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg); - return err; + return 0; } static int gve_set_features(struct net_device *netdev, @@ -2158,10 +2188,6 @@ static int gve_set_ts_config(struct net_device *dev, } kernel_config->rx_filter = HWTSTAMP_FILTER_ALL; - gve_clock_nic_ts_read(priv); - ptp_schedule_worker(priv->ptp->clock, 0); - } else { - ptp_cancel_worker_sync(priv->ptp->clock); } priv->ts_config.rx_filter = kernel_config->rx_filter; @@ -2322,6 +2348,10 @@ static void gve_set_netdev_xdp_features(struct gve_priv *priv) xdp_set_features_flag_locked(priv->dev, xdp_features); } +static const struct xdp_metadata_ops gve_xdp_metadata_ops = { + .xmo_rx_timestamp = gve_xdp_rx_timestamp, +}; + static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) { int num_ntfy; @@ -2417,6 +2447,9 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device) } gve_set_netdev_xdp_features(priv); + if (!gve_is_gqi(priv)) + priv->dev->xdp_metadata_ops = &gve_xdp_metadata_ops; + err = gve_setup_device_resources(priv); if (err) goto err_free_xsk_bitmap; diff --git a/drivers/net/ethernet/google/gve/gve_ptp.c b/drivers/net/ethernet/google/gve/gve_ptp.c index a384a9ed4914e..073677d82ee8e 100644 --- a/drivers/net/ethernet/google/gve/gve_ptp.c +++ b/drivers/net/ethernet/google/gve/gve_ptp.c @@ -133,9 +133,21 @@ int gve_init_clock(struct gve_priv *priv) err = -ENOMEM; goto release_ptp; } + err = gve_clock_nic_ts_read(priv); + if (err) { + dev_err(&priv->pdev->dev, "failed to read NIC clock %d\n", err); + goto release_nic_ts_report; + } + ptp_schedule_worker(priv->ptp->clock, + msecs_to_jiffies(GVE_NIC_TS_SYNC_INTERVAL_MS)); return 0; +release_nic_ts_report: + dma_free_coherent(&priv->pdev->dev, + sizeof(struct gve_nic_ts_report), + priv->nic_ts_report, priv->nic_ts_report_bus); + priv->nic_ts_report = NULL; release_ptp: gve_ptp_release(priv); return err; diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c index 1aff3bbb8cfcf..f1bd8f5d57323 100644 --- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c +++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c @@ -240,6 +240,11 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv, rx->rx_headroom = 0; } + /* struct gve_xdp_buff is overlaid on struct xdp_buff_xsk and utilizes + * the 24 byte field cb to store gve specific data. + */ + XSK_CHECK_PRIV_TYPE(struct gve_xdp_buff); + rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots : gve_get_rx_pages_per_qpl_dqo(cfg->ring_size); rx->dqo.buf_states = kvcalloc_node(rx->dqo.num_buf_states, @@ -456,20 +461,38 @@ static void gve_rx_skb_hash(struct sk_buff *skb, * Note that this means if the time delta between packet reception and the last * clock read is greater than ~2 seconds, this will provide invalid results. */ +static ktime_t gve_rx_get_hwtstamp(struct gve_priv *gve, u32 hwts) +{ + u64 last_read = READ_ONCE(gve->last_sync_nic_counter); + u32 low = (u32)last_read; + s32 diff = hwts - low; + + return ns_to_ktime(last_read + diff); +} + static void gve_rx_skb_hwtstamp(struct gve_rx_ring *rx, const struct gve_rx_compl_desc_dqo *desc) { - u64 last_read = READ_ONCE(rx->gve->last_sync_nic_counter); struct sk_buff *skb = rx->ctx.skb_head; - u32 ts, low; - s32 diff; - - if (desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID) { - ts = le32_to_cpu(desc->ts); - low = (u32)last_read; - diff = ts - low; - skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(last_read + diff); - } + + if (desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID) + skb_hwtstamps(skb)->hwtstamp = + gve_rx_get_hwtstamp(rx->gve, le32_to_cpu(desc->ts)); +} + +int gve_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) +{ + const struct gve_xdp_buff *ctx = (void *)_ctx; + + if (!ctx->gve->nic_ts_report) + return -ENODATA; + + if (!(ctx->compl_desc->ts_sub_nsecs_low & GVE_DQO_RX_HWTSTAMP_VALID)) + return -ENODATA; + + *timestamp = gve_rx_get_hwtstamp(ctx->gve, + le32_to_cpu(ctx->compl_desc->ts)); + return 0; } static void gve_rx_free_skb(struct napi_struct *napi, struct gve_rx_ring *rx) @@ -683,16 +706,23 @@ static void gve_xdp_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx, } static int gve_rx_xsk_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, - struct gve_rx_buf_state_dqo *buf_state, int buf_len, + const struct gve_rx_compl_desc_dqo *compl_desc, + struct gve_rx_buf_state_dqo *buf_state, struct bpf_prog *xprog) { struct xdp_buff *xdp = buf_state->xsk_buff; + int buf_len = compl_desc->packet_len; struct gve_priv *priv = rx->gve; + struct gve_xdp_buff *gve_xdp; int xdp_act; xdp->data_end = xdp->data + buf_len; xsk_buff_dma_sync_for_cpu(xdp); + gve_xdp = (void *)xdp; + gve_xdp->gve = priv; + gve_xdp->compl_desc = compl_desc; + if (xprog) { xdp_act = bpf_prog_run_xdp(xprog, xdp); buf_len = xdp->data_end - xdp->data; @@ -782,7 +812,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, xprog = READ_ONCE(priv->xdp_prog); if (buf_state->xsk_buff) - return gve_rx_xsk_dqo(napi, rx, buf_state, buf_len, xprog); + return gve_rx_xsk_dqo(napi, rx, compl_desc, buf_state, xprog); /* Page might have not been used for awhile and was likely last written * by a different thread. @@ -840,23 +870,26 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx, } if (xprog) { - struct xdp_buff xdp; + struct gve_xdp_buff gve_xdp; void *old_data; int xdp_act; - xdp_init_buff(&xdp, buf_state->page_info.buf_size, + xdp_init_buff(&gve_xdp.xdp, buf_state->page_info.buf_size, &rx->xdp_rxq); - xdp_prepare_buff(&xdp, + xdp_prepare_buff(&gve_xdp.xdp, buf_state->page_info.page_address + buf_state->page_info.page_offset, buf_state->page_info.pad, buf_len, false); - old_data = xdp.data; - xdp_act = bpf_prog_run_xdp(xprog, &xdp); - buf_state->page_info.pad += xdp.data - old_data; - buf_len = xdp.data_end - xdp.data; + gve_xdp.gve = priv; + gve_xdp.compl_desc = compl_desc; + + old_data = gve_xdp.xdp.data; + xdp_act = bpf_prog_run_xdp(xprog, &gve_xdp.xdp); + buf_state->page_info.pad += gve_xdp.xdp.data - old_data; + buf_len = gve_xdp.xdp.data_end - gve_xdp.xdp.data; if (xdp_act != XDP_PASS) { - gve_xdp_done_dqo(priv, rx, &xdp, xprog, xdp_act, + gve_xdp_done_dqo(priv, rx, &gve_xdp.xdp, xprog, xdp_act, buf_state); return 0; } diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index 38875c196cb69..18eca7d12c20a 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -151,6 +151,7 @@ config HIBMCGE select FIXED_PHY select MOTORCOMM_PHY select REALTEK_PHY + select PAGE_POOL help If you wish to compile a kernel for a BMC with HIBMC-xx_gmac then you should answer Y to this. This makes this driver suitable for use diff --git a/drivers/net/ethernet/hisilicon/hibmcge/Makefile b/drivers/net/ethernet/hisilicon/hibmcge/Makefile index 1a9da564b306a..d6610ba16855d 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/Makefile +++ b/drivers/net/ethernet/hisilicon/hibmcge/Makefile @@ -3,6 +3,7 @@ # Makefile for the HISILICON BMC GE network device drivers. # +ccflags-y += -I$(src) obj-$(CONFIG_HIBMCGE) += hibmcge.o hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o \ diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h index 2097e4c2b3d74..39cc18686f7e4 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h @@ -7,6 +7,7 @@ #include #include #include +#include #include "hbg_reg.h" #define HBG_STATUS_DISABLE 0x0 @@ -52,8 +53,24 @@ struct hbg_buffer { dma_addr_t state_dma; struct sk_buff *skb; - dma_addr_t skb_dma; - u32 skb_len; + struct page *page; + u32 page_offset; + + union { + void *skb_data_addr; + void *page_addr; + void *pkt_addr; + }; + union { + dma_addr_t skb_dma; + dma_addr_t page_dma; + dma_addr_t pkt_dma; + }; + union { + u32 skb_len; + u32 page_size; + u32 pkt_len; + }; enum hbg_dir dir; struct hbg_ring *ring; @@ -78,6 +95,7 @@ struct hbg_ring { struct hbg_priv *priv; struct napi_struct napi; char *tout_log_buf; /* tx timeout log buffer */ + struct page_pool *page_pool; }; enum hbg_hw_event_type { @@ -101,6 +119,7 @@ struct hbg_dev_specs { u32 max_frame_len; u32 rx_buf_size; + bool page_pool_enabled; }; struct hbg_irq_info { diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c index 01ad82d2f5cc7..d963913def817 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c @@ -122,6 +122,8 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused) np_link_fail = !hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR, HBG_REG_AN_NEG_STATE_NP_LINK_OK_B); seq_printf(s, "np_link fail state: %s\n", str_true_false(np_link_fail)); + seq_printf(s, "page_pool enabled: %s\n", + str_true_false(priv->dev_specs.page_pool_enabled)); return 0; } diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c index 0b92a2e5e9869..9d8b80db9f8bd 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c @@ -19,6 +19,10 @@ #define HBG_SUPPORT_FEATURES (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \ NETIF_F_RXCSUM) +static bool page_pool_enabled = true; +module_param(page_pool_enabled, bool, 0400); +MODULE_PARM_DESC(page_pool_enabled, "set page_pool enabled, default is true"); + static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled) { const struct hbg_irq_info *info; @@ -367,6 +371,9 @@ static int hbg_init(struct hbg_priv *priv) { int ret; + if (IS_ENABLED(CONFIG_PAGE_POOL)) + priv->dev_specs.page_pool_enabled = page_pool_enabled; + ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_INIT); if (ret) return ret; @@ -472,6 +479,22 @@ static int hbg_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; } +static void hbg_shutdown(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + + rtnl_lock(); + if (netif_running(netdev)) + dev_close(netdev); + rtnl_unlock(); + + pci_disable_device(pdev); + pci_set_drvdata(pdev, NULL); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + static const struct pci_device_id hbg_pci_tbl[] = { {PCI_VDEVICE(HUAWEI, 0x3730), 0}, { } @@ -482,6 +505,7 @@ static struct pci_driver hbg_driver = { .name = "hibmcge", .id_table = hbg_pci_tbl, .probe = hbg_probe, + .shutdown = hbg_shutdown, }; static int __init hbg_module_init(void) diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h index a39d1e796e4a4..30b3903c8f2de 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h @@ -252,6 +252,8 @@ struct hbg_rx_desc { #define HBG_RX_DESC_W2_PKT_LEN_M GENMASK(31, 16) #define HBG_RX_DESC_W2_PORT_NUM_M GENMASK(15, 12) +#define HBG_RX_DESC_W3_IP_OFFSET_M GENMASK(23, 16) +#define HBG_RX_DESC_W3_VLAN_M GENMASK(15, 0) #define HBG_RX_DESC_W4_IP_TCP_UDP_M GENMASK(31, 30) #define HBG_RX_DESC_W4_IPSEC_B BIT(29) #define HBG_RX_DESC_W4_IP_VERSION_B BIT(28) @@ -269,6 +271,8 @@ struct hbg_rx_desc { #define HBG_RX_DESC_W4_L3_ERR_CODE_M GENMASK(12, 9) #define HBG_RX_DESC_W4_L2_ERR_B BIT(8) #define HBG_RX_DESC_W4_IDX_MATCH_B BIT(7) +#define HBG_RX_DESC_W4_PARSE_MODE_M GENMASK(6, 5) +#define HBG_RX_DESC_W5_VALID_SIZE_M GENMASK(15, 0) enum hbg_l3_err_code { HBG_L3_OK = 0, diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h new file mode 100644 index 0000000000000..b70fd960da8d6 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_trace.h @@ -0,0 +1,84 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* Copyright (c) 2025 Hisilicon Limited. */ + +/* This must be outside ifdef _HBG_TRACE_H */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM hibmcge + +#if !defined(_HBG_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ) +#define _HBG_TRACE_H_ + +#include +#include +#include +#include +#include "hbg_reg.h" + +TRACE_EVENT(hbg_rx_desc, + TP_PROTO(struct hbg_priv *priv, u32 index, + struct hbg_rx_desc *rx_desc), + TP_ARGS(priv, index, rx_desc), + + TP_STRUCT__entry(__field(u32, index) + __field(u8, port_num) + __field(u8, ip_offset) + __field(u8, parse_mode) + __field(u8, l4_error_code) + __field(u8, l3_error_code) + __field(u8, l2_error_code) + __field(u16, packet_len) + __field(u16, valid_size) + __field(u16, vlan) + __string(pciname, pci_name(priv->pdev)) + __string(devname, priv->netdev->name) + ), + + TP_fast_assign(__entry->index = index, + __entry->packet_len = + FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, + rx_desc->word2); + __entry->port_num = + FIELD_GET(HBG_RX_DESC_W2_PORT_NUM_M, + rx_desc->word2); + __entry->ip_offset = + FIELD_GET(HBG_RX_DESC_W3_IP_OFFSET_M, + rx_desc->word3); + __entry->vlan = + FIELD_GET(HBG_RX_DESC_W3_VLAN_M, + rx_desc->word3); + __entry->parse_mode = + FIELD_GET(HBG_RX_DESC_W4_PARSE_MODE_M, + rx_desc->word4); + __entry->l4_error_code = + FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, + rx_desc->word4); + __entry->l3_error_code = + FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, + rx_desc->word4); + __entry->l2_error_code = + FIELD_GET(HBG_RX_DESC_W4_L2_ERR_B, + rx_desc->word4); + __entry->valid_size = + FIELD_GET(HBG_RX_DESC_W5_VALID_SIZE_M, + rx_desc->word5); + __assign_str(pciname); + __assign_str(devname); + ), + + TP_printk("%s %s index:%u, port num:%u, len:%u, valid size:%u, ip_offset:%u, vlan:0x%04x, parse mode:%u, l4_err:0x%x, l3_err:0x%x, l2_err:0x%x", + __get_str(pciname), __get_str(devname), __entry->index, + __entry->port_num, __entry->packet_len, + __entry->valid_size, __entry->ip_offset, __entry->vlan, + __entry->parse_mode, __entry->l4_error_code, + __entry->l3_error_code, __entry->l2_error_code + ) +); + +#endif /* _HBG_TRACE_H_ */ + +/* This must be outside ifdef _HBG_TRACE_H */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE hbg_trace +#include diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c index 8d814c8f19ea0..b71f277419fad 100644 --- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c +++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c @@ -7,6 +7,9 @@ #include "hbg_reg.h" #include "hbg_txrx.h" +#define CREATE_TRACE_POINTS +#include "hbg_trace.h" + #define netdev_get_tx_ring(netdev) \ (&(((struct hbg_priv *)netdev_priv(netdev))->tx_ring)) @@ -28,6 +31,11 @@ typeof(ring) _ring = (ring); \ _ring->p = hbg_queue_next_prt(_ring->p, _ring); }) +#define hbg_get_page_order(ring) ({ \ + typeof(ring) _ring = (ring); \ + get_order(hbg_spec_max_frame_len(_ring->priv, _ring->dir)); }) +#define hbg_get_page_size(ring) (PAGE_SIZE << hbg_get_page_order((ring))) + #define HBG_TX_STOP_THRS 2 #define HBG_TX_START_THRS (2 * HBG_TX_STOP_THRS) @@ -133,6 +141,7 @@ static void hbg_buffer_free_skb(struct hbg_buffer *buffer) dev_kfree_skb_any(buffer->skb); buffer->skb = NULL; + buffer->skb_data_addr = NULL; } static int hbg_buffer_alloc_skb(struct hbg_buffer *buffer) @@ -145,7 +154,44 @@ static int hbg_buffer_alloc_skb(struct hbg_buffer *buffer) return -ENOMEM; buffer->skb_len = len; - memset(buffer->skb->data, 0, HBG_PACKET_HEAD_SIZE); + buffer->skb_data_addr = buffer->skb->data; + return 0; +} + +static void hbg_buffer_free_page(struct hbg_buffer *buffer) +{ + struct hbg_ring *ring = buffer->ring; + + if (unlikely(!ring->page_pool || !buffer->page)) + return; + + page_pool_put_full_page(ring->page_pool, buffer->page, false); + + buffer->page = NULL; + buffer->page_dma = 0; + buffer->page_addr = NULL; + buffer->page_size = 0; + buffer->page_offset = 0; +} + +static int hbg_buffer_alloc_page(struct hbg_buffer *buffer) +{ + struct hbg_ring *ring = buffer->ring; + u32 len = hbg_get_page_size(ring); + u32 offset; + + if (unlikely(!ring->page_pool)) + return 0; + + buffer->page = page_pool_dev_alloc_frag(ring->page_pool, &offset, len); + if (unlikely(!buffer->page)) + return -ENOMEM; + + buffer->page_dma = page_pool_get_dma_addr(buffer->page) + offset; + buffer->page_addr = page_address(buffer->page) + offset; + buffer->page_size = len; + buffer->page_offset = offset; + return 0; } @@ -368,31 +414,80 @@ static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc, return true; } +static int hbg_alloc_mapping_buffer(struct hbg_buffer *buffer) +{ + struct hbg_ring *ring = buffer->ring; + int ret; + + if (ring->page_pool) + return hbg_buffer_alloc_page(buffer); + + ret = hbg_buffer_alloc_skb(buffer); + if (unlikely(ret)) + return ret; + + ret = hbg_dma_map(buffer); + if (unlikely(ret)) + hbg_buffer_free_skb(buffer); + + return ret; +} + +static void hbg_free_mapping_buffer(struct hbg_buffer *buffer) +{ + struct hbg_ring *ring = buffer->ring; + + if (ring->page_pool) + return hbg_buffer_free_page(buffer); + + hbg_dma_unmap(buffer); + hbg_buffer_free_skb(buffer); +} + static int hbg_rx_fill_one_buffer(struct hbg_priv *priv) { struct hbg_ring *ring = &priv->rx_ring; struct hbg_buffer *buffer; int ret; - if (hbg_queue_is_full(ring->ntc, ring->ntu, ring)) + if (hbg_queue_is_full(ring->ntc, ring->ntu, ring) || + hbg_fifo_is_full(priv, ring->dir)) return 0; buffer = &ring->queue[ring->ntu]; - ret = hbg_buffer_alloc_skb(buffer); + ret = hbg_alloc_mapping_buffer(buffer); if (unlikely(ret)) return ret; - ret = hbg_dma_map(buffer); - if (unlikely(ret)) { - hbg_buffer_free_skb(buffer); - return ret; - } + memset(buffer->pkt_addr, 0, HBG_PACKET_HEAD_SIZE); + dma_sync_single_for_device(&priv->pdev->dev, buffer->pkt_dma, + HBG_PACKET_HEAD_SIZE, DMA_TO_DEVICE); - hbg_hw_fill_buffer(priv, buffer->skb_dma); + hbg_hw_fill_buffer(priv, buffer->pkt_dma); hbg_queue_move_next(ntu, ring); return 0; } +static int hbg_rx_fill_buffers(struct hbg_priv *priv) +{ + u32 remained = hbg_hw_get_fifo_used_num(priv, HBG_DIR_RX); + u32 max_count = priv->dev_specs.rx_fifo_num; + u32 refill_count; + int ret; + + if (unlikely(remained >= max_count)) + return 0; + + refill_count = max_count - remained; + while (refill_count--) { + ret = hbg_rx_fill_one_buffer(priv); + if (unlikely(ret)) + break; + } + + return ret; +} + static bool hbg_sync_data_from_hw(struct hbg_priv *priv, struct hbg_buffer *buffer) { @@ -401,13 +496,29 @@ static bool hbg_sync_data_from_hw(struct hbg_priv *priv, /* make sure HW write desc complete */ dma_rmb(); - dma_sync_single_for_cpu(&priv->pdev->dev, buffer->skb_dma, - buffer->skb_len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(&priv->pdev->dev, buffer->pkt_dma, + buffer->pkt_len, DMA_FROM_DEVICE); - rx_desc = (struct hbg_rx_desc *)buffer->skb->data; + rx_desc = (struct hbg_rx_desc *)buffer->pkt_addr; return FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2) != 0; } +static int hbg_build_skb(struct hbg_buffer *buffer) +{ + if (!buffer->ring->page_pool) { + hbg_dma_unmap(buffer); + return 0; + } + + net_prefetch(buffer->page_addr); + buffer->skb = napi_build_skb(buffer->page_addr, buffer->page_size); + if (unlikely(!buffer->skb)) + return -ENOMEM; + + skb_mark_for_recycle(buffer->skb); + return 0; +} + static int hbg_napi_rx_poll(struct napi_struct *napi, int budget) { struct hbg_ring *ring = container_of(napi, struct hbg_ring, napi); @@ -417,25 +528,31 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget) u32 packet_done = 0; u32 pkt_len; + hbg_rx_fill_buffers(priv); while (packet_done < budget) { if (unlikely(hbg_queue_is_empty(ring->ntc, ring->ntu, ring))) break; buffer = &ring->queue[ring->ntc]; - if (unlikely(!buffer->skb)) + if (unlikely(!buffer->pkt_addr)) goto next_buffer; if (unlikely(!hbg_sync_data_from_hw(priv, buffer))) break; - rx_desc = (struct hbg_rx_desc *)buffer->skb->data; + rx_desc = (struct hbg_rx_desc *)buffer->pkt_addr; pkt_len = FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2); + trace_hbg_rx_desc(priv, ring->ntc, rx_desc); + + if (unlikely(hbg_build_skb(buffer))) { + hbg_free_mapping_buffer(buffer); + goto next_buffer; + } if (unlikely(!hbg_rx_pkt_check(priv, rx_desc, buffer->skb))) { - hbg_buffer_free(buffer); + hbg_free_mapping_buffer(buffer); goto next_buffer; } - hbg_dma_unmap(buffer); skb_reserve(buffer->skb, HBG_PACKET_HEAD_SIZE + NET_IP_ALIGN); skb_put(buffer->skb, pkt_len); buffer->skb->protocol = eth_type_trans(buffer->skb, @@ -444,6 +561,8 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget) dev_sw_netstats_rx_add(priv->netdev, pkt_len); napi_gro_receive(napi, buffer->skb); buffer->skb = NULL; + buffer->page = NULL; + buffer->pkt_addr = NULL; next_buffer: hbg_rx_fill_one_buffer(priv); @@ -458,6 +577,15 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget) return packet_done; } +static void hbg_ring_page_pool_destory(struct hbg_ring *ring) +{ + if (!ring->page_pool) + return; + + page_pool_destroy(ring->page_pool); + ring->page_pool = NULL; +} + static void hbg_ring_uninit(struct hbg_ring *ring) { struct hbg_buffer *buffer; @@ -471,11 +599,12 @@ static void hbg_ring_uninit(struct hbg_ring *ring) for (i = 0; i < ring->len; i++) { buffer = &ring->queue[i]; - hbg_buffer_free(buffer); + hbg_free_mapping_buffer(buffer); buffer->ring = NULL; buffer->priv = NULL; } + hbg_ring_page_pool_destory(ring); dma_free_coherent(&ring->priv->pdev->dev, ring->len * sizeof(*ring->queue), ring->queue, ring->queue_dma); @@ -485,6 +614,33 @@ static void hbg_ring_uninit(struct hbg_ring *ring) ring->priv = NULL; } +static int hbg_ring_page_pool_init(struct hbg_priv *priv, struct hbg_ring *ring) +{ + u32 buf_size = hbg_spec_max_frame_len(priv, ring->dir); + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = hbg_get_page_order(ring), + .pool_size = ring->len * buf_size / hbg_get_page_size(ring), + .nid = dev_to_node(&priv->pdev->dev), + .dev = &priv->pdev->dev, + .napi = &ring->napi, + .dma_dir = DMA_FROM_DEVICE, + .offset = 0, + .max_len = hbg_get_page_size(ring), + }; + int ret = 0; + + ring->page_pool = page_pool_create(&pp_params); + if (IS_ERR(ring->page_pool)) { + ret = PTR_ERR(ring->page_pool); + dev_err(&priv->pdev->dev, + "failed to create page pool, ret = %d\n", ret); + ring->page_pool = NULL; + } + + return ret; +} + static int hbg_ring_init(struct hbg_priv *priv, struct hbg_ring *ring, int (*napi_poll)(struct napi_struct *, int), enum hbg_dir dir) @@ -493,6 +649,16 @@ static int hbg_ring_init(struct hbg_priv *priv, struct hbg_ring *ring, u32 i, len; len = hbg_get_spec_fifo_max_num(priv, dir) + 1; + /* To improve receiving performance under high-stress scenarios, + * in the `hbg_napi_rx_poll()`, we first use the other half of + * the buffer to receive packets from the hardware via the + * `hbg_rx_fill_buffers()`, and then process the packets in the + * original half of the buffer to avoid packet loss caused by + * hardware overflow as much as possible. + */ + if (dir == HBG_DIR_RX) + len += hbg_get_spec_fifo_max_num(priv, dir); + ring->queue = dma_alloc_coherent(&priv->pdev->dev, len * sizeof(*ring->queue), &ring->queue_dma, GFP_KERNEL); @@ -541,21 +707,24 @@ static int hbg_tx_ring_init(struct hbg_priv *priv) static int hbg_rx_ring_init(struct hbg_priv *priv) { int ret; - u32 i; ret = hbg_ring_init(priv, &priv->rx_ring, hbg_napi_rx_poll, HBG_DIR_RX); if (ret) return ret; - for (i = 0; i < priv->rx_ring.len - 1; i++) { - ret = hbg_rx_fill_one_buffer(priv); + if (priv->dev_specs.page_pool_enabled) { + ret = hbg_ring_page_pool_init(priv, &priv->rx_ring); if (ret) { hbg_ring_uninit(&priv->rx_ring); return ret; } } - return 0; + ret = hbg_rx_fill_buffers(priv); + if (ret) + hbg_ring_uninit(&priv->rx_ring); + + return ret; } int hbg_txrx_init(struct hbg_priv *priv) diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 3b548f71fa8a7..d7c3df1958f39 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -804,6 +804,11 @@ struct hnae3_ae_ops { int (*dbg_get_read_func)(struct hnae3_handle *handle, enum hnae3_dbg_cmd cmd, read_func *func); + int (*hwtstamp_get)(struct hnae3_handle *handle, + struct kernel_hwtstamp_config *config); + int (*hwtstamp_set)(struct hnae3_handle *handle, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); }; struct hnae3_dcb_ops { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index bfa5568baa926..7a0654e2d3dd9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -2419,6 +2419,35 @@ static int hns3_nic_do_ioctl(struct net_device *netdev, return h->ae_algo->ops->do_ioctl(h, ifr, cmd); } +static int hns3_nic_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!netif_running(netdev)) + return -EINVAL; + + if (!h->ae_algo->ops->hwtstamp_get) + return -EOPNOTSUPP; + + return h->ae_algo->ops->hwtstamp_get(h, config); +} + +static int hns3_nic_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!netif_running(netdev)) + return -EINVAL; + + if (!h->ae_algo->ops->hwtstamp_set) + return -EOPNOTSUPP; + + return h->ae_algo->ops->hwtstamp_set(h, config, extack); +} + static int hns3_nic_set_features(struct net_device *netdev, netdev_features_t features) { @@ -3048,6 +3077,8 @@ static const struct net_device_ops hns3_nic_netdev_ops = { .ndo_set_vf_rate = hns3_nic_set_vf_rate, .ndo_set_vf_mac = hns3_nic_set_vf_mac, .ndo_select_queue = hns3_nic_select_queue, + .ndo_hwtstamp_get = hns3_nic_hwtstamp_get, + .ndo_hwtstamp_set = hns3_nic_hwtstamp_set, }; bool hns3_is_phys_func(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 782bb48c9f3d7..cf8abbe018402 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -9444,15 +9444,8 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr, struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - switch (cmd) { - case SIOCGHWTSTAMP: - return hclge_ptp_get_cfg(hdev, ifr); - case SIOCSHWTSTAMP: - return hclge_ptp_set_cfg(hdev, ifr); - default: - if (!hdev->hw.mac.phydev) - return hclge_mii_ioctl(hdev, ifr, cmd); - } + if (!hdev->hw.mac.phydev) + return hclge_mii_ioctl(hdev, ifr, cmd); return phy_mii_ioctl(hdev->hw.mac.phydev, ifr, cmd); } @@ -12900,6 +12893,8 @@ static const struct hnae3_ae_ops hclge_ops = { .get_dscp_prio = hclge_get_dscp_prio, .get_wol = hclge_get_wol, .set_wol = hclge_set_wol, + .hwtstamp_get = hclge_ptp_get_cfg, + .hwtstamp_set = hclge_ptp_set_cfg, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c index 4bd52eab39145..0081c52814550 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -204,13 +204,17 @@ static int hclge_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr) +int hclge_ptp_get_cfg(struct hnae3_handle *handle, + struct kernel_hwtstamp_config *config) { + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) return -EOPNOTSUPP; - return copy_to_user(ifr->ifr_data, &hdev->ptp->ts_cfg, - sizeof(struct hwtstamp_config)) ? -EFAULT : 0; + *config = hdev->ptp->ts_cfg; + return 0; } static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en) @@ -269,7 +273,7 @@ static int hclge_ptp_cfg(struct hclge_dev *hdev, u32 cfg) return ret; } -static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg, +static int hclge_ptp_set_tx_mode(struct kernel_hwtstamp_config *cfg, unsigned long *flags, u32 *ptp_cfg) { switch (cfg->tx_type) { @@ -287,7 +291,7 @@ static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg, return 0; } -static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg, +static int hclge_ptp_set_rx_mode(struct kernel_hwtstamp_config *cfg, unsigned long *flags, u32 *ptp_cfg) { int rx_filter = cfg->rx_filter; @@ -332,7 +336,7 @@ static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg, } static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev, - struct hwtstamp_config *cfg) + struct kernel_hwtstamp_config *cfg) { unsigned long flags = hdev->ptp->flags; u32 ptp_cfg = 0; @@ -359,9 +363,12 @@ static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev, return 0; } -int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr) +int hclge_ptp_set_cfg(struct hnae3_handle *handle, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config cfg; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; int ret; if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) { @@ -369,16 +376,13 @@ int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr) return -EOPNOTSUPP; } - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; - - ret = hclge_ptp_set_ts_mode(hdev, &cfg); + ret = hclge_ptp_set_ts_mode(hdev, config); if (ret) return ret; - hdev->ptp->ts_cfg = cfg; + hdev->ptp->ts_cfg = *config; - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + return 0; } int hclge_ptp_get_ts_info(struct hnae3_handle *handle, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h index 61faddcc3dd09..0162fa5ac1462 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h @@ -62,7 +62,7 @@ struct hclge_ptp { unsigned long flags; void __iomem *io_base; struct ptp_clock_info info; - struct hwtstamp_config ts_cfg; + struct kernel_hwtstamp_config ts_cfg; spinlock_t lock; /* protects ptp registers */ u32 ptp_cfg; u32 last_tx_seqid; @@ -133,8 +133,11 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb); void hclge_ptp_clean_tx_hwts(struct hclge_dev *hdev); void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, u32 nsec, u32 sec); -int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr); -int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr); +int hclge_ptp_get_cfg(struct hnae3_handle *handle, + struct kernel_hwtstamp_config *config); +int hclge_ptp_set_cfg(struct hnae3_handle *handle, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); int hclge_ptp_init(struct hclge_dev *hdev); void hclge_ptp_uninit(struct hclge_dev *hdev); int hclge_ptp_get_ts_info(struct hnae3_handle *handle, diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c index 0fa3c79002251..bbf22811a029d 100644 --- a/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c +++ b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c @@ -304,7 +304,7 @@ static int hinic3_open_channel(struct net_device *netdev) err = hinic3_configure(netdev); if (err) { - netdev_err(netdev, "Failed to init txrxq irq\n"); + netdev_err(netdev, "Failed to configure device resources\n"); goto err_uninit_qps_irq; } diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 122ee23497e6a..288fa8ce53af0 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -296,6 +296,7 @@ config ICE depends on GNSS || GNSS = n select AUXILIARY_BUS select DIMLIB + select LIBETH_XDP select LIBIE select LIBIE_ADMINQ select LIBIE_FWLOG if DEBUG_FS diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index 018e61aea787d..aa08f397988e6 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -461,6 +461,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca); #define FLAG2_CHECK_RX_HWTSTAMP BIT(13) #define FLAG2_CHECK_SYSTIM_OVERFLOW BIT(14) #define FLAG2_ENABLE_S0IX_FLOWS BIT(15) +#define FLAG2_DISABLE_K1 BIT(16) #define E1000_RX_DESC_PS(R, i) \ (&(((union e1000_rx_desc_packet_split *)((R).desc))[i])) diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 8e40bb50a01e1..cee57a2149abb 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -26,6 +26,8 @@ struct e1000_stats { static const char e1000e_priv_flags_strings[][ETH_GSTRING_LEN] = { #define E1000E_PRIV_FLAGS_S0IX_ENABLED BIT(0) "s0ix-enabled", +#define E1000E_PRIV_FLAGS_DISABLE_K1 BIT(1) + "disable-k1", }; #define E1000E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(e1000e_priv_flags_strings) @@ -2301,26 +2303,59 @@ static u32 e1000e_get_priv_flags(struct net_device *netdev) if (adapter->flags2 & FLAG2_ENABLE_S0IX_FLOWS) priv_flags |= E1000E_PRIV_FLAGS_S0IX_ENABLED; + if (adapter->flags2 & FLAG2_DISABLE_K1) + priv_flags |= E1000E_PRIV_FLAGS_DISABLE_K1; + return priv_flags; } static int e1000e_set_priv_flags(struct net_device *netdev, u32 priv_flags) { struct e1000_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; unsigned int flags2 = adapter->flags2; + unsigned int changed; - flags2 &= ~FLAG2_ENABLE_S0IX_FLOWS; - if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) { - struct e1000_hw *hw = &adapter->hw; + flags2 &= ~(FLAG2_ENABLE_S0IX_FLOWS | FLAG2_DISABLE_K1); - if (hw->mac.type < e1000_pch_cnp) + if (priv_flags & E1000E_PRIV_FLAGS_S0IX_ENABLED) { + if (hw->mac.type < e1000_pch_cnp) { + e_err("S0ix is not supported on this device\n"); return -EINVAL; + } + flags2 |= FLAG2_ENABLE_S0IX_FLOWS; } - if (flags2 != adapter->flags2) + if (priv_flags & E1000E_PRIV_FLAGS_DISABLE_K1) { + if (hw->mac.type < e1000_ich8lan) { + e_err("Disabling K1 is not supported on this device\n"); + return -EINVAL; + } + + flags2 |= FLAG2_DISABLE_K1; + } + + changed = adapter->flags2 ^ flags2; + if (changed) adapter->flags2 = flags2; + if (changed & FLAG2_DISABLE_K1) { + /* reset the hardware to apply the changes */ + while (test_and_set_bit(__E1000_RESETTING, + &adapter->state)) + usleep_range(1000, 2000); + + if (netif_running(adapter->netdev)) { + e1000e_down(adapter, true); + e1000e_up(adapter); + } else { + e1000e_reset(adapter); + } + + clear_bit(__E1000_RESETTING, &adapter->state); + } + return 0; } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index df4e7d781cb1c..0ff8688ac3b84 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -286,21 +286,26 @@ static void e1000_toggle_lanphypc_pch_lpt(struct e1000_hw *hw) } /** - * e1000_reconfigure_k1_exit_timeout - reconfigure K1 exit timeout to - * align to MTP and later platform requirements. + * e1000_reconfigure_k1_params - reconfigure Kumeran K1 parameters. * @hw: pointer to the HW structure * + * By default K1 is enabled after MAC reset, so this function only + * disables it. + * * Context: PHY semaphore must be held by caller. * Return: 0 on success, negative on failure */ -static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw) +static s32 e1000_reconfigure_k1_params(struct e1000_hw *hw) { u16 phy_timeout; u32 fextnvm12; s32 ret_val; - if (hw->mac.type < e1000_pch_mtp) + if (hw->mac.type < e1000_pch_mtp) { + if (hw->adapter->flags2 & FLAG2_DISABLE_K1) + return e1000_configure_k1_ich8lan(hw, false); return 0; + } /* Change Kumeran K1 power down state from P0s to P1 */ fextnvm12 = er32(FEXTNVM12); @@ -310,6 +315,8 @@ static s32 e1000_reconfigure_k1_exit_timeout(struct e1000_hw *hw) /* Wait for the interface the settle */ usleep_range(1000, 1100); + if (hw->adapter->flags2 & FLAG2_DISABLE_K1) + return e1000_configure_k1_ich8lan(hw, false); /* Change K1 exit timeout */ ret_val = e1e_rphy_locked(hw, I217_PHY_TIMEOUTS_REG, @@ -373,8 +380,8 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) /* At this point the PHY might be inaccessible so don't * propagate the failure */ - if (e1000_reconfigure_k1_exit_timeout(hw)) - e_dbg("Failed to reconfigure K1 exit timeout\n"); + if (e1000_reconfigure_k1_params(hw)) + e_dbg("Failed to reconfigure K1 parameters\n"); fallthrough; case e1000_pch_lpt: @@ -473,10 +480,10 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) if (hw->mac.type >= e1000_pch_mtp) { ret_val = hw->phy.ops.acquire(hw); if (ret_val) { - e_err("Failed to reconfigure K1 exit timeout\n"); + e_err("Failed to reconfigure K1 parameters\n"); goto out; } - ret_val = e1000_reconfigure_k1_exit_timeout(hw); + ret_val = e1000_reconfigure_k1_params(hw); hw->phy.ops.release(hw); } } @@ -4948,17 +4955,15 @@ static s32 e1000_init_hw_ich8lan(struct e1000_hw *hw) u16 i; e1000_initialize_hw_bits_ich8lan(hw); - if (hw->mac.type >= e1000_pch_mtp) { - ret_val = hw->phy.ops.acquire(hw); - if (ret_val) - return ret_val; + ret_val = hw->phy.ops.acquire(hw); + if (ret_val) + return ret_val; - ret_val = e1000_reconfigure_k1_exit_timeout(hw); - hw->phy.ops.release(hw); - if (ret_val) { - e_dbg("Error failed to reconfigure K1 exit timeout\n"); - return ret_val; - } + ret_val = e1000_reconfigure_k1_params(hw); + hw->phy.ops.release(hw); + if (ret_val) { + e_dbg("Error failed to reconfigure K1 parameters\n"); + return ret_val; } /* Initialize identification LED */ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 201322dac2330..116f3c92b5bc5 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -7675,6 +7675,9 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* init PTP hardware clock */ e1000e_ptp_init(adapter); + if (hw->mac.type >= e1000_pch_mtp) + adapter->flags2 |= FLAG2_DISABLE_K1; + /* reset the hardware with the new settings */ e1000e_reset(adapter); diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 801a57a925dad..d2d03db2acec6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -574,6 +574,10 @@ struct i40e_pf { struct i40e_vf *vf; int num_alloc_vfs; /* actual number of VFs allocated */ u32 vf_aq_requests; + /* If set to non-zero, the device uses this value + * as maximum number of MAC filters per VF. + */ + u32 max_mac_per_vf; u32 arq_overflows; /* Not fatal, possibly indicative of problems */ struct ratelimit_state mdd_message_rate_limit; /* DCBx/DCBNL capability for PF that indicates diff --git a/drivers/net/ethernet/intel/i40e/i40e_devlink.c b/drivers/net/ethernet/intel/i40e/i40e_devlink.c index cc4e9e2addb75..bc205e3077c7f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_devlink.c +++ b/drivers/net/ethernet/intel/i40e/i40e_devlink.c @@ -5,6 +5,41 @@ #include "i40e.h" #include "i40e_devlink.h" +static int i40e_max_mac_per_vf_set(struct devlink *devlink, + u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct i40e_pf *pf = devlink_priv(devlink); + + if (pf->num_alloc_vfs > 0) { + NL_SET_ERR_MSG_MOD(extack, + "Cannot change max_mac_per_vf while SR-IOV is enabled"); + return -EBUSY; + } + + pf->max_mac_per_vf = ctx->val.vu32; + return 0; +} + +static int i40e_max_mac_per_vf_get(struct devlink *devlink, + u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct i40e_pf *pf = devlink_priv(devlink); + + ctx->val.vu32 = pf->max_mac_per_vf; + return 0; +} + +static const struct devlink_param i40e_dl_params[] = { + DEVLINK_PARAM_GENERIC(MAX_MAC_PER_VF, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + i40e_max_mac_per_vf_get, + i40e_max_mac_per_vf_set, + NULL), +}; + static void i40e_info_get_dsn(struct i40e_pf *pf, char *buf, size_t len) { u8 dsn[8]; @@ -165,7 +200,18 @@ void i40e_free_pf(struct i40e_pf *pf) **/ void i40e_devlink_register(struct i40e_pf *pf) { - devlink_register(priv_to_devlink(pf)); + struct devlink *dl = priv_to_devlink(pf); + struct device *dev = &pf->pdev->dev; + int err; + + err = devlink_params_register(dl, i40e_dl_params, + ARRAY_SIZE(i40e_dl_params)); + if (err) + dev_err(dev, + "devlink params register failed with error %d", err); + + devlink_register(dl); + } /** @@ -176,7 +222,11 @@ void i40e_devlink_register(struct i40e_pf *pf) **/ void i40e_devlink_unregister(struct i40e_pf *pf) { - devlink_unregister(priv_to_devlink(pf)); + struct devlink *dl = priv_to_devlink(pf); + + devlink_unregister(dl); + devlink_params_unregister(dl, i40e_dl_params, + ARRAY_SIZE(i40e_dl_params)); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 081a4526a2f00..9d91a382612dc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2935,33 +2935,48 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, if (!f) ++mac_add_cnt; } - - /* If this VF is not privileged, then we can't add more than a limited - * number of addresses. + /* Determine the maximum number of MAC addresses this VF may use. + * + * - For untrusted VFs: use a fixed small limit. + * + * - For trusted VFs: limit is calculated by dividing total MAC + * filter pool across all VFs/ports. * - * If this VF is trusted, it can use more resources than untrusted. - * However to ensure that every trusted VF has appropriate number of - * resources, divide whole pool of resources per port and then across - * all VFs. + * - User can override this by devlink param "max_mac_per_vf". + * If set its value is used as a strict cap for both trusted and + * untrusted VFs. + * Note: + * even when overridden, this is a theoretical maximum; hardware + * may reject additional MACs if the absolute HW limit is reached. */ if (!vf_trusted) mac_add_max = I40E_VC_MAX_MAC_ADDR_PER_VF; else mac_add_max = I40E_VC_MAX_MACVLAN_PER_TRUSTED_VF(pf->num_alloc_vfs, hw->num_ports); + if (pf->max_mac_per_vf > 0) + mac_add_max = pf->max_mac_per_vf; + /* VF can replace all its filters in one step, in this case mac_add_max * will be added as active and another mac_add_max will be in * a to-be-removed state. Account for that. */ if ((i40e_count_active_filters(vsi) + mac_add_cnt) > mac_add_max || (i40e_count_all_filters(vsi) + mac_add_cnt) > 2 * mac_add_max) { + if (pf->max_mac_per_vf == mac_add_max && mac_add_max > 0) { + dev_err(&pf->pdev->dev, + "Cannot add more MAC addresses: VF reached its maximum allowed limit (%d)\n", + mac_add_max); + return -EPERM; + } if (!vf_trusted) { dev_err(&pf->pdev->dev, "Cannot add more MAC addresses, VF is not trusted, switch the VF to trusted to add more functionality\n"); return -EPERM; } else { dev_err(&pf->pdev->dev, - "Cannot add more MAC addresses, trusted VF exhausted it's resources\n"); + "Cannot add more MAC addresses: trusted VF reached its maximum allowed limit (%d)\n", + mac_add_max); return -EPERM; } } @@ -4788,6 +4803,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) unsigned long q_map; struct i40e_vf *vf; int abs_vf_id; + int old_link; int ret = 0; int tmp; @@ -4806,6 +4822,17 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) vf = &pf->vf[vf_id]; abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; + /* skip VF link state change if requested state is already set */ + if (!vf->link_forced) + old_link = IFLA_VF_LINK_STATE_AUTO; + else if (vf->link_up) + old_link = IFLA_VF_LINK_STATE_ENABLE; + else + old_link = IFLA_VF_LINK_STATE_DISABLE; + + if (link == old_link) + goto error_out; + pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c index a9e1da35e2489..4d12dfe1b4819 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c +++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.c @@ -90,6 +90,55 @@ iavf_fill_adv_rss_sctp_hdr(struct virtchnl_proto_hdr *hdr, u64 hash_flds) VIRTCHNL_ADD_PROTO_HDR_FIELD_BIT(hdr, SCTP, DST_PORT); } +/** + * iavf_fill_adv_rss_gtp_hdr - Fill GTP-related RSS protocol headers + * @proto_hdrs: pointer to the virtchnl protocol headers structure to populate + * @packet_hdrs: bitmask of packet header types to configure + * @hash_flds: RSS hash field configuration + * + * This function populates the virtchnl protocol header structure with + * appropriate GTP-related header types based on the specified packet_hdrs. + * It supports GTPC, GTPU with extension headers, and uplink/downlink PDU + * types. For certain GTPU types, it also appends an IPv4 header to enable + * hashing on the destination IP address. + * + * Return: 0 on success or -EOPNOTSUPP if the packet_hdrs value is unsupported. + */ +static int +iavf_fill_adv_rss_gtp_hdr(struct virtchnl_proto_hdrs *proto_hdrs, + u32 packet_hdrs, u64 hash_flds) +{ + struct virtchnl_proto_hdr *hdr; + + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count - 1]; + + switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) { + case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID: + case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC: + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPC); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH: + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP: + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH_PDU_UP); + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + iavf_fill_adv_rss_ip4_hdr(hdr, IAVF_ADV_RSS_HASH_FLD_IPV4_DA); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN: + VIRTCHNL_SET_PROTO_HDR_TYPE(hdr, GTPU_EH_PDU_DWN); + fallthrough; + case IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP: + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + iavf_fill_adv_rss_ip4_hdr(hdr, IAVF_ADV_RSS_HASH_FLD_IPV4_DA); + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + /** * iavf_fill_adv_rss_cfg_msg - fill the RSS configuration into virtchnl message * @rss_cfg: the virtchnl message to be filled with RSS configuration setting @@ -103,6 +152,8 @@ int iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg, u32 packet_hdrs, u64 hash_flds, bool symm) { + const u32 packet_l3_hdrs = packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3; + const u32 packet_l4_hdrs = packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4; struct virtchnl_proto_hdrs *proto_hdrs = &rss_cfg->proto_hdrs; struct virtchnl_proto_hdr *hdr; @@ -113,31 +164,41 @@ iavf_fill_adv_rss_cfg_msg(struct virtchnl_rss_cfg *rss_cfg, proto_hdrs->tunnel_level = 0; /* always outer layer */ - hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; - switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L3) { - case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4: - iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds); - break; - case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6: - iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds); - break; - default: - return -EINVAL; + if (packet_l3_hdrs) { + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + switch (packet_l3_hdrs) { + case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4: + iavf_fill_adv_rss_ip4_hdr(hdr, hash_flds); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6: + iavf_fill_adv_rss_ip6_hdr(hdr, hash_flds); + break; + default: + return -EINVAL; + } } - hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; - switch (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_L4) { - case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP: - iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds); - break; - case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP: - iavf_fill_adv_rss_udp_hdr(hdr, hash_flds); - break; - case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP: - iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds); - break; - default: - return -EINVAL; + if (packet_l4_hdrs) { + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + switch (packet_l4_hdrs) { + case IAVF_ADV_RSS_FLOW_SEG_HDR_TCP: + iavf_fill_adv_rss_tcp_hdr(hdr, hash_flds); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_UDP: + iavf_fill_adv_rss_udp_hdr(hdr, hash_flds); + break; + case IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP: + iavf_fill_adv_rss_sctp_hdr(hdr, hash_flds); + break; + default: + return -EINVAL; + } + } + + if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) { + hdr = &proto_hdrs->proto_hdr[proto_hdrs->count++]; + if (iavf_fill_adv_rss_gtp_hdr(proto_hdrs, packet_hdrs, hash_flds)) + return -EINVAL; } return 0; @@ -186,6 +247,8 @@ iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss, proto = "UDP"; else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP) proto = "SCTP"; + else if (packet_hdrs & IAVF_ADV_RSS_FLOW_SEG_HDR_GTP) + proto = "GTP"; else return; @@ -211,6 +274,16 @@ iavf_print_adv_rss_cfg(struct iavf_adapter *adapter, struct iavf_adv_rss *rss, IAVF_ADV_RSS_HASH_FLD_UDP_DST_PORT | IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT)) strcat(hash_opt, "dst port,"); + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPC_TEID) + strcat(hash_opt, "gtp-c,"); + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID) + strcat(hash_opt, "gtp-u ip,"); + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID) + strcat(hash_opt, "gtp-u ext,"); + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID) + strcat(hash_opt, "gtp-u ul,"); + if (hash_flds & IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID) + strcat(hash_opt, "gtp-u dl,"); if (!action) action = ""; diff --git a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h index e31eb2afebeab..74cc9e0d528c8 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h +++ b/drivers/net/ethernet/intel/iavf/iavf_adv_rss.h @@ -22,6 +22,12 @@ enum iavf_adv_rss_flow_seg_hdr { IAVF_ADV_RSS_FLOW_SEG_HDR_TCP = 0x00000004, IAVF_ADV_RSS_FLOW_SEG_HDR_UDP = 0x00000008, IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP = 0x00000010, + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC = 0x00000400, + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID = 0x00000800, + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP = 0x00001000, + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH = 0x00002000, + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN = 0x00004000, + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP = 0x00008000, }; #define IAVF_ADV_RSS_FLOW_SEG_HDR_L3 \ @@ -33,6 +39,14 @@ enum iavf_adv_rss_flow_seg_hdr { IAVF_ADV_RSS_FLOW_SEG_HDR_UDP | \ IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP) +#define IAVF_ADV_RSS_FLOW_SEG_HDR_GTP \ + (IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN | \ + IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP) + enum iavf_adv_rss_flow_field { /* L3 */ IAVF_ADV_RSS_FLOW_FIELD_IDX_IPV4_SA, @@ -46,6 +60,17 @@ enum iavf_adv_rss_flow_field { IAVF_ADV_RSS_FLOW_FIELD_IDX_UDP_DST_PORT, IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_SRC_PORT, IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_DST_PORT, + /* GTPC_TEID */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPC_TEID, + /* GTPU_IP */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_IP_TEID, + /* GTPU_EH */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_EH_TEID, + IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_EH_QFI, + /* GTPU_UP */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_UP_TEID, + /* GTPU_DWN */ + IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_DWN_TEID, /* The total number of enums must not exceed 64 */ IAVF_ADV_RSS_FLOW_FIELD_IDX_MAX @@ -72,6 +97,12 @@ enum iavf_adv_rss_flow_field { BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_SRC_PORT) #define IAVF_ADV_RSS_HASH_FLD_SCTP_DST_PORT \ BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_SCTP_DST_PORT) +#define IAVF_ADV_RSS_HASH_FLD_GTPC_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPC_TEID) +#define IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_IP_TEID) +#define IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_EH_TEID) +#define IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_UP_TEID) +#define IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID \ + BIT_ULL(IAVF_ADV_RSS_FLOW_FIELD_IDX_GTPU_DWN_TEID) /* bookkeeping of advanced RSS configuration */ struct iavf_adv_rss { diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 05d72be3fe80c..a3f8ced232662 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1336,6 +1336,56 @@ static u32 iavf_adv_rss_parse_hdrs(const struct ethtool_rxfh_fields *cmd) hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_SCTP | IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; break; + case GTPU_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case GTPC_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC | + IAVF_ADV_RSS_FLOW_SEG_HDR_UDP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case GTPC_TEID_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID | + IAVF_ADV_RSS_FLOW_SEG_HDR_UDP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case GTPU_EH_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case GTPU_UL_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case GTPU_DL_V4_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV4; + break; + case GTPU_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_IP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case GTPC_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case GTPC_TEID_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPC_TEID | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case GTPU_EH_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_EH | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case GTPU_UL_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_UP | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; + case GTPU_DL_V6_FLOW: + hdrs |= IAVF_ADV_RSS_FLOW_SEG_HDR_GTPU_DWN | + IAVF_ADV_RSS_FLOW_SEG_HDR_IPV6; + break; default: break; } @@ -1353,6 +1403,12 @@ iavf_adv_rss_parse_hash_flds(const struct ethtool_rxfh_fields *cmd, bool symm) case TCP_V4_FLOW: case UDP_V4_FLOW: case SCTP_V4_FLOW: + case GTPU_V4_FLOW: + case GTPC_V4_FLOW: + case GTPC_TEID_V4_FLOW: + case GTPU_EH_V4_FLOW: + case GTPU_UL_V4_FLOW: + case GTPU_DL_V4_FLOW: if (cmd->data & RXH_IP_SRC) hfld |= IAVF_ADV_RSS_HASH_FLD_IPV4_SA; if (cmd->data & RXH_IP_DST) @@ -1361,6 +1417,12 @@ iavf_adv_rss_parse_hash_flds(const struct ethtool_rxfh_fields *cmd, bool symm) case TCP_V6_FLOW: case UDP_V6_FLOW: case SCTP_V6_FLOW: + case GTPU_V6_FLOW: + case GTPC_V6_FLOW: + case GTPC_TEID_V6_FLOW: + case GTPU_EH_V6_FLOW: + case GTPU_UL_V6_FLOW: + case GTPU_DL_V6_FLOW: if (cmd->data & RXH_IP_SRC) hfld |= IAVF_ADV_RSS_HASH_FLD_IPV6_SA; if (cmd->data & RXH_IP_DST) @@ -1382,6 +1444,7 @@ iavf_adv_rss_parse_hash_flds(const struct ethtool_rxfh_fields *cmd, bool symm) break; case UDP_V4_FLOW: case UDP_V6_FLOW: + case GTPC_V4_FLOW: if (cmd->data & RXH_L4_B_0_1) hfld |= IAVF_ADV_RSS_HASH_FLD_UDP_SRC_PORT; if (cmd->data & RXH_L4_B_2_3) @@ -1398,6 +1461,32 @@ iavf_adv_rss_parse_hash_flds(const struct ethtool_rxfh_fields *cmd, bool symm) break; } } + if (cmd->data & RXH_GTP_TEID) { + switch (cmd->flow_type) { + case GTPC_TEID_V4_FLOW: + case GTPC_TEID_V6_FLOW: + hfld |= IAVF_ADV_RSS_HASH_FLD_GTPC_TEID; + break; + case GTPU_V4_FLOW: + case GTPU_V6_FLOW: + hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_IP_TEID; + break; + case GTPU_EH_V4_FLOW: + case GTPU_EH_V6_FLOW: + hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_EH_TEID; + break; + case GTPU_UL_V4_FLOW: + case GTPU_UL_V6_FLOW: + hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_UP_TEID; + break; + case GTPU_DL_V4_FLOW: + case GTPU_DL_V6_FLOW: + hfld |= IAVF_ADV_RSS_HASH_FLD_GTPU_DWN_TEID; + break; + default: + break; + } + } return hfld; } diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index fb2de521731ae..938914abbe066 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -459,6 +459,7 @@ static void ice_devlink_reinit_down(struct ice_pf *pf) rtnl_lock(); ice_vsi_decfg(ice_get_main_vsi(pf)); rtnl_unlock(); + ice_deinit_pf(pf); ice_deinit_dev(pf); } @@ -1231,11 +1232,13 @@ static void ice_set_min_max_msix(struct ice_pf *pf) static int ice_devlink_reinit_up(struct ice_pf *pf) { struct ice_vsi *vsi = ice_get_main_vsi(pf); + struct device *dev = ice_pf_to_dev(pf); + bool need_dev_deinit = false; int err; err = ice_init_hw(&pf->hw); if (err) { - dev_err(ice_pf_to_dev(pf), "ice_init_hw failed: %d\n", err); + dev_err(dev, "ice_init_hw failed: %d\n", err); return err; } @@ -1246,13 +1249,19 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) if (err) goto unroll_hw_init; + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); + goto unroll_dev_init; + } + vsi->flags = ICE_VSI_FLAG_INIT; rtnl_lock(); err = ice_vsi_cfg(vsi); rtnl_unlock(); if (err) - goto err_vsi_cfg; + goto unroll_pf_init; /* No need to take devl_lock, it's already taken by devlink API */ err = ice_load(pf); @@ -1265,10 +1274,14 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) rtnl_lock(); ice_vsi_decfg(vsi); rtnl_unlock(); -err_vsi_cfg: - ice_deinit_dev(pf); +unroll_pf_init: + ice_deinit_pf(pf); +unroll_dev_init: + need_dev_deinit = true; unroll_hw_init: ice_deinit_hw(&pf->hw); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 22b8323ff0d0e..147aaee192a79 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -351,6 +351,7 @@ struct ice_vsi { u16 num_q_vectors; /* tell if only dynamic irq allocation is allowed */ bool irq_dyn_alloc; + bool hsplit:1; u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ @@ -374,6 +375,8 @@ struct ice_vsi { spinlock_t arfs_lock; /* protects aRFS hash table and filter state */ atomic_t *arfs_last_fltr_id; + u16 max_frame; + struct ice_aqc_vsi_props info; /* VSI properties */ struct ice_vsi_vlan_info vlan_info; /* vlan config to be restored */ @@ -509,7 +512,6 @@ enum ice_pf_flags { ICE_FLAG_MOD_POWER_UNSUPPORTED, ICE_FLAG_PHY_FW_LOAD_FAILED, ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */ - ICE_FLAG_LEGACY_RX, ICE_FLAG_VF_TRUE_PROMISC_ENA, ICE_FLAG_MDD_AUTO_RESET_VF, ICE_FLAG_VF_VLAN_PRUNING, @@ -1029,11 +1031,15 @@ int ice_open(struct net_device *netdev); int ice_open_internal(struct net_device *netdev); int ice_stop(struct net_device *netdev); void ice_service_task_schedule(struct ice_pf *pf); +void ice_start_service_task(struct ice_pf *pf); int ice_load(struct ice_pf *pf); void ice_unload(struct ice_pf *pf); void ice_adv_lnk_speed_maps_init(void); +void ice_init_dev_hw(struct ice_pf *pf); int ice_init_dev(struct ice_pf *pf); void ice_deinit_dev(struct ice_pf *pf); +int ice_init_pf(struct ice_pf *pf); +void ice_deinit_pf(struct ice_pf *pf); int ice_change_mtu(struct net_device *netdev, int new_mtu); void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue); int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp); diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 2d35a278c555c..eadb1e3d12b3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include +#include #include "ice_base.h" #include "ice_lib.h" #include "ice_dcb_lib.h" @@ -461,19 +462,6 @@ u16 ice_calc_ts_ring_count(struct ice_tx_ring *tx_ring) return tx_ring->count + max_fetch_desc; } -/** - * ice_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int ice_rx_offset(struct ice_rx_ring *rx_ring) -{ - if (ice_ring_uses_build_skb(rx_ring)) - return ICE_SKB_PAD; - return 0; -} - /** * ice_setup_rx_ctx - Configure a receive ring context * @ring: The Rx ring to configure @@ -536,8 +524,29 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) else rlan_ctx.l2tsel = 1; - rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; - rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; + if (ring->hdr_pp) { + rlan_ctx.hbuf = ring->rx_hdr_len >> ICE_RLAN_CTX_HBUF_S; + rlan_ctx.dtype = ICE_RX_DTYPE_HEADER_SPLIT; + + /* + * If the frame is TCP/UDP/SCTP, it will be split by the + * payload. + * If not, but it's an IPv4/IPv6 frame, it will be split by + * the IP header. + * If not IP, it will be split by the Ethernet header. + * + * In any case, the header buffer will never be left empty. + */ + rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_SPLIT_L2 | + ICE_RLAN_RX_HSPLIT_0_SPLIT_IP | + ICE_RLAN_RX_HSPLIT_0_SPLIT_TCP_UDP | + ICE_RLAN_RX_HSPLIT_0_SPLIT_SCTP; + } else { + rlan_ctx.hbuf = 0; + rlan_ctx.dtype = ICE_RX_DTYPE_NO_SPLIT; + rlan_ctx.hsplit_0 = ICE_RLAN_RX_HSPLIT_0_NO_SPLIT; + } + rlan_ctx.hsplit_1 = ICE_RLAN_RX_HSPLIT_1_NO_SPLIT; /* This controls whether VLAN is stripped from inner headers @@ -549,7 +558,7 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) /* Max packet size for this queue - must not be set to a larger value * than 5 x DBUF */ - rlan_ctx.rxmax = min_t(u32, ring->max_frame, + rlan_ctx.rxmax = min_t(u32, vsi->max_frame, ICE_MAX_CHAINED_RX_BUFS * ring->rx_buf_len); /* Rx queue threshold in units of 64 */ @@ -586,14 +595,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) if (vsi->type == ICE_VSI_VF) return 0; - /* configure Rx buffer alignment */ - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) - ice_clear_ring_build_skb_ena(ring); - else - ice_set_ring_build_skb_ena(ring); - - ring->rx_offset = ice_rx_offset(ring); - /* init queue specific tail register */ ring->tail = hw->hw_addr + QRX_TAIL(pf_q); writel(0, ring->tail); @@ -601,36 +602,51 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) return 0; } -static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring) +static int ice_rxq_pp_create(struct ice_rx_ring *rq) { - void *ctx_ptr = &ring->pkt_ctx; - struct xsk_cb_desc desc = {}; - - XSK_CHECK_PRIV_TYPE(struct ice_xdp_buff); - desc.src = &ctx_ptr; - desc.off = offsetof(struct ice_xdp_buff, pkt_ctx) - - sizeof(struct xdp_buff); - desc.bytes = sizeof(ctx_ptr); - xsk_pool_fill_cb(ring->xsk_pool, &desc); -} + struct libeth_fq fq = { + .count = rq->count, + .nid = NUMA_NO_NODE, + .hsplit = rq->vsi->hsplit, + .xdp = ice_is_xdp_ena_vsi(rq->vsi), + .buf_len = LIBIE_MAX_RX_BUF_LEN, + }; + int err; -/** - * ice_get_frame_sz - calculate xdp_buff::frame_sz - * @rx_ring: the ring being configured - * - * Return frame size based on underlying PAGE_SIZE - */ -static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) -{ - unsigned int frame_sz; + err = libeth_rx_fq_create(&fq, &rq->q_vector->napi); + if (err) + return err; + + rq->pp = fq.pp; + rq->rx_fqes = fq.fqes; + rq->truesize = fq.truesize; + rq->rx_buf_len = fq.buf_len; -#if (PAGE_SIZE >= 8192) - frame_sz = rx_ring->rx_buf_len; -#else - frame_sz = ice_rx_pg_size(rx_ring) / 2; -#endif + if (!fq.hsplit) + return 0; + + fq = (struct libeth_fq){ + .count = rq->count, + .type = LIBETH_FQE_HDR, + .nid = NUMA_NO_NODE, + .xdp = ice_is_xdp_ena_vsi(rq->vsi), + }; - return frame_sz; + err = libeth_rx_fq_create(&fq, &rq->q_vector->napi); + if (err) + goto destroy; + + rq->hdr_pp = fq.pp; + rq->hdr_fqes = fq.fqes; + rq->hdr_truesize = fq.truesize; + rq->rx_hdr_len = fq.buf_len; + + return 0; + +destroy: + ice_rxq_pp_destroy(rq); + + return err; } /** @@ -642,7 +658,8 @@ static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring) static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) { struct device *dev = ice_pf_to_dev(ring->vsi->back); - u32 num_bufs = ICE_RX_DESC_UNUSED(ring); + u32 num_bufs = ICE_DESC_UNUSED(ring); + u32 rx_buf_len; int err; if (ring->vsi->type == ICE_VSI_PF || ring->vsi->type == ICE_VSI_SF) { @@ -656,15 +673,19 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) } ice_rx_xsk_pool(ring); + err = ice_realloc_rx_xdp_bufs(ring, ring->xsk_pool); + if (err) + return err; + if (ring->xsk_pool) { xdp_rxq_info_unreg(&ring->xdp_rxq); - ring->rx_buf_len = + rx_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, - ring->rx_buf_len); + rx_buf_len); if (err) return err; err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, @@ -673,36 +694,33 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (err) return err; xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); - ice_xsk_pool_fill_cb(ring); dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n", ring->q_index); } else { + err = ice_rxq_pp_create(ring); + if (err) + return err; + if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) { err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index, ring->q_vector->napi.napi_id, ring->rx_buf_len); if (err) - return err; + goto err_destroy_fq; } - - err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, - NULL); - if (err) - return err; + xdp_rxq_info_attach_page_pool(&ring->xdp_rxq, + ring->pp); } } - xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq); ring->xdp.data = NULL; - ring->xdp_ext.pkt_ctx = &ring->pkt_ctx; err = ice_setup_rx_ctx(ring); if (err) { dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n", ring->q_index, err); - return err; + goto err_destroy_fq; } if (ring->xsk_pool) { @@ -730,9 +748,17 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) if (ring->vsi->type == ICE_VSI_CTRL) ice_init_ctrl_rx_descs(ring, num_bufs); else - ice_alloc_rx_bufs(ring, num_bufs); + err = ice_alloc_rx_bufs(ring, num_bufs); + + if (err) + goto err_destroy_fq; return 0; + +err_destroy_fq: + ice_rxq_pp_destroy(ring); + + return err; } int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) @@ -753,18 +779,10 @@ int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx) */ static void ice_vsi_cfg_frame_size(struct ice_vsi *vsi, struct ice_rx_ring *ring) { - if (!vsi->netdev || test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) { - ring->max_frame = ICE_MAX_FRAME_LEGACY_RX; - ring->rx_buf_len = ICE_RXBUF_1664; -#if (PAGE_SIZE < 8192) - } else if (!ICE_2K_TOO_SMALL_WITH_PADDING && - (vsi->netdev->mtu <= ETH_DATA_LEN)) { - ring->max_frame = ICE_RXBUF_1536 - NET_IP_ALIGN; - ring->rx_buf_len = ICE_RXBUF_1536 - NET_IP_ALIGN; -#endif + if (!vsi->netdev) { + vsi->max_frame = ICE_MAX_FRAME_LEGACY_RX; } else { - ring->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; - ring->rx_buf_len = ICE_RXBUF_3072; + vsi->max_frame = ICE_AQ_SET_MAC_FRAME_SIZE_MAX; } } diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2532b6f82e971..046bc9c65c51f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1161,6 +1161,9 @@ int ice_init_hw(struct ice_hw *hw) status = ice_init_hw_tbls(hw); if (status) goto err_unroll_fltr_mgmt_struct; + + ice_init_dev_hw(hw->back); + mutex_init(&hw->tnl_lock); ice_init_chk_recipe_reuse_support(hw); @@ -3389,6 +3392,7 @@ bool ice_is_100m_speed_supported(struct ice_hw *hw) case ICE_DEV_ID_E822L_SGMII: case ICE_DEV_ID_E823L_1GBE: case ICE_DEV_ID_E823C_SGMII: + case ICE_DEV_ID_E825C_SGMII: return true; default: return false; diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index dc131779d4267..a1d9abee97e5f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -10,6 +10,7 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" #include +#include struct ice_stats { char stat_string[ETH_GSTRING_LEN]; @@ -340,7 +341,6 @@ static const struct ice_priv_flag ice_gstrings_priv_flags[] = { ICE_FLAG_VF_TRUE_PROMISC_ENA), ICE_PRIV_FLAG("mdd-auto-reset-vf", ICE_FLAG_MDD_AUTO_RESET_VF), ICE_PRIV_FLAG("vf-vlan-pruning", ICE_FLAG_VF_VLAN_PRUNING), - ICE_PRIV_FLAG("legacy-rx", ICE_FLAG_LEGACY_RX), }; #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) @@ -794,8 +794,7 @@ static int ice_get_extended_regs(struct net_device *netdev, void *p) static void ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_hw *hw = &pf->hw; u32 *regs_buf = (u32 *)p; unsigned int i; @@ -810,8 +809,7 @@ ice_get_regs(struct net_device *netdev, struct ethtool_regs *regs, void *p) static u32 ice_get_msglevel(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); #ifndef CONFIG_DYNAMIC_DEBUG if (pf->hw.debug_mask) @@ -824,8 +822,7 @@ static u32 ice_get_msglevel(struct net_device *netdev) static void ice_set_msglevel(struct net_device *netdev, u32 data) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); #ifndef CONFIG_DYNAMIC_DEBUG if (ICE_DBG_USER & data) @@ -840,16 +837,14 @@ static void ice_set_msglevel(struct net_device *netdev, u32 data) static void ice_get_link_ext_stats(struct net_device *netdev, struct ethtool_link_ext_stats *stats) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); stats->link_down_events = pf->link_down_events; } static int ice_get_eeprom_len(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); return (int)pf->hw.flash.flash_size; } @@ -858,9 +853,7 @@ static int ice_get_eeprom(struct net_device *netdev, struct ethtool_eeprom *eeprom, u8 *bytes) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_hw *hw = &pf->hw; struct device *dev; int ret; @@ -959,8 +952,7 @@ static u64 ice_link_test(struct net_device *netdev) */ static u64 ice_eeprom_test(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); netdev_info(netdev, "EEPROM test\n"); return !!(ice_nvm_validate_checksum(&pf->hw)); @@ -1239,8 +1231,9 @@ static int ice_diag_send(struct ice_tx_ring *tx_ring, u8 *data, u16 size) */ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) { - struct ice_rx_buf *rx_buf; + struct libeth_fqe *rx_buf; int valid_frames, i; + struct page *page; u8 *received_buf; valid_frames = 0; @@ -1255,8 +1248,10 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S))))) continue; - rx_buf = &rx_ring->rx_buf[i]; - received_buf = page_address(rx_buf->page) + rx_buf->page_offset; + rx_buf = &rx_ring->rx_fqes[i]; + page = __netmem_to_page(rx_buf->netmem); + received_buf = page_address(page) + rx_buf->offset + + page->pp->p.offset; if (ice_lbtest_check_frame(received_buf)) valid_frames++; @@ -1274,9 +1269,8 @@ static int ice_lbtest_receive_frames(struct ice_rx_ring *rx_ring) */ static u64 ice_loopback_test(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *orig_vsi = np->vsi, *test_vsi; - struct ice_pf *pf = orig_vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_vsi *test_vsi; u8 *tx_frame __free(kfree) = NULL; u8 broadcast[ETH_ALEN], ret = 0; int num_frames, valid_frames; @@ -1365,8 +1359,7 @@ static u64 ice_loopback_test(struct net_device *netdev) */ static u64 ice_intr_test(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); u16 swic_old = pf->sw_int_count; netdev_info(netdev, "interrupt test\n"); @@ -1394,9 +1387,8 @@ static void ice_self_test(struct net_device *netdev, struct ethtool_test *eth_test, u64 *data) { - struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = ice_netdev_to_pf(netdev); bool if_running = netif_running(netdev); - struct ice_pf *pf = np->vsi->back; struct device *dev; dev = ice_pf_to_dev(pf); @@ -1720,9 +1712,7 @@ static int ice_nway_reset(struct net_device *netdev) */ static u32 ice_get_priv_flags(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); u32 i, ret_flags = 0; for (i = 0; i < ICE_PRIV_FLAG_ARRAY_SIZE; i++) { @@ -1869,10 +1859,6 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) ice_nway_reset(netdev); } } - if (test_bit(ICE_FLAG_LEGACY_RX, change_flags)) { - /* down and up VSI so that changes of Rx cfg are reflected. */ - ice_down_up(vsi); - } /* don't allow modification of this flag when a single VF is in * promiscuous mode because it's not supported */ @@ -3165,6 +3151,10 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, ring->rx_jumbo_max_pending = 0; ring->rx_mini_pending = 0; ring->rx_jumbo_pending = 0; + + kernel_ring->tcp_data_split = vsi->hsplit ? + ETHTOOL_TCP_DATA_SPLIT_ENABLED : + ETHTOOL_TCP_DATA_SPLIT_DISABLED; } static int @@ -3181,6 +3171,7 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, int i, timeout = 50, err = 0; struct ice_hw *hw = &pf->hw; u16 new_rx_cnt, new_tx_cnt; + bool hsplit; if (ring->tx_pending > ICE_MAX_NUM_DESC_BY_MAC(hw) || ring->tx_pending < ICE_MIN_NUM_DESC || @@ -3206,9 +3197,12 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, netdev_info(netdev, "Requested Rx descriptor count rounded up to %d\n", new_rx_cnt); + hsplit = kernel_ring->tcp_data_split == ETHTOOL_TCP_DATA_SPLIT_ENABLED; + /* if nothing to do return success */ if (new_tx_cnt == vsi->tx_rings[0]->count && - new_rx_cnt == vsi->rx_rings[0]->count) { + new_rx_cnt == vsi->rx_rings[0]->count && + hsplit == vsi->hsplit) { netdev_dbg(netdev, "Nothing to change, descriptor count is same as requested\n"); return 0; } @@ -3238,6 +3232,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, vsi->xdp_rings[i]->count = new_tx_cnt; vsi->num_tx_desc = (u16)new_tx_cnt; vsi->num_rx_desc = (u16)new_rx_cnt; + vsi->hsplit = hsplit; + netdev_dbg(netdev, "Link is down, descriptor count change happens when link is brought up\n"); goto done; } @@ -3321,7 +3317,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, rx_rings[i].count = new_rx_cnt; rx_rings[i].cached_phctime = pf->ptp.cached_phc_time; rx_rings[i].desc = NULL; - rx_rings[i].rx_buf = NULL; + rx_rings[i].xdp_buf = NULL; + /* this is to allow wr32 to have something to write to * during early allocation of Rx buffers */ @@ -3330,10 +3327,6 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, err = ice_setup_rx_ring(&rx_rings[i]); if (err) goto rx_unwind; - - /* allocate Rx buffers */ - err = ice_alloc_rx_bufs(&rx_rings[i], - ICE_RX_DESC_UNUSED(&rx_rings[i])); rx_unwind: if (err) { while (i) { @@ -3347,6 +3340,8 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, } process_link: + vsi->hsplit = hsplit; + /* Bring interface down, copy in the new ring info, then restore the * interface. if VSI is up, bring it down and then back up */ @@ -4417,9 +4412,7 @@ static int ice_get_module_info(struct net_device *netdev, struct ethtool_modinfo *modinfo) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_hw *hw = &pf->hw; u8 sff8472_comp = 0; u8 sff8472_swap = 0; @@ -4491,12 +4484,10 @@ static int ice_get_module_eeprom(struct net_device *netdev, struct ethtool_eeprom *ee, u8 *data) { - struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_pf *pf = ice_netdev_to_pf(netdev); #define SFF_READ_BLOCK_SIZE 8 u8 value[SFF_READ_BLOCK_SIZE] = { 0 }; u8 addr = ICE_I2C_EEPROM_DEV_ADDR; - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; bool is_sfp = false; unsigned int i, j; @@ -4661,6 +4652,98 @@ static void ice_get_fec_stats(struct net_device *netdev, pi->lport, err); } +static void ice_get_eth_mac_stats(struct net_device *netdev, + struct ethtool_eth_mac_stats *mac_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_hw_port_stats *ps = &pf->stats; + + mac_stats->FramesTransmittedOK = ps->eth.tx_unicast + + ps->eth.tx_multicast + + ps->eth.tx_broadcast; + mac_stats->FramesReceivedOK = ps->eth.rx_unicast + + ps->eth.rx_multicast + + ps->eth.rx_broadcast; + mac_stats->FrameCheckSequenceErrors = ps->crc_errors; + mac_stats->OctetsTransmittedOK = ps->eth.tx_bytes; + mac_stats->OctetsReceivedOK = ps->eth.rx_bytes; + mac_stats->MulticastFramesXmittedOK = ps->eth.tx_multicast; + mac_stats->BroadcastFramesXmittedOK = ps->eth.tx_broadcast; + mac_stats->MulticastFramesReceivedOK = ps->eth.rx_multicast; + mac_stats->BroadcastFramesReceivedOK = ps->eth.rx_broadcast; + mac_stats->InRangeLengthErrors = ps->rx_len_errors; + mac_stats->FrameTooLongErrors = ps->rx_oversize; +} + +static void ice_get_pause_stats(struct net_device *netdev, + struct ethtool_pause_stats *pause_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_hw_port_stats *ps = &pf->stats; + + pause_stats->tx_pause_frames = ps->link_xon_tx + ps->link_xoff_tx; + pause_stats->rx_pause_frames = ps->link_xon_rx + ps->link_xoff_rx; +} + +static const struct ethtool_rmon_hist_range ice_rmon_ranges[] = { + { 0, 64 }, + { 65, 127 }, + { 128, 255 }, + { 256, 511 }, + { 512, 1023 }, + { 1024, 1522 }, + { 1523, 9522 }, + {} +}; + +static void ice_get_rmon_stats(struct net_device *netdev, + struct ethtool_rmon_stats *rmon, + const struct ethtool_rmon_hist_range **ranges) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_hw_port_stats *ps = &pf->stats; + + rmon->undersize_pkts = ps->rx_undersize; + rmon->oversize_pkts = ps->rx_oversize; + rmon->fragments = ps->rx_fragments; + rmon->jabbers = ps->rx_jabber; + + rmon->hist[0] = ps->rx_size_64; + rmon->hist[1] = ps->rx_size_127; + rmon->hist[2] = ps->rx_size_255; + rmon->hist[3] = ps->rx_size_511; + rmon->hist[4] = ps->rx_size_1023; + rmon->hist[5] = ps->rx_size_1522; + rmon->hist[6] = ps->rx_size_big; + + rmon->hist_tx[0] = ps->tx_size_64; + rmon->hist_tx[1] = ps->tx_size_127; + rmon->hist_tx[2] = ps->tx_size_255; + rmon->hist_tx[3] = ps->tx_size_511; + rmon->hist_tx[4] = ps->tx_size_1023; + rmon->hist_tx[5] = ps->tx_size_1522; + rmon->hist_tx[6] = ps->tx_size_big; + + *ranges = ice_rmon_ranges; +} + +/* ice_get_ts_stats - provide timestamping stats + * @netdev: the netdevice pointer from ethtool + * @ts_stats: the ethtool data structure to fill in + */ +static void ice_get_ts_stats(struct net_device *netdev, + struct ethtool_ts_stats *ts_stats) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); + struct ice_ptp *ptp = &pf->ptp; + + ts_stats->pkts = ptp->tx_hwtstamp_good; + ts_stats->err = ptp->tx_hwtstamp_skipped + + ptp->tx_hwtstamp_flushed + + ptp->tx_hwtstamp_discarded; + ts_stats->lost = ptp->tx_hwtstamp_timeouts; +} + #define ICE_ETHTOOL_PFR (ETH_RESET_IRQ | ETH_RESET_DMA | \ ETH_RESET_FILTER | ETH_RESET_OFFLOAD) @@ -4682,8 +4765,7 @@ static void ice_get_fec_stats(struct net_device *netdev, */ static int ice_ethtool_reset(struct net_device *dev, u32 *flags) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); enum ice_reset_req reset; switch (*flags) { @@ -4741,9 +4823,14 @@ static const struct ethtool_ops ice_ethtool_ops = { ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, .supported_input_xfrm = RXH_XFRM_SYM_XOR, + .supported_ring_params = ETHTOOL_RING_USE_TCP_DATA_SPLIT, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, .get_fec_stats = ice_get_fec_stats, + .get_eth_mac_stats = ice_get_eth_mac_stats, + .get_pause_stats = ice_get_pause_stats, + .get_rmon_stats = ice_get_rmon_stats, + .get_ts_stats = ice_get_ts_stats, .get_drvinfo = ice_get_drvinfo, .get_regs_len = ice_get_regs_len, .get_regs = ice_get_regs, diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c index 013c93b6605ed..c0dbec3693669 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -574,9 +574,7 @@ ice_destroy_tunnel(struct ice_hw *hw, u16 index, enum ice_tunnel_type type, int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); enum ice_tunnel_type tnl_type; int status; u16 index; @@ -598,9 +596,7 @@ int ice_udp_tunnel_set_port(struct net_device *netdev, unsigned int table, int ice_udp_tunnel_unset_port(struct net_device *netdev, unsigned int table, unsigned int idx, struct udp_tunnel_info *ti) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); enum ice_tunnel_type tnl_type; int status; @@ -3581,6 +3577,19 @@ ice_move_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig, return 0; } +/** + * ice_set_tcam_flags - set TCAM flag don't care mask + * @mask: mask for flags + * @dc_mask: pointer to the don't care mask + */ +static void ice_set_tcam_flags(u16 mask, u8 dc_mask[ICE_TCAM_KEY_VAL_SZ]) +{ + u16 inverted_mask = ~mask; + + /* flags are lowest u16 */ + put_unaligned_le16(inverted_mask, dc_mask); +} + /** * ice_rem_chg_tcam_ent - remove a specific TCAM entry from change list * @hw: pointer to the HW struct @@ -3651,6 +3660,9 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, if (!p) return -ENOMEM; + /* set don't care masks for TCAM flags */ + ice_set_tcam_flags(tcam->attr.mask, dc_msk); + status = ice_tcam_write_entry(hw, blk, tcam->tcam_idx, tcam->prof_id, tcam->ptg, vsig, 0, tcam->attr.flags, vl_msk, dc_msk, nm_msk); @@ -3676,6 +3688,34 @@ ice_prof_tcam_ena_dis(struct ice_hw *hw, enum ice_block blk, bool enable, return status; } +/** + * ice_ptg_attr_in_use - determine if PTG and attribute pair is in use + * @ptg_attr: pointer to the PTG and attribute pair to check + * @ptgs_used: bitmap that denotes which PTGs are in use + * @attr_used: array of PTG and attributes pairs already used + * @attr_cnt: count of entries in the attr_used array + * + * Return: true if the PTG and attribute pair is in use, false otherwise. + */ +static bool +ice_ptg_attr_in_use(struct ice_tcam_inf *ptg_attr, unsigned long *ptgs_used, + struct ice_tcam_inf *attr_used[], u16 attr_cnt) +{ + u16 i; + + if (!test_bit(ptg_attr->ptg, ptgs_used)) + return false; + + /* the PTG is used, so now look for correct attributes */ + for (i = 0; i < attr_cnt; i++) + if (attr_used[i]->ptg == ptg_attr->ptg && + attr_used[i]->attr.flags == ptg_attr->attr.flags && + attr_used[i]->attr.mask == ptg_attr->attr.mask) + return true; + + return false; +} + /** * ice_adj_prof_priorities - adjust profile based on priorities * @hw: pointer to the HW struct @@ -3688,10 +3728,16 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, struct list_head *chg) { DECLARE_BITMAP(ptgs_used, ICE_XLT1_CNT); + struct ice_tcam_inf **attr_used; struct ice_vsig_prof *t; - int status; + u16 attr_used_cnt = 0; + int status = 0; u16 idx; + attr_used = kcalloc(ICE_MAX_PTG_ATTRS, sizeof(*attr_used), GFP_KERNEL); + if (!attr_used) + return -ENOMEM; + bitmap_zero(ptgs_used, ICE_XLT1_CNT); idx = vsig & ICE_VSIG_IDX_M; @@ -3709,11 +3755,15 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, u16 i; for (i = 0; i < t->tcam_count; i++) { + bool used; + /* Scan the priorities from newest to oldest. * Make sure that the newest profiles take priority. */ - if (test_bit(t->tcam[i].ptg, ptgs_used) && - t->tcam[i].in_use) { + used = ice_ptg_attr_in_use(&t->tcam[i], ptgs_used, + attr_used, attr_used_cnt); + + if (used && t->tcam[i].in_use) { /* need to mark this PTG as never match, as it * was already in use and therefore duplicate * (and lower priority) @@ -3723,9 +3773,8 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, &t->tcam[i], chg); if (status) - return status; - } else if (!test_bit(t->tcam[i].ptg, ptgs_used) && - !t->tcam[i].in_use) { + goto free_attr_used; + } else if (!used && !t->tcam[i].in_use) { /* need to enable this PTG, as it in not in use * and not enabled (highest priority) */ @@ -3734,15 +3783,21 @@ ice_adj_prof_priorities(struct ice_hw *hw, enum ice_block blk, u16 vsig, &t->tcam[i], chg); if (status) - return status; + goto free_attr_used; } /* keep track of used ptgs */ - __set_bit(t->tcam[i].ptg, ptgs_used); + set_bit(t->tcam[i].ptg, ptgs_used); + if (attr_used_cnt < ICE_MAX_PTG_ATTRS) + attr_used[attr_used_cnt++] = &t->tcam[i]; + else + ice_debug(hw, ICE_DBG_INIT, "Warn: ICE_MAX_PTG_ATTRS exceeded\n"); } } - return 0; +free_attr_used: + kfree(attr_used); + return status; } /** @@ -3825,11 +3880,15 @@ ice_add_prof_id_vsig(struct ice_hw *hw, enum ice_block blk, u16 vsig, u64 hdl, p->vsig = vsig; p->tcam_idx = t->tcam[i].tcam_idx; + /* set don't care masks for TCAM flags */ + ice_set_tcam_flags(t->tcam[i].attr.mask, dc_msk); + /* write the TCAM entry */ status = ice_tcam_write_entry(hw, blk, t->tcam[i].tcam_idx, t->tcam[i].prof_id, - t->tcam[i].ptg, vsig, 0, 0, - vl_msk, dc_msk, nm_msk); + t->tcam[i].ptg, vsig, 0, + t->tcam[i].attr.flags, vl_msk, + dc_msk, nm_msk); if (status) { devm_kfree(ice_hw_to_dev(hw), p); goto err_ice_add_prof_id_vsig; @@ -4143,9 +4202,6 @@ ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, u16 vsi_num; int status; - if (blk != ICE_BLK_FD) - return -EINVAL; - vsi_num = ice_get_hw_vsi_num(hw, dest_vsi); status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); if (status) { @@ -4154,6 +4210,9 @@ ice_flow_assoc_fdir_prof(struct ice_hw *hw, enum ice_block blk, return status; } + if (blk != ICE_BLK_FD) + return 0; + vsi_num = ice_get_hw_vsi_num(hw, fdir_vsi); status = ice_add_prof_id_flow(hw, blk, vsi_num, hdl); if (status) { diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h index 817beca591e0c..80c9e7c749c22 100644 --- a/drivers/net/ethernet/intel/ice/ice_flex_type.h +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -187,6 +187,7 @@ struct ice_prof_map { }; #define ICE_INVALID_TCAM 0xFFFF +#define ICE_MAX_PTG_ATTRS 1024 struct ice_tcam_inf { u16 tcam_idx; diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c index 6d5c939dc8a51..c9b6d0a84bd16 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.c +++ b/drivers/net/ethernet/intel/ice/ice_flow.c @@ -5,6 +5,38 @@ #include "ice_flow.h" #include +/* Size of known protocol header fields */ +#define ICE_FLOW_FLD_SZ_ETH_TYPE 2 +#define ICE_FLOW_FLD_SZ_VLAN 2 +#define ICE_FLOW_FLD_SZ_IPV4_ADDR 4 +#define ICE_FLOW_FLD_SZ_IPV6_ADDR 16 +#define ICE_FLOW_FLD_SZ_IPV6_PRE32_ADDR 4 +#define ICE_FLOW_FLD_SZ_IPV6_PRE48_ADDR 6 +#define ICE_FLOW_FLD_SZ_IPV6_PRE64_ADDR 8 +#define ICE_FLOW_FLD_SZ_IPV4_ID 2 +#define ICE_FLOW_FLD_SZ_IPV6_ID 4 +#define ICE_FLOW_FLD_SZ_IP_CHKSUM 2 +#define ICE_FLOW_FLD_SZ_TCP_CHKSUM 2 +#define ICE_FLOW_FLD_SZ_UDP_CHKSUM 2 +#define ICE_FLOW_FLD_SZ_SCTP_CHKSUM 4 +#define ICE_FLOW_FLD_SZ_IP_DSCP 1 +#define ICE_FLOW_FLD_SZ_IP_TTL 1 +#define ICE_FLOW_FLD_SZ_IP_PROT 1 +#define ICE_FLOW_FLD_SZ_PORT 2 +#define ICE_FLOW_FLD_SZ_TCP_FLAGS 1 +#define ICE_FLOW_FLD_SZ_ICMP_TYPE 1 +#define ICE_FLOW_FLD_SZ_ICMP_CODE 1 +#define ICE_FLOW_FLD_SZ_ARP_OPER 2 +#define ICE_FLOW_FLD_SZ_GRE_KEYID 4 +#define ICE_FLOW_FLD_SZ_GTP_TEID 4 +#define ICE_FLOW_FLD_SZ_GTP_QFI 2 +#define ICE_FLOW_FLD_SZ_PFCP_SEID 8 +#define ICE_FLOW_FLD_SZ_ESP_SPI 4 +#define ICE_FLOW_FLD_SZ_AH_SPI 4 +#define ICE_FLOW_FLD_SZ_NAT_T_ESP_SPI 4 +#define ICE_FLOW_FLD_SZ_L2TPV2_SESS_ID 2 +#define ICE_FLOW_FLD_SZ_L2TPV2_LEN_SESS_ID 2 + /* Describe properties of a protocol header field */ struct ice_flow_field_info { enum ice_flow_seg_hdr hdr; @@ -20,6 +52,7 @@ struct ice_flow_field_info { .mask = 0, \ } +/* QFI: 6-bit field in GTP-U PDU Session Container (3GPP TS 38.415) */ #define ICE_FLOW_FLD_INFO_MSK(_hdr, _offset_bytes, _size_bytes, _mask) { \ .hdr = _hdr, \ .off = (_offset_bytes) * BITS_PER_BYTE, \ @@ -61,7 +94,33 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { /* ICE_FLOW_FIELD_IDX_IPV6_SA */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8, sizeof(struct in6_addr)), /* ICE_FLOW_FIELD_IDX_IPV6_DA */ - ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, sizeof(struct in6_addr)), + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, ICE_FLOW_FLD_SZ_IPV6_ADDR), + /* ICE_FLOW_FIELD_IDX_IPV4_CHKSUM */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV4, 10, ICE_FLOW_FLD_SZ_IP_CHKSUM), + /* ICE_FLOW_FIELD_IDX_IPV4_FRAG */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV_FRAG, 4, + ICE_FLOW_FLD_SZ_IPV4_ID), + /* ICE_FLOW_FIELD_IDX_IPV6_FRAG */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV_FRAG, 4, + ICE_FLOW_FLD_SZ_IPV6_ID), + /* ICE_FLOW_FIELD_IDX_IPV6_PRE32_SA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8, + ICE_FLOW_FLD_SZ_IPV6_PRE32_ADDR), + /* ICE_FLOW_FIELD_IDX_IPV6_PRE32_DA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, + ICE_FLOW_FLD_SZ_IPV6_PRE32_ADDR), + /* ICE_FLOW_FIELD_IDX_IPV6_PRE48_SA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8, + ICE_FLOW_FLD_SZ_IPV6_PRE48_ADDR), + /* ICE_FLOW_FIELD_IDX_IPV6_PRE48_DA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, + ICE_FLOW_FLD_SZ_IPV6_PRE48_ADDR), + /* ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 8, + ICE_FLOW_FLD_SZ_IPV6_PRE64_ADDR), + /* ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_IPV6, 24, + ICE_FLOW_FLD_SZ_IPV6_PRE64_ADDR), /* Transport */ /* ICE_FLOW_FIELD_IDX_TCP_SRC_PORT */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 0, sizeof(__be16)), @@ -76,7 +135,14 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { /* ICE_FLOW_FIELD_IDX_SCTP_DST_PORT */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 2, sizeof(__be16)), /* ICE_FLOW_FIELD_IDX_TCP_FLAGS */ - ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 13, 1), + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 13, ICE_FLOW_FLD_SZ_TCP_FLAGS), + /* ICE_FLOW_FIELD_IDX_TCP_CHKSUM */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_TCP, 16, ICE_FLOW_FLD_SZ_TCP_CHKSUM), + /* ICE_FLOW_FIELD_IDX_UDP_CHKSUM */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_UDP, 6, ICE_FLOW_FLD_SZ_UDP_CHKSUM), + /* ICE_FLOW_FIELD_IDX_SCTP_CHKSUM */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_SCTP, 8, + ICE_FLOW_FLD_SZ_SCTP_CHKSUM), /* ARP */ /* ICE_FLOW_FIELD_IDX_ARP_SIP */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_ARP, 14, sizeof(struct in_addr)), @@ -108,9 +174,17 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_EH, 22, sizeof(__be16), 0x3f00), /* ICE_FLOW_FIELD_IDX_GTPU_UP_TEID */ - ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_UP, 12, sizeof(__be32)), + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_UP, 12, + ICE_FLOW_FLD_SZ_GTP_TEID), + /* ICE_FLOW_FIELD_IDX_GTPU_UP_QFI */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_UP, 22, + ICE_FLOW_FLD_SZ_GTP_QFI, 0x3f00), /* ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID */ - ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_DWN, 12, sizeof(__be32)), + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_GTPU_DWN, 12, + ICE_FLOW_FLD_SZ_GTP_TEID), + /* ICE_FLOW_FIELD_IDX_GTPU_DWN_QFI */ + ICE_FLOW_FLD_INFO_MSK(ICE_FLOW_SEG_HDR_GTPU_DWN, 22, + ICE_FLOW_FLD_SZ_GTP_QFI, 0x3f00), /* PPPoE */ /* ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID */ ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_PPPOE, 2, sizeof(__be16)), @@ -128,7 +202,16 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_AH, 4, sizeof(__be32)), /* NAT_T_ESP */ /* ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI */ - ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_NAT_T_ESP, 8, sizeof(__be32)), + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_NAT_T_ESP, 8, + ICE_FLOW_FLD_SZ_NAT_T_ESP_SPI), + /* L2TPV2 */ + /* ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_L2TPV2, 12, + ICE_FLOW_FLD_SZ_L2TPV2_SESS_ID), + /* L2TPV2_LEN */ + /* ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID */ + ICE_FLOW_FLD_INFO(ICE_FLOW_SEG_HDR_L2TPV2, 14, + ICE_FLOW_FLD_SZ_L2TPV2_LEN_SESS_ID), }; /* Bitmaps indicating relevant packet types for a particular protocol header @@ -137,9 +220,9 @@ struct ice_flow_field_info ice_flds_info[ICE_FLOW_FIELD_IDX_MAX] = { */ static const u32 ice_ptypes_mac_ofos[] = { 0xFDC00846, 0xBFBF7F7E, 0xF70001DF, 0xFEFDFDFB, - 0x0000077E, 0x00000000, 0x00000000, 0x00000000, - 0x00400000, 0x03FFF000, 0x7FFFFFE0, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x0000077E, 0x000003FF, 0x00000000, 0x00000000, + 0x00400000, 0x03FFF000, 0xFFFFFFE0, 0x00000707, + 0xFFFFF000, 0x000003FF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -162,10 +245,10 @@ static const u32 ice_ptypes_macvlan_il[] = { * include IPv4 other PTYPEs */ static const u32 ice_ptypes_ipv4_ofos[] = { - 0x1DC00000, 0x04000800, 0x00000000, 0x00000000, + 0x1D800000, 0xBFBF7800, 0x000001DF, 0x00000000, 0x00000000, 0x00000155, 0x00000000, 0x00000000, - 0x00000000, 0x000FC000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x000FC000, 0x000002A0, 0x00000000, + 0x00015000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -176,10 +259,10 @@ static const u32 ice_ptypes_ipv4_ofos[] = { * IPv4 other PTYPEs */ static const u32 ice_ptypes_ipv4_ofos_all[] = { - 0x1DC00000, 0x04000800, 0x00000000, 0x00000000, + 0x1D800000, 0x27BF7800, 0x00000000, 0x00000000, 0x00000000, 0x00000155, 0x00000000, 0x00000000, - 0x00000000, 0x000FC000, 0x83E0F800, 0x00000101, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x000FC000, 0x83E0FAA0, 0x00000101, + 0x3FFD5000, 0x00000000, 0x02FBEFBC, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -191,7 +274,7 @@ static const u32 ice_ptypes_ipv4_il[] = { 0xE0000000, 0xB807700E, 0x80000003, 0xE01DC03B, 0x0000000E, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x001FF800, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0xC0FC0000, 0x0000000F, 0xBC0BC0BC, 0x00000BC0, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -202,10 +285,10 @@ static const u32 ice_ptypes_ipv4_il[] = { * include IPv6 other PTYPEs */ static const u32 ice_ptypes_ipv6_ofos[] = { - 0x00000000, 0x00000000, 0x77000000, 0x10002000, + 0x00000000, 0x00000000, 0x76000000, 0x10002000, 0x00000000, 0x000002AA, 0x00000000, 0x00000000, - 0x00000000, 0x03F00000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x03F00000, 0x00000540, 0x00000000, + 0x0002A000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -216,10 +299,10 @@ static const u32 ice_ptypes_ipv6_ofos[] = { * IPv6 other PTYPEs */ static const u32 ice_ptypes_ipv6_ofos_all[] = { - 0x00000000, 0x00000000, 0x77000000, 0x10002000, - 0x00000000, 0x000002AA, 0x00000000, 0x00000000, - 0x00080F00, 0x03F00000, 0x7C1F0000, 0x00000206, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0x76000000, 0xFEFDE000, + 0x0000077E, 0x000002AA, 0x00000000, 0x00000000, + 0x00000000, 0x03F00000, 0x7C1F0540, 0x00000206, + 0xC002A000, 0x000003FF, 0xBC000000, 0x0002FBEF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -231,7 +314,7 @@ static const u32 ice_ptypes_ipv6_il[] = { 0x00000000, 0x03B80770, 0x000001DC, 0x0EE00000, 0x00000770, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x7FE00000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x3F000000, 0x000003F0, 0x02F02F00, 0x0002F02F, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -304,8 +387,8 @@ static const u32 ice_ptypes_ipv6_il_no_l4[] = { static const u32 ice_ptypes_udp_il[] = { 0x81000000, 0x20204040, 0x04000010, 0x80810102, 0x00000040, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00410000, 0x90842000, 0x00000007, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00410000, 0x908427E0, 0x00000007, + 0x0413F000, 0x00000041, 0x10410410, 0x00004104, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -317,7 +400,7 @@ static const u32 ice_ptypes_tcp_il[] = { 0x04000000, 0x80810102, 0x10000040, 0x02040408, 0x00000102, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00820000, 0x21084000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x08200000, 0x00000082, 0x20820820, 0x00008208, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -329,7 +412,7 @@ static const u32 ice_ptypes_sctp_il[] = { 0x08000000, 0x01020204, 0x20000081, 0x04080810, 0x00000204, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x01040000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x10400000, 0x00000104, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -353,7 +436,7 @@ static const u32 ice_ptypes_icmp_il[] = { 0x00000000, 0x02040408, 0x40000102, 0x08101020, 0x00000408, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x42108000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x20800000, 0x00000208, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -365,7 +448,7 @@ static const u32 ice_ptypes_gre_of[] = { 0x00000000, 0xBFBF7800, 0x000001DF, 0xFEFDE000, 0x0000017E, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x00000000, 0xBEFBEFBC, 0x0002FBEF, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -374,7 +457,7 @@ static const u32 ice_ptypes_gre_of[] = { /* Packet types for packets with an Innermost/Last MAC header */ static const u32 ice_ptypes_mac_il[] = { - 0x00000000, 0x00000000, 0x00000000, 0x00000000, + 0x00000000, 0x20000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -388,7 +471,7 @@ static const u32 ice_ptypes_mac_il[] = { static const u32 ice_ptypes_gtpc[] = { 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, - 0x00000000, 0x00000000, 0x00000180, 0x00000000, + 0x00000000, 0x00000000, 0x000001E0, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, 0x00000000, @@ -2324,6 +2407,130 @@ static void ice_rss_set_symm(struct ice_hw *hw, struct ice_flow_prof *prof) } } +/** + * ice_rss_cfg_raw_symm - Configure symmetric RSS for a raw parser profile + * @hw: device HW + * @prof: parser profile describing extracted FV (field vector) entries + * @prof_id: RSS profile identifier used to program symmetry registers + * + * The routine scans the parser profile's FV entries and looks for + * direction-sensitive pairs (L3 src/dst, L4 src/dst). When a pair is found, + * it programs XOR-based symmetry so that flows hash identically regardless + * of packet direction. This preserves CPU affinity for the same 5-tuple. + * + * Notes: + * - The size of each logical field (IPv4/IPv6 address, L4 port) is expressed + * in units of ICE_FLOW_FV_EXTRACT_SZ so we can step across fv[] correctly. + * - We guard against out-of-bounds access before looking at fv[i + len]. + */ +static void ice_rss_cfg_raw_symm(struct ice_hw *hw, + const struct ice_parser_profile *prof, + u64 prof_id) +{ + for (size_t i = 0; i < prof->fv_num; i++) { + u8 proto_id = prof->fv[i].proto_id; + u16 src_off = 0, dst_off = 0; + size_t src_idx, dst_idx; + bool is_matched = false; + unsigned int len = 0; + + switch (proto_id) { + /* IPv4 address pairs (outer/inner variants) */ + case ICE_PROT_IPV4_OF_OR_S: + case ICE_PROT_IPV4_IL: + case ICE_PROT_IPV4_IL_IL: + len = ICE_FLOW_FLD_SZ_IPV4_ADDR / + ICE_FLOW_FV_EXTRACT_SZ; + src_off = ICE_FLOW_FIELD_IPV4_SRC_OFFSET; + dst_off = ICE_FLOW_FIELD_IPV4_DST_OFFSET; + break; + + /* IPv6 address pairs (outer/inner variants) */ + case ICE_PROT_IPV6_OF_OR_S: + case ICE_PROT_IPV6_IL: + case ICE_PROT_IPV6_IL_IL: + len = ICE_FLOW_FLD_SZ_IPV6_ADDR / + ICE_FLOW_FV_EXTRACT_SZ; + src_off = ICE_FLOW_FIELD_IPV6_SRC_OFFSET; + dst_off = ICE_FLOW_FIELD_IPV6_DST_OFFSET; + break; + + /* L4 port pairs (TCP/UDP/SCTP) */ + case ICE_PROT_TCP_IL: + case ICE_PROT_UDP_IL_OR_S: + case ICE_PROT_SCTP_IL: + len = ICE_FLOW_FLD_SZ_PORT / ICE_FLOW_FV_EXTRACT_SZ; + src_off = ICE_FLOW_FIELD_SRC_PORT_OFFSET; + dst_off = ICE_FLOW_FIELD_DST_PORT_OFFSET; + break; + + default: + continue; + } + + /* Bounds check before accessing fv[i + len]. */ + if (i + len >= prof->fv_num) + continue; + + /* Verify src/dst pairing for this protocol id. */ + is_matched = prof->fv[i].offset == src_off && + prof->fv[i + len].proto_id == proto_id && + prof->fv[i + len].offset == dst_off; + if (!is_matched) + continue; + + /* Program XOR symmetry for this field pair. */ + src_idx = i; + dst_idx = i + len; + + ice_rss_config_xor(hw, prof_id, src_idx, dst_idx, len); + + /* Skip over the pair we just handled; the loop's ++i advances + * one more element, hence the --i after the jump. + */ + i += (2 * len); + /* not strictly needed; keeps static analyzers happy */ + if (i == 0) + break; + --i; + } +} + +/* Max registers index per packet profile */ +#define ICE_SYMM_REG_INDEX_MAX 6 + +/** + * ice_rss_update_raw_symm - update symmetric hash configuration + * for raw pattern + * @hw: pointer to the hardware structure + * @cfg: configure parameters for raw pattern + * @id: profile tracking ID + * + * Update symmetric hash configuration for raw pattern if required. + * Otherwise only clear to default. + */ +void +ice_rss_update_raw_symm(struct ice_hw *hw, + struct ice_rss_raw_cfg *cfg, u64 id) +{ + struct ice_prof_map *map; + u8 prof_id, m; + + mutex_lock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock); + map = ice_search_prof_id(hw, ICE_BLK_RSS, id); + if (map) + prof_id = map->prof_id; + mutex_unlock(&hw->blk[ICE_BLK_RSS].es.prof_map_lock); + if (!map) + return; + /* clear to default */ + for (m = 0; m < ICE_SYMM_REG_INDEX_MAX; m++) + wr32(hw, GLQF_HSYMM(prof_id, m), 0); + + if (cfg->symm) + ice_rss_cfg_raw_symm(hw, &cfg->prof, prof_id); +} + /** * ice_add_rss_cfg_sync - add an RSS configuration * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h index 52f906d89eca1..6c6cdc8addb12 100644 --- a/drivers/net/ethernet/intel/ice/ice_flow.h +++ b/drivers/net/ethernet/intel/ice/ice_flow.h @@ -22,6 +22,15 @@ #define ICE_FLOW_HASH_IPV6 \ (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) | \ BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_DA)) +#define ICE_FLOW_HASH_IPV6_PRE32 \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE32_SA) | \ + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE32_DA)) +#define ICE_FLOW_HASH_IPV6_PRE48 \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE48_SA) | \ + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE48_DA)) +#define ICE_FLOW_HASH_IPV6_PRE64 \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA) | \ + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA)) #define ICE_FLOW_HASH_TCP_PORT \ (BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) | \ BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT)) @@ -40,6 +49,33 @@ #define ICE_HASH_SCTP_IPV4 (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_SCTP_PORT) #define ICE_HASH_SCTP_IPV6 (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_SCTP_PORT) +#define ICE_HASH_TCP_IPV6_PRE32 \ + (ICE_FLOW_HASH_IPV6_PRE32 | ICE_FLOW_HASH_TCP_PORT) +#define ICE_HASH_UDP_IPV6_PRE32 \ + (ICE_FLOW_HASH_IPV6_PRE32 | ICE_FLOW_HASH_UDP_PORT) +#define ICE_HASH_SCTP_IPV6_PRE32 \ + (ICE_FLOW_HASH_IPV6_PRE32 | ICE_FLOW_HASH_SCTP_PORT) +#define ICE_HASH_TCP_IPV6_PRE48 \ + (ICE_FLOW_HASH_IPV6_PRE48 | ICE_FLOW_HASH_TCP_PORT) +#define ICE_HASH_UDP_IPV6_PRE48 \ + (ICE_FLOW_HASH_IPV6_PRE48 | ICE_FLOW_HASH_UDP_PORT) +#define ICE_HASH_SCTP_IPV6_PRE48 \ + (ICE_FLOW_HASH_IPV6_PRE48 | ICE_FLOW_HASH_SCTP_PORT) +#define ICE_HASH_TCP_IPV6_PRE64 \ + (ICE_FLOW_HASH_IPV6_PRE64 | ICE_FLOW_HASH_TCP_PORT) +#define ICE_HASH_UDP_IPV6_PRE64 \ + (ICE_FLOW_HASH_IPV6_PRE64 | ICE_FLOW_HASH_UDP_PORT) +#define ICE_HASH_SCTP_IPV6_PRE64 \ + (ICE_FLOW_HASH_IPV6_PRE64 | ICE_FLOW_HASH_SCTP_PORT) + +#define ICE_FLOW_HASH_GTP_TEID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)) + +#define ICE_FLOW_HASH_GTP_IPV4_TEID \ + (ICE_FLOW_HASH_IPV4 | ICE_FLOW_HASH_GTP_TEID) +#define ICE_FLOW_HASH_GTP_IPV6_TEID \ + (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_GTP_TEID) + #define ICE_FLOW_HASH_GTP_C_TEID \ (BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)) @@ -128,6 +164,23 @@ #define ICE_FLOW_HASH_NAT_T_ESP_IPV6_SPI \ (ICE_FLOW_HASH_IPV6 | ICE_FLOW_HASH_NAT_T_ESP_SPI) +#define ICE_FLOW_HASH_L2TPV2_SESS_ID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID)) +#define ICE_FLOW_HASH_L2TPV2_SESS_ID_ETH \ + (ICE_FLOW_HASH_ETH | ICE_FLOW_HASH_L2TPV2_SESS_ID) + +#define ICE_FLOW_HASH_L2TPV2_LEN_SESS_ID \ + (BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID)) +#define ICE_FLOW_HASH_L2TPV2_LEN_SESS_ID_ETH \ + (ICE_FLOW_HASH_ETH | ICE_FLOW_HASH_L2TPV2_LEN_SESS_ID) + +#define ICE_FLOW_FIELD_IPV4_SRC_OFFSET 12 +#define ICE_FLOW_FIELD_IPV4_DST_OFFSET 16 +#define ICE_FLOW_FIELD_IPV6_SRC_OFFSET 8 +#define ICE_FLOW_FIELD_IPV6_DST_OFFSET 24 +#define ICE_FLOW_FIELD_SRC_PORT_OFFSET 0 +#define ICE_FLOW_FIELD_DST_PORT_OFFSET 2 + /* Protocol header fields within a packet segment. A segment consists of one or * more protocol headers that make up a logical group of protocol headers. Each * logical group of protocol headers encapsulates or is encapsulated using/by @@ -160,10 +213,13 @@ enum ice_flow_seg_hdr { ICE_FLOW_SEG_HDR_AH = 0x00200000, ICE_FLOW_SEG_HDR_NAT_T_ESP = 0x00400000, ICE_FLOW_SEG_HDR_ETH_NON_IP = 0x00800000, + ICE_FLOW_SEG_HDR_GTPU_NON_IP = 0x01000000, + ICE_FLOW_SEG_HDR_L2TPV2 = 0x10000000, /* The following is an additive bit for ICE_FLOW_SEG_HDR_IPV4 and - * ICE_FLOW_SEG_HDR_IPV6 which include the IPV4 other PTYPEs + * ICE_FLOW_SEG_HDR_IPV6. */ - ICE_FLOW_SEG_HDR_IPV_OTHER = 0x20000000, + ICE_FLOW_SEG_HDR_IPV_FRAG = 0x40000000, + ICE_FLOW_SEG_HDR_IPV_OTHER = 0x80000000, }; /* These segments all have the same PTYPES, but are otherwise distinguished by @@ -200,6 +256,15 @@ enum ice_flow_field { ICE_FLOW_FIELD_IDX_IPV4_DA, ICE_FLOW_FIELD_IDX_IPV6_SA, ICE_FLOW_FIELD_IDX_IPV6_DA, + ICE_FLOW_FIELD_IDX_IPV4_CHKSUM, + ICE_FLOW_FIELD_IDX_IPV4_ID, + ICE_FLOW_FIELD_IDX_IPV6_ID, + ICE_FLOW_FIELD_IDX_IPV6_PRE32_SA, + ICE_FLOW_FIELD_IDX_IPV6_PRE32_DA, + ICE_FLOW_FIELD_IDX_IPV6_PRE48_SA, + ICE_FLOW_FIELD_IDX_IPV6_PRE48_DA, + ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA, + ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA, /* L4 */ ICE_FLOW_FIELD_IDX_TCP_SRC_PORT, ICE_FLOW_FIELD_IDX_TCP_DST_PORT, @@ -208,6 +273,9 @@ enum ice_flow_field { ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT, ICE_FLOW_FIELD_IDX_SCTP_DST_PORT, ICE_FLOW_FIELD_IDX_TCP_FLAGS, + ICE_FLOW_FIELD_IDX_TCP_CHKSUM, + ICE_FLOW_FIELD_IDX_UDP_CHKSUM, + ICE_FLOW_FIELD_IDX_SCTP_CHKSUM, /* ARP */ ICE_FLOW_FIELD_IDX_ARP_SIP, ICE_FLOW_FIELD_IDX_ARP_DIP, @@ -228,13 +296,13 @@ enum ice_flow_field { ICE_FLOW_FIELD_IDX_GTPU_EH_QFI, /* GTPU_UP */ ICE_FLOW_FIELD_IDX_GTPU_UP_TEID, + ICE_FLOW_FIELD_IDX_GTPU_UP_QFI, /* GTPU_DWN */ ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID, - /* PPPoE */ + ICE_FLOW_FIELD_IDX_GTPU_DWN_QFI, ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID, /* PFCP */ ICE_FLOW_FIELD_IDX_PFCP_SEID, - /* L2TPv3 */ ICE_FLOW_FIELD_IDX_L2TPV3_SESS_ID, /* ESP */ ICE_FLOW_FIELD_IDX_ESP_SPI, @@ -242,10 +310,16 @@ enum ice_flow_field { ICE_FLOW_FIELD_IDX_AH_SPI, /* NAT_T ESP */ ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI, + /* L2TPV2 SESSION ID*/ + ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID, + /* L2TPV2_LEN SESSION ID */ + ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID, /* The total number of enums must not exceed 64 */ ICE_FLOW_FIELD_IDX_MAX }; +static_assert(ICE_FLOW_FIELD_IDX_MAX <= 64, "The total number of enums must not exceed 64"); + #define ICE_FLOW_HASH_FLD_IPV4_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) #define ICE_FLOW_HASH_FLD_IPV6_SA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA) #define ICE_FLOW_HASH_FLD_IPV4_DA BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) @@ -296,6 +370,10 @@ enum ice_rss_cfg_hdr_type { /* take inner headers as inputset for packet with outer ipv6. */ ICE_RSS_INNER_HEADERS_W_OUTER_IPV6, /* take outer headers first then inner headers as inputset */ + /* take inner as inputset for GTPoGRE with outer IPv4 + GRE. */ + ICE_RSS_INNER_HEADERS_W_OUTER_IPV4_GRE, + /* take inner as inputset for GTPoGRE with outer IPv6 + GRE. */ + ICE_RSS_INNER_HEADERS_W_OUTER_IPV6_GRE, ICE_RSS_ANY_HEADERS }; @@ -406,6 +484,12 @@ struct ice_flow_prof { bool symm; /* Symmetric Hash for RSS */ }; +struct ice_rss_raw_cfg { + struct ice_parser_profile prof; + bool raw_ena; + bool symm; +}; + struct ice_rss_cfg { struct list_head l_entry; /* bitmap of VSIs added to the RSS entry */ @@ -444,4 +528,6 @@ int ice_add_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, int ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle, const struct ice_rss_hash_cfg *cfg); u64 ice_get_rss_cfg(struct ice_hw *hw, u16 vsi_handle, u32 hdrs, bool *symm); +void ice_rss_update_raw_symm(struct ice_hw *hw, + struct ice_rss_raw_cfg *cfg, u64 id); #endif /* _ICE_FLOW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c index aebf8e08a297b..d2576d606e10e 100644 --- a/drivers/net/ethernet/intel/ice/ice_lag.c +++ b/drivers/net/ethernet/intel/ice/ice_lag.c @@ -2177,8 +2177,7 @@ static void ice_lag_chk_disabled_bond(struct ice_lag *lag, void *ptr) */ static void ice_lag_disable_sriov_bond(struct ice_lag *lag) { - struct ice_netdev_priv *np = netdev_priv(lag->netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(lag->netdev); ice_clear_feature_support(pf, ICE_F_SRIOV_LAG); ice_clear_feature_support(pf, ICE_F_SRIOV_AA_LAG); diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 10c312d49e052..185672c7e17d0 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -342,6 +342,9 @@ enum ice_flg64_bits { /* for ice_32byte_rx_flex_desc.pkt_length member */ #define ICE_RX_FLX_DESC_PKT_LEN_M (0x3FFF) /* 14-bits */ +/* ice_32byte_rx_flex_desc::hdr_len_sph_flex_flags1 */ +#define ICE_RX_FLEX_DESC_HDR_LEN_M GENMASK(10, 0) + enum ice_rx_flex_desc_status_error_0_bits { /* Note: These are predefined bit offsets */ ICE_RX_FLEX_DESC_STATUS0_DD_S = 0, diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 4479c824561e9..15621707fbf81 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -1427,7 +1427,6 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->reg_idx = vsi->rxq_map[i]; ring->vsi = vsi; ring->netdev = vsi->netdev; - ring->dev = dev; ring->count = vsi->num_rx_desc; ring->cached_phctime = pf->ptp.cached_phc_time; @@ -2769,7 +2768,6 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked) * @vsi: VSI pointer * * Associate queue[s] with napi for all vectors. - * The caller must hold rtnl_lock. */ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) { @@ -2779,6 +2777,7 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) if (!netdev) return; + ASSERT_RTNL(); ice_for_each_rxq(vsi, q_idx) netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, &vsi->rx_rings[q_idx]->q_vector->napi); @@ -2799,7 +2798,6 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) * @vsi: VSI pointer * * Clear the association between all VSI queues queue[s] and napi. - * The caller must hold rtnl_lock. */ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { @@ -2809,6 +2807,7 @@ void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) if (!netdev) return; + ASSERT_RTNL(); /* Clear the NAPI's interrupt number */ ice_for_each_q_vector(vsi, v_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 86f5859e88ef5..2533876f1a2fd 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -37,6 +37,8 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; #define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg" MODULE_DESCRIPTION(DRV_SUMMARY); +MODULE_IMPORT_NS("LIBETH"); +MODULE_IMPORT_NS("LIBETH_XDP"); MODULE_IMPORT_NS("LIBIE"); MODULE_IMPORT_NS("LIBIE_ADMINQ"); MODULE_IMPORT_NS("LIBIE_FWLOG"); @@ -2957,10 +2959,7 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi) */ static int ice_max_xdp_frame_size(struct ice_vsi *vsi) { - if (test_bit(ICE_FLAG_LEGACY_RX, vsi->back->flags)) - return ICE_RXBUF_1664; - else - return ICE_RXBUF_3072; + return ICE_RXBUF_3072; } /** @@ -3018,19 +3017,11 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog, } } xdp_features_set_redirect_target(vsi->netdev, true); - /* reallocate Rx queues that are used for zero-copy */ - xdp_ring_err = ice_realloc_zc_buf(vsi, true); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed"); } else if (ice_is_xdp_ena_vsi(vsi) && !prog) { xdp_features_clear_redirect_target(vsi->netdev); xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL); if (xdp_ring_err) NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed"); - /* reallocate Rx queues that were used for zero-copy */ - xdp_ring_err = ice_realloc_zc_buf(vsi, false); - if (xdp_ring_err) - NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Rx resources failed"); } resume_if: @@ -3949,9 +3940,10 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf) * ice_deinit_pf - Unrolls initialziations done by ice_init_pf * @pf: board private structure to initialize */ -static void ice_deinit_pf(struct ice_pf *pf) +void ice_deinit_pf(struct ice_pf *pf) { - ice_service_task_stop(pf); + /* note that we unroll also on ice_init_pf() failure here */ + mutex_destroy(&pf->lag_mutex); mutex_destroy(&pf->adev_mutex); mutex_destroy(&pf->sw_mutex); @@ -3977,6 +3969,9 @@ static void ice_deinit_pf(struct ice_pf *pf) if (pf->ptp.clock) ptp_clock_unregister(pf->ptp.clock); + if (!xa_empty(&pf->irq_tracker.entries)) + ice_free_irq_msix_misc(pf); + xa_destroy(&pf->dyn_ports); xa_destroy(&pf->sf_nums); } @@ -4030,13 +4025,25 @@ static void ice_set_pf_caps(struct ice_pf *pf) pf->max_pf_rxqs = func_caps->common_cap.num_rxq; } +void ice_start_service_task(struct ice_pf *pf) +{ + timer_setup(&pf->serv_tmr, ice_service_timer, 0); + pf->serv_tmr_period = HZ; + INIT_WORK(&pf->serv_task, ice_service_task); + clear_bit(ICE_SERVICE_SCHED, pf->state); +} + /** * ice_init_pf - Initialize general software structures (struct ice_pf) * @pf: board private structure to initialize + * Return: 0 on success, negative errno otherwise. */ -static int ice_init_pf(struct ice_pf *pf) +int ice_init_pf(struct ice_pf *pf) { - ice_set_pf_caps(pf); + struct udp_tunnel_nic_info *udp_tunnel_nic = &pf->hw.udp_tunnel_nic; + struct device *dev = ice_pf_to_dev(pf); + struct ice_hw *hw = &pf->hw; + int err = -ENOMEM; mutex_init(&pf->sw_mutex); mutex_init(&pf->tc_mutex); @@ -4049,32 +4056,7 @@ static int ice_init_pf(struct ice_pf *pf) init_waitqueue_head(&pf->reset_wait_queue); - /* setup service timer and periodic service task */ - timer_setup(&pf->serv_tmr, ice_service_timer, 0); - pf->serv_tmr_period = HZ; - INIT_WORK(&pf->serv_task, ice_service_task); - clear_bit(ICE_SERVICE_SCHED, pf->state); - mutex_init(&pf->avail_q_mutex); - pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->avail_txqs) - return -ENOMEM; - - pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); - if (!pf->avail_rxqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - return -ENOMEM; - } - - pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); - if (!pf->txtime_txqs) { - bitmap_free(pf->avail_txqs); - pf->avail_txqs = NULL; - bitmap_free(pf->avail_rxqs); - pf->avail_rxqs = NULL; - return -ENOMEM; - } mutex_init(&pf->vfs.table_lock); hash_init(pf->vfs.table); @@ -4087,7 +4069,36 @@ static int ice_init_pf(struct ice_pf *pf) xa_init(&pf->dyn_ports); xa_init(&pf->sf_nums); + pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); + pf->txtime_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + if (!pf->avail_txqs || !pf->avail_rxqs || !pf->txtime_txqs) + goto undo_init; + + udp_tunnel_nic->set_port = ice_udp_tunnel_set_port; + udp_tunnel_nic->unset_port = ice_udp_tunnel_unset_port; + udp_tunnel_nic->shared = &hw->udp_tunnel_shared; + udp_tunnel_nic->tables[0].n_entries = hw->tnl.valid_count[TNL_VXLAN]; + udp_tunnel_nic->tables[0].tunnel_types = UDP_TUNNEL_TYPE_VXLAN; + udp_tunnel_nic->tables[1].n_entries = hw->tnl.valid_count[TNL_GENEVE]; + udp_tunnel_nic->tables[1].tunnel_types = UDP_TUNNEL_TYPE_GENEVE; + + /* In case of MSIX we are going to setup the misc vector right here + * to handle admin queue events etc. In case of legacy and MSI + * the misc functionality and queue processing is combined in + * the same vector and that gets setup at open. + */ + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "setup of misc vector failed: %d\n", err); + goto undo_init; + } + return 0; +undo_init: + /* deinit handles half-initialized pf just fine */ + ice_deinit_pf(pf); + return err; } /** @@ -4722,9 +4733,8 @@ static void ice_decfg_netdev(struct ice_vsi *vsi) vsi->netdev = NULL; } -int ice_init_dev(struct ice_pf *pf) +void ice_init_dev_hw(struct ice_pf *pf) { - struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int err; @@ -4744,61 +4754,28 @@ int ice_init_dev(struct ice_pf *pf) */ ice_set_safe_mode_caps(hw); } +} - err = ice_init_pf(pf); - if (err) { - dev_err(dev, "ice_init_pf failed: %d\n", err); - return err; - } - - pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port; - pf->hw.udp_tunnel_nic.unset_port = ice_udp_tunnel_unset_port; - pf->hw.udp_tunnel_nic.shared = &pf->hw.udp_tunnel_shared; - if (pf->hw.tnl.valid_count[TNL_VXLAN]) { - pf->hw.udp_tunnel_nic.tables[0].n_entries = - pf->hw.tnl.valid_count[TNL_VXLAN]; - pf->hw.udp_tunnel_nic.tables[0].tunnel_types = - UDP_TUNNEL_TYPE_VXLAN; - } - if (pf->hw.tnl.valid_count[TNL_GENEVE]) { - pf->hw.udp_tunnel_nic.tables[1].n_entries = - pf->hw.tnl.valid_count[TNL_GENEVE]; - pf->hw.udp_tunnel_nic.tables[1].tunnel_types = - UDP_TUNNEL_TYPE_GENEVE; - } +int ice_init_dev(struct ice_pf *pf) +{ + struct device *dev = ice_pf_to_dev(pf); + int err; + ice_set_pf_caps(pf); err = ice_init_interrupt_scheme(pf); if (err) { dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err); - err = -EIO; - goto unroll_pf_init; + return -EIO; } - /* In case of MSIX we are going to setup the misc vector right here - * to handle admin queue events etc. In case of legacy and MSI - * the misc functionality and queue processing is combined in - * the same vector and that gets setup at open. - */ - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "setup of misc vector failed: %d\n", err); - goto unroll_irq_scheme_init; - } + ice_start_service_task(pf); return 0; - -unroll_irq_scheme_init: - ice_clear_interrupt_scheme(pf); -unroll_pf_init: - ice_deinit_pf(pf); - return err; } void ice_deinit_dev(struct ice_pf *pf) { - ice_free_irq_msix_misc(pf); - ice_deinit_pf(pf); - ice_deinit_hw(&pf->hw); + ice_service_task_stop(pf); /* Service task is already stopped, so call reset directly. */ ice_reset(&pf->hw, ICE_RESET_PFR); @@ -5038,21 +5015,24 @@ static void ice_deinit_devlink(struct ice_pf *pf) static int ice_init(struct ice_pf *pf) { + struct device *dev = ice_pf_to_dev(pf); int err; - err = ice_init_dev(pf); - if (err) + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); return err; + } if (pf->hw.mac_type == ICE_MAC_E830) { err = pci_enable_ptm(pf->pdev, NULL); if (err) - dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n"); + dev_dbg(dev, "PCIe PTM not supported by PCIe bus/controller\n"); } err = ice_alloc_vsis(pf); if (err) - goto err_alloc_vsis; + goto unroll_pf_init; err = ice_init_pf_sw(pf); if (err) @@ -5089,8 +5069,8 @@ static int ice_init(struct ice_pf *pf) ice_deinit_pf_sw(pf); err_init_pf_sw: ice_dealloc_vsis(pf); -err_alloc_vsis: - ice_deinit_dev(pf); +unroll_pf_init: + ice_deinit_pf(pf); return err; } @@ -5101,7 +5081,7 @@ static void ice_deinit(struct ice_pf *pf) ice_deinit_pf_sw(pf); ice_dealloc_vsis(pf); - ice_deinit_dev(pf); + ice_deinit_pf(pf); } /** @@ -5235,6 +5215,7 @@ static int ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) { struct device *dev = &pdev->dev; + bool need_dev_deinit = false; struct ice_adapter *adapter; struct ice_pf *pf; struct ice_hw *hw; @@ -5331,10 +5312,14 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) } pf->adapter = adapter; - err = ice_init(pf); + err = ice_init_dev(pf); if (err) goto unroll_adapter; + err = ice_init(pf); + if (err) + goto unroll_dev_init; + devl_lock(priv_to_devlink(pf)); err = ice_load(pf); if (err) @@ -5352,10 +5337,14 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) unroll_init: devl_unlock(priv_to_devlink(pf)); ice_deinit(pf); +unroll_dev_init: + need_dev_deinit = true; unroll_adapter: ice_adapter_put(pdev); unroll_hw_init: ice_deinit_hw(hw); + if (need_dev_deinit) + ice_deinit_dev(pf); return err; } @@ -5450,10 +5439,6 @@ static void ice_remove(struct pci_dev *pdev) ice_hwmon_exit(pf); - ice_service_task_stop(pf); - ice_aq_cancel_waiting_tasks(pf); - set_bit(ICE_DOWN, pf->state); - if (!ice_is_safe_mode(pf)) ice_remove_arfs(pf); @@ -5471,6 +5456,11 @@ static void ice_remove(struct pci_dev *pdev) ice_set_wake(pf); ice_adapter_put(pdev); + ice_deinit_hw(&pf->hw); + + ice_deinit_dev(pf); + ice_aq_cancel_waiting_tasks(pf); + set_bit(ICE_DOWN, pf->state); } /** @@ -7138,6 +7128,9 @@ void ice_update_pf_stats(struct ice_pf *pf) &prev_ps->mac_remote_faults, &cur_ps->mac_remote_faults); + ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded, + &prev_ps->rx_len_errors, &cur_ps->rx_len_errors); + ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded, &prev_ps->rx_undersize, &cur_ps->rx_undersize); @@ -7862,12 +7855,6 @@ int ice_change_mtu(struct net_device *netdev, int new_mtu) frame_size - ICE_ETH_PKT_HDR_PAD); return -EINVAL; } - } else if (test_bit(ICE_FLAG_LEGACY_RX, pf->flags)) { - if (new_mtu + ICE_ETH_PKT_HDR_PAD > ICE_MAX_FRAME_LEGACY_RX) { - netdev_err(netdev, "Too big MTU for legacy-rx; Max is %d\n", - ICE_MAX_FRAME_LEGACY_RX - ICE_ETH_PKT_HDR_PAD); - return -EINVAL; - } } /* if a reset is in progress, wait for some time for it to complete */ @@ -8071,9 +8058,7 @@ static int ice_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_vsi *vsi = np->vsi; - struct ice_pf *pf = vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); u16 bmode; bmode = pf->first_sw->bridge_mode; @@ -8143,8 +8128,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 __always_unused flags, struct netlink_ext_ack __always_unused *extack) { - struct ice_netdev_priv *np = netdev_priv(dev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(dev); struct nlattr *attr, *br_spec; struct ice_hw *hw = &pf->hw; struct ice_sw *pf_sw; @@ -9578,8 +9562,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, */ int ice_open(struct net_device *netdev) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); if (ice_is_reset_in_progress(pf->state)) { netdev_err(netdev, "can't open net device while reset is in progress"); diff --git a/drivers/net/ethernet/intel/ice/ice_protocol_type.h b/drivers/net/ethernet/intel/ice/ice_protocol_type.h index 7c09ea0f03ba6..725167d557a8a 100644 --- a/drivers/net/ethernet/intel/ice/ice_protocol_type.h +++ b/drivers/net/ethernet/intel/ice/ice_protocol_type.h @@ -82,26 +82,46 @@ enum ice_sw_tunnel_type { enum ice_prot_id { ICE_PROT_ID_INVAL = 0, ICE_PROT_MAC_OF_OR_S = 1, + ICE_PROT_MAC_O2 = 2, ICE_PROT_MAC_IL = 4, + ICE_PROT_MAC_IN_MAC = 7, ICE_PROT_ETYPE_OL = 9, ICE_PROT_ETYPE_IL = 10, + ICE_PROT_PAY = 15, + ICE_PROT_EVLAN_O = 16, + ICE_PROT_VLAN_O = 17, + ICE_PROT_VLAN_IF = 18, + ICE_PROT_MPLS_OL_MINUS_1 = 27, + ICE_PROT_MPLS_OL_OR_OS = 28, + ICE_PROT_MPLS_IL = 29, ICE_PROT_IPV4_OF_OR_S = 32, ICE_PROT_IPV4_IL = 33, + ICE_PROT_IPV4_IL_IL = 34, ICE_PROT_IPV6_OF_OR_S = 40, ICE_PROT_IPV6_IL = 41, + ICE_PROT_IPV6_IL_IL = 42, + ICE_PROT_IPV6_NEXT_PROTO = 43, + ICE_PROT_IPV6_FRAG = 47, ICE_PROT_TCP_IL = 49, ICE_PROT_UDP_OF = 52, ICE_PROT_UDP_IL_OR_S = 53, ICE_PROT_GRE_OF = 64, + ICE_PROT_NSH_F = 84, ICE_PROT_ESP_F = 88, ICE_PROT_ESP_2 = 89, ICE_PROT_SCTP_IL = 96, ICE_PROT_ICMP_IL = 98, ICE_PROT_ICMPV6_IL = 100, + ICE_PROT_VRRP_F = 101, + ICE_PROT_OSPF = 102, ICE_PROT_PPPOE = 103, ICE_PROT_L2TPV3 = 104, + ICE_PROT_ATAOE_OF = 114, + ICE_PROT_CTRL_OF = 116, + ICE_PROT_LLDP_OF = 117, ICE_PROT_ARP_OF = 118, ICE_PROT_META_ID = 255, /* when offset == metadata */ + ICE_PROT_EAPOL_OF = 120, ICE_PROT_INVALID = 255 /* when offset == ICE_FV_OFFSET_INVAL */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index fb0f6365a6d6f..985b3e79b3126 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -500,6 +500,9 @@ void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx) if (tstamp) { shhwtstamps.hwtstamp = ns_to_ktime(tstamp); ice_trace(tx_tstamp_complete, skb, idx); + + /* Count the number of Tx timestamps that succeeded */ + pf->ptp.tx_hwtstamp_good++; } skb_tstamp_tx(skb, &shhwtstamps); @@ -558,6 +561,7 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) { struct ice_ptp_port *ptp_port; unsigned long flags; + u32 tstamp_good = 0; struct ice_pf *pf; struct ice_hw *hw; u64 tstamp_ready; @@ -658,11 +662,16 @@ static void ice_ptp_process_tx_tstamp(struct ice_ptp_tx *tx) if (tstamp) { shhwtstamps.hwtstamp = ns_to_ktime(tstamp); ice_trace(tx_tstamp_complete, skb, idx); + + /* Count the number of Tx timestamps that succeeded */ + tstamp_good++; } skb_tstamp_tx(skb, &shhwtstamps); dev_kfree_skb_any(skb); } + + pf->ptp.tx_hwtstamp_good += tstamp_good; } /** @@ -2206,8 +2215,7 @@ static int ice_ptp_getcrosststamp(struct ptp_clock_info *info, int ice_ptp_hwtstamp_get(struct net_device *netdev, struct kernel_hwtstamp_config *config) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); if (pf->ptp.state != ICE_PTP_READY) return -EIO; @@ -2278,8 +2286,7 @@ int ice_ptp_hwtstamp_set(struct net_device *netdev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); int err; if (pf->ptp.state != ICE_PTP_READY) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index 137f2070a2d99..27016aac4f1e8 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -237,6 +237,7 @@ struct ice_ptp_pin_desc { * @clock: pointer to registered PTP clock device * @tstamp_config: hardware timestamping configuration * @reset_time: kernel time after clock stop on reset + * @tx_hwtstamp_good: number of completed Tx timestamp requests * @tx_hwtstamp_skipped: number of Tx time stamp requests skipped * @tx_hwtstamp_timeouts: number of Tx skbs discarded with no time stamp * @tx_hwtstamp_flushed: number of Tx skbs flushed due to interface closed @@ -261,6 +262,7 @@ struct ice_ptp { struct ptp_clock *clock; struct kernel_hwtstamp_config tstamp_config; u64 reset_time; + u64 tx_hwtstamp_good; u32 tx_hwtstamp_skipped; u32 tx_hwtstamp_timeouts; u32 tx_hwtstamp_flushed; diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 843e82fd3bf93..6b1126ddb5616 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1190,8 +1190,7 @@ ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) */ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) { - struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_pf *pf = np->vsi->back; + struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vsi *vf_vsi; struct device *dev; struct ice_vf *vf; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 73f08d02f9c76..ad76768a42323 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -7,6 +7,8 @@ #include #include #include +#include +#include #include #include #include @@ -111,7 +113,7 @@ ice_prgm_fdir_fltr(struct ice_vsi *vsi, struct ice_fltr_desc *fdir_desc, static void ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) { - if (dma_unmap_len(tx_buf, len)) + if (tx_buf->type != ICE_TX_BUF_XDP_TX && dma_unmap_len(tx_buf, len)) dma_unmap_page(ring->dev, dma_unmap_addr(tx_buf, dma), dma_unmap_len(tx_buf, len), @@ -125,7 +127,7 @@ ice_unmap_and_free_tx_buf(struct ice_tx_ring *ring, struct ice_tx_buf *tx_buf) dev_kfree_skb_any(tx_buf->skb); break; case ICE_TX_BUF_XDP_TX: - page_frag_free(tx_buf->raw_buf); + libeth_xdp_return_va(tx_buf->raw_buf, false); break; case ICE_TX_BUF_XDP_XMIT: xdp_return_frame(tx_buf->xdpf); @@ -506,61 +508,67 @@ int ice_setup_tx_ring(struct ice_tx_ring *tx_ring) return -ENOMEM; } +void ice_rxq_pp_destroy(struct ice_rx_ring *rq) +{ + struct libeth_fq fq = { + .fqes = rq->rx_fqes, + .pp = rq->pp, + }; + + libeth_rx_fq_destroy(&fq); + rq->rx_fqes = NULL; + rq->pp = NULL; + + if (!rq->hdr_pp) + return; + + fq.fqes = rq->hdr_fqes; + fq.pp = rq->hdr_pp; + + libeth_rx_fq_destroy(&fq); + rq->hdr_fqes = NULL; + rq->hdr_pp = NULL; +} + /** * ice_clean_rx_ring - Free Rx buffers * @rx_ring: ring to be cleaned */ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) { - struct xdp_buff *xdp = &rx_ring->xdp; - struct device *dev = rx_ring->dev; u32 size; - u16 i; - - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_buf) - return; if (rx_ring->xsk_pool) { ice_xsk_clean_rx_ring(rx_ring); goto rx_skip_free; } - if (xdp->data) { - xdp_return_buff(xdp); - xdp->data = NULL; - } + /* ring already cleared, nothing to do */ + if (!rx_ring->rx_fqes) + return; + + libeth_xdp_return_stash(&rx_ring->xdp); /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { - struct ice_rx_buf *rx_buf = &rx_ring->rx_buf[i]; + for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) { + libeth_rx_recycle_slow(rx_ring->rx_fqes[i].netmem); - if (!rx_buf->page) - continue; + if (rx_ring->hdr_pp) + libeth_rx_recycle_slow(rx_ring->hdr_fqes[i].netmem); - /* Invalidate cache lines that may have been written to by - * device so that we avoid corrupting memory. - */ - dma_sync_single_range_for_cpu(dev, rx_buf->dma, - rx_buf->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - - /* free resources associated with mapping */ - dma_unmap_page_attrs(dev, rx_buf->dma, ice_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, ICE_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias); - - rx_buf->page = NULL; - rx_buf->page_offset = 0; + if (unlikely(++i == rx_ring->count)) + i = 0; } -rx_skip_free: - if (rx_ring->xsk_pool) - memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf))); - else - memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf))); + if (rx_ring->vsi->type == ICE_VSI_PF && + xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) { + xdp_rxq_info_detach_mem_model(&rx_ring->xdp_rxq); + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + } + ice_rxq_pp_destroy(rx_ring); + +rx_skip_free: /* Zero out the descriptor ring */ size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), PAGE_SIZE); @@ -568,7 +576,6 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; - rx_ring->first_desc = 0; rx_ring->next_to_use = 0; } @@ -580,26 +587,20 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring) */ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) { + struct device *dev = ice_pf_to_dev(rx_ring->vsi->back); u32 size; ice_clean_rx_ring(rx_ring); - if (rx_ring->vsi->type == ICE_VSI_PF) - if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) - xdp_rxq_info_unreg(&rx_ring->xdp_rxq); WRITE_ONCE(rx_ring->xdp_prog, NULL); if (rx_ring->xsk_pool) { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; - } else { - kfree(rx_ring->rx_buf); - rx_ring->rx_buf = NULL; } if (rx_ring->desc) { size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), PAGE_SIZE); - dmam_free_coherent(rx_ring->dev, size, - rx_ring->desc, rx_ring->dma); + dmam_free_coherent(dev, size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } } @@ -612,19 +613,9 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring) */ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) { - struct device *dev = rx_ring->dev; + struct device *dev = ice_pf_to_dev(rx_ring->vsi->back); u32 size; - if (!dev) - return -ENOMEM; - - /* warn if we are about to overwrite the pointer */ - WARN_ON(rx_ring->rx_buf); - rx_ring->rx_buf = - kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL); - if (!rx_ring->rx_buf) - return -ENOMEM; - /* round up to nearest page */ size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc), PAGE_SIZE); @@ -633,22 +624,16 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) if (!rx_ring->desc) { dev_err(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", size); - goto err; + return -ENOMEM; } rx_ring->next_to_use = 0; rx_ring->next_to_clean = 0; - rx_ring->first_desc = 0; if (ice_is_xdp_ena_vsi(rx_ring->vsi)) WRITE_ONCE(rx_ring->xdp_prog, rx_ring->vsi->xdp_prog); return 0; - -err: - kfree(rx_ring->rx_buf); - rx_ring->rx_buf = NULL; - return -ENOMEM; } /** @@ -662,7 +647,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring) * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR} */ static u32 -ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, +ice_run_xdp(struct ice_rx_ring *rx_ring, struct libeth_xdp_buff *xdp, struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring, union ice_32b_rx_flex_desc *eop_desc) { @@ -672,23 +657,23 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, if (!xdp_prog) goto exit; - ice_xdp_meta_set_desc(xdp, eop_desc); + xdp->desc = eop_desc; - act = bpf_prog_run_xdp(xdp_prog, xdp); + act = bpf_prog_run_xdp(xdp_prog, &xdp->base); switch (act) { case XDP_PASS: break; case XDP_TX: if (static_branch_unlikely(&ice_xdp_locking_key)) spin_lock(&xdp_ring->tx_lock); - ret = __ice_xmit_xdp_ring(xdp, xdp_ring, false); + ret = __ice_xmit_xdp_ring(&xdp->base, xdp_ring, false); if (static_branch_unlikely(&ice_xdp_locking_key)) spin_unlock(&xdp_ring->tx_lock); if (ret == ICE_XDP_CONSUMED) goto out_failure; break; case XDP_REDIRECT: - if (xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog)) + if (xdp_do_redirect(rx_ring->netdev, &xdp->base, xdp_prog)) goto out_failure; ret = ICE_XDP_REDIR; break; @@ -700,8 +685,10 @@ ice_run_xdp(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, trace_xdp_exception(rx_ring->netdev, xdp_prog, act); fallthrough; case XDP_DROP: + libeth_xdp_return_buff(xdp); ret = ICE_XDP_CONSUMED; } + exit: return ret; } @@ -789,53 +776,6 @@ ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, return nxmit; } -/** - * ice_alloc_mapped_page - recycle or make a new page - * @rx_ring: ring to use - * @bi: rx_buf struct to modify - * - * Returns true if the page was successfully allocated or - * reused. - */ -static bool -ice_alloc_mapped_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *bi) -{ - struct page *page = bi->page; - dma_addr_t dma; - - /* since we are recycling buffers we should seldom need to alloc */ - if (likely(page)) - return true; - - /* alloc new page for storage */ - page = dev_alloc_pages(ice_rx_pg_order(rx_ring)); - if (unlikely(!page)) { - rx_ring->ring_stats->rx_stats.alloc_page_failed++; - return false; - } - - /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, ice_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, ICE_RX_DMA_ATTR); - - /* if mapping failed free memory back to system since - * there isn't much point in holding memory we can't use - */ - if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, ice_rx_pg_order(rx_ring)); - rx_ring->ring_stats->rx_stats.alloc_page_failed++; - return false; - } - - bi->dma = dma; - bi->page = page; - bi->page_offset = rx_ring->rx_offset; - page_ref_add(page, USHRT_MAX - 1); - bi->pagecnt_bias = USHRT_MAX; - - return true; -} - /** * ice_init_ctrl_rx_descs - Initialize Rx descriptors for control vsi. * @rx_ring: ring to init descriptors on @@ -882,9 +822,20 @@ void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 count) */ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) { + const struct libeth_fq_fp hdr_fq = { + .pp = rx_ring->hdr_pp, + .fqes = rx_ring->hdr_fqes, + .truesize = rx_ring->hdr_truesize, + .count = rx_ring->count, + }; + const struct libeth_fq_fp fq = { + .pp = rx_ring->pp, + .fqes = rx_ring->rx_fqes, + .truesize = rx_ring->truesize, + .count = rx_ring->count, + }; union ice_32b_rx_flex_desc *rx_desc; u16 ntu = rx_ring->next_to_use; - struct ice_rx_buf *bi; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) @@ -892,30 +843,39 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) /* get the Rx descriptor and buffer based on next_to_use */ rx_desc = ICE_RX_DESC(rx_ring, ntu); - bi = &rx_ring->rx_buf[ntu]; do { - /* if we fail here, we have work remaining */ - if (!ice_alloc_mapped_page(rx_ring, bi)) - break; + dma_addr_t addr; - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); + addr = libeth_rx_alloc(&fq, ntu); + if (addr == DMA_MAPPING_ERROR) { + rx_ring->ring_stats->rx_stats.alloc_page_failed++; + break; + } /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + rx_desc->read.pkt_addr = cpu_to_le64(addr); + + if (!hdr_fq.pp) + goto next; + + addr = libeth_rx_alloc(&hdr_fq, ntu); + if (addr == DMA_MAPPING_ERROR) { + rx_ring->ring_stats->rx_stats.alloc_page_failed++; + + libeth_rx_recycle_slow(fq.fqes[ntu].netmem); + break; + } + + rx_desc->read.hdr_addr = cpu_to_le64(addr); +next: rx_desc++; - bi++; ntu++; if (unlikely(ntu == rx_ring->count)) { rx_desc = ICE_RX_DESC(rx_ring, 0); - bi = rx_ring->rx_buf; ntu = 0; } @@ -931,402 +891,6 @@ bool ice_alloc_rx_bufs(struct ice_rx_ring *rx_ring, unsigned int cleaned_count) return !!cleaned_count; } -/** - * ice_rx_buf_adjust_pg_offset - Prepare Rx buffer for reuse - * @rx_buf: Rx buffer to adjust - * @size: Size of adjustment - * - * Update the offset within page so that Rx buf will be ready to be reused. - * For systems with PAGE_SIZE < 8192 this function will flip the page offset - * so the second half of page assigned to Rx buffer will be used, otherwise - * the offset is moved by "size" bytes - */ -static void -ice_rx_buf_adjust_pg_offset(struct ice_rx_buf *rx_buf, unsigned int size) -{ -#if (PAGE_SIZE < 8192) - /* flip page offset to other buffer */ - rx_buf->page_offset ^= size; -#else - /* move offset up to the next cache line */ - rx_buf->page_offset += size; -#endif -} - -/** - * ice_can_reuse_rx_page - Determine if page can be reused for another Rx - * @rx_buf: buffer containing the page - * - * If page is reusable, we have a green light for calling ice_reuse_rx_page, - * which will assign the current buffer to the buffer that next_to_alloc is - * pointing to; otherwise, the DMA mapping needs to be destroyed and - * page freed - */ -static bool -ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf) -{ - unsigned int pagecnt_bias = rx_buf->pagecnt_bias; - struct page *page = rx_buf->page; - - /* avoid re-using remote and pfmemalloc pages */ - if (!dev_page_is_reusable(page)) - return false; - - /* if we are only owner of page we can reuse it */ - if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1)) - return false; -#if (PAGE_SIZE >= 8192) -#define ICE_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072) - if (rx_buf->page_offset > ICE_LAST_OFFSET) - return false; -#endif /* PAGE_SIZE >= 8192) */ - - /* If we have drained the page fragment pool we need to update - * the pagecnt_bias and page count so that we fully restock the - * number of references the driver holds. - */ - if (unlikely(pagecnt_bias == 1)) { - page_ref_add(page, USHRT_MAX - 1); - rx_buf->pagecnt_bias = USHRT_MAX; - } - - return true; -} - -/** - * ice_add_xdp_frag - Add contents of Rx buffer to xdp buf as a frag - * @rx_ring: Rx descriptor ring to transact packets on - * @xdp: xdp buff to place the data into - * @rx_buf: buffer containing page to add - * @size: packet length from rx_desc - * - * This function will add the data contained in rx_buf->page to the xdp buf. - * It will just attach the page as a frag. - */ -static int -ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - struct ice_rx_buf *rx_buf, const unsigned int size) -{ - struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); - - if (!size) - return 0; - - if (!xdp_buff_has_frags(xdp)) { - sinfo->nr_frags = 0; - sinfo->xdp_frags_size = 0; - xdp_buff_set_frags_flag(xdp); - } - - if (unlikely(sinfo->nr_frags == MAX_SKB_FRAGS)) - return -ENOMEM; - - __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page, - rx_buf->page_offset, size); - sinfo->xdp_frags_size += size; - - if (page_is_pfmemalloc(rx_buf->page)) - xdp_buff_set_frag_pfmemalloc(xdp); - - return 0; -} - -/** - * ice_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: Rx descriptor ring to store buffers on - * @old_buf: donor buffer to have page reused - * - * Synchronizes page for reuse by the adapter - */ -static void -ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf) -{ - u16 nta = rx_ring->next_to_alloc; - struct ice_rx_buf *new_buf; - - new_buf = &rx_ring->rx_buf[nta]; - - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* Transfer page from old buffer to new buffer. - * Move each member individually to avoid possible store - * forwarding stalls and unnecessary copy of skb. - */ - new_buf->dma = old_buf->dma; - new_buf->page = old_buf->page; - new_buf->page_offset = old_buf->page_offset; - new_buf->pagecnt_bias = old_buf->pagecnt_bias; -} - -/** - * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use - * @rx_ring: Rx descriptor ring to transact packets on - * @size: size of buffer to add to skb - * @ntc: index of next to clean element - * - * This function will pull an Rx buffer from the ring and synchronize it - * for use by the CPU. - */ -static struct ice_rx_buf * -ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size, - const unsigned int ntc) -{ - struct ice_rx_buf *rx_buf; - - rx_buf = &rx_ring->rx_buf[ntc]; - prefetchw(rx_buf->page); - - if (!size) - return rx_buf; - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma, - rx_buf->page_offset, size, - DMA_FROM_DEVICE); - - /* We have pulled a buffer for use, so decrement pagecnt_bias */ - rx_buf->pagecnt_bias--; - - return rx_buf; -} - -/** - * ice_get_pgcnts - grab page_count() for gathered fragments - * @rx_ring: Rx descriptor ring to store the page counts on - * @ntc: the next to clean element (not included in this frame!) - * - * This function is intended to be called right before running XDP - * program so that the page recycling mechanism will be able to take - * a correct decision regarding underlying pages; this is done in such - * way as XDP program can change the refcount of page - */ -static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc) -{ - u32 idx = rx_ring->first_desc; - struct ice_rx_buf *rx_buf; - u32 cnt = rx_ring->count; - - while (idx != ntc) { - rx_buf = &rx_ring->rx_buf[idx]; - rx_buf->pgcnt = page_count(rx_buf->page); - - if (++idx == cnt) - idx = 0; - } -} - -/** - * ice_build_skb - Build skb around an existing buffer - * @rx_ring: Rx descriptor ring to transact packets on - * @xdp: xdp_buff pointing to the data - * - * This function builds an skb around an existing XDP buffer, taking care - * to set up the skb correctly and avoid any memcpy overhead. Driver has - * already combined frags (if any) to skb_shared_info. - */ -static struct sk_buff * -ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) -{ - u8 metasize = xdp->data - xdp->data_meta; - struct skb_shared_info *sinfo = NULL; - unsigned int nr_frags; - struct sk_buff *skb; - - if (unlikely(xdp_buff_has_frags(xdp))) { - sinfo = xdp_get_shared_info_from_buff(xdp); - nr_frags = sinfo->nr_frags; - } - - /* Prefetch first cache line of first page. If xdp->data_meta - * is unused, this points exactly as xdp->data, otherwise we - * likely have a consumer accessing first few bytes of meta - * data, and then actual data. - */ - net_prefetch(xdp->data_meta); - /* build an skb around the page buffer */ - skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); - if (unlikely(!skb)) - return NULL; - - /* must to record Rx queue, otherwise OS features such as - * symmetric queue won't work - */ - skb_record_rx_queue(skb, rx_ring->q_index); - - /* update pointers within the skb to store the data */ - skb_reserve(skb, xdp->data - xdp->data_hard_start); - __skb_put(skb, xdp->data_end - xdp->data); - if (metasize) - skb_metadata_set(skb, metasize); - - if (unlikely(xdp_buff_has_frags(xdp))) - xdp_update_skb_frags_info(skb, nr_frags, sinfo->xdp_frags_size, - nr_frags * xdp->frame_sz, - xdp_buff_get_skb_flags(xdp)); - - return skb; -} - -/** - * ice_construct_skb - Allocate skb and populate it - * @rx_ring: Rx descriptor ring to transact packets on - * @xdp: xdp_buff pointing to the data - * - * This function allocates an skb. It then populates it with the page - * data from the current receive descriptor, taking care to set up the - * skb correctly. - */ -static struct sk_buff * -ice_construct_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) -{ - unsigned int size = xdp->data_end - xdp->data; - struct skb_shared_info *sinfo = NULL; - struct ice_rx_buf *rx_buf; - unsigned int nr_frags = 0; - unsigned int headlen; - struct sk_buff *skb; - - /* prefetch first cache line of first page */ - net_prefetch(xdp->data); - - if (unlikely(xdp_buff_has_frags(xdp))) { - sinfo = xdp_get_shared_info_from_buff(xdp); - nr_frags = sinfo->nr_frags; - } - - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, ICE_RX_HDR_SIZE); - if (unlikely(!skb)) - return NULL; - - rx_buf = &rx_ring->rx_buf[rx_ring->first_desc]; - skb_record_rx_queue(skb, rx_ring->q_index); - /* Determine available headroom for copy */ - headlen = size; - if (headlen > ICE_RX_HDR_SIZE) - headlen = eth_get_headlen(skb->dev, xdp->data, ICE_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, - sizeof(long))); - - /* if we exhaust the linear part then add what is left as a frag */ - size -= headlen; - if (size) { - /* besides adding here a partial frag, we are going to add - * frags from xdp_buff, make sure there is enough space for - * them - */ - if (unlikely(nr_frags >= MAX_SKB_FRAGS - 1)) { - dev_kfree_skb(skb); - return NULL; - } - skb_add_rx_frag(skb, 0, rx_buf->page, - rx_buf->page_offset + headlen, size, - xdp->frame_sz); - } else { - /* buffer is unused, restore biased page count in Rx buffer; - * data was copied onto skb's linear part so there's no - * need for adjusting page offset and we can reuse this buffer - * as-is - */ - rx_buf->pagecnt_bias++; - } - - if (unlikely(xdp_buff_has_frags(xdp))) { - struct skb_shared_info *skinfo = skb_shinfo(skb); - - memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0], - sizeof(skb_frag_t) * nr_frags); - - xdp_update_skb_frags_info(skb, skinfo->nr_frags + nr_frags, - sinfo->xdp_frags_size, - nr_frags * xdp->frame_sz, - xdp_buff_get_skb_flags(xdp)); - } - - return skb; -} - -/** - * ice_put_rx_buf - Clean up used buffer and either recycle or free - * @rx_ring: Rx descriptor ring to transact packets on - * @rx_buf: Rx buffer to pull data from - * - * This function will clean up the contents of the rx_buf. It will either - * recycle the buffer or unmap it and free the associated resources. - */ -static void -ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf) -{ - if (!rx_buf) - return; - - if (ice_can_reuse_rx_page(rx_buf)) { - /* hand second half of page back to the ring */ - ice_reuse_rx_page(rx_ring, rx_buf); - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buf->dma, - ice_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - ICE_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buf->page, rx_buf->pagecnt_bias); - } - - /* clear contents of buffer_info */ - rx_buf->page = NULL; -} - -/** - * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame - * @rx_ring: Rx ring with all the auxiliary data - * @xdp: XDP buffer carrying linear + frags part - * @ntc: the next to clean element (not included in this frame!) - * @verdict: return code from XDP program execution - * - * Called after XDP program is completed, or on error with verdict set to - * ICE_XDP_CONSUMED. - * - * Walk through buffers from first_desc to the end of the frame, releasing - * buffers and satisfying internal page recycle mechanism. The action depends - * on verdict from XDP program. - */ -static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp, - u32 ntc, u32 verdict) -{ - u32 idx = rx_ring->first_desc; - u32 cnt = rx_ring->count; - struct ice_rx_buf *buf; - u32 xdp_frags = 0; - int i = 0; - - if (unlikely(xdp_buff_has_frags(xdp))) - xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags; - - while (idx != ntc) { - buf = &rx_ring->rx_buf[idx]; - if (++idx == cnt) - idx = 0; - - /* An XDP program could release fragments from the end of the - * buffer. For these, we need to keep the pagecnt_bias as-is. - * To do this, only adjust pagecnt_bias for fragments up to - * the total remaining after the XDP program has run. - */ - if (verdict != ICE_XDP_CONSUMED) - ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz); - else if (i++ <= xdp_frags) - buf->pagecnt_bias++; - - ice_put_rx_buf(rx_ring, buf); - } - - xdp->data = NULL; - rx_ring->first_desc = ntc; -} - /** * ice_clean_ctrl_rx_irq - Clean descriptors from flow director Rx ring * @rx_ring: Rx descriptor ring for ctrl_vsi to transact packets on @@ -1361,9 +925,8 @@ void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring) total_rx_pkts++; } - rx_ring->first_desc = ntc; rx_ring->next_to_clean = ntc; - ice_init_ctrl_rx_descs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); + ice_init_ctrl_rx_descs(rx_ring, ICE_DESC_UNUSED(rx_ring)); } /** @@ -1381,16 +944,17 @@ void ice_clean_ctrl_rx_irq(struct ice_rx_ring *rx_ring) static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0; - unsigned int offset = rx_ring->rx_offset; - struct xdp_buff *xdp = &rx_ring->xdp; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; + LIBETH_XDP_ONSTACK_BUFF(xdp); u32 cached_ntu, xdp_verdict; u32 cnt = rx_ring->count; u32 xdp_xmit = 0; bool failure; + libeth_xdp_init_buff(xdp, &rx_ring->xdp, &rx_ring->xdp_rxq); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); if (xdp_prog) { xdp_ring = rx_ring->xdp_ring; @@ -1400,19 +964,21 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; - struct ice_rx_buf *rx_buf; + struct libeth_fqe *rx_buf; struct sk_buff *skb; unsigned int size; u16 stat_err_bits; u16 vlan_tci; + bool rxe; /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, ntc); - /* status_error_len will always be zero for unused descriptors - * because it's cleared in cleanup, and overlaps with hdr_addr - * which is always zero because packet split isn't used, if the - * hardware wrote DD then it will be non-zero + /* + * The DD bit will always be zero for unused descriptors + * because it's cleared in cleanup or when setting the DMA + * address of the header buffer, which never uses the DD bit. + * If the hardware wrote the descriptor, it will be non-zero. */ stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S); if (!ice_test_staterr(rx_desc->wb.status_error0, stat_err_bits)) @@ -1426,71 +992,65 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) ice_trace(clean_rx_irq, rx_ring, rx_desc); + stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_HBO_S) | + BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); + rxe = ice_test_staterr(rx_desc->wb.status_error0, + stat_err_bits); + + if (!rx_ring->hdr_pp) + goto payload; + + size = le16_get_bits(rx_desc->wb.hdr_len_sph_flex_flags1, + ICE_RX_FLEX_DESC_HDR_LEN_M); + if (unlikely(rxe)) + size = 0; + + rx_buf = &rx_ring->hdr_fqes[ntc]; + libeth_xdp_process_buff(xdp, rx_buf, size); + rx_buf->netmem = 0; + +payload: size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; + if (unlikely(rxe)) + size = 0; /* retrieve a buffer from the ring */ - rx_buf = ice_get_rx_buf(rx_ring, size, ntc); + rx_buf = &rx_ring->rx_fqes[ntc]; + libeth_xdp_process_buff(xdp, rx_buf, size); - /* Increment ntc before calls to ice_put_rx_mbuf() */ if (++ntc == cnt) ntc = 0; - if (!xdp->data) { - void *hard_start; - - hard_start = page_address(rx_buf->page) + rx_buf->page_offset - - offset; - xdp_prepare_buff(xdp, hard_start, offset, size, !!offset); - xdp_buff_clear_frags_flag(xdp); - } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) { - ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED); - break; - } - /* skip if it is NOP desc */ - if (ice_is_non_eop(rx_ring, rx_desc)) + if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!xdp->data)) continue; - ice_get_pgcnts(rx_ring, ntc); xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc); if (xdp_verdict == ICE_XDP_PASS) goto construct_skb; - total_rx_bytes += xdp_get_buff_len(xdp); - total_rx_pkts++; - ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); - xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR); + if (xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) + xdp_xmit |= xdp_verdict; + total_rx_bytes += xdp_get_buff_len(&xdp->base); + total_rx_pkts++; + xdp->data = NULL; continue; + construct_skb: - if (likely(ice_ring_uses_build_skb(rx_ring))) - skb = ice_build_skb(rx_ring, xdp); - else - skb = ice_construct_skb(rx_ring, xdp); + skb = xdp_build_skb_from_buff(&xdp->base); + xdp->data = NULL; + /* exit if we failed to retrieve a buffer */ if (!skb) { + libeth_xdp_return_buff_slow(xdp); rx_ring->ring_stats->rx_stats.alloc_buf_failed++; - xdp_verdict = ICE_XDP_CONSUMED; - } - ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict); - - if (!skb) - break; - - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_RXE_S); - if (unlikely(ice_test_staterr(rx_desc->wb.status_error0, - stat_err_bits))) { - dev_kfree_skb_any(skb); continue; } vlan_tci = ice_get_vlan_tci(rx_desc); - /* pad the skb if needed, to make a valid ethernet frame */ - if (eth_skb_pad(skb)) - continue; - /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; @@ -1507,11 +1067,13 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) rx_ring->next_to_clean = ntc; /* return up to cleaned_count buffers to hardware */ - failure = ice_alloc_rx_bufs(rx_ring, ICE_RX_DESC_UNUSED(rx_ring)); + failure = ice_alloc_rx_bufs(rx_ring, ICE_DESC_UNUSED(rx_ring)); if (xdp_xmit) ice_finalize_xdp_rx(xdp_ring, xdp_xmit, cached_ntu); + libeth_xdp_save_buff(&rx_ring->xdp, xdp); + if (rx_ring->ring_stats) ice_update_rx_ring_stats(rx_ring, total_rx_pkts, total_rx_bytes); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 841a07bfba54f..e440c55d9e9f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -4,6 +4,8 @@ #ifndef _ICE_TXRX_H_ #define _ICE_TXRX_H_ +#include + #include "ice_type.h" #define ICE_DFLT_IRQ_WORK 256 @@ -27,72 +29,6 @@ #define ICE_MAX_TXQ_PER_TXQG 128 -/* Attempt to maximize the headroom available for incoming frames. We use a 2K - * buffer for MTUs <= 1500 and need 1536/1534 to store the data for the frame. - * This leaves us with 512 bytes of room. From that we need to deduct the - * space needed for the shared info and the padding needed to IP align the - * frame. - * - * Note: For cache line sizes 256 or larger this value is going to end - * up negative. In these cases we should fall back to the legacy - * receive path. - */ -#if (PAGE_SIZE < 8192) -#define ICE_2K_TOO_SMALL_WITH_PADDING \ - ((unsigned int)(NET_SKB_PAD + ICE_RXBUF_1536) > \ - SKB_WITH_OVERHEAD(ICE_RXBUF_2048)) - -/** - * ice_compute_pad - compute the padding - * @rx_buf_len: buffer length - * - * Figure out the size of half page based on given buffer length and - * then subtract the skb_shared_info followed by subtraction of the - * actual buffer length; this in turn results in the actual space that - * is left for padding usage - */ -static inline int ice_compute_pad(int rx_buf_len) -{ - int half_page_size; - - half_page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); - return SKB_WITH_OVERHEAD(half_page_size) - rx_buf_len; -} - -/** - * ice_skb_pad - determine the padding that we can supply - * - * Figure out the right Rx buffer size and based on that calculate the - * padding - */ -static inline int ice_skb_pad(void) -{ - int rx_buf_len; - - /* If a 2K buffer cannot handle a standard Ethernet frame then - * optimize padding for a 3K buffer instead of a 1.5K buffer. - * - * For a 3K buffer we need to add enough padding to allow for - * tailroom due to NET_IP_ALIGN possibly shifting us out of - * cache-line alignment. - */ - if (ICE_2K_TOO_SMALL_WITH_PADDING) - rx_buf_len = ICE_RXBUF_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); - else - rx_buf_len = ICE_RXBUF_1536; - - /* if needed make room for NET_IP_ALIGN */ - rx_buf_len -= NET_IP_ALIGN; - - return ice_compute_pad(rx_buf_len); -} - -#define ICE_SKB_PAD ice_skb_pad() -#else -#define ICE_2K_TOO_SMALL_WITH_PADDING false -#define ICE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -#endif - /* We are assuming that the cache line is always 64 Bytes here for ice. * In order to make sure that is a correct assumption there is a check in probe * to print a warning if the read from GLPCI_CNF2 tells us that the cache line @@ -112,10 +48,6 @@ static inline int ice_skb_pad(void) (u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ (R)->next_to_clean - (R)->next_to_use - 1) -#define ICE_RX_DESC_UNUSED(R) \ - ((((R)->first_desc > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->first_desc - (R)->next_to_use - 1) - #define ICE_RING_QUARTER(R) ((R)->count >> 2) #define ICE_TX_FLAGS_TSO BIT(0) @@ -197,14 +129,6 @@ struct ice_tx_offload_params { u8 header_len; }; -struct ice_rx_buf { - dma_addr_t dma; - struct page *page; - unsigned int page_offset; - unsigned int pgcnt; - unsigned int pagecnt_bias; -}; - struct ice_q_stats { u64 pkts; u64 bytes; @@ -262,15 +186,6 @@ struct ice_pkt_ctx { __be16 vlan_proto; }; -struct ice_xdp_buff { - struct xdp_buff xdp_buff; - const union ice_32b_rx_flex_desc *eop_desc; - const struct ice_pkt_ctx *pkt_ctx; -}; - -/* Required for compatibility with xdp_buffs from xsk_pool */ -static_assert(offsetof(struct ice_xdp_buff, xdp_buff) == 0); - /* indices into GLINT_ITR registers */ #define ICE_RX_ITR ICE_IDX_ITR0 #define ICE_TX_ITR ICE_IDX_ITR1 @@ -323,7 +238,7 @@ struct ice_tstamp_ring { struct ice_rx_ring { /* CL1 - 1st cacheline starts here */ void *desc; /* Descriptor ring memory */ - struct device *dev; /* Used for DMA mapping */ + struct page_pool *pp; struct net_device *netdev; /* netdev ring maps to */ struct ice_vsi *vsi; /* Backreference to associated VSI */ struct ice_q_vector *q_vector; /* Backreference to associated vector */ @@ -335,14 +250,19 @@ struct ice_rx_ring { u16 next_to_alloc; union { - struct ice_rx_buf *rx_buf; + struct libeth_fqe *rx_fqes; struct xdp_buff **xdp_buf; }; + /* CL2 - 2nd cacheline starts here */ + struct libeth_fqe *hdr_fqes; + struct page_pool *hdr_pp; + union { - struct ice_xdp_buff xdp_ext; - struct xdp_buff xdp; + struct libeth_xdp_buff_stash xdp; + struct libeth_xdp_buff *xsk; }; + /* CL3 - 3rd cacheline starts here */ union { struct ice_pkt_ctx pkt_ctx; @@ -352,12 +272,13 @@ struct ice_rx_ring { }; }; struct bpf_prog *xdp_prog; - u16 rx_offset; /* used in interrupt processing */ u16 next_to_use; u16 next_to_clean; - u16 first_desc; + + u32 hdr_truesize; + u32 truesize; /* stats structs */ struct ice_ring_stats *ring_stats; @@ -368,12 +289,11 @@ struct ice_rx_ring { struct ice_tx_ring *xdp_ring; struct ice_rx_ring *next; /* pointer to next ring in q_vector */ struct xsk_buff_pool *xsk_pool; - u16 max_frame; + u16 rx_hdr_len; u16 rx_buf_len; dma_addr_t dma; /* physical address of ring */ u8 dcb_tc; /* Traffic class of ring */ u8 ptp_rx; -#define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) #define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) #define ICE_RX_FLAGS_MULTIDEV BIT(3) #define ICE_RX_FLAGS_RING_GCS BIT(4) @@ -422,21 +342,6 @@ struct ice_tx_ring { u16 quanta_prof_id; } ____cacheline_internodealigned_in_smp; -static inline bool ice_ring_uses_build_skb(struct ice_rx_ring *ring) -{ - return !!(ring->flags & ICE_RX_FLAGS_RING_BUILD_SKB); -} - -static inline void ice_set_ring_build_skb_ena(struct ice_rx_ring *ring) -{ - ring->flags |= ICE_RX_FLAGS_RING_BUILD_SKB; -} - -static inline void ice_clear_ring_build_skb_ena(struct ice_rx_ring *ring) -{ - ring->flags &= ~ICE_RX_FLAGS_RING_BUILD_SKB; -} - static inline bool ice_ring_ch_enabled(struct ice_tx_ring *ring) { return !!ring->ch; @@ -491,18 +396,13 @@ struct ice_coalesce_stored { static inline unsigned int ice_rx_pg_order(struct ice_rx_ring *ring) { -#if (PAGE_SIZE < 8192) - if (ring->rx_buf_len > (PAGE_SIZE / 2)) - return 1; -#endif return 0; } -#define ice_rx_pg_size(_ring) (PAGE_SIZE << ice_rx_pg_order(_ring)) - union ice_32b_rx_flex_desc; void ice_init_ctrl_rx_descs(struct ice_rx_ring *rx_ring, u32 num_descs); +void ice_rxq_pp_destroy(struct ice_rx_ring *rq); bool ice_alloc_rx_bufs(struct ice_rx_ring *rxr, unsigned int cleaned_count); netdev_tx_t ice_start_xmit(struct sk_buff *skb, struct net_device *netdev); u16 diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 45cfaabc41cbe..956da38d63b00 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -3,6 +3,7 @@ #include #include +#include #include "ice_txrx_lib.h" #include "ice_eswitch.h" @@ -230,9 +231,12 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, if (ice_is_port_repr_netdev(netdev)) ice_repr_inc_rx_stats(netdev, skb->len); + + /* __skb_push() is needed because xdp_build_skb_from_buff() + * calls eth_type_trans() + */ + __skb_push(skb, ETH_HLEN); skb->protocol = eth_type_trans(skb, netdev); - } else { - skb->protocol = eth_type_trans(skb, rx_ring->netdev); } ice_rx_csum(rx_ring, skb, rx_desc, ptype); @@ -270,19 +274,18 @@ static void ice_clean_xdp_tx_buf(struct device *dev, struct ice_tx_buf *tx_buf, struct xdp_frame_bulk *bq) { - dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma), - dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); - dma_unmap_len_set(tx_buf, len, 0); - switch (tx_buf->type) { case ICE_TX_BUF_XDP_TX: - page_frag_free(tx_buf->raw_buf); + libeth_xdp_return_va(tx_buf->raw_buf, true); break; case ICE_TX_BUF_XDP_XMIT: + dma_unmap_single(dev, dma_unmap_addr(tx_buf, dma), + dma_unmap_len(tx_buf, len), DMA_TO_DEVICE); xdp_return_frame_bulk(tx_buf->xdpf, bq); break; } + dma_unmap_len_set(tx_buf, len, 0); tx_buf->type = ICE_TX_BUF_EMPTY; } @@ -377,9 +380,11 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, struct ice_tx_buf *tx_buf; u32 cnt = xdp_ring->count; void *data = xdp->data; + struct page *page; u32 nr_frags = 0; u32 free_space; u32 frag = 0; + u32 offset; free_space = ICE_DESC_UNUSED(xdp_ring); if (free_space < ICE_RING_QUARTER(xdp_ring)) @@ -399,24 +404,28 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, tx_head = &xdp_ring->tx_buf[ntu]; tx_buf = tx_head; + page = virt_to_page(data); + offset = offset_in_page(xdp->data); + for (;;) { dma_addr_t dma; - dma = dma_map_single(dev, data, size, DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma)) - goto dma_unmap; - - /* record length, and DMA address */ - dma_unmap_len_set(tx_buf, len, size); - dma_unmap_addr_set(tx_buf, dma, dma); - if (frame) { + dma = dma_map_single(dev, data, size, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma)) + goto dma_unmap; tx_buf->type = ICE_TX_BUF_FRAG; } else { + dma = page_pool_get_dma_addr(page) + offset; + dma_sync_single_for_device(dev, dma, size, DMA_BIDIRECTIONAL); tx_buf->type = ICE_TX_BUF_XDP_TX; tx_buf->raw_buf = data; } + /* record length, and DMA address */ + dma_unmap_len_set(tx_buf, len, size); + dma_unmap_addr_set(tx_buf, dma, dma); + tx_desc->buf_addr = cpu_to_le64(dma); tx_desc->cmd_type_offset_bsz = ice_build_ctob(0, 0, size, 0); @@ -430,6 +439,8 @@ int __ice_xmit_xdp_ring(struct xdp_buff *xdp, struct ice_tx_ring *xdp_ring, tx_desc = ICE_TX_DESC(xdp_ring, ntu); tx_buf = &xdp_ring->tx_buf[ntu]; + page = skb_frag_page(&sinfo->frags[frag]); + offset = skb_frag_off(&sinfo->frags[frag]); data = skb_frag_address(&sinfo->frags[frag]); size = skb_frag_size(&sinfo->frags[frag]); frag++; @@ -514,10 +525,13 @@ void ice_finalize_xdp_rx(struct ice_tx_ring *xdp_ring, unsigned int xdp_res, */ static int ice_xdp_rx_hw_ts(const struct xdp_md *ctx, u64 *ts_ns) { - const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const struct libeth_xdp_buff *xdp_ext = (void *)ctx; + struct ice_rx_ring *rx_ring; - *ts_ns = ice_ptp_get_rx_hwts(xdp_ext->eop_desc, - xdp_ext->pkt_ctx); + rx_ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*rx_ring), xdp_rxq); + + *ts_ns = ice_ptp_get_rx_hwts(xdp_ext->desc, + &rx_ring->pkt_ctx); if (!*ts_ns) return -ENODATA; @@ -545,10 +559,10 @@ ice_xdp_rx_hash_type(const union ice_32b_rx_flex_desc *eop_desc) static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, enum xdp_rss_hash_type *rss_type) { - const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const struct libeth_xdp_buff *xdp_ext = (void *)ctx; - *hash = ice_get_rx_hash(xdp_ext->eop_desc); - *rss_type = ice_xdp_rx_hash_type(xdp_ext->eop_desc); + *hash = ice_get_rx_hash(xdp_ext->desc); + *rss_type = ice_xdp_rx_hash_type(xdp_ext->desc); if (!likely(*hash)) return -ENODATA; @@ -567,13 +581,16 @@ static int ice_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, static int ice_xdp_rx_vlan_tag(const struct xdp_md *ctx, __be16 *vlan_proto, u16 *vlan_tci) { - const struct ice_xdp_buff *xdp_ext = (void *)ctx; + const struct libeth_xdp_buff *xdp_ext = (void *)ctx; + struct ice_rx_ring *rx_ring; + + rx_ring = libeth_xdp_buff_to_rq(xdp_ext, typeof(*rx_ring), xdp_rxq); - *vlan_proto = xdp_ext->pkt_ctx->vlan_proto; + *vlan_proto = rx_ring->pkt_ctx.vlan_proto; if (!*vlan_proto) return -ENODATA; - *vlan_tci = ice_get_vlan_tci(xdp_ext->eop_desc); + *vlan_tci = ice_get_vlan_tci(xdp_ext->desc); if (!*vlan_tci) return -ENODATA; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h index 99717730f21a7..6a3f10f7a53f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.h @@ -135,13 +135,4 @@ ice_process_skb_fields(struct ice_rx_ring *rx_ring, void ice_receive_skb(struct ice_rx_ring *rx_ring, struct sk_buff *skb, u16 vlan_tci); -static inline void -ice_xdp_meta_set_desc(struct xdp_buff *xdp, - union ice_32b_rx_flex_desc *eop_desc) -{ - struct ice_xdp_buff *xdp_ext = container_of(xdp, struct ice_xdp_buff, - xdp_buff); - - xdp_ext->eop_desc = eop_desc; -} #endif /* !_ICE_TXRX_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index b0a1b67071c5e..6a2ec8389a8f3 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -1063,6 +1063,7 @@ struct ice_hw_port_stats { u64 error_bytes; /* errbc */ u64 mac_local_faults; /* mlfc */ u64 mac_remote_faults; /* mrfc */ + u64 rx_len_errors; /* rlec */ u64 link_xon_rx; /* lxonrxc */ u64 link_xoff_rx; /* lxoffrxc */ u64 link_xon_tx; /* lxontxc */ diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index b007089071767..7a9c75d1d07cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -53,6 +53,46 @@ struct ice_mdd_vf_events { u16 last_printed; }; +enum ice_hash_ip_ctx_type { + ICE_HASH_IP_CTX_IP = 0, + ICE_HASH_IP_CTX_IP_ESP, + ICE_HASH_IP_CTX_IP_UDP_ESP, + ICE_HASH_IP_CTX_IP_AH, + ICE_HASH_IP_CTX_IP_PFCP, + ICE_HASH_IP_CTX_IP_UDP, + ICE_HASH_IP_CTX_IP_TCP, + ICE_HASH_IP_CTX_IP_SCTP, + ICE_HASH_IP_CTX_MAX, +}; + +struct ice_vf_hash_ip_ctx { + struct ice_rss_hash_cfg ctx[ICE_HASH_IP_CTX_MAX]; +}; + +enum ice_hash_gtpu_ctx_type { + ICE_HASH_GTPU_CTX_EH_IP = 0, + ICE_HASH_GTPU_CTX_EH_IP_UDP, + ICE_HASH_GTPU_CTX_EH_IP_TCP, + ICE_HASH_GTPU_CTX_UP_IP, + ICE_HASH_GTPU_CTX_UP_IP_UDP, + ICE_HASH_GTPU_CTX_UP_IP_TCP, + ICE_HASH_GTPU_CTX_DW_IP, + ICE_HASH_GTPU_CTX_DW_IP_UDP, + ICE_HASH_GTPU_CTX_DW_IP_TCP, + ICE_HASH_GTPU_CTX_MAX, +}; + +struct ice_vf_hash_gtpu_ctx { + struct ice_rss_hash_cfg ctx[ICE_HASH_GTPU_CTX_MAX]; +}; + +struct ice_vf_hash_ctx { + struct ice_vf_hash_ip_ctx v4; + struct ice_vf_hash_ip_ctx v6; + struct ice_vf_hash_gtpu_ctx ipv4; + struct ice_vf_hash_gtpu_ctx ipv6; +}; + /* Structure to store fdir fv entry */ struct ice_fdir_prof_info { struct ice_parser_profile prof; @@ -66,6 +106,12 @@ struct ice_vf_qs_bw { u8 tc; }; +/* Structure to store RSS field vector entry */ +struct ice_rss_prof_info { + struct ice_parser_profile prof; + bool symm; +}; + /* VF operations */ struct ice_vf_ops { enum ice_disq_rst_src reset_type; @@ -106,6 +152,8 @@ struct ice_vf { u16 ctrl_vsi_idx; struct ice_vf_fdir fdir; struct ice_fdir_prof_info fdir_prof_info[ICE_MAX_PTGS]; + struct ice_rss_prof_info rss_prof_info[ICE_MAX_PTGS]; + struct ice_vf_hash_ctx hash_ctx; u64 rss_hashcfg; /* RSS hash configuration */ struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ struct virtchnl_version_info vf_ver; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 575fd48f485f1..989ff1fd91103 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -3,6 +3,7 @@ #include #include +#include #include #include #include "ice.h" @@ -169,50 +170,18 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) * If allocation was successful, substitute buffer with allocated one. * Returns 0 on success, negative on failure */ -static int +int ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present) { - size_t elem_size = pool_present ? sizeof(*rx_ring->xdp_buf) : - sizeof(*rx_ring->rx_buf); - void *sw_ring = kcalloc(rx_ring->count, elem_size, GFP_KERNEL); - - if (!sw_ring) - return -ENOMEM; - if (pool_present) { - kfree(rx_ring->rx_buf); - rx_ring->rx_buf = NULL; - rx_ring->xdp_buf = sw_ring; + rx_ring->xdp_buf = kcalloc(rx_ring->count, + sizeof(*rx_ring->xdp_buf), + GFP_KERNEL); + if (!rx_ring->xdp_buf) + return -ENOMEM; } else { kfree(rx_ring->xdp_buf); rx_ring->xdp_buf = NULL; - rx_ring->rx_buf = sw_ring; - } - - return 0; -} - -/** - * ice_realloc_zc_buf - reallocate XDP ZC queue pairs - * @vsi: Current VSI - * @zc: is zero copy set - * - * Reallocate buffer for rx_rings that might be used by XSK. - * XDP requires more memory, than rx_buf provides. - * Returns 0 on success, negative on failure - */ -int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) -{ - struct ice_rx_ring *rx_ring; - uint i; - - ice_for_each_rxq(vsi, i) { - rx_ring = vsi->rx_rings[i]; - if (!rx_ring->xsk_pool) - continue; - - if (ice_realloc_rx_xdp_bufs(rx_ring, zc)) - return -ENOMEM; } return 0; @@ -228,6 +197,7 @@ int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc) */ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) { + struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; bool if_running, pool_present = !!pool; int ret = 0, pool_failure = 0; @@ -241,8 +211,6 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) ice_is_xdp_ena_vsi(vsi); if (if_running) { - struct ice_rx_ring *rx_ring = vsi->rx_rings[qid]; - ret = ice_qp_dis(vsi, qid); if (ret) { netdev_err(vsi->netdev, "ice_qp_dis error = %d\n", ret); @@ -303,11 +271,6 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, rx_desc->read.pkt_addr = cpu_to_le64(dma); rx_desc->wb.status_error0 = 0; - /* Put private info that changes on a per-packet basis - * into xdp_buff_xsk->cb. - */ - ice_xdp_meta_set_desc(*xdp, rx_desc); - rx_desc++; xdp++; } @@ -392,69 +355,6 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover); } -/** - * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer - * @rx_ring: Rx ring - * @xdp: Pointer to XDP buffer - * - * This function allocates a new skb from a zero-copy Rx buffer. - * - * Returns the skb on success, NULL on failure. - */ -static struct sk_buff * -ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) -{ - unsigned int totalsize = xdp->data_end - xdp->data_meta; - unsigned int metasize = xdp->data - xdp->data_meta; - struct skb_shared_info *sinfo = NULL; - struct sk_buff *skb; - u32 nr_frags = 0; - - if (unlikely(xdp_buff_has_frags(xdp))) { - sinfo = xdp_get_shared_info_from_buff(xdp); - nr_frags = sinfo->nr_frags; - } - net_prefetch(xdp->data_meta); - - skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); - if (unlikely(!skb)) - return NULL; - - memcpy(__skb_put(skb, totalsize), xdp->data_meta, - ALIGN(totalsize, sizeof(long))); - - if (metasize) { - skb_metadata_set(skb, metasize); - __skb_pull(skb, metasize); - } - - if (likely(!xdp_buff_has_frags(xdp))) - goto out; - - for (int i = 0; i < nr_frags; i++) { - struct skb_shared_info *skinfo = skb_shinfo(skb); - skb_frag_t *frag = &sinfo->frags[i]; - struct page *page; - void *addr; - - page = dev_alloc_page(); - if (!page) { - dev_kfree_skb(skb); - return NULL; - } - addr = page_to_virt(page); - - memcpy(addr, skb_frag_page(frag), skb_frag_size(frag)); - - __skb_fill_page_desc_noacc(skinfo, skinfo->nr_frags++, - addr, 0, skb_frag_size(frag)); - } - -out: - xsk_buff_free(xdp); - return skb; -} - /** * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ * @xdp_ring: XDP Tx ring @@ -669,10 +569,10 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, struct xsk_buff_pool *xsk_pool, int budget) { + struct xdp_buff *first = (struct xdp_buff *)rx_ring->xsk; unsigned int total_rx_bytes = 0, total_rx_packets = 0; u32 ntc = rx_ring->next_to_clean; u32 ntu = rx_ring->next_to_use; - struct xdp_buff *first = NULL; struct ice_tx_ring *xdp_ring; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; @@ -686,9 +586,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, xdp_prog = READ_ONCE(rx_ring->xdp_prog); xdp_ring = rx_ring->xdp_ring; - if (ntc != rx_ring->first_desc) - first = *ice_xdp_buf(rx_ring, rx_ring->first_desc); - while (likely(total_rx_packets < (unsigned int)budget)) { union ice_32b_rx_flex_desc *rx_desc; unsigned int size, xdp_res = 0; @@ -724,15 +621,17 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, first = xdp; } else if (likely(size) && !xsk_buff_add_frag(first, xdp)) { xsk_buff_free(first); - break; + first = NULL; } if (++ntc == cnt) ntc = 0; - if (ice_is_non_eop(rx_ring, rx_desc)) + if (ice_is_non_eop(rx_ring, rx_desc) || unlikely(!first)) continue; + ((struct libeth_xdp_buff *)first)->desc = rx_desc; + xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring, xsk_pool); if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) { @@ -740,7 +639,6 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, } else if (xdp_res == ICE_XDP_EXIT) { failure = true; first = NULL; - rx_ring->first_desc = ntc; break; } else if (xdp_res == ICE_XDP_CONSUMED) { xsk_buff_free(first); @@ -752,24 +650,20 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, total_rx_packets++; first = NULL; - rx_ring->first_desc = ntc; continue; construct_skb: /* XDP_PASS path */ - skb = ice_construct_skb_zc(rx_ring, first); + skb = xdp_build_skb_from_zc(first); if (!skb) { + xsk_buff_free(first); + first = NULL; + rx_ring->ring_stats->rx_stats.alloc_buf_failed++; - break; + continue; } first = NULL; - rx_ring->first_desc = ntc; - - if (eth_skb_pad(skb)) { - skb = NULL; - continue; - } total_rx_bytes += skb->len; total_rx_packets++; @@ -781,7 +675,9 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, } rx_ring->next_to_clean = ntc; - entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring); + rx_ring->xsk = (struct libeth_xdp_buff *)first; + + entries_to_alloc = ICE_DESC_UNUSED(rx_ring); if (entries_to_alloc > ICE_RING_QUARTER(rx_ring)) failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, entries_to_alloc); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 600cbeeaa2030..5275fcedc9e1d 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -22,7 +22,7 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi); void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring); void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring); bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool); -int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc); +int ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present); void ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid); void ice_qvec_toggle_napi(struct ice_vsi *vsi, struct ice_q_vector *q_vector, @@ -77,8 +77,8 @@ static inline void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring) { } static inline void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring) { } static inline int -ice_realloc_zc_buf(struct ice_vsi __always_unused *vsi, - bool __always_unused zc) +ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, + bool __always_unused pool_present) { return 0; } diff --git a/drivers/net/ethernet/intel/ice/virt/queues.c b/drivers/net/ethernet/intel/ice/virt/queues.c index 370f6ec2a374c..7928f4e8e788e 100644 --- a/drivers/net/ethernet/intel/ice/virt/queues.c +++ b/drivers/net/ethernet/intel/ice/virt/queues.c @@ -842,18 +842,17 @@ int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || qpi->rxq.databuffer_size < 1024)) goto error_param; - ring->rx_buf_len = qpi->rxq.databuffer_size; if (qpi->rxq.max_pkt_size > max_frame_size || qpi->rxq.max_pkt_size < 64) goto error_param; - ring->max_frame = qpi->rxq.max_pkt_size; + vsi->max_frame = qpi->rxq.max_pkt_size; /* add space for the port VLAN since the VF driver is * not expected to account for it in the MTU * calculation */ if (ice_vf_is_port_vlan_ena(vf)) - ring->max_frame += VLAN_HLEN; + vsi->max_frame += VLAN_HLEN; if (ice_vsi_cfg_single_rxq(vsi, q_idx)) { dev_warn(ice_pf_to_dev(pf), "VF-%d failed to configure RX queue %d\n", diff --git a/drivers/net/ethernet/intel/ice/virt/rss.c b/drivers/net/ethernet/intel/ice/virt/rss.c index cbdbb32d512b2..085e69ec0cfce 100644 --- a/drivers/net/ethernet/intel/ice/virt/rss.c +++ b/drivers/net/ethernet/intel/ice/virt/rss.c @@ -36,6 +36,11 @@ static const struct ice_vc_hdr_match_type ice_vc_hdr_list[] = { {VIRTCHNL_PROTO_HDR_ESP, ICE_FLOW_SEG_HDR_ESP}, {VIRTCHNL_PROTO_HDR_AH, ICE_FLOW_SEG_HDR_AH}, {VIRTCHNL_PROTO_HDR_PFCP, ICE_FLOW_SEG_HDR_PFCP_SESSION}, + {VIRTCHNL_PROTO_HDR_GTPC, ICE_FLOW_SEG_HDR_GTPC}, + {VIRTCHNL_PROTO_HDR_L2TPV2, ICE_FLOW_SEG_HDR_L2TPV2}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, ICE_FLOW_SEG_HDR_IPV_FRAG}, + {VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG, ICE_FLOW_SEG_HDR_IPV_FRAG}, + {VIRTCHNL_PROTO_HDR_GRE, ICE_FLOW_SEG_HDR_GRE}, }; struct ice_vc_hash_field_match_type { @@ -87,8 +92,125 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, - {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + {VIRTCHNL_PROTO_HDR_IPV4, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_ID)}, + {VIRTCHNL_PROTO_HDR_IPV4, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST), + ICE_FLOW_HASH_IPV4}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_ID)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + ICE_FLOW_HASH_IPV4 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_IPV4_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_PROT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV4_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_PROT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_CHKSUM)}, {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_SRC), BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_SA)}, {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_DST), @@ -110,6 +232,35 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { ICE_FLOW_HASH_IPV6 | BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, {VIRTCHNL_PROTO_HDR_IPV6, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_ID)}, + {VIRTCHNL_PROTO_HDR_IPV6, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST), + ICE_FLOW_HASH_IPV6_PRE64}, + {VIRTCHNL_PROTO_HDR_IPV6, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA)}, + {VIRTCHNL_PROTO_HDR_IPV6, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA)}, + {VIRTCHNL_PROTO_HDR_IPV6, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + ICE_FLOW_HASH_IPV6_PRE64 | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_SA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, + {VIRTCHNL_PROTO_HDR_IPV6, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_IPV6_PROT), + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PRE64_DA) | + BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_PROT)}, {VIRTCHNL_PROTO_HDR_TCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT), BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT)}, @@ -120,6 +271,25 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT), ICE_FLOW_HASH_TCP_PORT}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_SRC_PORT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_DST_PORT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_TCP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_DST_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_TCP_CHKSUM), + ICE_FLOW_HASH_TCP_PORT | + BIT_ULL(ICE_FLOW_FIELD_IDX_TCP_CHKSUM)}, {VIRTCHNL_PROTO_HDR_UDP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT), BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT)}, @@ -130,6 +300,25 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT), ICE_FLOW_HASH_UDP_PORT}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_SRC_PORT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_DST_PORT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_UDP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_DST_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_UDP_CHKSUM), + ICE_FLOW_HASH_UDP_PORT | + BIT_ULL(ICE_FLOW_FIELD_IDX_UDP_CHKSUM)}, {VIRTCHNL_PROTO_HDR_SCTP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT), BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT)}, @@ -140,6 +329,25 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT), ICE_FLOW_HASH_SCTP_PORT}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_SRC_PORT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM), + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_DST_PORT) | + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)}, + {VIRTCHNL_PROTO_HDR_SCTP, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_DST_PORT) | + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_SCTP_CHKSUM), + ICE_FLOW_HASH_SCTP_PORT | + BIT_ULL(ICE_FLOW_FIELD_IDX_SCTP_CHKSUM)}, {VIRTCHNL_PROTO_HDR_PPPOE, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PPPOE_SESS_ID), BIT_ULL(ICE_FLOW_FIELD_IDX_PPPOE_SESS_ID)}, @@ -155,8 +363,54 @@ ice_vc_hash_field_match_type ice_vc_hash_field_list[] = { BIT_ULL(ICE_FLOW_FIELD_IDX_AH_SPI)}, {VIRTCHNL_PROTO_HDR_PFCP, FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_PFCP_SEID), BIT_ULL(ICE_FLOW_FIELD_IDX_PFCP_SEID)}, + {VIRTCHNL_PROTO_HDR_GTPC, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_GTPC_TEID), + BIT_ULL(ICE_FLOW_FIELD_IDX_GTPC_TEID)}, + {VIRTCHNL_PROTO_HDR_L2TPV2, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV2_SESS_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_SESS_ID)}, + {VIRTCHNL_PROTO_HDR_L2TPV2, + FIELD_SELECTOR(VIRTCHNL_PROTO_HDR_L2TPV2_LEN_SESS_ID), + BIT_ULL(ICE_FLOW_FIELD_IDX_L2TPV2_LEN_SESS_ID)}, }; +static int +ice_vc_rss_hash_update(struct ice_hw *hw, struct ice_vsi *vsi, u8 hash_type) +{ + struct ice_vsi_ctx *ctx; + int ret; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + /* clear previous hash_type */ + ctx->info.q_opt_rss = vsi->info.q_opt_rss & + ~ICE_AQ_VSI_Q_OPT_RSS_HASH_M; + /* hash_type is passed in as ICE_AQ_VSI_Q_OPT_RSS_info.q_opt_rss |= FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, + hash_type); + + /* Preserve existing queueing option setting */ + ctx->info.q_opt_tc = vsi->info.q_opt_tc; + ctx->info.q_opt_flags = vsi->info.q_opt_flags; + + ctx->info.valid_sections = + cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); + + ret = ice_update_vsi(hw, vsi->idx, ctx, NULL); + if (ret) { + dev_err(ice_hw_to_dev(hw), "update VSI for RSS failed, err %d aq_err %s\n", + ret, libie_aq_str(hw->adminq.sq_last_status)); + } else { + vsi->info.q_opt_rss = ctx->info.q_opt_rss; + } + + kfree(ctx); + + return ret; +} + /** * ice_vc_validate_pattern * @vf: pointer to the VF info @@ -271,6 +525,11 @@ static bool ice_vc_parse_rss_cfg(struct ice_hw *hw, const struct ice_vc_hash_field_match_type *hf_list; const struct ice_vc_hdr_match_type *hdr_list; int i, hf_list_len, hdr_list_len; + bool outer_ipv4 = false; + bool outer_ipv6 = false; + bool inner_hdr = false; + bool has_gre = false; + u32 *addl_hdrs = &hash_cfg->addl_hdrs; u64 *hash_flds = &hash_cfg->hash_flds; @@ -290,17 +549,17 @@ static bool ice_vc_parse_rss_cfg(struct ice_hw *hw, for (i = 0; i < rss_cfg->proto_hdrs.count; i++) { struct virtchnl_proto_hdr *proto_hdr = &rss_cfg->proto_hdrs.proto_hdr[i]; - bool hdr_found = false; + u32 hdr_found = 0; int j; - /* Find matched ice headers according to virtchnl headers. */ + /* Find matched ice headers according to virtchnl headers. + * Also figure out the outer type of GTPU headers. + */ for (j = 0; j < hdr_list_len; j++) { struct ice_vc_hdr_match_type hdr_map = hdr_list[j]; - if (proto_hdr->type == hdr_map.vc_hdr) { - *addl_hdrs |= hdr_map.ice_hdr; - hdr_found = true; - } + if (proto_hdr->type == hdr_map.vc_hdr) + hdr_found = hdr_map.ice_hdr; } if (!hdr_found) @@ -318,8 +577,98 @@ static bool ice_vc_parse_rss_cfg(struct ice_hw *hw, break; } } + + if (proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV4 && !inner_hdr) + outer_ipv4 = true; + else if (proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV6 && + !inner_hdr) + outer_ipv6 = true; + /* for GRE and L2TPv2, take inner header as input set if no + * any field is selected from outer headers. + * for GTPU, take inner header and GTPU teid as input set. + */ + else if ((proto_hdr->type == VIRTCHNL_PROTO_HDR_GTPU_IP || + proto_hdr->type == VIRTCHNL_PROTO_HDR_GTPU_EH || + proto_hdr->type == VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN || + proto_hdr->type == + VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP) || + ((proto_hdr->type == VIRTCHNL_PROTO_HDR_L2TPV2 || + proto_hdr->type == VIRTCHNL_PROTO_HDR_GRE) && + *hash_flds == 0)) { + /* set inner_hdr flag, and clean up outer header */ + inner_hdr = true; + + /* clear outer headers */ + *addl_hdrs = 0; + + if (outer_ipv4 && outer_ipv6) + return false; + + if (outer_ipv4) + hash_cfg->hdr_type = ICE_RSS_INNER_HEADERS_W_OUTER_IPV4; + else if (outer_ipv6) + hash_cfg->hdr_type = ICE_RSS_INNER_HEADERS_W_OUTER_IPV6; + else + hash_cfg->hdr_type = ICE_RSS_INNER_HEADERS; + + if (has_gre && outer_ipv4) + hash_cfg->hdr_type = + ICE_RSS_INNER_HEADERS_W_OUTER_IPV4_GRE; + if (has_gre && outer_ipv6) + hash_cfg->hdr_type = + ICE_RSS_INNER_HEADERS_W_OUTER_IPV6_GRE; + + if (proto_hdr->type == VIRTCHNL_PROTO_HDR_GRE) + has_gre = true; + } + + *addl_hdrs |= hdr_found; + + /* refine hash hdrs and fields for IP fragment */ + if (VIRTCHNL_TEST_PROTO_HDR_FIELD(proto_hdr, + VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID) && + proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV4_FRAG) { + *addl_hdrs |= ICE_FLOW_SEG_HDR_IPV_FRAG; + *addl_hdrs &= ~(ICE_FLOW_SEG_HDR_IPV_OTHER); + *hash_flds |= BIT_ULL(ICE_FLOW_FIELD_IDX_IPV4_ID); + VIRTCHNL_DEL_PROTO_HDR_FIELD(proto_hdr, + VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID); + } + if (VIRTCHNL_TEST_PROTO_HDR_FIELD(proto_hdr, + VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID) && + proto_hdr->type == VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG) { + *addl_hdrs |= ICE_FLOW_SEG_HDR_IPV_FRAG; + *addl_hdrs &= ~(ICE_FLOW_SEG_HDR_IPV_OTHER); + *hash_flds |= BIT_ULL(ICE_FLOW_FIELD_IDX_IPV6_ID); + VIRTCHNL_DEL_PROTO_HDR_FIELD(proto_hdr, + VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID); + } + } + + /* refine gtpu header if we take outer as input set for a no inner + * ip gtpu flow. + */ + if (hash_cfg->hdr_type == ICE_RSS_OUTER_HEADERS && + *addl_hdrs & ICE_FLOW_SEG_HDR_GTPU_IP) { + *addl_hdrs &= ~(ICE_FLOW_SEG_HDR_GTPU_IP); + *addl_hdrs |= ICE_FLOW_SEG_HDR_GTPU_NON_IP; } + /* refine hash field for esp and nat-t-esp. */ + if ((*addl_hdrs & ICE_FLOW_SEG_HDR_UDP) && + (*addl_hdrs & ICE_FLOW_SEG_HDR_ESP)) { + *addl_hdrs &= ~(ICE_FLOW_SEG_HDR_ESP | ICE_FLOW_SEG_HDR_UDP); + *addl_hdrs |= ICE_FLOW_SEG_HDR_NAT_T_ESP; + *hash_flds &= ~(BIT_ULL(ICE_FLOW_FIELD_IDX_ESP_SPI)); + *hash_flds |= BIT_ULL(ICE_FLOW_FIELD_IDX_NAT_T_ESP_SPI); + } + + /* refine hash hdrs for L4 udp/tcp/sctp. */ + if (*addl_hdrs & (ICE_FLOW_SEG_HDR_TCP | ICE_FLOW_SEG_HDR_UDP | + ICE_FLOW_SEG_HDR_SCTP) && + *addl_hdrs & ICE_FLOW_SEG_HDR_IPV_OTHER) + *addl_hdrs &= ~ICE_FLOW_SEG_HDR_IPV_OTHER; + return true; } @@ -336,6 +685,874 @@ static bool ice_vf_adv_rss_offload_ena(u32 caps) return !!(caps & VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF); } +/** + * ice_is_hash_cfg_valid - Check whether an RSS hash context is valid + * @cfg: RSS hash configuration to test + * + * Return: true if both @cfg->hash_flds and @cfg->addl_hdrs are non-zero; false otherwise. + */ +static bool ice_is_hash_cfg_valid(struct ice_rss_hash_cfg *cfg) +{ + return cfg->hash_flds && cfg->addl_hdrs; +} + +/** + * ice_hash_cfg_reset - Reset an RSS hash context + * @cfg: RSS hash configuration to reset + * + * Reset fields of @cfg that store the active rule information. + */ +static void ice_hash_cfg_reset(struct ice_rss_hash_cfg *cfg) +{ + cfg->hash_flds = 0; + cfg->addl_hdrs = 0; + cfg->hdr_type = ICE_RSS_OUTER_HEADERS; + cfg->symm = 0; +} + +/** + * ice_hash_cfg_record - Record an RSS hash context + * @ctx: destination (global) RSS hash configuration + * @cfg: source RSS hash configuration to record + * + * Copy the active rule information from @cfg into @ctx. + */ +static void ice_hash_cfg_record(struct ice_rss_hash_cfg *ctx, + struct ice_rss_hash_cfg *cfg) +{ + ctx->hash_flds = cfg->hash_flds; + ctx->addl_hdrs = cfg->addl_hdrs; + ctx->hdr_type = cfg->hdr_type; + ctx->symm = cfg->symm; +} + +/** + * ice_hash_moveout - Delete an RSS configuration (keep context) + * @vf: VF pointer + * @cfg: RSS hash configuration + * + * Return: 0 on success (including when already absent); -ENOENT if @cfg is + * invalid or VSI is missing; -EBUSY on hardware removal failure. + */ +static int +ice_hash_moveout(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_hw *hw = &vf->pf->hw; + int ret; + + if (!ice_is_hash_cfg_valid(cfg) || !vsi) + return -ENOENT; + + ret = ice_rem_rss_cfg(hw, vsi->idx, cfg); + if (ret && ret != -ENOENT) { + dev_err(dev, "ice_rem_rss_cfg failed for VF %d, VSI %d, error:%d\n", + vf->vf_id, vf->lan_vsi_idx, ret); + return -EBUSY; + } + + return 0; +} + +/** + * ice_hash_moveback - Add an RSS hash configuration for a VF + * @vf: VF pointer + * @cfg: RSS hash configuration to apply + * + * Add @cfg to @vf if the context is valid and VSI exists; programs HW. + * + * Return: + * * 0 on success + * * -ENOENT if @cfg is invalid or VSI is missing + * * -EBUSY if hardware programming fails + */ +static int +ice_hash_moveback(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_hw *hw = &vf->pf->hw; + int ret; + + if (!ice_is_hash_cfg_valid(cfg) || !vsi) + return -ENOENT; + + ret = ice_add_rss_cfg(hw, vsi, cfg); + if (ret) { + dev_err(dev, "ice_add_rss_cfg failed for VF %d, VSI %d, error:%d\n", + vf->vf_id, vf->lan_vsi_idx, ret); + return -EBUSY; + } + + return 0; +} + +/** + * ice_hash_remove - remove a RSS configuration + * @vf: pointer to the VF info + * @cfg: pointer to the RSS hash configuration + * + * This function will delete a RSS hash configuration and also delete the + * hash context which stores the rule info. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int +ice_hash_remove(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + int ret; + + ret = ice_hash_moveout(vf, cfg); + if (ret && ret != -ENOENT) + return ret; + + ice_hash_cfg_reset(cfg); + + return 0; +} + +struct ice_gtpu_ctx_action { + u32 ctx_idx; + const u32 *remove_list; + int remove_count; + const u32 *moveout_list; + int moveout_count; +}; + +/** + * ice_add_rss_cfg_pre_gtpu - Pre-process the GTPU RSS configuration + * @vf: pointer to the VF info + * @ctx: pointer to the context of the GTPU hash + * @ctx_idx: index of the hash context + * + * Pre-processes the GTPU hash configuration before adding a new + * hash context. It removes or reorders existing hash configurations that may + * conflict with the new one. For example, if a GTPU_UP or GTPU_DWN rule is + * configured after a GTPU_EH rule, the GTPU_EH hash will be matched first due + * to TCAM write and match order (top-down). In such cases, the GTPU_EH rule + * must be moved after the GTPU_UP/DWN rule. Conversely, if a GTPU_EH rule is + * configured after a GTPU_UP/DWN rule, the UP/DWN rules should be removed to + * avoid conflict. + * + * Return: 0 on success or a negative error code on failure + */ +static int ice_add_rss_cfg_pre_gtpu(struct ice_vf *vf, + struct ice_vf_hash_gtpu_ctx *ctx, + u32 ctx_idx) +{ + int ret, i; + + static const u32 remove_eh_ip[] = { + ICE_HASH_GTPU_CTX_EH_IP_UDP, ICE_HASH_GTPU_CTX_EH_IP_TCP, + ICE_HASH_GTPU_CTX_UP_IP, ICE_HASH_GTPU_CTX_UP_IP_UDP, + ICE_HASH_GTPU_CTX_UP_IP_TCP, ICE_HASH_GTPU_CTX_DW_IP, + ICE_HASH_GTPU_CTX_DW_IP_UDP, ICE_HASH_GTPU_CTX_DW_IP_TCP, + }; + + static const u32 remove_eh_ip_udp[] = { + ICE_HASH_GTPU_CTX_UP_IP_UDP, + ICE_HASH_GTPU_CTX_DW_IP_UDP, + }; + static const u32 moveout_eh_ip_udp[] = { + ICE_HASH_GTPU_CTX_UP_IP, + ICE_HASH_GTPU_CTX_UP_IP_TCP, + ICE_HASH_GTPU_CTX_DW_IP, + ICE_HASH_GTPU_CTX_DW_IP_TCP, + }; + + static const u32 remove_eh_ip_tcp[] = { + ICE_HASH_GTPU_CTX_UP_IP_TCP, + ICE_HASH_GTPU_CTX_DW_IP_TCP, + }; + static const u32 moveout_eh_ip_tcp[] = { + ICE_HASH_GTPU_CTX_UP_IP, + ICE_HASH_GTPU_CTX_UP_IP_UDP, + ICE_HASH_GTPU_CTX_DW_IP, + ICE_HASH_GTPU_CTX_DW_IP_UDP, + }; + + static const u32 remove_up_ip[] = { + ICE_HASH_GTPU_CTX_UP_IP_UDP, + ICE_HASH_GTPU_CTX_UP_IP_TCP, + }; + static const u32 moveout_up_ip[] = { + ICE_HASH_GTPU_CTX_EH_IP, + ICE_HASH_GTPU_CTX_EH_IP_UDP, + ICE_HASH_GTPU_CTX_EH_IP_TCP, + }; + + static const u32 moveout_up_ip_udp_tcp[] = { + ICE_HASH_GTPU_CTX_EH_IP, + ICE_HASH_GTPU_CTX_EH_IP_UDP, + ICE_HASH_GTPU_CTX_EH_IP_TCP, + }; + + static const u32 remove_dw_ip[] = { + ICE_HASH_GTPU_CTX_DW_IP_UDP, + ICE_HASH_GTPU_CTX_DW_IP_TCP, + }; + static const u32 moveout_dw_ip[] = { + ICE_HASH_GTPU_CTX_EH_IP, + ICE_HASH_GTPU_CTX_EH_IP_UDP, + ICE_HASH_GTPU_CTX_EH_IP_TCP, + }; + + static const struct ice_gtpu_ctx_action actions[] = { + { ICE_HASH_GTPU_CTX_EH_IP, remove_eh_ip, + ARRAY_SIZE(remove_eh_ip), NULL, 0 }, + { ICE_HASH_GTPU_CTX_EH_IP_UDP, remove_eh_ip_udp, + ARRAY_SIZE(remove_eh_ip_udp), moveout_eh_ip_udp, + ARRAY_SIZE(moveout_eh_ip_udp) }, + { ICE_HASH_GTPU_CTX_EH_IP_TCP, remove_eh_ip_tcp, + ARRAY_SIZE(remove_eh_ip_tcp), moveout_eh_ip_tcp, + ARRAY_SIZE(moveout_eh_ip_tcp) }, + { ICE_HASH_GTPU_CTX_UP_IP, remove_up_ip, + ARRAY_SIZE(remove_up_ip), moveout_up_ip, + ARRAY_SIZE(moveout_up_ip) }, + { ICE_HASH_GTPU_CTX_UP_IP_UDP, NULL, 0, moveout_up_ip_udp_tcp, + ARRAY_SIZE(moveout_up_ip_udp_tcp) }, + { ICE_HASH_GTPU_CTX_UP_IP_TCP, NULL, 0, moveout_up_ip_udp_tcp, + ARRAY_SIZE(moveout_up_ip_udp_tcp) }, + { ICE_HASH_GTPU_CTX_DW_IP, remove_dw_ip, + ARRAY_SIZE(remove_dw_ip), moveout_dw_ip, + ARRAY_SIZE(moveout_dw_ip) }, + { ICE_HASH_GTPU_CTX_DW_IP_UDP, NULL, 0, moveout_dw_ip, + ARRAY_SIZE(moveout_dw_ip) }, + { ICE_HASH_GTPU_CTX_DW_IP_TCP, NULL, 0, moveout_dw_ip, + ARRAY_SIZE(moveout_dw_ip) }, + }; + + for (i = 0; i < ARRAY_SIZE(actions); i++) { + if (actions[i].ctx_idx != ctx_idx) + continue; + + if (actions[i].remove_list) { + for (int j = 0; j < actions[i].remove_count; j++) { + u16 rm = actions[i].remove_list[j]; + + ret = ice_hash_remove(vf, &ctx->ctx[rm]); + if (ret && ret != -ENOENT) + return ret; + } + } + + if (actions[i].moveout_list) { + for (int j = 0; j < actions[i].moveout_count; j++) { + u16 mv = actions[i].moveout_list[j]; + + ret = ice_hash_moveout(vf, &ctx->ctx[mv]); + if (ret && ret != -ENOENT) + return ret; + } + } + break; + } + + return 0; +} + +/** + * ice_add_rss_cfg_pre_ip - Pre-process IP-layer RSS configuration + * @vf: VF pointer + * @ctx: IP L4 hash context (ESP/UDP-ESP/AH/PFCP and UDP/TCP/SCTP) + * + * Remove covered/recorded IP RSS configurations prior to adding a new one. + * + * Return: 0 on success; negative error code on failure. + */ +static int +ice_add_rss_cfg_pre_ip(struct ice_vf *vf, struct ice_vf_hash_ip_ctx *ctx) +{ + int i, ret; + + for (i = 1; i < ICE_HASH_IP_CTX_MAX; i++) + if (ice_is_hash_cfg_valid(&ctx->ctx[i])) { + ret = ice_hash_remove(vf, &ctx->ctx[i]); + if (ret) + return ret; + } + + return 0; +} + +/** + * ice_calc_gtpu_ctx_idx - Calculate GTPU hash context index + * @hdrs: Bitmask of protocol headers prefixed with ICE_FLOW_SEG_HDR_* + * + * Determine the GTPU hash context index based on the combination of + * encapsulation headers (GTPU_EH, GTPU_UP, GTPU_DWN) and transport + * protocols (UDP, TCP) within IPv4 or IPv6 flows. + * + * Return: A valid context index (0-8) if the header combination is supported, + * or ICE_HASH_GTPU_CTX_MAX if the combination is invalid. + */ +static enum ice_hash_gtpu_ctx_type ice_calc_gtpu_ctx_idx(u32 hdrs) +{ + u32 eh_idx, ip_idx; + + if (hdrs & ICE_FLOW_SEG_HDR_GTPU_EH) + eh_idx = 0; + else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_UP) + eh_idx = 1; + else if (hdrs & ICE_FLOW_SEG_HDR_GTPU_DWN) + eh_idx = 2; + else + return ICE_HASH_GTPU_CTX_MAX; + + ip_idx = 0; + if (hdrs & ICE_FLOW_SEG_HDR_UDP) + ip_idx = 1; + else if (hdrs & ICE_FLOW_SEG_HDR_TCP) + ip_idx = 2; + + if (hdrs & (ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV6)) + return eh_idx * 3 + ip_idx; + else + return ICE_HASH_GTPU_CTX_MAX; +} + +/** + * ice_map_ip_ctx_idx - map the index of the IP L4 hash context + * @hdrs: protocol headers prefix with ICE_FLOW_SEG_HDR_XXX. + * + * The IP L4 hash context use the index to classify for IPv4/IPv6 with + * ESP/UDP_ESP/AH/PFCP and non-tunnel UDP/TCP/SCTP + * this function map the index based on the protocol headers. + * + * Return: The mapped IP context index on success, or ICE_HASH_IP_CTX_MAX + * if no matching context is found. + */ +static u8 ice_map_ip_ctx_idx(u32 hdrs) +{ + u8 i; + + static struct { + u32 hdrs; + u8 ctx_idx; + } ip_ctx_idx_map[] = { + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_ESP, + ICE_HASH_IP_CTX_IP_ESP }, + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_NAT_T_ESP, + ICE_HASH_IP_CTX_IP_UDP_ESP }, + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_AH, + ICE_HASH_IP_CTX_IP_AH }, + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_PFCP_SESSION, + ICE_HASH_IP_CTX_IP_PFCP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_UDP, + ICE_HASH_IP_CTX_IP_UDP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_TCP, + ICE_HASH_IP_CTX_IP_TCP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_SCTP, + ICE_HASH_IP_CTX_IP_SCTP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER, + ICE_HASH_IP_CTX_IP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_ESP, + ICE_HASH_IP_CTX_IP_ESP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_NAT_T_ESP, + ICE_HASH_IP_CTX_IP_UDP_ESP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_AH, + ICE_HASH_IP_CTX_IP_AH }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER | + ICE_FLOW_SEG_HDR_PFCP_SESSION, + ICE_HASH_IP_CTX_IP_PFCP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_UDP, + ICE_HASH_IP_CTX_IP_UDP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_TCP, + ICE_HASH_IP_CTX_IP_TCP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_SCTP, + ICE_HASH_IP_CTX_IP_SCTP }, + { ICE_FLOW_SEG_HDR_ETH | ICE_FLOW_SEG_HDR_VLAN | + ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER, + ICE_HASH_IP_CTX_IP }, + /* the remaining mappings are used for default RSS */ + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_UDP, + ICE_HASH_IP_CTX_IP_UDP }, + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_TCP, + ICE_HASH_IP_CTX_IP_TCP }, + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_SCTP, + ICE_HASH_IP_CTX_IP_SCTP }, + { ICE_FLOW_SEG_HDR_IPV4 | ICE_FLOW_SEG_HDR_IPV_OTHER, + ICE_HASH_IP_CTX_IP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_UDP, + ICE_HASH_IP_CTX_IP_UDP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_TCP, + ICE_HASH_IP_CTX_IP_TCP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_SCTP, + ICE_HASH_IP_CTX_IP_SCTP }, + { ICE_FLOW_SEG_HDR_IPV6 | ICE_FLOW_SEG_HDR_IPV_OTHER, + ICE_HASH_IP_CTX_IP }, + }; + + for (i = 0; i < ARRAY_SIZE(ip_ctx_idx_map); i++) { + if (hdrs == ip_ctx_idx_map[i].hdrs) + return ip_ctx_idx_map[i].ctx_idx; + } + + return ICE_HASH_IP_CTX_MAX; +} + +/** + * ice_add_rss_cfg_pre - Prepare RSS configuration context for a VF + * @vf: pointer to the VF structure + * @cfg: pointer to the RSS hash configuration + * + * Prepare the RSS hash context for a given VF based on the additional + * protocol headers specified in @cfg. This includes pre-configuration + * for IP and GTPU-based flows. + * + * If the configuration matches a known IP context, the function sets up + * the appropriate IP hash context. If the configuration includes GTPU + * headers, it prepares the GTPU-specific context accordingly. + * + * Return: 0 on success, or a negative error code on failure. + */ +static int +ice_add_rss_cfg_pre(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + u32 ice_gtpu_ctx_idx = ice_calc_gtpu_ctx_idx(cfg->addl_hdrs); + u8 ip_ctx_idx = ice_map_ip_ctx_idx(cfg->addl_hdrs); + + if (ip_ctx_idx == ICE_HASH_IP_CTX_IP) { + int ret = 0; + + if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) + ret = ice_add_rss_cfg_pre_ip(vf, &vf->hash_ctx.v4); + else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) + ret = ice_add_rss_cfg_pre_ip(vf, &vf->hash_ctx.v6); + + if (ret) + return ret; + } + + if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) { + return ice_add_rss_cfg_pre_gtpu(vf, &vf->hash_ctx.ipv4, + ice_gtpu_ctx_idx); + } else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) { + return ice_add_rss_cfg_pre_gtpu(vf, &vf->hash_ctx.ipv6, + ice_gtpu_ctx_idx); + } + + return 0; +} + +/** + * ice_add_rss_cfg_post_gtpu - Post-process GTPU RSS configuration + * @vf: pointer to the VF info + * @ctx: pointer to the context of the GTPU hash + * @cfg: pointer to the RSS hash configuration + * @ctx_idx: index of the hash context + * + * Post-processes the GTPU hash configuration after a new hash + * context has been successfully added. It updates the context with the new + * configuration and restores any previously removed hash contexts that need + * to be re-applied. This ensures proper TCAM rule ordering and avoids + * conflicts between overlapping GTPU rules. + * + * Return: 0 on success or a negative error code on failure + */ +static int ice_add_rss_cfg_post_gtpu(struct ice_vf *vf, + struct ice_vf_hash_gtpu_ctx *ctx, + struct ice_rss_hash_cfg *cfg, u32 ctx_idx) +{ + /* GTPU hash moveback lookup table indexed by context ID. + * Each entry is a bitmap indicating which contexts need moveback + * operations when the corresponding context index is processed. + */ + static const unsigned long + ice_gtpu_moveback_tbl[ICE_HASH_GTPU_CTX_MAX] = { + [ICE_HASH_GTPU_CTX_EH_IP] = 0, + [ICE_HASH_GTPU_CTX_EH_IP_UDP] = + BIT(ICE_HASH_GTPU_CTX_UP_IP) | + BIT(ICE_HASH_GTPU_CTX_UP_IP_TCP) | + BIT(ICE_HASH_GTPU_CTX_DW_IP) | + BIT(ICE_HASH_GTPU_CTX_DW_IP_TCP), + [ICE_HASH_GTPU_CTX_EH_IP_TCP] = + BIT(ICE_HASH_GTPU_CTX_UP_IP) | + BIT(ICE_HASH_GTPU_CTX_UP_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_DW_IP) | + BIT(ICE_HASH_GTPU_CTX_DW_IP_UDP), + [ICE_HASH_GTPU_CTX_UP_IP] = + BIT(ICE_HASH_GTPU_CTX_EH_IP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP), + [ICE_HASH_GTPU_CTX_UP_IP_UDP] = + BIT(ICE_HASH_GTPU_CTX_EH_IP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP), + [ICE_HASH_GTPU_CTX_UP_IP_TCP] = + BIT(ICE_HASH_GTPU_CTX_EH_IP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP), + [ICE_HASH_GTPU_CTX_DW_IP] = + BIT(ICE_HASH_GTPU_CTX_EH_IP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP), + [ICE_HASH_GTPU_CTX_DW_IP_UDP] = + BIT(ICE_HASH_GTPU_CTX_EH_IP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP), + [ICE_HASH_GTPU_CTX_DW_IP_TCP] = + BIT(ICE_HASH_GTPU_CTX_EH_IP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_UDP) | + BIT(ICE_HASH_GTPU_CTX_EH_IP_TCP), + }; + unsigned long moveback_mask; + int ret; + int i; + + if (unlikely(ctx_idx >= ICE_HASH_GTPU_CTX_MAX)) + return 0; + + ctx->ctx[ctx_idx].addl_hdrs = cfg->addl_hdrs; + ctx->ctx[ctx_idx].hash_flds = cfg->hash_flds; + ctx->ctx[ctx_idx].hdr_type = cfg->hdr_type; + ctx->ctx[ctx_idx].symm = cfg->symm; + + moveback_mask = ice_gtpu_moveback_tbl[ctx_idx]; + for_each_set_bit(i, &moveback_mask, ICE_HASH_GTPU_CTX_MAX) { + ret = ice_hash_moveback(vf, &ctx->ctx[i]); + if (ret && ret != -ENOENT) + return ret; + } + + return 0; +} + +static int +ice_add_rss_cfg_post(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + u32 ice_gtpu_ctx_idx = ice_calc_gtpu_ctx_idx(cfg->addl_hdrs); + u8 ip_ctx_idx = ice_map_ip_ctx_idx(cfg->addl_hdrs); + + if (ip_ctx_idx && ip_ctx_idx < ICE_HASH_IP_CTX_MAX) { + if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) + ice_hash_cfg_record(&vf->hash_ctx.v4.ctx[ip_ctx_idx], cfg); + else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) + ice_hash_cfg_record(&vf->hash_ctx.v6.ctx[ip_ctx_idx], cfg); + } + + if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) { + return ice_add_rss_cfg_post_gtpu(vf, &vf->hash_ctx.ipv4, + cfg, ice_gtpu_ctx_idx); + } else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) { + return ice_add_rss_cfg_post_gtpu(vf, &vf->hash_ctx.ipv6, + cfg, ice_gtpu_ctx_idx); + } + + return 0; +} + +/** + * ice_rem_rss_cfg_post - post-process the RSS configuration + * @vf: pointer to the VF info + * @cfg: pointer to the RSS hash configuration + * + * Post process the RSS hash configuration after deleting a hash + * config. Such as, it will reset the hash context for the GTPU hash. + */ +static void +ice_rem_rss_cfg_post(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + u32 ice_gtpu_ctx_idx = ice_calc_gtpu_ctx_idx(cfg->addl_hdrs); + u8 ip_ctx_idx = ice_map_ip_ctx_idx(cfg->addl_hdrs); + + if (ip_ctx_idx && ip_ctx_idx < ICE_HASH_IP_CTX_MAX) { + if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) + ice_hash_cfg_reset(&vf->hash_ctx.v4.ctx[ip_ctx_idx]); + else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) + ice_hash_cfg_reset(&vf->hash_ctx.v6.ctx[ip_ctx_idx]); + } + + if (ice_gtpu_ctx_idx >= ICE_HASH_GTPU_CTX_MAX) + return; + + if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV4) + ice_hash_cfg_reset(&vf->hash_ctx.ipv4.ctx[ice_gtpu_ctx_idx]); + else if (cfg->addl_hdrs & ICE_FLOW_SEG_HDR_IPV6) + ice_hash_cfg_reset(&vf->hash_ctx.ipv6.ctx[ice_gtpu_ctx_idx]); +} + +/** + * ice_rem_rss_cfg_wrap - Wrapper for deleting an RSS configuration + * @vf: pointer to the VF info + * @cfg: pointer to the RSS hash configuration + * + * Wrapper function to delete a flow profile base on an RSS configuration, + * and also post process the hash context base on the rollback mechanism + * which handle some rules conflict by ice_add_rss_cfg_wrap. + * + * Return: 0 on success; negative error code on failure. + */ +static int +ice_rem_rss_cfg_wrap(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_hw *hw = &vf->pf->hw; + int ret; + + ret = ice_rem_rss_cfg(hw, vsi->idx, cfg); + /* We just ignore -ENOENT, because if two configurations share the same + * profile remove one of them actually removes both, since the + * profile is deleted. + */ + if (ret && ret != -ENOENT) { + dev_err(dev, "ice_rem_rss_cfg failed for VF %d, VSI %d, error:%d\n", + vf->vf_id, vf->lan_vsi_idx, ret); + return ret; + } + + ice_rem_rss_cfg_post(vf, cfg); + + return 0; +} + +/** + * ice_add_rss_cfg_wrap - Wrapper for adding an RSS configuration + * @vf: pointer to the VF info + * @cfg: pointer to the RSS hash configuration + * + * Add a flow profile based on an RSS configuration. Use a rollback + * mechanism to handle rule conflicts due to TCAM + * write sequence from top to down. + * + * Return: 0 on success; negative error code on failure. + */ +static int +ice_add_rss_cfg_wrap(struct ice_vf *vf, struct ice_rss_hash_cfg *cfg) +{ + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_vsi *vsi = ice_get_vf_vsi(vf); + struct ice_hw *hw = &vf->pf->hw; + int ret; + + if (ice_add_rss_cfg_pre(vf, cfg)) + return -EINVAL; + + ret = ice_add_rss_cfg(hw, vsi, cfg); + if (ret) { + dev_err(dev, "ice_add_rss_cfg failed for VF %d, VSI %d, error:%d\n", + vf->vf_id, vf->lan_vsi_idx, ret); + return ret; + } + + if (ice_add_rss_cfg_post(vf, cfg)) + ret = -EINVAL; + + return ret; +} + +/** + * ice_parse_raw_rss_pattern - Parse raw pattern spec and mask for RSS + * @vf: pointer to the VF info + * @proto: pointer to the virtchnl protocol header + * @raw_cfg: pointer to the RSS raw pattern configuration + * + * Parser function to get spec and mask from virtchnl message, and parse + * them to get the corresponding profile and offset. The profile is used + * to add RSS configuration. + * + * Return: 0 on success; negative error code on failure. + */ +static int +ice_parse_raw_rss_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto, + struct ice_rss_raw_cfg *raw_cfg) +{ + struct ice_parser_result pkt_parsed; + struct ice_hw *hw = &vf->pf->hw; + struct ice_parser_profile prof; + struct ice_parser *psr; + u8 *pkt_buf, *msk_buf; + u16 pkt_len; + int ret = 0; + + pkt_len = proto->raw.pkt_len; + if (!pkt_len) + return -EINVAL; + if (pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET) + pkt_len = VIRTCHNL_MAX_SIZE_RAW_PACKET; + + pkt_buf = kzalloc(pkt_len, GFP_KERNEL); + msk_buf = kzalloc(pkt_len, GFP_KERNEL); + if (!pkt_buf || !msk_buf) { + ret = -ENOMEM; + goto free_alloc; + } + + memcpy(pkt_buf, proto->raw.spec, pkt_len); + memcpy(msk_buf, proto->raw.mask, pkt_len); + + psr = ice_parser_create(hw); + if (IS_ERR(psr)) { + ret = PTR_ERR(psr); + goto free_alloc; + } + + ret = ice_parser_run(psr, pkt_buf, pkt_len, &pkt_parsed); + if (ret) + goto parser_destroy; + + ret = ice_parser_profile_init(&pkt_parsed, pkt_buf, msk_buf, + pkt_len, ICE_BLK_RSS, &prof); + if (ret) + goto parser_destroy; + + memcpy(&raw_cfg->prof, &prof, sizeof(prof)); + +parser_destroy: + ice_parser_destroy(psr); +free_alloc: + kfree(pkt_buf); + kfree(msk_buf); + return ret; +} + +/** + * ice_add_raw_rss_cfg - add RSS configuration for raw pattern + * @vf: pointer to the VF info + * @cfg: pointer to the RSS raw pattern configuration + * + * This function adds the RSS configuration for raw pattern. + * Check if current profile is matched. If not, remove the old + * one and add the new profile to HW directly. Update the symmetric + * hash configuration as well. + * + * Return: 0 on success; negative error code on failure. + */ +static int +ice_add_raw_rss_cfg(struct ice_vf *vf, struct ice_rss_raw_cfg *cfg) +{ + struct ice_parser_profile *prof = &cfg->prof; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_rss_prof_info *rss_prof; + struct ice_hw *hw = &vf->pf->hw; + int i, ptg, ret = 0; + u16 vsi_handle; + u64 id; + + vsi_handle = vf->lan_vsi_idx; + id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX); + + ptg = hw->blk[ICE_BLK_RSS].xlt1.t[id]; + rss_prof = &vf->rss_prof_info[ptg]; + + /* check if ptg already has a profile */ + if (rss_prof->prof.fv_num) { + for (i = 0; i < ICE_MAX_FV_WORDS; i++) { + if (rss_prof->prof.fv[i].proto_id != + prof->fv[i].proto_id || + rss_prof->prof.fv[i].offset != + prof->fv[i].offset) + break; + } + + /* current profile is matched, check symmetric hash */ + if (i == ICE_MAX_FV_WORDS) { + if (rss_prof->symm != cfg->symm) + goto update_symm; + return ret; + } + + /* current profile is not matched, remove it */ + ret = + ice_rem_prof_id_flow(hw, ICE_BLK_RSS, + ice_get_hw_vsi_num(hw, vsi_handle), + id); + if (ret) { + dev_err(dev, "remove RSS flow failed\n"); + return ret; + } + + ret = ice_rem_prof(hw, ICE_BLK_RSS, id); + if (ret) { + dev_err(dev, "remove RSS profile failed\n"); + return ret; + } + } + + /* add new profile */ + ret = ice_flow_set_parser_prof(hw, vsi_handle, 0, prof, ICE_BLK_RSS); + if (ret) { + dev_err(dev, "HW profile add failed\n"); + return ret; + } + + memcpy(&rss_prof->prof, prof, sizeof(struct ice_parser_profile)); + +update_symm: + rss_prof->symm = cfg->symm; + ice_rss_update_raw_symm(hw, cfg, id); + return ret; +} + +/** + * ice_rem_raw_rss_cfg - remove RSS configuration for raw pattern + * @vf: pointer to the VF info + * @cfg: pointer to the RSS raw pattern configuration + * + * This function removes the RSS configuration for raw pattern. + * Check if vsi group is already removed first. If not, remove the + * profile. + * + * Return: 0 on success; negative error code on failure. + */ +static int +ice_rem_raw_rss_cfg(struct ice_vf *vf, struct ice_rss_raw_cfg *cfg) +{ + struct ice_parser_profile *prof = &cfg->prof; + struct device *dev = ice_pf_to_dev(vf->pf); + struct ice_hw *hw = &vf->pf->hw; + int ptg, ret = 0; + u16 vsig, vsi; + u64 id; + + id = find_first_bit(prof->ptypes, ICE_FLOW_PTYPE_MAX); + + ptg = hw->blk[ICE_BLK_RSS].xlt1.t[id]; + + memset(&vf->rss_prof_info[ptg], 0, + sizeof(struct ice_rss_prof_info)); + + /* check if vsig is already removed */ + vsi = ice_get_hw_vsi_num(hw, vf->lan_vsi_idx); + if (vsi >= ICE_MAX_VSI) { + ret = -EINVAL; + goto err; + } + + vsig = hw->blk[ICE_BLK_RSS].xlt2.vsis[vsi].vsig; + if (vsig) { + ret = ice_rem_prof_id_flow(hw, ICE_BLK_RSS, vsi, id); + if (ret) + goto err; + + ret = ice_rem_prof(hw, ICE_BLK_RSS, id); + if (ret) + goto err; + } + + return ret; + +err: + dev_err(dev, "HW profile remove failed\n"); + return ret; +} + /** * ice_vc_handle_rss_cfg * @vf: pointer to the VF info @@ -352,6 +1569,9 @@ int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) struct device *dev = ice_pf_to_dev(vf->pf); struct ice_hw *hw = &vf->pf->hw; struct ice_vsi *vsi; + u8 hash_type; + bool symm; + int ret; if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { dev_dbg(dev, "VF %d attempting to configure RSS, but RSS is not supported by the PF\n", @@ -387,49 +1607,44 @@ int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) goto error_param; } - if (!ice_vc_validate_pattern(vf, &rss_cfg->proto_hdrs)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; + if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) { + hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR : + ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; + + ret = ice_vc_rss_hash_update(hw, vsi, hash_type); + if (ret) + v_ret = ice_err_to_virt_err(ret); goto error_param; } - if (rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_R_ASYMMETRIC) { - struct ice_vsi_ctx *ctx; - u8 lut_type, hash_type; - int status; + hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ : + ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; + ret = ice_vc_rss_hash_update(hw, vsi, hash_type); + if (ret) { + v_ret = ice_err_to_virt_err(ret); + goto error_param; + } - lut_type = ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI; - hash_type = add ? ICE_AQ_VSI_Q_OPT_RSS_HASH_XOR : - ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ; + symm = rss_cfg->rss_algorithm == VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC; + /* Configure RSS hash for raw pattern */ + if (rss_cfg->proto_hdrs.tunnel_level == 0 && + rss_cfg->proto_hdrs.count == 0) { + struct ice_rss_raw_cfg raw_cfg; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); - if (!ctx) { - v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + if (ice_parse_raw_rss_pattern(vf, &rss_cfg->proto_hdrs, + &raw_cfg)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - ctx->info.q_opt_rss = - FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_LUT_M, lut_type) | - FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hash_type); - - /* Preserve existing queueing option setting */ - ctx->info.q_opt_rss |= (vsi->info.q_opt_rss & - ICE_AQ_VSI_Q_OPT_RSS_GBL_LUT_M); - ctx->info.q_opt_tc = vsi->info.q_opt_tc; - ctx->info.q_opt_flags = vsi->info.q_opt_rss; - - ctx->info.valid_sections = - cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); - - status = ice_update_vsi(hw, vsi->idx, ctx, NULL); - if (status) { - dev_err(dev, "update VSI for RSS failed, err %d aq_err %s\n", - status, libie_aq_str(hw->adminq.sq_last_status)); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; + if (add) { + raw_cfg.symm = symm; + if (ice_add_raw_rss_cfg(vf, &raw_cfg)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; } else { - vsi->info.q_opt_rss = ctx->info.q_opt_rss; + if (ice_rem_raw_rss_cfg(vf, &raw_cfg)) + v_ret = VIRTCHNL_STATUS_ERR_PARAM; } - - kfree(ctx); } else { struct ice_rss_hash_cfg cfg; @@ -448,24 +1663,12 @@ int ice_vc_handle_rss_cfg(struct ice_vf *vf, u8 *msg, bool add) } if (add) { - if (ice_add_rss_cfg(hw, vsi, &cfg)) { + cfg.symm = symm; + if (ice_add_rss_cfg_wrap(vf, &cfg)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "ice_add_rss_cfg failed for vsi = %d, v_ret = %d\n", - vsi->vsi_num, v_ret); - } } else { - int status; - - status = ice_rem_rss_cfg(hw, vsi->idx, &cfg); - /* We just ignore -ENOENT, because if two configurations - * share the same profile remove one of them actually - * removes both, since the profile is deleted. - */ - if (status && status != -ENOENT) { + if (ice_rem_rss_cfg_wrap(vf, &cfg)) v_ret = VIRTCHNL_STATUS_ERR_PARAM; - dev_err(dev, "ice_rem_rss_cfg failed for VF ID:%d, error:%d\n", - vf->vf_id, status); - } } } diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h index ca4da0c899794..50fa7be0c00d4 100644 --- a/drivers/net/ethernet/intel/idpf/idpf.h +++ b/drivers/net/ethernet/intel/idpf/idpf.h @@ -734,13 +734,11 @@ static inline bool idpf_is_rdma_cap_ena(struct idpf_adapter *adapter) } #define IDPF_CAP_RSS (\ - VIRTCHNL2_FLOW_IPV4_TCP |\ VIRTCHNL2_FLOW_IPV4_TCP |\ VIRTCHNL2_FLOW_IPV4_UDP |\ VIRTCHNL2_FLOW_IPV4_SCTP |\ VIRTCHNL2_FLOW_IPV4_OTHER |\ VIRTCHNL2_FLOW_IPV6_TCP |\ - VIRTCHNL2_FLOW_IPV6_TCP |\ VIRTCHNL2_FLOW_IPV6_UDP |\ VIRTCHNL2_FLOW_IPV6_SCTP |\ VIRTCHNL2_FLOW_IPV6_OTHER) diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c index 8c46481d2e1f4..7a06eaf46a08e 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_main.c +++ b/drivers/net/ethernet/intel/idpf/idpf_main.c @@ -3,15 +3,93 @@ #include "idpf.h" #include "idpf_devids.h" +#include "idpf_lan_vf_regs.h" #include "idpf_virtchnl.h" #define DRV_SUMMARY "Intel(R) Infrastructure Data Path Function Linux Driver" +#define IDPF_NETWORK_ETHERNET_PROGIF 0x01 +#define IDPF_CLASS_NETWORK_ETHERNET_PROGIF \ + (PCI_CLASS_NETWORK_ETHERNET << 8 | IDPF_NETWORK_ETHERNET_PROGIF) +#define IDPF_VF_TEST_VAL 0xfeed0000u + MODULE_DESCRIPTION(DRV_SUMMARY); MODULE_IMPORT_NS("LIBETH"); MODULE_IMPORT_NS("LIBETH_XDP"); MODULE_LICENSE("GPL"); +/** + * idpf_get_device_type - Helper to find if it is a VF or PF device + * @pdev: PCI device information struct + * + * Return: PF/VF device ID or -%errno on failure. + */ +static int idpf_get_device_type(struct pci_dev *pdev) +{ + void __iomem *addr; + int ret; + + addr = ioremap(pci_resource_start(pdev, 0) + VF_ARQBAL, 4); + if (!addr) { + pci_err(pdev, "Failed to allocate BAR0 mbx region\n"); + return -EIO; + } + + writel(IDPF_VF_TEST_VAL, addr); + if (readl(addr) == IDPF_VF_TEST_VAL) + ret = IDPF_DEV_ID_VF; + else + ret = IDPF_DEV_ID_PF; + + iounmap(addr); + + return ret; +} + +/** + * idpf_dev_init - Initialize device specific parameters + * @adapter: adapter to initialize + * @ent: entry in idpf_pci_tbl + * + * Return: %0 on success, -%errno on failure. + */ +static int idpf_dev_init(struct idpf_adapter *adapter, + const struct pci_device_id *ent) +{ + int ret; + + if (ent->class == IDPF_CLASS_NETWORK_ETHERNET_PROGIF) { + ret = idpf_get_device_type(adapter->pdev); + switch (ret) { + case IDPF_DEV_ID_VF: + idpf_vf_dev_ops_init(adapter); + adapter->crc_enable = true; + break; + case IDPF_DEV_ID_PF: + idpf_dev_ops_init(adapter); + break; + default: + return ret; + } + + return 0; + } + + switch (ent->device) { + case IDPF_DEV_ID_PF: + idpf_dev_ops_init(adapter); + break; + case IDPF_DEV_ID_VF: + idpf_vf_dev_ops_init(adapter); + adapter->crc_enable = true; + break; + default: + return -ENODEV; + } + + return 0; +} + /** * idpf_remove - Device removal routine * @pdev: PCI device information struct @@ -165,21 +243,6 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->req_tx_splitq = true; adapter->req_rx_splitq = true; - switch (ent->device) { - case IDPF_DEV_ID_PF: - idpf_dev_ops_init(adapter); - break; - case IDPF_DEV_ID_VF: - idpf_vf_dev_ops_init(adapter); - adapter->crc_enable = true; - break; - default: - err = -ENODEV; - dev_err(&pdev->dev, "Unexpected dev ID 0x%x in idpf probe\n", - ent->device); - goto err_free; - } - adapter->pdev = pdev; err = pcim_enable_device(pdev); if (err) @@ -259,11 +322,18 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* setup msglvl */ adapter->msg_enable = netif_msg_init(-1, IDPF_AVAIL_NETIF_M); + err = idpf_dev_init(adapter, ent); + if (err) { + dev_err(&pdev->dev, "Unexpected dev ID 0x%x in idpf probe\n", + ent->device); + goto destroy_vc_event_wq; + } + err = idpf_cfg_hw(adapter); if (err) { dev_err(dev, "Failed to configure HW structure for adapter: %d\n", err); - goto err_cfg_hw; + goto destroy_vc_event_wq; } mutex_init(&adapter->vport_ctrl_lock); @@ -284,7 +354,7 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) return 0; -err_cfg_hw: +destroy_vc_event_wq: destroy_workqueue(adapter->vc_event_wq); err_vc_event_wq_alloc: destroy_workqueue(adapter->stats_wq); @@ -304,6 +374,7 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) static const struct pci_device_id idpf_pci_tbl[] = { { PCI_VDEVICE(INTEL, IDPF_DEV_ID_PF)}, { PCI_VDEVICE(INTEL, IDPF_DEV_ID_VF)}, + { PCI_DEVICE_CLASS(IDPF_CLASS_NETWORK_ETHERNET_PROGIF, ~0)}, { /* Sentinel */ } }; MODULE_DEVICE_TABLE(pci, idpf_pci_tbl); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 61dfcd8cb370a..ac57212ab02bd 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1235,7 +1235,7 @@ static int igbvf_vlan_rx_add_vid(struct net_device *netdev, spin_lock_bh(&hw->mbx_lock); if (hw->mac.ops.set_vfta(hw, vid, true)) { - dev_warn(&adapter->pdev->dev, "Vlan id %d\n is not added", vid); + dev_warn(&adapter->pdev->dev, "Vlan id %d is not added\n", vid); spin_unlock_bh(&hw->mbx_lock); return -EINVAL; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index d5b1b974b4a33..3069b583fd81a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -198,7 +198,7 @@ static int prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, * @hw: pointer to hardware structure * @autoc: value to write to AUTOC * @locked: bool to indicate whether the SW/FW lock was already taken by - * previous proc_autoc_read_82599. + * previous prot_autoc_read_82599. * * This part (82599) may need to hold a the SW/FW lock around all writes to * AUTOC. Likewise after a write we need to do a pipeline reset. @@ -1622,7 +1622,7 @@ int ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, break; } - /* store source and destination IP masks (big-enian) */ + /* store source and destination IP masks (big-endian) */ IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIP4M, ~input_mask->formatted.src_ip[0]); IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRDIP4M, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 2d660e9edb80a..2ad81f687a844 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2805,6 +2805,14 @@ static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) return 64; } +static u32 ixgbe_get_rx_ring_count(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = ixgbe_from_netdev(dev); + + return min_t(u32, adapter->num_rx_queues, + ixgbe_rss_indir_tbl_max(adapter)); +} + static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -2812,11 +2820,6 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, int ret = -EOPNOTSUPP; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = min_t(int, adapter->num_rx_queues, - ixgbe_rss_indir_tbl_max(adapter)); - ret = 0; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = adapter->fdir_filter_count; ret = 0; @@ -3743,6 +3746,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .get_ethtool_stats = ixgbe_get_ethtool_stats, .get_coalesce = ixgbe_get_coalesce, .set_coalesce = ixgbe_set_coalesce, + .get_rx_ring_count = ixgbe_get_rx_ring_count, .get_rxnfc = ixgbe_get_rxnfc, .set_rxnfc = ixgbe_set_rxnfc, .get_rxfh_indir_size = ixgbe_rss_indir_size, @@ -3791,6 +3795,7 @@ static const struct ethtool_ops ixgbe_ethtool_ops_e610 = { .get_ethtool_stats = ixgbe_get_ethtool_stats, .get_coalesce = ixgbe_get_coalesce, .set_coalesce = ixgbe_set_coalesce, + .get_rx_ring_count = ixgbe_get_rx_ring_count, .get_rxnfc = ixgbe_get_rxnfc, .set_rxnfc = ixgbe_set_rxnfc, .get_rxfh_indir_size = ixgbe_rss_indir_size, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index 170a29d162c65..a1d04914fbbca 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -318,7 +318,7 @@ static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter) * ixgbe_set_dcb_sriov_queues: Allocate queues for SR-IOV devices w/ DCB * @adapter: board private structure to initialize * - * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * When SR-IOV (Single Root IO Virtualization) is enabled, allocate queues * and VM pools where appropriate. Also assign queues based on DCB * priorities and map accordingly.. * @@ -492,7 +492,7 @@ static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) * ixgbe_set_sriov_queues - Allocate queues for SR-IOV devices * @adapter: board private structure to initialize * - * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * When SR-IOV (Single Root IO Virtualization) is enabled, allocate queues * and VM pools where appropriate. If RSS is available, then also try and * enable RSS and map accordingly. * diff --git a/drivers/net/ethernet/marvell/octeontx2/af/Makefile b/drivers/net/ethernet/marvell/octeontx2/af/Makefile index 532813d8d0281..244de500963ed 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/Makefile +++ b/drivers/net/ethernet/marvell/octeontx2/af/Makefile @@ -12,4 +12,5 @@ rvu_af-y := cgx.o rvu.o rvu_cgx.o rvu_npa.o rvu_nix.o \ rvu_reg.o rvu_npc.o rvu_debugfs.o ptp.o rvu_npc_fs.o \ rvu_cpt.o rvu_devlink.o rpm.o rvu_cn10k.o rvu_switch.o \ rvu_sdp.o rvu_npc_hash.o mcs.o mcs_rvu_if.o mcs_cnf10kb.o \ - rvu_rep.o cn20k/mbox_init.o + rvu_rep.o cn20k/mbox_init.o cn20k/nix.o cn20k/debugfs.o \ + cn20k/npa.o diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c index ec0e11c77cbf2..42044cd810b1f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c @@ -1994,7 +1994,7 @@ static int cgx_probe(struct pci_dev *pdev, const struct pci_device_id *id) nvec = pci_msix_vec_count(cgx->pdev); err = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_MSIX); - if (err < 0 || err != nvec) { + if (err < 0) { dev_err(dev, "Request for %d msix vectors failed, err %d\n", nvec, err); goto err_release_regions; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c new file mode 100644 index 0000000000000..498968bf4cf59 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.c @@ -0,0 +1,218 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include +#include +#include +#include + +#include "struct.h" +#include "debugfs.h" + +void print_nix_cn20k_sq_ctx(struct seq_file *m, + struct nix_cn20k_sq_ctx_s *sq_ctx) +{ + seq_printf(m, "W0: ena \t\t\t%d\nW0: qint_idx \t\t\t%d\n", + sq_ctx->ena, sq_ctx->qint_idx); + seq_printf(m, "W0: substream \t\t\t0x%03x\nW0: sdp_mcast \t\t\t%d\n", + sq_ctx->substream, sq_ctx->sdp_mcast); + seq_printf(m, "W0: cq \t\t\t\t%d\nW0: sqe_way_mask \t\t%d\n\n", + sq_ctx->cq, sq_ctx->sqe_way_mask); + + seq_printf(m, "W1: smq \t\t\t%d\nW1: cq_ena \t\t\t%d\nW1: xoff\t\t\t%d\n", + sq_ctx->smq, sq_ctx->cq_ena, sq_ctx->xoff); + seq_printf(m, "W1: sso_ena \t\t\t%d\nW1: smq_rr_weight\t\t%d\n", + sq_ctx->sso_ena, sq_ctx->smq_rr_weight); + seq_printf(m, "W1: default_chan\t\t%d\nW1: sqb_count\t\t\t%d\n\n", + sq_ctx->default_chan, sq_ctx->sqb_count); + + seq_printf(m, "W1: smq_rr_count_lb \t\t%d\n", sq_ctx->smq_rr_count_lb); + seq_printf(m, "W2: smq_rr_count_ub \t\t%d\n", sq_ctx->smq_rr_count_ub); + seq_printf(m, "W2: sqb_aura \t\t\t%d\nW2: sq_int \t\t\t%d\n", + sq_ctx->sqb_aura, sq_ctx->sq_int); + seq_printf(m, "W2: sq_int_ena \t\t\t%d\nW2: sqe_stype \t\t\t%d\n", + sq_ctx->sq_int_ena, sq_ctx->sqe_stype); + + seq_printf(m, "W3: max_sqe_size\t\t%d\nW3: cq_limit\t\t\t%d\n", + sq_ctx->max_sqe_size, sq_ctx->cq_limit); + seq_printf(m, "W3: lmt_dis \t\t\t%d\nW3: mnq_dis \t\t\t%d\n", + sq_ctx->lmt_dis, sq_ctx->mnq_dis); + seq_printf(m, "W3: smq_next_sq\t\t\t%d\nW3: smq_lso_segnum\t\t%d\n", + sq_ctx->smq_next_sq, sq_ctx->smq_lso_segnum); + seq_printf(m, "W3: tail_offset \t\t%d\nW3: smenq_offset\t\t%d\n", + sq_ctx->tail_offset, sq_ctx->smenq_offset); + seq_printf(m, "W3: head_offset\t\t\t%d\nW3: smenq_next_sqb_vld\t\t%d\n\n", + sq_ctx->head_offset, sq_ctx->smenq_next_sqb_vld); + + seq_printf(m, "W3: smq_next_sq_vld\t\t%d\nW3: smq_pend\t\t\t%d\n", + sq_ctx->smq_next_sq_vld, sq_ctx->smq_pend); + seq_printf(m, "W4: next_sqb \t\t\t%llx\n\n", sq_ctx->next_sqb); + seq_printf(m, "W5: tail_sqb \t\t\t%llx\n\n", sq_ctx->tail_sqb); + seq_printf(m, "W6: smenq_sqb \t\t\t%llx\n\n", sq_ctx->smenq_sqb); + seq_printf(m, "W7: smenq_next_sqb \t\t%llx\n\n", + sq_ctx->smenq_next_sqb); + + seq_printf(m, "W8: head_sqb\t\t\t%llx\n\n", sq_ctx->head_sqb); + + seq_printf(m, "W9: vfi_lso_total\t\t%d\n", sq_ctx->vfi_lso_total); + seq_printf(m, "W9: vfi_lso_sizem1\t\t%d\nW9: vfi_lso_sb\t\t\t%d\n", + sq_ctx->vfi_lso_sizem1, sq_ctx->vfi_lso_sb); + seq_printf(m, "W9: vfi_lso_mps\t\t\t%d\nW9: vfi_lso_vlan0_ins_ena\t%d\n", + sq_ctx->vfi_lso_mps, sq_ctx->vfi_lso_vlan0_ins_ena); + seq_printf(m, "W9: vfi_lso_vlan1_ins_ena\t%d\nW9: vfi_lso_vld \t\t%d\n\n", + sq_ctx->vfi_lso_vld, sq_ctx->vfi_lso_vlan1_ins_ena); + + seq_printf(m, "W10: scm_lso_rem \t\t%llu\n\n", + (u64)sq_ctx->scm_lso_rem); + seq_printf(m, "W11: octs \t\t\t%llu\n\n", (u64)sq_ctx->octs); + seq_printf(m, "W12: pkts \t\t\t%llu\n\n", (u64)sq_ctx->pkts); + seq_printf(m, "W13: aged_drop_octs \t\t\t%llu\n\n", + (u64)sq_ctx->aged_drop_octs); + seq_printf(m, "W13: aged_drop_pkts \t\t\t%llu\n\n", + (u64)sq_ctx->aged_drop_pkts); + seq_printf(m, "W14: dropped_octs \t\t%llu\n\n", + (u64)sq_ctx->dropped_octs); + seq_printf(m, "W15: dropped_pkts \t\t%llu\n\n", + (u64)sq_ctx->dropped_pkts); +} + +void print_nix_cn20k_cq_ctx(struct seq_file *m, + struct nix_cn20k_aq_enq_rsp *rsp) +{ + struct nix_cn20k_cq_ctx_s *cq_ctx = &rsp->cq; + + seq_printf(m, "W0: base \t\t\t%llx\n\n", cq_ctx->base); + + seq_printf(m, "W1: wrptr \t\t\t%llx\n", (u64)cq_ctx->wrptr); + seq_printf(m, "W1: avg_con \t\t\t%d\nW1: cint_idx \t\t\t%d\n", + cq_ctx->avg_con, cq_ctx->cint_idx); + seq_printf(m, "W1: cq_err \t\t\t%d\nW1: qint_idx \t\t\t%d\n", + cq_ctx->cq_err, cq_ctx->qint_idx); + seq_printf(m, "W1: bpid \t\t\t%d\nW1: bp_ena \t\t\t%d\n\n", + cq_ctx->bpid, cq_ctx->bp_ena); + + seq_printf(m, "W1: lbpid_high \t\t\t0x%03x\n", cq_ctx->lbpid_high); + seq_printf(m, "W1: lbpid_med \t\t\t0x%03x\n", cq_ctx->lbpid_med); + seq_printf(m, "W1: lbpid_low \t\t\t0x%03x\n", cq_ctx->lbpid_low); + seq_printf(m, "(W1: lbpid) \t\t\t0x%03x\n", + cq_ctx->lbpid_high << 6 | cq_ctx->lbpid_med << 3 | + cq_ctx->lbpid_low); + seq_printf(m, "W1: lbp_ena \t\t\t\t%d\n\n", cq_ctx->lbp_ena); + + seq_printf(m, "W2: update_time \t\t%d\nW2:avg_level \t\t\t%d\n", + cq_ctx->update_time, cq_ctx->avg_level); + seq_printf(m, "W2: head \t\t\t%d\nW2:tail \t\t\t%d\n\n", + cq_ctx->head, cq_ctx->tail); + + seq_printf(m, "W3: cq_err_int_ena \t\t%d\nW3:cq_err_int \t\t\t%d\n", + cq_ctx->cq_err_int_ena, cq_ctx->cq_err_int); + seq_printf(m, "W3: qsize \t\t\t%d\nW3:stashing \t\t\t%d\n", + cq_ctx->qsize, cq_ctx->stashing); + + seq_printf(m, "W3: caching \t\t\t%d\n", cq_ctx->caching); + seq_printf(m, "W3: lbp_frac \t\t\t%d\n", cq_ctx->lbp_frac); + seq_printf(m, "W3: stash_thresh \t\t\t%d\n", + cq_ctx->stash_thresh); + + seq_printf(m, "W3: msh_valid \t\t\t%d\nW3:msh_dst \t\t\t%d\n", + cq_ctx->msh_valid, cq_ctx->msh_dst); + + seq_printf(m, "W3: cpt_drop_err_en \t\t\t%d\n", + cq_ctx->cpt_drop_err_en); + seq_printf(m, "W3: ena \t\t\t%d\n", + cq_ctx->ena); + seq_printf(m, "W3: drop_ena \t\t\t%d\nW3: drop \t\t\t%d\n", + cq_ctx->drop_ena, cq_ctx->drop); + seq_printf(m, "W3: bp \t\t\t\t%d\n\n", cq_ctx->bp); + + seq_printf(m, "W4: lbpid_ext \t\t\t\t%d\n\n", cq_ctx->lbpid_ext); + seq_printf(m, "W4: bpid_ext \t\t\t\t%d\n\n", cq_ctx->bpid_ext); +} + +void print_npa_cn20k_aura_ctx(struct seq_file *m, + struct npa_cn20k_aq_enq_rsp *rsp) +{ + struct npa_cn20k_aura_s *aura = &rsp->aura; + + seq_printf(m, "W0: Pool addr\t\t%llx\n", aura->pool_addr); + + seq_printf(m, "W1: ena\t\t\t%d\nW1: pool caching\t%d\n", + aura->ena, aura->pool_caching); + seq_printf(m, "W1: avg con\t\t%d\n", aura->avg_con); + seq_printf(m, "W1: pool drop ena\t%d\nW1: aura drop ena\t%d\n", + aura->pool_drop_ena, aura->aura_drop_ena); + seq_printf(m, "W1: bp_ena\t\t%d\nW1: aura drop\t\t%d\n", + aura->bp_ena, aura->aura_drop); + seq_printf(m, "W1: aura shift\t\t%d\nW1: avg_level\t\t%d\n", + aura->shift, aura->avg_level); + + seq_printf(m, "W2: count\t\t%llu\nW2: nix_bpid\t\t%d\n", + (u64)aura->count, aura->bpid); + + seq_printf(m, "W3: limit\t\t%llu\nW3: bp\t\t\t%d\nW3: fc_ena\t\t%d\n", + (u64)aura->limit, aura->bp, aura->fc_ena); + + seq_printf(m, "W3: fc_up_crossing\t%d\nW3: fc_stype\t\t%d\n", + aura->fc_up_crossing, aura->fc_stype); + seq_printf(m, "W3: fc_hyst_bits\t%d\n", aura->fc_hyst_bits); + + seq_printf(m, "W4: fc_addr\t\t%llx\n", aura->fc_addr); + + seq_printf(m, "W5: pool_drop\t\t%d\nW5: update_time\t\t%d\n", + aura->pool_drop, aura->update_time); + seq_printf(m, "W5: err_int \t\t%d\nW5: err_int_ena\t\t%d\n", + aura->err_int, aura->err_int_ena); + seq_printf(m, "W5: thresh_int\t\t%d\nW5: thresh_int_ena \t%d\n", + aura->thresh_int, aura->thresh_int_ena); + seq_printf(m, "W5: thresh_up\t\t%d\nW5: thresh_qint_idx\t%d\n", + aura->thresh_up, aura->thresh_qint_idx); + seq_printf(m, "W5: err_qint_idx \t%d\n", aura->err_qint_idx); + + seq_printf(m, "W6: thresh\t\t%llu\n", (u64)aura->thresh); + seq_printf(m, "W6: fc_msh_dst\t\t%d\n", aura->fc_msh_dst); +} + +void print_npa_cn20k_pool_ctx(struct seq_file *m, + struct npa_cn20k_aq_enq_rsp *rsp) +{ + struct npa_cn20k_pool_s *pool = &rsp->pool; + + seq_printf(m, "W0: Stack base\t\t%llx\n", pool->stack_base); + + seq_printf(m, "W1: ena \t\t%d\nW1: nat_align \t\t%d\n", + pool->ena, pool->nat_align); + seq_printf(m, "W1: stack_caching\t%d\n", + pool->stack_caching); + seq_printf(m, "W1: buf_offset\t\t%d\nW1: buf_size\t\t%d\n", + pool->buf_offset, pool->buf_size); + + seq_printf(m, "W2: stack_max_pages \t%d\nW2: stack_pages\t\t%d\n", + pool->stack_max_pages, pool->stack_pages); + + seq_printf(m, "W4: stack_offset\t%d\nW4: shift\t\t%d\nW4: avg_level\t\t%d\n", + pool->stack_offset, pool->shift, pool->avg_level); + seq_printf(m, "W4: avg_con \t\t%d\nW4: fc_ena\t\t%d\nW4: fc_stype\t\t%d\n", + pool->avg_con, pool->fc_ena, pool->fc_stype); + seq_printf(m, "W4: fc_hyst_bits\t%d\nW4: fc_up_crossing\t%d\n", + pool->fc_hyst_bits, pool->fc_up_crossing); + seq_printf(m, "W4: update_time\t\t%d\n", pool->update_time); + + seq_printf(m, "W5: fc_addr\t\t%llx\n", pool->fc_addr); + + seq_printf(m, "W6: ptr_start\t\t%llx\n", pool->ptr_start); + + seq_printf(m, "W7: ptr_end\t\t%llx\n", pool->ptr_end); + + seq_printf(m, "W8: err_int\t\t%d\nW8: err_int_ena\t\t%d\n", + pool->err_int, pool->err_int_ena); + seq_printf(m, "W8: thresh_int\t\t%d\n", pool->thresh_int); + seq_printf(m, "W8: thresh_int_ena\t%d\nW8: thresh_up\t\t%d\n", + pool->thresh_int_ena, pool->thresh_up); + seq_printf(m, "W8: thresh_qint_idx\t%d\nW8: err_qint_idx\t%d\n", + pool->thresh_qint_idx, pool->err_qint_idx); + seq_printf(m, "W8: fc_msh_dst\t\t%d\n", pool->fc_msh_dst); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.h new file mode 100644 index 0000000000000..a2e3a2cd6edb3 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/debugfs.h @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Marvell OcteonTx2 CGX driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#ifndef DEBUFS_H +#define DEBUFS_H + +#include +#include +#include +#include + +#include "struct.h" +#include "../mbox.h" + +void print_nix_cn20k_sq_ctx(struct seq_file *m, + struct nix_cn20k_sq_ctx_s *sq_ctx); +void print_nix_cn20k_cq_ctx(struct seq_file *m, + struct nix_cn20k_aq_enq_rsp *rsp); +void print_npa_cn20k_aura_ctx(struct seq_file *m, + struct npa_cn20k_aq_enq_rsp *rsp); +void print_npa_cn20k_pool_ctx(struct seq_file *m, + struct npa_cn20k_aq_enq_rsp *rsp); + +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/nix.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/nix.c new file mode 100644 index 0000000000000..aa2016fd1bba9 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/nix.c @@ -0,0 +1,20 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include +#include + +#include "struct.h" +#include "../rvu.h" + +int rvu_mbox_handler_nix_cn20k_aq_enq(struct rvu *rvu, + struct nix_cn20k_aq_enq_req *req, + struct nix_cn20k_aq_enq_rsp *rsp) +{ + return rvu_nix_aq_enq_inst(rvu, (struct nix_aq_enq_req *)req, + (struct nix_aq_enq_rsp *)rsp); +} diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c new file mode 100644 index 0000000000000..fe8f926c8b750 --- /dev/null +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/npa.c @@ -0,0 +1,21 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Marvell RVU Admin Function driver + * + * Copyright (C) 2024 Marvell. + * + */ + +#include +#include + +#include "struct.h" +#include "../rvu.h" + +int rvu_mbox_handler_npa_cn20k_aq_enq(struct rvu *rvu, + struct npa_cn20k_aq_enq_req *req, + struct npa_cn20k_aq_enq_rsp *rsp) +{ + return rvu_npa_aq_enq_inst(rvu, (struct npa_aq_enq_req *)req, + (struct npa_aq_enq_rsp *)rsp); +} +EXPORT_SYMBOL(rvu_mbox_handler_npa_cn20k_aq_enq); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h index 76ce3ec6da9cd..763f6cabd7c24 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/cn20k/struct.h @@ -8,6 +8,8 @@ #ifndef STRUCT_H #define STRUCT_H +#define NIX_MAX_CTX_SIZE 128 + /* * CN20k RVU PF MBOX Interrupt Vector Enumeration * @@ -37,4 +39,342 @@ enum rvu_af_cn20k_int_vec_e { RVU_AF_CN20K_INT_VEC_PFAF1_MBOX1 = 0x9, RVU_AF_CN20K_INT_VEC_CNT = 0xa, }; + +struct nix_cn20k_sq_ctx_s { + u64 ena : 1; /* W0 */ + u64 qint_idx : 6; + u64 substream : 20; + u64 sdp_mcast : 1; + u64 cq : 20; + u64 sqe_way_mask : 16; + u64 smq : 11; /* W1 */ + u64 cq_ena : 1; + u64 xoff : 1; + u64 sso_ena : 1; + u64 smq_rr_weight : 14; + u64 default_chan : 12; + u64 sqb_count : 16; + u64 reserved_120_120 : 1; + u64 smq_rr_count_lb : 7; + u64 smq_rr_count_ub : 25; /* W2 */ + u64 sqb_aura : 20; + u64 sq_int : 8; + u64 sq_int_ena : 8; + u64 sqe_stype : 2; + u64 reserved_191_191 : 1; + u64 max_sqe_size : 2; /* W3 */ + u64 cq_limit : 8; + u64 lmt_dis : 1; + u64 mnq_dis : 1; + u64 smq_next_sq : 20; + u64 smq_lso_segnum : 8; + u64 tail_offset : 6; + u64 smenq_offset : 6; + u64 head_offset : 6; + u64 smenq_next_sqb_vld : 1; + u64 smq_pend : 1; + u64 smq_next_sq_vld : 1; + u64 reserved_253_255 : 3; + u64 next_sqb : 64; /* W4 */ + u64 tail_sqb : 64; /* W5 */ + u64 smenq_sqb : 64; /* W6 */ + u64 smenq_next_sqb : 64; /* W7 */ + u64 head_sqb : 64; /* W8 */ + u64 reserved_576_583 : 8; /* W9 */ + u64 vfi_lso_total : 18; + u64 vfi_lso_sizem1 : 3; + u64 vfi_lso_sb : 8; + u64 vfi_lso_mps : 14; + u64 vfi_lso_vlan0_ins_ena : 1; + u64 vfi_lso_vlan1_ins_ena : 1; + u64 vfi_lso_vld : 1; + u64 reserved_630_639 : 10; + u64 scm_lso_rem : 18; /* W10 */ + u64 reserved_658_703 : 46; + u64 octs : 48; /* W11 */ + u64 reserved_752_767 : 16; + u64 pkts : 48; /* W12 */ + u64 reserved_816_831 : 16; + u64 aged_drop_octs : 32; /* W13 */ + u64 aged_drop_pkts : 32; + u64 dropped_octs : 48; /* W14 */ + u64 reserved_944_959 : 16; + u64 dropped_pkts : 48; /* W15 */ + u64 reserved_1008_1023 : 16; +}; + +static_assert(sizeof(struct nix_cn20k_sq_ctx_s) == NIX_MAX_CTX_SIZE); + +struct nix_cn20k_cq_ctx_s { + u64 base : 64; /* W0 */ + u64 lbp_ena : 1; /* W1 */ + u64 lbpid_low : 3; + u64 bp_ena : 1; + u64 lbpid_med : 3; + u64 bpid : 9; + u64 lbpid_high : 3; + u64 qint_idx : 7; + u64 cq_err : 1; + u64 cint_idx : 7; + u64 avg_con : 9; + u64 wrptr : 20; + u64 tail : 20; /* W2 */ + u64 head : 20; + u64 avg_level : 8; + u64 update_time : 16; + u64 bp : 8; /* W3 */ + u64 drop : 8; + u64 drop_ena : 1; + u64 ena : 1; + u64 cpt_drop_err_en : 1; + u64 reserved_211_211 : 1; + u64 msh_dst : 11; + u64 msh_valid : 1; + u64 stash_thresh : 4; + u64 lbp_frac : 4; + u64 caching : 1; + u64 stashing : 1; + u64 reserved_234_235 : 2; + u64 qsize : 4; + u64 cq_err_int : 8; + u64 cq_err_int_ena : 8; + u64 bpid_ext : 2; /* W4 */ + u64 reserved_258_259 : 2; + u64 lbpid_ext : 2; + u64 reserved_262_319 : 58; + u64 reserved_320_383 : 64; /* W5 */ + u64 reserved_384_447 : 64; /* W6 */ + u64 reserved_448_511 : 64; /* W7 */ + u64 padding[8]; +}; + +static_assert(sizeof(struct nix_cn20k_sq_ctx_s) == NIX_MAX_CTX_SIZE); + +struct nix_cn20k_rq_ctx_s { + u64 ena : 1; + u64 sso_ena : 1; + u64 ipsech_ena : 1; + u64 ena_wqwd : 1; + u64 cq : 20; + u64 reserved_24_34 : 11; + u64 port_il4_dis : 1; + u64 port_ol4_dis : 1; + u64 lenerr_dis : 1; + u64 csum_il4_dis : 1; + u64 csum_ol4_dis : 1; + u64 len_il4_dis : 1; + u64 len_il3_dis : 1; + u64 len_ol4_dis : 1; + u64 len_ol3_dis : 1; + u64 wqe_aura : 20; + u64 spb_aura : 20; + u64 lpb_aura : 20; + u64 sso_grp : 10; + u64 sso_tt : 2; + u64 pb_caching : 2; + u64 wqe_caching : 1; + u64 xqe_drop_ena : 1; + u64 spb_drop_ena : 1; + u64 lpb_drop_ena : 1; + u64 pb_stashing : 1; + u64 ipsecd_drop_en : 1; + u64 chi_ena : 1; + u64 reserved_125_127 : 3; + u64 band_prof_id_l : 10; + u64 sso_fc_ena : 1; + u64 policer_ena : 1; + u64 spb_sizem1 : 6; + u64 wqe_skip : 2; + u64 spb_high_sizem1 : 3; + u64 spb_ena : 1; + u64 lpb_sizem1 : 12; + u64 first_skip : 7; + u64 reserved_171_171 : 1; + u64 later_skip : 6; + u64 xqe_imm_size : 6; + u64 band_prof_id_h : 4; + u64 reserved_188_189 : 2; + u64 xqe_imm_copy : 1; + u64 xqe_hdr_split : 1; + u64 xqe_drop : 8; + u64 xqe_pass : 8; + u64 wqe_pool_drop : 8; + u64 wqe_pool_pass : 8; + u64 spb_aura_drop : 8; + u64 spb_aura_pass : 8; + u64 spb_pool_drop : 8; + u64 spb_pool_pass : 8; + u64 lpb_aura_drop : 8; + u64 lpb_aura_pass : 8; + u64 lpb_pool_drop : 8; + u64 lpb_pool_pass : 8; + u64 reserved_288_291 : 4; + u64 rq_int : 8; + u64 rq_int_ena : 8; + u64 qint_idx : 7; + u64 reserved_315_319 : 5; + u64 ltag : 24; + u64 good_utag : 8; + u64 bad_utag : 8; + u64 flow_tagw : 6; + u64 ipsec_vwqe : 1; + u64 vwqe_ena : 1; + u64 vtime_wait : 8; + u64 max_vsize_exp : 4; + u64 vwqe_skip : 2; + u64 reserved_382_383 : 2; + u64 octs : 48; + u64 reserved_432_447 : 16; + u64 pkts : 48; + u64 reserved_496_511 : 16; + u64 drop_octs : 48; + u64 reserved_560_575 : 16; + u64 drop_pkts : 48; + u64 reserved_624_639 : 16; + u64 re_pkts : 48; + u64 reserved_688_703 : 16; + u64 reserved_704_767 : 64; + u64 reserved_768_831 : 64; + u64 reserved_832_895 : 64; + u64 reserved_896_959 : 64; + u64 reserved_960_1023 : 64; +}; + +static_assert(sizeof(struct nix_cn20k_rq_ctx_s) == NIX_MAX_CTX_SIZE); + +struct npa_cn20k_aura_s { + u64 pool_addr; /* W0 */ + u64 ena : 1; /* W1 */ + u64 reserved_65 : 2; + u64 pool_caching : 1; + u64 reserved_68 : 16; + u64 avg_con : 9; + u64 reserved_93 : 1; + u64 pool_drop_ena : 1; + u64 aura_drop_ena : 1; + u64 bp_ena : 1; + u64 reserved_97_103 : 7; + u64 aura_drop : 8; + u64 shift : 6; + u64 reserved_118_119 : 2; + u64 avg_level : 8; + u64 count : 36; /* W2 */ + u64 reserved_164_167 : 4; + u64 bpid : 12; + u64 reserved_180_191 : 12; + u64 limit : 36; /* W3 */ + u64 reserved_228_231 : 4; + u64 bp : 7; + u64 reserved_239_243 : 5; + u64 fc_ena : 1; + u64 fc_up_crossing : 1; + u64 fc_stype : 2; + u64 fc_hyst_bits : 4; + u64 reserved_252_255 : 4; + u64 fc_addr; /* W4 */ + u64 pool_drop : 8; /* W5 */ + u64 update_time : 16; + u64 err_int : 8; + u64 err_int_ena : 8; + u64 thresh_int : 1; + u64 thresh_int_ena : 1; + u64 thresh_up : 1; + u64 reserved_363 : 1; + u64 thresh_qint_idx : 7; + u64 reserved_371 : 1; + u64 err_qint_idx : 7; + u64 reserved_379_383 : 5; + u64 thresh : 36; /* W6*/ + u64 rsvd_423_420 : 4; + u64 fc_msh_dst : 11; + u64 reserved_435_438 : 4; + u64 op_dpc_ena : 1; + u64 op_dpc_set : 5; + u64 reserved_445_445 : 1; + u64 stream_ctx : 1; + u64 unified_ctx : 1; + u64 reserved_448_511; /* W7 */ + u64 padding[8]; +}; + +static_assert(sizeof(struct npa_cn20k_aura_s) == NIX_MAX_CTX_SIZE); + +struct npa_cn20k_pool_s { + u64 stack_base; /* W0 */ + u64 ena : 1; + u64 nat_align : 1; + u64 reserved_66_67 : 2; + u64 stack_caching : 1; + u64 reserved_69_87 : 19; + u64 buf_offset : 12; + u64 reserved_100_103 : 4; + u64 buf_size : 12; + u64 reserved_116_119 : 4; + u64 ref_cnt_prof : 3; + u64 reserved_123_127 : 5; + u64 stack_max_pages : 32; + u64 stack_pages : 32; + uint64_t bp_0 : 7; + uint64_t bp_1 : 7; + uint64_t bp_2 : 7; + uint64_t bp_3 : 7; + uint64_t bp_4 : 7; + uint64_t bp_5 : 7; + uint64_t bp_6 : 7; + uint64_t bp_7 : 7; + uint64_t bp_ena_0 : 1; + uint64_t bp_ena_1 : 1; + uint64_t bp_ena_2 : 1; + uint64_t bp_ena_3 : 1; + uint64_t bp_ena_4 : 1; + uint64_t bp_ena_5 : 1; + uint64_t bp_ena_6 : 1; + uint64_t bp_ena_7 : 1; + u64 stack_offset : 4; + u64 reserved_260_263 : 4; + u64 shift : 6; + u64 reserved_270_271 : 2; + u64 avg_level : 8; + u64 avg_con : 9; + u64 fc_ena : 1; + u64 fc_stype : 2; + u64 fc_hyst_bits : 4; + u64 fc_up_crossing : 1; + u64 reserved_297_299 : 3; + u64 update_time : 16; + u64 reserved_316_319 : 4; + u64 fc_addr; /* W5 */ + u64 ptr_start; /* W6 */ + u64 ptr_end; /* W7 */ + u64 bpid_0 : 12; + u64 reserved_524_535 : 12; + u64 err_int : 8; + u64 err_int_ena : 8; + u64 thresh_int : 1; + u64 thresh_int_ena : 1; + u64 thresh_up : 1; + u64 reserved_555 : 1; + u64 thresh_qint_idx : 7; + u64 reserved_563 : 1; + u64 err_qint_idx : 7; + u64 reserved_571_575 : 5; + u64 thresh : 36; + u64 rsvd_612_615 : 4; + u64 fc_msh_dst : 11; + u64 reserved_627_630 : 4; + u64 op_dpc_ena : 1; + u64 op_dpc_set : 5; + u64 reserved_637_637 : 1; + u64 stream_ctx : 1; + u64 reserved_639 : 1; + u64 reserved_640_703; /* W10 */ + u64 reserved_704_767; /* W11 */ + u64 reserved_768_831; /* W12 */ + u64 reserved_832_895; /* W13 */ + u64 reserved_896_959; /* W14 */ + u64 reserved_960_1023; /* W15 */ +}; + +static_assert(sizeof(struct npa_cn20k_pool_s) == NIX_MAX_CTX_SIZE); + #endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index 933073cd22804..a3e273126e4e1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -203,6 +203,8 @@ M(NPA_LF_ALLOC, 0x400, npa_lf_alloc, \ M(NPA_LF_FREE, 0x401, npa_lf_free, msg_req, msg_rsp) \ M(NPA_AQ_ENQ, 0x402, npa_aq_enq, npa_aq_enq_req, npa_aq_enq_rsp) \ M(NPA_HWCTX_DISABLE, 0x403, npa_hwctx_disable, hwctx_disable_req, msg_rsp)\ +M(NPA_CN20K_AQ_ENQ, 0x404, npa_cn20k_aq_enq, npa_cn20k_aq_enq_req, \ + npa_cn20k_aq_enq_rsp) \ /* SSO/SSOW mbox IDs (range 0x600 - 0x7FF) */ \ /* TIM mbox IDs (range 0x800 - 0x9FF) */ \ /* CPT mbox IDs (range 0xA00 - 0xBFF) */ \ @@ -336,6 +338,8 @@ M(NIX_MCAST_GRP_UPDATE, 0x802d, nix_mcast_grp_update, \ nix_mcast_grp_update_req, \ nix_mcast_grp_update_rsp) \ M(NIX_LF_STATS, 0x802e, nix_lf_stats, nix_stats_req, nix_stats_rsp) \ +M(NIX_CN20K_AQ_ENQ, 0x802f, nix_cn20k_aq_enq, nix_cn20k_aq_enq_req, \ + nix_cn20k_aq_enq_rsp) \ /* MCS mbox IDs (range 0xA000 - 0xBFFF) */ \ M(MCS_ALLOC_RESOURCES, 0xa000, mcs_alloc_resources, mcs_alloc_rsrc_req, \ mcs_alloc_rsrc_rsp) \ @@ -832,6 +836,39 @@ struct npa_aq_enq_rsp { }; }; +struct npa_cn20k_aq_enq_req { + struct mbox_msghdr hdr; + u32 aura_id; + u8 ctype; + u8 op; + union { + /* Valid when op == WRITE/INIT and ctype == AURA. + * LF fills the pool_id in aura.pool_addr. AF will translate + * the pool_id to pool context pointer. + */ + struct npa_cn20k_aura_s aura; + /* Valid when op == WRITE/INIT and ctype == POOL */ + struct npa_cn20k_pool_s pool; + }; + /* Mask data when op == WRITE (1=write, 0=don't write) */ + union { + /* Valid when op == WRITE and ctype == AURA */ + struct npa_cn20k_aura_s aura_mask; + /* Valid when op == WRITE and ctype == POOL */ + struct npa_cn20k_pool_s pool_mask; + }; +}; + +struct npa_cn20k_aq_enq_rsp { + struct mbox_msghdr hdr; + union { + /* Valid when op == READ and ctype == AURA */ + struct npa_cn20k_aura_s aura; + /* Valid when op == READ and ctype == POOL */ + struct npa_cn20k_pool_s pool; + }; +}; + /* Disable all contexts of type 'ctype' */ struct hwctx_disable_req { struct mbox_msghdr hdr; @@ -940,6 +977,42 @@ struct nix_lf_free_req { u64 flags; }; +/* CN20K NIX AQ enqueue msg */ +struct nix_cn20k_aq_enq_req { + struct mbox_msghdr hdr; + u32 qidx; + u8 ctype; + u8 op; + union { + struct nix_cn20k_rq_ctx_s rq; + struct nix_cn20k_sq_ctx_s sq; + struct nix_cn20k_cq_ctx_s cq; + struct nix_rsse_s rss; + struct nix_rx_mce_s mce; + struct nix_bandprof_s prof; + }; + union { + struct nix_cn20k_rq_ctx_s rq_mask; + struct nix_cn20k_sq_ctx_s sq_mask; + struct nix_cn20k_cq_ctx_s cq_mask; + struct nix_rsse_s rss_mask; + struct nix_rx_mce_s mce_mask; + struct nix_bandprof_s prof_mask; + }; +}; + +struct nix_cn20k_aq_enq_rsp { + struct mbox_msghdr hdr; + union { + struct nix_cn20k_rq_ctx_s rq; + struct nix_cn20k_sq_ctx_s sq; + struct nix_cn20k_cq_ctx_s cq; + struct nix_rsse_s rss; + struct nix_rx_mce_s mce; + struct nix_bandprof_s prof; + }; +}; + /* CN10K NIX AQ enqueue msg */ struct nix_cn10k_aq_enq_req { struct mbox_msghdr hdr; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index b582833419232..e85dac2c806d9 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -498,6 +498,14 @@ struct channel_fwdata { u8 reserved[RVU_CHANL_INFO_RESERVED]; }; +struct altaf_intr_notify { + unsigned long flr_pf_bmap[2]; + unsigned long flr_vf_bmap[2]; + unsigned long gint_paddr; + unsigned long gint_iova_addr; + unsigned long reserved[6]; +}; + struct rvu_fwdata { #define RVU_FWDATA_HEADER_MAGIC 0xCFDA /* Custom Firmware Data*/ #define RVU_FWDATA_VERSION 0x0001 @@ -517,7 +525,8 @@ struct rvu_fwdata { u32 ptp_ext_clk_rate; u32 ptp_ext_tstamp; struct channel_fwdata channel_data; -#define FWDATA_RESERVED_MEM 958 + struct altaf_intr_notify altaf_intr_info; +#define FWDATA_RESERVED_MEM 946 u64 reserved[FWDATA_RESERVED_MEM]; #define CGX_MAX 9 #define CGX_LMACS_MAX 4 @@ -648,6 +657,7 @@ struct rvu { struct mutex mbox_lock; /* Serialize mbox up and down msgs */ u16 rep_pcifunc; + bool altaf_ready; int rep_cnt; u16 *rep2pfvf_map; u8 rep_mode; @@ -1032,6 +1042,9 @@ void rvu_nix_flr_free_bpids(struct rvu *rvu, u16 pcifunc); int rvu_alloc_cint_qint_mem(struct rvu *rvu, struct rvu_pfvf *pfvf, int blkaddr, int nixlf); void rvu_block_bcast_xon(struct rvu *rvu, int blkaddr); +int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, + struct nix_aq_enq_rsp *rsp); + /* NPC APIs */ void rvu_npc_freemem(struct rvu *rvu); int rvu_npc_get_pkind(struct rvu *rvu, u16 pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 8375f18c8e074..15d3cb0b9da64 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -21,6 +21,8 @@ #include "rvu_npc_hash.h" #include "mcs.h" +#include "cn20k/debugfs.h" + #define DEBUGFS_DIR_NAME "octeontx2" enum { @@ -1101,6 +1103,11 @@ static void print_npa_aura_ctx(struct seq_file *m, struct npa_aq_enq_rsp *rsp) struct npa_aura_s *aura = &rsp->aura; struct rvu *rvu = m->private; + if (is_cn20k(rvu->pdev)) { + print_npa_cn20k_aura_ctx(m, (struct npa_cn20k_aq_enq_rsp *)rsp); + return; + } + seq_printf(m, "W0: Pool addr\t\t%llx\n", aura->pool_addr); seq_printf(m, "W1: ena\t\t\t%d\nW1: pool caching\t%d\n", @@ -1149,6 +1156,11 @@ static void print_npa_pool_ctx(struct seq_file *m, struct npa_aq_enq_rsp *rsp) struct npa_pool_s *pool = &rsp->pool; struct rvu *rvu = m->private; + if (is_cn20k(rvu->pdev)) { + print_npa_cn20k_pool_ctx(m, (struct npa_cn20k_aq_enq_rsp *)rsp); + return; + } + seq_printf(m, "W0: Stack base\t\t%llx\n", pool->stack_base); seq_printf(m, "W1: ena \t\t%d\nW1: nat_align \t\t%d\n", @@ -1651,6 +1663,9 @@ static void print_tm_tree(struct seq_file *m, int blkaddr; u64 cfg; + if (!sq_ctx->ena) + return; + blkaddr = nix_hw->blkaddr; schq = sq_ctx->smq; @@ -2009,10 +2024,16 @@ static void print_nix_sq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp) struct nix_hw *nix_hw = m->private; struct rvu *rvu = nix_hw->rvu; + if (is_cn20k(rvu->pdev)) { + print_nix_cn20k_sq_ctx(m, (struct nix_cn20k_sq_ctx_s *)sq_ctx); + return; + } + if (!is_rvu_otx2(rvu)) { print_nix_cn10k_sq_ctx(m, (struct nix_cn10k_sq_ctx_s *)sq_ctx); return; } + seq_printf(m, "W0: sqe_way_mask \t\t%d\nW0: cq \t\t\t\t%d\n", sq_ctx->sqe_way_mask, sq_ctx->cq); seq_printf(m, "W0: sdp_mcast \t\t\t%d\nW0: substream \t\t\t0x%03x\n", @@ -2103,7 +2124,9 @@ static void print_nix_cn10k_rq_ctx(struct seq_file *m, seq_printf(m, "W1: ipsecd_drop_ena \t\t%d\nW1: chi_ena \t\t\t%d\n\n", rq_ctx->ipsecd_drop_ena, rq_ctx->chi_ena); - seq_printf(m, "W2: band_prof_id \t\t%d\n", rq_ctx->band_prof_id); + seq_printf(m, "W2: band_prof_id \t\t%d\n", + (u16)rq_ctx->band_prof_id_h << 10 | rq_ctx->band_prof_id); + seq_printf(m, "W2: policer_ena \t\t%d\n", rq_ctx->policer_ena); seq_printf(m, "W2: spb_sizem1 \t\t\t%d\n", rq_ctx->spb_sizem1); seq_printf(m, "W2: wqe_skip \t\t\t%d\nW2: sqb_ena \t\t\t%d\n", @@ -2225,6 +2248,11 @@ static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp) struct nix_hw *nix_hw = m->private; struct rvu *rvu = nix_hw->rvu; + if (is_cn20k(rvu->pdev)) { + print_nix_cn20k_cq_ctx(m, (struct nix_cn20k_aq_enq_rsp *)rsp); + return; + } + seq_printf(m, "W0: base \t\t\t%llx\n\n", cq_ctx->base); seq_printf(m, "W1: wrptr \t\t\t%llx\n", (u64)cq_ctx->wrptr); @@ -2254,6 +2282,7 @@ static void print_nix_cq_ctx(struct seq_file *m, struct nix_aq_enq_rsp *rsp) cq_ctx->cq_err_int_ena, cq_ctx->cq_err_int); seq_printf(m, "W3: qsize \t\t\t%d\nW3:caching \t\t\t%d\n", cq_ctx->qsize, cq_ctx->caching); + seq_printf(m, "W3: substream \t\t\t0x%03x\nW3: ena \t\t\t%d\n", cq_ctx->substream, cq_ctx->ena); if (!is_rvu_otx2(rvu)) { @@ -2615,7 +2644,10 @@ static void print_band_prof_ctx(struct seq_file *m, (prof->rc_action == 1) ? "DROP" : "RED"; seq_printf(m, "W1: rc_action\t\t%s\n", str); seq_printf(m, "W1: meter_algo\t\t%d\n", prof->meter_algo); - seq_printf(m, "W1: band_prof_id\t%d\n", prof->band_prof_id); + + seq_printf(m, "W1: band_prof_id\t%d\n", + (u16)prof->band_prof_id_h << 7 | prof->band_prof_id); + seq_printf(m, "W1: hl_en\t\t%d\n", prof->hl_en); seq_printf(m, "W2: ts\t\t\t%lld\n", (u64)prof->ts); @@ -2784,6 +2816,9 @@ static void rvu_dbg_npa_init(struct rvu *rvu) &rvu_dbg_npa_aura_ctx_fops); debugfs_create_file("pool_ctx", 0600, rvu->rvu_dbg.npa, rvu, &rvu_dbg_npa_pool_ctx_fops); + + if (is_cn20k(rvu->pdev)) /* NDC not appliable for cn20k */ + return; debugfs_create_file("ndc_cache", 0600, rvu->rvu_dbg.npa, rvu, &rvu_dbg_npa_ndc_cache_fops); debugfs_create_file("ndc_hits_miss", 0600, rvu->rvu_dbg.npa, rvu, @@ -3950,6 +3985,9 @@ static void rvu_dbg_cpt_init(struct rvu *rvu, int blkaddr) static const char *rvu_get_dbg_dir_name(struct rvu *rvu) { + if (is_cn20k(rvu->pdev)) + return "cn20k"; + if (!is_rvu_otx2(rvu)) return "cn10k"; else diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 828316211b245..2f485a930edd1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -1019,6 +1019,12 @@ static void nix_get_aq_req_smq(struct rvu *rvu, struct nix_aq_enq_req *req, { struct nix_cn10k_aq_enq_req *aq_req; + if (is_cn20k(rvu->pdev)) { + *smq = ((struct nix_cn20k_aq_enq_req *)req)->sq.smq; + *smq_mask = ((struct nix_cn20k_aq_enq_req *)req)->sq_mask.smq; + return; + } + if (!is_rvu_otx2(rvu)) { aq_req = (struct nix_cn10k_aq_enq_req *)req; *smq = aq_req->sq.smq; @@ -1149,36 +1155,36 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, case NIX_AQ_INSTOP_WRITE: if (req->ctype == NIX_AQ_CTYPE_RQ) memcpy(mask, &req->rq_mask, - sizeof(struct nix_rq_ctx_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_SQ) memcpy(mask, &req->sq_mask, - sizeof(struct nix_sq_ctx_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_CQ) memcpy(mask, &req->cq_mask, - sizeof(struct nix_cq_ctx_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_RSS) memcpy(mask, &req->rss_mask, - sizeof(struct nix_rsse_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(mask, &req->mce_mask, - sizeof(struct nix_rx_mce_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_BANDPROF) memcpy(mask, &req->prof_mask, - sizeof(struct nix_bandprof_s)); + NIX_MAX_CTX_SIZE); fallthrough; case NIX_AQ_INSTOP_INIT: if (req->ctype == NIX_AQ_CTYPE_RQ) - memcpy(ctx, &req->rq, sizeof(struct nix_rq_ctx_s)); + memcpy(ctx, &req->rq, NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_SQ) - memcpy(ctx, &req->sq, sizeof(struct nix_sq_ctx_s)); + memcpy(ctx, &req->sq, NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_CQ) - memcpy(ctx, &req->cq, sizeof(struct nix_cq_ctx_s)); + memcpy(ctx, &req->cq, NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_RSS) - memcpy(ctx, &req->rss, sizeof(struct nix_rsse_s)); + memcpy(ctx, &req->rss, NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_MCE) - memcpy(ctx, &req->mce, sizeof(struct nix_rx_mce_s)); + memcpy(ctx, &req->mce, NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_BANDPROF) - memcpy(ctx, &req->prof, sizeof(struct nix_bandprof_s)); + memcpy(ctx, &req->prof, NIX_MAX_CTX_SIZE); break; case NIX_AQ_INSTOP_NOP: case NIX_AQ_INSTOP_READ: @@ -1243,22 +1249,22 @@ static int rvu_nix_blk_aq_enq_inst(struct rvu *rvu, struct nix_hw *nix_hw, if (req->op == NIX_AQ_INSTOP_READ) { if (req->ctype == NIX_AQ_CTYPE_RQ) memcpy(&rsp->rq, ctx, - sizeof(struct nix_rq_ctx_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_SQ) memcpy(&rsp->sq, ctx, - sizeof(struct nix_sq_ctx_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_CQ) memcpy(&rsp->cq, ctx, - sizeof(struct nix_cq_ctx_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_RSS) memcpy(&rsp->rss, ctx, - sizeof(struct nix_rsse_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_MCE) memcpy(&rsp->mce, ctx, - sizeof(struct nix_rx_mce_s)); + NIX_MAX_CTX_SIZE); else if (req->ctype == NIX_AQ_CTYPE_BANDPROF) memcpy(&rsp->prof, ctx, - sizeof(struct nix_bandprof_s)); + NIX_MAX_CTX_SIZE); } } @@ -1289,8 +1295,8 @@ static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw, /* Make copy of original context & mask which are required * for resubmission */ - memcpy(&aq_req.cq_mask, &req->cq_mask, sizeof(struct nix_cq_ctx_s)); - memcpy(&aq_req.cq, &req->cq, sizeof(struct nix_cq_ctx_s)); + memcpy(&aq_req.cq_mask, &req->cq_mask, NIX_MAX_CTX_SIZE); + memcpy(&aq_req.cq, &req->cq, NIX_MAX_CTX_SIZE); /* exclude fields which HW can update */ aq_req.cq_mask.cq_err = 0; @@ -1309,7 +1315,7 @@ static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw, * updated fields are masked out for request and response * comparison */ - for (word = 0; word < sizeof(struct nix_cq_ctx_s) / sizeof(u64); + for (word = 0; word < NIX_MAX_CTX_SIZE / sizeof(u64); word++) { *(u64 *)((u8 *)&aq_rsp.cq + word * 8) &= (*(u64 *)((u8 *)&aq_req.cq_mask + word * 8)); @@ -1317,14 +1323,14 @@ static int rvu_nix_verify_aq_ctx(struct rvu *rvu, struct nix_hw *nix_hw, (*(u64 *)((u8 *)&aq_req.cq_mask + word * 8)); } - if (memcmp(&aq_req.cq, &aq_rsp.cq, sizeof(struct nix_cq_ctx_s))) + if (memcmp(&aq_req.cq, &aq_rsp.cq, NIX_MAX_CTX_SIZE)) return NIX_AF_ERR_AQ_CTX_RETRY_WRITE; return 0; } -static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, - struct nix_aq_enq_rsp *rsp) +int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req, + struct nix_aq_enq_rsp *rsp) { struct nix_hw *nix_hw; int err, retries = 5; @@ -5812,6 +5818,8 @@ static void nix_ipolicer_freemem(struct rvu *rvu, struct nix_hw *nix_hw) } } +#define NIX_BW_PROF_HI_MASK GENMASK(10, 7) + static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req, struct nix_hw *nix_hw, u16 pcifunc) { @@ -5850,7 +5858,8 @@ static int nix_verify_bandprof(struct nix_cn10k_aq_enq_req *req, return -EINVAL; ipolicer = &nix_hw->ipolicer[hi_layer]; - prof_idx = req->prof.band_prof_id; + prof_idx = FIELD_PREP(NIX_BW_PROF_HI_MASK, req->prof.band_prof_id_h); + prof_idx |= req->prof.band_prof_id; if (prof_idx >= ipolicer->band_prof.max || ipolicer->pfvf_map[prof_idx] != pcifunc) return -EINVAL; @@ -6015,8 +6024,10 @@ static int nix_ipolicer_map_leaf_midprofs(struct rvu *rvu, aq_req->op = NIX_AQ_INSTOP_WRITE; aq_req->qidx = leaf_prof; - aq_req->prof.band_prof_id = mid_prof; + aq_req->prof.band_prof_id = mid_prof & 0x7F; aq_req->prof_mask.band_prof_id = GENMASK(6, 0); + aq_req->prof.band_prof_id_h = FIELD_GET(NIX_BW_PROF_HI_MASK, mid_prof); + aq_req->prof_mask.band_prof_id_h = GENMASK(3, 0); aq_req->prof.hl_en = 1; aq_req->prof_mask.hl_en = 1; @@ -6025,6 +6036,8 @@ static int nix_ipolicer_map_leaf_midprofs(struct rvu *rvu, (struct nix_aq_enq_rsp *)aq_rsp); } +#define NIX_RQ_PROF_HI_MASK GENMASK(13, 10) + int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc, u16 rq_idx, u16 match_id) { @@ -6056,7 +6069,8 @@ int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc, return 0; /* Get the bandwidth profile ID mapped to this RQ */ - leaf_prof = aq_rsp.rq.band_prof_id; + leaf_prof = FIELD_PREP(NIX_RQ_PROF_HI_MASK, aq_rsp.rq.band_prof_id_h); + leaf_prof |= aq_rsp.rq.band_prof_id; ipolicer = &nix_hw->ipolicer[BAND_PROF_LEAF_LAYER]; ipolicer->match_id[leaf_prof] = match_id; @@ -6094,7 +6108,10 @@ int rvu_nix_setup_ratelimit_aggr(struct rvu *rvu, u16 pcifunc, * to different RQs and marked with same match_id * are rate limited in a aggregate fashion */ - mid_prof = aq_rsp.prof.band_prof_id; + mid_prof = FIELD_PREP(NIX_BW_PROF_HI_MASK, + aq_rsp.prof.band_prof_id_h); + mid_prof |= aq_rsp.prof.band_prof_id; + rc = nix_ipolicer_map_leaf_midprofs(rvu, nix_hw, &aq_req, &aq_rsp, leaf_prof, mid_prof); @@ -6216,7 +6233,8 @@ static void nix_clear_ratelimit_aggr(struct rvu *rvu, struct nix_hw *nix_hw, if (!aq_rsp.prof.hl_en) return; - mid_prof = aq_rsp.prof.band_prof_id; + mid_prof = FIELD_PREP(NIX_BW_PROF_HI_MASK, aq_rsp.prof.band_prof_id_h); + mid_prof |= aq_rsp.prof.band_prof_id; ipolicer = &nix_hw->ipolicer[BAND_PROF_MID_LAYER]; ipolicer->ref_count[mid_prof]--; /* If ref_count is zero, free mid layer profile */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c index 4f5ca5ab13a40..e2a33e46b48ad 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npa.c @@ -464,6 +464,23 @@ int rvu_mbox_handler_npa_lf_free(struct rvu *rvu, struct msg_req *req, return 0; } +static void npa_aq_ndc_config(struct rvu *rvu, struct rvu_block *block) +{ + u64 cfg; + + if (is_cn20k(rvu->pdev)) /* NDC not applicable to cn20k */ + return; + + /* Do not bypass NDC cache */ + cfg = rvu_read64(rvu, block->addr, NPA_AF_NDC_CFG); + cfg &= ~0x03DULL; +#ifdef CONFIG_NDC_DIS_DYNAMIC_CACHING + /* Disable caching of stack pages */ + cfg |= 0x10ULL; +#endif + rvu_write64(rvu, block->addr, NPA_AF_NDC_CFG, cfg); +} + static int npa_aq_init(struct rvu *rvu, struct rvu_block *block) { u64 cfg; @@ -479,14 +496,7 @@ static int npa_aq_init(struct rvu *rvu, struct rvu_block *block) rvu_write64(rvu, block->addr, NPA_AF_GEN_CFG, cfg); #endif - /* Do not bypass NDC cache */ - cfg = rvu_read64(rvu, block->addr, NPA_AF_NDC_CFG); - cfg &= ~0x03DULL; -#ifdef CONFIG_NDC_DIS_DYNAMIC_CACHING - /* Disable caching of stack pages */ - cfg |= 0x10ULL; -#endif - rvu_write64(rvu, block->addr, NPA_AF_NDC_CFG, cfg); + npa_aq_ndc_config(rvu, block); /* For CN10K NPA BATCH DMA set 35 cache lines */ if (!is_rvu_otx2(rvu)) { @@ -567,6 +577,9 @@ int rvu_ndc_fix_locked_cacheline(struct rvu *rvu, int blkaddr) int bank, max_bank, line, max_line, err; u64 reg, ndc_af_const; + if (is_cn20k(rvu->pdev)) /* NDC not applicable to cn20k */ + return 0; + /* Set the ENABLE bit(63) to '0' */ reg = rvu_read64(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL); rvu_write64(rvu, blkaddr, NDC_AF_CAMS_RD_INTERVAL, reg & GENMASK_ULL(62, 0)); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h index 0596a3ac4c12b..8e868f815de1f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_struct.h @@ -13,6 +13,8 @@ #define RVU_MULTI_BLK_VER 0x7ULL +#define NIX_MAX_CTX_SIZE 128 + /* RVU Block Address Enumeration */ enum rvu_block_addr_e { BLKADDR_RVUM = 0x0ULL, @@ -370,8 +372,12 @@ struct nix_cq_ctx_s { u64 qsize : 4; u64 cq_err_int : 8; u64 cq_err_int_ena : 8; + /* Ensure all context sizes are 128 bytes */ + u64 padding[12]; }; +static_assert(sizeof(struct nix_cq_ctx_s) == NIX_MAX_CTX_SIZE); + /* CN10K NIX Receive queue context structure */ struct nix_cn10k_rq_ctx_s { u64 ena : 1; @@ -413,7 +419,8 @@ struct nix_cn10k_rq_ctx_s { u64 rsvd_171 : 1; u64 later_skip : 6; u64 xqe_imm_size : 6; - u64 rsvd_189_184 : 6; + u64 band_prof_id_h : 4; + u64 rsvd_189_188 : 2; u64 xqe_imm_copy : 1; u64 xqe_hdr_split : 1; u64 xqe_drop : 8; /* W3 */ @@ -460,6 +467,8 @@ struct nix_cn10k_rq_ctx_s { u64 rsvd_1023_960; /* W15 */ }; +static_assert(sizeof(struct nix_cn10k_rq_ctx_s) == NIX_MAX_CTX_SIZE); + /* CN10K NIX Send queue context structure */ struct nix_cn10k_sq_ctx_s { u64 ena : 1; @@ -523,6 +532,8 @@ struct nix_cn10k_sq_ctx_s { u64 rsvd_1023_1008 : 16; }; +static_assert(sizeof(struct nix_cn10k_sq_ctx_s) == NIX_MAX_CTX_SIZE); + /* NIX Receive queue context structure */ struct nix_rq_ctx_s { u64 ena : 1; @@ -594,6 +605,8 @@ struct nix_rq_ctx_s { u64 rsvd_1023_960; /* W15 */ }; +static_assert(sizeof(struct nix_rq_ctx_s) == NIX_MAX_CTX_SIZE); + /* NIX sqe sizes */ enum nix_maxsqesz { NIX_MAXSQESZ_W16 = 0x0, @@ -668,13 +681,18 @@ struct nix_sq_ctx_s { u64 rsvd_1023_1008 : 16; }; +static_assert(sizeof(struct nix_sq_ctx_s) == NIX_MAX_CTX_SIZE); + /* NIX Receive side scaling entry structure*/ struct nix_rsse_s { uint32_t rq : 20; uint32_t reserved_20_31 : 12; - + /* Ensure all context sizes are minimum 128 bytes */ + u64 padding[15]; }; +static_assert(sizeof(struct nix_rsse_s) == NIX_MAX_CTX_SIZE); + /* NIX receive multicast/mirror entry structure */ struct nix_rx_mce_s { uint64_t op : 2; @@ -684,8 +702,12 @@ struct nix_rx_mce_s { uint64_t rsvd_31_24 : 8; uint64_t pf_func : 16; uint64_t next : 16; + /* Ensure all context sizes are minimum 128 bytes */ + u64 padding[15]; }; +static_assert(sizeof(struct nix_rx_mce_s) == NIX_MAX_CTX_SIZE); + enum nix_band_prof_layers { BAND_PROF_LEAF_LAYER = 0, BAND_PROF_INVAL_LAYER = 1, @@ -736,7 +758,8 @@ struct nix_bandprof_s { uint64_t rc_action : 2; uint64_t meter_algo : 2; uint64_t band_prof_id : 7; - uint64_t reserved_111_118 : 8; + uint64_t band_prof_id_h : 4; + uint64_t reserved_115_118 : 4; uint64_t hl_en : 1; uint64_t reserved_120_127 : 8; uint64_t ts : 48; /* W2 */ @@ -769,6 +792,8 @@ struct nix_bandprof_s { uint64_t reserved_1008_1023 : 16; }; +static_assert(sizeof(struct nix_bandprof_s) == NIX_MAX_CTX_SIZE); + enum nix_lsoalg { NIX_LSOALG_NOP, NIX_LSOALG_ADD_SEGNUM, diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c index bec7d5b4d7cc0..3e1bf22cba69c 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c @@ -15,6 +15,8 @@ static struct dev_hw_ops otx2_hw_ops = { .aura_freeptr = otx2_aura_freeptr, .refill_pool_ptrs = otx2_refill_pool_ptrs, .pfaf_mbox_intr_handler = otx2_pfaf_mbox_intr_handler, + .aura_aq_init = otx2_aura_aq_init, + .pool_aq_init = otx2_pool_aq_init, }; static struct dev_hw_ops cn10k_hw_ops = { @@ -23,6 +25,8 @@ static struct dev_hw_ops cn10k_hw_ops = { .aura_freeptr = cn10k_aura_freeptr, .refill_pool_ptrs = cn10k_refill_pool_ptrs, .pfaf_mbox_intr_handler = otx2_pfaf_mbox_intr_handler, + .aura_aq_init = otx2_aura_aq_init, + .pool_aq_init = otx2_pool_aq_init, }; void otx2_init_hw_ops(struct otx2_nic *pfvf) @@ -337,6 +341,12 @@ int cn10k_map_unmap_rq_policer(struct otx2_nic *pfvf, int rq_idx, aq->rq.band_prof_id = policer; aq->rq_mask.band_prof_id = GENMASK(9, 0); + /* If policer id is greater than 1023 then it implies hardware supports + * more leaf profiles. In that case use band_prof_id_h for 4 MSBs. + */ + aq->rq.band_prof_id_h = policer >> 10; + aq->rq_mask.band_prof_id_h = GENMASK(3, 0); + /* Fill AQ info */ aq->qidx = rq_idx; aq->ctype = NIX_AQ_CTYPE_RQ; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c index ec8cde98076dc..a60f8cf53febb 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn20k.c @@ -10,17 +10,6 @@ #include "otx2_struct.h" #include "cn10k.h" -static struct dev_hw_ops cn20k_hw_ops = { - .pfaf_mbox_intr_handler = cn20k_pfaf_mbox_intr_handler, - .vfaf_mbox_intr_handler = cn20k_vfaf_mbox_intr_handler, - .pfvf_mbox_intr_handler = cn20k_pfvf_mbox_intr_handler, -}; - -void cn20k_init(struct otx2_nic *pfvf) -{ - pfvf->hw_ops = &cn20k_hw_ops; -} -EXPORT_SYMBOL(cn20k_init); /* CN20K mbox AF => PFx irq handler */ irqreturn_t cn20k_pfaf_mbox_intr_handler(int irq, void *pf_irq) { @@ -250,3 +239,212 @@ int cn20k_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs) return 0; } + +#define RQ_BP_LVL_AURA (255 - ((85 * 256) / 100)) /* BP when 85% is full */ + +static u8 cn20k_aura_bpid_idx(struct otx2_nic *pfvf, int aura_id) +{ +#ifdef CONFIG_DCB + return pfvf->queue_to_pfc_map[aura_id]; +#else + return 0; +#endif +} + +static int cn20k_aura_aq_init(struct otx2_nic *pfvf, int aura_id, + int pool_id, int numptrs) +{ + struct npa_cn20k_aq_enq_req *aq; + struct otx2_pool *pool; + u8 bpid_idx; + int err; + + pool = &pfvf->qset.pool[pool_id]; + + /* Allocate memory for HW to update Aura count. + * Alloc one cache line, so that it fits all FC_STYPE modes. + */ + if (!pool->fc_addr) { + err = qmem_alloc(pfvf->dev, &pool->fc_addr, 1, OTX2_ALIGN); + if (err) + return err; + } + + /* Initialize this aura's context via AF */ + aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox); + if (!aq) { + /* Shared mbox memory buffer is full, flush it and retry */ + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) + return err; + aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox); + if (!aq) + return -ENOMEM; + } + + aq->aura_id = aura_id; + + /* Will be filled by AF with correct pool context address */ + aq->aura.pool_addr = pool_id; + aq->aura.pool_caching = 1; + aq->aura.shift = ilog2(numptrs) - 8; + aq->aura.count = numptrs; + aq->aura.limit = numptrs; + aq->aura.avg_level = 255; + aq->aura.ena = 1; + aq->aura.fc_ena = 1; + aq->aura.fc_addr = pool->fc_addr->iova; + aq->aura.fc_hyst_bits = 0; /* Store count on all updates */ + + /* Enable backpressure for RQ aura */ + if (aura_id < pfvf->hw.rqpool_cnt && !is_otx2_lbkvf(pfvf->pdev)) { + aq->aura.bp_ena = 0; + /* If NIX1 LF is attached then specify NIX1_RX. + * + * Below NPA_AURA_S[BP_ENA] is set according to the + * NPA_BPINTF_E enumeration given as: + * 0x0 + a*0x1 where 'a' is 0 for NIX0_RX and 1 for NIX1_RX so + * NIX0_RX is 0x0 + 0*0x1 = 0 + * NIX1_RX is 0x0 + 1*0x1 = 1 + * But in HRM it is given that + * "NPA_AURA_S[BP_ENA](w1[33:32]) - Enable aura backpressure to + * NIX-RX based on [BP] level. One bit per NIX-RX; index + * enumerated by NPA_BPINTF_E." + */ + if (pfvf->nix_blkaddr == BLKADDR_NIX1) + aq->aura.bp_ena = 1; + + bpid_idx = cn20k_aura_bpid_idx(pfvf, aura_id); + aq->aura.bpid = pfvf->bpid[bpid_idx]; + + /* Set backpressure level for RQ's Aura */ + aq->aura.bp = RQ_BP_LVL_AURA; + } + + /* Fill AQ info */ + aq->ctype = NPA_AQ_CTYPE_AURA; + aq->op = NPA_AQ_INSTOP_INIT; + + return 0; +} + +static int cn20k_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, + int stack_pages, int numptrs, int buf_size, + int type) +{ + struct page_pool_params pp_params = { 0 }; + struct npa_cn20k_aq_enq_req *aq; + struct otx2_pool *pool; + int err, sz; + + pool = &pfvf->qset.pool[pool_id]; + /* Alloc memory for stack which is used to store buffer pointers */ + err = qmem_alloc(pfvf->dev, &pool->stack, + stack_pages, pfvf->hw.stack_pg_bytes); + if (err) + return err; + + pool->rbsize = buf_size; + + /* Initialize this pool's context via AF */ + aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox); + if (!aq) { + /* Shared mbox memory buffer is full, flush it and retry */ + err = otx2_sync_mbox_msg(&pfvf->mbox); + if (err) { + qmem_free(pfvf->dev, pool->stack); + return err; + } + aq = otx2_mbox_alloc_msg_npa_cn20k_aq_enq(&pfvf->mbox); + if (!aq) { + qmem_free(pfvf->dev, pool->stack); + return -ENOMEM; + } + } + + aq->aura_id = pool_id; + aq->pool.stack_base = pool->stack->iova; + aq->pool.stack_caching = 1; + aq->pool.ena = 1; + aq->pool.buf_size = buf_size / 128; + aq->pool.stack_max_pages = stack_pages; + aq->pool.shift = ilog2(numptrs) - 8; + aq->pool.ptr_start = 0; + aq->pool.ptr_end = ~0ULL; + + /* Fill AQ info */ + aq->ctype = NPA_AQ_CTYPE_POOL; + aq->op = NPA_AQ_INSTOP_INIT; + + if (type != AURA_NIX_RQ) { + pool->page_pool = NULL; + return 0; + } + + sz = ALIGN(ALIGN(SKB_DATA_ALIGN(buf_size), OTX2_ALIGN), PAGE_SIZE); + pp_params.order = get_order(sz); + pp_params.flags = PP_FLAG_DMA_MAP; + pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs); + pp_params.nid = NUMA_NO_NODE; + pp_params.dev = pfvf->dev; + pp_params.dma_dir = DMA_FROM_DEVICE; + pool->page_pool = page_pool_create(&pp_params); + if (IS_ERR(pool->page_pool)) { + netdev_err(pfvf->netdev, "Creation of page pool failed\n"); + return PTR_ERR(pool->page_pool); + } + + return 0; +} + +static int cn20k_sq_aq_init(void *dev, u16 qidx, u8 chan_offset, u16 sqb_aura) +{ + struct nix_cn20k_aq_enq_req *aq; + struct otx2_nic *pfvf = dev; + + /* Get memory to put this msg */ + aq = otx2_mbox_alloc_msg_nix_cn20k_aq_enq(&pfvf->mbox); + if (!aq) + return -ENOMEM; + + aq->sq.cq = pfvf->hw.rx_queues + qidx; + aq->sq.max_sqe_size = NIX_MAXSQESZ_W16; /* 128 byte */ + aq->sq.cq_ena = 1; + aq->sq.ena = 1; + aq->sq.smq = otx2_get_smq_idx(pfvf, qidx); + aq->sq.smq_rr_weight = mtu_to_dwrr_weight(pfvf, pfvf->tx_max_pktlen); + aq->sq.default_chan = pfvf->hw.tx_chan_base + chan_offset; + aq->sq.sqe_stype = NIX_STYPE_STF; /* Cache SQB */ + aq->sq.sqb_aura = sqb_aura; + aq->sq.sq_int_ena = NIX_SQINT_BITS; + aq->sq.qint_idx = 0; + /* Due pipelining impact minimum 2000 unused SQ CQE's + * need to maintain to avoid CQ overflow. + */ + aq->sq.cq_limit = (SEND_CQ_SKID * 256) / (pfvf->qset.sqe_cnt); + + /* Fill AQ info */ + aq->qidx = qidx; + aq->ctype = NIX_AQ_CTYPE_SQ; + aq->op = NIX_AQ_INSTOP_INIT; + + return otx2_sync_mbox_msg(&pfvf->mbox); +} + +static struct dev_hw_ops cn20k_hw_ops = { + .pfaf_mbox_intr_handler = cn20k_pfaf_mbox_intr_handler, + .vfaf_mbox_intr_handler = cn20k_vfaf_mbox_intr_handler, + .pfvf_mbox_intr_handler = cn20k_pfvf_mbox_intr_handler, + .sq_aq_init = cn20k_sq_aq_init, + .sqe_flush = cn10k_sqe_flush, + .aura_freeptr = cn10k_aura_freeptr, + .refill_pool_ptrs = cn10k_refill_pool_ptrs, + .aura_aq_init = cn20k_aura_aq_init, + .pool_aq_init = cn20k_pool_aq_init, +}; + +void cn20k_init(struct otx2_nic *pfvf) +{ + pfvf->hw_ops = &cn20k_hw_ops; +} +EXPORT_SYMBOL(cn20k_init); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c index 902d6abaa3ec1..75ebb17419c4b 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c @@ -1368,6 +1368,13 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf) int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, int pool_id, int numptrs) +{ + return pfvf->hw_ops->aura_aq_init(pfvf, aura_id, pool_id, + numptrs); +} + +int otx2_aura_aq_init(struct otx2_nic *pfvf, int aura_id, + int pool_id, int numptrs) { struct npa_aq_enq_req *aq; struct otx2_pool *pool; @@ -1445,6 +1452,13 @@ int otx2_aura_init(struct otx2_nic *pfvf, int aura_id, int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id, int stack_pages, int numptrs, int buf_size, int type) +{ + return pfvf->hw_ops->pool_aq_init(pfvf, pool_id, stack_pages, numptrs, + buf_size, type); +} + +int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, + int stack_pages, int numptrs, int buf_size, int type) { struct page_pool_params pp_params = { 0 }; struct xsk_buff_pool *xsk_pool; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 1c8a3c078a647..e616a727a3a91 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include #include @@ -375,6 +376,11 @@ struct dev_hw_ops { irqreturn_t (*pfaf_mbox_intr_handler)(int irq, void *pf_irq); irqreturn_t (*vfaf_mbox_intr_handler)(int irq, void *pf_irq); irqreturn_t (*pfvf_mbox_intr_handler)(int irq, void *pf_irq); + int (*aura_aq_init)(struct otx2_nic *pfvf, int aura_id, + int pool_id, int numptrs); + int (*pool_aq_init)(struct otx2_nic *pfvf, u16 pool_id, + int stack_pages, int numptrs, int buf_size, + int type); }; #define CN10K_MCS_SA_PER_SC 4 @@ -527,7 +533,7 @@ struct otx2_nic { u32 nix_lmt_size; struct otx2_ptp *ptp; - struct hwtstamp_config tstamp; + struct kernel_hwtstamp_config tstamp; unsigned long rq_bmap; @@ -1059,6 +1065,10 @@ irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq); int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura); int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx); int otx2_set_hw_capabilities(struct otx2_nic *pfvf); +int otx2_aura_aq_init(struct otx2_nic *pfvf, int aura_id, + int pool_id, int numptrs); +int otx2_pool_aq_init(struct otx2_nic *pfvf, u16 pool_id, + int stack_pages, int numptrs, int buf_size, int type); /* RSS configuration APIs*/ int otx2_rss_init(struct otx2_nic *pfvf); @@ -1098,8 +1108,11 @@ int otx2_open(struct net_device *netdev); int otx2_stop(struct net_device *netdev); int otx2_set_real_num_queues(struct net_device *netdev, int tx_queues, int rx_queues); -int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd); -int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr); +int otx2_config_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config); +int otx2_config_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); /* MCAM filter related APIs */ int otx2_mcam_flow_init(struct otx2_nic *pf); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index e808995703cfd..a7feb4c392b36 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -2445,18 +2445,26 @@ static int otx2_config_hw_tx_tstamp(struct otx2_nic *pfvf, bool enable) return 0; } -int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) +int otx2_config_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct otx2_nic *pfvf = netdev_priv(netdev); + + *config = pfvf->tstamp; + return 0; +} +EXPORT_SYMBOL(otx2_config_hwtstamp_get); + +int otx2_config_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct otx2_nic *pfvf = netdev_priv(netdev); - struct hwtstamp_config config; if (!pfvf->ptp) return -ENODEV; - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: if (pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC) pfvf->flags &= ~OTX2_FLAG_PTP_ONESTEP_SYNC; @@ -2465,8 +2473,11 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) otx2_config_hw_tx_tstamp(pfvf, false); break; case HWTSTAMP_TX_ONESTEP_SYNC: - if (!test_bit(CN10K_PTP_ONESTEP, &pfvf->hw.cap_flag)) + if (!test_bit(CN10K_PTP_ONESTEP, &pfvf->hw.cap_flag)) { + NL_SET_ERR_MSG_MOD(extack, + "One-step time stamping is not supported"); return -ERANGE; + } pfvf->flags |= OTX2_FLAG_PTP_ONESTEP_SYNC; schedule_delayed_work(&pfvf->ptp->synctstamp_work, msecs_to_jiffies(500)); @@ -2478,7 +2489,7 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: otx2_config_hw_rx_tstamp(pfvf, false); break; @@ -2497,35 +2508,17 @@ int otx2_config_hwtstamp(struct net_device *netdev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: otx2_config_hw_rx_tstamp(pfvf, true); - config.rx_filter = HWTSTAMP_FILTER_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } - memcpy(&pfvf->tstamp, &config, sizeof(config)); + pfvf->tstamp = *config; - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; -} -EXPORT_SYMBOL(otx2_config_hwtstamp); - -int otx2_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) -{ - struct otx2_nic *pfvf = netdev_priv(netdev); - struct hwtstamp_config *cfg = &pfvf->tstamp; - - switch (cmd) { - case SIOCSHWTSTAMP: - return otx2_config_hwtstamp(netdev, req); - case SIOCGHWTSTAMP: - return copy_to_user(req->ifr_data, cfg, - sizeof(*cfg)) ? -EFAULT : 0; - default: - return -EOPNOTSUPP; - } + return 0; } -EXPORT_SYMBOL(otx2_ioctl); +EXPORT_SYMBOL(otx2_config_hwtstamp_set); static int otx2_do_set_vf_mac(struct otx2_nic *pf, int vf, const u8 *mac) { @@ -2942,7 +2935,6 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_features = otx2_set_features, .ndo_tx_timeout = otx2_tx_timeout, .ndo_get_stats64 = otx2_get_stats64, - .ndo_eth_ioctl = otx2_ioctl, .ndo_set_vf_mac = otx2_set_vf_mac, .ndo_set_vf_vlan = otx2_set_vf_vlan, .ndo_get_vf_config = otx2_get_vf_config, @@ -2951,6 +2943,8 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_xdp_xmit = otx2_xdp_xmit, .ndo_setup_tc = otx2_setup_tc, .ndo_set_vf_trust = otx2_ndo_set_vf_trust, + .ndo_hwtstamp_get = otx2_config_hwtstamp_get, + .ndo_hwtstamp_set = otx2_config_hwtstamp_set, }; int otx2_wq_init(struct otx2_nic *pf) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 25381f079b97d..f4fdbfba86676 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -534,8 +534,9 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_set_features = otx2vf_set_features, .ndo_get_stats64 = otx2_get_stats64, .ndo_tx_timeout = otx2_tx_timeout, - .ndo_eth_ioctl = otx2_ioctl, .ndo_setup_tc = otx2_setup_tc, + .ndo_hwtstamp_get = otx2_config_hwtstamp_get, + .ndo_hwtstamp_set = otx2_config_hwtstamp_set, }; static int otx2_vf_wq_init(struct otx2_nic *vf) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index a68cd3f0304c6..ad62984566397 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1727,6 +1727,13 @@ static int mlx4_en_get_num_flows(struct mlx4_en_priv *priv) } +static u32 mlx4_en_get_rx_ring_count(struct net_device *dev) +{ + struct mlx4_en_priv *priv = netdev_priv(dev); + + return priv->rx_ring_num; +} + static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -1743,9 +1750,6 @@ static int mlx4_en_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, return -EINVAL; switch (cmd->cmd) { - case ETHTOOL_GRXRINGS: - cmd->data = priv->rx_ring_num; - break; case ETHTOOL_GRXCLSRLCNT: cmd->rule_cnt = mlx4_en_get_num_flows(priv); break; @@ -2154,6 +2158,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = { .set_ringparam = mlx4_en_set_ringparam, .get_rxnfc = mlx4_en_get_rxnfc, .set_rxnfc = mlx4_en_set_rxnfc, + .get_rx_ring_count = mlx4_en_get_rx_ring_count, .get_rxfh_indir_size = mlx4_en_get_rxfh_indir_size, .get_rxfh_key_size = mlx4_en_get_rxfh_key_size, .get_rxfh = mlx4_en_get_rxfh, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 308b4458e0d44..81bf8908b8974 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2420,21 +2420,22 @@ static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) return 0; } -static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) +static int mlx4_en_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - struct hwtstamp_config config; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; /* device doesn't support time stamping */ - if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) + if (!(mdev->dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS)) { + NL_SET_ERR_MSG_MOD(extack, + "device doesn't support time stamping"); return -EINVAL; + } /* TX HW timestamp */ - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: break; @@ -2443,7 +2444,7 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) } /* RX HW timestamp */ - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: break; case HWTSTAMP_FILTER_ALL: @@ -2461,39 +2462,27 @@ static int mlx4_en_hwtstamp_set(struct net_device *dev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - config.rx_filter = HWTSTAMP_FILTER_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } if (mlx4_en_reset_config(dev, config, dev->features)) { - config.tx_type = HWTSTAMP_TX_OFF; - config.rx_filter = HWTSTAMP_FILTER_NONE; + config->tx_type = HWTSTAMP_TX_OFF; + config->rx_filter = HWTSTAMP_FILTER_NONE; } - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; + return 0; } -static int mlx4_en_hwtstamp_get(struct net_device *dev, struct ifreq *ifr) +static int mlx4_en_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) { struct mlx4_en_priv *priv = netdev_priv(dev); - return copy_to_user(ifr->ifr_data, &priv->hwtstamp_config, - sizeof(priv->hwtstamp_config)) ? -EFAULT : 0; -} - -static int mlx4_en_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - case SIOCSHWTSTAMP: - return mlx4_en_hwtstamp_set(dev, ifr); - case SIOCGHWTSTAMP: - return mlx4_en_hwtstamp_get(dev, ifr); - default: - return -EOPNOTSUPP; - } + *config = priv->hwtstamp_config; + return 0; } static netdev_features_t mlx4_en_fix_features(struct net_device *netdev, @@ -2560,7 +2549,7 @@ static int mlx4_en_set_features(struct net_device *netdev, } if (reset) { - ret = mlx4_en_reset_config(netdev, priv->hwtstamp_config, + ret = mlx4_en_reset_config(netdev, &priv->hwtstamp_config, features); if (ret) return ret; @@ -2844,7 +2833,6 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_set_mac_address = mlx4_en_set_mac, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = mlx4_en_change_mtu, - .ndo_eth_ioctl = mlx4_en_ioctl, .ndo_tx_timeout = mlx4_en_tx_timeout, .ndo_vlan_rx_add_vid = mlx4_en_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = mlx4_en_vlan_rx_kill_vid, @@ -2858,6 +2846,8 @@ static const struct net_device_ops mlx4_netdev_ops = { .ndo_features_check = mlx4_en_features_check, .ndo_set_tx_maxrate = mlx4_en_set_tx_maxrate, .ndo_bpf = mlx4_xdp, + .ndo_hwtstamp_get = mlx4_en_hwtstamp_get, + .ndo_hwtstamp_set = mlx4_en_hwtstamp_set, }; static const struct net_device_ops mlx4_netdev_ops_master = { @@ -3512,7 +3502,7 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, } int mlx4_en_reset_config(struct net_device *dev, - struct hwtstamp_config ts_config, + struct kernel_hwtstamp_config *ts_config, netdev_features_t features) { struct mlx4_en_priv *priv = netdev_priv(dev); @@ -3522,8 +3512,8 @@ int mlx4_en_reset_config(struct net_device *dev, int port_up = 0; int err = 0; - if (priv->hwtstamp_config.tx_type == ts_config.tx_type && - priv->hwtstamp_config.rx_filter == ts_config.rx_filter && + if (priv->hwtstamp_config.tx_type == ts_config->tx_type && + priv->hwtstamp_config.rx_filter == ts_config->rx_filter && !DEV_FEATURE_CHANGED(dev, features, NETIF_F_HW_VLAN_CTAG_RX) && !DEV_FEATURE_CHANGED(dev, features, NETIF_F_RXFCS)) return 0; /* Nothing to change */ @@ -3542,7 +3532,7 @@ int mlx4_en_reset_config(struct net_device *dev, mutex_lock(&mdev->state_lock); memcpy(&new_prof, priv->prof, sizeof(struct mlx4_en_port_profile)); - memcpy(&new_prof.hwtstamp_config, &ts_config, sizeof(ts_config)); + memcpy(&new_prof.hwtstamp_config, ts_config, sizeof(*ts_config)); err = mlx4_en_try_alloc_resources(priv, tmp, &new_prof, true); if (err) @@ -3560,7 +3550,7 @@ int mlx4_en_reset_config(struct net_device *dev, dev->features |= NETIF_F_HW_VLAN_CTAG_RX; else dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; - } else if (ts_config.rx_filter == HWTSTAMP_FILTER_NONE) { + } else if (ts_config->rx_filter == HWTSTAMP_FILTER_NONE) { /* RX time-stamping is OFF, update the RX vlan offload * to the latest wanted state */ @@ -3581,7 +3571,7 @@ int mlx4_en_reset_config(struct net_device *dev, * Regardless of the caller's choice, * Turn Off RX vlan offload in case of time-stamping is ON */ - if (ts_config.rx_filter != HWTSTAMP_FILTER_NONE) { + if (ts_config->rx_filter != HWTSTAMP_FILTER_NONE) { if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) en_warn(priv, "Turning off RX vlan offload since RX time-stamping is ON\n"); dev->features &= ~NETIF_F_HW_VLAN_CTAG_RX; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index ad0d91a751848..aab97694f86b3 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -388,7 +388,7 @@ struct mlx4_en_port_profile { u8 num_up; int rss_rings; int inline_thold; - struct hwtstamp_config hwtstamp_config; + struct kernel_hwtstamp_config hwtstamp_config; }; struct mlx4_en_profile { @@ -612,7 +612,7 @@ struct mlx4_en_priv { bool wol; struct device *ddev; struct hlist_head mac_hash[MLX4_EN_MAC_HASH_SIZE]; - struct hwtstamp_config hwtstamp_config; + struct kernel_hwtstamp_config hwtstamp_config; u32 counter_index; #ifdef CONFIG_MLX4_EN_DCB @@ -780,7 +780,7 @@ void mlx4_en_ptp_overflow_check(struct mlx4_en_dev *mdev); int mlx4_en_moderation_update(struct mlx4_en_priv *priv); int mlx4_en_reset_config(struct net_device *dev, - struct hwtstamp_config ts_config, + struct kernel_hwtstamp_config *ts_config, netdev_features_t new_features); void mlx4_en_update_pfc_stats_bitmap(struct mlx4_dev *dev, struct mlx4_en_stats_bitmap *stats_bitmap, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dev.c b/drivers/net/ethernet/mellanox/mlx5/core/dev.c index 891bbbbfbbf1a..64c04f52990fe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/dev.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/dev.c @@ -564,10 +564,14 @@ int mlx5_rescan_drivers_locked(struct mlx5_core_dev *dev) bool mlx5_same_hw_devs(struct mlx5_core_dev *dev, struct mlx5_core_dev *peer_dev) { - u64 fsystem_guid, psystem_guid; + u8 fsystem_guid[MLX5_SW_IMAGE_GUID_MAX_BYTES]; + u8 psystem_guid[MLX5_SW_IMAGE_GUID_MAX_BYTES]; + u8 flen; + u8 plen; - fsystem_guid = mlx5_query_nic_system_image_guid(dev); - psystem_guid = mlx5_query_nic_system_image_guid(peer_dev); + mlx5_query_nic_sw_system_image_guid(dev, fsystem_guid, &flen); + mlx5_query_nic_sw_system_image_guid(peer_dev, psystem_guid, &plen); - return (fsystem_guid && psystem_guid && fsystem_guid == psystem_guid); + return plen && flen && flen == plen && + !memcmp(fsystem_guid, psystem_guid, flen); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index a163f81f07c13..3ada7c16adfbc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -699,7 +699,7 @@ struct mlx5e_rq { struct mlx5e_rq_stats *stats; struct mlx5e_cq cq; struct mlx5e_cq_decomp cqd; - struct hwtstamp_config *tstamp; + struct kernel_hwtstamp_config *hwtstamp_config; struct mlx5_clock *clock; struct mlx5e_icosq *icosq; struct mlx5e_priv *priv; @@ -787,7 +787,6 @@ struct mlx5e_channel { /* control */ struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; - struct hwtstamp_config *tstamp; DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; int vec_ix; @@ -921,7 +920,7 @@ struct mlx5e_priv { u8 max_opened_tc; bool tx_ptp_opened; bool rx_ptp_opened; - struct hwtstamp_config tstamp; + struct kernel_hwtstamp_config hwtstamp_config; u16 q_counter[MLX5_SD_MAX_GROUP_SZ]; u16 drop_rq_q_counter; struct notifier_block events_nb; @@ -1030,8 +1029,11 @@ void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest, u64 *buf); void mlx5e_set_rx_mode_work(struct work_struct *work); -int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr); -int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr); +int mlx5e_hwtstamp_set(struct mlx5e_priv *priv, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +int mlx5e_hwtstamp_get(struct mlx5e_priv *priv, + struct kernel_hwtstamp_config *config); int mlx5e_modify_rx_cqe_compression_locked(struct mlx5e_priv *priv, bool val, bool rx_filter); int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto, @@ -1157,7 +1159,9 @@ extern const struct ethtool_ops mlx5e_ethtool_ops; int mlx5e_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, u32 *mkey); int mlx5e_create_mdev_resources(struct mlx5_core_dev *mdev, bool create_tises); void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev); -int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, +int mlx5e_modify_tirs_lb(struct mlx5_core_dev *mdev, bool enable_uc_lb, + bool enable_mc_lb); +int mlx5e_refresh_tirs(struct mlx5_core_dev *mdev, bool enable_uc_lb, bool enable_mc_lb); void mlx5e_mkey_set_relaxed_ordering(struct mlx5_core_dev *mdev, void *mkc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c index 0b1ac6e5c8900..8818f65d1fbc4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/devlink.c @@ -40,11 +40,8 @@ void mlx5e_destroy_devlink(struct mlx5e_dev *mlx5e_dev) static void mlx5e_devlink_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) { - u64 parent_id; - - parent_id = mlx5_query_nic_system_image_guid(dev); - ppid->id_len = sizeof(parent_id); - memcpy(ppid->id, &parent_id, sizeof(parent_id)); + BUILD_BUG_ON(MLX5_SW_IMAGE_GUID_MAX_BYTES > MAX_PHYS_ITEM_ID_LEN); + mlx5_query_nic_sw_system_image_guid(dev, ppid->id, &ppid->id_len); } int mlx5e_devlink_port_register(struct mlx5e_dev *mlx5e_dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c index 4e72ca8070e24..1de18c7e96ec9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "mapping.h" @@ -24,7 +25,8 @@ struct mapping_ctx { struct delayed_work dwork; struct list_head pending_list; spinlock_t pending_list_lock; /* Guards pending list */ - u64 id; + u8 id[MLX5_SW_IMAGE_GUID_MAX_BYTES]; + u8 id_len; u8 type; struct list_head list; refcount_t refcount; @@ -220,13 +222,15 @@ mapping_create(size_t data_size, u32 max_id, bool delayed_removal) } struct mapping_ctx * -mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal) +mapping_create_for_id(u8 *id, u8 id_len, u8 type, size_t data_size, u32 max_id, + bool delayed_removal) { struct mapping_ctx *ctx; mutex_lock(&shared_ctx_lock); list_for_each_entry(ctx, &shared_ctx_list, list) { - if (ctx->id == id && ctx->type == type) { + if (ctx->type == type && ctx->id_len == id_len && + !memcmp(id, ctx->id, id_len)) { if (refcount_inc_not_zero(&ctx->refcount)) goto unlock; break; @@ -237,7 +241,8 @@ mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delaye if (IS_ERR(ctx)) goto unlock; - ctx->id = id; + memcpy(ctx->id, id, id_len); + ctx->id_len = id_len; ctx->type = type; list_add(&ctx->list, &shared_ctx_list); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h index 4e2119f0f4c11..e86a103d58b9c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/mapping.h @@ -27,6 +27,7 @@ void mapping_destroy(struct mapping_ctx *ctx); /* adds mapping with an id or get an existing mapping with the same id */ struct mapping_ctx * -mapping_create_for_id(u64 id, u8 type, size_t data_size, u32 max_id, bool delayed_removal); +mapping_create_for_id(u8 *id, u8 id_len, u8 type, size_t data_size, u32 max_id, + bool delayed_removal); #endif /* __MLX5_MAPPING_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index c93ee969ea647..12e10feb30f06 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -713,7 +713,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params, rq->netdev = priv->netdev; rq->priv = priv; rq->clock = mdev->clock; - rq->tstamp = &priv->tstamp; + rq->hwtstamp_config = &priv->hwtstamp_config; rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); rq->stats = &c->priv->ptp_stats.rq; @@ -896,7 +896,6 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params, c->priv = priv; c->mdev = priv->mdev; - c->tstamp = &priv->tstamp; c->pdev = mlx5_core_dma_dev(priv->mdev); c->netdev = priv->netdev; c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h index 1b3c9648220b3..1c0e0a86a9ac8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h @@ -64,7 +64,6 @@ struct mlx5e_ptp { /* control */ struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; - struct hwtstamp_config *tstamp; DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES); struct mlx5_sq_bfreg *bfreg; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c index 9d1c677814e06..87a2ad69526d7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c @@ -30,15 +30,11 @@ static bool mlx5_esw_bridge_dev_same_hw(struct net_device *dev, struct mlx5_eswi { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5_core_dev *mdev, *esw_mdev; - u64 system_guid, esw_system_guid; mdev = priv->mdev; esw_mdev = esw->dev; - system_guid = mlx5_query_nic_system_image_guid(mdev); - esw_system_guid = mlx5_query_nic_system_image_guid(esw_mdev); - - return system_guid == esw_system_guid; + return mlx5_same_hw_devs(mdev, esw_mdev); } static struct net_device * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index b1415992ffa24..0686fbdd5a059 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -318,7 +318,8 @@ mlx5e_rx_reporter_diagnose_common_ptp_config(struct mlx5e_priv *priv, struct mlx struct devlink_fmsg *fmsg) { mlx5e_health_fmsg_named_obj_nest_start(fmsg, "PTP"); - devlink_fmsg_u32_pair_put(fmsg, "filter_type", priv->tstamp.rx_filter); + devlink_fmsg_u32_pair_put(fmsg, "filter_type", + priv->hwtstamp_config.rx_filter); mlx5e_rx_reporter_diagnose_generic_rq(&ptp_ch->rq, fmsg); mlx5e_health_fmsg_named_obj_nest_end(fmsg); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c index c96cbc4b0dbfa..88b0e1050d1af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c @@ -231,6 +231,8 @@ mlx5e_rss_create_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, rqtn, rss_inner); mlx5e_tir_builder_build_packet_merge(builder, pkt_merge_param); rss_tt = mlx5e_rss_get_tt_config(rss, tt); + mlx5e_tir_builder_build_self_lb_block(builder, rss->params.self_lb_blk, + rss->params.self_lb_blk); mlx5e_tir_builder_build_rss(builder, &rss->hash, &rss_tt, inner); err = mlx5e_tir_init(tir, builder, rss->mdev, true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h index 5fb03cd0a411b..17664757a561c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h @@ -23,6 +23,7 @@ struct mlx5e_rss_init_params { struct mlx5e_rss_params { bool inner_ft_support; u32 drop_rqn; + bool self_lb_blk; }; struct mlx5e_rss_params_traffic_type diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c index ac26a32845d0d..55c117b7d8c4a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c @@ -71,6 +71,8 @@ static int mlx5e_rx_res_rss_init_def(struct mlx5e_rx_res *res, rss_params = (struct mlx5e_rss_params) { .inner_ft_support = inner_ft_support, .drop_rqn = res->drop_rqn, + .self_lb_blk = + res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK, }; rss = mlx5e_rss_init(res->mdev, &rss_params, &init_params); @@ -104,6 +106,8 @@ int mlx5e_rx_res_rss_init(struct mlx5e_rx_res *res, u32 rss_idx, unsigned int in rss_params = (struct mlx5e_rss_params) { .inner_ft_support = inner_ft_support, .drop_rqn = res->drop_rqn, + .self_lb_blk = + res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK, }; rss = mlx5e_rss_init(res->mdev, &rss_params, &init_params); @@ -346,6 +350,7 @@ static struct mlx5e_rx_res *mlx5e_rx_res_alloc(struct mlx5_core_dev *mdev, unsig static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res) { bool inner_ft_support = res->features & MLX5E_RX_RES_FEATURE_INNER_FT; + bool self_lb_blk = res->features & MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK; struct mlx5e_tir_builder *builder; int err = 0; int ix; @@ -376,6 +381,8 @@ static int mlx5e_rx_res_channels_init(struct mlx5e_rx_res *res) mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt), inner_ft_support); mlx5e_tir_builder_build_packet_merge(builder, &res->pkt_merge_param); + mlx5e_tir_builder_build_self_lb_block(builder, self_lb_blk, + self_lb_blk); mlx5e_tir_builder_build_direct(builder); err = mlx5e_tir_init(&res->channels[ix].direct_tir, builder, res->mdev, true); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h index 65a857c215e1a..675780120a20d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h @@ -21,6 +21,7 @@ enum mlx5e_rx_res_features { MLX5E_RX_RES_FEATURE_INNER_FT = BIT(0), MLX5E_RX_RES_FEATURE_PTP = BIT(1), MLX5E_RX_RES_FEATURE_MULTI_VHCA = BIT(2), + MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK = BIT(3), }; /* Setup */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c index 896f718483c30..991f47050643d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/int_port.c @@ -307,7 +307,8 @@ mlx5e_tc_int_port_init(struct mlx5e_priv *priv) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_tc_int_port_priv *int_port_priv; - u64 mapping_id; + u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES]; + u8 id_len; if (!mlx5e_tc_int_port_supported(esw)) return NULL; @@ -316,9 +317,10 @@ mlx5e_tc_int_port_init(struct mlx5e_priv *priv) if (!int_port_priv) return NULL; - mapping_id = mlx5_query_nic_system_image_guid(priv->mdev); + mlx5_query_nic_sw_system_image_guid(priv->mdev, mapping_id, &id_len); - int_port_priv->metadata_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_INT_PORT, + int_port_priv->metadata_mapping = mapping_create_for_id(mapping_id, id_len, + MAPPING_TYPE_INT_PORT, sizeof(u32) * 2, (1 << ESW_VPORT_BITS) - 1, true); if (IS_ERR(int_port_priv->metadata_mapping)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c index 870d12364f99e..fc0e57403d254 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c @@ -2287,9 +2287,10 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, enum mlx5_flow_namespace_type ns_type, struct mlx5e_post_act *post_act) { + u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES]; struct mlx5_tc_ct_priv *ct_priv; struct mlx5_core_dev *dev; - u64 mapping_id; + u8 id_len; int err; dev = priv->mdev; @@ -2301,16 +2302,18 @@ mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains, if (!ct_priv) goto err_alloc; - mapping_id = mlx5_query_nic_system_image_guid(dev); + mlx5_query_nic_sw_system_image_guid(dev, mapping_id, &id_len); - ct_priv->zone_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_ZONE, + ct_priv->zone_mapping = mapping_create_for_id(mapping_id, id_len, + MAPPING_TYPE_ZONE, sizeof(u16), 0, true); if (IS_ERR(ct_priv->zone_mapping)) { err = PTR_ERR(ct_priv->zone_mapping); goto err_mapping_zone; } - ct_priv->labels_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_LABELS, + ct_priv->labels_mapping = mapping_create_for_id(mapping_id, id_len, + MAPPING_TYPE_LABELS, sizeof(u32) * 4, 0, true); if (IS_ERR(ct_priv->labels_mapping)) { err = PTR_ERR(ct_priv->labels_mapping); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c index 19499072f67f6..0b55e77f19c8d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c @@ -146,6 +146,31 @@ void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder) MLX5_SET(tirc, tirc, rx_hash_fn, MLX5_RX_HASH_FN_INVERTED_XOR8); } +static void mlx5e_tir_context_self_lb_block(void *tirc, bool enable_uc_lb, + bool enable_mc_lb) +{ + u8 lb_flags = 0; + + if (enable_uc_lb) + lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST; + if (enable_mc_lb) + lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST; + + MLX5_SET(tirc, tirc, self_lb_block, lb_flags); +} + +void mlx5e_tir_builder_build_self_lb_block(struct mlx5e_tir_builder *builder, + bool enable_uc_lb, + bool enable_mc_lb) +{ + void *tirc = mlx5e_tir_builder_get_tirc(builder); + + if (builder->modify) + MLX5_SET(modify_tir_in, builder->in, bitmask.self_lb_en, 1); + + mlx5e_tir_context_self_lb_block(tirc, enable_uc_lb, enable_mc_lb); +} + void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder) { void *tirc = mlx5e_tir_builder_get_tirc(builder); @@ -153,9 +178,7 @@ void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder) WARN_ON(builder->modify); MLX5_SET(tirc, tirc, tls_en, 1); - MLX5_SET(tirc, tirc, self_lb_block, - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST | - MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST); + mlx5e_tir_context_self_lb_block(tirc, true, true); } int mlx5e_tir_init(struct mlx5e_tir *tir, struct mlx5e_tir_builder *builder, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h index e8df3aaf6562f..958eeb959a192 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h @@ -35,6 +35,9 @@ void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder, const struct mlx5e_rss_params_traffic_type *rss_tt, bool inner); void mlx5e_tir_builder_build_direct(struct mlx5e_tir_builder *builder); +void mlx5e_tir_builder_build_self_lb_block(struct mlx5e_tir_builder *builder, + bool enable_uc_lb, + bool enable_mc_lb); void mlx5e_tir_builder_build_tls(struct mlx5e_tir_builder *builder); struct mlx5_core_dev; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c index 996fcdb5a29d0..da8c44f46edb1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c @@ -47,7 +47,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params rq->netdev = priv->netdev; rq->priv = priv; rq->clock = mdev->clock; - rq->tstamp = &priv->tstamp; + rq->hwtstamp_config = &priv->hwtstamp_config; rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); rq->stats = &priv->trap_stats.rq; @@ -144,7 +144,6 @@ static struct mlx5e_trap *mlx5e_open_trap(struct mlx5e_priv *priv) t->priv = priv; t->mdev = priv->mdev; - t->tstamp = &priv->tstamp; t->pdev = mlx5_core_dma_dev(priv->mdev); t->netdev = priv->netdev; t->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.hw_objs.mkey); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h index aa3f17658c6d4..394e917ea2b0a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.h @@ -22,7 +22,6 @@ struct mlx5e_trap { /* control */ struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; - struct hwtstamp_config *tstamp; DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); struct mlx5e_params params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 6760bb0336df9..7e191e1569e82 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -92,7 +92,7 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); void mlx5e_free_rx_descs(struct mlx5e_rq *rq); void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq); -static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) +static inline bool mlx5e_rx_hw_stamp(struct kernel_hwtstamp_config *config) { return config->rx_filter == HWTSTAMP_FILTER_ALL; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index 5d51600935a6f..80f9fc10877ad 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -179,7 +179,7 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) { const struct mlx5e_xdp_buff *_ctx = (void *)ctx; - if (unlikely(!mlx5e_rx_hw_stamp(_ctx->rq->tstamp))) + if (unlikely(!mlx5e_rx_hw_stamp(_ctx->rq->hwtstamp_config))) return -ENODATA; *timestamp = mlx5e_cqe_ts_to_ns(_ctx->rq->ptp_cyc2time, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index dbd88eb5c082a..5981c71cae2d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -71,7 +71,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c, rq->pdev = c->pdev; rq->netdev = c->netdev; rq->priv = c->priv; - rq->tstamp = c->tstamp; + rq->hwtstamp_config = &c->priv->hwtstamp_config; rq->clock = mdev->clock; rq->icosq = &c->icosq; rq->ix = c->ix; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c index 8565cfe8d7dce..38e7c77cc8514 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.c @@ -28,12 +28,15 @@ struct mlx5e_psp_tx { struct mlx5_flow_handle *rule; struct mutex mutex; /* Protect PSP TX steering */ u32 refcnt; + struct mlx5_fc *tx_counter; }; struct mlx5e_psp_rx_err { struct mlx5_flow_table *ft; struct mlx5_flow_handle *rule; - struct mlx5_flow_handle *drop_rule; + struct mlx5_flow_handle *auth_fail_rule; + struct mlx5_flow_handle *err_rule; + struct mlx5_flow_handle *bad_rule; struct mlx5_modify_hdr *copy_modify_hdr; }; @@ -50,6 +53,10 @@ struct mlx5e_accel_fs_psp_prot { struct mlx5e_accel_fs_psp { struct mlx5e_accel_fs_psp_prot fs_prot[ACCEL_FS_PSP_NUM_TYPES]; + struct mlx5_fc *rx_counter; + struct mlx5_fc *rx_auth_fail_counter; + struct mlx5_fc *rx_err_counter; + struct mlx5_fc *rx_bad_counter; }; struct mlx5e_psp_fs { @@ -72,9 +79,19 @@ static enum mlx5_traffic_types fs_psp2tt(enum accel_fs_psp_type i) static void accel_psp_fs_rx_err_del_rules(struct mlx5e_psp_fs *fs, struct mlx5e_psp_rx_err *rx_err) { - if (rx_err->drop_rule) { - mlx5_del_flow_rules(rx_err->drop_rule); - rx_err->drop_rule = NULL; + if (rx_err->bad_rule) { + mlx5_del_flow_rules(rx_err->bad_rule); + rx_err->bad_rule = NULL; + } + + if (rx_err->err_rule) { + mlx5_del_flow_rules(rx_err->err_rule); + rx_err->err_rule = NULL; + } + + if (rx_err->auth_fail_rule) { + mlx5_del_flow_rules(rx_err->auth_fail_rule); + rx_err->auth_fail_rule = NULL; } if (rx_err->rule) { @@ -117,6 +134,7 @@ static int accel_psp_fs_rx_err_add_rule(struct mlx5e_psp_fs *fs, { u8 action[MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)] = {}; struct mlx5_core_dev *mdev = fs->mdev; + struct mlx5_flow_destination dest[2]; struct mlx5_flow_act flow_act = {}; struct mlx5_modify_hdr *modify_hdr; struct mlx5_flow_handle *fte; @@ -147,10 +165,14 @@ static int accel_psp_fs_rx_err_add_rule(struct mlx5e_psp_fs *fs, accel_psp_setup_syndrome_match(spec, PSP_OK); /* create fte */ flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | - MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_COUNT; flow_act.modify_hdr = modify_hdr; - fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, - &fs_prot->default_dest, 1); + dest[0].type = fs_prot->default_dest.type; + dest[0].ft = fs_prot->default_dest.ft; + dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[1].counter = fs->rx_fs->rx_counter; + fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 2); if (IS_ERR(fte)) { err = PTR_ERR(fte); mlx5_core_err(mdev, "fail to add psp rx err copy rule err=%d\n", err); @@ -158,22 +180,69 @@ static int accel_psp_fs_rx_err_add_rule(struct mlx5e_psp_fs *fs, } rx_err->rule = fte; - /* add default drop rule */ + /* add auth fail drop rule */ memset(spec, 0, sizeof(*spec)); memset(&flow_act, 0, sizeof(flow_act)); + accel_psp_setup_syndrome_match(spec, PSP_ICV_FAIL); /* create fte */ - flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; - fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, NULL, 0); + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[0].counter = fs->rx_fs->rx_auth_fail_counter; + fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1); if (IS_ERR(fte)) { err = PTR_ERR(fte); - mlx5_core_err(mdev, "fail to add psp rx err drop rule err=%d\n", err); + mlx5_core_err(mdev, "fail to add psp rx auth fail drop rule err=%d\n", + err); goto out_drop_rule; } - rx_err->drop_rule = fte; + rx_err->auth_fail_rule = fte; + + /* add framing drop rule */ + memset(spec, 0, sizeof(*spec)); + memset(&flow_act, 0, sizeof(flow_act)); + accel_psp_setup_syndrome_match(spec, PSP_BAD_TRAILER); + /* create fte */ + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[0].counter = fs->rx_fs->rx_err_counter; + fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1); + if (IS_ERR(fte)) { + err = PTR_ERR(fte); + mlx5_core_err(mdev, "fail to add psp rx framing err drop rule err=%d\n", + err); + goto out_drop_auth_fail_rule; + } + rx_err->err_rule = fte; + + /* add misc. errors drop rule */ + memset(spec, 0, sizeof(*spec)); + memset(&flow_act, 0, sizeof(flow_act)); + /* create fte */ + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest[0].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest[0].counter = fs->rx_fs->rx_bad_counter; + fte = mlx5_add_flow_rules(rx_err->ft, spec, &flow_act, dest, 1); + if (IS_ERR(fte)) { + err = PTR_ERR(fte); + mlx5_core_err(mdev, "fail to add psp rx misc. err drop rule err=%d\n", + err); + goto out_drop_error_rule; + } + rx_err->bad_rule = fte; + rx_err->copy_modify_hdr = modify_hdr; goto out_spec; +out_drop_error_rule: + mlx5_del_flow_rules(rx_err->err_rule); + rx_err->err_rule = NULL; +out_drop_auth_fail_rule: + mlx5_del_flow_rules(rx_err->auth_fail_rule); + rx_err->auth_fail_rule = NULL; out_drop_rule: mlx5_del_flow_rules(rx_err->rule); rx_err->rule = NULL; @@ -461,6 +530,10 @@ static void accel_psp_fs_cleanup_rx(struct mlx5e_psp_fs *fs) return; accel_psp = fs->rx_fs; + mlx5_fc_destroy(fs->mdev, accel_psp->rx_bad_counter); + mlx5_fc_destroy(fs->mdev, accel_psp->rx_err_counter); + mlx5_fc_destroy(fs->mdev, accel_psp->rx_auth_fail_counter); + mlx5_fc_destroy(fs->mdev, accel_psp->rx_counter); for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) { fs_prot = &accel_psp->fs_prot[i]; mutex_destroy(&fs_prot->prot_mutex); @@ -474,7 +547,10 @@ static int accel_psp_fs_init_rx(struct mlx5e_psp_fs *fs) { struct mlx5e_accel_fs_psp_prot *fs_prot; struct mlx5e_accel_fs_psp *accel_psp; + struct mlx5_core_dev *mdev = fs->mdev; + struct mlx5_fc *flow_counter; enum accel_fs_psp_type i; + int err; accel_psp = kzalloc(sizeof(*accel_psp), GFP_KERNEL); if (!accel_psp) @@ -485,9 +561,68 @@ static int accel_psp_fs_init_rx(struct mlx5e_psp_fs *fs) mutex_init(&fs_prot->prot_mutex); } + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + mlx5_core_warn(mdev, + "fail to create psp rx flow counter err=%pe\n", + flow_counter); + err = PTR_ERR(flow_counter); + goto out_err; + } + accel_psp->rx_counter = flow_counter; + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + mlx5_core_warn(mdev, + "fail to create psp rx auth fail flow counter err=%pe\n", + flow_counter); + err = PTR_ERR(flow_counter); + goto out_counter_err; + } + accel_psp->rx_auth_fail_counter = flow_counter; + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + mlx5_core_warn(mdev, + "fail to create psp rx error flow counter err=%pe\n", + flow_counter); + err = PTR_ERR(flow_counter); + goto out_auth_fail_counter_err; + } + accel_psp->rx_err_counter = flow_counter; + + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + mlx5_core_warn(mdev, + "fail to create psp rx bad flow counter err=%pe\n", + flow_counter); + err = PTR_ERR(flow_counter); + goto out_err_counter_err; + } + accel_psp->rx_bad_counter = flow_counter; + fs->rx_fs = accel_psp; return 0; + +out_err_counter_err: + mlx5_fc_destroy(mdev, accel_psp->rx_err_counter); + accel_psp->rx_err_counter = NULL; +out_auth_fail_counter_err: + mlx5_fc_destroy(mdev, accel_psp->rx_auth_fail_counter); + accel_psp->rx_auth_fail_counter = NULL; +out_counter_err: + mlx5_fc_destroy(mdev, accel_psp->rx_counter); + accel_psp->rx_counter = NULL; +out_err: + for (i = 0; i < ACCEL_FS_PSP_NUM_TYPES; i++) { + fs_prot = &accel_psp->fs_prot[i]; + mutex_destroy(&fs_prot->prot_mutex); + } + kfree(accel_psp); + fs->rx_fs = NULL; + + return err; } void mlx5_accel_psp_fs_cleanup_rx_tables(struct mlx5e_priv *priv) @@ -532,6 +667,7 @@ static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs) { int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_destination dest = {}; struct mlx5_core_dev *mdev = fs->mdev; struct mlx5_flow_act flow_act = {}; u32 *in, *mc, *outer_headers_c; @@ -580,8 +716,11 @@ static int accel_psp_fs_tx_create_ft_table(struct mlx5e_psp_fs *fs) flow_act.crypto.type = MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_PSP; flow_act.flags |= FLOW_ACT_NO_APPEND; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_ALLOW | - MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT; - rule = mlx5_add_flow_rules(ft, spec, &flow_act, NULL, 0); + MLX5_FLOW_CONTEXT_ACTION_CRYPTO_ENCRYPT | + MLX5_FLOW_CONTEXT_ACTION_COUNT; + dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + dest.counter = tx_fs->tx_counter; + rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1); if (IS_ERR(rule)) { err = PTR_ERR(rule); mlx5_core_err(mdev, "PSP: fail to add psp tx flow rule, err = %d\n", err); @@ -650,6 +789,7 @@ static void accel_psp_fs_cleanup_tx(struct mlx5e_psp_fs *fs) if (!tx_fs) return; + mlx5_fc_destroy(fs->mdev, tx_fs->tx_counter); mutex_destroy(&tx_fs->mutex); WARN_ON(tx_fs->refcnt); kfree(tx_fs); @@ -658,10 +798,12 @@ static void accel_psp_fs_cleanup_tx(struct mlx5e_psp_fs *fs) static int accel_psp_fs_init_tx(struct mlx5e_psp_fs *fs) { + struct mlx5_core_dev *mdev = fs->mdev; struct mlx5_flow_namespace *ns; + struct mlx5_fc *flow_counter; struct mlx5e_psp_tx *tx_fs; - ns = mlx5_get_flow_namespace(fs->mdev, MLX5_FLOW_NAMESPACE_EGRESS_IPSEC); + ns = mlx5_get_flow_namespace(mdev, MLX5_FLOW_NAMESPACE_EGRESS_IPSEC); if (!ns) return -EOPNOTSUPP; @@ -669,12 +811,55 @@ static int accel_psp_fs_init_tx(struct mlx5e_psp_fs *fs) if (!tx_fs) return -ENOMEM; + flow_counter = mlx5_fc_create(mdev, false); + if (IS_ERR(flow_counter)) { + mlx5_core_warn(mdev, + "fail to create psp tx flow counter err=%pe\n", + flow_counter); + kfree(tx_fs); + return PTR_ERR(flow_counter); + } + tx_fs->tx_counter = flow_counter; mutex_init(&tx_fs->mutex); tx_fs->ns = ns; fs->tx_fs = tx_fs; return 0; } +static void +mlx5e_accel_psp_fs_get_stats_fill(struct mlx5e_priv *priv, + struct mlx5e_psp_stats *stats) +{ + struct mlx5e_psp_tx *tx_fs = priv->psp->fs->tx_fs; + struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_accel_fs_psp *accel_psp; + + accel_psp = (struct mlx5e_accel_fs_psp *)priv->psp->fs->rx_fs; + + if (tx_fs->tx_counter) + mlx5_fc_query(mdev, tx_fs->tx_counter, &stats->psp_tx_pkts, + &stats->psp_tx_bytes); + + if (accel_psp->rx_counter) + mlx5_fc_query(mdev, accel_psp->rx_counter, &stats->psp_rx_pkts, + &stats->psp_rx_bytes); + + if (accel_psp->rx_auth_fail_counter) + mlx5_fc_query(mdev, accel_psp->rx_auth_fail_counter, + &stats->psp_rx_pkts_auth_fail, + &stats->psp_rx_bytes_auth_fail); + + if (accel_psp->rx_err_counter) + mlx5_fc_query(mdev, accel_psp->rx_err_counter, + &stats->psp_rx_pkts_frame_err, + &stats->psp_rx_bytes_frame_err); + + if (accel_psp->rx_bad_counter) + mlx5_fc_query(mdev, accel_psp->rx_bad_counter, + &stats->psp_rx_pkts_drop, + &stats->psp_rx_bytes_drop); +} + void mlx5_accel_psp_fs_cleanup_tx_tables(struct mlx5e_priv *priv) { if (!priv->psp) @@ -849,12 +1034,30 @@ mlx5e_psp_key_rotate(struct psp_dev *psd, struct netlink_ext_ack *exack) return mlx5e_psp_rotate_key(priv->mdev); } +static void +mlx5e_psp_get_stats(struct psp_dev *psd, struct psp_dev_stats *stats) +{ + struct mlx5e_priv *priv = netdev_priv(psd->main_netdev); + struct mlx5e_psp_stats nstats; + + mlx5e_accel_psp_fs_get_stats_fill(priv, &nstats); + stats->rx_packets = nstats.psp_rx_pkts; + stats->rx_bytes = nstats.psp_rx_bytes; + stats->rx_auth_fail = nstats.psp_rx_pkts_auth_fail; + stats->rx_error = nstats.psp_rx_pkts_frame_err; + stats->rx_bad = nstats.psp_rx_pkts_drop; + stats->tx_packets = nstats.psp_tx_pkts; + stats->tx_bytes = nstats.psp_tx_bytes; + stats->tx_error = atomic_read(&priv->psp->tx_drop); +} + static struct psp_dev_ops mlx5_psp_ops = { .set_config = mlx5e_psp_set_config, .rx_spi_alloc = mlx5e_psp_rx_spi_alloc, .tx_key_add = mlx5e_psp_assoc_add, .tx_key_del = mlx5e_psp_assoc_del, .key_rotate = mlx5e_psp_key_rotate, + .get_stats = mlx5e_psp_get_stats, }; void mlx5e_psp_unregister(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h index 42bb671fb2cb3..6b62fef0d9a73 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp.h @@ -7,11 +7,27 @@ #include #include "en.h" +struct mlx5e_psp_stats { + u64 psp_rx_pkts; + u64 psp_rx_bytes; + u64 psp_rx_pkts_auth_fail; + u64 psp_rx_bytes_auth_fail; + u64 psp_rx_pkts_frame_err; + u64 psp_rx_bytes_frame_err; + u64 psp_rx_pkts_drop; + u64 psp_rx_bytes_drop; + u64 psp_tx_pkts; + u64 psp_tx_bytes; + u64 psp_tx_pkts_drop; + u64 psp_tx_bytes_drop; +}; + struct mlx5e_psp { struct psp_dev *psp; struct psp_dev_caps caps; struct mlx5e_psp_fs *fs; atomic_t tx_key_cnt; + atomic_t tx_drop; }; static inline bool mlx5_is_psp_device(struct mlx5_core_dev *mdev) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c index 828bff1137aff..c17ea0fcd8efe 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/psp_rxtx.c @@ -186,6 +186,7 @@ bool mlx5e_psp_handle_tx_skb(struct net_device *netdev, /* psp_encap of the packet */ if (!psp_dev_encapsulate(net, skb, psp_st->spi, psp_st->ver, 0)) { kfree_skb_reason(skb, SKB_DROP_REASON_PSP_OUTPUT); + atomic_inc(&priv->psp->tx_drop); return false; } if (skb_is_gso(skb)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 30424ccad584f..5a2ac7b6f2607 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -247,45 +247,43 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev) memset(res, 0, sizeof(*res)); } -int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb, - bool enable_mc_lb) +int mlx5e_modify_tirs_lb(struct mlx5_core_dev *mdev, bool enable_uc_lb, + bool enable_mc_lb) { - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_tir_builder *builder; struct mlx5e_tir *tir; - u8 lb_flags = 0; - int err = 0; - u32 tirn = 0; - int inlen; - void *in; + int err = 0; - inlen = MLX5_ST_SZ_BYTES(modify_tir_in); - in = kvzalloc(inlen, GFP_KERNEL); - if (!in) + builder = mlx5e_tir_builder_alloc(true); + if (!builder) return -ENOMEM; - if (enable_uc_lb) - lb_flags = MLX5_TIRC_SELF_LB_BLOCK_BLOCK_UNICAST; - - if (enable_mc_lb) - lb_flags |= MLX5_TIRC_SELF_LB_BLOCK_BLOCK_MULTICAST; - - if (lb_flags) - MLX5_SET(modify_tir_in, in, ctx.self_lb_block, lb_flags); - - MLX5_SET(modify_tir_in, in, bitmask.self_lb_en, 1); + mlx5e_tir_builder_build_self_lb_block(builder, enable_uc_lb, + enable_mc_lb); mutex_lock(&mdev->mlx5e_res.hw_objs.td.list_lock); list_for_each_entry(tir, &mdev->mlx5e_res.hw_objs.td.tirs_list, list) { - tirn = tir->tirn; - err = mlx5_core_modify_tir(mdev, tirn, in); - if (err) + err = mlx5e_tir_modify(tir, builder); + if (err) { + mlx5_core_err(mdev, + "modify tir(0x%x) enable_lb uc(%d) mc(%d) failed, %d\n", + mlx5e_tir_get_tirn(tir), + enable_uc_lb, enable_mc_lb, err); break; + } } mutex_unlock(&mdev->mlx5e_res.hw_objs.td.list_lock); - kvfree(in); - if (err) - netdev_err(priv->netdev, "refresh tir(0x%x) failed, %d\n", tirn, err); + mlx5e_tir_builder_free(builder); return err; } + +int mlx5e_refresh_tirs(struct mlx5_core_dev *mdev, bool enable_uc_lb, + bool enable_mc_lb) +{ + if (MLX5_CAP_GEN(mdev, tis_tir_td_order)) + return 0; /* refresh not needed */ + + return mlx5e_modify_tirs_lb(mdev, enable_uc_lb, enable_mc_lb); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 893e1380a7c97..939e274779b39 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -2271,7 +2271,7 @@ static int set_pflag_rx_cqe_compress(struct net_device *netdev, if (!MLX5_CAP_GEN(mdev, cqe_compression)) return -EOPNOTSUPP; - rx_filter = priv->tstamp.rx_filter != HWTSTAMP_FILTER_NONE; + rx_filter = priv->hwtstamp_config.rx_filter != HWTSTAMP_FILTER_NONE; err = mlx5e_modify_rx_cqe_compression_locked(priv, enable, rx_filter); if (err) return err; @@ -2492,21 +2492,18 @@ static int mlx5e_set_rxfh_fields(struct net_device *dev, return mlx5e_ethtool_set_rxfh_fields(priv, cmd, extack); } +static u32 mlx5e_get_rx_ring_count(struct net_device *dev) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + + return priv->channels.params.num_channels; +} + static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = netdev_priv(dev); - /* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part - * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc, - * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc - * is compiled out via CONFIG_MLX5_EN_RXNFC=n. - */ - if (info->cmd == ETHTOOL_GRXRINGS) { - info->data = priv->channels.params.num_channels; - return 0; - } - return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } @@ -2766,6 +2763,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .remove_rxfh_context = mlx5e_remove_rxfh_context, .get_rxnfc = mlx5e_get_rxnfc, .set_rxnfc = mlx5e_set_rxnfc, + .get_rx_ring_count = mlx5e_get_rx_ring_count, .get_tunable = mlx5e_get_tunable, .set_tunable = mlx5e_set_tunable, .get_pause_stats = mlx5e_get_pause_stats, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 5e17eae81f4b3..e537df6707583 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -735,7 +735,7 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param rq->pdev = c->pdev; rq->netdev = c->netdev; rq->priv = c->priv; - rq->tstamp = c->tstamp; + rq->hwtstamp_config = &c->priv->hwtstamp_config; rq->clock = mdev->clock; rq->icosq = &c->icosq; rq->ix = c->ix; @@ -2816,7 +2816,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->priv = priv; c->mdev = mdev; - c->tstamp = &priv->tstamp; c->ix = ix; c->vec_ix = vec_ix; c->sd_ix = mlx5_sd_ch_ix_get_dev_ix(mdev, ix); @@ -3370,12 +3369,12 @@ static int mlx5e_switch_priv_params(struct mlx5e_priv *priv, } static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv, + struct mlx5e_channels *old_chs, struct mlx5e_channels *new_chs, mlx5e_fp_preactivate preactivate, void *context) { struct net_device *netdev = priv->netdev; - struct mlx5e_channels old_chs; int carrier_ok; int err = 0; @@ -3384,7 +3383,6 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv, mlx5e_deactivate_priv_channels(priv); - old_chs = priv->channels; priv->channels = *new_chs; /* New channels are ready to roll, call the preactivate hook if needed @@ -3393,12 +3391,13 @@ static int mlx5e_switch_priv_channels(struct mlx5e_priv *priv, if (preactivate) { err = preactivate(priv, context); if (err) { - priv->channels = old_chs; + priv->channels = *old_chs; goto out; } } - mlx5e_close_channels(&old_chs); + if (!MLX5_CAP_GEN(priv->mdev, tis_tir_td_order)) + mlx5e_close_channels(old_chs); priv->profile->update_rx(priv); mlx5e_selq_apply(&priv->selq); @@ -3417,16 +3416,20 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv, mlx5e_fp_preactivate preactivate, void *context, bool reset) { - struct mlx5e_channels *new_chs; + struct mlx5e_channels *old_chs, *new_chs; int err; reset &= test_bit(MLX5E_STATE_OPENED, &priv->state); if (!reset) return mlx5e_switch_priv_params(priv, params, preactivate, context); + old_chs = kzalloc(sizeof(*old_chs), GFP_KERNEL); new_chs = kzalloc(sizeof(*new_chs), GFP_KERNEL); - if (!new_chs) - return -ENOMEM; + if (!old_chs || !new_chs) { + err = -ENOMEM; + goto err_free_chs; + } + new_chs->params = *params; mlx5e_selq_prepare_params(&priv->selq, &new_chs->params); @@ -3435,11 +3438,18 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv, if (err) goto err_cancel_selq; - err = mlx5e_switch_priv_channels(priv, new_chs, preactivate, context); + *old_chs = priv->channels; + + err = mlx5e_switch_priv_channels(priv, old_chs, new_chs, + preactivate, context); if (err) goto err_close; + if (MLX5_CAP_GEN(priv->mdev, tis_tir_td_order)) + mlx5e_close_channels(old_chs); + kfree(new_chs); + kfree(old_chs); return 0; err_close: @@ -3447,7 +3457,9 @@ int mlx5e_safe_switch_params(struct mlx5e_priv *priv, err_cancel_selq: mlx5e_selq_cancel(&priv->selq); +err_free_chs: kfree(new_chs); + kfree(old_chs); return err; } @@ -3458,8 +3470,8 @@ int mlx5e_safe_reopen_channels(struct mlx5e_priv *priv) void mlx5e_timestamp_init(struct mlx5e_priv *priv) { - priv->tstamp.tx_type = HWTSTAMP_TX_OFF; - priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE; + priv->hwtstamp_config.tx_type = HWTSTAMP_TX_OFF; + priv->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; } static void mlx5e_modify_admin_state(struct mlx5_core_dev *mdev, @@ -4012,6 +4024,11 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) s->rx_bytes += rq_stats->bytes; s->multicast += rq_stats->mcast_packets; } + +#ifdef CONFIG_MLX5_EN_PSP + if (priv->psp) + s->tx_dropped += atomic_read(&priv->psp->tx_drop); +#endif } void @@ -4754,22 +4771,23 @@ static int mlx5e_hwstamp_config_ptp_rx(struct mlx5e_priv *priv, bool ptp_rx) &new_params.ptp_rx, true); } -int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) +int mlx5e_hwtstamp_set(struct mlx5e_priv *priv, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config config; bool rx_cqe_compress_def; bool ptp_rx; int err; if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) || - (mlx5_clock_get_ptp_index(priv->mdev) == -1)) + (mlx5_clock_get_ptp_index(priv->mdev) == -1)) { + NL_SET_ERR_MSG_MOD(extack, + "Timestamps are not supported on this device"); return -EOPNOTSUPP; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; + } /* TX HW timestamp */ - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: break; @@ -4781,7 +4799,7 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) rx_cqe_compress_def = priv->channels.params.rx_cqe_compress_def; /* RX HW timestamp */ - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: ptp_rx = false; break; @@ -4800,7 +4818,7 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: - config.rx_filter = HWTSTAMP_FILTER_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; /* ptp_rx is set if both HW TS is set and CQE * compression is set */ @@ -4813,47 +4831,50 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) if (!mlx5e_profile_feature_cap(priv->profile, PTP_RX)) err = mlx5e_hwstamp_config_no_ptp_rx(priv, - config.rx_filter != HWTSTAMP_FILTER_NONE); + config->rx_filter != HWTSTAMP_FILTER_NONE); else err = mlx5e_hwstamp_config_ptp_rx(priv, ptp_rx); if (err) goto err_unlock; - memcpy(&priv->tstamp, &config, sizeof(config)); + priv->hwtstamp_config = *config; mutex_unlock(&priv->state_lock); /* might need to fix some features */ netdev_update_features(priv->netdev); - return copy_to_user(ifr->ifr_data, &config, - sizeof(config)) ? -EFAULT : 0; + return 0; err_unlock: mutex_unlock(&priv->state_lock); return err; } -int mlx5e_hwstamp_get(struct mlx5e_priv *priv, struct ifreq *ifr) +static int mlx5e_hwtstamp_set_ndo(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config *cfg = &priv->tstamp; + struct mlx5e_priv *priv = netdev_priv(netdev); + return mlx5e_hwtstamp_set(priv, config, extack); +} + +int mlx5e_hwtstamp_get(struct mlx5e_priv *priv, + struct kernel_hwtstamp_config *config) +{ if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz)) return -EOPNOTSUPP; - return copy_to_user(ifr->ifr_data, cfg, sizeof(*cfg)) ? -EFAULT : 0; + *config = priv->hwtstamp_config; + + return 0; } -static int mlx5e_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +static int mlx5e_hwtstamp_get_ndo(struct net_device *dev, + struct kernel_hwtstamp_config *config) { struct mlx5e_priv *priv = netdev_priv(dev); - switch (cmd) { - case SIOCSHWTSTAMP: - return mlx5e_hwstamp_set(priv, ifr); - case SIOCGHWTSTAMP: - return mlx5e_hwstamp_get(priv, ifr); - default: - return -EOPNOTSUPP; - } + return mlx5e_hwtstamp_get(priv, config); } #ifdef CONFIG_MLX5_ESWITCH @@ -5294,13 +5315,14 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_set_features = mlx5e_set_features, .ndo_fix_features = mlx5e_fix_features, .ndo_change_mtu = mlx5e_change_nic_mtu, - .ndo_eth_ioctl = mlx5e_ioctl, .ndo_set_tx_maxrate = mlx5e_set_tx_maxrate, .ndo_features_check = mlx5e_features_check, .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, .ndo_xdp_xmit = mlx5e_xdp_xmit, .ndo_xsk_wakeup = mlx5e_xsk_wakeup, + .ndo_hwtstamp_get = mlx5e_hwtstamp_get_ndo, + .ndo_hwtstamp_set = mlx5e_hwtstamp_set_ndo, #ifdef CONFIG_MLX5_EN_ARFS .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif @@ -6145,7 +6167,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) static int mlx5e_update_nic_rx(struct mlx5e_priv *priv) { - return mlx5e_refresh_tirs(priv, false, false); + return mlx5e_refresh_tirs(priv->mdev, false, false); } static const struct mlx5e_profile mlx5e_nic_profile = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 687cf123211d7..1f6930c774378 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -1604,7 +1604,7 @@ static inline bool mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe, stats->lro_bytes += cqe_bcnt; } - if (unlikely(mlx5e_rx_hw_stamp(rq->tstamp))) + if (unlikely(mlx5e_rx_hw_stamp(rq->hwtstamp_config))) skb_hwtstamps(skb)->hwtstamp = mlx5e_cqe_ts_to_ns(rq->ptp_cyc2time, rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); @@ -2656,7 +2656,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, u32 cqe_bcnt, struct sk_buff *skb) { - struct hwtstamp_config *tstamp; struct mlx5e_rq_stats *stats; struct net_device *netdev; struct mlx5e_priv *priv; @@ -2680,7 +2679,6 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, } priv = mlx5i_epriv(netdev); - tstamp = &priv->tstamp; stats = &priv->channel_stats[rq->ix]->rq; flags_rqpn = be32_to_cpu(cqe->flags_rqpn); @@ -2716,7 +2714,7 @@ static inline void mlx5i_complete_rx_cqe(struct mlx5e_rq *rq, stats->csum_none++; } - if (unlikely(mlx5e_rx_hw_stamp(tstamp))) + if (unlikely(mlx5e_rx_hw_stamp(&priv->hwtstamp_config))) skb_hwtstamps(skb)->hwtstamp = mlx5e_cqe_ts_to_ns(rq->ptp_cyc2time, rq->clock, get_cqe_ts(cqe)); skb_record_rx_queue(skb, rq->ix); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c index 2f7a543feca62..fcad464bc4d58 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c @@ -214,7 +214,7 @@ static int mlx5e_test_loopback_setup(struct mlx5e_priv *priv, return err; } - err = mlx5e_refresh_tirs(priv, true, false); + err = mlx5e_modify_tirs_lb(priv->mdev, true, false); if (err) goto out; @@ -243,7 +243,7 @@ static void mlx5e_test_loopback_cleanup(struct mlx5e_priv *priv, mlx5_nic_vport_update_local_lb(priv->mdev, false); dev_remove_pack(&lbtp->pt); - mlx5e_refresh_tirs(priv, false, false); + mlx5e_modify_tirs_lb(priv->mdev, false, false); } static int mlx5e_cond_loopback(struct mlx5e_priv *priv) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 00c2763e57ca1..a8773b2342c2a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -3614,15 +3614,11 @@ static bool same_port_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv bool mlx5e_same_hw_devs(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *fmdev, *pmdev; - u64 fsystem_guid, psystem_guid; fmdev = priv->mdev; pmdev = peer_priv->mdev; - fsystem_guid = mlx5_query_nic_system_image_guid(fmdev); - psystem_guid = mlx5_query_nic_system_image_guid(pmdev); - - return (fsystem_guid == psystem_guid); + return mlx5_same_hw_devs(fmdev, pmdev); } static int @@ -5237,10 +5233,11 @@ static void mlx5e_tc_nic_destroy_miss_table(struct mlx5e_priv *priv) int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { struct mlx5e_tc_table *tc = mlx5e_fs_get_tc(priv->fs); + u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES]; struct mlx5_core_dev *dev = priv->mdev; struct mapping_ctx *chains_mapping; struct mlx5_chains_attr attr = {}; - u64 mapping_id; + u8 id_len; int err; mlx5e_mod_hdr_tbl_init(&tc->mod_hdr); @@ -5256,11 +5253,13 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) lockdep_set_class(&tc->ht.mutex, &tc_ht_lock_key); lockdep_init_map(&tc->ht.run_work.lockdep_map, "tc_ht_wq_key", &tc_ht_wq_key, 0); - mapping_id = mlx5_query_nic_system_image_guid(dev); + mlx5_query_nic_sw_system_image_guid(dev, mapping_id, &id_len); - chains_mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN, + chains_mapping = mapping_create_for_id(mapping_id, id_len, + MAPPING_TYPE_CHAIN, sizeof(struct mlx5_mapped_obj), - MLX5E_TC_TABLE_CHAIN_TAG_MASK, true); + MLX5E_TC_TABLE_CHAIN_TAG_MASK, + true); if (IS_ERR(chains_mapping)) { err = PTR_ERR(chains_mapping); @@ -5391,14 +5390,15 @@ void mlx5e_tc_ht_cleanup(struct rhashtable *tc_ht) int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) { const size_t sz_enc_opts = sizeof(struct tunnel_match_enc_opts); + u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES]; struct mlx5_devcom_match_attr attr = {}; struct netdev_phys_item_id ppid; struct mlx5e_rep_priv *rpriv; struct mapping_ctx *mapping; struct mlx5_eswitch *esw; struct mlx5e_priv *priv; - u64 mapping_id; int err = 0; + u8 id_len; rpriv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv); priv = netdev_priv(rpriv->netdev); @@ -5416,9 +5416,9 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) uplink_priv->tc_psample = mlx5e_tc_sample_init(esw, uplink_priv->post_act); - mapping_id = mlx5_query_nic_system_image_guid(esw->dev); + mlx5_query_nic_sw_system_image_guid(esw->dev, mapping_id, &id_len); - mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL, + mapping = mapping_create_for_id(mapping_id, id_len, MAPPING_TYPE_TUNNEL, sizeof(struct tunnel_match_key), TUNNEL_INFO_BITS_MASK, true); @@ -5431,8 +5431,10 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) /* Two last values are reserved for stack devices slow path table mark * and bridge ingress push mark. */ - mapping = mapping_create_for_id(mapping_id, MAPPING_TYPE_TUNNEL_ENC_OPTS, - sz_enc_opts, ENC_OPTS_BITS_MASK - 2, true); + mapping = mapping_create_for_id(mapping_id, id_len, + MAPPING_TYPE_TUNNEL_ENC_OPTS, + sz_enc_opts, ENC_OPTS_BITS_MASK - 2, + true); if (IS_ERR(mapping)) { err = PTR_ERR(mapping); goto err_enc_opts_mapping; @@ -5453,7 +5455,7 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv) err = netif_get_port_parent_id(priv->netdev, &ppid, false); if (!err) { - memcpy(&attr.key.val, &ppid.id, sizeof(attr.key.val)); + memcpy(&attr.key.buf, &ppid.id, ppid.id_len); attr.flags = MLX5_DEVCOM_MATCH_FLAGS_NS; attr.net = mlx5_core_net(esw->dev); mlx5_esw_offloads_devcom_init(esw, &attr); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c index 0091ba697baec..250af09b5af23 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/adj_vport.c @@ -4,13 +4,8 @@ #include "fs_core.h" #include "eswitch.h" -enum { - MLX5_ADJ_VPORT_DISCONNECT = 0x0, - MLX5_ADJ_VPORT_CONNECT = 0x1, -}; - -static int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, - u16 vport, bool connect) +int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, u16 vport, + bool connect) { u32 in[MLX5_ST_SZ_DW(modify_vport_state_in)] = {}; @@ -24,7 +19,7 @@ static int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, MLX5_SET(modify_vport_state_in, in, egress_connect_valid, 1); MLX5_SET(modify_vport_state_in, in, ingress_connect, connect); MLX5_SET(modify_vport_state_in, in, egress_connect, connect); - + MLX5_SET(modify_vport_state_in, in, admin_state, connect); return mlx5_cmd_exec_in(dev, modify_vport_state, in); } @@ -96,7 +91,6 @@ static int mlx5_esw_adj_vport_create(struct mlx5_eswitch *esw, u16 vhca_id, if (err) goto acl_ns_remove; - mlx5_esw_adj_vport_modify(esw->dev, vport_num, MLX5_ADJ_VPORT_CONNECT); return 0; acl_ns_remove: @@ -117,8 +111,7 @@ static void mlx5_esw_adj_vport_destroy(struct mlx5_eswitch *esw, esw_debug(esw->dev, "Destroying adjacent vport %d for vhca_id 0x%x\n", vport_num, vport->vhca_id); - mlx5_esw_adj_vport_modify(esw->dev, vport_num, - MLX5_ADJ_VPORT_DISCONNECT); + mlx5_esw_offloads_rep_remove(esw, vport); mlx5_fs_vport_egress_acl_ns_remove(esw->dev->priv.steering, vport->index); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c index cf88a106d80d7..89a58dee50b3a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c @@ -7,11 +7,7 @@ static void mlx5_esw_get_port_parent_id(struct mlx5_core_dev *dev, struct netdev_phys_item_id *ppid) { - u64 parent_id; - - parent_id = mlx5_query_nic_system_image_guid(dev); - ppid->id_len = sizeof(parent_id); - memcpy(ppid->id, &parent_id, sizeof(parent_id)); + mlx5_query_nic_sw_system_image_guid(dev, ppid->id, &ppid->id_len); } static bool mlx5_esw_devlink_port_supported(struct mlx5_eswitch *esw, u16 vport_num) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index e2ffb87b94cbe..25af8bd7f0779 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -875,13 +875,10 @@ static int esw_vport_setup(struct mlx5_eswitch *esw, struct mlx5_vport *vport) vport_num, 1, vport->info.link_state); - /* Host PF has its own mac/guid. */ - if (vport_num) { - mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, - vport->info.mac); - mlx5_modify_nic_vport_node_guid(esw->dev, vport_num, - vport->info.node_guid); - } + mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, + vport->info.mac); + mlx5_query_nic_vport_node_guid(esw->dev, vport_num, true, + &vport->info.node_guid); flags = (vport->info.vlan || vport->info.qos) ? SET_VLAN_STRIP | SET_VLAN_INSERT : 0; @@ -947,12 +944,6 @@ int mlx5_esw_vport_enable(struct mlx5_eswitch *esw, struct mlx5_vport *vport, goto err_vhca_mapping; } - /* External controller host PF has factory programmed MAC. - * Read it from the device. - */ - if (mlx5_core_is_ecpf(esw->dev) && vport_num == MLX5_VPORT_PF) - mlx5_query_nic_vport_mac_address(esw->dev, vport_num, true, vport->info.mac); - esw_vport_change_handle_locked(vport); esw->enabled_vports++; @@ -2235,6 +2226,9 @@ int mlx5_eswitch_get_vport_config(struct mlx5_eswitch *esw, ivi->vf = vport - 1; mutex_lock(&esw->state_lock); + + mlx5_query_nic_vport_mac_address(esw->dev, vport, true, + evport->info.mac); ether_addr_copy(ivi->mac, evport->info.mac); ivi->linkstate = evport->info.link_state; ivi->vlan = evport->info.vlan; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 16eb99aba2a7e..beaec450a7343 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -264,6 +264,9 @@ struct mlx5_eswitch_fdb { struct offloads_fdb { struct mlx5_flow_namespace *ns; + struct mlx5_flow_table *drop_root; + struct mlx5_flow_handle *drop_root_rule; + struct mlx5_fc *drop_root_fc; struct mlx5_flow_table *tc_miss_table; struct mlx5_flow_table *slow_fdb; struct mlx5_flow_group *send_to_vport_grp; @@ -392,6 +395,7 @@ struct mlx5_eswitch { struct mlx5_esw_offload offloads; u32 last_vport_idx; int mode; + bool offloads_inactive; u16 manager_vport; u16 first_host_vport; u8 num_peers; @@ -634,6 +638,8 @@ const u32 *mlx5_esw_query_functions(struct mlx5_core_dev *dev); void mlx5_esw_adjacent_vhcas_setup(struct mlx5_eswitch *esw); void mlx5_esw_adjacent_vhcas_cleanup(struct mlx5_eswitch *esw); +int mlx5_esw_adj_vport_modify(struct mlx5_core_dev *dev, u16 vport, + bool connect); #define MLX5_DEBUG_ESWITCH_MASK BIT(3) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 44a142a041b2f..8ebca0d17f655 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1577,6 +1577,7 @@ esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb) attr.max_grp_num = esw->params.large_group_num; attr.default_ft = miss_fdb; attr.mapping = esw->offloads.reg_c0_obj_pool; + attr.fs_base_prio = FDB_BYPASS_PATH; chains = mlx5_chains_create(dev, &attr); if (IS_ERR(chains)) { @@ -2355,6 +2356,131 @@ static void esw_mode_change(struct mlx5_eswitch *esw, u16 mode) mlx5_devcom_comp_unlock(esw->dev->priv.hca_devcom_comp); } +static void mlx5_esw_fdb_drop_destroy(struct mlx5_eswitch *esw) +{ + if (!esw->fdb_table.offloads.drop_root) + return; + + esw_debug(esw->dev, "Destroying FDB drop root table %#x fc %#x\n", + esw->fdb_table.offloads.drop_root->id, + esw->fdb_table.offloads.drop_root_fc->id); + mlx5_del_flow_rules(esw->fdb_table.offloads.drop_root_rule); + /* Don't free flow counter here, can be reused on a later activation */ + mlx5_destroy_flow_table(esw->fdb_table.offloads.drop_root); + esw->fdb_table.offloads.drop_root_rule = NULL; + esw->fdb_table.offloads.drop_root = NULL; +} + +static int mlx5_esw_fdb_drop_create(struct mlx5_eswitch *esw) +{ + struct mlx5_flow_destination drop_fc_dst = {}; + struct mlx5_flow_table_attr ft_attr = {}; + struct mlx5_flow_destination *dst = NULL; + struct mlx5_core_dev *dev = esw->dev; + struct mlx5_flow_namespace *root_ns; + struct mlx5_flow_act flow_act = {}; + struct mlx5_flow_handle *flow_rule; + struct mlx5_flow_table *table; + int err = 0, dst_num = 0; + + if (esw->fdb_table.offloads.drop_root) + return 0; + + root_ns = esw->fdb_table.offloads.ns; + + ft_attr.prio = FDB_DROP_ROOT; + ft_attr.max_fte = 1; + ft_attr.autogroup.max_num_groups = 1; + table = mlx5_create_auto_grouped_flow_table(root_ns, &ft_attr); + if (IS_ERR(table)) { + esw_warn(dev, "Failed to create fdb drop root table, err %pe\n", + table); + return PTR_ERR(table); + } + + /* Drop FC reusable, create once on first deactivation of FDB */ + if (!esw->fdb_table.offloads.drop_root_fc) { + struct mlx5_fc *counter = mlx5_fc_create(dev, 0); + + err = PTR_ERR_OR_ZERO(counter); + if (err) + esw_warn(esw->dev, "create fdb drop fc err %d\n", err); + else + esw->fdb_table.offloads.drop_root_fc = counter; + } + + flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; + + if (esw->fdb_table.offloads.drop_root_fc) { + flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_COUNT; + drop_fc_dst.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; + drop_fc_dst.counter = esw->fdb_table.offloads.drop_root_fc; + dst = &drop_fc_dst; + dst_num++; + } + + flow_rule = mlx5_add_flow_rules(table, NULL, &flow_act, dst, dst_num); + err = PTR_ERR_OR_ZERO(flow_rule); + if (err) { + esw_warn(esw->dev, + "fs offloads: Failed to add vport rx drop rule err %d\n", + err); + goto err_flow_rule; + } + + esw->fdb_table.offloads.drop_root = table; + esw->fdb_table.offloads.drop_root_rule = flow_rule; + esw_debug(esw->dev, "Created FDB drop root table %#x fc %#x\n", + table->id, dst ? dst->counter->id : 0); + return 0; + +err_flow_rule: + /* no need to free drop fc, esw_offloads_steering_cleanup will do it */ + mlx5_destroy_flow_table(table); + return err; +} + +static void mlx5_esw_fdb_active(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + unsigned long i; + + mlx5_esw_fdb_drop_destroy(esw); + mlx5_mpfs_enable(esw->dev); + + mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) { + if (!vport->adjacent) + continue; + esw_debug(esw->dev, "Connecting vport %d to eswitch\n", + vport->vport); + mlx5_esw_adj_vport_modify(esw->dev, vport->vport, true); + } + + esw->offloads_inactive = false; + esw_warn(esw->dev, "MPFS/FDB active\n"); +} + +static void mlx5_esw_fdb_inactive(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + unsigned long i; + + mlx5_mpfs_disable(esw->dev); + mlx5_esw_fdb_drop_create(esw); + + mlx5_esw_for_each_vf_vport(esw, i, vport, U16_MAX) { + if (!vport->adjacent) + continue; + esw_debug(esw->dev, "Disconnecting vport %u from eswitch\n", + vport->vport); + + mlx5_esw_adj_vport_modify(esw->dev, vport->vport, false); + } + + esw->offloads_inactive = true; + esw_warn(esw->dev, "MPFS/FDB inactive\n"); +} + static int esw_offloads_start(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack) { @@ -3438,6 +3564,10 @@ static int esw_offloads_steering_init(struct mlx5_eswitch *esw) static void esw_offloads_steering_cleanup(struct mlx5_eswitch *esw) { + mlx5_esw_fdb_drop_destroy(esw); + if (esw->fdb_table.offloads.drop_root_fc) + mlx5_fc_destroy(esw->dev, esw->fdb_table.offloads.drop_root_fc); + esw->fdb_table.offloads.drop_root_fc = NULL; esw_destroy_vport_rx_drop_rule(esw); esw_destroy_vport_rx_drop_group(esw); esw_destroy_vport_rx_group(esw); @@ -3556,10 +3686,11 @@ bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 cont int esw_offloads_enable(struct mlx5_eswitch *esw) { + u8 mapping_id[MLX5_SW_IMAGE_GUID_MAX_BYTES]; struct mapping_ctx *reg_c0_obj_pool; struct mlx5_vport *vport; unsigned long i; - u64 mapping_id; + u8 id_len; int err; mutex_init(&esw->offloads.termtbl_mutex); @@ -3581,9 +3712,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_vport_metadata; - mapping_id = mlx5_query_nic_system_image_guid(esw->dev); + mlx5_query_nic_sw_system_image_guid(esw->dev, mapping_id, &id_len); - reg_c0_obj_pool = mapping_create_for_id(mapping_id, MAPPING_TYPE_CHAIN, + reg_c0_obj_pool = mapping_create_for_id(mapping_id, id_len, + MAPPING_TYPE_CHAIN, sizeof(struct mlx5_mapped_obj), ESW_REG_C0_USER_DATA_METADATA_MASK, true); @@ -3598,6 +3730,11 @@ int esw_offloads_enable(struct mlx5_eswitch *esw) if (err) goto err_steering_init; + if (esw->offloads_inactive) + mlx5_esw_fdb_inactive(esw); + else + mlx5_esw_fdb_active(esw); + /* Representor will control the vport link state */ mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) vport->info.link_state = MLX5_VPORT_ADMIN_STATE_DOWN; @@ -3664,6 +3801,9 @@ void esw_offloads_disable(struct mlx5_eswitch *esw) esw_offloads_metadata_uninit(esw); mlx5_rdma_disable_roce(esw->dev); mlx5_esw_adjacent_vhcas_cleanup(esw); + /* must be done after vhcas cleanup to avoid adjacent vports connect */ + if (esw->offloads_inactive) + mlx5_esw_fdb_active(esw); /* legacy mode always active */ mutex_destroy(&esw->offloads.termtbl_mutex); } @@ -3674,6 +3814,7 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) *mlx5_mode = MLX5_ESWITCH_LEGACY; break; case DEVLINK_ESWITCH_MODE_SWITCHDEV: + case DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE: *mlx5_mode = MLX5_ESWITCH_OFFLOADS; break; default: @@ -3683,14 +3824,17 @@ static int esw_mode_from_devlink(u16 mode, u16 *mlx5_mode) return 0; } -static int esw_mode_to_devlink(u16 mlx5_mode, u16 *mode) +static int esw_mode_to_devlink(struct mlx5_eswitch *esw, u16 *mode) { - switch (mlx5_mode) { + switch (esw->mode) { case MLX5_ESWITCH_LEGACY: *mode = DEVLINK_ESWITCH_MODE_LEGACY; break; case MLX5_ESWITCH_OFFLOADS: - *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; + if (esw->offloads_inactive) + *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE; + else + *mode = DEVLINK_ESWITCH_MODE_SWITCHDEV; break; default: return -EINVAL; @@ -3796,6 +3940,45 @@ static bool mlx5_devlink_netdev_netns_immutable_set(struct devlink *devlink, return ret; } +/* Returns true when only changing between active and inactive switchdev mode */ +static bool mlx5_devlink_switchdev_active_mode_change(struct mlx5_eswitch *esw, + u16 devlink_mode) +{ + /* current mode is not switchdev */ + if (esw->mode != MLX5_ESWITCH_OFFLOADS) + return false; + + /* new mode is not switchdev */ + if (devlink_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV && + devlink_mode != DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE) + return false; + + /* already inactive: no change in current state */ + if (devlink_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE && + esw->offloads_inactive) + return false; + + /* already active: no change in current state */ + if (devlink_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && + !esw->offloads_inactive) + return false; + + down_write(&esw->mode_lock); + esw->offloads_inactive = !esw->offloads_inactive; + esw->eswitch_operation_in_progress = true; + up_write(&esw->mode_lock); + + if (esw->offloads_inactive) + mlx5_esw_fdb_inactive(esw); + else + mlx5_esw_fdb_active(esw); + + down_write(&esw->mode_lock); + esw->eswitch_operation_in_progress = false; + up_write(&esw->mode_lock); + return true; +} + int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, struct netlink_ext_ack *extack) { @@ -3810,12 +3993,16 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, if (esw_mode_from_devlink(mode, &mlx5_mode)) return -EINVAL; - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && mlx5_get_sd(esw->dev)) { + if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && mlx5_get_sd(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't change E-Switch mode to switchdev when multi-PF netdev (Socket Direct) is configured."); return -EPERM; } + /* Avoid try_lock, active/inactive mode change is not restricted */ + if (mlx5_devlink_switchdev_active_mode_change(esw, mode)) + return 0; + mlx5_lag_disable_change(esw->dev); err = mlx5_esw_try_lock(esw); if (err < 0) { @@ -3838,7 +4025,7 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, esw->eswitch_operation_in_progress = true; up_write(&esw->mode_lock); - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && + if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && !mlx5_devlink_netdev_netns_immutable_set(devlink, true)) { NL_SET_ERR_MSG_MOD(extack, "Can't change E-Switch mode to switchdev when netdev net namespace has diverged from the devlink's."); @@ -3846,25 +4033,27 @@ int mlx5_devlink_eswitch_mode_set(struct devlink *devlink, u16 mode, goto skip; } - if (mode == DEVLINK_ESWITCH_MODE_LEGACY) + if (mlx5_mode == MLX5_ESWITCH_LEGACY) esw->dev->priv.flags |= MLX5_PRIV_FLAGS_SWITCH_LEGACY; mlx5_eswitch_disable_locked(esw); - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV) { + if (mlx5_mode == MLX5_ESWITCH_OFFLOADS) { if (mlx5_devlink_trap_get_num_active(esw->dev)) { NL_SET_ERR_MSG_MOD(extack, "Can't change mode while devlink traps are active"); err = -EOPNOTSUPP; goto skip; } + esw->offloads_inactive = + (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE); err = esw_offloads_start(esw, extack); - } else if (mode == DEVLINK_ESWITCH_MODE_LEGACY) { + } else if (mlx5_mode == MLX5_ESWITCH_LEGACY) { err = esw_offloads_stop(esw, extack); } else { err = -EINVAL; } skip: - if (mode == DEVLINK_ESWITCH_MODE_SWITCHDEV && err) + if (mlx5_mode == MLX5_ESWITCH_OFFLOADS && err) mlx5_devlink_netdev_netns_immutable_set(devlink, false); down_write(&esw->mode_lock); esw->eswitch_operation_in_progress = false; @@ -3883,7 +4072,7 @@ int mlx5_devlink_eswitch_mode_get(struct devlink *devlink, u16 *mode) if (IS_ERR(esw)) return PTR_ERR(esw); - return esw_mode_to_devlink(esw->mode, mode); + return esw_mode_to_devlink(esw, mode); } static int mlx5_esw_vports_inline_set(struct mlx5_eswitch *esw, u8 mlx5_mode, @@ -4302,6 +4491,9 @@ int mlx5_devlink_port_fn_hw_addr_get(struct devlink_port *port, struct mlx5_vport *vport = mlx5_devlink_port_vport_get(port); mutex_lock(&esw->state_lock); + + mlx5_query_nic_vport_mac_address(esw->dev, vport->vport, true, + vport->info.mac); ether_addr_copy(hw_addr, vport->info.mac); *hw_addr_len = ETH_ALEN; mutex_unlock(&esw->state_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 1af76da8b1320..ced747bef6415 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -239,6 +239,10 @@ static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, MLX5_SET(set_flow_table_root_in, in, vport_number, ft->vport); MLX5_SET(set_flow_table_root_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(set_flow_table_root_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(set_flow_table_root_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); err = mlx5_cmd_exec_in(dev, set_flow_table_root, in); if (!err && @@ -302,6 +306,10 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(create_flow_table_in, in, vport_number, ft->vport); MLX5_SET(create_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(create_flow_table_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(create_flow_table_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); MLX5_SET(create_flow_table_in, in, flow_table_context.decap_en, en_decap); @@ -360,6 +368,10 @@ static int mlx5_cmd_destroy_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_table_in, in, vport_number, ft->vport); MLX5_SET(destroy_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(destroy_flow_table_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(destroy_flow_table_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); err = mlx5_cmd_exec_in(dev, destroy_flow_table, in); if (!err) @@ -394,6 +406,10 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, MLX5_SET(modify_flow_table_in, in, vport_number, ft->vport); MLX5_SET(modify_flow_table_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(modify_flow_table_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(modify_flow_table_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); MLX5_SET(modify_flow_table_in, in, modify_field_select, MLX5_MODIFY_FLOW_TABLE_MISS_TABLE_ID); if (next_ft) { @@ -429,6 +445,10 @@ static int mlx5_cmd_create_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_SET(create_flow_group_in, in, vport_number, ft->vport); MLX5_SET(create_flow_group_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(create_flow_group_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(create_flow_group_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); err = mlx5_cmd_exec_inout(dev, create_flow_group, in, out); if (!err) fg->id = MLX5_GET(create_flow_group_out, out, @@ -451,6 +471,10 @@ static int mlx5_cmd_destroy_flow_group(struct mlx5_flow_root_namespace *ns, MLX5_SET(destroy_flow_group_in, in, vport_number, ft->vport); MLX5_SET(destroy_flow_group_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(destroy_flow_group_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(destroy_flow_group_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); return mlx5_cmd_exec_in(dev, destroy_flow_group, in); } @@ -559,6 +583,9 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_SET(set_fte_in, in, vport_number, ft->vport); MLX5_SET(set_fte_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(set_fte_in, in, eswitch_owner_vhca_id, ft->esw_owner_vhca_id); + MLX5_SET(set_fte_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); MLX5_SET(flow_context, in_flow_context, group_id, group_id); @@ -788,6 +815,10 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, MLX5_SET(delete_fte_in, in, vport_number, ft->vport); MLX5_SET(delete_fte_in, in, other_vport, !!(ft->flags & MLX5_FLOW_TABLE_OTHER_VPORT)); + MLX5_SET(delete_fte_in, in, eswitch_owner_vhca_id, + ft->esw_owner_vhca_id); + MLX5_SET(delete_fte_in, in, other_eswitch, + !!(ft->flags & MLX5_FLOW_TABLE_OTHER_ESWITCH)); return mlx5_cmd_exec_in(dev, delete_fte, in); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 2db3ffb0a2b28..2b755a0035ced 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -939,10 +939,10 @@ static struct mlx5_flow_group *alloc_insert_flow_group(struct mlx5_flow_table *f return fg; } -static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, - enum fs_flow_table_type table_type, - enum fs_flow_table_op_mod op_mod, - u32 flags) +static struct mlx5_flow_table * +alloc_flow_table(struct mlx5_flow_table_attr *ft_attr, u16 vport, + enum fs_flow_table_type table_type, + enum fs_flow_table_op_mod op_mod) { struct mlx5_flow_table *ft; int ret; @@ -957,12 +957,13 @@ static struct mlx5_flow_table *alloc_flow_table(int level, u16 vport, return ERR_PTR(ret); } - ft->level = level; + ft->level = ft_attr->level; ft->node.type = FS_TYPE_FLOW_TABLE; ft->op_mod = op_mod; ft->type = table_type; ft->vport = vport; - ft->flags = flags; + ft->esw_owner_vhca_id = ft_attr->esw_owner_vhca_id; + ft->flags = ft_attr->flags; INIT_LIST_HEAD(&ft->fwd_rules); mutex_init(&ft->lock); @@ -1370,10 +1371,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa /* The level is related to the * priority level range. */ - ft = alloc_flow_table(ft_attr->level, - vport, - root->table_type, - op_mod, ft_attr->flags); + ft = alloc_flow_table(ft_attr, vport, root->table_type, op_mod); if (IS_ERR(ft)) { err = PTR_ERR(ft); goto unlock_root; @@ -3310,6 +3308,62 @@ init_rdma_transport_tx_root_ns_one(struct mlx5_flow_steering *steering, return ret; } +static bool mlx5_fs_ns_is_empty(struct mlx5_flow_namespace *ns) +{ + struct fs_prio *iter_prio; + + fs_for_each_prio(iter_prio, ns) { + if (iter_prio->num_ft) + return false; + } + + return true; +} + +int mlx5_fs_set_root_dev(struct mlx5_core_dev *dev, + struct mlx5_core_dev *new_dev, + enum fs_flow_table_type table_type) +{ + struct mlx5_flow_root_namespace **root; + int total_vports; + int i; + + switch (table_type) { + case FS_FT_RDMA_TRANSPORT_TX: + root = dev->priv.steering->rdma_transport_tx_root_ns; + total_vports = dev->priv.steering->rdma_transport_tx_vports; + break; + case FS_FT_RDMA_TRANSPORT_RX: + root = dev->priv.steering->rdma_transport_rx_root_ns; + total_vports = dev->priv.steering->rdma_transport_rx_vports; + break; + default: + WARN_ON_ONCE(true); + return -EINVAL; + } + + for (i = 0; i < total_vports; i++) { + mutex_lock(&root[i]->chain_lock); + if (!mlx5_fs_ns_is_empty(&root[i]->ns)) { + mutex_unlock(&root[i]->chain_lock); + goto err; + } + root[i]->dev = new_dev; + mutex_unlock(&root[i]->chain_lock); + } + return 0; +err: + while (i--) { + mutex_lock(&root[i]->chain_lock); + root[i]->dev = dev; + mutex_unlock(&root[i]->chain_lock); + } + /* If you hit this error try destroying all flow tables and try again */ + mlx5_core_err(dev, "Failed to set root device for RDMA TRANSPORT\n"); + return -EINVAL; +} +EXPORT_SYMBOL(mlx5_fs_set_root_dev); + static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering) { struct mlx5_core_dev *dev = steering->dev; @@ -3520,6 +3574,11 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) if (!steering->fdb_root_ns) return -ENOMEM; + maj_prio = fs_create_prio(&steering->fdb_root_ns->ns, FDB_DROP_ROOT, 1); + err = PTR_ERR_OR_ZERO(maj_prio); + if (err) + goto out_err; + err = create_fdb_bypass(steering); if (err) goto out_err; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index 8458ce203dac6..1c65914252604 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -103,24 +103,6 @@ enum fs_node_type { FS_TYPE_FLOW_DEST }; -enum fs_flow_table_type { - FS_FT_NIC_RX = 0x0, - FS_FT_NIC_TX = 0x1, - FS_FT_ESW_EGRESS_ACL = 0x2, - FS_FT_ESW_INGRESS_ACL = 0x3, - FS_FT_FDB = 0X4, - FS_FT_SNIFFER_RX = 0X5, - FS_FT_SNIFFER_TX = 0X6, - FS_FT_RDMA_RX = 0X7, - FS_FT_RDMA_TX = 0X8, - FS_FT_PORT_SEL = 0X9, - FS_FT_FDB_RX = 0xa, - FS_FT_FDB_TX = 0xb, - FS_FT_RDMA_TRANSPORT_RX = 0xd, - FS_FT_RDMA_TRANSPORT_TX = 0xe, - FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX, -}; - enum fs_flow_table_op_mod { FS_FT_OP_MOD_NORMAL, FS_FT_OP_MOD_LAG_DEMUX, @@ -205,6 +187,7 @@ struct mlx5_flow_table { }; u32 id; u16 vport; + u16 esw_owner_vhca_id; unsigned int max_fte; unsigned int level; enum fs_flow_table_type type; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c index 4b3430ac39058..3b2f54ca30a80 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ethtool.c @@ -266,21 +266,18 @@ static int mlx5i_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return mlx5e_ethtool_set_rxnfc(priv, cmd); } +static u32 mlx5i_get_rx_ring_count(struct net_device *dev) +{ + struct mlx5e_priv *priv = mlx5i_epriv(dev); + + return priv->channels.params.num_channels; +} + static int mlx5i_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = mlx5i_epriv(dev); - /* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part - * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc, - * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc - * is compiled out via CONFIG_MLX5_EN_RXNFC=n. - */ - if (info->cmd == ETHTOOL_GRXRINGS) { - info->data = priv->channels.params.num_channels; - return 0; - } - return mlx5e_ethtool_get_rxnfc(priv, info, rule_locs); } @@ -304,6 +301,7 @@ const struct ethtool_ops mlx5i_ethtool_ops = { .set_rxfh_fields = mlx5i_set_rxfh_fields, .get_rxnfc = mlx5i_get_rxnfc, .set_rxnfc = mlx5i_set_rxnfc, + .get_rx_ring_count = mlx5i_get_rx_ring_count, .get_link_ksettings = mlx5i_get_link_ksettings, .get_link = ethtool_op_get_link, }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 79ae3a51a4b3e..0a6003fe60e9f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -45,6 +45,23 @@ static int mlx5i_open(struct net_device *netdev); static int mlx5i_close(struct net_device *netdev); static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu); +int mlx5i_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(dev); + + return mlx5e_hwtstamp_set(epriv, config, extack); +} + +int mlx5i_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config) +{ + struct mlx5e_priv *epriv = mlx5i_epriv(dev); + + return mlx5e_hwtstamp_get(epriv, config); +} + static const struct net_device_ops mlx5i_netdev_ops = { .ndo_open = mlx5i_open, .ndo_stop = mlx5i_close, @@ -52,7 +69,8 @@ static const struct net_device_ops mlx5i_netdev_ops = { .ndo_init = mlx5i_dev_init, .ndo_uninit = mlx5i_dev_cleanup, .ndo_change_mtu = mlx5i_change_mtu, - .ndo_eth_ioctl = mlx5i_ioctl, + .ndo_hwtstamp_get = mlx5i_hwtstamp_get, + .ndo_hwtstamp_set = mlx5i_hwtstamp_set, }; /* IPoIB mlx5 netdev profile */ @@ -316,7 +334,7 @@ void mlx5i_destroy_underlay_qp(struct mlx5_core_dev *mdev, u32 qpn) int mlx5i_update_nic_rx(struct mlx5e_priv *priv) { - return mlx5e_refresh_tirs(priv, true, true); + return mlx5e_refresh_tirs(priv->mdev, true, true); } int mlx5i_create_tis(struct mlx5_core_dev *mdev, u32 underlay_qpn, u32 *tisn) @@ -409,6 +427,7 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv) static int mlx5i_init_rx(struct mlx5e_priv *priv) { struct mlx5_core_dev *mdev = priv->mdev; + enum mlx5e_rx_res_features features; int err; priv->fs = mlx5e_fs_init(priv->profile, mdev, @@ -427,7 +446,9 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) goto err_destroy_q_counters; } - priv->rx_res = mlx5e_rx_res_create(priv->mdev, 0, priv->max_nch, priv->drop_rq.rqn, + features = MLX5E_RX_RES_FEATURE_SELF_LB_BLOCK; + priv->rx_res = mlx5e_rx_res_create(priv->mdev, features, priv->max_nch, + priv->drop_rq.rqn, &priv->channels.params.packet_merge, priv->channels.params.num_channels); if (IS_ERR(priv->rx_res)) { @@ -557,20 +578,6 @@ int mlx5i_dev_init(struct net_device *dev) return 0; } -int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - struct mlx5e_priv *priv = mlx5i_epriv(dev); - - switch (cmd) { - case SIOCSHWTSTAMP: - return mlx5e_hwstamp_set(priv, ifr); - case SIOCGHWTSTAMP: - return mlx5e_hwstamp_get(priv, ifr); - default: - return -EOPNOTSUPP; - } -} - void mlx5i_dev_cleanup(struct net_device *dev) { struct mlx5e_priv *priv = mlx5i_epriv(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h index 2ab6437a1c49f..d67d5a72bb419 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.h @@ -88,7 +88,11 @@ struct net_device *mlx5i_pkey_get_netdev(struct net_device *netdev, u32 qpn); /* Shared ndo functions */ int mlx5i_dev_init(struct net_device *dev); void mlx5i_dev_cleanup(struct net_device *dev); -int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); +int mlx5i_hwtstamp_set(struct net_device *dev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +int mlx5i_hwtstamp_get(struct net_device *dev, + struct kernel_hwtstamp_config *config); /* Parent profile functions */ int mlx5i_init(struct mlx5_core_dev *mdev, struct net_device *netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index 028a76944d82d..04444dad3a0db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -140,7 +140,6 @@ static int mlx5i_pkey_close(struct net_device *netdev); static int mlx5i_pkey_dev_init(struct net_device *dev); static void mlx5i_pkey_dev_cleanup(struct net_device *netdev); static int mlx5i_pkey_change_mtu(struct net_device *netdev, int new_mtu); -static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); static const struct net_device_ops mlx5i_pkey_netdev_ops = { .ndo_open = mlx5i_pkey_open, @@ -149,7 +148,8 @@ static const struct net_device_ops mlx5i_pkey_netdev_ops = { .ndo_get_stats64 = mlx5i_get_stats, .ndo_uninit = mlx5i_pkey_dev_cleanup, .ndo_change_mtu = mlx5i_pkey_change_mtu, - .ndo_eth_ioctl = mlx5i_pkey_ioctl, + .ndo_hwtstamp_get = mlx5i_hwtstamp_get, + .ndo_hwtstamp_set = mlx5i_hwtstamp_set, }; /* Child NDOs */ @@ -184,11 +184,6 @@ static int mlx5i_pkey_dev_init(struct net_device *dev) return mlx5i_dev_init(dev); } -static int mlx5i_pkey_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) -{ - return mlx5i_ioctl(dev, ifr, cmd); -} - static void mlx5i_pkey_dev_cleanup(struct net_device *netdev) { mlx5i_parent_put(netdev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c index 3db0387bf6dcb..1ac933cd8f02b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c @@ -1418,10 +1418,12 @@ static void mlx5_lag_unregister_hca_devcom_comp(struct mlx5_core_dev *dev) static int mlx5_lag_register_hca_devcom_comp(struct mlx5_core_dev *dev) { struct mlx5_devcom_match_attr attr = { - .key.val = mlx5_query_nic_system_image_guid(dev), .flags = MLX5_DEVCOM_MATCH_FLAGS_NS, .net = mlx5_core_net(dev), }; + u8 len __always_unused; + + mlx5_query_nic_sw_system_image_guid(dev, attr.key.buf, &len); /* This component is use to sync adding core_dev to lag_dev and to sync * changes of mlx5_adev_devices between LAG layer and other layers. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c index 29e7fa09c32c8..0ba0ef8bae421 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c @@ -1432,15 +1432,17 @@ static int mlx5_clock_alloc(struct mlx5_core_dev *mdev, bool shared) return 0; } -static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, u64 key) +static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, + u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE]) { struct mlx5_core_dev *peer_dev, *next = NULL; - struct mlx5_devcom_match_attr attr = { - .key.val = key, - }; + struct mlx5_devcom_match_attr attr = {}; struct mlx5_devcom_comp_dev *compd; struct mlx5_devcom_comp_dev *pos; + BUILD_BUG_ON(MLX5_RT_CLOCK_IDENTITY_SIZE > MLX5_DEVCOM_MATCH_KEY_MAX); + memcpy(attr.key.buf, identity, MLX5_RT_CLOCK_IDENTITY_SIZE); + compd = mlx5_devcom_register_component(mdev->priv.devc, MLX5_DEVCOM_SHARED_CLOCK, &attr, NULL, mdev); @@ -1594,7 +1596,6 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev) { u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE]; struct mlx5_clock_dev_state *clock_state; - u64 key; int err; if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) { @@ -1610,12 +1611,10 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev) mdev->clock_state = clock_state; if (MLX5_CAP_MCAM_REG3(mdev, mrtcq) && mlx5_real_time_mode(mdev)) { - if (mlx5_clock_identity_get(mdev, identity)) { + if (mlx5_clock_identity_get(mdev, identity)) mlx5_core_warn(mdev, "failed to get rt clock identity, create ptp dev per function\n"); - } else { - memcpy(&key, &identity, sizeof(key)); - mlx5_shared_clock_register(mdev, key); - } + else + mlx5_shared_clock_register(mdev, identity); } if (!mdev->clock) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h index c18a652c0faa1..aff3aed62c748 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h @@ -54,7 +54,6 @@ struct mlx5_timer { struct mlx5_clock { seqlock_t lock; - struct hwtstamp_config hwtstamp_config; struct ptp_clock *ptp; struct ptp_clock_info ptp_info; struct mlx5_pps pps_info; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h index 609c85f479173..91e5ae529d5c6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h @@ -10,8 +10,10 @@ enum mlx5_devom_match_flags { MLX5_DEVCOM_MATCH_FLAGS_NS = BIT(0), }; +#define MLX5_DEVCOM_MATCH_KEY_MAX 32 union mlx5_devcom_match_key { u64 val; + u8 buf[MLX5_DEVCOM_MATCH_KEY_MAX]; }; struct mlx5_devcom_match_attr { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c index 4450091e181a1..4a88a42ae4f7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.c @@ -65,13 +65,14 @@ static int del_l2table_entry_cmd(struct mlx5_core_dev *dev, u32 index) /* UC L2 table hash node */ struct l2table_node { struct l2addr_node node; - u32 index; /* index in HW l2 table */ + int index; /* index in HW l2 table */ int ref_count; }; struct mlx5_mpfs { struct hlist_head hash[MLX5_L2_ADDR_HASH_SIZE]; struct mutex lock; /* Synchronize l2 table access */ + bool enabled; u32 size; unsigned long *bitmap; }; @@ -114,6 +115,8 @@ int mlx5_mpfs_init(struct mlx5_core_dev *dev) return -ENOMEM; } + mpfs->enabled = true; + dev->priv.mpfs = mpfs; return 0; } @@ -135,7 +138,7 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) struct mlx5_mpfs *mpfs = dev->priv.mpfs; struct l2table_node *l2addr; int err = 0; - u32 index; + int index; if (!mpfs) return 0; @@ -148,30 +151,34 @@ int mlx5_mpfs_add_mac(struct mlx5_core_dev *dev, u8 *mac) goto out; } - err = alloc_l2table_index(mpfs, &index); - if (err) - goto out; - l2addr = l2addr_hash_add(mpfs->hash, mac, struct l2table_node, GFP_KERNEL); if (!l2addr) { err = -ENOMEM; - goto hash_add_err; + goto out; } - err = set_l2table_entry_cmd(dev, index, mac); - if (err) - goto set_table_entry_err; + index = -1; + + if (mpfs->enabled) { + err = alloc_l2table_index(mpfs, &index); + if (err) + goto hash_del; + err = set_l2table_entry_cmd(dev, index, mac); + if (err) + goto free_l2table_index; + mlx5_core_dbg(dev, "MPFS entry %pM, set @index (%d)\n", + l2addr->node.addr, index); + } l2addr->index = index; l2addr->ref_count = 1; mlx5_core_dbg(dev, "MPFS mac added %pM, index (%d)\n", mac, index); goto out; - -set_table_entry_err: - l2addr_hash_del(l2addr); -hash_add_err: +free_l2table_index: free_l2table_index(mpfs, index); +hash_del: + l2addr_hash_del(l2addr); out: mutex_unlock(&mpfs->lock); return err; @@ -183,7 +190,7 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) struct mlx5_mpfs *mpfs = dev->priv.mpfs; struct l2table_node *l2addr; int err = 0; - u32 index; + int index; if (!mpfs) return 0; @@ -200,12 +207,87 @@ int mlx5_mpfs_del_mac(struct mlx5_core_dev *dev, u8 *mac) goto unlock; index = l2addr->index; - del_l2table_entry_cmd(dev, index); + if (index >= 0) { + del_l2table_entry_cmd(dev, index); + free_l2table_index(mpfs, index); + mlx5_core_dbg(dev, "MPFS entry %pM, deleted @index (%d)\n", + mac, index); + } l2addr_hash_del(l2addr); - free_l2table_index(mpfs, index); mlx5_core_dbg(dev, "MPFS mac deleted %pM, index (%d)\n", mac, index); unlock: mutex_unlock(&mpfs->lock); return err; } EXPORT_SYMBOL(mlx5_mpfs_del_mac); + +int mlx5_mpfs_enable(struct mlx5_core_dev *dev) +{ + struct mlx5_mpfs *mpfs = dev->priv.mpfs; + struct l2table_node *l2addr; + struct hlist_node *n; + int err = 0, i; + + if (!mpfs) + return -ENODEV; + + mutex_lock(&mpfs->lock); + if (mpfs->enabled) + goto out; + mpfs->enabled = true; + mlx5_core_dbg(dev, "MPFS enabling mpfs\n"); + + mlx5_mpfs_foreach(l2addr, n, mpfs, i) { + u32 index; + + err = alloc_l2table_index(mpfs, &index); + if (err) { + mlx5_core_err(dev, "Failed to allocated MPFS index for %pM, err(%d)\n", + l2addr->node.addr, err); + goto out; + } + + err = set_l2table_entry_cmd(dev, index, l2addr->node.addr); + if (err) { + mlx5_core_err(dev, "Failed to set MPFS l2table entry for %pM index=%d, err(%d)\n", + l2addr->node.addr, index, err); + free_l2table_index(mpfs, index); + goto out; + } + + l2addr->index = index; + mlx5_core_dbg(dev, "MPFS entry %pM, set @index (%d)\n", + l2addr->node.addr, l2addr->index); + } +out: + mutex_unlock(&mpfs->lock); + return err; +} + +void mlx5_mpfs_disable(struct mlx5_core_dev *dev) +{ + struct mlx5_mpfs *mpfs = dev->priv.mpfs; + struct l2table_node *l2addr; + struct hlist_node *n; + int i; + + if (!mpfs) + return; + + mutex_lock(&mpfs->lock); + if (!mpfs->enabled) + goto unlock; + mlx5_mpfs_foreach(l2addr, n, mpfs, i) { + if (l2addr->index < 0) + continue; + del_l2table_entry_cmd(dev, l2addr->index); + free_l2table_index(mpfs, l2addr->index); + mlx5_core_dbg(dev, "MPFS entry %pM, deleted @index (%d)\n", + l2addr->node.addr, l2addr->index); + l2addr->index = -1; + } + mpfs->enabled = false; + mlx5_core_dbg(dev, "MPFS disabled\n"); +unlock: + mutex_unlock(&mpfs->lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h index 4a293542a7aa1..9c63838ce1f32 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mpfs.h @@ -45,6 +45,10 @@ struct l2addr_node { u8 addr[ETH_ALEN]; }; +#define mlx5_mpfs_foreach(hs, tmp, mpfs, i) \ + for (i = 0; i < MLX5_L2_ADDR_HASH_SIZE; i++) \ + hlist_for_each_entry_safe(hs, tmp, &(mpfs)->hash[i], node.hlist) + #define for_each_l2hash_node(hn, tmp, hash, i) \ for (i = 0; i < MLX5_L2_ADDR_HASH_SIZE; i++) \ hlist_for_each_entry_safe(hn, tmp, &(hash)[i], hlist) @@ -82,11 +86,16 @@ struct l2addr_node { }) #ifdef CONFIG_MLX5_MPFS +struct mlx5_core_dev; int mlx5_mpfs_init(struct mlx5_core_dev *dev); void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev); +int mlx5_mpfs_enable(struct mlx5_core_dev *dev); +void mlx5_mpfs_disable(struct mlx5_core_dev *dev); #else /* #ifndef CONFIG_MLX5_MPFS */ static inline int mlx5_mpfs_init(struct mlx5_core_dev *dev) { return 0; } static inline void mlx5_mpfs_cleanup(struct mlx5_core_dev *dev) {} +static inline int mlx5_mpfs_enable(struct mlx5_core_dev *dev) { return 0; } +static inline void mlx5_mpfs_disable(struct mlx5_core_dev *dev) {} #endif #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c index 47fe215f66bf0..ef06fe6cbb519 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c @@ -19,13 +19,16 @@ struct mlx5_st { struct mutex lock; struct xa_limit index_limit; struct xarray idx_xa; /* key == index, value == struct mlx5_st_idx_data */ + u8 direct_mode : 1; }; struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev) { struct pci_dev *pdev = dev->pdev; struct mlx5_st *st; + u8 direct_mode = 0; u16 num_entries; + u32 tbl_loc; int ret; if (!MLX5_CAP_GEN(dev, mkey_pcie_tph)) @@ -40,10 +43,16 @@ struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev) if (!pdev->tph_cap) return NULL; - num_entries = pcie_tph_get_st_table_size(pdev); - /* We need a reserved entry for non TPH cases */ - if (num_entries < 2) - return NULL; + tbl_loc = pcie_tph_get_st_table_loc(pdev); + if (tbl_loc == PCI_TPH_LOC_NONE) + direct_mode = 1; + + if (!direct_mode) { + num_entries = pcie_tph_get_st_table_size(pdev); + /* We need a reserved entry for non TPH cases */ + if (num_entries < 2) + return NULL; + } /* The OS doesn't support ST */ ret = pcie_enable_tph(pdev, PCI_TPH_ST_DS_MODE); @@ -56,6 +65,10 @@ struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev) mutex_init(&st->lock); xa_init_flags(&st->idx_xa, XA_FLAGS_ALLOC); + st->direct_mode = direct_mode; + if (st->direct_mode) + return st; + /* entry 0 is reserved for non TPH cases */ st->index_limit.min = MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX + 1; st->index_limit.max = num_entries - 1; @@ -96,6 +109,11 @@ int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type, if (ret) return ret; + if (st->direct_mode) { + *st_index = tag; + return 0; + } + mutex_lock(&st->lock); xa_for_each(&st->idx_xa, index, idx_data) { @@ -145,6 +163,9 @@ int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index) if (!st) return -EOPNOTSUPP; + if (st->direct_mode) + return 0; + mutex_lock(&st->lock); idx_data = xa_load(&st->idx_xa, st_index); if (WARN_ON_ONCE(!idx_data)) { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 70c156591b0ba..c904696cbc3a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -553,6 +553,7 @@ EXPORT_SYMBOL(mlx5_is_roce_on); static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx) { + bool do_set = false; void *set_hca_cap; int err; @@ -563,17 +564,27 @@ static int handle_hca_cap_2(struct mlx5_core_dev *dev, void *set_ctx) if (err) return err; - if (!MLX5_CAP_GEN_2_MAX(dev, sw_vhca_id_valid) || - !(dev->priv.sw_vhca_id > 0)) - return 0; - set_hca_cap = MLX5_ADDR_OF(set_hca_cap_in, set_ctx, capability); memcpy(set_hca_cap, dev->caps.hca[MLX5_CAP_GENERAL_2]->cur, MLX5_ST_SZ_BYTES(cmd_hca_cap_2)); - MLX5_SET(cmd_hca_cap_2, set_hca_cap, sw_vhca_id_valid, 1); - return set_caps(dev, set_ctx, MLX5_CAP_GENERAL_2); + if (MLX5_CAP_GEN_2_MAX(dev, sw_vhca_id_valid) && + dev->priv.sw_vhca_id > 0) { + MLX5_SET(cmd_hca_cap_2, set_hca_cap, sw_vhca_id_valid, 1); + do_set = true; + } + + if (MLX5_CAP_GEN_2_MAX(dev, lag_per_mp_group)) { + MLX5_SET(cmd_hca_cap_2, set_hca_cap, lag_per_mp_group, 1); + do_set = true; + } + + /* some FW versions that support querying MLX5_CAP_GENERAL_2 + * capabilities but don't support setting them. + * Skip unnecessary update to hca_cap_2 when no changes were introduced + */ + return do_set ? set_caps(dev, set_ctx, MLX5_CAP_GENERAL_2) : 0; } static int handle_hca_cap(struct mlx5_core_dev *dev, void *set_ctx) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 082259b56816c..acef7d0ffa097 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -444,6 +444,8 @@ int mlx5_init_one_light(struct mlx5_core_dev *dev); void mlx5_uninit_one_light(struct mlx5_core_dev *dev); void mlx5_unload_one_light(struct mlx5_core_dev *dev); +void mlx5_query_nic_sw_system_image_guid(struct mlx5_core_dev *mdev, u8 *buf, + u8 *len); int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap, u16 vport, u16 opmod); #define mlx5_vport_get_other_func_general_cap(dev, vport, out) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index 2ed2e530b07d0..306affbcfd3b0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -78,15 +78,14 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, } static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport, - u32 *out) + bool other_vport, u32 *out) { u32 in[MLX5_ST_SZ_DW(query_nic_vport_context_in)] = {}; MLX5_SET(query_nic_vport_context_in, in, opcode, MLX5_CMD_OP_QUERY_NIC_VPORT_CONTEXT); MLX5_SET(query_nic_vport_context_in, in, vport_number, vport); - if (vport) - MLX5_SET(query_nic_vport_context_in, in, other_vport, 1); + MLX5_SET(query_nic_vport_context_in, in, other_vport, other_vport); return mlx5_cmd_exec_inout(mdev, query_nic_vport_context, in, out); } @@ -97,7 +96,7 @@ int mlx5_query_nic_vport_min_inline(struct mlx5_core_dev *mdev, u32 out[MLX5_ST_SZ_DW(query_nic_vport_context_out)] = {}; int err; - err = mlx5_query_nic_vport_context(mdev, vport, out); + err = mlx5_query_nic_vport_context(mdev, vport, vport > 0, out); if (!err) *min_inline = MLX5_GET(query_nic_vport_context_out, out, nic_vport_context.min_wqe_inline_mode); @@ -219,7 +218,7 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (!err) *mtu = MLX5_GET(query_nic_vport_context_out, out, nic_vport_context.mtu); @@ -429,7 +428,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -451,7 +450,7 @@ int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -462,7 +461,8 @@ int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group) return err; } -int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) +int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, + u16 vport, bool other_vport, u64 *node_guid) { u32 *out; int outlen = MLX5_ST_SZ_BYTES(query_nic_vport_context_out); @@ -472,7 +472,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, vport, other_vport, out); if (err) goto out; @@ -529,7 +529,7 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -804,7 +804,7 @@ int mlx5_query_nic_vport_promisc(struct mlx5_core_dev *mdev, if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, vport, out); + err = mlx5_query_nic_vport_context(mdev, vport, vport > 0, out); if (err) goto out; @@ -908,7 +908,7 @@ int mlx5_nic_vport_query_local_lb(struct mlx5_core_dev *mdev, bool *status) if (!out) return -ENOMEM; - err = mlx5_query_nic_vport_context(mdev, 0, out); + err = mlx5_query_nic_vport_context(mdev, 0, false, out); if (err) goto out; @@ -1190,6 +1190,25 @@ u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev) } EXPORT_SYMBOL_GPL(mlx5_query_nic_system_image_guid); +void mlx5_query_nic_sw_system_image_guid(struct mlx5_core_dev *mdev, u8 *buf, + u8 *len) +{ + u64 fw_system_image_guid; + + *len = 0; + + fw_system_image_guid = mlx5_query_nic_system_image_guid(mdev); + if (!fw_system_image_guid) + return; + + memcpy(buf, &fw_system_image_guid, sizeof(fw_system_image_guid)); + *len += sizeof(fw_system_image_guid); + + if (MLX5_CAP_GEN_2(mdev, load_balance_id) && + MLX5_CAP_GEN_2(mdev, lag_per_mp_group)) + buf[(*len)++] = MLX5_CAP_GEN_2(mdev, load_balance_id); +} + static bool mlx5_vport_use_vhca_id_as_func_id(struct mlx5_core_dev *dev, u16 vport_num, u16 *vhca_id) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c index b032d5a4b3b84..10f5bc4892fc7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_linecards.c @@ -601,6 +601,8 @@ int mlxsw_linecard_devlink_info_get(struct mlxsw_linecard *linecard, err = devlink_info_version_fixed_put(req, DEVLINK_INFO_VERSION_GENERIC_FW_PSID, info->psid); + if (err) + goto unlock; sprintf(buf, "%u.%u.%u", info->fw_major, info->fw_minor, info->fw_sub_minor); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 6a4a81c63451c..353fd9ca89a68 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -830,8 +830,10 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp, return -EINVAL; rule = mlxsw_sp_acl_rule_lookup(mlxsw_sp, ruleset, f->cookie); - if (!rule) - return -EINVAL; + if (!rule) { + err = -EINVAL; + goto err_rule_get_stats; + } err = mlxsw_sp_acl_rule_get_stats(mlxsw_sp, rule, &packets, &bytes, &drops, &lastuse, &used_hw_stats); diff --git a/drivers/net/ethernet/meta/Kconfig b/drivers/net/ethernet/meta/Kconfig index 3ba527514f1e9..ca5c7ac2a5bc2 100644 --- a/drivers/net/ethernet/meta/Kconfig +++ b/drivers/net/ethernet/meta/Kconfig @@ -19,13 +19,14 @@ if NET_VENDOR_META config FBNIC tristate "Meta Platforms Host Network Interface" - depends on X86_64 || COMPILE_TEST + depends on 64BIT || COMPILE_TEST depends on !S390 depends on MAX_SKB_FRAGS < 22 depends on PCI_MSI depends on PTP_1588_CLOCK_OPTIONAL select NET_DEVLINK select PAGE_POOL + select PCS_XPCS select PHYLINK select PLDMFW help diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile index 15e8ff6496159..72c41af65364b 100644 --- a/drivers/net/ethernet/meta/fbnic/Makefile +++ b/drivers/net/ethernet/meta/fbnic/Makefile @@ -21,6 +21,7 @@ fbnic-y := fbnic_csr.o \ fbnic_pci.o \ fbnic_phylink.o \ fbnic_rpc.o \ + fbnic_mdio.o \ fbnic_time.o \ fbnic_tlv.o \ fbnic_txrx.o \ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h index b03e5a3d51445..779a083b92159 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic.h @@ -34,7 +34,7 @@ struct fbnic_dev { u32 __iomem *uc_addr4; const struct fbnic_mac *mac; unsigned int fw_msix_vector; - unsigned int pcs_msix_vector; + unsigned int mac_msix_vector; unsigned short num_irqs; struct { @@ -83,6 +83,10 @@ struct fbnic_dev { /* Last @time_high refresh time in jiffies (to catch stalls) */ unsigned long last_read; + /* PMD specific data */ + unsigned long end_of_pmd_training; + u8 pmd_state; + /* Local copy of hardware statistics */ struct fbnic_hw_stats hw_stats; @@ -91,6 +95,9 @@ struct fbnic_dev { u64 prev_firmware_time; struct fbnic_fw_log fw_log; + + /* MDIO bus for PHYs */ + struct mii_bus *mdio_bus; }; /* Reserve entry 0 in the MSI-X "others" array until we have filled all @@ -175,8 +182,8 @@ void fbnic_fw_free_mbx(struct fbnic_dev *fbd); void fbnic_hwmon_register(struct fbnic_dev *fbd); void fbnic_hwmon_unregister(struct fbnic_dev *fbd); -int fbnic_pcs_request_irq(struct fbnic_dev *fbd); -void fbnic_pcs_free_irq(struct fbnic_dev *fbd); +int fbnic_mac_request_irq(struct fbnic_dev *fbd); +void fbnic_mac_free_irq(struct fbnic_dev *fbd); void fbnic_napi_name_irqs(struct fbnic_dev *fbd); int fbnic_napi_request_irq(struct fbnic_dev *fbd, @@ -200,6 +207,8 @@ void fbnic_dbg_exit(void); void fbnic_rpc_reset_valid_entries(struct fbnic_dev *fbd); +int fbnic_mdiobus_create(struct fbnic_dev *fbd); + void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version); int fbnic_csr_regs_len(struct fbnic_dev *fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h index d3a7ad921f18c..422265dc7abd6 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h @@ -787,6 +787,8 @@ enum { /* MAC PCS registers */ #define FBNIC_CSR_START_PCS 0x10000 /* CSR section delimiter */ +#define FBNIC_PCS_PAGE(n) (0x10000 + 0x400 * (n)) /* 0x40000 + 1024*n */ +#define FBNIC_PCS(reg, n) ((reg) + FBNIC_PCS_PAGE(n)) #define FBNIC_CSR_END_PCS 0x10668 /* CSR section delimiter */ #define FBNIC_CSR_START_RSFEC 0x10800 /* CSR section delimiter */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index 95fac020eb93c..693ebdf387055 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -1863,6 +1863,14 @@ fbnic_get_rmon_stats(struct net_device *netdev, *ranges = fbnic_rmon_ranges; } +static void fbnic_get_link_ext_stats(struct net_device *netdev, + struct ethtool_link_ext_stats *stats) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + stats->link_down_events = fbn->link_down_events; +} + static const struct ethtool_ops fbnic_ethtool_ops = { .cap_link_lanes_supported = true, .supported_coalesce_params = ETHTOOL_COALESCE_USECS | @@ -1874,6 +1882,7 @@ static const struct ethtool_ops fbnic_ethtool_ops = { .get_regs_len = fbnic_get_regs_len, .get_regs = fbnic_get_regs, .get_link = ethtool_op_get_link, + .get_link_ext_stats = fbnic_get_link_ext_stats, .get_coalesce = fbnic_get_coalesce, .set_coalesce = fbnic_set_coalesce, .get_ringparam = fbnic_get_ringparam, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c index c87cb9ed09e7e..1166fa17438d9 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c @@ -878,11 +878,11 @@ fbnic_fw_parse_coredump_info_resp(void *opaque, struct fbnic_tlv_msg **results) * @fbd: FBNIC device structure * @cmpl_data: Completion struct to store coredump * @offset: Offset into coredump requested - * @length: Length of section of cordeump to fetch + * @length: Length of section of coredump to fetch * * Return: zero on success, negative errno on failure * - * Asks the firmware to provide a section of the cordeump back in a message. + * Asks the firmware to provide a section of the coredump back in a message. * The response will have an offset and size matching the values provided. */ int fbnic_fw_xmit_coredump_read_msg(struct fbnic_dev *fbd, @@ -1868,7 +1868,7 @@ int fbnic_fw_xmit_rpc_macda_sync(struct fbnic_dev *fbd) if (err) goto free_message; - /* Send message of to FW notifying it of current RPC config */ + /* Send message off to FW notifying it of current RPC config */ err = fbnic_mbx_map_tlv_msg(fbd, msg); if (err) goto free_message; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c index 1c88a2bf3a7a7..f2ccb33fa67ae 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_irq.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_irq.c @@ -118,39 +118,52 @@ void fbnic_fw_free_mbx(struct fbnic_dev *fbd) fbd->fw_msix_vector = 0; } -static irqreturn_t fbnic_pcs_msix_intr(int __always_unused irq, void *data) +static irqreturn_t fbnic_mac_msix_intr(int __always_unused irq, void *data) { struct fbnic_dev *fbd = data; struct fbnic_net *fbn; + u64 link_down_event; - if (fbd->mac->pcs_get_link_event(fbd) == FBNIC_LINK_EVENT_NONE) { + if (fbd->mac->get_link_event(fbd) == FBNIC_LINK_EVENT_NONE) { fbnic_wr32(fbd, FBNIC_INTR_MASK_CLEAR(0), 1u << FBNIC_PCS_MSIX_ENTRY); return IRQ_HANDLED; } + /* If the link is up this would be a loss event */ + link_down_event = (fbd->pmd_state == FBNIC_PMD_SEND_DATA) ? 1 : 0; + fbn = netdev_priv(fbd->netdev); - phylink_pcs_change(&fbn->phylink_pcs, false); + /* Record link down events */ + if (!fbd->mac->get_link(fbd, fbn->aui, fbn->fec)) { + /* Do not count link down events if the PCS has yet to + * acknowledge the link. This allows for the flushing out + * PCS errors generated during link training. + */ + if (netif_carrier_ok(fbd->netdev)) + fbn->link_down_events += link_down_event; + phylink_pcs_change(fbn->pcs, false); + } return IRQ_HANDLED; } /** - * fbnic_pcs_request_irq - Configure the PCS to enable it to advertise link + * fbnic_mac_request_irq - Configure the MAC to enable it to advertise link * @fbd: Pointer to device to initialize * - * This function provides basic bringup for the MAC/PCS IRQ. For now the IRQ + * This function provides basic bringup for the MAC/PHY IRQ. For now the IRQ * will remain disabled until we start the MAC/PCS/PHY logic via phylink. * * Return: non-zero on failure. **/ -int fbnic_pcs_request_irq(struct fbnic_dev *fbd) +int fbnic_mac_request_irq(struct fbnic_dev *fbd) { struct pci_dev *pdev = to_pci_dev(fbd->dev); int vector, err; - WARN_ON(fbd->pcs_msix_vector); + WARN_ON(fbd->mac_msix_vector); vector = pci_irq_vector(pdev, FBNIC_PCS_MSIX_ENTRY); if (vector < 0) @@ -159,7 +172,7 @@ int fbnic_pcs_request_irq(struct fbnic_dev *fbd) /* Request the IRQ for PCS link vector. * Map PCS cause to it, and unmask it */ - err = request_irq(vector, &fbnic_pcs_msix_intr, 0, + err = request_irq(vector, &fbnic_mac_msix_intr, 0, fbd->netdev->name, fbd); if (err) return err; @@ -168,22 +181,22 @@ int fbnic_pcs_request_irq(struct fbnic_dev *fbd) fbnic_wr32(fbd, FBNIC_INTR_MSIX_CTRL(FBNIC_INTR_MSIX_CTRL_PCS_IDX), FBNIC_PCS_MSIX_ENTRY | FBNIC_INTR_MSIX_CTRL_ENABLE); - fbd->pcs_msix_vector = vector; + fbd->mac_msix_vector = vector; return 0; } /** - * fbnic_pcs_free_irq - Teardown the PCS IRQ to prepare for stopping + * fbnic_mac_free_irq - Teardown the MAC IRQ to prepare for stopping * @fbd: Pointer to device that is stopping * - * This function undoes the work done in fbnic_pcs_request_irq and prepares + * This function undoes the work done in fbnic_mac_request_irq and prepares * the device to no longer receive traffic on the host interface. **/ -void fbnic_pcs_free_irq(struct fbnic_dev *fbd) +void fbnic_mac_free_irq(struct fbnic_dev *fbd) { /* Vector has already been freed */ - if (!fbd->pcs_msix_vector) + if (!fbd->mac_msix_vector) return; /* Disable interrupt */ @@ -192,14 +205,14 @@ void fbnic_pcs_free_irq(struct fbnic_dev *fbd) fbnic_wrfl(fbd); /* Synchronize IRQ to prevent race that would unmask vector */ - synchronize_irq(fbd->pcs_msix_vector); + synchronize_irq(fbd->mac_msix_vector); /* Mask the vector */ fbnic_wr32(fbd, FBNIC_INTR_MASK_SET(0), 1u << FBNIC_PCS_MSIX_ENTRY); /* Free the vector */ - free_irq(fbd->pcs_msix_vector, fbd); - fbd->pcs_msix_vector = 0; + free_irq(fbd->mac_msix_vector, fbd); + fbd->mac_msix_vector = 0; } void fbnic_synchronize_irq(struct fbnic_dev *fbd, int nr) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c index 2a84bd1d7e268..fd01d95c53482 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c @@ -434,14 +434,14 @@ static void fbnic_mac_tx_pause_config(struct fbnic_dev *fbd, bool tx_pause) wr32(fbd, FBNIC_RXB_PAUSE_DROP_CTRL, rxb_pause_ctrl); } -static int fbnic_pcs_get_link_event_asic(struct fbnic_dev *fbd) +static int fbnic_mac_get_link_event(struct fbnic_dev *fbd) { - u32 pcs_intr_mask = rd32(fbd, FBNIC_SIG_PCS_INTR_STS); + u32 intr_mask = rd32(fbd, FBNIC_SIG_PCS_INTR_STS); - if (pcs_intr_mask & FBNIC_SIG_PCS_INTR_LINK_DOWN) + if (intr_mask & FBNIC_SIG_PCS_INTR_LINK_DOWN) return FBNIC_LINK_EVENT_DOWN; - return (pcs_intr_mask & FBNIC_SIG_PCS_INTR_LINK_UP) ? + return (intr_mask & FBNIC_SIG_PCS_INTR_LINK_UP) ? FBNIC_LINK_EVENT_UP : FBNIC_LINK_EVENT_NONE; } @@ -466,9 +466,8 @@ static u32 __fbnic_mac_cmd_config_asic(struct fbnic_dev *fbd, return command_config; } -static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) +static bool fbnic_mac_get_link_status(struct fbnic_dev *fbd, u8 aui, u8 fec) { - struct fbnic_net *fbn = netdev_priv(fbd->netdev); u32 pcs_status, lane_mask = ~0; pcs_status = rd32(fbd, FBNIC_SIG_PCS_OUT0); @@ -476,7 +475,7 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) return false; /* Define the expected lane mask for the status bits we need to check */ - switch (fbn->aui) { + switch (aui) { case FBNIC_AUI_100GAUI2: lane_mask = 0xf; break; @@ -484,7 +483,7 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) lane_mask = 3; break; case FBNIC_AUI_LAUI2: - switch (fbn->fec) { + switch (fec) { case FBNIC_FEC_OFF: lane_mask = 0x63; break; @@ -502,7 +501,7 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) } /* Use an XOR to remove the bits we expect to see set */ - switch (fbn->fec) { + switch (fec) { case FBNIC_FEC_OFF: lane_mask ^= FIELD_GET(FBNIC_SIG_PCS_OUT0_BLOCK_LOCK, pcs_status); @@ -521,7 +520,36 @@ static bool fbnic_mac_get_pcs_link_status(struct fbnic_dev *fbd) return !lane_mask; } -static bool fbnic_pcs_get_link_asic(struct fbnic_dev *fbd) +static bool fbnic_pmd_update_state(struct fbnic_dev *fbd, bool signal_detect) +{ + /* Delay link up for 4 seconds to allow for link training. + * The state transitions for this are as follows: + * + * All states have the following two transitions in common: + * Loss of signal -> FBNIC_PMD_INITIALIZE + * The condition handled below (!signal) + * Reconfiguration -> FBNIC_PMD_INITIALIZE + * Occurs when mac_prepare starts a PHY reconfig + * FBNIC_PMD_TRAINING: + * signal still detected && 4s have passed -> Report link up + * When link is brought up in link_up -> FBNIC_PMD_SEND_DATA + * FBNIC_PMD_INITIALIZE: + * signal detected -> FBNIC_PMD_TRAINING + */ + if (!signal_detect) { + fbd->pmd_state = FBNIC_PMD_INITIALIZE; + } else if (fbd->pmd_state == FBNIC_PMD_TRAINING && + time_before(fbd->end_of_pmd_training, jiffies)) { + return true; + } else if (fbd->pmd_state == FBNIC_PMD_INITIALIZE) { + fbd->end_of_pmd_training = jiffies + 4 * HZ; + fbd->pmd_state = FBNIC_PMD_TRAINING; + } + + return fbd->pmd_state == FBNIC_PMD_SEND_DATA; +} + +static bool fbnic_mac_get_link(struct fbnic_dev *fbd, u8 aui, u8 fec) { bool link; @@ -538,7 +566,8 @@ static bool fbnic_pcs_get_link_asic(struct fbnic_dev *fbd) wr32(fbd, FBNIC_SIG_PCS_INTR_STS, FBNIC_SIG_PCS_INTR_LINK_DOWN | FBNIC_SIG_PCS_INTR_LINK_UP); - link = fbnic_mac_get_pcs_link_status(fbd); + link = fbnic_mac_get_link_status(fbd, aui, fec); + link = fbnic_pmd_update_state(fbd, link); /* Enable interrupt to only capture changes in link state */ wr32(fbd, FBNIC_SIG_PCS_INTR_MASK, @@ -586,20 +615,15 @@ void fbnic_mac_get_fw_settings(struct fbnic_dev *fbd, u8 *aui, u8 *fec) } } -static int fbnic_pcs_enable_asic(struct fbnic_dev *fbd) +static void fbnic_mac_prepare(struct fbnic_dev *fbd, u8 aui, u8 fec) { /* Mask and clear the PCS interrupt, will be enabled by link handler */ wr32(fbd, FBNIC_SIG_PCS_INTR_MASK, ~0); wr32(fbd, FBNIC_SIG_PCS_INTR_STS, ~0); - return 0; -} - -static void fbnic_pcs_disable_asic(struct fbnic_dev *fbd) -{ - /* Mask and clear the PCS interrupt */ - wr32(fbd, FBNIC_SIG_PCS_INTR_MASK, ~0); - wr32(fbd, FBNIC_SIG_PCS_INTR_STS, ~0); + /* If we don't have link tear it all down and start over */ + if (!fbnic_mac_get_link_status(fbd, aui, fec)) + fbd->pmd_state = FBNIC_PMD_INITIALIZE; } static void fbnic_mac_link_down_asic(struct fbnic_dev *fbd) @@ -867,10 +891,9 @@ static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, static const struct fbnic_mac fbnic_mac_asic = { .init_regs = fbnic_mac_init_regs, - .pcs_enable = fbnic_pcs_enable_asic, - .pcs_disable = fbnic_pcs_disable_asic, - .pcs_get_link = fbnic_pcs_get_link_asic, - .pcs_get_link_event = fbnic_pcs_get_link_event_asic, + .get_link = fbnic_mac_get_link, + .get_link_event = fbnic_mac_get_link_event, + .prepare = fbnic_mac_prepare, .get_fec_stats = fbnic_mac_get_fec_stats, .get_pcs_stats = fbnic_mac_get_pcs_stats, .get_eth_mac_stats = fbnic_mac_get_eth_mac_stats, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h index ede5ff0dae22f..2a9440df5e1d1 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h @@ -10,6 +10,23 @@ struct fbnic_dev; #define FBNIC_MAX_JUMBO_FRAME_SIZE 9742 +/* States loosely based on section 136.8.11.7.5 of IEEE 802.3-2022 Ethernet + * Standard. These are needed to track the state of the PHY as it has a delay + * of several seconds from the time link comes up until it has completed + * training that we need to wait to report the link. + * + * Currently we treat training as a single block as this is managed by the + * firmware. + * + * We have FBNIC_PMD_SEND_DATA set to 0 as the expected default at driver load + * and we initialize the structure containing it to zero at allocation. + */ +enum { + FBNIC_PMD_SEND_DATA = 0x0, + FBNIC_PMD_INITIALIZE = 0x1, + FBNIC_PMD_TRAINING = 0x2, +}; + enum { FBNIC_LINK_EVENT_NONE = 0, FBNIC_LINK_EVENT_UP = 1, @@ -38,6 +55,7 @@ enum { FBNIC_AUI_50GAUI1 = 2, /* 53.125GBd 53.125 * 1 */ FBNIC_AUI_100GAUI2 = 3, /* 106.25GBd 53.125 * 2 */ FBNIC_AUI_UNKNOWN = 4, + __FBNIC_AUI_MAX__ }; #define FBNIC_AUI_MODE_R2 (FBNIC_AUI_LAUI2) @@ -55,15 +73,15 @@ enum fbnic_sensor_id { * void (*init_regs)(struct fbnic_dev *fbd); * Initialize MAC registers to enable Tx/Rx paths and FIFOs. * - * void (*pcs_enable)(struct fbnic_dev *fbd); - * Configure and enable PCS to enable link if not already enabled - * void (*pcs_disable)(struct fbnic_dev *fbd); - * Shutdown the link if we are the only consumer of it. - * bool (*pcs_get_link)(struct fbnic_dev *fbd); - * Check PCS link status - * int (*pcs_get_link_event)(struct fbnic_dev *fbd) + * int (*get_link_event)(struct fbnic_dev *fbd) * Get the current link event status, reports true if link has * changed to either FBNIC_LINK_EVENT_DOWN or FBNIC_LINK_EVENT_UP + * bool (*get_link)(struct fbnic_dev *fbd, u8 aui, u8 fec); + * Check link status + * + * void (*prepare)(struct fbnic_dev *fbd, u8 aui, u8 fec); + * Prepare PHY for init by fetching settings, disabling interrupts, + * and sending an updated PHY config to FW if needed. * * void (*link_down)(struct fbnic_dev *fbd); * Configure MAC for link down event @@ -74,10 +92,10 @@ enum fbnic_sensor_id { struct fbnic_mac { void (*init_regs)(struct fbnic_dev *fbd); - int (*pcs_enable)(struct fbnic_dev *fbd); - void (*pcs_disable)(struct fbnic_dev *fbd); - bool (*pcs_get_link)(struct fbnic_dev *fbd); - int (*pcs_get_link_event)(struct fbnic_dev *fbd); + int (*get_link_event)(struct fbnic_dev *fbd); + bool (*get_link)(struct fbnic_dev *fbd, u8 aui, u8 fec); + + void (*prepare)(struct fbnic_dev *fbd, u8 aui, u8 fec); void (*get_fec_stats)(struct fbnic_dev *fbd, bool reset, struct fbnic_fec_stats *fec_stats); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c b/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c new file mode 100644 index 0000000000000..7eeaeb03529b6 --- /dev/null +++ b/drivers/net/ethernet/meta/fbnic/fbnic_mdio.c @@ -0,0 +1,190 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) Meta Platforms, Inc. and affiliates. */ + +#include +#include + +#include "fbnic.h" +#include "fbnic_netdev.h" + +#define DW_VENDOR BIT(15) +#define FBNIC_PCS_VENDOR BIT(9) +#define FBNIC_PCS_ZERO_MASK (DW_VENDOR - FBNIC_PCS_VENDOR) + +static int +fbnic_mdio_read_pmapmd(struct fbnic_dev *fbd, int addr, int regnum) +{ + u16 ctrl1[__FBNIC_AUI_MAX__][2] = { + { MDIO_PMA_CTRL1_SPEED25G, MDIO_PMA_CTRL1_SPEED50G }, + { MDIO_PMA_CTRL1_SPEED50G, MDIO_PMA_CTRL1_SPEED50G }, + { MDIO_PMA_CTRL1_SPEED50G, MDIO_PMA_CTRL1_SPEED100G }, + { MDIO_PMA_CTRL1_SPEED100G, MDIO_PMA_CTRL1_SPEED100G }, + { 0, 0 }}; + u8 aui = FBNIC_AUI_UNKNOWN; + struct fbnic_net *fbn; + int ret = 0; + + if (fbd->netdev) { + fbn = netdev_priv(fbd->netdev); + if (fbn->aui < FBNIC_AUI_UNKNOWN) + aui = fbn->aui; + } + + switch (regnum) { + case MDIO_CTRL1: + ret = ctrl1[aui][addr & 1]; + break; + case MDIO_STAT1: + ret = (fbd->pmd_state == FBNIC_PMD_SEND_DATA) ? + MDIO_STAT1_LSTATUS : 0; + break; + case MDIO_DEVID1: + ret = MP_FBNIC_XPCS_PMA_100G_ID >> 16; + break; + case MDIO_DEVID2: + ret = MP_FBNIC_XPCS_PMA_100G_ID & 0xffff; + break; + case MDIO_DEVS1: + ret = MDIO_DEVS_PMAPMD | MDIO_DEVS_PCS; + break; + case MDIO_STAT2: + ret = MDIO_STAT2_DEVPRST_VAL; + break; + default: + break; + } + + dev_dbg(fbd->dev, + "SWMII PMAPMD Rd: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, ret); + + return ret; +} + +static int +fbnic_mdio_read_pcs(struct fbnic_dev *fbd, int addr, int regnum) +{ + int ret; + + /* Report 0 for reserved registers */ + if (regnum & FBNIC_PCS_ZERO_MASK) + return 0; + + /* Intercept and return correct ID for PCS */ + if (regnum == MDIO_DEVID1) + return DW_XPCS_ID >> 16; + if (regnum == MDIO_DEVID2) + return DW_XPCS_ID & 0xffff; + if (regnum == MDIO_DEVS1) + return MDIO_DEVS_PMAPMD | MDIO_DEVS_PCS; + + /* Swap vendor page bit for FBNIC PCS vendor page bit */ + if (regnum & DW_VENDOR) + regnum ^= DW_VENDOR | FBNIC_PCS_VENDOR; + + ret = fbnic_rd32(fbd, FBNIC_PCS_PAGE(addr) + regnum); + + dev_dbg(fbd->dev, + "SWMII PCS Rd: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, ret); + + return ret; +} + +static int +fbnic_mdio_read_c45(struct mii_bus *bus, int addr, int devnum, int regnum) +{ + struct fbnic_dev *fbd = bus->priv; + + if (addr & ~1) + return 0; + + if (devnum == MDIO_MMD_PMAPMD) + return fbnic_mdio_read_pmapmd(fbd, addr, regnum); + + if (devnum == MDIO_MMD_PCS) + return fbnic_mdio_read_pcs(fbd, addr, regnum); + + return 0; +} + +static void +fbnic_mdio_write_pmapmd(struct fbnic_dev *fbd, int addr, int regnum, u16 val) +{ + dev_dbg(fbd->dev, + "SWMII PMAPMD Wr: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, val); +} + +static void +fbnic_mdio_write_pcs(struct fbnic_dev *fbd, int addr, int regnum, u16 val) +{ + /* Skip write for reserved registers */ + if (regnum & FBNIC_PCS_ZERO_MASK) + return; + + /* Swap vendor page bit for FBNIC PCS vendor page bit */ + if (regnum & DW_VENDOR) + regnum ^= DW_VENDOR | FBNIC_PCS_VENDOR; + + fbnic_wr32(fbd, FBNIC_PCS_PAGE(addr) + regnum, val); + + dev_dbg(fbd->dev, + "SWMII PCS Wr: Addr: %d RegNum: %d Value: 0x%04x\n", + addr, regnum, val); +} + +static int +fbnic_mdio_write_c45(struct mii_bus *bus, int addr, int devnum, + int regnum, u16 val) +{ + struct fbnic_dev *fbd = bus->priv; + + if (addr & ~1) + return 0; + + if (devnum == MDIO_MMD_PMAPMD) + fbnic_mdio_write_pmapmd(fbd, addr, regnum, val); + + if (devnum == MDIO_MMD_PCS) + fbnic_mdio_write_pcs(fbd, addr, regnum, val); + + return 0; +} + +/** + * fbnic_mdiobus_create - Create an MDIO bus to allow interfacing w/ PHYs + * @fbd: Pointer to FBNIC device structure to populate bus on + * + * Initialize an MDIO bus and place a pointer to it on the fbd struct. This bus + * will be used to interface with the PMA/PMD and PCS. + * + * Return: 0 on success, negative on failure + **/ +int fbnic_mdiobus_create(struct fbnic_dev *fbd) +{ + struct mii_bus *bus; + int err; + + bus = devm_mdiobus_alloc(fbd->dev); + if (!bus) + return -ENOMEM; + + bus->name = "fbnic_mii_bus"; + bus->read_c45 = &fbnic_mdio_read_c45; + bus->write_c45 = &fbnic_mdio_write_c45; + bus->parent = fbd->dev; + bus->phy_mask = GENMASK(31, 2); + bus->priv = fbd; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mii", dev_name(fbd->dev)); + + err = devm_mdiobus_register(fbd->dev, bus); + if (err) { + dev_err(fbd->dev, "Failed to create MDIO bus: %d\n", err); + return err; + } + + fbd->mdio_bus = bus; + + return 0; +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index e95be0e7bd9e0..81c9d5c9a4b2c 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -44,7 +44,7 @@ int __fbnic_open(struct fbnic_net *fbn) if (err) goto time_stop; - err = fbnic_pcs_request_irq(fbd); + err = fbnic_mac_request_irq(fbd); if (err) goto time_stop; @@ -86,10 +86,10 @@ static int fbnic_stop(struct net_device *netdev) { struct fbnic_net *fbn = netdev_priv(netdev); + fbnic_mac_free_irq(fbn->fbd); phylink_suspend(fbn->phylink, fbnic_bmc_present(fbn->fbd)); fbnic_down(fbn); - fbnic_pcs_free_irq(fbn->fbd); fbnic_time_stop(fbn); fbnic_fw_xmit_ownership_msg(fbn->fbd, false); @@ -697,10 +697,7 @@ void fbnic_reset_queues(struct fbnic_net *fbn, **/ void fbnic_netdev_free(struct fbnic_dev *fbd) { - struct fbnic_net *fbn = netdev_priv(fbd->netdev); - - if (fbn->phylink) - phylink_destroy(fbn->phylink); + fbnic_phylink_destroy(fbd->netdev); free_netdev(fbd->netdev); fbd->netdev = NULL; @@ -802,7 +799,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netif_tx_stop_all_queues(netdev); - if (fbnic_phylink_init(netdev)) { + if (fbnic_phylink_create(netdev)) { fbnic_netdev_free(fbd); return NULL; } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h index b0a87c57910f2..9129a658f8fad 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h @@ -44,7 +44,7 @@ struct fbnic_net { struct phylink *phylink; struct phylink_config phylink_config; - struct phylink_pcs phylink_pcs; + struct phylink_pcs *pcs; u8 aui; u8 fec; @@ -73,6 +73,8 @@ struct fbnic_net { /* Time stamping filter config */ struct kernel_hwtstamp_config hwtstamp_config; + + bool tx_pause; }; int __fbnic_open(struct fbnic_net *fbn); @@ -106,8 +108,10 @@ int fbnic_phylink_ethtool_ksettings_get(struct net_device *netdev, struct ethtool_link_ksettings *cmd); int fbnic_phylink_get_fecparam(struct net_device *netdev, struct ethtool_fecparam *fecparam); +int fbnic_phylink_create(struct net_device *netdev); +void fbnic_phylink_destroy(struct net_device *netdev); int fbnic_phylink_init(struct net_device *netdev); - +void fbnic_phylink_pmd_training_complete_notify(struct net_device *netdev); bool fbnic_check_split_frames(struct bpf_prog *prog, unsigned int mtu, u32 hds_threshold); #endif /* _FBNIC_NETDEV_H_ */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index a7a6b4db8016f..7991e28700813 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -185,7 +185,7 @@ static void fbnic_health_check(struct fbnic_dev *fbd) { struct fbnic_fw_mbx *tx_mbx = &fbd->mbx[FBNIC_IPC_MBX_TX_IDX]; - /* As long as the heart is beating the FW is healty */ + /* As long as the heart is beating the FW is healthy */ if (fbd->fw_heartbeat_enabled) return; @@ -196,7 +196,7 @@ static void fbnic_health_check(struct fbnic_dev *fbd) if (tx_mbx->head != tx_mbx->tail) return; - fbnic_devlink_fw_report(fbd, "Firmware crashed detected!"); + fbnic_devlink_fw_report(fbd, "Firmware crash detected!"); fbnic_devlink_otp_check(fbd, "error detected after firmware recovery"); if (fbnic_fw_config_after_crash(fbd)) @@ -207,6 +207,10 @@ static void fbnic_service_task(struct work_struct *work) { struct fbnic_dev *fbd = container_of(to_delayed_work(work), struct fbnic_dev, service_task); + struct net_device *netdev = fbd->netdev; + + if (netif_running(netdev)) + fbnic_phylink_pmd_training_complete_notify(netdev); rtnl_lock(); @@ -218,13 +222,13 @@ static void fbnic_service_task(struct work_struct *work) fbnic_bmc_rpc_check(fbd); - if (netif_carrier_ok(fbd->netdev)) { - netdev_lock(fbd->netdev); - fbnic_napi_depletion_check(fbd->netdev); - netdev_unlock(fbd->netdev); + if (netif_carrier_ok(netdev)) { + netdev_lock(netdev); + fbnic_napi_depletion_check(netdev); + netdev_unlock(netdev); } - if (netif_running(fbd->netdev)) + if (netif_running(netdev)) schedule_delayed_work(&fbd->service_task, HZ); rtnl_unlock(); @@ -335,6 +339,9 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_failure_mode; } + if (fbnic_mdiobus_create(fbd)) + goto init_failure_mode; + netdev = fbnic_netdev_alloc(fbd); if (!netdev) { dev_err(&pdev->dev, "Netdev allocation failed\n"); @@ -378,7 +385,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * @pdev: PCI device information struct * * Called by the PCI subsystem to alert the driver that it should release - * a PCI device. The could be caused by a Hot-Plug event, or because the + * a PCI device. This could be caused by a Hot-Plug event, or because the * driver is going to be removed from memory. **/ static void fbnic_remove(struct pci_dev *pdev) diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c index 7ce3fdd252828..c98365c4d4989 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) Meta Platforms, Inc. and affiliates. */ +#include #include #include @@ -101,88 +102,47 @@ int fbnic_phylink_get_fecparam(struct net_device *netdev, return 0; } -static struct fbnic_net * -fbnic_pcs_to_net(struct phylink_pcs *pcs) -{ - return container_of(pcs, struct fbnic_net, phylink_pcs); -} - -static void -fbnic_phylink_pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, - struct phylink_link_state *state) +static struct phylink_pcs * +fbnic_phylink_mac_select_pcs(struct phylink_config *config, + phy_interface_t interface) { - struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); - struct fbnic_dev *fbd = fbn->fbd; - - switch (fbn->aui) { - case FBNIC_AUI_25GAUI: - state->speed = SPEED_25000; - break; - case FBNIC_AUI_LAUI2: - case FBNIC_AUI_50GAUI1: - state->speed = SPEED_50000; - break; - case FBNIC_AUI_100GAUI2: - state->speed = SPEED_100000; - break; - default: - state->link = 0; - return; - } - - state->duplex = DUPLEX_FULL; + struct net_device *netdev = to_net_dev(config->dev); + struct fbnic_net *fbn = netdev_priv(netdev); - state->link = fbd->mac->pcs_get_link(fbd); + return fbn->pcs; } static int -fbnic_phylink_pcs_enable(struct phylink_pcs *pcs) +fbnic_phylink_mac_prepare(struct phylink_config *config, unsigned int mode, + phy_interface_t iface) { - struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); + struct net_device *netdev = to_net_dev(config->dev); + struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; - return fbd->mac->pcs_enable(fbd); + fbd->mac->prepare(fbd, fbn->aui, fbn->fec); + + return 0; } static void -fbnic_phylink_pcs_disable(struct phylink_pcs *pcs) +fbnic_phylink_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) { - struct fbnic_net *fbn = fbnic_pcs_to_net(pcs); - struct fbnic_dev *fbd = fbn->fbd; - - return fbd->mac->pcs_disable(fbd); } static int -fbnic_phylink_pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, - phy_interface_t interface, - const unsigned long *advertising, - bool permit_pause_to_mac) -{ - return 0; -} - -static const struct phylink_pcs_ops fbnic_phylink_pcs_ops = { - .pcs_config = fbnic_phylink_pcs_config, - .pcs_enable = fbnic_phylink_pcs_enable, - .pcs_disable = fbnic_phylink_pcs_disable, - .pcs_get_state = fbnic_phylink_pcs_get_state, -}; - -static struct phylink_pcs * -fbnic_phylink_mac_select_pcs(struct phylink_config *config, - phy_interface_t interface) +fbnic_phylink_mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t iface) { struct net_device *netdev = to_net_dev(config->dev); struct fbnic_net *fbn = netdev_priv(netdev); + struct fbnic_dev *fbd = fbn->fbd; - return &fbn->phylink_pcs; -} + /* Retest the link state and restart interrupts */ + fbd->mac->get_link(fbd, fbn->aui, fbn->fec); -static void -fbnic_phylink_mac_config(struct phylink_config *config, unsigned int mode, - const struct phylink_link_state *state) -{ + return 0; } static void @@ -194,8 +154,6 @@ fbnic_phylink_mac_link_down(struct phylink_config *config, unsigned int mode, struct fbnic_dev *fbd = fbn->fbd; fbd->mac->link_down(fbd); - - fbn->link_down_events++; } static void @@ -208,23 +166,48 @@ fbnic_phylink_mac_link_up(struct phylink_config *config, struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; + fbn->tx_pause = tx_pause; + fbnic_config_drop_mode(fbn, tx_pause); + fbd->mac->link_up(fbd, tx_pause, rx_pause); } static const struct phylink_mac_ops fbnic_phylink_mac_ops = { .mac_select_pcs = fbnic_phylink_mac_select_pcs, + .mac_prepare = fbnic_phylink_mac_prepare, .mac_config = fbnic_phylink_mac_config, + .mac_finish = fbnic_phylink_mac_finish, .mac_link_down = fbnic_phylink_mac_link_down, .mac_link_up = fbnic_phylink_mac_link_up, }; -int fbnic_phylink_init(struct net_device *netdev) +/** + * fbnic_phylink_create - Phylink device creation + * @netdev: Network Device struct to attach phylink device + * + * Initialize and attach a phylink instance to the device. The phylink + * device will make use of the netdev struct to track carrier and will + * eventually be used to expose the current state of the MAC and PCS + * setup. + * + * Return: 0 on success, negative on failure + **/ +int fbnic_phylink_create(struct net_device *netdev) { struct fbnic_net *fbn = netdev_priv(netdev); struct fbnic_dev *fbd = fbn->fbd; + struct phylink_pcs *pcs; struct phylink *phylink; + int err; + + pcs = xpcs_create_pcs_mdiodev(fbd->mdio_bus, 0); + if (IS_ERR(pcs)) { + err = PTR_ERR(pcs); + dev_err(fbd->dev, "Failed to create PCS device: %d\n", err); + return err; + } - fbn->phylink_pcs.ops = &fbnic_phylink_pcs_ops; + fbn->pcs = pcs; fbn->phylink_config.dev = &netdev->dev; fbn->phylink_config.type = PHYLINK_NETDEV; @@ -247,10 +230,57 @@ int fbnic_phylink_init(struct net_device *netdev) phylink = phylink_create(&fbn->phylink_config, NULL, fbnic_phylink_select_interface(fbn->aui), &fbnic_phylink_mac_ops); - if (IS_ERR(phylink)) - return PTR_ERR(phylink); + if (IS_ERR(phylink)) { + err = PTR_ERR(phylink); + dev_err(netdev->dev.parent, + "Failed to create Phylink interface, err: %d\n", err); + xpcs_destroy_pcs(pcs); + return err; + } fbn->phylink = phylink; return 0; } + +/** + * fbnic_phylink_destroy - Teardown phylink related interfaces + * @netdev: Network Device struct containing phylink device + * + * Detach and free resources related to phylink interface. + **/ +void fbnic_phylink_destroy(struct net_device *netdev) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + + if (fbn->phylink) + phylink_destroy(fbn->phylink); + if (fbn->pcs) + xpcs_destroy_pcs(fbn->pcs); +} + +/** + * fbnic_phylink_pmd_training_complete_notify - PMD training complete notifier + * @netdev: Netdev struct phylink device attached to + * + * When the link first comes up the PMD will have a period of 2 to 3 seconds + * where the link will flutter due to link training. To avoid spamming the + * kernel log with messages about this we add a delay of 4 seconds from the + * time of the last PCS report of link so that we can guarantee we are unlikely + * to see any further link loss events due to link training. + **/ +void fbnic_phylink_pmd_training_complete_notify(struct net_device *netdev) +{ + struct fbnic_net *fbn = netdev_priv(netdev); + struct fbnic_dev *fbd = fbn->fbd; + + if (fbd->pmd_state != FBNIC_PMD_TRAINING) + return; + + if (!time_before(fbd->end_of_pmd_training, jiffies)) + return; + + fbd->pmd_state = FBNIC_PMD_SEND_DATA; + + phylink_pcs_change(fbn->pcs, false); +} diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_time.c b/drivers/net/ethernet/meta/fbnic/fbnic_time.c index 39d99677b71ea..db7748189f457 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_time.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_time.c @@ -253,7 +253,7 @@ static void fbnic_ptp_reset(struct fbnic_dev *fbd) void fbnic_time_init(struct fbnic_net *fbn) { - /* This is not really a statistic, but the lockng primitive fits + /* This is not really a statistic, but the locking primitive fits * our usecase perfectly, we need an atomic 8 bytes READ_ONCE() / * WRITE_ONCE() behavior. */ diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h index c34bf87eeec95..3508b46ebdd00 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h @@ -80,7 +80,7 @@ struct fbnic_tlv_index { enum fbnic_tlv_type type; }; -#define TLV_MAX_DATA (PAGE_SIZE - 512) +#define TLV_MAX_DATA ((PAGE_SIZE - 512) & 0xFFFF) #define FBNIC_TLV_ATTR_ID_UNKNOWN USHRT_MAX #define FBNIC_TLV_ATTR_STRING(id, len) { id, len, FBNIC_TLV_STRING } #define FBNIC_TLV_ATTR_FLAG(id) { id, 0, FBNIC_TLV_FLAG } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index b1e8ce89870f7..c2d7b67fec286 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -887,6 +887,7 @@ static void fbnic_bd_prep(struct fbnic_ring *bdq, u16 id, netmem_ref netmem) *bdq_desc = cpu_to_le64(bd); bd += FIELD_PREP(FBNIC_BD_DESC_ADDR_MASK, 1) | FIELD_PREP(FBNIC_BD_DESC_ID_MASK, 1); + bdq_desc++; } while (--i); } @@ -2573,11 +2574,15 @@ static void fbnic_enable_bdq(struct fbnic_ring *hpq, struct fbnic_ring *ppq) } static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, - struct fbnic_ring *rcq) + struct fbnic_ring *rcq, bool tx_pause) { + struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 drop_mode, rcq_ctl; - drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_IMMEDIATE; + if (!tx_pause && fbn->num_rx_queues > 1) + drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_IMMEDIATE; + else + drop_mode = FBNIC_QUEUE_RDE_CTL0_DROP_NEVER; /* Specify packet layout */ rcq_ctl = FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_DROP_MODE_MASK, drop_mode) | @@ -2587,6 +2592,21 @@ static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl); } +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause) +{ + int i, t; + + for (i = 0; i < fbn->num_napi; i++) { + struct fbnic_napi_vector *nv = fbn->napi[i]; + + for (t = 0; t < nv->rxt_count; t++) { + struct fbnic_q_triad *qt = &nv->qt[nv->txt_count + t]; + + fbnic_config_drop_mode_rcq(nv, &qt->cmpl, tx_pause); + } + } +} + static void fbnic_config_rim_threshold(struct fbnic_ring *rcq, u16 nv_idx, u32 rx_desc) { u32 threshold; @@ -2636,7 +2656,7 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, u32 hds_thresh = fbn->hds_thresh; u32 rcq_ctl = 0; - fbnic_config_drop_mode_rcq(nv, rcq); + fbnic_config_drop_mode_rcq(nv, rcq, fbn->tx_pause); /* Force lower bound on MAX_HEADER_BYTES. Below this, all frames should * be split at L4. It would also result in the frames being split at @@ -2699,7 +2719,6 @@ static void __fbnic_nv_enable(struct fbnic_napi_vector *nv) &nv->napi); fbnic_enable_bdq(&qt->sub0, &qt->sub1); - fbnic_config_drop_mode_rcq(nv, &qt->cmpl); fbnic_enable_rcq(nv, &qt->cmpl); } } diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index ca37da5a0b179..27776e844e29b 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -184,6 +184,7 @@ void fbnic_reset_netif_queues(struct fbnic_net *fbn); irqreturn_t fbnic_msix_clean_rings(int irq, void *data); void fbnic_napi_enable(struct fbnic_net *fbn); void fbnic_napi_disable(struct fbnic_net *fbn); +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause); void fbnic_enable(struct fbnic_net *fbn); void fbnic_disable(struct fbnic_net *fbn); void fbnic_flush(struct fbnic_net *fbn); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index 40b1bfc600a79..582145713cfd1 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -395,6 +395,8 @@ static int sparx5_create_port(struct sparx5 *sparx5, spx5_port->phylink = phylink; + spx5_port->ndev->dev.of_node = spx5_port->of_node; + return 0; } diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c index 43f034e180c41..effe0a2f207aa 100644 --- a/drivers/net/ethernet/microsoft/mana/gdma_main.c +++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c @@ -528,6 +528,7 @@ static void mana_gd_process_eqe(struct gdma_queue *eq) case GDMA_EQE_HWC_INIT_DONE: case GDMA_EQE_HWC_SOC_SERVICE: case GDMA_EQE_RNIC_QP_FATAL: + case GDMA_EQE_HWC_SOC_RECONFIG_DATA: if (!eq->eq.callback) break; diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c index ada6c78a2bef4..aa4e2731e2ba7 100644 --- a/drivers/net/ethernet/microsoft/mana/hw_channel.c +++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c @@ -118,6 +118,7 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, struct gdma_dev *gd = hwc->gdma_dev; union hwc_init_type_data type_data; union hwc_init_eq_id_db eq_db; + struct mana_context *ac; u32 type, val; int ret; @@ -196,6 +197,17 @@ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self, hwc->hwc_timeout = val; break; + case HWC_DATA_HW_LINK_CONNECT: + case HWC_DATA_HW_LINK_DISCONNECT: + ac = gd->gdma_context->mana.driver_data; + if (!ac) + break; + + WRITE_ONCE(ac->link_event, type); + schedule_work(&ac->link_change_work); + + break; + default: dev_warn(hwc->dev, "Received unknown reconfig type %u\n", type); break; diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index 0142fd98392c2..13f47be7aca69 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -20,6 +20,7 @@ #include #include +#include static DEFINE_IDA(mana_adev_ida); @@ -84,7 +85,6 @@ static int mana_open(struct net_device *ndev) /* Ensure port state updated before txq state */ smp_wmb(); - netif_carrier_on(ndev); netif_tx_wake_all_queues(ndev); netdev_dbg(ndev, "%s successful\n", __func__); return 0; @@ -100,6 +100,46 @@ static int mana_close(struct net_device *ndev) return mana_detach(ndev, true); } +static void mana_link_state_handle(struct work_struct *w) +{ + struct mana_context *ac; + struct net_device *ndev; + u32 link_event; + bool link_up; + int i; + + ac = container_of(w, struct mana_context, link_change_work); + + rtnl_lock(); + + link_event = READ_ONCE(ac->link_event); + + if (link_event == HWC_DATA_HW_LINK_CONNECT) + link_up = true; + else if (link_event == HWC_DATA_HW_LINK_DISCONNECT) + link_up = false; + else + goto out; + + /* Process all ports */ + for (i = 0; i < ac->num_ports; i++) { + ndev = ac->ports[i]; + if (!ndev) + continue; + + if (link_up) { + netif_carrier_on(ndev); + + __netdev_notify_peers(ndev); + } else { + netif_carrier_off(ndev); + } + } + +out: + rtnl_unlock(); +} + static bool mana_can_tx(struct gdma_queue *wq) { return mana_gd_wq_avail_space(wq) >= MAX_TX_WQE_SIZE; @@ -494,6 +534,11 @@ static void mana_get_stats64(struct net_device *ndev, netdev_stats_to_stats64(st, &ndev->stats); + if (apc->ac->hwc_timeout_occurred) + netdev_warn_once(ndev, "HWC timeout occurred\n"); + + st->rx_missed_errors = apc->ac->hc_stats.hc_rx_discards_no_wqe; + for (q = 0; q < num_queues; q++) { rx_stats = &apc->rxqs[q]->stats; @@ -814,7 +859,7 @@ static int mana_shaper_del(struct net_shaper_binding *binding, /* Reset mana port context parameters */ apc->handle.id = 0; apc->handle.scope = NET_SHAPER_SCOPE_UNSPEC; - apc->speed = 0; + apc->speed = apc->max_speed; } return err; @@ -2769,11 +2814,12 @@ int mana_config_rss(struct mana_port_context *apc, enum TRI_STATE rx, return 0; } -void mana_query_gf_stats(struct mana_port_context *apc) +int mana_query_gf_stats(struct mana_context *ac) { + struct gdma_context *gc = ac->gdma_dev->gdma_context; struct mana_query_gf_stat_resp resp = {}; struct mana_query_gf_stat_req req = {}; - struct net_device *ndev = apc->ndev; + struct device *dev = gc->dev; int err; mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_GF_STAT, @@ -2807,52 +2853,54 @@ void mana_query_gf_stats(struct mana_port_context *apc) STATISTICS_FLAGS_HC_TX_BCAST_BYTES | STATISTICS_FLAGS_TX_ERRORS_GDMA_ERROR; - err = mana_send_request(apc->ac, &req, sizeof(req), &resp, + err = mana_send_request(ac, &req, sizeof(req), &resp, sizeof(resp)); if (err) { - netdev_err(ndev, "Failed to query GF stats: %d\n", err); - return; + dev_err(dev, "Failed to query GF stats: %d\n", err); + return err; } err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_GF_STAT, sizeof(resp)); if (err || resp.hdr.status) { - netdev_err(ndev, "Failed to query GF stats: %d, 0x%x\n", err, - resp.hdr.status); - return; + dev_err(dev, "Failed to query GF stats: %d, 0x%x\n", err, + resp.hdr.status); + return err; } - apc->eth_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; - apc->eth_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; - apc->eth_stats.hc_rx_bytes = resp.hc_rx_bytes; - apc->eth_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; - apc->eth_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; - apc->eth_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; - apc->eth_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; - apc->eth_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; - apc->eth_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; - apc->eth_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; - apc->eth_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; - apc->eth_stats.hc_tx_err_inval_vportoffset_pkt = + ac->hc_stats.hc_rx_discards_no_wqe = resp.rx_discards_nowqe; + ac->hc_stats.hc_rx_err_vport_disabled = resp.rx_err_vport_disabled; + ac->hc_stats.hc_rx_bytes = resp.hc_rx_bytes; + ac->hc_stats.hc_rx_ucast_pkts = resp.hc_rx_ucast_pkts; + ac->hc_stats.hc_rx_ucast_bytes = resp.hc_rx_ucast_bytes; + ac->hc_stats.hc_rx_bcast_pkts = resp.hc_rx_bcast_pkts; + ac->hc_stats.hc_rx_bcast_bytes = resp.hc_rx_bcast_bytes; + ac->hc_stats.hc_rx_mcast_pkts = resp.hc_rx_mcast_pkts; + ac->hc_stats.hc_rx_mcast_bytes = resp.hc_rx_mcast_bytes; + ac->hc_stats.hc_tx_err_gf_disabled = resp.tx_err_gf_disabled; + ac->hc_stats.hc_tx_err_vport_disabled = resp.tx_err_vport_disabled; + ac->hc_stats.hc_tx_err_inval_vportoffset_pkt = resp.tx_err_inval_vport_offset_pkt; - apc->eth_stats.hc_tx_err_vlan_enforcement = + ac->hc_stats.hc_tx_err_vlan_enforcement = resp.tx_err_vlan_enforcement; - apc->eth_stats.hc_tx_err_eth_type_enforcement = + ac->hc_stats.hc_tx_err_eth_type_enforcement = resp.tx_err_ethtype_enforcement; - apc->eth_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; - apc->eth_stats.hc_tx_err_sqpdid_enforcement = + ac->hc_stats.hc_tx_err_sa_enforcement = resp.tx_err_SA_enforcement; + ac->hc_stats.hc_tx_err_sqpdid_enforcement = resp.tx_err_SQPDID_enforcement; - apc->eth_stats.hc_tx_err_cqpdid_enforcement = + ac->hc_stats.hc_tx_err_cqpdid_enforcement = resp.tx_err_CQPDID_enforcement; - apc->eth_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; - apc->eth_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; - apc->eth_stats.hc_tx_bytes = resp.hc_tx_bytes; - apc->eth_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; - apc->eth_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; - apc->eth_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; - apc->eth_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; - apc->eth_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; - apc->eth_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; - apc->eth_stats.hc_tx_err_gdma = resp.tx_err_gdma; + ac->hc_stats.hc_tx_err_mtu_violation = resp.tx_err_mtu_violation; + ac->hc_stats.hc_tx_err_inval_oob = resp.tx_err_inval_oob; + ac->hc_stats.hc_tx_bytes = resp.hc_tx_bytes; + ac->hc_stats.hc_tx_ucast_pkts = resp.hc_tx_ucast_pkts; + ac->hc_stats.hc_tx_ucast_bytes = resp.hc_tx_ucast_bytes; + ac->hc_stats.hc_tx_bcast_pkts = resp.hc_tx_bcast_pkts; + ac->hc_stats.hc_tx_bcast_bytes = resp.hc_tx_bcast_bytes; + ac->hc_stats.hc_tx_mcast_pkts = resp.hc_tx_mcast_pkts; + ac->hc_stats.hc_tx_mcast_bytes = resp.hc_tx_mcast_bytes; + ac->hc_stats.hc_tx_err_gdma = resp.tx_err_gdma; + + return 0; } void mana_query_phy_stats(struct mana_port_context *apc) @@ -3059,9 +3107,6 @@ int mana_attach(struct net_device *ndev) /* Ensure port state updated before txq state */ smp_wmb(); - if (apc->port_is_up) - netif_carrier_on(ndev); - netif_device_attach(ndev); return 0; @@ -3154,7 +3199,6 @@ int mana_detach(struct net_device *ndev, bool from_close) smp_wmb(); netif_tx_disable(ndev); - netif_carrier_off(ndev); if (apc->port_st_save) { err = mana_dealloc_queues(ndev); @@ -3243,6 +3287,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx, goto free_indir; } + netif_carrier_on(ndev); + debugfs_create_u32("current_speed", 0400, apc->mana_port_debugfs, &apc->speed); return 0; @@ -3389,6 +3435,24 @@ int mana_rdma_service_event(struct gdma_context *gc, enum gdma_service_type even return 0; } +#define MANA_GF_STATS_PERIOD (2 * HZ) + +static void mana_gf_stats_work_handler(struct work_struct *work) +{ + struct mana_context *ac = + container_of(to_delayed_work(work), struct mana_context, gf_stats_work); + int err; + + err = mana_query_gf_stats(ac); + if (err == -ETIMEDOUT) { + /* HWC timeout detected - reset stats and stop rescheduling */ + ac->hwc_timeout_occurred = true; + memset(&ac->hc_stats, 0, sizeof(ac->hc_stats)); + return; + } + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); +} + int mana_probe(struct gdma_dev *gd, bool resuming) { struct gdma_context *gc = gd->gdma_context; @@ -3431,6 +3495,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) if (!resuming) { ac->num_ports = num_ports; + + INIT_WORK(&ac->link_change_work, mana_link_state_handle); } else { if (ac->num_ports != num_ports) { dev_err(dev, "The number of vPorts changed: %d->%d\n", @@ -3438,6 +3504,8 @@ int mana_probe(struct gdma_dev *gd, bool resuming) err = -EPROTO; goto out; } + + enable_work(&ac->link_change_work); } if (ac->num_ports == 0) @@ -3477,6 +3545,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming) } err = add_adev(gd, "eth"); + + INIT_DELAYED_WORK(&ac->gf_stats_work, mana_gf_stats_work_handler); + schedule_delayed_work(&ac->gf_stats_work, MANA_GF_STATS_PERIOD); + out: if (err) { mana_remove(gd, false); @@ -3500,6 +3572,9 @@ void mana_remove(struct gdma_dev *gd, bool suspending) int err; int i; + disable_work_sync(&ac->link_change_work); + cancel_delayed_work_sync(&ac->gf_stats_work); + /* adev currently doesn't support suspending, always remove it */ if (gd->adev) remove_adev(gd); diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c index a1afa75a94631..99e8112086833 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c +++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c @@ -15,66 +15,69 @@ struct mana_stats_desc { static const struct mana_stats_desc mana_eth_stats[] = { {"stop_queue", offsetof(struct mana_ethtool_stats, stop_queue)}, {"wake_queue", offsetof(struct mana_ethtool_stats, wake_queue)}, - {"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_stats, + {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, + {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + tx_cqe_unknown_type)}, + {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, + rx_coalesced_err)}, + {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, + rx_cqe_unknown_type)}, +}; + +static const struct mana_stats_desc mana_hc_stats[] = { + {"hc_rx_discards_no_wqe", offsetof(struct mana_ethtool_hc_stats, hc_rx_discards_no_wqe)}, - {"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_stats, + {"hc_rx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats, hc_rx_err_vport_disabled)}, - {"hc_rx_bytes", offsetof(struct mana_ethtool_stats, hc_rx_bytes)}, - {"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_rx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bytes)}, + {"hc_rx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_rx_ucast_pkts)}, - {"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_ucast_bytes)}, - {"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_rx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_rx_bcast_pkts)}, - {"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_bcast_bytes)}, - {"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_stats, - hc_rx_mcast_pkts)}, - {"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_rx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats, + hc_rx_mcast_pkts)}, + {"hc_rx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_rx_mcast_bytes)}, - {"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_gf_disabled", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_gf_disabled)}, - {"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_vport_disabled", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_vport_disabled)}, {"hc_tx_err_inval_vportoffset_pkt", - offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_inval_vportoffset_pkt)}, - {"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_vlan_enforcement", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_vlan_enforcement)}, {"hc_tx_err_eth_type_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_eth_type_enforcement)}, - {"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_eth_type_enforcement)}, + {"hc_tx_err_sa_enforcement", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sa_enforcement)}, {"hc_tx_err_sqpdid_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_sqpdid_enforcement)}, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_sqpdid_enforcement)}, {"hc_tx_err_cqpdid_enforcement", - offsetof(struct mana_ethtool_stats, hc_tx_err_cqpdid_enforcement)}, - {"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_stats, + offsetof(struct mana_ethtool_hc_stats, hc_tx_err_cqpdid_enforcement)}, + {"hc_tx_err_mtu_violation", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_mtu_violation)}, - {"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_inval_oob", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_inval_oob)}, - {"hc_tx_err_gdma", offsetof(struct mana_ethtool_stats, + {"hc_tx_err_gdma", offsetof(struct mana_ethtool_hc_stats, hc_tx_err_gdma)}, - {"hc_tx_bytes", offsetof(struct mana_ethtool_stats, hc_tx_bytes)}, - {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bytes)}, + {"hc_tx_ucast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_ucast_pkts)}, - {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_ucast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_ucast_bytes)}, - {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_bcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_bcast_pkts)}, - {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_bcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_bcast_bytes)}, - {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_stats, + {"hc_tx_mcast_pkts", offsetof(struct mana_ethtool_hc_stats, hc_tx_mcast_pkts)}, - {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_stats, + {"hc_tx_mcast_bytes", offsetof(struct mana_ethtool_hc_stats, hc_tx_mcast_bytes)}, - {"tx_cq_err", offsetof(struct mana_ethtool_stats, tx_cqe_err)}, - {"tx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, - tx_cqe_unknown_type)}, - {"rx_coalesced_err", offsetof(struct mana_ethtool_stats, - rx_coalesced_err)}, - {"rx_cqe_unknown_type", offsetof(struct mana_ethtool_stats, - rx_cqe_unknown_type)}, }; static const struct mana_stats_desc mana_phy_stats[] = { @@ -138,7 +141,7 @@ static int mana_get_sset_count(struct net_device *ndev, int stringset) if (stringset != ETH_SS_STATS) return -EINVAL; - return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + + return ARRAY_SIZE(mana_eth_stats) + ARRAY_SIZE(mana_phy_stats) + ARRAY_SIZE(mana_hc_stats) + num_queues * (MANA_STATS_RX_COUNT + MANA_STATS_TX_COUNT); } @@ -150,10 +153,12 @@ static void mana_get_strings(struct net_device *ndev, u32 stringset, u8 *data) if (stringset != ETH_SS_STATS) return; - for (i = 0; i < ARRAY_SIZE(mana_eth_stats); i++) ethtool_puts(&data, mana_eth_stats[i].name); + for (i = 0; i < ARRAY_SIZE(mana_hc_stats); i++) + ethtool_puts(&data, mana_hc_stats[i].name); + for (i = 0; i < ARRAY_SIZE(mana_phy_stats); i++) ethtool_puts(&data, mana_phy_stats[i].name); @@ -186,6 +191,7 @@ static void mana_get_ethtool_stats(struct net_device *ndev, struct mana_port_context *apc = netdev_priv(ndev); unsigned int num_queues = apc->num_queues; void *eth_stats = &apc->eth_stats; + void *hc_stats = &apc->ac->hc_stats; void *phy_stats = &apc->phy_stats; struct mana_stats_rx *rx_stats; struct mana_stats_tx *tx_stats; @@ -207,8 +213,6 @@ static void mana_get_ethtool_stats(struct net_device *ndev, if (!apc->port_is_up) return; - /* we call mana function to update stats from GDMA */ - mana_query_gf_stats(apc); /* We call this mana function to get the phy stats from GDMA and includes * aggregate tx/rx drop counters, Per-TC(Traffic Channel) tx/rx and pause @@ -219,6 +223,9 @@ static void mana_get_ethtool_stats(struct net_device *ndev, for (q = 0; q < ARRAY_SIZE(mana_eth_stats); q++) data[i++] = *(u64 *)(eth_stats + mana_eth_stats[q].offset); + for (q = 0; q < ARRAY_SIZE(mana_hc_stats); q++) + data[i++] = *(u64 *)(hc_stats + mana_hc_stats[q].offset); + for (q = 0; q < ARRAY_SIZE(mana_phy_stats); q++) data[i++] = *(u64 *)(phy_stats + mana_phy_stats[q].offset); diff --git a/drivers/net/ethernet/mucse/Kconfig b/drivers/net/ethernet/mucse/Kconfig new file mode 100644 index 0000000000000..0b3e853d625f1 --- /dev/null +++ b/drivers/net/ethernet/mucse/Kconfig @@ -0,0 +1,33 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Mucse network device configuration +# + +config NET_VENDOR_MUCSE + bool "Mucse devices" + default y + help + If you have a network (Ethernet) card from Mucse(R), say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Mucse(R) cards. If you say Y, you will + be asked for your specific card in the following questions. + +if NET_VENDOR_MUCSE + +config MGBE + tristate "Mucse(R) 1GbE PCI Express adapters support" + depends on PCI + help + This driver supports Mucse(R) 1GbE PCI Express family of + adapters. + + More specific information on configuring the driver is in + . + + To compile this driver as a module, choose M here. The module + will be called rnpgbe. + +endif # NET_VENDOR_MUCSE + diff --git a/drivers/net/ethernet/mucse/Makefile b/drivers/net/ethernet/mucse/Makefile new file mode 100644 index 0000000000000..675173fa05f74 --- /dev/null +++ b/drivers/net/ethernet/mucse/Makefile @@ -0,0 +1,7 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2020 - 2025 MUCSE Corporation. +# +# Makefile for the MUCSE(R) network device drivers +# + +obj-$(CONFIG_MGBE) += rnpgbe/ diff --git a/drivers/net/ethernet/mucse/rnpgbe/Makefile b/drivers/net/ethernet/mucse/rnpgbe/Makefile new file mode 100644 index 0000000000000..de8bcb7772ab4 --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2020 - 2025 MUCSE Corporation. +# +# Makefile for the MUCSE(R) 1GbE PCI Express ethernet driver +# + +obj-$(CONFIG_MGBE) += rnpgbe.o +rnpgbe-objs := rnpgbe_main.o\ + rnpgbe_chip.o\ + rnpgbe_mbx.o\ + rnpgbe_mbx_fw.o diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe.h new file mode 100644 index 0000000000000..5b024f9f7e17a --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#ifndef _RNPGBE_H +#define _RNPGBE_H + +#include +#include + +enum rnpgbe_boards { + board_n500, + board_n210 +}; + +struct mucse_mbx_info { + u32 timeout_us; + u32 delay_us; + u16 fw_req; + u16 fw_ack; + /* lock for only one use mbx */ + struct mutex lock; + /* fw <--> pf mbx */ + u32 fwpf_shm_base; + u32 pf2fw_mbx_ctrl; + u32 fwpf_mbx_mask; + u32 fwpf_ctrl_base; +}; + +/* Enum for firmware notification modes, + * more modes (e.g., portup, link_report) will be added in future + **/ +enum { + mucse_fw_powerup, +}; + +struct mucse_hw { + void __iomem *hw_addr; + struct pci_dev *pdev; + struct mucse_mbx_info mbx; + int port; + u8 pfvfnum; +}; + +struct mucse_stats { + u64 tx_dropped; +}; + +struct mucse { + struct net_device *netdev; + struct pci_dev *pdev; + struct mucse_hw hw; + struct mucse_stats stats; +}; + +int rnpgbe_get_permanent_mac(struct mucse_hw *hw, u8 *perm_addr); +int rnpgbe_reset_hw(struct mucse_hw *hw); +int rnpgbe_send_notify(struct mucse_hw *hw, + bool enable, + int mode); +int rnpgbe_init_hw(struct mucse_hw *hw, int board_type); + +/* Device IDs */ +#define PCI_VENDOR_ID_MUCSE 0x8848 +#define RNPGBE_DEVICE_ID_N500_QUAD_PORT 0x8308 +#define RNPGBE_DEVICE_ID_N500_DUAL_PORT 0x8318 +#define RNPGBE_DEVICE_ID_N210 0x8208 +#define RNPGBE_DEVICE_ID_N210L 0x820a + +#define mucse_hw_wr32(hw, reg, val) \ + writel((val), (hw)->hw_addr + (reg)) +#endif /* _RNPGBE_H */ diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_chip.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_chip.c new file mode 100644 index 0000000000000..ebc7b3750157b --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_chip.c @@ -0,0 +1,143 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#include +#include +#include + +#include "rnpgbe.h" +#include "rnpgbe_hw.h" +#include "rnpgbe_mbx.h" +#include "rnpgbe_mbx_fw.h" + +/** + * rnpgbe_get_permanent_mac - Get permanent mac + * @hw: hw information structure + * @perm_addr: pointer to store perm_addr + * + * rnpgbe_get_permanent_mac tries to get mac from hw + * + * Return: 0 on success, negative errno on failure + **/ +int rnpgbe_get_permanent_mac(struct mucse_hw *hw, u8 *perm_addr) +{ + struct device *dev = &hw->pdev->dev; + int err; + + err = mucse_mbx_get_macaddr(hw, hw->pfvfnum, perm_addr, hw->port); + if (err) { + dev_err(dev, "Failed to get MAC from FW %d\n", err); + return err; + } + + if (!is_valid_ether_addr(perm_addr)) { + dev_err(dev, "Failed to get valid MAC from FW\n"); + return -EINVAL; + } + + return 0; +} + +/** + * rnpgbe_reset_hw - Do a hardware reset + * @hw: hw information structure + * + * rnpgbe_reset_hw calls fw to do a hardware + * reset, and cleans some regs to default. + * + * Return: 0 on success, negative errno on failure + **/ +int rnpgbe_reset_hw(struct mucse_hw *hw) +{ + mucse_hw_wr32(hw, RNPGBE_DMA_AXI_EN, 0); + return mucse_mbx_reset_hw(hw); +} + +/** + * rnpgbe_send_notify - Echo fw status + * @hw: hw information structure + * @enable: true or false status + * @mode: status mode + * + * Return: 0 on success, negative errno on failure + **/ +int rnpgbe_send_notify(struct mucse_hw *hw, + bool enable, + int mode) +{ + int err; + /* Keep switch struct to support more modes in the future */ + switch (mode) { + case mucse_fw_powerup: + err = mucse_mbx_powerup(hw, enable); + break; + default: + err = -EINVAL; + } + + return err; +} + +/** + * rnpgbe_init_n500 - Setup n500 hw info + * @hw: hw information structure + * + * rnpgbe_init_n500 initializes all private + * structure for n500 + **/ +static void rnpgbe_init_n500(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + + mbx->fwpf_ctrl_base = MUCSE_N500_FWPF_CTRL_BASE; + mbx->fwpf_shm_base = MUCSE_N500_FWPF_SHM_BASE; +} + +/** + * rnpgbe_init_n210 - Setup n210 hw info + * @hw: hw information structure + * + * rnpgbe_init_n210 initializes all private + * structure for n210 + **/ +static void rnpgbe_init_n210(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + + mbx->fwpf_ctrl_base = MUCSE_N210_FWPF_CTRL_BASE; + mbx->fwpf_shm_base = MUCSE_N210_FWPF_SHM_BASE; +} + +/** + * rnpgbe_init_hw - Setup hw info according to board_type + * @hw: hw information structure + * @board_type: board type + * + * rnpgbe_init_hw initializes all hw data + * + * Return: 0 on success, -EINVAL on failure + **/ +int rnpgbe_init_hw(struct mucse_hw *hw, int board_type) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + + hw->port = 0; + + mbx->pf2fw_mbx_ctrl = MUCSE_GBE_PFFW_MBX_CTRL_OFFSET; + mbx->fwpf_mbx_mask = MUCSE_GBE_FWPF_MBX_MASK_OFFSET; + + switch (board_type) { + case board_n500: + rnpgbe_init_n500(hw); + break; + case board_n210: + rnpgbe_init_n210(hw); + break; + default: + return -EINVAL; + } + /* init_params with mbx base */ + mucse_init_mbx_params_pf(hw); + + return 0; +} diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_hw.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_hw.h new file mode 100644 index 0000000000000..e77e6bc3d3e30 --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_hw.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#ifndef _RNPGBE_HW_H +#define _RNPGBE_HW_H + +#define MUCSE_N500_FWPF_CTRL_BASE 0x28b00 +#define MUCSE_N500_FWPF_SHM_BASE 0x2d000 +#define MUCSE_GBE_PFFW_MBX_CTRL_OFFSET 0x5500 +#define MUCSE_GBE_FWPF_MBX_MASK_OFFSET 0x5700 +#define MUCSE_N210_FWPF_CTRL_BASE 0x29400 +#define MUCSE_N210_FWPF_SHM_BASE 0x2d900 + +#define RNPGBE_DMA_AXI_EN 0x0010 + +#define RNPGBE_MAX_QUEUES 8 +#endif /* _RNPGBE_HW_H */ diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c new file mode 100644 index 0000000000000..316f941629d4a --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_main.c @@ -0,0 +1,320 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#include +#include +#include + +#include "rnpgbe.h" +#include "rnpgbe_hw.h" +#include "rnpgbe_mbx_fw.h" + +static const char rnpgbe_driver_name[] = "rnpgbe"; + +/* rnpgbe_pci_tbl - PCI Device ID Table + * + * { PCI_VDEVICE(Vendor ID, Device ID), + * private_data (used for different hw chip) } + */ +static struct pci_device_id rnpgbe_pci_tbl[] = { + { PCI_VDEVICE(MUCSE, RNPGBE_DEVICE_ID_N210), board_n210 }, + { PCI_VDEVICE(MUCSE, RNPGBE_DEVICE_ID_N210L), board_n210 }, + { PCI_VDEVICE(MUCSE, RNPGBE_DEVICE_ID_N500_DUAL_PORT), board_n500 }, + { PCI_VDEVICE(MUCSE, RNPGBE_DEVICE_ID_N500_QUAD_PORT), board_n500 }, + /* required last entry */ + {0, }, +}; + +/** + * rnpgbe_open - Called when a network interface is made active + * @netdev: network interface device structure + * + * The open entry point is called when a network interface is made + * active by the system (IFF_UP). + * + * Return: 0 + **/ +static int rnpgbe_open(struct net_device *netdev) +{ + return 0; +} + +/** + * rnpgbe_close - Disables a network interface + * @netdev: network interface device structure + * + * The close entry point is called when an interface is de-activated + * by the OS. + * + * Return: 0, this is not allowed to fail + **/ +static int rnpgbe_close(struct net_device *netdev) +{ + return 0; +} + +/** + * rnpgbe_xmit_frame - Send a skb to driver + * @skb: skb structure to be sent + * @netdev: network interface device structure + * + * Return: NETDEV_TX_OK + **/ +static netdev_tx_t rnpgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + struct mucse *mucse = netdev_priv(netdev); + + dev_kfree_skb_any(skb); + mucse->stats.tx_dropped++; + + return NETDEV_TX_OK; +} + +static const struct net_device_ops rnpgbe_netdev_ops = { + .ndo_open = rnpgbe_open, + .ndo_stop = rnpgbe_close, + .ndo_start_xmit = rnpgbe_xmit_frame, +}; + +/** + * rnpgbe_add_adapter - Add netdev for this pci_dev + * @pdev: PCI device information structure + * @board_type: board type + * + * rnpgbe_add_adapter initializes a netdev for this pci_dev + * structure. Initializes Bar map, private structure, and a + * hardware reset occur. + * + * Return: 0 on success, negative errno on failure + **/ +static int rnpgbe_add_adapter(struct pci_dev *pdev, + int board_type) +{ + struct net_device *netdev; + u8 perm_addr[ETH_ALEN]; + void __iomem *hw_addr; + struct mucse *mucse; + struct mucse_hw *hw; + int err, err_notify; + + netdev = alloc_etherdev_mq(sizeof(struct mucse), RNPGBE_MAX_QUEUES); + if (!netdev) + return -ENOMEM; + + SET_NETDEV_DEV(netdev, &pdev->dev); + mucse = netdev_priv(netdev); + mucse->netdev = netdev; + mucse->pdev = pdev; + pci_set_drvdata(pdev, mucse); + + hw = &mucse->hw; + hw_addr = devm_ioremap(&pdev->dev, + pci_resource_start(pdev, 2), + pci_resource_len(pdev, 2)); + if (!hw_addr) { + err = -EIO; + goto err_free_net; + } + + hw->hw_addr = hw_addr; + hw->pdev = pdev; + + err = rnpgbe_init_hw(hw, board_type); + if (err) { + dev_err(&pdev->dev, "Init hw err %d\n", err); + goto err_free_net; + } + /* Step 1: Send power-up notification to firmware (no response expected) + * This informs firmware to initialize hardware power state, but + * firmware only acknowledges receipt without returning data. Must be + * done before synchronization as firmware may be in low-power idle + * state initially. + */ + err_notify = rnpgbe_send_notify(hw, true, mucse_fw_powerup); + if (err_notify) { + dev_warn(&pdev->dev, "Send powerup to hw failed %d\n", + err_notify); + dev_warn(&pdev->dev, "Maybe low performance\n"); + } + /* Step 2: Synchronize mailbox communication with firmware (requires + * response) After power-up, confirm firmware is ready to process + * requests with responses. This ensures subsequent request/response + * interactions work reliably. + */ + err = mucse_mbx_sync_fw(hw); + if (err) { + dev_err(&pdev->dev, "Sync fw failed! %d\n", err); + goto err_powerdown; + } + + netdev->netdev_ops = &rnpgbe_netdev_ops; + err = rnpgbe_reset_hw(hw); + if (err) { + dev_err(&pdev->dev, "Hw reset failed %d\n", err); + goto err_powerdown; + } + + err = rnpgbe_get_permanent_mac(hw, perm_addr); + if (!err) { + eth_hw_addr_set(netdev, perm_addr); + } else if (err == -EINVAL) { + dev_warn(&pdev->dev, "Using random MAC\n"); + eth_hw_addr_random(netdev); + } else if (err) { + dev_err(&pdev->dev, "get perm_addr failed %d\n", err); + goto err_powerdown; + } + + err = register_netdev(netdev); + if (err) + goto err_powerdown; + + return 0; +err_powerdown: + /* notify powerdown only powerup ok */ + if (!err_notify) { + err_notify = rnpgbe_send_notify(hw, false, mucse_fw_powerup); + if (err_notify) + dev_warn(&pdev->dev, "Send powerdown to hw failed %d\n", + err_notify); + } +err_free_net: + free_netdev(netdev); + return err; +} + +/** + * rnpgbe_probe - Device initialization routine + * @pdev: PCI device information struct + * @id: entry in rnpgbe_pci_tbl + * + * rnpgbe_probe initializes a PF adapter identified by a pci_dev + * structure. + * + * Return: 0 on success, negative errno on failure + **/ +static int rnpgbe_probe(struct pci_dev *pdev, const struct pci_device_id *id) +{ + int board_type = id->driver_data; + int err; + + err = pci_enable_device_mem(pdev); + if (err) + return err; + + err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(56)); + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting %d\n", err); + goto err_disable_dev; + } + + err = pci_request_mem_regions(pdev, rnpgbe_driver_name); + if (err) { + dev_err(&pdev->dev, + "pci_request_selected_regions failed %d\n", err); + goto err_disable_dev; + } + + pci_set_master(pdev); + err = pci_save_state(pdev); + if (err) { + dev_err(&pdev->dev, "pci_save_state failed %d\n", err); + goto err_free_regions; + } + + err = rnpgbe_add_adapter(pdev, board_type); + if (err) + goto err_free_regions; + + return 0; +err_free_regions: + pci_release_mem_regions(pdev); +err_disable_dev: + pci_disable_device(pdev); + return err; +} + +/** + * rnpgbe_rm_adapter - Remove netdev for this mucse structure + * @pdev: PCI device information struct + * + * rnpgbe_rm_adapter remove a netdev for this mucse structure + **/ +static void rnpgbe_rm_adapter(struct pci_dev *pdev) +{ + struct mucse *mucse = pci_get_drvdata(pdev); + struct mucse_hw *hw = &mucse->hw; + struct net_device *netdev; + int err; + + if (!mucse) + return; + netdev = mucse->netdev; + unregister_netdev(netdev); + err = rnpgbe_send_notify(hw, false, mucse_fw_powerup); + if (err) + dev_warn(&pdev->dev, "Send powerdown to hw failed %d\n", err); + free_netdev(netdev); +} + +/** + * rnpgbe_remove - Device removal routine + * @pdev: PCI device information struct + * + * rnpgbe_remove is called by the PCI subsystem to alert the driver + * that it should release a PCI device. This could be caused by a + * Hot-Plug event, or because the driver is going to be removed from + * memory. + **/ +static void rnpgbe_remove(struct pci_dev *pdev) +{ + rnpgbe_rm_adapter(pdev); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} + +/** + * rnpgbe_dev_shutdown - Device shutdown routine + * @pdev: PCI device information struct + **/ +static void rnpgbe_dev_shutdown(struct pci_dev *pdev) +{ + struct mucse *mucse = pci_get_drvdata(pdev); + struct net_device *netdev = mucse->netdev; + + rtnl_lock(); + netif_device_detach(netdev); + if (netif_running(netdev)) + rnpgbe_close(netdev); + rtnl_unlock(); + pci_disable_device(pdev); +} + +/** + * rnpgbe_shutdown - Device shutdown routine + * @pdev: PCI device information struct + * + * rnpgbe_shutdown is called by the PCI subsystem to alert the driver + * that os shutdown. Device should setup wakeup state here. + **/ +static void rnpgbe_shutdown(struct pci_dev *pdev) +{ + rnpgbe_dev_shutdown(pdev); +} + +static struct pci_driver rnpgbe_driver = { + .name = rnpgbe_driver_name, + .id_table = rnpgbe_pci_tbl, + .probe = rnpgbe_probe, + .remove = rnpgbe_remove, + .shutdown = rnpgbe_shutdown, +}; + +module_pci_driver(rnpgbe_driver); + +MODULE_DEVICE_TABLE(pci, rnpgbe_pci_tbl); +MODULE_AUTHOR("Yibo Dong, "); +MODULE_DESCRIPTION("Mucse(R) 1 Gigabit PCI Express Network Driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c new file mode 100644 index 0000000000000..de5e29230b3c8 --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2022 - 2025 Mucse Corporation. */ + +#include +#include +#include + +#include "rnpgbe_mbx.h" + +/** + * mbx_data_rd32 - Reads reg with base mbx->fwpf_shm_base + * @mbx: pointer to the MBX structure + * @reg: register offset + * + * Return: register value + **/ +static u32 mbx_data_rd32(struct mucse_mbx_info *mbx, u32 reg) +{ + struct mucse_hw *hw = container_of(mbx, struct mucse_hw, mbx); + + return readl(hw->hw_addr + mbx->fwpf_shm_base + reg); +} + +/** + * mbx_data_wr32 - Writes value to reg with base mbx->fwpf_shm_base + * @mbx: pointer to the MBX structure + * @reg: register offset + * @value: value to be written + * + **/ +static void mbx_data_wr32(struct mucse_mbx_info *mbx, u32 reg, u32 value) +{ + struct mucse_hw *hw = container_of(mbx, struct mucse_hw, mbx); + + writel(value, hw->hw_addr + mbx->fwpf_shm_base + reg); +} + +/** + * mbx_ctrl_rd32 - Reads reg with base mbx->fwpf_ctrl_base + * @mbx: pointer to the MBX structure + * @reg: register offset + * + * Return: register value + **/ +static u32 mbx_ctrl_rd32(struct mucse_mbx_info *mbx, u32 reg) +{ + struct mucse_hw *hw = container_of(mbx, struct mucse_hw, mbx); + + return readl(hw->hw_addr + mbx->fwpf_ctrl_base + reg); +} + +/** + * mbx_ctrl_wr32 - Writes value to reg with base mbx->fwpf_ctrl_base + * @mbx: pointer to the MBX structure + * @reg: register offset + * @value: value to be written + * + **/ +static void mbx_ctrl_wr32(struct mucse_mbx_info *mbx, u32 reg, u32 value) +{ + struct mucse_hw *hw = container_of(mbx, struct mucse_hw, mbx); + + writel(value, hw->hw_addr + mbx->fwpf_ctrl_base + reg); +} + +/** + * mucse_mbx_get_lock_pf - Write ctrl and read back lock status + * @hw: pointer to the HW structure + * + * Return: register value after write + **/ +static u32 mucse_mbx_get_lock_pf(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u32 reg = MUCSE_MBX_PF2FW_CTRL(mbx); + + mbx_ctrl_wr32(mbx, reg, MUCSE_MBX_PFU); + + return mbx_ctrl_rd32(mbx, reg); +} + +/** + * mucse_obtain_mbx_lock_pf - Obtain mailbox lock + * @hw: pointer to the HW structure + * + * Pair with mucse_release_mbx_lock_pf() + * This function maybe used in an irq handler. + * + * Return: 0 on success, negative errno on failure + **/ +static int mucse_obtain_mbx_lock_pf(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u32 val; + + return read_poll_timeout_atomic(mucse_mbx_get_lock_pf, + val, val & MUCSE_MBX_PFU, + mbx->delay_us, + mbx->timeout_us, + false, hw); +} + +/** + * mucse_release_mbx_lock_pf - Release mailbox lock + * @hw: pointer to the HW structure + * @req: send a request or not + * + * Pair with mucse_obtain_mbx_lock_pf(): + * - Releases the mailbox lock by clearing MUCSE_MBX_PFU bit + * - Simultaneously sends the request by setting MUCSE_MBX_REQ bit + * if req is true + * (Both bits are in the same mailbox control register, + * so operations are combined) + **/ +static void mucse_release_mbx_lock_pf(struct mucse_hw *hw, bool req) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u32 reg = MUCSE_MBX_PF2FW_CTRL(mbx); + + mbx_ctrl_wr32(mbx, reg, req ? MUCSE_MBX_REQ : 0); +} + +/** + * mucse_mbx_get_fwreq - Read fw req from reg + * @mbx: pointer to the mbx structure + * + * Return: the fwreq value + **/ +static u16 mucse_mbx_get_fwreq(struct mucse_mbx_info *mbx) +{ + u32 val = mbx_data_rd32(mbx, MUCSE_MBX_FW2PF_CNT); + + return FIELD_GET(GENMASK_U32(15, 0), val); +} + +/** + * mucse_mbx_inc_pf_ack - Increase ack + * @hw: pointer to the HW structure + * + * mucse_mbx_inc_pf_ack reads pf_ack from hw, then writes + * new value back after increase + **/ +static void mucse_mbx_inc_pf_ack(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u16 ack; + u32 val; + + val = mbx_data_rd32(mbx, MUCSE_MBX_PF2FW_CNT); + ack = FIELD_GET(GENMASK_U32(31, 16), val); + ack++; + val &= ~GENMASK_U32(31, 16); + val |= FIELD_PREP(GENMASK_U32(31, 16), ack); + mbx_data_wr32(mbx, MUCSE_MBX_PF2FW_CNT, val); +} + +/** + * mucse_read_mbx_pf - Read a message from the mailbox + * @hw: pointer to the HW structure + * @msg: the message buffer + * @size: length of buffer + * + * mucse_read_mbx_pf copies a message from the mbx buffer to the caller's + * memory buffer. The presumption is that the caller knows that there was + * a message due to a fw request so no polling for message is needed. + * + * Return: 0 on success, negative errno on failure + **/ +static int mucse_read_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) +{ + const int size_in_words = size / sizeof(u32); + struct mucse_mbx_info *mbx = &hw->mbx; + int err; + + err = mucse_obtain_mbx_lock_pf(hw); + if (err) + return err; + + for (int i = 0; i < size_in_words; i++) + msg[i] = mbx_data_rd32(mbx, MUCSE_MBX_FWPF_SHM + 4 * i); + /* Hw needs write data_reg at last */ + mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM, 0); + /* flush reqs as we have read this request data */ + hw->mbx.fw_req = mucse_mbx_get_fwreq(mbx); + mucse_mbx_inc_pf_ack(hw); + mucse_release_mbx_lock_pf(hw, false); + + return 0; +} + +/** + * mucse_check_for_msg_pf - Check to see if the fw has sent mail + * @hw: pointer to the HW structure + * + * Return: 0 if the fw has set the Status bit or else -EIO + **/ +static int mucse_check_for_msg_pf(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u16 fw_req; + + fw_req = mucse_mbx_get_fwreq(mbx); + /* chip's register is reset to 0 when rc send reset + * mbx command. Return -EIO if in this state, others + * fw == hw->mbx.fw_req means no new msg. + **/ + if (fw_req == 0 || fw_req == hw->mbx.fw_req) + return -EIO; + + return 0; +} + +/** + * mucse_poll_for_msg - Wait for message notification + * @hw: pointer to the HW structure + * + * Return: 0 on success, negative errno on failure + **/ +static int mucse_poll_for_msg(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + int val; + + return read_poll_timeout(mucse_check_for_msg_pf, + val, !val, mbx->delay_us, + mbx->timeout_us, + false, hw); +} + +/** + * mucse_poll_and_read_mbx - Wait for message notification and receive message + * @hw: pointer to the HW structure + * @msg: the message buffer + * @size: length of buffer + * + * Return: 0 if it successfully received a message notification and + * copied it into the receive buffer, negative errno on failure + **/ +int mucse_poll_and_read_mbx(struct mucse_hw *hw, u32 *msg, u16 size) +{ + int err; + + err = mucse_poll_for_msg(hw); + if (err) + return err; + + return mucse_read_mbx_pf(hw, msg, size); +} + +/** + * mucse_mbx_get_fwack - Read fw ack from reg + * @mbx: pointer to the MBX structure + * + * Return: the fwack value + **/ +static u16 mucse_mbx_get_fwack(struct mucse_mbx_info *mbx) +{ + u32 val = mbx_data_rd32(mbx, MUCSE_MBX_FW2PF_CNT); + + return FIELD_GET(GENMASK_U32(31, 16), val); +} + +/** + * mucse_mbx_inc_pf_req - Increase req + * @hw: pointer to the HW structure + * + * mucse_mbx_inc_pf_req reads pf_req from hw, then writes + * new value back after increase + **/ +static void mucse_mbx_inc_pf_req(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u16 req; + u32 val; + + val = mbx_data_rd32(mbx, MUCSE_MBX_PF2FW_CNT); + req = FIELD_GET(GENMASK_U32(15, 0), val); + req++; + val &= ~GENMASK_U32(15, 0); + val |= FIELD_PREP(GENMASK_U32(15, 0), req); + mbx_data_wr32(mbx, MUCSE_MBX_PF2FW_CNT, val); +} + +/** + * mucse_write_mbx_pf - Place a message in the mailbox + * @hw: pointer to the HW structure + * @msg: the message buffer + * @size: length of buffer + * + * Return: 0 if it successfully copied message into the buffer, + * negative errno on failure + **/ +static int mucse_write_mbx_pf(struct mucse_hw *hw, u32 *msg, u16 size) +{ + const int size_in_words = size / sizeof(u32); + struct mucse_mbx_info *mbx = &hw->mbx; + int err; + + err = mucse_obtain_mbx_lock_pf(hw); + if (err) + return err; + + for (int i = 0; i < size_in_words; i++) + mbx_data_wr32(mbx, MUCSE_MBX_FWPF_SHM + i * 4, msg[i]); + + /* flush acks as we are overwriting the message buffer */ + hw->mbx.fw_ack = mucse_mbx_get_fwack(mbx); + mucse_mbx_inc_pf_req(hw); + mucse_release_mbx_lock_pf(hw, true); + + return 0; +} + +/** + * mucse_check_for_ack_pf - Check to see if the fw has ACKed + * @hw: pointer to the HW structure + * + * Return: 0 if the fw has set the Status bit or else -EIO + **/ +static int mucse_check_for_ack_pf(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u16 fw_ack; + + fw_ack = mucse_mbx_get_fwack(mbx); + /* chip's register is reset to 0 when rc send reset + * mbx command. Return -EIO if in this state, others + * fw_ack == hw->mbx.fw_ack means no new ack. + **/ + if (fw_ack == 0 || fw_ack == hw->mbx.fw_ack) + return -EIO; + + return 0; +} + +/** + * mucse_poll_for_ack - Wait for message acknowledgment + * @hw: pointer to the HW structure + * + * Return: 0 if it successfully received a message acknowledgment, + * else negative errno + **/ +static int mucse_poll_for_ack(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + int val; + + return read_poll_timeout(mucse_check_for_ack_pf, + val, !val, mbx->delay_us, + mbx->timeout_us, + false, hw); +} + +/** + * mucse_write_and_wait_ack_mbx - Write a message to the mailbox, wait for ack + * @hw: pointer to the HW structure + * @msg: the message buffer + * @size: length of buffer + * + * Return: 0 if it successfully copied message into the buffer and + * received an ack to that message within delay * timeout_cnt period + **/ +int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, u32 *msg, u16 size) +{ + int err; + + err = mucse_write_mbx_pf(hw, msg, size); + if (err) + return err; + + return mucse_poll_for_ack(hw); +} + +/** + * mucse_mbx_reset - Reset mbx info, sync info from regs + * @hw: pointer to the HW structure + * + * mucse_mbx_reset resets all mbx variables to default. + **/ +static void mucse_mbx_reset(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + u32 val; + + val = mbx_data_rd32(mbx, MUCSE_MBX_FW2PF_CNT); + hw->mbx.fw_req = FIELD_GET(GENMASK_U32(15, 0), val); + hw->mbx.fw_ack = FIELD_GET(GENMASK_U32(31, 16), val); + mbx_ctrl_wr32(mbx, MUCSE_MBX_PF2FW_CTRL(mbx), 0); + mbx_ctrl_wr32(mbx, MUCSE_MBX_FWPF_MASK(mbx), GENMASK_U32(31, 16)); +} + +/** + * mucse_init_mbx_params_pf - Set initial values for pf mailbox + * @hw: pointer to the HW structure + * + * Initializes the hw->mbx struct to correct values for pf mailbox + */ +void mucse_init_mbx_params_pf(struct mucse_hw *hw) +{ + struct mucse_mbx_info *mbx = &hw->mbx; + + mbx->delay_us = 100; + mbx->timeout_us = 4 * USEC_PER_SEC; + mutex_init(&mbx->lock); + mucse_mbx_reset(hw); +} diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h new file mode 100644 index 0000000000000..e6fcc8d1d3ca7 --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx.h @@ -0,0 +1,20 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#ifndef _RNPGBE_MBX_H +#define _RNPGBE_MBX_H + +#include "rnpgbe.h" + +#define MUCSE_MBX_FW2PF_CNT 0 +#define MUCSE_MBX_PF2FW_CNT 4 +#define MUCSE_MBX_FWPF_SHM 8 +#define MUCSE_MBX_PF2FW_CTRL(mbx) ((mbx)->pf2fw_mbx_ctrl) +#define MUCSE_MBX_FWPF_MASK(mbx) ((mbx)->fwpf_mbx_mask) +#define MUCSE_MBX_REQ BIT(0) /* Request a req to mailbox */ +#define MUCSE_MBX_PFU BIT(3) /* PF owns the mailbox buffer */ + +int mucse_write_and_wait_ack_mbx(struct mucse_hw *hw, u32 *msg, u16 size); +void mucse_init_mbx_params_pf(struct mucse_hw *hw); +int mucse_poll_and_read_mbx(struct mucse_hw *hw, u32 *msg, u16 size); +#endif /* _RNPGBE_MBX_H */ diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c new file mode 100644 index 0000000000000..8c8bd5e8e1db1 --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#include +#include + +#include "rnpgbe.h" +#include "rnpgbe_mbx.h" +#include "rnpgbe_mbx_fw.h" + +/** + * mucse_fw_send_cmd_wait_resp - Send cmd req and wait for response + * @hw: pointer to the HW structure + * @req: pointer to the cmd req structure + * @reply: pointer to the fw reply structure + * + * mucse_fw_send_cmd_wait_resp sends req to pf-fw mailbox and wait + * reply from fw. + * + * Return: 0 on success, negative errno on failure + **/ +static int mucse_fw_send_cmd_wait_resp(struct mucse_hw *hw, + struct mbx_fw_cmd_req *req, + struct mbx_fw_cmd_reply *reply) +{ + int len = le16_to_cpu(req->datalen); + int retry_cnt = 3; + int err; + + mutex_lock(&hw->mbx.lock); + err = mucse_write_and_wait_ack_mbx(hw, (u32 *)req, len); + if (err) + goto out; + do { + err = mucse_poll_and_read_mbx(hw, (u32 *)reply, + sizeof(*reply)); + if (err) + goto out; + /* mucse_write_and_wait_ack_mbx return 0 means fw has + * received request, wait for the expect opcode + * reply with 'retry_cnt' times. + */ + } while (--retry_cnt >= 0 && reply->opcode != req->opcode); +out: + mutex_unlock(&hw->mbx.lock); + if (!err && retry_cnt < 0) + return -ETIMEDOUT; + if (!err && reply->error_code) + return -EIO; + + return err; +} + +/** + * mucse_mbx_get_info - Get hw info from fw + * @hw: pointer to the HW structure + * + * mucse_mbx_get_info tries to get hw info from hw. + * + * Return: 0 on success, negative errno on failure + **/ +static int mucse_mbx_get_info(struct mucse_hw *hw) +{ + struct mbx_fw_cmd_req req = { + .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(GET_HW_INFO), + }; + struct mbx_fw_cmd_reply reply = {}; + int err; + + err = mucse_fw_send_cmd_wait_resp(hw, &req, &reply); + if (!err) + hw->pfvfnum = FIELD_GET(GENMASK_U16(7, 0), + le16_to_cpu(reply.hw_info.pfnum)); + + return err; +} + +/** + * mucse_mbx_sync_fw - Try to sync with fw + * @hw: pointer to the HW structure + * + * mucse_mbx_sync_fw tries to sync with fw. It is only called in + * probe. Nothing (register network) todo if failed. + * Try more times to do sync. + * + * Return: 0 on success, negative errno on failure + **/ +int mucse_mbx_sync_fw(struct mucse_hw *hw) +{ + int try_cnt = 3; + int err; + + do { + err = mucse_mbx_get_info(hw); + } while (err == -ETIMEDOUT && try_cnt--); + + return err; +} + +/** + * mucse_mbx_powerup - Echo fw to powerup + * @hw: pointer to the HW structure + * @is_powerup: true for powerup, false for powerdown + * + * mucse_mbx_powerup echo fw to change working frequency + * to normal after received true, and reduce working frequency + * if false. + * + * Return: 0 on success, negative errno on failure + **/ +int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup) +{ + struct mbx_fw_cmd_req req = { + .datalen = cpu_to_le16(sizeof(req.powerup) + + MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(POWER_UP), + .powerup = { + /* fw needs this to reply correct cmd */ + .version = cpu_to_le32(GENMASK_U32(31, 0)), + .status = cpu_to_le32(is_powerup ? 1 : 0), + }, + }; + int len, err; + + len = le16_to_cpu(req.datalen); + mutex_lock(&hw->mbx.lock); + err = mucse_write_and_wait_ack_mbx(hw, (u32 *)&req, len); + mutex_unlock(&hw->mbx.lock); + + return err; +} + +/** + * mucse_mbx_reset_hw - Posts a mbx req to reset hw + * @hw: pointer to the HW structure + * + * mucse_mbx_reset_hw posts a mbx req to firmware to reset hw. + * We use mucse_fw_send_cmd_wait_resp to wait hw reset ok. + * + * Return: 0 on success, negative errno on failure + **/ +int mucse_mbx_reset_hw(struct mucse_hw *hw) +{ + struct mbx_fw_cmd_req req = { + .datalen = cpu_to_le16(MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(RESET_HW), + }; + struct mbx_fw_cmd_reply reply = {}; + + return mucse_fw_send_cmd_wait_resp(hw, &req, &reply); +} + +/** + * mucse_mbx_get_macaddr - Posts a mbx req to request macaddr + * @hw: pointer to the HW structure + * @pfvfnum: index of pf/vf num + * @mac_addr: pointer to store mac_addr + * @port: port index + * + * mucse_mbx_get_macaddr posts a mbx req to firmware to get mac_addr. + * + * Return: 0 on success, negative errno on failure + **/ +int mucse_mbx_get_macaddr(struct mucse_hw *hw, int pfvfnum, + u8 *mac_addr, + int port) +{ + struct mbx_fw_cmd_req req = { + .datalen = cpu_to_le16(sizeof(req.get_mac_addr) + + MUCSE_MBX_REQ_HDR_LEN), + .opcode = cpu_to_le16(GET_MAC_ADDRESS), + .get_mac_addr = { + .port_mask = cpu_to_le32(BIT(port)), + .pfvf_num = cpu_to_le32(pfvfnum), + }, + }; + struct mbx_fw_cmd_reply reply = {}; + int err; + + err = mucse_fw_send_cmd_wait_resp(hw, &req, &reply); + if (err) + return err; + + if (le32_to_cpu(reply.mac_addr.ports) & BIT(port)) + memcpy(mac_addr, reply.mac_addr.addrs[port].mac, ETH_ALEN); + else + return -ENODATA; + + return 0; +} diff --git a/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h new file mode 100644 index 0000000000000..fb24fc12b6139 --- /dev/null +++ b/drivers/net/ethernet/mucse/rnpgbe/rnpgbe_mbx_fw.h @@ -0,0 +1,88 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2020 - 2025 Mucse Corporation. */ + +#ifndef _RNPGBE_MBX_FW_H +#define _RNPGBE_MBX_FW_H + +#include + +#include "rnpgbe.h" + +#define MUCSE_MBX_REQ_HDR_LEN 24 + +enum MUCSE_FW_CMD { + GET_HW_INFO = 0x0601, + GET_MAC_ADDRESS = 0x0602, + RESET_HW = 0x0603, + POWER_UP = 0x0803, +}; + +struct mucse_hw_info { + u8 link_stat; + u8 port_mask; + __le32 speed; + __le16 phy_type; + __le16 nic_mode; + __le16 pfnum; + __le32 fw_version; + __le32 axi_mhz; + union { + u8 port_id[4]; + __le32 port_ids; + }; + __le32 bd_uid; + __le32 phy_id; + __le32 wol_status; + __le32 ext_info; +} __packed; + +struct mbx_fw_cmd_req { + __le16 flags; + __le16 opcode; + __le16 datalen; + __le16 ret_value; + __le32 cookie_lo; + __le32 cookie_hi; + __le32 reply_lo; + __le32 reply_hi; + union { + u8 data[32]; + struct { + __le32 version; + __le32 status; + } powerup; + struct { + __le32 port_mask; + __le32 pfvf_num; + } get_mac_addr; + }; +} __packed; + +struct mbx_fw_cmd_reply { + __le16 flags; + __le16 opcode; + __le16 error_code; + __le16 datalen; + __le32 cookie_lo; + __le32 cookie_hi; + union { + u8 data[40]; + struct mac_addr { + __le32 ports; + struct _addr { + /* for macaddr:01:02:03:04:05:06 + * mac-hi=0x01020304 mac-lo=0x05060000 + */ + u8 mac[8]; + } addrs[4]; + } mac_addr; + struct mucse_hw_info hw_info; + }; +} __packed; + +int mucse_mbx_sync_fw(struct mucse_hw *hw); +int mucse_mbx_powerup(struct mucse_hw *hw, bool is_powerup); +int mucse_mbx_reset_hw(struct mucse_hw *hw); +int mucse_mbx_get_macaddr(struct mucse_hw *hw, int pfvfnum, + u8 *mac_addr, int port); +#endif /* _RNPGBE_MBX_FW_H */ diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index e5a6f59af0b63..62f05f4569b10 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -198,23 +198,21 @@ pch_tx_timestamp(struct pch_gbe_adapter *adapter, struct sk_buff *skb) pch_ch_event_write(pdev, TX_SNAPSHOT_LOCKED); } -static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) +static int pch_gbe_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { - struct hwtstamp_config cfg; struct pch_gbe_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev; u8 station[20]; - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; - /* Get ieee1588's dev information */ pdev = adapter->ptp_pdev; - if (cfg.tx_type != HWTSTAMP_TX_OFF && cfg.tx_type != HWTSTAMP_TX_ON) + if (cfg->tx_type != HWTSTAMP_TX_OFF && cfg->tx_type != HWTSTAMP_TX_ON) return -ERANGE; - switch (cfg.rx_filter) { + switch (cfg->rx_filter) { case HWTSTAMP_FILTER_NONE: adapter->hwts_rx_en = 0; break; @@ -223,17 +221,17 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) pch_ch_control_write(pdev, SLAVE_MODE | CAP_MODE0); break; case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - adapter->hwts_rx_en = 1; + adapter->hwts_rx_en = cfg->rx_filter; pch_ch_control_write(pdev, MASTER_MODE | CAP_MODE0); break; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - adapter->hwts_rx_en = 1; + adapter->hwts_rx_en = cfg->rx_filter; pch_ch_control_write(pdev, V2_MODE | CAP_MODE2); strcpy(station, PTP_L4_MULTICAST_SA); pch_set_station_address(station, pdev); break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - adapter->hwts_rx_en = 1; + adapter->hwts_rx_en = cfg->rx_filter; pch_ch_control_write(pdev, V2_MODE | CAP_MODE2); strcpy(station, PTP_L2_MULTICAST_SA); pch_set_station_address(station, pdev); @@ -242,12 +240,23 @@ static int hwtstamp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return -ERANGE; } - adapter->hwts_tx_en = cfg.tx_type == HWTSTAMP_TX_ON; + adapter->hwts_tx_en = cfg->tx_type == HWTSTAMP_TX_ON; /* Clear out any old time stamps. */ pch_ch_event_write(pdev, TX_SNAPSHOT_LOCKED | RX_SNAPSHOT_LOCKED); - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + return 0; +} + +static int pch_gbe_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg) +{ + struct pch_gbe_adapter *adapter = netdev_priv(netdev); + + cfg->tx_type = adapter->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + cfg->rx_filter = adapter->hwts_rx_en; + + return 0; } static inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw) @@ -2234,9 +2243,6 @@ static int pch_gbe_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) netdev_dbg(netdev, "cmd : 0x%04x\n", cmd); - if (cmd == SIOCSHWTSTAMP) - return hwtstamp_ioctl(netdev, ifr, cmd); - return generic_mii_ioctl(&adapter->mii, if_mii(ifr), cmd, NULL); } @@ -2328,6 +2334,8 @@ static const struct net_device_ops pch_gbe_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = pch_gbe_netpoll, #endif + .ndo_hwtstamp_get = pch_gbe_hwtstamp_get, + .ndo_hwtstamp_set = pch_gbe_hwtstamp_set, }; static pci_ers_result_t pch_gbe_io_error_detected(struct pci_dev *pdev, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c index b28966ae50c22..058eea86e141c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -2335,20 +2335,6 @@ static int ionic_stop(struct net_device *netdev) return 0; } -static int ionic_eth_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) -{ - struct ionic_lif *lif = netdev_priv(netdev); - - switch (cmd) { - case SIOCSHWTSTAMP: - return ionic_lif_hwstamp_set(lif, ifr); - case SIOCGHWTSTAMP: - return ionic_lif_hwstamp_get(lif, ifr); - default: - return -EOPNOTSUPP; - } -} - static int ionic_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivf) { @@ -2812,7 +2798,6 @@ static int ionic_xdp(struct net_device *netdev, struct netdev_bpf *bpf) static const struct net_device_ops ionic_netdev_ops = { .ndo_open = ionic_open, .ndo_stop = ionic_stop, - .ndo_eth_ioctl = ionic_eth_ioctl, .ndo_start_xmit = ionic_start_xmit, .ndo_bpf = ionic_xdp, .ndo_xdp_xmit = ionic_xdp_xmit, @@ -2833,6 +2818,8 @@ static const struct net_device_ops ionic_netdev_ops = { .ndo_get_vf_config = ionic_get_vf_config, .ndo_set_vf_link_state = ionic_set_vf_link_state, .ndo_get_vf_stats = ionic_get_vf_stats, + .ndo_hwtstamp_get = ionic_hwstamp_get, + .ndo_hwtstamp_set = ionic_hwstamp_set, }; static int ionic_cmb_reconfig(struct ionic_lif *lif, diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h index 43bdd0fb87336..8e10f66dc50e9 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_lif.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include #include "ionic_rx_filter.h" @@ -254,7 +254,7 @@ struct ionic_phc { struct timecounter tc; struct mutex config_lock; /* lock for ts_config */ - struct hwtstamp_config ts_config; + struct kernel_hwtstamp_config ts_config; u64 ts_config_rx_filt; u32 ts_config_tx_mode; @@ -362,8 +362,11 @@ int ionic_lif_size(struct ionic *ionic); #if IS_ENABLED(CONFIG_PTP_1588_CLOCK) void ionic_lif_hwstamp_replay(struct ionic_lif *lif); void ionic_lif_hwstamp_recreate_queues(struct ionic_lif *lif); -int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr); -int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr); +int ionic_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +int ionic_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config); ktime_t ionic_lif_phc_ktime(struct ionic_lif *lif, u64 counter); void ionic_lif_register_phc(struct ionic_lif *lif); void ionic_lif_unregister_phc(struct ionic_lif *lif); @@ -373,12 +376,15 @@ void ionic_lif_free_phc(struct ionic_lif *lif); static inline void ionic_lif_hwstamp_replay(struct ionic_lif *lif) {} static inline void ionic_lif_hwstamp_recreate_queues(struct ionic_lif *lif) {} -static inline int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) +static inline int ionic_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -static inline int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr) +static inline int ionic_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c index 9f5c81d44f995..05b44fc482f87 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c @@ -65,11 +65,12 @@ static u64 ionic_hwstamp_rx_filt(int config_rx_filter) } static int ionic_lif_hwstamp_set_ts_config(struct ionic_lif *lif, - struct hwtstamp_config *new_ts) + struct kernel_hwtstamp_config *new_ts, + struct netlink_ext_ack *extack) { + struct kernel_hwtstamp_config *config; + struct kernel_hwtstamp_config ts = {}; struct ionic *ionic = lif->ionic; - struct hwtstamp_config *config; - struct hwtstamp_config ts; int tx_mode = 0; u64 rx_filt = 0; int err, err2; @@ -99,12 +100,16 @@ static int ionic_lif_hwstamp_set_ts_config(struct ionic_lif *lif, tx_mode = ionic_hwstamp_tx_mode(config->tx_type); if (tx_mode < 0) { + NL_SET_ERR_MSG_MOD(extack, + "TX time stamping mode isn't supported"); err = tx_mode; goto err_queues; } mask = cpu_to_le64(BIT_ULL(tx_mode)); if ((ionic->ident.lif.eth.hwstamp_tx_modes & mask) != mask) { + NL_SET_ERR_MSG_MOD(extack, + "TX time stamping mode isn't supported"); err = -ERANGE; goto err_queues; } @@ -124,32 +129,47 @@ static int ionic_lif_hwstamp_set_ts_config(struct ionic_lif *lif, if (tx_mode) { err = ionic_lif_create_hwstamp_txq(lif); - if (err) + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Error creating TX timestamp queue"); goto err_queues; + } } if (rx_filt) { err = ionic_lif_create_hwstamp_rxq(lif); - if (err) + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Error creating RX timestamp queue"); goto err_queues; + } } if (tx_mode != lif->phc->ts_config_tx_mode) { err = ionic_lif_set_hwstamp_txmode(lif, tx_mode); - if (err) + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Error enabling TX timestamp mode"); goto err_txmode; + } } if (rx_filt != lif->phc->ts_config_rx_filt) { err = ionic_lif_set_hwstamp_rxfilt(lif, rx_filt); - if (err) + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Error enabling RX timestamp mode"); goto err_rxfilt; + } } if (rx_all != (lif->phc->ts_config.rx_filter == HWTSTAMP_FILTER_ALL)) { err = ionic_lif_config_hwstamp_rxq_all(lif, rx_all); - if (err) + if (err) { + NL_SET_ERR_MSG_MOD(extack, + "Error enabling RX timestamp mode"); goto err_rxall; + } } memcpy(&lif->phc->ts_config, config, sizeof(*config)); @@ -183,28 +203,24 @@ static int ionic_lif_hwstamp_set_ts_config(struct ionic_lif *lif, return err; } -int ionic_lif_hwstamp_set(struct ionic_lif *lif, struct ifreq *ifr) +int ionic_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { - struct hwtstamp_config config; + struct ionic_lif *lif = netdev_priv(netdev); int err; if (!lif->phc || !lif->phc->ptp) return -EOPNOTSUPP; - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - mutex_lock(&lif->queue_lock); - err = ionic_lif_hwstamp_set_ts_config(lif, &config); + err = ionic_lif_hwstamp_set_ts_config(lif, config, extack); mutex_unlock(&lif->queue_lock); if (err) { netdev_info(lif->netdev, "hwstamp set failed: %d\n", err); return err; } - if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) - return -EFAULT; - return 0; } @@ -216,7 +232,7 @@ void ionic_lif_hwstamp_replay(struct ionic_lif *lif) return; mutex_lock(&lif->queue_lock); - err = ionic_lif_hwstamp_set_ts_config(lif, NULL); + err = ionic_lif_hwstamp_set_ts_config(lif, NULL, NULL); mutex_unlock(&lif->queue_lock); if (err) netdev_info(lif->netdev, "hwstamp replay failed: %d\n", err); @@ -246,19 +262,18 @@ void ionic_lif_hwstamp_recreate_queues(struct ionic_lif *lif) mutex_unlock(&lif->phc->config_lock); } -int ionic_lif_hwstamp_get(struct ionic_lif *lif, struct ifreq *ifr) +int ionic_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) { - struct hwtstamp_config config; + struct ionic_lif *lif = netdev_priv(netdev); if (!lif->phc || !lif->phc->ptp) return -EOPNOTSUPP; mutex_lock(&lif->phc->config_lock); - memcpy(&config, &lif->phc->ts_config, sizeof(config)); + memcpy(config, &lif->phc->ts_config, sizeof(*config)); mutex_unlock(&lif->phc->config_lock); - if (copy_to_user(ifr->ifr_data, &config, sizeof(config))) - return -EFAULT; return 0; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c index 847fa62c80df8..e338bfc8b7b2f 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_fp.c +++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c @@ -4,6 +4,7 @@ * Copyright (c) 2019-2020 Marvell International Ltd. */ +#include #include #include #include @@ -960,7 +961,7 @@ static inline void qede_tpa_cont(struct qede_dev *edev, { int i; - for (i = 0; cqe->len_list[i]; i++) + for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++) qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, le16_to_cpu(cqe->len_list[i])); @@ -985,7 +986,7 @@ static int qede_tpa_end(struct qede_dev *edev, dma_unmap_page(rxq->dev, tpa_info->buffer.mapping, PAGE_SIZE, rxq->data_direction); - for (i = 0; cqe->len_list[i]; i++) + for (i = 0; cqe->len_list[i] && i < ARRAY_SIZE(cqe->len_list); i++) qede_fill_frag_skb(edev, rxq, cqe->tpa_agg_index, le16_to_cpu(cqe->len_list[i])); if (unlikely(i > 1)) diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index d18734fe12e42..de304d1eb477c 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -57,6 +57,7 @@ #define FIRMWARE_8125B_2 "rtl_nic/rtl8125b-2.fw" #define FIRMWARE_8125D_1 "rtl_nic/rtl8125d-1.fw" #define FIRMWARE_8125D_2 "rtl_nic/rtl8125d-2.fw" +#define FIRMWARE_8125K_1 "rtl_nic/rtl8125k-1.fw" #define FIRMWARE_8125BP_2 "rtl_nic/rtl8125bp-2.fw" #define FIRMWARE_8126A_2 "rtl_nic/rtl8126a-2.fw" #define FIRMWARE_8126A_3 "rtl_nic/rtl8126a-3.fw" @@ -110,6 +111,7 @@ static const struct rtl_chip_info { { 0x7cf, 0x681, RTL_GIGA_MAC_VER_66, "RTL8125BP", FIRMWARE_8125BP_2 }, /* 8125D family. */ + { 0x7cf, 0x68a, RTL_GIGA_MAC_VER_64, "RTL8125K", FIRMWARE_8125K_1 }, { 0x7cf, 0x689, RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_2 }, { 0x7cf, 0x688, RTL_GIGA_MAC_VER_64, "RTL8125D", FIRMWARE_8125D_1 }, @@ -770,6 +772,7 @@ MODULE_FIRMWARE(FIRMWARE_8125A_3); MODULE_FIRMWARE(FIRMWARE_8125B_2); MODULE_FIRMWARE(FIRMWARE_8125D_1); MODULE_FIRMWARE(FIRMWARE_8125D_2); +MODULE_FIRMWARE(FIRMWARE_8125K_1); MODULE_FIRMWARE(FIRMWARE_8125BP_2); MODULE_FIRMWARE(FIRMWARE_8126A_2); MODULE_FIRMWARE(FIRMWARE_8126A_3); @@ -4995,9 +4998,7 @@ static int rtl8169_resume(struct device *device) clk_prepare_enable(tp->clk); /* Some chip versions may truncate packets without this initialization */ - if (tp->mac_version == RTL_GIGA_MAC_VER_37 || - tp->mac_version == RTL_GIGA_MAC_VER_46) - rtl_init_rxcfg(tp); + rtl_init_rxcfg(tp); return rtl8169_runtime_resume(device); } @@ -5450,6 +5451,15 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } tp->aspm_manageable = !rc; + /* Fiber mode on RTL8127AF isn't supported */ + if (rtl_is_8125(tp)) { + u16 data = r8168_mac_ocp_read(tp, 0xd006); + + if ((data & 0xff) == 0x07) + return dev_err_probe(&pdev->dev, -ENODEV, + "Fiber mode not supported\n"); + } + tp->dash_type = rtl_get_dash_type(tp); tp->dash_enabled = rtl_dash_is_enabled(tp); diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index 7b48060c250b4..5e56ec9b1013a 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -35,16 +35,6 @@ /* Driver's parameters */ #define RAVB_ALIGN 128 -/* Hardware time stamp */ -#define RAVB_TXTSTAMP_VALID 0x00000001 /* TX timestamp valid */ -#define RAVB_TXTSTAMP_ENABLED 0x00000010 /* Enable TX timestamping */ - -#define RAVB_RXTSTAMP_VALID 0x00000001 /* RX timestamp valid */ -#define RAVB_RXTSTAMP_TYPE 0x00000006 /* RX type mask */ -#define RAVB_RXTSTAMP_TYPE_V2_L2_EVENT 0x00000002 -#define RAVB_RXTSTAMP_TYPE_ALL 0x00000006 -#define RAVB_RXTSTAMP_ENABLED 0x00000010 /* Enable RX timestamping */ - enum ravb_reg { /* AVB-DMAC registers */ CCC = 0x0000, @@ -1017,7 +1007,6 @@ enum CSR2_BIT { #define CSR2_CSUM_ENABLE (CSR2_RTCP4 | CSR2_RUDP4 | CSR2_RICMP4 | \ CSR2_RTCP6 | CSR2_RUDP6 | CSR2_RICMP6) -#define DBAT_ENTRY_NUM 22 #define RX_QUEUE_OFFSET 4 #define NUM_RX_QUEUE 2 #define NUM_TX_QUEUE 2 @@ -1062,6 +1051,7 @@ struct ravb_hw_info { u32 rx_max_frame_size; u32 rx_buffer_size; u32 rx_desc_size; + u32 dbat_entry_num; unsigned aligned_tx: 1; unsigned coalesce_irqs:1; /* Needs software IRQ coalescing */ @@ -1114,8 +1104,8 @@ struct ravb_private { u32 rx_over_errors; u32 rx_fifo_errors; struct net_device_stats stats[NUM_RX_QUEUE]; - u32 tstamp_tx_ctrl; - u32 tstamp_rx_ctrl; + enum hwtstamp_tx_types tstamp_tx_ctrl; + enum hwtstamp_rx_filters tstamp_rx_ctrl; struct list_head ts_skb_list; u32 ts_skb_tag; struct ravb_ptp ptp; diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index e2d7ce1a85e84..57b0db314fb5e 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -946,6 +946,30 @@ static int ravb_rx_gbeth(struct net_device *ndev, int budget, int q) return rx_packets; } +static void ravb_rx_rcar_hwstamp(struct ravb_private *priv, int q, + struct ravb_ex_rx_desc *desc, + struct sk_buff *skb) +{ + struct skb_shared_hwtstamps *shhwtstamps; + struct timespec64 ts; + bool get_ts; + + if (q == RAVB_NC) + get_ts = priv->tstamp_rx_ctrl != HWTSTAMP_FILTER_NONE; + else + get_ts = priv->tstamp_rx_ctrl == HWTSTAMP_FILTER_ALL; + + if (!get_ts) + return; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + ts.tv_sec = ((u64)le16_to_cpu(desc->ts_sh) << 32) + | le32_to_cpu(desc->ts_sl); + ts.tv_nsec = le32_to_cpu(desc->ts_n); + shhwtstamps->hwtstamp = timespec64_to_ktime(ts); +} + /* Packet receive function for Ethernet AVB */ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q) { @@ -955,7 +979,6 @@ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q) struct ravb_ex_rx_desc *desc; unsigned int limit, i; struct sk_buff *skb; - struct timespec64 ts; int rx_packets = 0; u8 desc_status; u16 pkt_len; @@ -992,7 +1015,6 @@ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q) if (desc_status & MSC_CEEF) stats->rx_missed_errors++; } else { - u32 get_ts = priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE; struct ravb_rx_buffer *rx_buff; void *rx_addr; @@ -1010,19 +1032,8 @@ static int ravb_rx_rcar(struct net_device *ndev, int budget, int q) break; } skb_mark_for_recycle(skb); - get_ts &= (q == RAVB_NC) ? - RAVB_RXTSTAMP_TYPE_V2_L2_EVENT : - ~RAVB_RXTSTAMP_TYPE_V2_L2_EVENT; - if (get_ts) { - struct skb_shared_hwtstamps *shhwtstamps; - - shhwtstamps = skb_hwtstamps(skb); - memset(shhwtstamps, 0, sizeof(*shhwtstamps)); - ts.tv_sec = ((u64) le16_to_cpu(desc->ts_sh) << - 32) | le32_to_cpu(desc->ts_sl); - ts.tv_nsec = le32_to_cpu(desc->ts_n); - shhwtstamps->hwtstamp = timespec64_to_ktime(ts); - } + + ravb_rx_rcar_hwstamp(priv, q, desc, skb); skb_put(skb, pkt_len); skb->protocol = eth_type_trans(skb, ndev); @@ -1975,7 +1986,6 @@ static int ravb_open(struct net_device *ndev) out_set_reset: ravb_set_opmode(ndev, CCC_OPC_RESET); out_rpm_put: - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); out_napi_off: if (info->nc_queues) @@ -2404,95 +2414,55 @@ static int ravb_close(struct net_device *ndev) if (error) return error; - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); return 0; } -static int ravb_hwtstamp_get(struct net_device *ndev, struct ifreq *req) +static int ravb_hwtstamp_get(struct net_device *ndev, + struct kernel_hwtstamp_config *config) { struct ravb_private *priv = netdev_priv(ndev); - struct hwtstamp_config config; - config.flags = 0; - config.tx_type = priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : - HWTSTAMP_TX_OFF; - switch (priv->tstamp_rx_ctrl & RAVB_RXTSTAMP_TYPE) { - case RAVB_RXTSTAMP_TYPE_V2_L2_EVENT: - config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; - break; - case RAVB_RXTSTAMP_TYPE_ALL: - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - config.rx_filter = HWTSTAMP_FILTER_NONE; - } + config->flags = 0; + config->tx_type = priv->tstamp_tx_ctrl; + config->rx_filter = priv->tstamp_rx_ctrl; - return copy_to_user(req->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; + return 0; } /* Control hardware time stamping */ -static int ravb_hwtstamp_set(struct net_device *ndev, struct ifreq *req) +static int ravb_hwtstamp_set(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct ravb_private *priv = netdev_priv(ndev); - struct hwtstamp_config config; - u32 tstamp_rx_ctrl = RAVB_RXTSTAMP_ENABLED; - u32 tstamp_tx_ctrl; + enum hwtstamp_rx_filters tstamp_rx_ctrl; + enum hwtstamp_tx_types tstamp_tx_ctrl; - if (copy_from_user(&config, req->ifr_data, sizeof(config))) - return -EFAULT; - - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: - tstamp_tx_ctrl = 0; - break; case HWTSTAMP_TX_ON: - tstamp_tx_ctrl = RAVB_TXTSTAMP_ENABLED; + tstamp_tx_ctrl = config->tx_type; break; default: return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - tstamp_rx_ctrl = 0; - break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - tstamp_rx_ctrl |= RAVB_RXTSTAMP_TYPE_V2_L2_EVENT; + tstamp_rx_ctrl = config->rx_filter; break; default: - config.rx_filter = HWTSTAMP_FILTER_ALL; - tstamp_rx_ctrl |= RAVB_RXTSTAMP_TYPE_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; + tstamp_rx_ctrl = HWTSTAMP_FILTER_ALL; } priv->tstamp_tx_ctrl = tstamp_tx_ctrl; priv->tstamp_rx_ctrl = tstamp_rx_ctrl; - return copy_to_user(req->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} - -/* ioctl to device function */ -static int ravb_do_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) -{ - struct phy_device *phydev = ndev->phydev; - - if (!netif_running(ndev)) - return -EINVAL; - - if (!phydev) - return -ENODEV; - - switch (cmd) { - case SIOCGHWTSTAMP: - return ravb_hwtstamp_get(ndev, req); - case SIOCSHWTSTAMP: - return ravb_hwtstamp_set(ndev, req); - } - - return phy_mii_ioctl(phydev, req, cmd); + return 0; } static int ravb_change_mtu(struct net_device *ndev, int new_mtu) @@ -2628,11 +2598,13 @@ static const struct net_device_ops ravb_netdev_ops = { .ndo_get_stats = ravb_get_stats, .ndo_set_rx_mode = ravb_set_rx_mode, .ndo_tx_timeout = ravb_tx_timeout, - .ndo_eth_ioctl = ravb_do_ioctl, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_change_mtu = ravb_change_mtu, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, .ndo_set_features = ravb_set_features, + .ndo_hwtstamp_get = ravb_hwtstamp_get, + .ndo_hwtstamp_set = ravb_hwtstamp_set, }; /* MDIO bus init function */ @@ -2714,6 +2686,7 @@ static const struct ravb_hw_info ravb_gen2_hw_info = { .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), .rx_desc_size = sizeof(struct ravb_ex_rx_desc), + .dbat_entry_num = 22, .aligned_tx = 1, .gptp = 1, .nc_queues = 1, @@ -2737,6 +2710,7 @@ static const struct ravb_hw_info ravb_gen3_hw_info = { .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), .rx_desc_size = sizeof(struct ravb_ex_rx_desc), + .dbat_entry_num = 22, .internal_delay = 1, .tx_counters = 1, .multi_irqs = 1, @@ -2763,6 +2737,7 @@ static const struct ravb_hw_info ravb_gen4_hw_info = { .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), .rx_desc_size = sizeof(struct ravb_ex_rx_desc), + .dbat_entry_num = 22, .internal_delay = 1, .tx_counters = 1, .multi_irqs = 1, @@ -2789,6 +2764,7 @@ static const struct ravb_hw_info ravb_rzv2m_hw_info = { .rx_buffer_size = SZ_2K + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)), .rx_desc_size = sizeof(struct ravb_ex_rx_desc), + .dbat_entry_num = 22, .multi_irqs = 1, .err_mgmt_irqs = 1, .gptp = 1, @@ -2814,6 +2790,7 @@ static const struct ravb_hw_info gbeth_hw_info = { .rx_max_frame_size = SZ_8K, .rx_buffer_size = SZ_2K, .rx_desc_size = sizeof(struct ravb_rx_desc), + .dbat_entry_num = 2, .aligned_tx = 1, .coalesce_irqs = 1, .tx_counters = 1, @@ -2941,13 +2918,14 @@ static int ravb_probe(struct platform_device *pdev) return dev_err_probe(&pdev->dev, PTR_ERR(rstc), "failed to get cpg reset\n"); + info = of_device_get_match_data(&pdev->dev); + ndev = alloc_etherdev_mqs(sizeof(struct ravb_private), - NUM_TX_QUEUE, NUM_RX_QUEUE); + info->nc_queues ? NUM_TX_QUEUE : 1, + info->nc_queues ? NUM_RX_QUEUE : 1); if (!ndev) return -ENOMEM; - info = of_device_get_match_data(&pdev->dev); - ndev->features = info->net_features; ndev->hw_features = info->net_hw_features; ndev->vlan_features = info->vlan_features; @@ -3045,7 +3023,7 @@ static int ravb_probe(struct platform_device *pdev) ravb_parse_delay_mode(np, ndev); /* Allocate descriptor base address table */ - priv->desc_bat_size = sizeof(struct ravb_desc) * DBAT_ENTRY_NUM; + priv->desc_bat_size = sizeof(struct ravb_desc) * info->dbat_entry_num; priv->desc_bat = dma_alloc_coherent(ndev->dev.parent, priv->desc_bat_size, &priv->desc_bat_dma, GFP_KERNEL); if (!priv->desc_bat) { @@ -3055,7 +3033,7 @@ static int ravb_probe(struct platform_device *pdev) error = -ENOMEM; goto out_rpm_put; } - for (q = RAVB_BE; q < DBAT_ENTRY_NUM; q++) + for (q = RAVB_BE; q < info->dbat_entry_num; q++) priv->desc_bat[q].die_dt = DT_EOS; /* Initialise HW timestamp list */ @@ -3110,7 +3088,6 @@ static int ravb_probe(struct platform_device *pdev) netdev_info(ndev, "Base address at %#x, %pM, IRQ %d.\n", (u32)ndev->base_addr, ndev->dev_addr, ndev->irq); - pm_runtime_mark_last_busy(&pdev->dev); pm_runtime_put_autosuspend(&pdev->dev); return 0; @@ -3294,10 +3271,8 @@ static int ravb_resume(struct device *dev) return 0; out_rpm_put: - if (!priv->wol_enabled) { - pm_runtime_mark_last_busy(dev); + if (!priv->wol_enabled) pm_runtime_put_autosuspend(dev); - } return ret; } diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.h b/drivers/net/ethernet/renesas/rcar_gen4_ptp.h index f77e79e473572..9a9c232c854ef 100644 --- a/drivers/net/ethernet/renesas/rcar_gen4_ptp.h +++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.h @@ -9,24 +9,11 @@ #include -#define RCAR_GEN4_GPTP_OFFSET_S4 0x00018000 - -/* driver's definitions */ -#define RCAR_GEN4_RXTSTAMP_ENABLED BIT(0) -#define RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT BIT(1) -#define RCAR_GEN4_RXTSTAMP_TYPE_ALL (RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT | BIT(2)) -#define RCAR_GEN4_RXTSTAMP_TYPE RCAR_GEN4_RXTSTAMP_TYPE_ALL - -#define RCAR_GEN4_TXTSTAMP_ENABLED BIT(0) - - struct rcar_gen4_ptp_private { void __iomem *addr; struct ptp_clock *clock; struct ptp_clock_info info; spinlock_t lock; /* For multiple registers access */ - u32 tstamp_tx_ctrl; - u32 tstamp_rx_ctrl; s64 default_addend; bool initialized; }; diff --git a/drivers/net/ethernet/renesas/rswitch.h b/drivers/net/ethernet/renesas/rswitch.h index a1d4a877e5bd4..aa605304fed05 100644 --- a/drivers/net/ethernet/renesas/rswitch.h +++ b/drivers/net/ethernet/renesas/rswitch.h @@ -1063,6 +1063,9 @@ struct rswitch_private { bool etha_no_runtime_change; bool gwca_halt; struct net_device *offload_brdev; + + enum hwtstamp_tx_types tstamp_tx_ctrl; + enum hwtstamp_rx_filters tstamp_rx_ctrl; }; bool is_rdev(const struct net_device *ndev); diff --git a/drivers/net/ethernet/renesas/rswitch_main.c b/drivers/net/ethernet/renesas/rswitch_main.c index 8d8acc2124b8f..e14b21148f27a 100644 --- a/drivers/net/ethernet/renesas/rswitch_main.c +++ b/drivers/net/ethernet/renesas/rswitch_main.c @@ -30,6 +30,8 @@ #include "rswitch.h" #include "rswitch_l2.h" +#define RSWITCH_GPTP_OFFSET_S4 0x00018000 + static int rswitch_reg_wait(void __iomem *addr, u32 offs, u32 mask, u32 expected) { u32 val; @@ -843,7 +845,7 @@ static bool rswitch_rx(struct net_device *ndev, int *quota) if (!skb) goto out; - get_ts = rdev->priv->ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + get_ts = rdev->priv->tstamp_rx_ctrl != HWTSTAMP_FILTER_NONE; if (get_ts) { struct skb_shared_hwtstamps *shhwtstamps; struct timespec64 ts; @@ -1793,88 +1795,54 @@ static struct net_device_stats *rswitch_get_stats(struct net_device *ndev) return &ndev->stats; } -static int rswitch_hwstamp_get(struct net_device *ndev, struct ifreq *req) +static int rswitch_hwstamp_get(struct net_device *ndev, + struct kernel_hwtstamp_config *config) { struct rswitch_device *rdev = netdev_priv(ndev); - struct rcar_gen4_ptp_private *ptp_priv; - struct hwtstamp_config config; - - ptp_priv = rdev->priv->ptp_priv; + struct rswitch_private *priv = rdev->priv; - config.flags = 0; - config.tx_type = ptp_priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : - HWTSTAMP_TX_OFF; - switch (ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE) { - case RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT: - config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; - break; - case RCAR_GEN4_RXTSTAMP_TYPE_ALL: - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - config.rx_filter = HWTSTAMP_FILTER_NONE; - break; - } + config->flags = 0; + config->tx_type = priv->tstamp_tx_ctrl; + config->rx_filter = priv->tstamp_rx_ctrl; - return copy_to_user(req->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; + return 0; } -static int rswitch_hwstamp_set(struct net_device *ndev, struct ifreq *req) +static int rswitch_hwstamp_set(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct rswitch_device *rdev = netdev_priv(ndev); - u32 tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED; - struct hwtstamp_config config; - u32 tstamp_tx_ctrl; - - if (copy_from_user(&config, req->ifr_data, sizeof(config))) - return -EFAULT; + enum hwtstamp_rx_filters tstamp_rx_ctrl; + enum hwtstamp_tx_types tstamp_tx_ctrl; - if (config.flags) + if (config->flags) return -EINVAL; - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: - tstamp_tx_ctrl = 0; - break; case HWTSTAMP_TX_ON: - tstamp_tx_ctrl = RCAR_GEN4_TXTSTAMP_ENABLED; + tstamp_tx_ctrl = config->tx_type; break; default: return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - tstamp_rx_ctrl = 0; - break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - tstamp_rx_ctrl |= RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + tstamp_rx_ctrl = config->rx_filter; break; default: - config.rx_filter = HWTSTAMP_FILTER_ALL; - tstamp_rx_ctrl |= RCAR_GEN4_RXTSTAMP_TYPE_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; + tstamp_rx_ctrl = HWTSTAMP_FILTER_ALL; break; } - rdev->priv->ptp_priv->tstamp_tx_ctrl = tstamp_tx_ctrl; - rdev->priv->ptp_priv->tstamp_rx_ctrl = tstamp_rx_ctrl; - - return copy_to_user(req->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; -} - -static int rswitch_eth_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) -{ - if (!netif_running(ndev)) - return -EINVAL; + rdev->priv->tstamp_tx_ctrl = tstamp_tx_ctrl; + rdev->priv->tstamp_rx_ctrl = tstamp_rx_ctrl; - switch (cmd) { - case SIOCGHWTSTAMP: - return rswitch_hwstamp_get(ndev, req); - case SIOCSHWTSTAMP: - return rswitch_hwstamp_set(ndev, req); - default: - return phy_mii_ioctl(ndev->phydev, req, cmd); - } + return 0; } static int rswitch_get_port_parent_id(struct net_device *ndev, @@ -1905,11 +1873,13 @@ static const struct net_device_ops rswitch_netdev_ops = { .ndo_stop = rswitch_stop, .ndo_start_xmit = rswitch_start_xmit, .ndo_get_stats = rswitch_get_stats, - .ndo_eth_ioctl = rswitch_eth_ioctl, + .ndo_eth_ioctl = phy_do_ioctl_running, .ndo_get_port_parent_id = rswitch_get_port_parent_id, .ndo_get_phys_port_name = rswitch_get_phys_port_name, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = eth_mac_addr, + .ndo_hwtstamp_get = rswitch_hwstamp_get, + .ndo_hwtstamp_set = rswitch_hwstamp_set, }; bool is_rdev(const struct net_device *ndev) @@ -2190,7 +2160,7 @@ static int renesas_eth_sw_probe(struct platform_device *pdev) if (IS_ERR(priv->addr)) return PTR_ERR(priv->addr); - priv->ptp_priv->addr = priv->addr + RCAR_GEN4_GPTP_OFFSET_S4; + priv->ptp_priv->addr = priv->addr + RSWITCH_GPTP_OFFSET_S4; ret = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40)); if (ret < 0) { diff --git a/drivers/net/ethernet/renesas/rtsn.c b/drivers/net/ethernet/renesas/rtsn.c index 15a043e85431f..fdb1e7b7fb066 100644 --- a/drivers/net/ethernet/renesas/rtsn.c +++ b/drivers/net/ethernet/renesas/rtsn.c @@ -62,6 +62,9 @@ struct rtsn_private { int tx_data_irq; int rx_data_irq; + + u32 tstamp_tx_ctrl; + u32 tstamp_rx_ctrl; }; static u32 rtsn_read(struct rtsn_private *priv, enum rtsn_reg reg) @@ -162,8 +165,7 @@ static int rtsn_rx(struct net_device *ndev, int budget) unsigned int i; bool get_ts; - get_ts = priv->ptp_priv->tstamp_rx_ctrl & - RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + get_ts = priv->tstamp_rx_ctrl != HWTSTAMP_FILTER_NONE; ndescriptors = priv->dirty_rx + priv->num_rx_ring - priv->cur_rx; rx_packets = 0; @@ -1122,31 +1124,16 @@ static int rtsn_do_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) static int rtsn_hwtstamp_get(struct net_device *ndev, struct kernel_hwtstamp_config *config) { - struct rcar_gen4_ptp_private *ptp_priv; struct rtsn_private *priv; if (!netif_running(ndev)) return -ENODEV; priv = netdev_priv(ndev); - ptp_priv = priv->ptp_priv; config->flags = 0; - - config->tx_type = - ptp_priv->tstamp_tx_ctrl ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - - switch (ptp_priv->tstamp_rx_ctrl & RCAR_GEN4_RXTSTAMP_TYPE) { - case RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT: - config->rx_filter = HWTSTAMP_FILTER_PTP_V2_L2_EVENT; - break; - case RCAR_GEN4_RXTSTAMP_TYPE_ALL: - config->rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - config->rx_filter = HWTSTAMP_FILTER_NONE; - break; - } + config->tx_type = priv->tstamp_tx_ctrl; + config->rx_filter = priv->tstamp_rx_ctrl; return 0; } @@ -1155,26 +1142,22 @@ static int rtsn_hwtstamp_set(struct net_device *ndev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack) { - struct rcar_gen4_ptp_private *ptp_priv; + enum hwtstamp_rx_filters tstamp_rx_ctrl; + enum hwtstamp_tx_types tstamp_tx_ctrl; struct rtsn_private *priv; - u32 tstamp_rx_ctrl; - u32 tstamp_tx_ctrl; if (!netif_running(ndev)) return -ENODEV; priv = netdev_priv(ndev); - ptp_priv = priv->ptp_priv; if (config->flags) return -EINVAL; switch (config->tx_type) { case HWTSTAMP_TX_OFF: - tstamp_tx_ctrl = 0; - break; case HWTSTAMP_TX_ON: - tstamp_tx_ctrl = RCAR_GEN4_TXTSTAMP_ENABLED; + tstamp_tx_ctrl = config->tx_type; break; default: return -ERANGE; @@ -1182,21 +1165,17 @@ static int rtsn_hwtstamp_set(struct net_device *ndev, switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: - tstamp_rx_ctrl = 0; - break; case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED | - RCAR_GEN4_RXTSTAMP_TYPE_V2_L2_EVENT; + tstamp_rx_ctrl = config->rx_filter; break; default: config->rx_filter = HWTSTAMP_FILTER_ALL; - tstamp_rx_ctrl = RCAR_GEN4_RXTSTAMP_ENABLED | - RCAR_GEN4_RXTSTAMP_TYPE_ALL; + tstamp_rx_ctrl = HWTSTAMP_FILTER_ALL; break; } - ptp_priv->tstamp_tx_ctrl = tstamp_tx_ctrl; - ptp_priv->tstamp_rx_ctrl = tstamp_rx_ctrl; + priv->tstamp_tx_ctrl = tstamp_tx_ctrl; + priv->tstamp_rx_ctrl = tstamp_rx_ctrl; return 0; } diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c index 75bad561b3525..6b8e54391d7f4 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_main.c @@ -1063,7 +1063,12 @@ static int sxgbe_open(struct net_device *dev) struct sxgbe_priv_data *priv = netdev_priv(dev); int ret, queue_num; - clk_prepare_enable(priv->sxgbe_clk); + ret = clk_prepare_enable(priv->sxgbe_clk); + if (ret < 0) { + netdev_err(dev, "%s: Cannot enable clock (error: %d)\n", + __func__, ret); + goto clk_error; + } sxgbe_check_ether_addr(priv); @@ -1195,6 +1200,7 @@ static int sxgbe_open(struct net_device *dev) phy_error: clk_disable_unprepare(priv->sxgbe_clk); +clk_error: return ret; } diff --git a/drivers/net/ethernet/spacemit/k1_emac.h b/drivers/net/ethernet/spacemit/k1_emac.h index 5a09e946a276f..577efe66573eb 100644 --- a/drivers/net/ethernet/spacemit/k1_emac.h +++ b/drivers/net/ethernet/spacemit/k1_emac.h @@ -363,7 +363,7 @@ struct emac_desc { /* Keep stats in this order, index used for accessing hardware */ union emac_hw_tx_stats { - struct { + struct individual_tx_stats { u64 tx_ok_pkts; u64 tx_total_pkts; u64 tx_ok_bytes; @@ -378,11 +378,11 @@ union emac_hw_tx_stats { u64 tx_pause_pkts; } stats; - DECLARE_FLEX_ARRAY(u64, array); + u64 array[sizeof(struct individual_tx_stats) / sizeof(u64)]; }; union emac_hw_rx_stats { - struct { + struct individual_rx_stats { u64 rx_ok_pkts; u64 rx_total_pkts; u64 rx_crc_err_pkts; @@ -410,7 +410,7 @@ union emac_hw_rx_stats { u64 rx_truncate_fifo_full_pkts; } stats; - DECLARE_FLEX_ARRAY(u64, array); + u64 array[sizeof(struct individual_rx_stats) / sizeof(u64)]; }; #endif /* _K1_EMAC_H_ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 9507131875b2c..87c5bea6c2a24 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -10,6 +10,7 @@ config STMMAC_ETH select PHYLINK select CRC32 select RESET_CONTROLLER + select NET_DEVLINK help This is the driver for the Ethernet IPs built around a Synopsys IP Core. @@ -67,6 +68,15 @@ config DWMAC_ANARION This selects the Anarion SoC glue layer support for the stmmac driver. +config DWMAC_EIC7700 + tristate "Support for Eswin eic7700 ethernet driver" + depends on OF && HAS_DMA && ARCH_ESWIN || COMPILE_TEST + help + This driver supports the Eswin EIC7700 Ethernet controller, + which integrates Synopsys DesignWare QoS features. It enables + high-speed networking with DMA acceleration and is optimized + for embedded systems. + config DWMAC_INGENIC tristate "Ingenic MAC support" default MACH_INGENIC diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 51e068e26ce49..1681a8a283135 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -7,13 +7,14 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \ stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \ stmmac_xdp.o stmmac_est.o stmmac_fpe.o stmmac_vlan.o \ - $(stmmac-y) + stmmac_pcs.o $(stmmac-y) stmmac-$(CONFIG_STMMAC_SELFTESTS) += stmmac_selftests.o # Ordering matters. Generic driver must be last. obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o obj-$(CONFIG_DWMAC_ANARION) += dwmac-anarion.o +obj-$(CONFIG_DWMAC_EIC7700) += dwmac-eic7700.o obj-$(CONFIG_DWMAC_INGENIC) += dwmac-ingenic.o obj-$(CONFIG_DWMAC_IPQ806X) += dwmac-ipq806x.o obj-$(CONFIG_DWMAC_LPC18XX) += dwmac-lpc18xx.o diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 8f34c9ad457f0..7395bbb94aeaa 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -26,6 +26,9 @@ #include "hwif.h" #include "mmc.h" +#define DWMAC_SNPSVER GENMASK_U32(7, 0) +#define DWMAC_USERVER GENMASK_U32(15, 8) + /* Synopsys Core versions */ #define DWMAC_CORE_3_40 0x34 #define DWMAC_CORE_3_50 0x35 @@ -43,6 +46,11 @@ #define DWXGMAC_ID 0x76 #define DWXLGMAC_ID 0x27 +static inline bool dwmac_is_xmac(enum dwmac_core_type core_type) +{ + return core_type == DWMAC_CORE_GMAC4 || core_type == DWMAC_CORE_XGMAC; +} + #define STMMAC_CHAN0 0 /* Always supported and default for all chips */ /* TX and RX Descriptor Length, these need to be power of two. @@ -192,9 +200,6 @@ struct stmmac_extra_stats { unsigned long irq_pcs_ane_n; unsigned long irq_pcs_link_n; unsigned long irq_rgmii_n; - unsigned long pcs_link; - unsigned long pcs_duplex; - unsigned long pcs_speed; /* debug register */ unsigned long mtl_tx_status_fifo_full; unsigned long mtl_tx_fifo_not_empty; @@ -273,7 +278,6 @@ struct stmmac_safety_stats { #define FLOW_AUTO (FLOW_TX | FLOW_RX) /* PCS defines */ -#define STMMAC_PCS_RGMII (1 << 0) #define STMMAC_PCS_SGMII (1 << 1) #define SF_DMA_MODE 1 /* DMA STORE-AND-FORWARD Operation Mode */ @@ -309,6 +313,16 @@ struct stmmac_safety_stats { #define DMA_HW_FEAT_ACTPHYIF 0x70000000 /* Active/selected PHY iface */ #define DEFAULT_DMA_PBL 8 +/* phy_intf_sel_i and ACTPHYIF encodings */ +#define PHY_INTF_SEL_GMII_MII 0 +#define PHY_INTF_SEL_RGMII 1 +#define PHY_INTF_SEL_SGMII 2 +#define PHY_INTF_SEL_TBI 3 +#define PHY_INTF_SEL_RMII 4 +#define PHY_INTF_SEL_RTBI 5 +#define PHY_INTF_SEL_SMII 6 +#define PHY_INTF_SEL_REVMII 7 + /* MSI defines */ #define STMMAC_MSI_VEC_MAX 32 @@ -603,13 +617,18 @@ struct mac_device_info { unsigned int mcast_bits_log2; unsigned int rx_csum; unsigned int pcs; - unsigned int ps; unsigned int xlgmac; unsigned int num_vlan; u32 vlan_filter[32]; bool vlan_fail_q_en; u8 vlan_fail_q; bool hw_vlan_en; + bool reverse_sgmii_enable; + + /* This spinlock protects read-modify-write of the interrupt + * mask/enable registers. + */ + spinlock_t irq_ctrl_lock; }; struct stmmac_rx_routing { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index e8539cad4602e..c7cd6497d42df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -109,7 +109,7 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev, } /* dwc-qos needs GMAC4, AAL, TSO and PMT */ - plat_dat->has_gmac4 = 1; + plat_dat->core_type = DWMAC_CORE_GMAC4; plat_dat->dma_cfg->aal = 1; plat_dat->flags |= STMMAC_FLAG_TSO_EN; plat_dat->pmt = 1; @@ -162,7 +162,7 @@ static void tegra_eqos_fix_speed(void *bsp_priv, int speed, unsigned int mode) priv = netdev_priv(dev_get_drvdata(eqos->dev)); /* Calibration should be done with the MDIO bus idle */ - mutex_lock(&priv->mii->mdio_lock); + stmmac_mdio_lock(priv); /* calibrate */ value = readl(eqos->regs + SDMEMCOMPPADCTRL); @@ -198,7 +198,7 @@ static void tegra_eqos_fix_speed(void *bsp_priv, int speed, unsigned int mode) value &= ~SDMEMCOMPPADCTRL_PAD_E_INPUT_OR_E_PWRD; writel(value, eqos->regs + SDMEMCOMPPADCTRL); - mutex_unlock(&priv->mii->mdio_lock); + stmmac_mdio_unlock(priv); } else { value = readl(eqos->regs + AUTO_CAL_CONFIG); value &= ~AUTO_CAL_CONFIG_ENABLE; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c new file mode 100644 index 0000000000000..1dcf2037001ef --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-eic7700.c @@ -0,0 +1,235 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Eswin DWC Ethernet linux driver + * + * Copyright 2025, Beijing ESWIN Computing Technology Co., Ltd. + * + * Authors: + * Zhi Li + * Shuang Liang + * Shangjuan Wei + */ + +#include +#include +#include +#include +#include +#include + +#include "stmmac_platform.h" + +/* eth_phy_ctrl_offset eth0:0x100 */ +#define EIC7700_ETH_TX_CLK_SEL BIT(16) +#define EIC7700_ETH_PHY_INTF_SELI BIT(0) + +/* eth_axi_lp_ctrl_offset eth0:0x108 */ +#define EIC7700_ETH_CSYSREQ_VAL BIT(0) + +/* + * TX/RX Clock Delay Bit Masks: + * - TX Delay: bits [14:8] — TX_CLK delay (unit: 0.1ns per bit) + * - RX Delay: bits [30:24] — RX_CLK delay (unit: 0.1ns per bit) + */ +#define EIC7700_ETH_TX_ADJ_DELAY GENMASK(14, 8) +#define EIC7700_ETH_RX_ADJ_DELAY GENMASK(30, 24) + +#define EIC7700_MAX_DELAY_UNIT 0x7F + +static const char * const eic7700_clk_names[] = { + "tx", "axi", "cfg", +}; + +struct eic7700_qos_priv { + struct plat_stmmacenet_data *plat_dat; +}; + +static int eic7700_clks_config(void *priv, bool enabled) +{ + struct eic7700_qos_priv *dwc = (struct eic7700_qos_priv *)priv; + struct plat_stmmacenet_data *plat = dwc->plat_dat; + int ret = 0; + + if (enabled) + ret = clk_bulk_prepare_enable(plat->num_clks, plat->clks); + else + clk_bulk_disable_unprepare(plat->num_clks, plat->clks); + + return ret; +} + +static int eic7700_dwmac_init(struct platform_device *pdev, void *priv) +{ + struct eic7700_qos_priv *dwc = priv; + + return eic7700_clks_config(dwc, true); +} + +static void eic7700_dwmac_exit(struct platform_device *pdev, void *priv) +{ + struct eic7700_qos_priv *dwc = priv; + + eic7700_clks_config(dwc, false); +} + +static int eic7700_dwmac_suspend(struct device *dev, void *priv) +{ + return pm_runtime_force_suspend(dev); +} + +static int eic7700_dwmac_resume(struct device *dev, void *priv) +{ + int ret; + + ret = pm_runtime_force_resume(dev); + if (ret) + dev_err(dev, "%s failed: %d\n", __func__, ret); + + return ret; +} + +static int eic7700_dwmac_probe(struct platform_device *pdev) +{ + struct plat_stmmacenet_data *plat_dat; + struct stmmac_resources stmmac_res; + struct eic7700_qos_priv *dwc_priv; + struct regmap *eic7700_hsp_regmap; + u32 eth_axi_lp_ctrl_offset; + u32 eth_phy_ctrl_offset; + u32 eth_phy_ctrl_regset; + u32 eth_rxd_dly_offset; + u32 eth_dly_param = 0; + u32 delay_ps; + int i, ret; + + ret = stmmac_get_platform_resources(pdev, &stmmac_res); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "failed to get resources\n"); + + plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac); + if (IS_ERR(plat_dat)) + return dev_err_probe(&pdev->dev, PTR_ERR(plat_dat), + "dt configuration failed\n"); + + dwc_priv = devm_kzalloc(&pdev->dev, sizeof(*dwc_priv), GFP_KERNEL); + if (!dwc_priv) + return -ENOMEM; + + /* Read rx-internal-delay-ps and update rx_clk delay */ + if (!of_property_read_u32(pdev->dev.of_node, + "rx-internal-delay-ps", &delay_ps)) { + u32 val = min(delay_ps / 100, EIC7700_MAX_DELAY_UNIT); + + eth_dly_param &= ~EIC7700_ETH_RX_ADJ_DELAY; + eth_dly_param |= FIELD_PREP(EIC7700_ETH_RX_ADJ_DELAY, val); + } else { + return dev_err_probe(&pdev->dev, -EINVAL, + "missing required property rx-internal-delay-ps\n"); + } + + /* Read tx-internal-delay-ps and update tx_clk delay */ + if (!of_property_read_u32(pdev->dev.of_node, + "tx-internal-delay-ps", &delay_ps)) { + u32 val = min(delay_ps / 100, EIC7700_MAX_DELAY_UNIT); + + eth_dly_param &= ~EIC7700_ETH_TX_ADJ_DELAY; + eth_dly_param |= FIELD_PREP(EIC7700_ETH_TX_ADJ_DELAY, val); + } else { + return dev_err_probe(&pdev->dev, -EINVAL, + "missing required property tx-internal-delay-ps\n"); + } + + eic7700_hsp_regmap = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "eswin,hsp-sp-csr"); + if (IS_ERR(eic7700_hsp_regmap)) + return dev_err_probe(&pdev->dev, + PTR_ERR(eic7700_hsp_regmap), + "Failed to get hsp-sp-csr regmap\n"); + + ret = of_property_read_u32_index(pdev->dev.of_node, + "eswin,hsp-sp-csr", + 1, ð_phy_ctrl_offset); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "can't get eth_phy_ctrl_offset\n"); + + regmap_read(eic7700_hsp_regmap, eth_phy_ctrl_offset, + ð_phy_ctrl_regset); + eth_phy_ctrl_regset |= + (EIC7700_ETH_TX_CLK_SEL | EIC7700_ETH_PHY_INTF_SELI); + regmap_write(eic7700_hsp_regmap, eth_phy_ctrl_offset, + eth_phy_ctrl_regset); + + ret = of_property_read_u32_index(pdev->dev.of_node, + "eswin,hsp-sp-csr", + 2, ð_axi_lp_ctrl_offset); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "can't get eth_axi_lp_ctrl_offset\n"); + + regmap_write(eic7700_hsp_regmap, eth_axi_lp_ctrl_offset, + EIC7700_ETH_CSYSREQ_VAL); + + ret = of_property_read_u32_index(pdev->dev.of_node, + "eswin,hsp-sp-csr", + 3, ð_rxd_dly_offset); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "can't get eth_rxd_dly_offset\n"); + + regmap_write(eic7700_hsp_regmap, eth_rxd_dly_offset, + eth_dly_param); + + plat_dat->num_clks = ARRAY_SIZE(eic7700_clk_names); + plat_dat->clks = devm_kcalloc(&pdev->dev, + plat_dat->num_clks, + sizeof(*plat_dat->clks), + GFP_KERNEL); + if (!plat_dat->clks) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(eic7700_clk_names); i++) + plat_dat->clks[i].id = eic7700_clk_names[i]; + + ret = devm_clk_bulk_get_optional(&pdev->dev, + plat_dat->num_clks, + plat_dat->clks); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "Failed to get clocks\n"); + + plat_dat->clk_tx_i = stmmac_pltfr_find_clk(plat_dat, "tx"); + plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate; + plat_dat->clks_config = eic7700_clks_config; + plat_dat->bsp_priv = dwc_priv; + dwc_priv->plat_dat = plat_dat; + plat_dat->init = eic7700_dwmac_init; + plat_dat->exit = eic7700_dwmac_exit; + plat_dat->suspend = eic7700_dwmac_suspend; + plat_dat->resume = eic7700_dwmac_resume; + + return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res); +} + +static const struct of_device_id eic7700_dwmac_match[] = { + { .compatible = "eswin,eic7700-qos-eth" }, + { } +}; +MODULE_DEVICE_TABLE(of, eic7700_dwmac_match); + +static struct platform_driver eic7700_dwmac_driver = { + .probe = eic7700_dwmac_probe, + .driver = { + .name = "eic7700-eth-dwmac", + .pm = &stmmac_pltfr_pm_ops, + .of_match_table = eic7700_dwmac_match, + }, +}; +module_platform_driver(eic7700_dwmac_driver); + +MODULE_AUTHOR("Zhi Li "); +MODULE_AUTHOR("Shuang Liang "); +MODULE_AUTHOR("Shangjuan Wei "); +MODULE_DESCRIPTION("Eswin eic7700 qos ethernet driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index 4268b99872372..db288fbd5a4df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -23,18 +23,13 @@ #include "stmmac_platform.h" #define GPR_ENET_QOS_INTF_MODE_MASK GENMASK(21, 16) -#define GPR_ENET_QOS_INTF_SEL_MII (0x0 << 16) -#define GPR_ENET_QOS_INTF_SEL_RMII (0x4 << 16) -#define GPR_ENET_QOS_INTF_SEL_RGMII (0x1 << 16) +#define GPR_ENET_QOS_INTF_SEL_MASK GENMASK(20, 16) #define GPR_ENET_QOS_CLK_GEN_EN (0x1 << 19) #define GPR_ENET_QOS_CLK_TX_CLK_SEL (0x1 << 20) #define GPR_ENET_QOS_RGMII_EN (0x1 << 21) #define MX93_GPR_ENET_QOS_INTF_MODE_MASK GENMASK(3, 0) -#define MX93_GPR_ENET_QOS_INTF_MASK GENMASK(3, 1) -#define MX93_GPR_ENET_QOS_INTF_SEL_MII (0x0 << 1) -#define MX93_GPR_ENET_QOS_INTF_SEL_RMII (0x4 << 1) -#define MX93_GPR_ENET_QOS_INTF_SEL_RGMII (0x1 << 1) +#define MX93_GPR_ENET_QOS_INTF_SEL_MASK GENMASK(3, 1) #define MX93_GPR_ENET_QOS_CLK_GEN_EN (0x1 << 0) #define MX93_GPR_ENET_QOS_CLK_SEL_MASK BIT_MASK(0) #define MX93_GPR_CLK_SEL_OFFSET (4) @@ -44,13 +39,15 @@ #define RMII_RESET_SPEED (0x3 << 14) #define CTRL_SPEED_MASK GENMASK(15, 14) +struct imx_priv_data; + struct imx_dwmac_ops { u32 addr_width; u32 flags; bool mac_rgmii_txclk_auto_adj; int (*fix_soc_reset)(struct stmmac_priv *priv, void __iomem *ioaddr); - int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat); + int (*set_intf_mode)(struct imx_priv_data *dwmac, u8 phy_intf_sel); void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); }; @@ -67,79 +64,46 @@ struct imx_priv_data { struct plat_stmmacenet_data *plat_dat; }; -static int imx8mp_set_intf_mode(struct plat_stmmacenet_data *plat_dat) +static int imx8mp_set_intf_mode(struct imx_priv_data *dwmac, u8 phy_intf_sel) { - struct imx_priv_data *dwmac = plat_dat->bsp_priv; - int val; - - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_MII: - val = GPR_ENET_QOS_INTF_SEL_MII; - break; - case PHY_INTERFACE_MODE_RMII: - val = GPR_ENET_QOS_INTF_SEL_RMII; - val |= (dwmac->rmii_refclk_ext ? 0 : GPR_ENET_QOS_CLK_TX_CLK_SEL); - break; - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - val = GPR_ENET_QOS_INTF_SEL_RGMII | - GPR_ENET_QOS_RGMII_EN; - break; - default: - pr_debug("imx dwmac doesn't support %s interface\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; - } + unsigned int val; + + val = FIELD_PREP(GPR_ENET_QOS_INTF_SEL_MASK, phy_intf_sel) | + GPR_ENET_QOS_CLK_GEN_EN; + + if (phy_intf_sel == PHY_INTF_SEL_RMII && !dwmac->rmii_refclk_ext) + val |= GPR_ENET_QOS_CLK_TX_CLK_SEL; + else if (phy_intf_sel == PHY_INTF_SEL_RGMII) + val |= GPR_ENET_QOS_RGMII_EN; - val |= GPR_ENET_QOS_CLK_GEN_EN; return regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off, GPR_ENET_QOS_INTF_MODE_MASK, val); }; static int -imx8dxl_set_intf_mode(struct plat_stmmacenet_data *plat_dat) +imx8dxl_set_intf_mode(struct imx_priv_data *dwmac, u8 phy_intf_sel) { - int ret = 0; - /* TBD: depends on imx8dxl scu interfaces to be upstreamed */ - return ret; + return 0; } -static int imx93_set_intf_mode(struct plat_stmmacenet_data *plat_dat) +static int imx93_set_intf_mode(struct imx_priv_data *dwmac, u8 phy_intf_sel) { - struct imx_priv_data *dwmac = plat_dat->bsp_priv; - int val, ret; - - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_MII: - val = MX93_GPR_ENET_QOS_INTF_SEL_MII; - break; - case PHY_INTERFACE_MODE_RMII: - if (dwmac->rmii_refclk_ext) { - ret = regmap_clear_bits(dwmac->intf_regmap, - dwmac->intf_reg_off + - MX93_GPR_CLK_SEL_OFFSET, - MX93_GPR_ENET_QOS_CLK_SEL_MASK); - if (ret) - return ret; - } - val = MX93_GPR_ENET_QOS_INTF_SEL_RMII; - break; - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - val = MX93_GPR_ENET_QOS_INTF_SEL_RGMII; - break; - default: - dev_dbg(dwmac->dev, "imx dwmac doesn't support %s interface\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; + unsigned int val; + int ret; + + if (phy_intf_sel == PHY_INTF_SEL_RMII && dwmac->rmii_refclk_ext) { + ret = regmap_clear_bits(dwmac->intf_regmap, + dwmac->intf_reg_off + + MX93_GPR_CLK_SEL_OFFSET, + MX93_GPR_ENET_QOS_CLK_SEL_MASK); + if (ret) + return ret; } - val |= MX93_GPR_ENET_QOS_CLK_GEN_EN; + val = FIELD_PREP(MX93_GPR_ENET_QOS_INTF_SEL_MASK, phy_intf_sel) | + MX93_GPR_ENET_QOS_CLK_GEN_EN; + return regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off, MX93_GPR_ENET_QOS_INTF_MODE_MASK, val); }; @@ -170,34 +134,24 @@ static int imx_dwmac_clks_config(void *priv, bool enabled) return ret; } -static int imx_dwmac_init(struct platform_device *pdev, void *priv) +static int imx_set_phy_intf_sel(void *bsp_priv, u8 phy_intf_sel) { - struct plat_stmmacenet_data *plat_dat; - struct imx_priv_data *dwmac = priv; - int ret; - - plat_dat = dwmac->plat_dat; + struct imx_priv_data *dwmac = bsp_priv; - if (dwmac->ops->set_intf_mode) { - ret = dwmac->ops->set_intf_mode(plat_dat); - if (ret) - return ret; - } + if (!dwmac->ops->set_intf_mode) + return 0; - return 0; -} + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) + return -EINVAL; -static void imx_dwmac_exit(struct platform_device *pdev, void *priv) -{ - /* nothing to do now */ + return dwmac->ops->set_intf_mode(dwmac, phy_intf_sel); } static int imx_dwmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, phy_interface_t interface, int speed) { - struct imx_priv_data *dwmac = bsp_priv; - - interface = dwmac->plat_dat->phy_interface; if (interface == PHY_INTERFACE_MODE_RMII || interface == PHY_INTERFACE_MODE_MII) return 0; @@ -244,8 +198,8 @@ static void imx93_dwmac_fix_speed(void *priv, int speed, unsigned int mode) if (regmap_read(dwmac->intf_regmap, dwmac->intf_reg_off, &iface)) return; - iface &= MX93_GPR_ENET_QOS_INTF_MASK; - if (iface != MX93_GPR_ENET_QOS_INTF_SEL_RGMII) + if (FIELD_GET(MX93_GPR_ENET_QOS_INTF_SEL_MASK, iface) != + PHY_INTF_SEL_RGMII) return; old_ctrl = readl(dwmac->base_addr + MAC_CTRL_REG); @@ -258,6 +212,7 @@ static void imx93_dwmac_fix_speed(void *priv, int speed, unsigned int mode) readl(dwmac->base_addr + MAC_CTRL_REG); usleep_range(10, 20); + iface &= MX93_GPR_ENET_QOS_INTF_SEL_MASK; iface |= MX93_GPR_ENET_QOS_CLK_GEN_EN; regmap_update_bits(dwmac->intf_regmap, dwmac->intf_reg_off, MX93_GPR_ENET_QOS_INTF_MODE_MASK, iface); @@ -370,8 +325,7 @@ static int imx_dwmac_probe(struct platform_device *pdev) plat_dat->tx_queues_cfg[i].tbs_en = 1; plat_dat->host_dma_width = dwmac->ops->addr_width; - plat_dat->init = imx_dwmac_init; - plat_dat->exit = imx_dwmac_exit; + plat_dat->set_phy_intf_sel = imx_set_phy_intf_sel; plat_dat->clks_config = imx_dwmac_clks_config; plat_dat->bsp_priv = dwmac; dwmac->plat_dat = plat_dat; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c index c1670f6bae145..8e4a30c11db06 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ingenic.c @@ -35,10 +35,6 @@ #define MACPHYC_RX_DELAY_MASK GENMASK(10, 4) #define MACPHYC_SOFT_RST_MASK GENMASK(3, 3) #define MACPHYC_PHY_INFT_MASK GENMASK(2, 0) -#define MACPHYC_PHY_INFT_RMII 0x4 -#define MACPHYC_PHY_INFT_RGMII 0x1 -#define MACPHYC_PHY_INFT_GMII 0x0 -#define MACPHYC_PHY_INFT_MII 0x0 #define MACPHYC_TX_DELAY_PS_MAX 2496 #define MACPHYC_TX_DELAY_PS_MIN 20 @@ -68,172 +64,93 @@ struct ingenic_soc_info { enum ingenic_mac_version version; u32 mask; - int (*set_mode)(struct plat_stmmacenet_data *plat_dat); -}; - -static int ingenic_mac_init(struct platform_device *pdev, void *bsp_priv) -{ - struct ingenic_mac *mac = bsp_priv; - int ret; + int (*set_mode)(struct ingenic_mac *mac, u8 phy_intf_sel); - if (mac->soc_info->set_mode) { - ret = mac->soc_info->set_mode(mac->plat_dat); - if (ret) - return ret; - } - - return 0; -} + u8 valid_phy_intf_sel; +}; -static int jz4775_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +static int jz4775_mac_set_mode(struct ingenic_mac *mac, u8 phy_intf_sel) { - struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_MII: - val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | - FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_MII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_MII\n"); - break; - - case PHY_INTERFACE_MODE_GMII: - val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | - FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_GMII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_GMII\n"); - break; - - case PHY_INTERFACE_MODE_RMII: - val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | - FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); - break; - - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_RGMII_RXID: - val = FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT) | - FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RGMII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RGMII\n"); - break; - - default: - dev_err(mac->dev, "Unsupported interface %s\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; - } + val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, phy_intf_sel) | + FIELD_PREP(MACPHYC_TXCLK_SEL_MASK, MACPHYC_TXCLK_SEL_INPUT); /* Update MAC PHY control register */ return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); } -static int x1000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +static int x1000_mac_set_mode(struct ingenic_mac *mac, u8 phy_intf_sel) { - struct ingenic_mac *mac = plat_dat->bsp_priv; - - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_RMII: - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); - break; - - default: - dev_err(mac->dev, "Unsupported interface %s\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; - } - /* Update MAC PHY control register */ return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, 0); } -static int x1600_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +static int x1600_mac_set_mode(struct ingenic_mac *mac, u8 phy_intf_sel) { - struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_RMII: - val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); - break; - - default: - dev_err(mac->dev, "Unsupported interface %s\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; - } + val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, phy_intf_sel); /* Update MAC PHY control register */ return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); } -static int x1830_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +static int x1830_mac_set_mode(struct ingenic_mac *mac, u8 phy_intf_sel) { - struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_RMII: - val = FIELD_PREP(MACPHYC_MODE_SEL_MASK, MACPHYC_MODE_SEL_RMII) | - FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); - break; - - default: - dev_err(mac->dev, "Unsupported interface %s\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; - } + val = FIELD_PREP(MACPHYC_MODE_SEL_MASK, MACPHYC_MODE_SEL_RMII) | + FIELD_PREP(MACPHYC_PHY_INFT_MASK, phy_intf_sel); /* Update MAC PHY control register */ return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); } -static int x2000_mac_set_mode(struct plat_stmmacenet_data *plat_dat) +static int x2000_mac_set_mode(struct ingenic_mac *mac, u8 phy_intf_sel) { - struct ingenic_mac *mac = plat_dat->bsp_priv; unsigned int val; - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_RMII: - val = FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN) | - FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN) | - FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RMII); - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RMII\n"); - break; - - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_RGMII_RXID: - val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, MACPHYC_PHY_INFT_RGMII); + val = FIELD_PREP(MACPHYC_PHY_INFT_MASK, phy_intf_sel); + if (phy_intf_sel == PHY_INTF_SEL_RMII) { + val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN) | + FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN); + } else if (phy_intf_sel == PHY_INTF_SEL_RGMII) { if (mac->tx_delay == 0) val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_ORIGIN); else val |= FIELD_PREP(MACPHYC_TX_SEL_MASK, MACPHYC_TX_SEL_DELAY) | - FIELD_PREP(MACPHYC_TX_DELAY_MASK, (mac->tx_delay + 9750) / 19500 - 1); + FIELD_PREP(MACPHYC_TX_DELAY_MASK, (mac->tx_delay + 9750) / 19500 - 1); if (mac->rx_delay == 0) val |= FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_ORIGIN); else val |= FIELD_PREP(MACPHYC_RX_SEL_MASK, MACPHYC_RX_SEL_DELAY) | FIELD_PREP(MACPHYC_RX_DELAY_MASK, (mac->rx_delay + 9750) / 19500 - 1); - - dev_dbg(mac->dev, "MAC PHY Control Register: PHY_INTERFACE_MODE_RGMII\n"); - break; - - default: - dev_err(mac->dev, "Unsupported interface %s\n", - phy_modes(plat_dat->phy_interface)); - return -EINVAL; } /* Update MAC PHY control register */ return regmap_update_bits(mac->regmap, 0, mac->soc_info->mask, val); } +static int ingenic_set_phy_intf_sel(void *bsp_priv, u8 phy_intf_sel) +{ + struct ingenic_mac *mac = bsp_priv; + + if (!mac->soc_info->set_mode) + return 0; + + if (phy_intf_sel >= BITS_PER_BYTE || + ~mac->soc_info->valid_phy_intf_sel & BIT(phy_intf_sel)) + return -EINVAL; + + dev_dbg(mac->dev, "MAC PHY control register: interface %s\n", + phy_modes(mac->plat_dat->phy_interface)); + + return mac->soc_info->set_mode(mac, phy_intf_sel); +} + static int ingenic_mac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -293,7 +210,7 @@ static int ingenic_mac_probe(struct platform_device *pdev) mac->plat_dat = plat_dat; plat_dat->bsp_priv = mac; - plat_dat->init = ingenic_mac_init; + plat_dat->set_phy_intf_sel = ingenic_set_phy_intf_sel; return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res); } @@ -303,6 +220,9 @@ static struct ingenic_soc_info jz4775_soc_info = { .mask = MACPHYC_TXCLK_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, .set_mode = jz4775_mac_set_mode, + .valid_phy_intf_sel = BIT(PHY_INTF_SEL_GMII_MII) | + BIT(PHY_INTF_SEL_RGMII) | + BIT(PHY_INTF_SEL_RMII), }; static struct ingenic_soc_info x1000_soc_info = { @@ -310,6 +230,7 @@ static struct ingenic_soc_info x1000_soc_info = { .mask = MACPHYC_SOFT_RST_MASK, .set_mode = x1000_mac_set_mode, + .valid_phy_intf_sel = BIT(PHY_INTF_SEL_RMII), }; static struct ingenic_soc_info x1600_soc_info = { @@ -317,6 +238,7 @@ static struct ingenic_soc_info x1600_soc_info = { .mask = MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, .set_mode = x1600_mac_set_mode, + .valid_phy_intf_sel = BIT(PHY_INTF_SEL_RMII), }; static struct ingenic_soc_info x1830_soc_info = { @@ -324,6 +246,7 @@ static struct ingenic_soc_info x1830_soc_info = { .mask = MACPHYC_MODE_SEL_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, .set_mode = x1830_mac_set_mode, + .valid_phy_intf_sel = BIT(PHY_INTF_SEL_RMII), }; static struct ingenic_soc_info x2000_soc_info = { @@ -332,6 +255,8 @@ static struct ingenic_soc_info x2000_soc_info = { MACPHYC_RX_DELAY_MASK | MACPHYC_SOFT_RST_MASK | MACPHYC_PHY_INFT_MASK, .set_mode = x2000_mac_set_mode, + .valid_phy_intf_sel = BIT(PHY_INTF_SEL_RGMII) | + BIT(PHY_INTF_SEL_RMII), }; static const struct of_device_id ingenic_mac_of_matches[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index e74d00984b889..8938e7a599259 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -565,30 +565,10 @@ static void common_default_data(struct plat_stmmacenet_data *plat) { /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->clk_csr = STMMAC_CSR_20_35M; - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; plat->mdio_bus_data->needs_reset = true; - - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - - /* Set default number of RX and TX queues to use */ - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; - - /* Disable Priority config by default */ - plat->tx_queues_cfg[0].use_prio = false; - plat->rx_queues_cfg[0].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[0].pkt_route = 0x0; } static struct phylink_pcs *intel_mgbe_select_pcs(struct stmmac_priv *priv, @@ -612,8 +592,7 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->pdev = pdev; plat->phy_addr = -1; plat->clk_csr = STMMAC_CSR_250_300M; - plat->has_gmac = 0; - plat->has_gmac4 = 1; + plat->core_type = DWMAC_CORE_GMAC4; plat->force_sf_dma_mode = 0; plat->flags |= (STMMAC_FLAG_TSO_EN | STMMAC_FLAG_SPH_DISABLE); @@ -630,22 +609,12 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; - for (i = 0; i < plat->rx_queues_to_use; i++) { + for (i = 0; i < plat->rx_queues_to_use; i++) plat->rx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; - plat->rx_queues_cfg[i].chan = i; - - /* Disable Priority config by default */ - plat->rx_queues_cfg[i].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[i].pkt_route = 0x0; - } for (i = 0; i < plat->tx_queues_to_use; i++) { plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; - /* Disable Priority config by default */ - plat->tx_queues_cfg[i].use_prio = false; /* Default TX Q0 to use TSO and rest TXQ for TBS */ if (i > 0) plat->tx_queues_cfg[i].tbs_en = 1; @@ -707,15 +676,6 @@ static int intel_mgbe_common_data(struct pci_dev *pdev, plat->ptp_clk_freq_config = intel_mgbe_ptp_clk_freq_config; - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - plat->flags |= STMMAC_FLAG_VLAN_FAIL_Q_EN; /* Use the last Rx queue */ @@ -1287,7 +1247,7 @@ static int intel_eth_pci_probe(struct pci_dev *pdev, if (!intel_priv) return -ENOMEM; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return -ENOMEM; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c index ca4035cbb55b6..c05f85534f0ca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c @@ -473,7 +473,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev) return err; } - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->bsp_priv = gmac; plat_dat->set_clk_tx_rate = ipq806x_gmac_set_clk_tx_rate; plat_dat->multicast_filter_bins = 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c index 592aa9d636e50..5f9472f47e35f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c @@ -92,31 +92,15 @@ static void loongson_default_data(struct pci_dev *pdev, /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->clk_csr = STMMAC_CSR_20_35M; - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; - /* Set default value for multicast hash bins */ + /* Increase the default value for multicast hash bins */ plat->multicast_filter_bins = 256; - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - - /* Disable Priority config by default */ - plat->tx_queues_cfg[0].use_prio = false; - plat->rx_queues_cfg[0].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[0].pkt_route = 0x0; - plat->clk_ref_rate = 125000000; plat->clk_ptp_rate = 125000000; - /* Default to phy auto-detection */ - plat->phy_addr = -1; - plat->dma_cfg->pbl = 32; plat->dma_cfg->pblx8 = true; @@ -140,8 +124,6 @@ static void loongson_default_data(struct pci_dev *pdev, break; default: ld->multichan = 0; - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; break; } } @@ -320,10 +302,9 @@ static int loongson_dwmac_dma_interrupt(struct stmmac_priv *priv, return ret; } -static struct mac_device_info *loongson_dwmac_setup(void *apriv) +static int loongson_dwmac_setup(void *apriv, struct mac_device_info *mac) { struct stmmac_priv *priv = apriv; - struct mac_device_info *mac; struct stmmac_dma_ops *dma; struct loongson_data *ld; struct pci_dev *pdev; @@ -331,13 +312,9 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv) ld = priv->plat->bsp_priv; pdev = to_pci_dev(priv->device); - mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); - if (!mac) - return NULL; - dma = devm_kzalloc(priv->device, sizeof(*dma), GFP_KERNEL); if (!dma) - return NULL; + return -ENOMEM; /* The Loongson GMAC and GNET devices are based on the DW GMAC * v3.50a and v3.73a IP-cores. But the HW designers have changed @@ -396,7 +373,7 @@ static struct mac_device_info *loongson_dwmac_setup(void *apriv) mac->mii.clk_csr_shift = 2; mac->mii.clk_csr_mask = GENMASK(5, 2); - return mac; + return 0; } static int loongson_dwmac_msi_config(struct pci_dev *pdev, @@ -564,7 +541,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id struct loongson_data *ld; int ret; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return -ENOMEM; @@ -598,7 +575,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id goto err_disable_device; plat->bsp_priv = ld; - plat->setup = loongson_dwmac_setup; + plat->mac_setup = loongson_dwmac_setup; plat->fix_soc_reset = loongson_dwmac_fix_reset; plat->suspend = loongson_dwmac_suspend; plat->resume = loongson_dwmac_resume; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c index 32b5d1492e2e9..894ee66f5c9bc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson1.c @@ -38,8 +38,6 @@ #define GMAC_SHUT BIT(6) #define PHY_INTF_SELI GENMASK(30, 28) -#define PHY_INTF_MII FIELD_PREP(PHY_INTF_SELI, 0) -#define PHY_INTF_RMII FIELD_PREP(PHY_INTF_SELI, 4) struct ls1x_dwmac { struct plat_stmmacenet_data *plat_dat; @@ -140,22 +138,18 @@ static int ls1c_dwmac_syscon_init(struct platform_device *pdev, void *priv) struct ls1x_dwmac *dwmac = priv; struct plat_stmmacenet_data *plat = dwmac->plat_dat; struct regmap *regmap = dwmac->regmap; + int phy_intf_sel; - switch (plat->phy_interface) { - case PHY_INTERFACE_MODE_MII: - regmap_update_bits(regmap, LS1X_SYSCON1, PHY_INTF_SELI, - PHY_INTF_MII); - break; - case PHY_INTERFACE_MODE_RMII: - regmap_update_bits(regmap, LS1X_SYSCON1, PHY_INTF_SELI, - PHY_INTF_RMII); - break; - default: + phy_intf_sel = stmmac_get_phy_intf_sel(plat->phy_interface); + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RMII) { dev_err(&pdev->dev, "Unsupported PHY-mode %u\n", plat->phy_interface); return -EOPNOTSUPP; } + regmap_update_bits(regmap, LS1X_SYSCON1, PHY_INTF_SELI, + FIELD_PREP(PHY_INTF_SELI, phy_intf_sel)); regmap_update_bits(regmap, LS1X_SYSCON0, GMAC0_SHUT, 0); return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c index 2562a6d036a2a..c68d7de1f8ac5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-lpc18xx.c @@ -21,16 +21,29 @@ /* Register defines for CREG syscon */ #define LPC18XX_CREG_CREG6 0x12c -# define LPC18XX_CREG_CREG6_ETHMODE_MASK 0x7 -# define LPC18XX_CREG_CREG6_ETHMODE_MII 0x0 -# define LPC18XX_CREG_CREG6_ETHMODE_RMII 0x4 +# define LPC18XX_CREG_CREG6_ETHMODE_MASK GENMASK(2, 0) + +static int lpc18xx_set_phy_intf_sel(void *bsp_priv, u8 phy_intf_sel) +{ + struct regmap *reg = bsp_priv; + + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RMII) + return -EINVAL; + + regmap_update_bits(reg, LPC18XX_CREG_CREG6, + LPC18XX_CREG_CREG6_ETHMODE_MASK, + FIELD_PREP(LPC18XX_CREG_CREG6_ETHMODE_MASK, + phy_intf_sel)); + + return 0; +} static int lpc18xx_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; - struct regmap *reg; - u8 ethmode; + struct regmap *regmap; int ret; ret = stmmac_get_platform_resources(pdev, &stmmac_res); @@ -41,25 +54,16 @@ static int lpc18xx_dwmac_probe(struct platform_device *pdev) if (IS_ERR(plat_dat)) return PTR_ERR(plat_dat); - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; - reg = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); - if (IS_ERR(reg)) { + regmap = syscon_regmap_lookup_by_compatible("nxp,lpc1850-creg"); + if (IS_ERR(regmap)) { dev_err(&pdev->dev, "syscon lookup failed\n"); - return PTR_ERR(reg); - } - - if (plat_dat->phy_interface == PHY_INTERFACE_MODE_MII) { - ethmode = LPC18XX_CREG_CREG6_ETHMODE_MII; - } else if (plat_dat->phy_interface == PHY_INTERFACE_MODE_RMII) { - ethmode = LPC18XX_CREG_CREG6_ETHMODE_RMII; - } else { - dev_err(&pdev->dev, "Only MII and RMII mode supported\n"); - return -EINVAL; + return PTR_ERR(regmap); } - regmap_update_bits(reg, LPC18XX_CREG_CREG6, - LPC18XX_CREG_CREG6_ETHMODE_MASK, ethmode); + plat_dat->bsp_priv = regmap; + plat_dat->set_phy_intf_sel = lpc18xx_set_phy_intf_sel; return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res); } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index f1b36f0a401de..1f2d7d19ca56e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -17,9 +17,6 @@ /* Peri Configuration register for mt2712 */ #define PERI_ETH_PHY_INTF_SEL 0x418 -#define PHY_INTF_MII 0 -#define PHY_INTF_RGMII 1 -#define PHY_INTF_RMII 4 #define RMII_CLK_SRC_RXC BIT(4) #define RMII_CLK_SRC_INTERNAL BIT(5) @@ -88,7 +85,8 @@ struct mediatek_dwmac_plat_data { }; struct mediatek_dwmac_variant { - int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat); + int (*dwmac_set_phy_interface)(struct mediatek_dwmac_plat_data *plat, + u8 phy_intf_sel); int (*dwmac_set_delay)(struct mediatek_dwmac_plat_data *plat); /* clock ids to be requested */ @@ -109,29 +107,16 @@ static const char * const mt8195_dwmac_clk_l[] = { "axi", "apb", "mac_cg", "mac_main", "ptp_ref" }; -static int mt2712_set_interface(struct mediatek_dwmac_plat_data *plat) +static int mt2712_set_interface(struct mediatek_dwmac_plat_data *plat, + u8 phy_intf_sel) { - int rmii_clk_from_mac = plat->rmii_clk_from_mac ? RMII_CLK_SRC_INTERNAL : 0; - int rmii_rxc = plat->rmii_rxc ? RMII_CLK_SRC_RXC : 0; - u32 intf_val = 0; + u32 intf_val = phy_intf_sel; - /* select phy interface in top control domain */ - switch (plat->phy_mode) { - case PHY_INTERFACE_MODE_MII: - intf_val |= PHY_INTF_MII; - break; - case PHY_INTERFACE_MODE_RMII: - intf_val |= (PHY_INTF_RMII | rmii_rxc | rmii_clk_from_mac); - break; - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_ID: - intf_val |= PHY_INTF_RGMII; - break; - default: - dev_err(plat->dev, "phy interface not supported\n"); - return -EINVAL; + if (phy_intf_sel == PHY_INTF_SEL_RMII) { + if (plat->rmii_clk_from_mac) + intf_val |= RMII_CLK_SRC_INTERNAL; + if (plat->rmii_rxc) + intf_val |= RMII_CLK_SRC_RXC; } regmap_write(plat->peri_regmap, PERI_ETH_PHY_INTF_SEL, intf_val); @@ -288,30 +273,16 @@ static const struct mediatek_dwmac_variant mt2712_gmac_variant = { .tx_delay_max = 17600, }; -static int mt8195_set_interface(struct mediatek_dwmac_plat_data *plat) +static int mt8195_set_interface(struct mediatek_dwmac_plat_data *plat, + u8 phy_intf_sel) { - int rmii_clk_from_mac = plat->rmii_clk_from_mac ? MT8195_RMII_CLK_SRC_INTERNAL : 0; - int rmii_rxc = plat->rmii_rxc ? MT8195_RMII_CLK_SRC_RXC : 0; - u32 intf_val = 0; + u32 intf_val = FIELD_PREP(MT8195_ETH_INTF_SEL, phy_intf_sel); - /* select phy interface in top control domain */ - switch (plat->phy_mode) { - case PHY_INTERFACE_MODE_MII: - intf_val |= FIELD_PREP(MT8195_ETH_INTF_SEL, PHY_INTF_MII); - break; - case PHY_INTERFACE_MODE_RMII: - intf_val |= (rmii_rxc | rmii_clk_from_mac); - intf_val |= FIELD_PREP(MT8195_ETH_INTF_SEL, PHY_INTF_RMII); - break; - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_ID: - intf_val |= FIELD_PREP(MT8195_ETH_INTF_SEL, PHY_INTF_RGMII); - break; - default: - dev_err(plat->dev, "phy interface not supported\n"); - return -EINVAL; + if (phy_intf_sel == PHY_INTF_SEL_RMII) { + if (plat->rmii_clk_from_mac) + intf_val |= MT8195_RMII_CLK_SRC_INTERNAL; + if (plat->rmii_rxc) + intf_val |= MT8195_RMII_CLK_SRC_RXC; } /* MT8195 only support external PHY */ @@ -527,10 +498,18 @@ static int mediatek_dwmac_init(struct device *dev, void *priv) { struct mediatek_dwmac_plat_data *plat = priv; const struct mediatek_dwmac_variant *variant = plat->variant; - int ret; + int phy_intf_sel, ret; if (variant->dwmac_set_phy_interface) { - ret = variant->dwmac_set_phy_interface(plat); + phy_intf_sel = stmmac_get_phy_intf_sel(plat->phy_mode); + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) { + dev_err(plat->dev, "phy interface not supported\n"); + return phy_intf_sel < 0 ? phy_intf_sel : -EINVAL; + } + + ret = variant->dwmac_set_phy_interface(plat, phy_intf_sel); if (ret) { dev_err(dev, "failed to set phy interface, err = %d\n", ret); return ret; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index a50782994b979..e4d5c41294f4e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -26,8 +26,6 @@ #define PRG_ETH0_RGMII_MODE BIT(0) #define PRG_ETH0_EXT_PHY_MODE_MASK GENMASK(2, 0) -#define PRG_ETH0_EXT_RGMII_MODE 1 -#define PRG_ETH0_EXT_RMII_MODE 4 /* mux to choose between fclk_div2 (bit unset) and mpll2 (bit set) */ #define PRG_ETH0_CLK_M250_SEL_MASK GENMASK(4, 4) @@ -238,28 +236,20 @@ static int meson8b_set_phy_mode(struct meson8b_dwmac *dwmac) static int meson_axg_set_phy_mode(struct meson8b_dwmac *dwmac) { - switch (dwmac->phy_mode) { - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_TXID: - /* enable RGMII mode */ - meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, - PRG_ETH0_EXT_PHY_MODE_MASK, - PRG_ETH0_EXT_RGMII_MODE); - break; - case PHY_INTERFACE_MODE_RMII: - /* disable RGMII mode -> enables RMII mode */ - meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, - PRG_ETH0_EXT_PHY_MODE_MASK, - PRG_ETH0_EXT_RMII_MODE); - break; - default: + int phy_intf_sel; + + phy_intf_sel = stmmac_get_phy_intf_sel(dwmac->phy_mode); + if (phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) { dev_err(dwmac->dev, "fail to set phy-mode %s\n", phy_modes(dwmac->phy_mode)); - return -EINVAL; + return phy_intf_sel < 0 ? phy_intf_sel : -EINVAL; } + meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_EXT_PHY_MODE_MASK, + FIELD_PREP(PRG_ETH0_EXT_PHY_MODE_MASK, + phy_intf_sel)); + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c index d8fd4d8f6ced7..1a616a71c36ac 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c @@ -76,10 +76,6 @@ #define RGMII_CONFIG2_DATA_DIVIDE_CLK_SEL BIT(6) #define RGMII_CONFIG2_TX_CLK_PHASE_SHIFT_EN BIT(5) -/* MAC_CTRL_REG bits */ -#define ETHQOS_MAC_CTRL_SPEED_MODE BIT(14) -#define ETHQOS_MAC_CTRL_PORT_SEL BIT(15) - /* EMAC_WRAPPER_SGMII_PHY_CNTRL1 bits */ #define SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN BIT(3) @@ -96,7 +92,6 @@ struct ethqos_emac_driver_data { bool rgmii_config_loopback_en; bool has_emac_ge_3; const char *link_clk_name; - bool has_integrated_pcs; u32 dma_addr_width; struct dwmac4_addrs dwmac4_addrs; bool needs_sgmii_loopback; @@ -282,7 +277,6 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = { .rgmii_config_loopback_en = false, .has_emac_ge_3 = true, .link_clk_name = "phyaux", - .has_integrated_pcs = true, .needs_sgmii_loopback = true, .dma_addr_width = 36, .dwmac4_addrs = { @@ -624,7 +618,7 @@ static void ethqos_set_serdes_speed(struct qcom_ethqos *ethqos, int speed) static void ethqos_pcs_set_inband(struct stmmac_priv *priv, bool enable) { - stmmac_pcs_ctrl_ane(priv, enable, 0, 0); + stmmac_pcs_ctrl_ane(priv, enable, 0); } /* On interface toggle MAC registers gets reset. @@ -634,13 +628,9 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) { struct net_device *dev = platform_get_drvdata(ethqos->pdev); struct stmmac_priv *priv = netdev_priv(dev); - int val; - - val = readl(ethqos->mac_base + MAC_CTRL_REG); switch (speed) { case SPEED_2500: - val &= ~ETHQOS_MAC_CTRL_PORT_SEL; rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); @@ -648,7 +638,6 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) ethqos_pcs_set_inband(priv, false); break; case SPEED_1000: - val &= ~ETHQOS_MAC_CTRL_PORT_SEL; rgmii_updatel(ethqos, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_CONFIG2_RGMII_CLK_SEL_CFG, RGMII_IO_MACRO_CONFIG2); @@ -656,13 +645,10 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) ethqos_pcs_set_inband(priv, true); break; case SPEED_100: - val |= ETHQOS_MAC_CTRL_PORT_SEL | ETHQOS_MAC_CTRL_SPEED_MODE; ethqos_set_serdes_speed(ethqos, SPEED_1000); ethqos_pcs_set_inband(priv, true); break; case SPEED_10: - val |= ETHQOS_MAC_CTRL_PORT_SEL; - val &= ~ETHQOS_MAC_CTRL_SPEED_MODE; rgmii_updatel(ethqos, RGMII_CONFIG_SGMII_CLK_DVDR, FIELD_PREP(RGMII_CONFIG_SGMII_CLK_DVDR, SGMII_10M_RX_CLK_DVDR), @@ -672,9 +658,7 @@ static int ethqos_configure_sgmii(struct qcom_ethqos *ethqos, int speed) break; } - writel(val, ethqos->mac_base + MAC_CTRL_REG); - - return val; + return 0; } static int ethqos_configure(struct qcom_ethqos *ethqos, int speed) @@ -848,7 +832,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->fix_mac_speed = ethqos_fix_mac_speed; plat_dat->dump_debug_regs = rgmii_dump; plat_dat->ptp_clk_freq_config = ethqos_ptp_clk_freq_config; - plat_dat->has_gmac4 = 1; + plat_dat->core_type = DWMAC_CORE_GMAC4; if (ethqos->has_emac_ge_3) plat_dat->dwmac4_addrs = &data->dwmac4_addrs; plat_dat->pmt = 1; @@ -856,8 +840,6 @@ static int qcom_ethqos_probe(struct platform_device *pdev) plat_dat->flags |= STMMAC_FLAG_TSO_EN; if (of_device_is_compatible(np, "qcom,qcs404-ethqos")) plat_dat->flags |= STMMAC_FLAG_RX_CLK_RUNS_IN_LPI; - if (data->has_integrated_pcs) - plat_dat->flags |= STMMAC_FLAG_HAS_INTEGRATED_PCS; if (data->dma_addr_width) plat_dat->host_dma_width = data->dma_addr_width; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c index 0786816e05f04..6e75da577af5d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c @@ -149,11 +149,13 @@ static int rk_set_clk_mac_speed(struct rk_priv_data *bsp_priv, return clk_set_rate(clk_mac_speed, rate); } -#define HIWORD_UPDATE(val, mask, shift) \ - (FIELD_PREP_WM16((mask) << (shift), (val))) +#define GRF_FIELD(hi, lo, val) \ + FIELD_PREP_WM16(GENMASK_U16(hi, lo), val) +#define GRF_FIELD_CONST(hi, lo, val) \ + FIELD_PREP_WM16_CONST(GENMASK_U16(hi, lo), val) -#define GRF_BIT(nr) (BIT(nr) | BIT(nr+16)) -#define GRF_CLR_BIT(nr) (BIT(nr+16)) +#define GRF_BIT(nr) (BIT(nr) | BIT(nr+16)) +#define GRF_CLR_BIT(nr) (BIT(nr+16)) #define DELAY_ENABLE(soc, tx, rx) \ (((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \ @@ -167,9 +169,9 @@ static int rk_set_clk_mac_speed(struct rk_priv_data *bsp_priv, #define RK_MACPHY_ENABLE GRF_BIT(0) #define RK_MACPHY_DISABLE GRF_CLR_BIT(0) #define RK_MACPHY_CFG_CLK_50M GRF_BIT(14) -#define RK_GMAC2PHY_RMII_MODE (GRF_BIT(6) | GRF_CLR_BIT(7)) -#define RK_GRF_CON2_MACPHY_ID HIWORD_UPDATE(0x1234, 0xffff, 0) -#define RK_GRF_CON3_MACPHY_ID HIWORD_UPDATE(0x35, 0x3f, 0) +#define RK_GMAC2PHY_RMII_MODE GRF_FIELD(7, 6, 1) +#define RK_GRF_CON2_MACPHY_ID GRF_FIELD(15, 0, 0x1234) +#define RK_GRF_CON3_MACPHY_ID GRF_FIELD(5, 0, 0x35) static void rk_gmac_integrated_ephy_powerup(struct rk_priv_data *priv) { @@ -203,7 +205,7 @@ static void rk_gmac_integrated_ephy_powerdown(struct rk_priv_data *priv) #define RK_FEPHY_SHUTDOWN GRF_BIT(1) #define RK_FEPHY_POWERUP GRF_CLR_BIT(1) #define RK_FEPHY_INTERNAL_RMII_SEL GRF_BIT(6) -#define RK_FEPHY_24M_CLK_SEL (GRF_BIT(8) | GRF_BIT(9)) +#define RK_FEPHY_24M_CLK_SEL GRF_FIELD(9, 8, 3) #define RK_FEPHY_PHY_ID GRF_BIT(11) static void rk_gmac_integrated_fephy_powerup(struct rk_priv_data *priv, @@ -232,15 +234,14 @@ static void rk_gmac_integrated_fephy_powerdown(struct rk_priv_data *priv, #define PX30_GRF_GMAC_CON1 0x0904 /* PX30_GRF_GMAC_CON1 */ -#define PX30_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \ - GRF_BIT(6)) +#define PX30_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define PX30_GMAC_SPEED_10M GRF_CLR_BIT(2) #define PX30_GMAC_SPEED_100M GRF_BIT(2) static void px30_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1, - PX30_GMAC_PHY_INTF_SEL_RMII); + PX30_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static int px30_set_speed(struct rk_priv_data *bsp_priv, @@ -285,23 +286,20 @@ static const struct rk_gmac_ops px30_ops = { #define RK3128_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) #define RK3128_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3128_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3128_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3128_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3128_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3128_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RK3128_GRF_MAC_CON1 */ -#define RK3128_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(6) | GRF_CLR_BIT(7) | GRF_CLR_BIT(8)) -#define RK3128_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | GRF_BIT(8)) +#define RK3128_GMAC_PHY_INTF_SEL(val) GRF_FIELD(8, 6, val) #define RK3128_GMAC_FLOW_CTRL GRF_BIT(9) #define RK3128_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(9) #define RK3128_GMAC_SPEED_10M GRF_CLR_BIT(10) #define RK3128_GMAC_SPEED_100M GRF_BIT(10) #define RK3128_GMAC_RMII_CLK_25M GRF_BIT(11) #define RK3128_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(11) -#define RK3128_GMAC_CLK_125M (GRF_CLR_BIT(12) | GRF_CLR_BIT(13)) -#define RK3128_GMAC_CLK_25M (GRF_BIT(12) | GRF_BIT(13)) -#define RK3128_GMAC_CLK_2_5M (GRF_CLR_BIT(12) | GRF_BIT(13)) +#define RK3128_GMAC_CLK_125M GRF_FIELD_CONST(13, 12, 0) +#define RK3128_GMAC_CLK_25M GRF_FIELD_CONST(13, 12, 3) +#define RK3128_GMAC_CLK_2_5M GRF_FIELD_CONST(13, 12, 2) #define RK3128_GMAC_RMII_MODE GRF_BIT(14) #define RK3128_GMAC_RMII_MODE_CLR GRF_CLR_BIT(14) @@ -309,7 +307,7 @@ static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_PHY_INTF_SEL_RGMII | + RK3128_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3128_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON0, DELAY_ENABLE(RK3128, tx_delay, rx_delay) | @@ -320,7 +318,8 @@ static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1, - RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE); + RK3128_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3128_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3128_reg_speed_data = { @@ -350,23 +349,20 @@ static const struct rk_gmac_ops rk3128_ops = { #define RK3228_GRF_CON_MUX 0x50 /* RK3228_GRF_MAC_CON0 */ -#define RK3228_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3228_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3228_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3228_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RK3228_GRF_MAC_CON1 */ -#define RK3228_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RK3228_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3228_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RK3228_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3228_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3228_GMAC_SPEED_10M GRF_CLR_BIT(2) #define RK3228_GMAC_SPEED_100M GRF_BIT(2) #define RK3228_GMAC_RMII_CLK_25M GRF_BIT(7) #define RK3228_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(7) -#define RK3228_GMAC_CLK_125M (GRF_CLR_BIT(8) | GRF_CLR_BIT(9)) -#define RK3228_GMAC_CLK_25M (GRF_BIT(8) | GRF_BIT(9)) -#define RK3228_GMAC_CLK_2_5M (GRF_CLR_BIT(8) | GRF_BIT(9)) +#define RK3228_GMAC_CLK_125M GRF_FIELD_CONST(9, 8, 0) +#define RK3228_GMAC_CLK_25M GRF_FIELD_CONST(9, 8, 3) +#define RK3228_GMAC_CLK_2_5M GRF_FIELD_CONST(9, 8, 2) #define RK3228_GMAC_RMII_MODE GRF_BIT(10) #define RK3228_GMAC_RMII_MODE_CLR GRF_CLR_BIT(10) #define RK3228_GMAC_TXCLK_DLY_ENABLE GRF_BIT(0) @@ -381,7 +377,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_PHY_INTF_SEL_RGMII | + RK3228_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3228_GMAC_RMII_MODE_CLR | DELAY_ENABLE(RK3228, tx_delay, rx_delay)); @@ -393,7 +389,7 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3228_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1, - RK3228_GMAC_PHY_INTF_SEL_RMII | + RK3228_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | RK3228_GMAC_RMII_MODE); /* set MAC to RMII mode */ @@ -435,19 +431,16 @@ static const struct rk_gmac_ops rk3228_ops = { #define RK3288_GRF_SOC_CON3 0x0250 /*RK3288_GRF_SOC_CON1*/ -#define RK3288_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(6) | GRF_CLR_BIT(7) | \ - GRF_CLR_BIT(8)) -#define RK3288_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(6) | GRF_CLR_BIT(7) | \ - GRF_BIT(8)) +#define RK3288_GMAC_PHY_INTF_SEL(val) GRF_FIELD(8, 6, val) #define RK3288_GMAC_FLOW_CTRL GRF_BIT(9) #define RK3288_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(9) #define RK3288_GMAC_SPEED_10M GRF_CLR_BIT(10) #define RK3288_GMAC_SPEED_100M GRF_BIT(10) #define RK3288_GMAC_RMII_CLK_25M GRF_BIT(11) #define RK3288_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(11) -#define RK3288_GMAC_CLK_125M (GRF_CLR_BIT(12) | GRF_CLR_BIT(13)) -#define RK3288_GMAC_CLK_25M (GRF_BIT(12) | GRF_BIT(13)) -#define RK3288_GMAC_CLK_2_5M (GRF_CLR_BIT(12) | GRF_BIT(13)) +#define RK3288_GMAC_CLK_125M GRF_FIELD_CONST(13, 12, 0) +#define RK3288_GMAC_CLK_25M GRF_FIELD_CONST(13, 12, 3) +#define RK3288_GMAC_CLK_2_5M GRF_FIELD_CONST(13, 12, 2) #define RK3288_GMAC_RMII_MODE GRF_BIT(14) #define RK3288_GMAC_RMII_MODE_CLR GRF_CLR_BIT(14) @@ -456,14 +449,14 @@ static const struct rk_gmac_ops rk3228_ops = { #define RK3288_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) #define RK3288_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3288_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3288_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3288_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3288_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3288_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_PHY_INTF_SEL_RGMII | + RK3288_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3288_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON3, DELAY_ENABLE(RK3288, tx_delay, rx_delay) | @@ -474,7 +467,8 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3288_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1, - RK3288_GMAC_PHY_INTF_SEL_RMII | RK3288_GMAC_RMII_MODE); + RK3288_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3288_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3288_reg_speed_data = { @@ -501,8 +495,7 @@ static const struct rk_gmac_ops rk3288_ops = { #define RK3308_GRF_MAC_CON0 0x04a0 /* RK3308_GRF_MAC_CON0 */ -#define RK3308_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(2) | GRF_CLR_BIT(3) | \ - GRF_BIT(4)) +#define RK3308_GMAC_PHY_INTF_SEL(val) GRF_FIELD(4, 2, val) #define RK3308_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3308_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3308_GMAC_SPEED_10M GRF_CLR_BIT(0) @@ -511,7 +504,7 @@ static const struct rk_gmac_ops rk3288_ops = { static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0, - RK3308_GMAC_PHY_INTF_SEL_RMII); + RK3308_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_reg_speed_data rk3308_reg_speed_data = { @@ -537,23 +530,20 @@ static const struct rk_gmac_ops rk3308_ops = { #define RK3328_GRF_MACPHY_CON1 0xb04 /* RK3328_GRF_MAC_CON0 */ -#define RK3328_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 7) -#define RK3328_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3328_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(13, 7, val) +#define RK3328_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RK3328_GRF_MAC_CON1 */ -#define RK3328_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RK3328_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3328_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RK3328_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3328_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3328_GMAC_SPEED_10M GRF_CLR_BIT(2) #define RK3328_GMAC_SPEED_100M GRF_BIT(2) #define RK3328_GMAC_RMII_CLK_25M GRF_BIT(7) #define RK3328_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(7) -#define RK3328_GMAC_CLK_125M (GRF_CLR_BIT(11) | GRF_CLR_BIT(12)) -#define RK3328_GMAC_CLK_25M (GRF_BIT(11) | GRF_BIT(12)) -#define RK3328_GMAC_CLK_2_5M (GRF_CLR_BIT(11) | GRF_BIT(12)) +#define RK3328_GMAC_CLK_125M GRF_FIELD_CONST(12, 11, 0) +#define RK3328_GMAC_CLK_25M GRF_FIELD_CONST(12, 11, 3) +#define RK3328_GMAC_CLK_2_5M GRF_FIELD_CONST(12, 11, 2) #define RK3328_GMAC_RMII_MODE GRF_BIT(9) #define RK3328_GMAC_RMII_MODE_CLR GRF_CLR_BIT(9) #define RK3328_GMAC_TXCLK_DLY_ENABLE GRF_BIT(0) @@ -566,7 +556,7 @@ static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1, - RK3328_GMAC_PHY_INTF_SEL_RGMII | + RK3328_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3328_GMAC_RMII_MODE_CLR | RK3328_GMAC_RXCLK_DLY_ENABLE | RK3328_GMAC_TXCLK_DLY_ENABLE); @@ -584,7 +574,7 @@ static void rk3328_set_to_rmii(struct rk_priv_data *bsp_priv) RK3328_GRF_MAC_CON1; regmap_write(bsp_priv->grf, reg, - RK3328_GMAC_PHY_INTF_SEL_RMII | + RK3328_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | RK3328_GMAC_RMII_MODE); } @@ -630,19 +620,16 @@ static const struct rk_gmac_ops rk3328_ops = { #define RK3366_GRF_SOC_CON7 0x041c /* RK3366_GRF_SOC_CON6 */ -#define RK3366_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_CLR_BIT(11)) -#define RK3366_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_BIT(11)) +#define RK3366_GMAC_PHY_INTF_SEL(val) GRF_FIELD(11, 9, val) #define RK3366_GMAC_FLOW_CTRL GRF_BIT(8) #define RK3366_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(8) #define RK3366_GMAC_SPEED_10M GRF_CLR_BIT(7) #define RK3366_GMAC_SPEED_100M GRF_BIT(7) #define RK3366_GMAC_RMII_CLK_25M GRF_BIT(3) #define RK3366_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(3) -#define RK3366_GMAC_CLK_125M (GRF_CLR_BIT(4) | GRF_CLR_BIT(5)) -#define RK3366_GMAC_CLK_25M (GRF_BIT(4) | GRF_BIT(5)) -#define RK3366_GMAC_CLK_2_5M (GRF_CLR_BIT(4) | GRF_BIT(5)) +#define RK3366_GMAC_CLK_125M GRF_FIELD_CONST(5, 4, 0) +#define RK3366_GMAC_CLK_25M GRF_FIELD_CONST(5, 4, 3) +#define RK3366_GMAC_CLK_2_5M GRF_FIELD_CONST(5, 4, 2) #define RK3366_GMAC_RMII_MODE GRF_BIT(6) #define RK3366_GMAC_RMII_MODE_CLR GRF_CLR_BIT(6) @@ -651,14 +638,14 @@ static const struct rk_gmac_ops rk3328_ops = { #define RK3366_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) #define RK3366_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3366_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3366_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3366_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3366_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3366_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_PHY_INTF_SEL_RGMII | + RK3366_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3366_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON7, DELAY_ENABLE(RK3366, tx_delay, rx_delay) | @@ -669,7 +656,8 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3366_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6, - RK3366_GMAC_PHY_INTF_SEL_RMII | RK3366_GMAC_RMII_MODE); + RK3366_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3366_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3366_reg_speed_data = { @@ -697,19 +685,16 @@ static const struct rk_gmac_ops rk3366_ops = { #define RK3368_GRF_SOC_CON16 0x0440 /* RK3368_GRF_SOC_CON15 */ -#define RK3368_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_CLR_BIT(11)) -#define RK3368_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_BIT(11)) +#define RK3368_GMAC_PHY_INTF_SEL(val) GRF_FIELD(11, 9, val) #define RK3368_GMAC_FLOW_CTRL GRF_BIT(8) #define RK3368_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(8) #define RK3368_GMAC_SPEED_10M GRF_CLR_BIT(7) #define RK3368_GMAC_SPEED_100M GRF_BIT(7) #define RK3368_GMAC_RMII_CLK_25M GRF_BIT(3) #define RK3368_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(3) -#define RK3368_GMAC_CLK_125M (GRF_CLR_BIT(4) | GRF_CLR_BIT(5)) -#define RK3368_GMAC_CLK_25M (GRF_BIT(4) | GRF_BIT(5)) -#define RK3368_GMAC_CLK_2_5M (GRF_CLR_BIT(4) | GRF_BIT(5)) +#define RK3368_GMAC_CLK_125M GRF_FIELD_CONST(5, 4, 0) +#define RK3368_GMAC_CLK_25M GRF_FIELD_CONST(5, 4, 3) +#define RK3368_GMAC_CLK_2_5M GRF_FIELD_CONST(5, 4, 2) #define RK3368_GMAC_RMII_MODE GRF_BIT(6) #define RK3368_GMAC_RMII_MODE_CLR GRF_CLR_BIT(6) @@ -718,14 +703,14 @@ static const struct rk_gmac_ops rk3366_ops = { #define RK3368_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) #define RK3368_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3368_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3368_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3368_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3368_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3368_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_PHY_INTF_SEL_RGMII | + RK3368_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3368_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON16, DELAY_ENABLE(RK3368, tx_delay, rx_delay) | @@ -736,7 +721,8 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3368_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15, - RK3368_GMAC_PHY_INTF_SEL_RMII | RK3368_GMAC_RMII_MODE); + RK3368_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3368_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3368_reg_speed_data = { @@ -764,19 +750,16 @@ static const struct rk_gmac_ops rk3368_ops = { #define RK3399_GRF_SOC_CON6 0xc218 /* RK3399_GRF_SOC_CON5 */ -#define RK3399_GMAC_PHY_INTF_SEL_RGMII (GRF_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_CLR_BIT(11)) -#define RK3399_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(9) | GRF_CLR_BIT(10) | \ - GRF_BIT(11)) +#define RK3399_GMAC_PHY_INTF_SEL(val) GRF_FIELD(11, 9, val) #define RK3399_GMAC_FLOW_CTRL GRF_BIT(8) #define RK3399_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(8) #define RK3399_GMAC_SPEED_10M GRF_CLR_BIT(7) #define RK3399_GMAC_SPEED_100M GRF_BIT(7) #define RK3399_GMAC_RMII_CLK_25M GRF_BIT(3) #define RK3399_GMAC_RMII_CLK_2_5M GRF_CLR_BIT(3) -#define RK3399_GMAC_CLK_125M (GRF_CLR_BIT(4) | GRF_CLR_BIT(5)) -#define RK3399_GMAC_CLK_25M (GRF_BIT(4) | GRF_BIT(5)) -#define RK3399_GMAC_CLK_2_5M (GRF_CLR_BIT(4) | GRF_BIT(5)) +#define RK3399_GMAC_CLK_125M GRF_FIELD_CONST(5, 4, 0) +#define RK3399_GMAC_CLK_25M GRF_FIELD_CONST(5, 4, 3) +#define RK3399_GMAC_CLK_2_5M GRF_FIELD_CONST(5, 4, 2) #define RK3399_GMAC_RMII_MODE GRF_BIT(6) #define RK3399_GMAC_RMII_MODE_CLR GRF_CLR_BIT(6) @@ -785,14 +768,14 @@ static const struct rk_gmac_ops rk3368_ops = { #define RK3399_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) #define RK3399_GMAC_RXCLK_DLY_ENABLE GRF_BIT(15) #define RK3399_GMAC_RXCLK_DLY_DISABLE GRF_CLR_BIT(15) -#define RK3399_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3399_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3399_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3399_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_PHY_INTF_SEL_RGMII | + RK3399_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3399_GMAC_RMII_MODE_CLR); regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON6, DELAY_ENABLE(RK3399, tx_delay, rx_delay) | @@ -803,7 +786,8 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3399_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5, - RK3399_GMAC_PHY_INTF_SEL_RMII | RK3399_GMAC_RMII_MODE); + RK3399_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII) | + RK3399_GMAC_RMII_MODE); } static const struct rk_reg_speed_data rk3399_reg_speed_data = { @@ -827,6 +811,69 @@ static const struct rk_gmac_ops rk3399_ops = { .set_speed = rk3399_set_speed, }; +#define RK3506_GRF_SOC_CON8 0x0020 +#define RK3506_GRF_SOC_CON11 0x002c + +#define RK3506_GMAC_RMII_MODE GRF_BIT(1) + +#define RK3506_GMAC_CLK_RMII_DIV2 GRF_BIT(3) +#define RK3506_GMAC_CLK_RMII_DIV20 GRF_CLR_BIT(3) + +#define RK3506_GMAC_CLK_SELECT_CRU GRF_CLR_BIT(5) +#define RK3506_GMAC_CLK_SELECT_IO GRF_BIT(5) + +#define RK3506_GMAC_CLK_RMII_GATE GRF_BIT(2) +#define RK3506_GMAC_CLK_RMII_NOGATE GRF_CLR_BIT(2) + +static void rk3506_set_to_rmii(struct rk_priv_data *bsp_priv) +{ + unsigned int id = bsp_priv->id, offset; + + offset = (id == 1) ? RK3506_GRF_SOC_CON11 : RK3506_GRF_SOC_CON8; + regmap_write(bsp_priv->grf, offset, RK3506_GMAC_RMII_MODE); +} + +static const struct rk_reg_speed_data rk3506_reg_speed_data = { + .rmii_10 = RK3506_GMAC_CLK_RMII_DIV20, + .rmii_100 = RK3506_GMAC_CLK_RMII_DIV2, +}; + +static int rk3506_set_speed(struct rk_priv_data *bsp_priv, + phy_interface_t interface, int speed) +{ + unsigned int id = bsp_priv->id, offset; + + offset = (id == 1) ? RK3506_GRF_SOC_CON11 : RK3506_GRF_SOC_CON8; + return rk_set_reg_speed(bsp_priv, &rk3506_reg_speed_data, + offset, interface, speed); +} + +static void rk3506_set_clock_selection(struct rk_priv_data *bsp_priv, + bool input, bool enable) +{ + unsigned int value, offset, id = bsp_priv->id; + + offset = (id == 1) ? RK3506_GRF_SOC_CON11 : RK3506_GRF_SOC_CON8; + + value = input ? RK3506_GMAC_CLK_SELECT_IO : + RK3506_GMAC_CLK_SELECT_CRU; + value |= enable ? RK3506_GMAC_CLK_RMII_NOGATE : + RK3506_GMAC_CLK_RMII_GATE; + regmap_write(bsp_priv->grf, offset, value); +} + +static const struct rk_gmac_ops rk3506_ops = { + .set_to_rmii = rk3506_set_to_rmii, + .set_speed = rk3506_set_speed, + .set_clock_selection = rk3506_set_clock_selection, + .regs_valid = true, + .regs = { + 0xff4c8000, /* gmac0 */ + 0xff4d0000, /* gmac1 */ + 0x0, /* sentinel */ + }, +}; + #define RK3528_VO_GRF_GMAC_CON 0x0018 #define RK3528_VO_GRF_MACPHY_CON0 0x001c #define RK3528_VO_GRF_MACPHY_CON1 0x0020 @@ -838,8 +885,8 @@ static const struct rk_gmac_ops rk3399_ops = { #define RK3528_GMAC_TXCLK_DLY_ENABLE GRF_BIT(14) #define RK3528_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(14) -#define RK3528_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 8) -#define RK3528_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 0) +#define RK3528_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(15, 8, val) +#define RK3528_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(7, 0, val) #define RK3528_GMAC0_PHY_INTF_SEL_RMII GRF_BIT(1) #define RK3528_GMAC1_PHY_INTF_SEL_RGMII GRF_CLR_BIT(8) @@ -853,9 +900,9 @@ static const struct rk_gmac_ops rk3399_ops = { #define RK3528_GMAC1_CLK_RMII_DIV2 GRF_BIT(10) #define RK3528_GMAC1_CLK_RMII_DIV20 GRF_CLR_BIT(10) -#define RK3528_GMAC1_CLK_RGMII_DIV1 (GRF_CLR_BIT(11) | GRF_CLR_BIT(10)) -#define RK3528_GMAC1_CLK_RGMII_DIV5 (GRF_BIT(11) | GRF_BIT(10)) -#define RK3528_GMAC1_CLK_RGMII_DIV50 (GRF_BIT(11) | GRF_CLR_BIT(10)) +#define RK3528_GMAC1_CLK_RGMII_DIV1 GRF_FIELD_CONST(11, 10, 0) +#define RK3528_GMAC1_CLK_RGMII_DIV5 GRF_FIELD_CONST(11, 10, 3) +#define RK3528_GMAC1_CLK_RGMII_DIV50 GRF_FIELD_CONST(11, 10, 2) #define RK3528_GMAC0_CLK_RMII_GATE GRF_BIT(2) #define RK3528_GMAC0_CLK_RMII_NOGATE GRF_CLR_BIT(2) @@ -966,10 +1013,7 @@ static const struct rk_gmac_ops rk3528_ops = { #define RK3568_GRF_GMAC1_CON1 0x038c /* RK3568_GRF_GMAC0_CON1 && RK3568_GRF_GMAC1_CON1 */ -#define RK3568_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RK3568_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RK3568_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RK3568_GMAC_FLOW_CTRL GRF_BIT(3) #define RK3568_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RK3568_GMAC_RXCLK_DLY_ENABLE GRF_BIT(1) @@ -978,8 +1022,8 @@ static const struct rk_gmac_ops rk3528_ops = { #define RK3568_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(0) /* RK3568_GRF_GMAC0_CON0 && RK3568_GRF_GMAC1_CON0 */ -#define RK3568_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3568_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3568_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3568_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) @@ -996,7 +1040,7 @@ static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv, RK3568_GMAC_CLK_TX_DL_CFG(tx_delay)); regmap_write(bsp_priv->grf, con1, - RK3568_GMAC_PHY_INTF_SEL_RGMII | + RK3568_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RK3568_GMAC_RXCLK_DLY_ENABLE | RK3568_GMAC_TXCLK_DLY_ENABLE); } @@ -1007,7 +1051,8 @@ static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv) con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 : RK3568_GRF_GMAC0_CON1; - regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII); + regmap_write(bsp_priv->grf, con1, + RK3568_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_gmac_ops rk3568_ops = { @@ -1033,8 +1078,8 @@ static const struct rk_gmac_ops rk3568_ops = { #define RK3576_GMAC_TXCLK_DLY_ENABLE GRF_BIT(7) #define RK3576_GMAC_TXCLK_DLY_DISABLE GRF_CLR_BIT(7) -#define RK3576_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RK3576_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RK3576_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RK3576_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* SDGMAC_GRF */ #define RK3576_GRF_GMAC_CON0 0X0020 @@ -1049,12 +1094,9 @@ static const struct rk_gmac_ops rk3568_ops = { #define RK3576_GMAC_CLK_RMII_DIV2 GRF_BIT(5) #define RK3576_GMAC_CLK_RMII_DIV20 GRF_CLR_BIT(5) -#define RK3576_GMAC_CLK_RGMII_DIV1 \ - (GRF_CLR_BIT(6) | GRF_CLR_BIT(5)) -#define RK3576_GMAC_CLK_RGMII_DIV5 \ - (GRF_BIT(6) | GRF_BIT(5)) -#define RK3576_GMAC_CLK_RGMII_DIV50 \ - (GRF_BIT(6) | GRF_CLR_BIT(5)) +#define RK3576_GMAC_CLK_RGMII_DIV1 GRF_FIELD_CONST(6, 5, 0) +#define RK3576_GMAC_CLK_RGMII_DIV5 GRF_FIELD_CONST(6, 5, 3) +#define RK3576_GMAC_CLK_RGMII_DIV50 GRF_FIELD_CONST(6, 5, 2) #define RK3576_GMAC_CLK_RMII_GATE GRF_BIT(4) #define RK3576_GMAC_CLK_RMII_NOGATE GRF_CLR_BIT(4) @@ -1157,17 +1199,15 @@ static const struct rk_gmac_ops rk3576_ops = { #define RK3588_GMAC_TXCLK_DLY_ENABLE(id) GRF_BIT(2 * (id) + 2) #define RK3588_GMAC_TXCLK_DLY_DISABLE(id) GRF_CLR_BIT(2 * (id) + 2) -#define RK3588_GMAC_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 8) -#define RK3588_GMAC_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0xFF, 0) +#define RK3588_GMAC_CLK_RX_DL_CFG(val) GRF_FIELD(15, 8, val) +#define RK3588_GMAC_CLK_TX_DL_CFG(val) GRF_FIELD(7, 0, val) /* php_grf */ #define RK3588_GRF_GMAC_CON0 0X0008 #define RK3588_GRF_CLK_CON1 0X0070 -#define RK3588_GMAC_PHY_INTF_SEL_RGMII(id) \ - (GRF_BIT(3 + (id) * 6) | GRF_CLR_BIT(4 + (id) * 6) | GRF_CLR_BIT(5 + (id) * 6)) -#define RK3588_GMAC_PHY_INTF_SEL_RMII(id) \ - (GRF_CLR_BIT(3 + (id) * 6) | GRF_CLR_BIT(4 + (id) * 6) | GRF_BIT(5 + (id) * 6)) +#define RK3588_GMAC_PHY_INTF_SEL(id, val) \ + (GRF_FIELD(5, 3, val) << ((id) * 6)) #define RK3588_GMAC_CLK_RMII_MODE(id) GRF_BIT(5 * (id)) #define RK3588_GMAC_CLK_RGMII_MODE(id) GRF_CLR_BIT(5 * (id)) @@ -1179,11 +1219,11 @@ static const struct rk_gmac_ops rk3576_ops = { #define RK3588_GMA_CLK_RMII_DIV20(id) GRF_CLR_BIT(5 * (id) + 2) #define RK3588_GMAC_CLK_RGMII_DIV1(id) \ - (GRF_CLR_BIT(5 * (id) + 2) | GRF_CLR_BIT(5 * (id) + 3)) + (GRF_FIELD_CONST(3, 2, 0) << ((id) * 5)) #define RK3588_GMAC_CLK_RGMII_DIV5(id) \ - (GRF_BIT(5 * (id) + 2) | GRF_BIT(5 * (id) + 3)) + (GRF_FIELD_CONST(3, 2, 3) << ((id) * 5)) #define RK3588_GMAC_CLK_RGMII_DIV50(id) \ - (GRF_CLR_BIT(5 * (id) + 2) | GRF_BIT(5 * (id) + 3)) + (GRF_FIELD_CONST(3, 2, 2) << ((id) * 5)) #define RK3588_GMAC_CLK_RMII_GATE(id) GRF_BIT(5 * (id) + 1) #define RK3588_GMAC_CLK_RMII_NOGATE(id) GRF_CLR_BIT(5 * (id) + 1) @@ -1197,7 +1237,7 @@ static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv, RK3588_GRF_GMAC_CON8; regmap_write(bsp_priv->php_grf, RK3588_GRF_GMAC_CON0, - RK3588_GMAC_PHY_INTF_SEL_RGMII(id)); + RK3588_GMAC_PHY_INTF_SEL(id, PHY_INTF_SEL_RGMII)); regmap_write(bsp_priv->php_grf, RK3588_GRF_CLK_CON1, RK3588_GMAC_CLK_RGMII_MODE(id)); @@ -1214,7 +1254,7 @@ static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rk3588_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->php_grf, RK3588_GRF_GMAC_CON0, - RK3588_GMAC_PHY_INTF_SEL_RMII(bsp_priv->id)); + RK3588_GMAC_PHY_INTF_SEL(bsp_priv->id, PHY_INTF_SEL_RMII)); regmap_write(bsp_priv->php_grf, RK3588_GRF_CLK_CON1, RK3588_GMAC_CLK_RMII_MODE(bsp_priv->id)); @@ -1284,8 +1324,7 @@ static const struct rk_gmac_ops rk3588_ops = { #define RV1108_GRF_GMAC_CON0 0X0900 /* RV1108_GRF_GMAC_CON0 */ -#define RV1108_GMAC_PHY_INTF_SEL_RMII (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \ - GRF_BIT(6)) +#define RV1108_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RV1108_GMAC_FLOW_CTRL GRF_BIT(3) #define RV1108_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(3) #define RV1108_GMAC_SPEED_10M GRF_CLR_BIT(2) @@ -1296,7 +1335,7 @@ static const struct rk_gmac_ops rk3588_ops = { static void rv1108_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0, - RV1108_GMAC_PHY_INTF_SEL_RMII); + RV1108_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_reg_speed_data rv1108_reg_speed_data = { @@ -1321,10 +1360,7 @@ static const struct rk_gmac_ops rv1108_ops = { #define RV1126_GRF_GMAC_CON2 0X0078 /* RV1126_GRF_GMAC_CON0 */ -#define RV1126_GMAC_PHY_INTF_SEL_RGMII \ - (GRF_BIT(4) | GRF_CLR_BIT(5) | GRF_CLR_BIT(6)) -#define RV1126_GMAC_PHY_INTF_SEL_RMII \ - (GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | GRF_BIT(6)) +#define RV1126_GMAC_PHY_INTF_SEL(val) GRF_FIELD(6, 4, val) #define RV1126_GMAC_FLOW_CTRL GRF_BIT(7) #define RV1126_GMAC_FLOW_CTRL_CLR GRF_CLR_BIT(7) #define RV1126_GMAC_M0_RXCLK_DLY_ENABLE GRF_BIT(1) @@ -1337,17 +1373,17 @@ static const struct rk_gmac_ops rv1108_ops = { #define RV1126_GMAC_M1_TXCLK_DLY_DISABLE GRF_CLR_BIT(2) /* RV1126_GRF_GMAC_CON1 */ -#define RV1126_GMAC_M0_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RV1126_GMAC_M0_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RV1126_GMAC_M0_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RV1126_GMAC_M0_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) /* RV1126_GRF_GMAC_CON2 */ -#define RV1126_GMAC_M1_CLK_RX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 8) -#define RV1126_GMAC_M1_CLK_TX_DL_CFG(val) HIWORD_UPDATE(val, 0x7F, 0) +#define RV1126_GMAC_M1_CLK_RX_DL_CFG(val) GRF_FIELD(14, 8, val) +#define RV1126_GMAC_M1_CLK_TX_DL_CFG(val) GRF_FIELD(6, 0, val) static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv, int tx_delay, int rx_delay) { regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0, - RV1126_GMAC_PHY_INTF_SEL_RGMII | + RV1126_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RGMII) | RV1126_GMAC_M0_RXCLK_DLY_ENABLE | RV1126_GMAC_M0_TXCLK_DLY_ENABLE | RV1126_GMAC_M1_RXCLK_DLY_ENABLE | @@ -1365,7 +1401,7 @@ static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv, static void rv1126_set_to_rmii(struct rk_priv_data *bsp_priv) { regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0, - RV1126_GMAC_PHY_INTF_SEL_RMII); + RV1126_GMAC_PHY_INTF_SEL(PHY_INTF_SEL_RMII)); } static const struct rk_gmac_ops rv1126_ops = { @@ -1751,8 +1787,8 @@ static int rk_gmac_probe(struct platform_device *pdev) /* If the stmmac is not already selected as gmac4, * then make sure we fallback to gmac. */ - if (!plat_dat->has_gmac4) { - plat_dat->has_gmac = true; + if (plat_dat->core_type != DWMAC_CORE_GMAC4) { + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->rx_fifo_size = 4096; plat_dat->tx_fifo_size = 2048; } @@ -1809,6 +1845,7 @@ static const struct of_device_id rk_gmac_dwmac_match[] = { { .compatible = "rockchip,rk3366-gmac", .data = &rk3366_ops }, { .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops }, { .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops }, + { .compatible = "rockchip,rk3506-gmac", .data = &rk3506_ops }, { .compatible = "rockchip,rk3528-gmac", .data = &rk3528_ops }, { .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops }, { .compatible = "rockchip,rk3576-gmac", .data = &rk3576_ops }, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c index 221539d760bc8..2b7ad64bfdf74 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c @@ -24,10 +24,10 @@ #define GMAC_INTF_RATE_125M 125000000 /* 125MHz */ /* SoC PHY interface control register */ -#define PHY_INTF_SEL_MII 0x00 -#define PHY_INTF_SEL_SGMII 0x01 -#define PHY_INTF_SEL_RGMII 0x02 -#define PHY_INTF_SEL_RMII 0x08 +#define S32_PHY_INTF_SEL_MII 0x00 +#define S32_PHY_INTF_SEL_SGMII 0x01 +#define S32_PHY_INTF_SEL_RGMII 0x02 +#define S32_PHY_INTF_SEL_RMII 0x08 struct s32_priv_data { void __iomem *ioaddr; @@ -40,7 +40,7 @@ struct s32_priv_data { static int s32_gmac_write_phy_intf_select(struct s32_priv_data *gmac) { - writel(PHY_INTF_SEL_RGMII, gmac->ctrl_sts); + writel(S32_PHY_INTF_SEL_RGMII, gmac->ctrl_sts); dev_dbg(gmac->dev, "PHY mode set to %s\n", phy_modes(*gmac->intf_mode)); @@ -146,7 +146,7 @@ static int s32_dwmac_probe(struct platform_device *pdev) gmac->ioaddr = res.addr; /* S32CC core feature set */ - plat->has_gmac4 = true; + plat->core_type = DWMAC_CORE_GMAC4; plat->pmt = 1; plat->flags |= STMMAC_FLAG_SPH_DISABLE; plat->rx_fifo_size = 20480; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 354f01184e6cc..49d651948e2bd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -5,6 +5,7 @@ */ #include +#include #include #include #include @@ -15,8 +16,10 @@ #include #include +#include "dwxgmac2.h" #include "stmmac.h" #include "stmmac_platform.h" +#include "stmmac_ptp.h" #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_GMII_MII 0x0 #define SYSMGR_EMACGRP_CTRL_PHYSEL_ENUM_RGMII 0x1 @@ -41,9 +44,17 @@ #define SGMII_ADAPTER_ENABLE 0x0000 #define SGMII_ADAPTER_DISABLE 0x0001 +#define SMTG_MDIO_ADDR 0x15 +#define SMTG_TSC_WORD0 0xC +#define SMTG_TSC_WORD1 0xD +#define SMTG_TSC_WORD2 0xE +#define SMTG_TSC_WORD3 0xF +#define SMTG_TSC_SHIFT 16 + struct socfpga_dwmac; struct socfpga_dwmac_ops { int (*set_phy_mode)(struct socfpga_dwmac *dwmac_priv); + void (*setup_plat_dat)(struct socfpga_dwmac *dwmac_priv); }; struct socfpga_dwmac { @@ -268,6 +279,112 @@ static int socfpga_set_phy_mode_common(int phymode, u32 *val) return 0; } +static void get_smtgtime(struct mii_bus *mii, int smtg_addr, u64 *smtg_time) +{ + u64 ns; + + ns = mdiobus_read(mii, smtg_addr, SMTG_TSC_WORD3); + ns <<= SMTG_TSC_SHIFT; + ns |= mdiobus_read(mii, smtg_addr, SMTG_TSC_WORD2); + ns <<= SMTG_TSC_SHIFT; + ns |= mdiobus_read(mii, smtg_addr, SMTG_TSC_WORD1); + ns <<= SMTG_TSC_SHIFT; + ns |= mdiobus_read(mii, smtg_addr, SMTG_TSC_WORD0); + + *smtg_time = ns; +} + +static int smtg_crosststamp(ktime_t *device, struct system_counterval_t *system, + void *ctx) +{ + struct stmmac_priv *priv = (struct stmmac_priv *)ctx; + u32 num_snapshot, gpio_value, acr_value; + void __iomem *ptpaddr = priv->ptpaddr; + void __iomem *ioaddr = priv->hw->pcsr; + unsigned long flags; + u64 smtg_time = 0; + u64 ptp_time = 0; + int i, ret; + u32 v; + + /* Both internal crosstimestamping and external triggered event + * timestamping cannot be run concurrently. + */ + if (priv->plat->flags & STMMAC_FLAG_EXT_SNAPSHOT_EN) + return -EBUSY; + + mutex_lock(&priv->aux_ts_lock); + /* Enable Internal snapshot trigger */ + acr_value = readl(ptpaddr + PTP_ACR); + acr_value &= ~PTP_ACR_MASK; + switch (priv->plat->int_snapshot_num) { + case AUX_SNAPSHOT0: + acr_value |= PTP_ACR_ATSEN0; + break; + case AUX_SNAPSHOT1: + acr_value |= PTP_ACR_ATSEN1; + break; + case AUX_SNAPSHOT2: + acr_value |= PTP_ACR_ATSEN2; + break; + case AUX_SNAPSHOT3: + acr_value |= PTP_ACR_ATSEN3; + break; + default: + mutex_unlock(&priv->aux_ts_lock); + return -EINVAL; + } + writel(acr_value, ptpaddr + PTP_ACR); + + /* Clear FIFO */ + acr_value = readl(ptpaddr + PTP_ACR); + acr_value |= PTP_ACR_ATSFC; + writel(acr_value, ptpaddr + PTP_ACR); + /* Release the mutex */ + mutex_unlock(&priv->aux_ts_lock); + + /* Trigger Internal snapshot signal. Create a rising edge by just toggle + * the GPO0 to low and back to high. + */ + gpio_value = readl(ioaddr + XGMAC_GPIO_STATUS); + gpio_value &= ~XGMAC_GPIO_GPO0; + writel(gpio_value, ioaddr + XGMAC_GPIO_STATUS); + gpio_value |= XGMAC_GPIO_GPO0; + writel(gpio_value, ioaddr + XGMAC_GPIO_STATUS); + + /* Poll for time sync operation done */ + ret = readl_poll_timeout(priv->ioaddr + XGMAC_INT_STATUS, v, + (v & XGMAC_INT_TSIS), 100, 10000); + if (ret) { + netdev_err(priv->dev, "%s: Wait for time sync operation timeout\n", + __func__); + return ret; + } + + *system = (struct system_counterval_t) { + .cycles = 0, + .cs_id = CSID_ARM_ARCH_COUNTER, + .use_nsecs = false, + }; + + num_snapshot = (readl(ioaddr + XGMAC_TIMESTAMP_STATUS) & + XGMAC_TIMESTAMP_ATSNS_MASK) >> + XGMAC_TIMESTAMP_ATSNS_SHIFT; + + /* Repeat until the timestamps are from the FIFO last segment */ + for (i = 0; i < num_snapshot; i++) { + read_lock_irqsave(&priv->ptp_lock, flags); + stmmac_get_ptptime(priv, ptpaddr, &ptp_time); + *device = ns_to_ktime(ptp_time); + read_unlock_irqrestore(&priv->ptp_lock, flags); + } + + get_smtgtime(priv->mii, SMTG_MDIO_ADDR, &smtg_time); + system->cycles = smtg_time; + + return 0; +} + static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac) { struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr; @@ -441,6 +558,43 @@ static int socfpga_dwmac_init(struct platform_device *pdev, void *bsp_priv) return dwmac->ops->set_phy_mode(dwmac); } +static void socfpga_gen5_setup_plat_dat(struct socfpga_dwmac *dwmac) +{ + struct plat_stmmacenet_data *plat_dat = dwmac->plat_dat; + + plat_dat->core_type = DWMAC_CORE_GMAC; + + /* Rx watchdog timer in dwmac is buggy in this hw */ + plat_dat->riwt_off = 1; +} + +static void socfpga_agilex5_setup_plat_dat(struct socfpga_dwmac *dwmac) +{ + struct plat_stmmacenet_data *plat_dat = dwmac->plat_dat; + + plat_dat->core_type = DWMAC_CORE_XGMAC; + + /* Enable TSO */ + plat_dat->flags |= STMMAC_FLAG_TSO_EN; + + /* Enable TBS */ + switch (plat_dat->tx_queues_to_use) { + case 8: + plat_dat->tx_queues_cfg[7].tbs_en = true; + fallthrough; + case 7: + plat_dat->tx_queues_cfg[6].tbs_en = true; + break; + default: + /* Tx Queues 0 - 5 doesn't support TBS on Agilex5 */ + break; + } + + /* Hw supported cross-timestamp */ + plat_dat->int_snapshot_num = AUX_SNAPSHOT0; + plat_dat->crosststamp = smtg_crosststamp; +} + static int socfpga_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; @@ -497,25 +651,31 @@ static int socfpga_dwmac_probe(struct platform_device *pdev) plat_dat->pcs_init = socfpga_dwmac_pcs_init; plat_dat->pcs_exit = socfpga_dwmac_pcs_exit; plat_dat->select_pcs = socfpga_dwmac_select_pcs; - plat_dat->has_gmac = true; - plat_dat->riwt_off = 1; + ops->setup_plat_dat(dwmac); return devm_stmmac_pltfr_probe(pdev, plat_dat, &stmmac_res); } static const struct socfpga_dwmac_ops socfpga_gen5_ops = { .set_phy_mode = socfpga_gen5_set_phy_mode, + .setup_plat_dat = socfpga_gen5_setup_plat_dat, }; static const struct socfpga_dwmac_ops socfpga_gen10_ops = { .set_phy_mode = socfpga_gen10_set_phy_mode, + .setup_plat_dat = socfpga_gen5_setup_plat_dat, +}; + +static const struct socfpga_dwmac_ops socfpga_agilex5_ops = { + .set_phy_mode = socfpga_gen10_set_phy_mode, + .setup_plat_dat = socfpga_agilex5_setup_plat_dat, }; static const struct of_device_id socfpga_dwmac_match[] = { { .compatible = "altr,socfpga-stmmac", .data = &socfpga_gen5_ops }, { .compatible = "altr,socfpga-stmmac-a10-s10", .data = &socfpga_gen10_ops }, - { .compatible = "altr,socfpga-stmmac-agilex5", .data = &socfpga_gen10_ops }, + { .compatible = "altr,socfpga-stmmac-agilex5", .data = &socfpga_agilex5_ops }, { } }; MODULE_DEVICE_TABLE(of, socfpga_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c index 3b7947a7a7ba7..44d4ceb8415f6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c @@ -7,11 +7,16 @@ #include #include +#include #include #include #include "stmmac_platform.h" +struct sophgo_dwmac_data { + bool has_internal_rx_delay; +}; + static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, struct plat_stmmacenet_data *plat_dat, struct stmmac_resources *stmmac_res) @@ -24,7 +29,6 @@ static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE; plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate; plat_dat->multicast_filter_bins = 0; - plat_dat->unicast_filter_entries = 1; return 0; } @@ -32,6 +36,7 @@ static int sophgo_sg2044_dwmac_init(struct platform_device *pdev, static int sophgo_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; + const struct sophgo_dwmac_data *data; struct stmmac_resources stmmac_res; struct device *dev = &pdev->dev; int ret; @@ -50,11 +55,23 @@ static int sophgo_dwmac_probe(struct platform_device *pdev) if (ret) return ret; + data = device_get_match_data(&pdev->dev); + if (data && data->has_internal_rx_delay) { + plat_dat->phy_interface = phy_fix_phy_mode_for_mac_delays(plat_dat->phy_interface, + false, true); + if (plat_dat->phy_interface == PHY_INTERFACE_MODE_NA) + return -EINVAL; + } + return stmmac_dvr_probe(dev, plat_dat, &stmmac_res); } +static const struct sophgo_dwmac_data sg2042_dwmac_data = { + .has_internal_rx_delay = true, +}; + static const struct of_device_id sophgo_dwmac_match[] = { - { .compatible = "sophgo,sg2042-dwmac" }, + { .compatible = "sophgo,sg2042-dwmac", .data = &sg2042_dwmac_data }, { .compatible = "sophgo,sg2044-dwmac" }, { /* sentinel */ } }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c index 6938dd2a79b77..16b955a6d77ba 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c @@ -15,8 +15,6 @@ #include "stmmac_platform.h" -#define STARFIVE_DWMAC_PHY_INFT_RGMII 0x1 -#define STARFIVE_DWMAC_PHY_INFT_RMII 0x4 #define STARFIVE_DWMAC_PHY_INFT_FIELD 0x7U #define JH7100_SYSMAIN_REGISTER49_DLYCHAIN 0xc8 @@ -35,25 +33,15 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat) struct starfive_dwmac *dwmac = plat_dat->bsp_priv; struct regmap *regmap; unsigned int args[2]; - unsigned int mode; + int phy_intf_sel; int err; - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_RMII: - mode = STARFIVE_DWMAC_PHY_INFT_RMII; - break; - - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - mode = STARFIVE_DWMAC_PHY_INFT_RGMII; - break; - - default: + phy_intf_sel = stmmac_get_phy_intf_sel(plat_dat->phy_interface); + if (phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) { dev_err(dwmac->dev, "unsupported interface %s\n", phy_modes(plat_dat->phy_interface)); - return -EINVAL; + return phy_intf_sel < 0 ? phy_intf_sel : -EINVAL; } regmap = syscon_regmap_lookup_by_phandle_args(dwmac->dev->of_node, @@ -65,7 +53,7 @@ static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat) /* args[0]:offset args[1]: shift */ err = regmap_update_bits(regmap, args[0], STARFIVE_DWMAC_PHY_INFT_FIELD << args[1], - mode << args[1]); + phy_intf_sel << args[1]); if (err) return dev_err_probe(dwmac->dev, err, "error setting phy mode\n"); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c index 53d5ce1f6dc69..b0509ab6b31ca 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c @@ -77,13 +77,9 @@ * 001-RGMII * 010-SGMII * 100-RMII + * These are the DW MAC phy_intf_sel values. */ #define MII_PHY_SEL_MASK GENMASK(4, 2) -#define ETH_PHY_SEL_RMII BIT(4) -#define ETH_PHY_SEL_SGMII BIT(3) -#define ETH_PHY_SEL_RGMII BIT(2) -#define ETH_PHY_SEL_GMII 0x0 -#define ETH_PHY_SEL_MII 0x0 struct sti_dwmac { phy_interface_t interface; /* MII interface */ @@ -102,15 +98,6 @@ struct sti_dwmac_of_data { void (*fix_retime_src)(void *priv, int speed, unsigned int mode); }; -static u32 phy_intf_sels[] = { - [PHY_INTERFACE_MODE_MII] = ETH_PHY_SEL_MII, - [PHY_INTERFACE_MODE_GMII] = ETH_PHY_SEL_GMII, - [PHY_INTERFACE_MODE_RGMII] = ETH_PHY_SEL_RGMII, - [PHY_INTERFACE_MODE_RGMII_ID] = ETH_PHY_SEL_RGMII, - [PHY_INTERFACE_MODE_SGMII] = ETH_PHY_SEL_SGMII, - [PHY_INTERFACE_MODE_RMII] = ETH_PHY_SEL_RMII, -}; - enum { TX_RETIME_SRC_NA = 0, TX_RETIME_SRC_TXCLK = 1, @@ -159,19 +146,28 @@ static void stih4xx_fix_retime_src(void *priv, int spd, unsigned int mode) stih4xx_tx_retime_val[src]); } -static int sti_dwmac_set_mode(struct sti_dwmac *dwmac) +static int sti_set_phy_intf_sel(void *bsp_priv, u8 phy_intf_sel) { - struct regmap *regmap = dwmac->regmap; - int iface = dwmac->interface; - u32 reg = dwmac->ctrl_reg; - u32 val; + struct sti_dwmac *dwmac = bsp_priv; + struct regmap *regmap; + u32 reg, val; + + regmap = dwmac->regmap; + reg = dwmac->ctrl_reg; if (dwmac->gmac_en) regmap_update_bits(regmap, reg, EN_MASK, EN); - regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, phy_intf_sels[iface]); + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_SGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) + phy_intf_sel = PHY_INTF_SEL_GMII_MII; + + regmap_update_bits(regmap, reg, MII_PHY_SEL_MASK, + FIELD_PREP(MII_PHY_SEL_MASK, phy_intf_sel)); - val = (iface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII; + val = (dwmac->interface == PHY_INTERFACE_MODE_REVMII) ? 0 : ENMII; regmap_update_bits(regmap, reg, ENMII_MASK, val); dwmac->fix_retime_src(dwmac, dwmac->speed, 0); @@ -236,17 +232,8 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac, static int sti_dwmac_init(struct platform_device *pdev, void *bsp_priv) { struct sti_dwmac *dwmac = bsp_priv; - int ret; - - ret = clk_prepare_enable(dwmac->clk); - if (ret) - return ret; - - ret = sti_dwmac_set_mode(dwmac); - if (ret) - clk_disable_unprepare(dwmac->clk); - return ret; + return clk_prepare_enable(dwmac->clk); } static void sti_dwmac_exit(struct platform_device *pdev, void *bsp_priv) @@ -291,6 +278,7 @@ static int sti_dwmac_probe(struct platform_device *pdev) dwmac->fix_retime_src = data->fix_retime_src; plat_dat->bsp_priv = dwmac; + plat_dat->set_phy_intf_sel = sti_set_phy_intf_sel; plat_dat->fix_mac_speed = data->fix_retime_src; plat_dat->init = sti_dwmac_init; plat_dat->exit = sti_dwmac_exit; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c index 6c179911ef3f1..e1b260ed4790b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c @@ -47,23 +47,18 @@ *------------------------------------------ */ #define SYSCFG_PMCR_ETH_SEL_MII BIT(20) -#define SYSCFG_PMCR_ETH_SEL_RGMII BIT(21) -#define SYSCFG_PMCR_ETH_SEL_RMII BIT(23) -#define SYSCFG_PMCR_ETH_SEL_GMII 0 +#define SYSCFG_PMCR_PHY_INTF_SEL_MASK GENMASK(23, 21) #define SYSCFG_MCU_ETH_SEL_MII 0 #define SYSCFG_MCU_ETH_SEL_RMII 1 /* STM32MP2 register definitions */ #define SYSCFG_MP2_ETH_MASK GENMASK(31, 0) +#define SYSCFG_ETHCR_ETH_SEL_MASK GENMASK(6, 4) #define SYSCFG_ETHCR_ETH_PTP_CLK_SEL BIT(2) #define SYSCFG_ETHCR_ETH_CLK_SEL BIT(1) #define SYSCFG_ETHCR_ETH_REF_CLK_SEL BIT(0) -#define SYSCFG_ETHCR_ETH_SEL_MII 0 -#define SYSCFG_ETHCR_ETH_SEL_RGMII BIT(4) -#define SYSCFG_ETHCR_ETH_SEL_RMII BIT(6) - /* STM32MPx register definitions * * Below table summarizes the clock requirement and clock sources for @@ -232,11 +227,14 @@ static int stm32mp1_validate_ethck_rate(struct plat_stmmacenet_data *plat_dat) return -EINVAL; } -static int stm32mp1_configure_pmcr(struct plat_stmmacenet_data *plat_dat) +static int stm32mp1_configure_pmcr(struct plat_stmmacenet_data *plat_dat, + u8 phy_intf_sel) { struct stm32_dwmac *dwmac = plat_dat->bsp_priv; u32 reg = dwmac->mode_reg; - int val = 0; + int val; + + val = FIELD_PREP(SYSCFG_PMCR_PHY_INTF_SEL_MASK, phy_intf_sel); switch (plat_dat->phy_interface) { case PHY_INTERFACE_MODE_MII: @@ -250,12 +248,10 @@ static int stm32mp1_configure_pmcr(struct plat_stmmacenet_data *plat_dat) val |= SYSCFG_PMCR_ETH_SEL_MII; break; case PHY_INTERFACE_MODE_GMII: - val = SYSCFG_PMCR_ETH_SEL_GMII; if (dwmac->enable_eth_ck) val |= SYSCFG_PMCR_ETH_CLK_SEL; break; case PHY_INTERFACE_MODE_RMII: - val = SYSCFG_PMCR_ETH_SEL_RMII; if (dwmac->enable_eth_ck) val |= SYSCFG_PMCR_ETH_REF_CLK_SEL; break; @@ -263,7 +259,6 @@ static int stm32mp1_configure_pmcr(struct plat_stmmacenet_data *plat_dat) case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: - val = SYSCFG_PMCR_ETH_SEL_RGMII; if (dwmac->enable_eth_ck) val |= SYSCFG_PMCR_ETH_CLK_SEL; break; @@ -288,18 +283,20 @@ static int stm32mp1_configure_pmcr(struct plat_stmmacenet_data *plat_dat) dwmac->mode_mask, val); } -static int stm32mp2_configure_syscfg(struct plat_stmmacenet_data *plat_dat) +static int stm32mp2_configure_syscfg(struct plat_stmmacenet_data *plat_dat, + u8 phy_intf_sel) { struct stm32_dwmac *dwmac = plat_dat->bsp_priv; u32 reg = dwmac->mode_reg; - int val = 0; + int val; + + val = FIELD_PREP(SYSCFG_ETHCR_ETH_SEL_MASK, phy_intf_sel); switch (plat_dat->phy_interface) { case PHY_INTERFACE_MODE_MII: /* ETH_REF_CLK_SEL bit in SYSCFG register is not applicable in MII mode */ break; case PHY_INTERFACE_MODE_RMII: - val = SYSCFG_ETHCR_ETH_SEL_RMII; if (dwmac->enable_eth_ck) { /* Internal clock ETH_CLK of 50MHz from RCC is used */ val |= SYSCFG_ETHCR_ETH_REF_CLK_SEL; @@ -309,8 +306,6 @@ static int stm32mp2_configure_syscfg(struct plat_stmmacenet_data *plat_dat) case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_RXID: case PHY_INTERFACE_MODE_RGMII_TXID: - val = SYSCFG_ETHCR_ETH_SEL_RGMII; - fallthrough; case PHY_INTERFACE_MODE_GMII: if (dwmac->enable_eth_ck) { /* Internal clock ETH_CLK of 125MHz from RCC is used */ @@ -337,7 +332,7 @@ static int stm32mp2_configure_syscfg(struct plat_stmmacenet_data *plat_dat) static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) { struct stm32_dwmac *dwmac = plat_dat->bsp_priv; - int ret; + int phy_intf_sel, ret; ret = stm32mp1_select_ethck_external(plat_dat); if (ret) @@ -347,10 +342,19 @@ static int stm32mp1_set_mode(struct plat_stmmacenet_data *plat_dat) if (ret) return ret; + phy_intf_sel = stmmac_get_phy_intf_sel(plat_dat->phy_interface); + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) { + dev_err(dwmac->dev, "Mode %s not supported\n", + phy_modes(plat_dat->phy_interface)); + return phy_intf_sel < 0 ? phy_intf_sel : -EINVAL; + } + if (!dwmac->ops->is_mp2) - return stm32mp1_configure_pmcr(plat_dat); + return stm32mp1_configure_pmcr(plat_dat, phy_intf_sel); else - return stm32mp2_configure_syscfg(plat_dat); + return stm32mp2_configure_syscfg(plat_dat, phy_intf_sel); } static int stm32mcu_set_mode(struct plat_stmmacenet_data *plat_dat) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c index 5d871b2cd111c..7434d4bbb5260 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c @@ -1040,15 +1040,10 @@ static const struct stmmac_ops sun8i_dwmac_ops = { .set_mac_loopback = sun8i_dwmac_set_mac_loopback, }; -static struct mac_device_info *sun8i_dwmac_setup(void *ppriv) +static int sun8i_dwmac_setup(void *ppriv, struct mac_device_info *mac) { - struct mac_device_info *mac; struct stmmac_priv *priv = ppriv; - mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); - if (!mac) - return NULL; - mac->pcsr = priv->ioaddr; mac->mac = &sun8i_dwmac_ops; mac->dma = &sun8i_dwmac_dma_ops; @@ -1079,7 +1074,7 @@ static struct mac_device_info *sun8i_dwmac_setup(void *ppriv) /* Synopsys Id is not available */ priv->synopsys_id = 0; - return mac; + return 0; } static struct regmap *sun8i_dwmac_get_syscon_from_dev(struct device_node *node) @@ -1192,7 +1187,7 @@ static int sun8i_dwmac_probe(struct platform_device *pdev) plat_dat->bsp_priv = gmac; plat_dat->init = sun8i_dwmac_init; plat_dat->exit = sun8i_dwmac_exit; - plat_dat->setup = sun8i_dwmac_setup; + plat_dat->mac_setup = sun8i_dwmac_setup; plat_dat->tx_fifo_size = 4096; plat_dat->rx_fifo_size = 16384; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c index 1eadcf5d1ad63..7f560d78209d1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c @@ -136,7 +136,7 @@ static int sun7i_gmac_probe(struct platform_device *pdev) /* platform data specifying hardware features and callbacks. * hardware features were copied from Allwinner drivers. */ plat_dat->tx_coe = 1; - plat_dat->has_gmac = true; + plat_dat->core_type = DWMAC_CORE_GMAC; plat_dat->bsp_priv = gmac; plat_dat->init = sun7i_gmac_init; plat_dat->exit = sun7i_gmac_exit; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c index dc903b846b1bf..d765acbe37548 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-tegra.c @@ -308,7 +308,7 @@ static int tegra_mgbe_probe(struct platform_device *pdev) goto disable_clks; } - plat->has_xgmac = 1; + plat->core_type = DWMAC_CORE_XGMAC; plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; plat->bsp_priv = mgbe; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c index bd65d42390543..9497b13a57539 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c @@ -42,10 +42,6 @@ #define ETHER_CLK_SEL_RX_TX_CLK_EN (ETHER_CLK_SEL_RX_CLK_EN | ETHER_CLK_SEL_TX_CLK_EN) -#define ETHER_CONFIG_INTF_MII 0 -#define ETHER_CONFIG_INTF_RGMII BIT(0) -#define ETHER_CONFIG_INTF_RMII BIT(2) - struct visconti_eth { void __iomem *reg; struct clk *phy_ref_clk; @@ -150,22 +146,12 @@ static int visconti_eth_init_hw(struct platform_device *pdev, struct plat_stmmac { struct visconti_eth *dwmac = plat_dat->bsp_priv; unsigned int clk_sel_val; - u32 phy_intf_sel; - - switch (plat_dat->phy_interface) { - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_TXID: - phy_intf_sel = ETHER_CONFIG_INTF_RGMII; - break; - case PHY_INTERFACE_MODE_MII: - phy_intf_sel = ETHER_CONFIG_INTF_MII; - break; - case PHY_INTERFACE_MODE_RMII: - phy_intf_sel = ETHER_CONFIG_INTF_RMII; - break; - default: + int phy_intf_sel; + + phy_intf_sel = stmmac_get_phy_intf_sel(plat_dat->phy_interface); + if (phy_intf_sel != PHY_INTF_SEL_GMII_MII && + phy_intf_sel != PHY_INTF_SEL_RGMII && + phy_intf_sel != PHY_INTF_SEL_RMII) { dev_err(&pdev->dev, "Unsupported phy-mode (%d)\n", plat_dat->phy_interface); return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index 0c011a47d5a3e..697bba641e050 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -38,11 +38,10 @@ #define GMAC_INT_DISABLE_PCSAN BIT(2) #define GMAC_INT_DISABLE_PMT BIT(3) #define GMAC_INT_DISABLE_TIMESTAMP BIT(9) -#define GMAC_INT_DISABLE_PCS (GMAC_INT_DISABLE_RGMII | \ +#define GMAC_INT_DEFAULT_MASK (GMAC_INT_DISABLE_RGMII | \ GMAC_INT_DISABLE_PCSLINK | \ - GMAC_INT_DISABLE_PCSAN) -#define GMAC_INT_DEFAULT_MASK (GMAC_INT_DISABLE_TIMESTAMP | \ - GMAC_INT_DISABLE_PCS) + GMAC_INT_DISABLE_PCSAN | \ + GMAC_INT_DISABLE_TIMESTAMP) /* PMT Control and Status */ #define GMAC_PMT 0x0000002c diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index fe776ddf68895..a2ae136d2c0e9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -22,47 +22,35 @@ #include "stmmac_ptp.h" #include "dwmac1000.h" +static int dwmac1000_pcs_init(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.pcs) + return 0; + + return stmmac_integrated_pcs_init(priv, GMAC_PCS_BASE, + GMAC_INT_DISABLE_PCSLINK | + GMAC_INT_DISABLE_PCSAN); +} + static void dwmac1000_core_init(struct mac_device_info *hw, struct net_device *dev) { void __iomem *ioaddr = hw->pcsr; - u32 value = readl(ioaddr + GMAC_CONTROL); int mtu = dev->mtu; + u32 value; /* Configure GMAC core */ - value |= GMAC_CORE_INIT; + value = readl(ioaddr + GMAC_CONTROL); if (mtu > 1500) value |= GMAC_CONTROL_2K; if (mtu > 2000) value |= GMAC_CONTROL_JE; - if (hw->ps) { - value |= GMAC_CONTROL_TE; - - value &= ~hw->link.speed_mask; - switch (hw->ps) { - case SPEED_1000: - value |= hw->link.speed1000; - break; - case SPEED_100: - value |= hw->link.speed100; - break; - case SPEED_10: - value |= hw->link.speed10; - break; - } - } - - writel(value, ioaddr + GMAC_CONTROL); + writel(value | GMAC_CORE_INIT, ioaddr + GMAC_CONTROL); /* Mask GMAC interrupts */ - value = GMAC_INT_DEFAULT_MASK; - - if (hw->pcs) - value &= ~GMAC_INT_DISABLE_PCS; - - writel(value, ioaddr + GMAC_INT_MASK); + writel(GMAC_INT_DEFAULT_MASK, ioaddr + GMAC_INT_MASK); #ifdef STMMAC_VLAN_TAG_USED /* Tag detection without filtering */ @@ -70,6 +58,20 @@ static void dwmac1000_core_init(struct mac_device_info *hw, #endif } +static void dwmac1000_irq_modify(struct mac_device_info *hw, u32 disable, + u32 enable) +{ + void __iomem *int_mask = hw->pcsr + GMAC_INT_MASK; + unsigned long flags; + u32 value; + + spin_lock_irqsave(&hw->irq_ctrl_lock, flags); + value = readl(int_mask) | disable; + value &= ~enable; + writel(value, int_mask); + spin_unlock_irqrestore(&hw->irq_ctrl_lock, flags); +} + static int dwmac1000_rx_ipc_enable(struct mac_device_info *hw) { void __iomem *ioaddr = hw->pcsr; @@ -263,39 +265,6 @@ static void dwmac1000_pmt(struct mac_device_info *hw, unsigned long mode) writel(pmt, ioaddr + GMAC_PMT); } -/* RGMII or SMII interface */ -static void dwmac1000_rgsmii(void __iomem *ioaddr, struct stmmac_extra_stats *x) -{ - u32 status; - - status = readl(ioaddr + GMAC_RGSMIIIS); - x->irq_rgmii_n++; - - /* Check the link status */ - if (status & GMAC_RGSMIIIS_LNKSTS) { - int speed_value; - - x->pcs_link = 1; - - speed_value = ((status & GMAC_RGSMIIIS_SPEED) >> - GMAC_RGSMIIIS_SPEED_SHIFT); - if (speed_value == GMAC_RGSMIIIS_SPEED_125) - x->pcs_speed = SPEED_1000; - else if (speed_value == GMAC_RGSMIIIS_SPEED_25) - x->pcs_speed = SPEED_100; - else - x->pcs_speed = SPEED_10; - - x->pcs_duplex = (status & GMAC_RGSMIIIS_LNKMOD_MASK); - - pr_info("Link is Up - %d/%s\n", (int)x->pcs_speed, - x->pcs_duplex ? "Full" : "Half"); - } else { - x->pcs_link = 0; - pr_info("Link is Down\n"); - } -} - static int dwmac1000_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { @@ -337,9 +306,6 @@ static int dwmac1000_irq_status(struct mac_device_info *hw, dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x); - if (intr_status & PCS_RGSMIIIS_IRQ) - dwmac1000_rgsmii(ioaddr, x); - return ret; } @@ -394,9 +360,9 @@ static void dwmac1000_set_eee_timer(struct mac_device_info *hw, int ls, int tw) } static void dwmac1000_ctrl_ane(struct stmmac_priv *priv, bool ane, - bool srgmi_ral, bool loopback) + bool srgmi_ral) { - dwmac_ctrl_ane(priv->ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback); + dwmac_ctrl_ane(priv->ioaddr, GMAC_PCS_BASE, ane, srgmi_ral); } static void dwmac1000_debug(struct stmmac_priv *priv, void __iomem *ioaddr, @@ -488,7 +454,9 @@ static void dwmac1000_set_mac_loopback(void __iomem *ioaddr, bool enable) } const struct stmmac_ops dwmac1000_ops = { + .pcs_init = dwmac1000_pcs_init, .core_init = dwmac1000_core_init, + .irq_modify = dwmac1000_irq_modify, .set_mac = stmmac_set_mac, .rx_ipc = dwmac1000_rx_ipc_enable, .dump_regs = dwmac1000_dump_regs, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 3dec1a264cf60..3cb733781e1e8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -106,9 +106,6 @@ #define GMAC_INT_LPI_EN BIT(5) #define GMAC_INT_TSIE BIT(12) -#define GMAC_PCS_IRQ_DEFAULT (GMAC_INT_RGSMIIS | GMAC_INT_PCS_LINK | \ - GMAC_INT_PCS_ANE) - #define GMAC_INT_DEFAULT_ENABLE (GMAC_INT_PMT_EN | GMAC_INT_LPI_EN | \ GMAC_INT_TSIE) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index d85bc0bb5c3c0..a4282fd7c3c73 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -22,51 +22,51 @@ #include "dwmac4.h" #include "dwmac5.h" +static int dwmac4_pcs_init(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.pcs) + return 0; + + return stmmac_integrated_pcs_init(priv, GMAC_PCS_BASE, + GMAC_INT_PCS_LINK | GMAC_INT_PCS_ANE); +} + static void dwmac4_core_init(struct mac_device_info *hw, struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); void __iomem *ioaddr = hw->pcsr; - u32 value = readl(ioaddr + GMAC_CONFIG); unsigned long clk_rate; + u32 value; - value |= GMAC_CORE_INIT; - - if (hw->ps) { - value |= GMAC_CONFIG_TE; - - value &= hw->link.speed_mask; - switch (hw->ps) { - case SPEED_1000: - value |= hw->link.speed1000; - break; - case SPEED_100: - value |= hw->link.speed100; - break; - case SPEED_10: - value |= hw->link.speed10; - break; - } - } - - writel(value, ioaddr + GMAC_CONFIG); + value = readl(ioaddr + GMAC_CONFIG); + writel(value | GMAC_CORE_INIT, ioaddr + GMAC_CONFIG); /* Configure LPI 1us counter to number of CSR clock ticks in 1us - 1 */ clk_rate = clk_get_rate(priv->plat->stmmac_clk); writel((clk_rate / 1000000) - 1, ioaddr + GMAC4_MAC_ONEUS_TIC_COUNTER); /* Enable GMAC interrupts */ - value = GMAC_INT_DEFAULT_ENABLE; - - if (hw->pcs) - value |= GMAC_PCS_IRQ_DEFAULT; - - writel(value, ioaddr + GMAC_INT_EN); + writel(GMAC_INT_DEFAULT_ENABLE, ioaddr + GMAC_INT_EN); if (GMAC_INT_DEFAULT_ENABLE & GMAC_INT_TSIE) init_waitqueue_head(&priv->tstamp_busy_wait); } +static void dwmac4_irq_modify(struct mac_device_info *hw, u32 disable, + u32 enable) +{ + void __iomem *int_mask = hw->pcsr + GMAC_INT_EN; + unsigned long flags; + u32 value; + + spin_lock_irqsave(&hw->irq_ctrl_lock, flags); + value = readl(int_mask) & ~disable; + value |= enable; + writel(value, int_mask); + spin_unlock_irqrestore(&hw->irq_ctrl_lock, flags); +} + static void dwmac4_update_caps(struct stmmac_priv *priv) { if (priv->plat->tx_queues_to_use > 1) @@ -583,43 +583,9 @@ static void dwmac4_flow_ctrl(struct mac_device_info *hw, unsigned int duplex, } } -static void dwmac4_ctrl_ane(struct stmmac_priv *priv, bool ane, bool srgmi_ral, - bool loopback) -{ - dwmac_ctrl_ane(priv->ioaddr, GMAC_PCS_BASE, ane, srgmi_ral, loopback); -} - -/* RGMII or SMII interface */ -static void dwmac4_phystatus(void __iomem *ioaddr, struct stmmac_extra_stats *x) +static void dwmac4_ctrl_ane(struct stmmac_priv *priv, bool ane, bool srgmi_ral) { - u32 status; - - status = readl(ioaddr + GMAC_PHYIF_CONTROL_STATUS); - x->irq_rgmii_n++; - - /* Check the link status */ - if (status & GMAC_PHYIF_CTRLSTATUS_LNKSTS) { - int speed_value; - - x->pcs_link = 1; - - speed_value = ((status & GMAC_PHYIF_CTRLSTATUS_SPEED) >> - GMAC_PHYIF_CTRLSTATUS_SPEED_SHIFT); - if (speed_value == GMAC_PHYIF_CTRLSTATUS_SPEED_125) - x->pcs_speed = SPEED_1000; - else if (speed_value == GMAC_PHYIF_CTRLSTATUS_SPEED_25) - x->pcs_speed = SPEED_100; - else - x->pcs_speed = SPEED_10; - - x->pcs_duplex = (status & GMAC_PHYIF_CTRLSTATUS_LNKMOD); - - pr_info("Link is Up - %d/%s\n", (int)x->pcs_speed, - x->pcs_duplex ? "Full" : "Half"); - } else { - x->pcs_link = 0; - pr_info("Link is Down\n"); - } + dwmac_ctrl_ane(priv->ioaddr, GMAC_PCS_BASE, ane, srgmi_ral); } static int dwmac4_irq_mtl_status(struct stmmac_priv *priv, @@ -693,8 +659,6 @@ static int dwmac4_irq_status(struct mac_device_info *hw, } dwmac_pcs_isr(ioaddr, GMAC_PCS_BASE, intr_status, x); - if (intr_status & PCS_RGSMIIIS_IRQ) - dwmac4_phystatus(ioaddr, x); return ret; } @@ -929,7 +893,9 @@ static int dwmac4_config_l4_filter(struct mac_device_info *hw, u32 filter_no, } const struct stmmac_ops dwmac4_ops = { + .pcs_init = dwmac4_pcs_init, .core_init = dwmac4_core_init, + .irq_modify = dwmac4_irq_modify, .update_caps = dwmac4_update_caps, .set_mac = stmmac_set_mac, .rx_ipc = dwmac4_rx_ipc_enable, @@ -963,7 +929,9 @@ const struct stmmac_ops dwmac4_ops = { }; const struct stmmac_ops dwmac410_ops = { + .pcs_init = dwmac4_pcs_init, .core_init = dwmac4_core_init, + .irq_modify = dwmac4_irq_modify, .update_caps = dwmac4_update_caps, .set_mac = stmmac_dwmac4_set_mac, .rx_ipc = dwmac4_rx_ipc_enable, @@ -999,7 +967,9 @@ const struct stmmac_ops dwmac410_ops = { }; const struct stmmac_ops dwmac510_ops = { + .pcs_init = dwmac4_pcs_init, .core_init = dwmac4_core_init, + .irq_modify = dwmac4_irq_modify, .update_caps = dwmac4_update_caps, .set_mac = stmmac_dwmac4_set_mac, .rx_ipc = dwmac4_rx_ipc_enable, diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 0d408ee17f337..e48cfa05000c0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -79,6 +79,7 @@ #define XGMAC_PSRQ(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_PSRQ_SHIFT(x) ((x) * 8) #define XGMAC_INT_STATUS 0x000000b0 +#define XGMAC_INT_TSIS BIT(12) #define XGMAC_LPIIS BIT(5) #define XGMAC_PMTIS BIT(4) #define XGMAC_INT_EN 0x000000b4 @@ -173,6 +174,8 @@ #define XGMAC_MDIO_ADDR 0x00000200 #define XGMAC_MDIO_DATA 0x00000204 #define XGMAC_MDIO_C22P 0x00000220 +#define XGMAC_GPIO_STATUS 0x0000027c +#define XGMAC_GPIO_GPO0 BIT(16) #define XGMAC_ADDRx_HIGH(x) (0x00000300 + (x) * 0x8) #define XGMAC_ADDR_MAX 32 #define XGMAC_AE BIT(31) @@ -220,6 +223,8 @@ #define XGMAC_OB BIT(0) #define XGMAC_RSS_DATA 0x00000c8c #define XGMAC_TIMESTAMP_STATUS 0x00000d20 +#define XGMAC_TIMESTAMP_ATSNS_MASK GENMASK(29, 25) +#define XGMAC_TIMESTAMP_ATSNS_SHIFT 25 #define XGMAC_TXTSC BIT(15) #define XGMAC_TXTIMESTAMP_NSEC 0x00000d30 #define XGMAC_TXTSSTSLO GENMASK(30, 0) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 00e929bf280ba..b40b3ea50e253 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -23,30 +23,23 @@ static void dwxgmac2_core_init(struct mac_device_info *hw, tx = readl(ioaddr + XGMAC_TX_CONFIG); rx = readl(ioaddr + XGMAC_RX_CONFIG); - tx |= XGMAC_CORE_INIT_TX; - rx |= XGMAC_CORE_INIT_RX; - - if (hw->ps) { - tx |= XGMAC_CONFIG_TE; - tx &= ~hw->link.speed_mask; + writel(tx | XGMAC_CORE_INIT_TX, ioaddr + XGMAC_TX_CONFIG); + writel(rx | XGMAC_CORE_INIT_RX, ioaddr + XGMAC_RX_CONFIG); + writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN); +} - switch (hw->ps) { - case SPEED_10000: - tx |= hw->link.xgmii.speed10000; - break; - case SPEED_2500: - tx |= hw->link.speed2500; - break; - case SPEED_1000: - default: - tx |= hw->link.speed1000; - break; - } - } +static void dwxgmac2_irq_modify(struct mac_device_info *hw, u32 disable, + u32 enable) +{ + void __iomem *int_mask = hw->pcsr + XGMAC_INT_EN; + unsigned long flags; + u32 value; - writel(tx, ioaddr + XGMAC_TX_CONFIG); - writel(rx, ioaddr + XGMAC_RX_CONFIG); - writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN); + spin_lock_irqsave(&hw->irq_ctrl_lock, flags); + value = readl(int_mask) & ~disable; + value |= enable; + writel(value, int_mask); + spin_unlock_irqrestore(&hw->irq_ctrl_lock, flags); } static void dwxgmac2_update_caps(struct stmmac_priv *priv) @@ -1432,6 +1425,7 @@ static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en, const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, + .irq_modify = dwxgmac2_irq_modify, .update_caps = dwxgmac2_update_caps, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, @@ -1487,6 +1481,7 @@ static void dwxlgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode, const struct stmmac_ops dwxlgmac2_ops = { .core_init = dwxgmac2_core_init, + .irq_modify = dwxgmac2_irq_modify, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxlgmac2_rx_queue_enable, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 3f7c765dcb797..014f7cd79a3cc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -13,31 +13,42 @@ #include "dwmac4_descs.h" #include "dwxgmac2.h" -static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg) +struct stmmac_version { + u8 snpsver; + u8 dev_id; +}; + +static void stmmac_get_version(struct stmmac_priv *priv, + struct stmmac_version *ver) { - u32 reg = readl(priv->ioaddr + id_reg); + enum dwmac_core_type core_type = priv->plat->core_type; + unsigned int version_offset; + u32 version; - if (!reg) { - dev_info(priv->device, "Version ID not available\n"); - return 0x0; - } + ver->snpsver = 0; + ver->dev_id = 0; - dev_info(priv->device, "User ID: 0x%x, Synopsys ID: 0x%x\n", - (unsigned int)(reg & GENMASK(15, 8)) >> 8, - (unsigned int)(reg & GENMASK(7, 0))); - return reg & GENMASK(7, 0); -} + if (core_type == DWMAC_CORE_MAC100) + return; -static u32 stmmac_get_dev_id(struct stmmac_priv *priv, u32 id_reg) -{ - u32 reg = readl(priv->ioaddr + id_reg); + if (core_type == DWMAC_CORE_GMAC) + version_offset = GMAC_VERSION; + else + version_offset = GMAC4_VERSION; - if (!reg) { + version = readl(priv->ioaddr + version_offset); + if (version == 0) { dev_info(priv->device, "Version ID not available\n"); - return 0x0; + return; } - return (reg & GENMASK(15, 8)) >> 8; + dev_info(priv->device, "User ID: 0x%x, Synopsys ID: 0x%x\n", + FIELD_GET(DWMAC_USERVER, version), + FIELD_GET(DWMAC_SNPSVER, version)); + + ver->snpsver = FIELD_GET(DWMAC_SNPSVER, version); + if (core_type == DWMAC_CORE_XGMAC) + ver->dev_id = FIELD_GET(DWMAC_USERVER, version); } static void stmmac_dwmac_mode_quirk(struct stmmac_priv *priv) @@ -92,12 +103,10 @@ static int stmmac_dwxlgmac_quirks(struct stmmac_priv *priv) return 0; } -int stmmac_reset(struct stmmac_priv *priv, void __iomem *ioaddr) +int stmmac_reset(struct stmmac_priv *priv) { - struct plat_stmmacenet_data *plat = priv ? priv->plat : NULL; - - if (!priv) - return -EINVAL; + struct plat_stmmacenet_data *plat = priv->plat; + void __iomem *ioaddr = priv->ioaddr; if (plat && plat->fix_soc_reset) return plat->fix_soc_reset(priv, ioaddr); @@ -106,9 +115,7 @@ int stmmac_reset(struct stmmac_priv *priv, void __iomem *ioaddr) } static const struct stmmac_hwif_entry { - bool gmac; - bool gmac4; - bool xgmac; + enum dwmac_core_type core_type; u32 min_id; u32 dev_id; const struct stmmac_regs_off regs; @@ -127,9 +134,7 @@ static const struct stmmac_hwif_entry { } stmmac_hw[] = { /* NOTE: New HW versions shall go to the end of this table */ { - .gmac = false, - .gmac4 = false, - .xgmac = false, + .core_type = DWMAC_CORE_MAC100, .min_id = 0, .regs = { .ptp_off = PTP_GMAC3_X_OFFSET, @@ -146,9 +151,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac100_setup, .quirks = stmmac_dwmac1_quirks, }, { - .gmac = true, - .gmac4 = false, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC, .min_id = 0, .regs = { .ptp_off = PTP_GMAC3_X_OFFSET, @@ -165,9 +168,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac1000_setup, .quirks = stmmac_dwmac1_quirks, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = 0, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -187,9 +188,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = stmmac_dwmac4_quirks, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = DWMAC_CORE_4_00, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -210,9 +209,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = DWMAC_CORE_4_10, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -233,9 +230,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = true, - .xgmac = false, + .core_type = DWMAC_CORE_GMAC4, .min_id = DWMAC_CORE_5_10, .regs = { .ptp_off = PTP_GMAC4_OFFSET, @@ -256,9 +251,7 @@ static const struct stmmac_hwif_entry { .setup = dwmac4_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = false, - .xgmac = true, + .core_type = DWMAC_CORE_XGMAC, .min_id = DWXGMAC_CORE_2_10, .dev_id = DWXGMAC_ID, .regs = { @@ -280,9 +273,7 @@ static const struct stmmac_hwif_entry { .setup = dwxgmac2_setup, .quirks = NULL, }, { - .gmac = false, - .gmac4 = false, - .xgmac = true, + .core_type = DWMAC_CORE_XGMAC, .min_id = DWXLGMAC_CORE_2_00, .dev_id = DWXLGMAC_ID, .regs = { @@ -306,100 +297,114 @@ static const struct stmmac_hwif_entry { }, }; +static const struct stmmac_hwif_entry * +stmmac_hwif_find(enum dwmac_core_type core_type, u8 snpsver, u8 dev_id) +{ + const struct stmmac_hwif_entry *entry; + int i; + + for (i = ARRAY_SIZE(stmmac_hw) - 1; i >= 0; i--) { + entry = &stmmac_hw[i]; + + if (core_type != entry->core_type) + continue; + /* Use synopsys_id var because some setups can override this */ + if (snpsver < entry->min_id) + continue; + if (core_type == DWMAC_CORE_XGMAC && + dev_id != entry->dev_id) + continue; + + return entry; + } + + return NULL; +} + int stmmac_hwif_init(struct stmmac_priv *priv) { - bool needs_xgmac = priv->plat->has_xgmac; - bool needs_gmac4 = priv->plat->has_gmac4; - bool needs_gmac = priv->plat->has_gmac; + enum dwmac_core_type core_type = priv->plat->core_type; const struct stmmac_hwif_entry *entry; + struct stmmac_version version; struct mac_device_info *mac; bool needs_setup = true; - u32 id, dev_id = 0; - int i, ret; - - if (needs_gmac) { - id = stmmac_get_id(priv, GMAC_VERSION); - } else if (needs_gmac4 || needs_xgmac) { - id = stmmac_get_id(priv, GMAC4_VERSION); - if (needs_xgmac) - dev_id = stmmac_get_dev_id(priv, GMAC4_VERSION); - } else { - id = 0; - } + int ret; + + stmmac_get_version(priv, &version); /* Save ID for later use */ - priv->synopsys_id = id; + priv->synopsys_id = version.snpsver; /* Lets assume some safe values first */ - priv->ptpaddr = priv->ioaddr + - (needs_gmac4 ? PTP_GMAC4_OFFSET : PTP_GMAC3_X_OFFSET); - priv->mmcaddr = priv->ioaddr + - (needs_gmac4 ? MMC_GMAC4_OFFSET : MMC_GMAC3_X_OFFSET); - if (needs_gmac4) + if (core_type == DWMAC_CORE_GMAC4) { + priv->ptpaddr = priv->ioaddr + PTP_GMAC4_OFFSET; + priv->mmcaddr = priv->ioaddr + MMC_GMAC4_OFFSET; priv->estaddr = priv->ioaddr + EST_GMAC4_OFFSET; - else if (needs_xgmac) - priv->estaddr = priv->ioaddr + EST_XGMAC_OFFSET; - - /* Check for HW specific setup first */ - if (priv->plat->setup) { - mac = priv->plat->setup(priv); - needs_setup = false; } else { - mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); + priv->ptpaddr = priv->ioaddr + PTP_GMAC3_X_OFFSET; + priv->mmcaddr = priv->ioaddr + MMC_GMAC3_X_OFFSET; + if (core_type == DWMAC_CORE_XGMAC) + priv->estaddr = priv->ioaddr + EST_XGMAC_OFFSET; } + mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); if (!mac) return -ENOMEM; + /* Check for HW specific setup first */ + if (priv->plat->mac_setup) { + ret = priv->plat->mac_setup(priv, mac); + if (ret) + return ret; + + needs_setup = false; + } + + spin_lock_init(&mac->irq_ctrl_lock); + /* Fallback to generic HW */ - for (i = ARRAY_SIZE(stmmac_hw) - 1; i >= 0; i--) { - entry = &stmmac_hw[i]; - if (needs_gmac ^ entry->gmac) - continue; - if (needs_gmac4 ^ entry->gmac4) - continue; - if (needs_xgmac ^ entry->xgmac) - continue; - /* Use synopsys_id var because some setups can override this */ - if (priv->synopsys_id < entry->min_id) - continue; - if (needs_xgmac && (dev_id ^ entry->dev_id)) - continue; + /* Use synopsys_id var because some setups can override this */ + entry = stmmac_hwif_find(core_type, priv->synopsys_id, version.dev_id); + if (!entry) { + dev_err(priv->device, + "Failed to find HW IF (id=0x%x, gmac=%d/%d)\n", + version.snpsver, core_type == DWMAC_CORE_GMAC, + core_type == DWMAC_CORE_GMAC4); - /* Only use generic HW helpers if needed */ - mac->desc = mac->desc ? : entry->desc; - mac->dma = mac->dma ? : entry->dma; - mac->mac = mac->mac ? : entry->mac; - mac->ptp = mac->ptp ? : entry->hwtimestamp; - mac->mode = mac->mode ? : entry->mode; - mac->tc = mac->tc ? : entry->tc; - mac->mmc = mac->mmc ? : entry->mmc; - mac->est = mac->est ? : entry->est; - mac->vlan = mac->vlan ? : entry->vlan; - - priv->hw = mac; - priv->fpe_cfg.reg = entry->regs.fpe_reg; - priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off; - priv->mmcaddr = priv->ioaddr + entry->regs.mmc_off; - memcpy(&priv->ptp_clock_ops, entry->ptp, - sizeof(struct ptp_clock_info)); - if (entry->est) - priv->estaddr = priv->ioaddr + entry->regs.est_off; - - /* Entry found */ - if (needs_setup) { - ret = entry->setup(priv); - if (ret) - return ret; - } + return -EINVAL; + } - /* Save quirks, if needed for posterior use */ - priv->hwif_quirks = entry->quirks; - return 0; + /* Only use generic HW helpers if needed */ + mac->desc = mac->desc ? : entry->desc; + mac->dma = mac->dma ? : entry->dma; + mac->mac = mac->mac ? : entry->mac; + mac->ptp = mac->ptp ? : entry->hwtimestamp; + mac->mode = mac->mode ? : entry->mode; + mac->tc = mac->tc ? : entry->tc; + mac->mmc = mac->mmc ? : entry->mmc; + mac->est = mac->est ? : entry->est; + mac->vlan = mac->vlan ? : entry->vlan; + + priv->hw = mac; + priv->fpe_cfg.reg = entry->regs.fpe_reg; + priv->ptpaddr = priv->ioaddr + entry->regs.ptp_off; + priv->mmcaddr = priv->ioaddr + entry->regs.mmc_off; + memcpy(&priv->ptp_clock_ops, entry->ptp, + sizeof(struct ptp_clock_info)); + + if (entry->est) + priv->estaddr = priv->ioaddr + entry->regs.est_off; + + /* Entry found */ + if (needs_setup) { + ret = entry->setup(priv); + if (ret) + return ret; } - dev_err(priv->device, "Failed to find HW IF (id=0x%x, gmac=%d/%d)\n", - id, needs_gmac, needs_gmac4); - return -EINVAL; + /* Save quirks, if needed for posterior use */ + priv->hwif_quirks = entry->quirks; + + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 14dbe0685997d..d359722100fa3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -313,10 +313,14 @@ enum stmmac_lpi_mode { /* Helpers to program the MAC core */ struct stmmac_ops { + /* Initialise any PCS instances */ + int (*pcs_init)(struct stmmac_priv *priv); /* MAC core initialization */ void (*core_init)(struct mac_device_info *hw, struct net_device *dev); /* Update MAC capabilities */ void (*update_caps)(struct stmmac_priv *priv); + /* Change the interrupt enable setting. Enable takes precedence. */ + void (*irq_modify)(struct mac_device_info *hw, u32 disable, u32 enable); /* Enable the MAC RX/TX */ void (*set_mac)(void __iomem *ioaddr, bool enable); /* Enable and verify that the IPC module is supported */ @@ -374,8 +378,8 @@ struct stmmac_ops { struct stmmac_extra_stats *x, u32 rx_queues, u32 tx_queues); /* PCS calls */ - void (*pcs_ctrl_ane)(struct stmmac_priv *priv, bool ane, bool srgmi_ral, - bool loopback); + void (*pcs_ctrl_ane)(struct stmmac_priv *priv, bool ane, + bool srgmi_ral); /* Safety Features */ int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_feature_cfg *safety_cfg); @@ -413,10 +417,14 @@ struct stmmac_ops { u32 pclass); }; +#define stmmac_mac_pcs_init(__priv) \ + stmmac_do_callback(__priv, mac, pcs_init, __priv) #define stmmac_core_init(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, core_init, __args) #define stmmac_mac_update_caps(__priv) \ stmmac_do_void_callback(__priv, mac, update_caps, __priv) +#define stmmac_mac_irq_modify(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, irq_modify, (__priv)->hw, __args) #define stmmac_mac_set(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_mac, __args) #define stmmac_rx_ipc(__priv, __args...) \ @@ -690,7 +698,7 @@ extern const struct stmmac_tc_ops dwmac510_tc_ops; #define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ #define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */ -int stmmac_reset(struct stmmac_priv *priv, void __iomem *ioaddr); +int stmmac_reset(struct stmmac_priv *priv); int stmmac_hwif_init(struct stmmac_priv *priv); #endif /* __STMMAC_HWIF_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 7ca5477be390b..e9ed5086c049d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -25,6 +25,8 @@ #include #include +struct stmmac_pcs; + struct stmmac_resources { void __iomem *addr; u8 mac[ETH_ALEN]; @@ -257,6 +259,7 @@ struct stmmac_priv { u32 sarc_type; u32 rx_riwt[MTL_MAX_RX_QUEUES]; int hwts_rx_en; + bool tsfupdt_coarse; void __iomem *ioaddr; struct net_device *dev; @@ -273,6 +276,8 @@ struct stmmac_priv { unsigned int pause_time; struct mii_bus *mii; + struct stmmac_pcs *integrated_pcs; + struct phylink_config phylink_config; struct phylink *phylink; @@ -287,6 +292,7 @@ struct stmmac_priv { int hw_cap_support; int synopsys_id; u32 msg_enable; + /* Our MAC Wake-on-Lan options */ int wolopts; int wol_irq; u32 gmii_address_bus_config; @@ -364,6 +370,8 @@ struct stmmac_priv { /* XDP BPF Program */ unsigned long *af_xdp_zc_qps; struct bpf_prog *xdp_prog; + + struct devlink *devlink; }; enum stmmac_state { @@ -375,19 +383,11 @@ enum stmmac_state { extern const struct dev_pm_ops stmmac_simple_pm_ops; -static inline bool stmmac_wol_enabled_mac(struct stmmac_priv *priv) -{ - return priv->plat->pmt && device_may_wakeup(priv->device); -} - -static inline bool stmmac_wol_enabled_phy(struct stmmac_priv *priv) -{ - return !priv->plat->pmt && device_may_wakeup(priv->device); -} - int stmmac_mdio_unregister(struct net_device *ndev); int stmmac_mdio_register(struct net_device *ndev); int stmmac_mdio_reset(struct mii_bus *mii); +void stmmac_mdio_lock(struct stmmac_priv *priv); +void stmmac_mdio_unlock(struct stmmac_priv *priv); int stmmac_pcs_setup(struct net_device *ndev); void stmmac_pcs_clean(struct net_device *ndev); void stmmac_set_ethtool_ops(struct net_device *netdev); @@ -396,6 +396,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv); void stmmac_ptp_unregister(struct stmmac_priv *priv); int stmmac_xdp_open(struct net_device *dev); void stmmac_xdp_release(struct net_device *dev); +int stmmac_get_phy_intf_sel(phy_interface_t interface); int stmmac_resume(struct device *dev); int stmmac_suspend(struct device *dev); void stmmac_dvr_remove(struct device *dev); @@ -407,6 +408,8 @@ int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size); int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i, phy_interface_t interface, int speed); +struct plat_stmmacenet_data *stmmac_plat_dat_alloc(struct device *dev); + static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv) { return !!priv->xdp_prog; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c index 4b513d27a9889..afc516059b897 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_est.c @@ -53,7 +53,7 @@ static int est_configure(struct stmmac_priv *priv, struct stmmac_est *cfg, } ctrl = readl(est_addr + EST_CONTROL); - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { ctrl &= ~EST_XGMAC_PTOV; ctrl |= ((NSEC_PER_SEC / ptp_rate) * EST_XGMAC_PTOV_MUL) << EST_XGMAC_PTOV_SHIFT; @@ -148,7 +148,7 @@ static void est_irq_status(struct stmmac_priv *priv, struct net_device *dev, } if (status & EST_BTRE) { - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { btrl = FIELD_GET(EST_XGMAC_BTRL, status); btrl_max = FIELD_MAX(EST_XGMAC_BTRL); } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 39fa1ec92f82f..b155e71aac51f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -303,9 +303,10 @@ static void stmmac_ethtool_getdrvinfo(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->plat->has_gmac || priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC || + priv->plat->core_type == DWMAC_CORE_GMAC4) strscpy(info->driver, GMAC_ETHTOOL_NAME, sizeof(info->driver)); - else if (priv->plat->has_xgmac) + else if (priv->plat->core_type == DWMAC_CORE_XGMAC) strscpy(info->driver, XGMAC_ETHTOOL_NAME, sizeof(info->driver)); else strscpy(info->driver, MAC100_ETHTOOL_NAME, @@ -322,47 +323,6 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && - (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII)) { - u32 supported, advertising, lp_advertising; - - if (!priv->xstats.pcs_link) { - cmd->base.speed = SPEED_UNKNOWN; - cmd->base.duplex = DUPLEX_UNKNOWN; - return 0; - } - cmd->base.duplex = priv->xstats.pcs_duplex; - - cmd->base.speed = priv->xstats.pcs_speed; - - /* Encoding of PSE bits is defined in 802.3z, 37.2.1.4 */ - - ethtool_convert_link_mode_to_legacy_u32( - &supported, cmd->link_modes.supported); - ethtool_convert_link_mode_to_legacy_u32( - &advertising, cmd->link_modes.advertising); - ethtool_convert_link_mode_to_legacy_u32( - &lp_advertising, cmd->link_modes.lp_advertising); - - /* Reg49[3] always set because ANE is always supported */ - cmd->base.autoneg = ADVERTISED_Autoneg; - supported |= SUPPORTED_Autoneg; - advertising |= ADVERTISED_Autoneg; - lp_advertising |= ADVERTISED_Autoneg; - - cmd->base.port = PORT_OTHER; - - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.supported, supported); - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.advertising, advertising); - ethtool_convert_legacy_u32_to_link_mode( - cmd->link_modes.lp_advertising, lp_advertising); - - return 0; - } - return phylink_ethtool_ksettings_get(priv->phylink, cmd); } @@ -372,20 +332,6 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev, { struct stmmac_priv *priv = netdev_priv(dev); - if (!(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS) && - (priv->hw->pcs & STMMAC_PCS_RGMII || - priv->hw->pcs & STMMAC_PCS_SGMII)) { - /* Only support ANE */ - if (cmd->base.autoneg != AUTONEG_ENABLE) - return -EINVAL; - - mutex_lock(&priv->lock); - stmmac_pcs_ctrl_ane(priv, 1, priv->hw->ps, 0); - mutex_unlock(&priv->lock); - - return 0; - } - return phylink_ethtool_ksettings_set(priv->phylink, cmd); } @@ -406,9 +352,9 @@ static int stmmac_ethtool_get_regs_len(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) return XGMAC_REGSIZE * 4; - else if (priv->plat->has_gmac4) + else if (priv->plat->core_type == DWMAC_CORE_GMAC4) return GMAC4_REG_SPACE_SIZE; return REG_SPACE_SIZE; } @@ -423,12 +369,12 @@ static void stmmac_ethtool_gregs(struct net_device *dev, stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); /* Copy DMA registers to where ethtool expects them */ - if (priv->plat->has_gmac4) { + if (priv->plat->core_type == DWMAC_CORE_GMAC4) { /* GMAC4 dumps its DMA registers at its DMA_CHAN_BASE_ADDR */ memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[GMAC4_DMA_CHAN_BASE_ADDR / 4], NUM_DWMAC4_DMA_REGS * 4); - } else if (!priv->plat->has_xgmac) { + } else if (priv->plat->core_type != DWMAC_CORE_XGMAC) { memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], NUM_DWMAC1000_DMA_REGS * 4); @@ -479,11 +425,7 @@ stmmac_get_pauseparam(struct net_device *netdev, { struct stmmac_priv *priv = netdev_priv(netdev); - if (priv->hw->pcs) { - pause->autoneg = 1; - } else { - phylink_ethtool_get_pauseparam(priv->phylink, pause); - } + phylink_ethtool_get_pauseparam(priv->phylink, pause); } static int @@ -492,12 +434,7 @@ stmmac_set_pauseparam(struct net_device *netdev, { struct stmmac_priv *priv = netdev_priv(netdev); - if (priv->hw->pcs) { - pause->autoneg = 1; - return 0; - } else { - return phylink_ethtool_set_pauseparam(priv->phylink, pause); - } + return phylink_ethtool_set_pauseparam(priv->phylink, pause); } static u64 stmmac_get_rx_normal_irq_n(struct stmmac_priv *priv, int q) @@ -787,41 +724,14 @@ static void stmmac_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct stmmac_priv *priv = netdev_priv(dev); - if (!priv->plat->pmt) - return phylink_ethtool_get_wol(priv->phylink, wol); - - mutex_lock(&priv->lock); - if (device_can_wakeup(priv->device)) { - wol->supported = WAKE_MAGIC | WAKE_UCAST; - if (priv->hw_cap_support && !priv->dma_cap.pmt_magic_frame) - wol->supported &= ~WAKE_MAGIC; - wol->wolopts = priv->wolopts; - } - mutex_unlock(&priv->lock); + return phylink_ethtool_get_wol(priv->phylink, wol); } static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol) { struct stmmac_priv *priv = netdev_priv(dev); - if (!device_can_wakeup(priv->device)) - return -EOPNOTSUPP; - - if (!priv->plat->pmt) { - int ret = phylink_ethtool_set_wol(priv->phylink, wol); - - if (!ret) - device_set_wakeup_enable(priv->device, !!wol->wolopts); - return ret; - } - - device_set_wakeup_enable(priv->device, !!wol->wolopts); - - mutex_lock(&priv->lock); - priv->wolopts = wol->wolopts; - mutex_unlock(&priv->lock); - - return 0; + return phylink_ethtool_set_wol(priv->phylink, wol); } static int stmmac_ethtool_op_get_eee(struct net_device *dev, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c index 75b470ee621a3..c54c702243517 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_fpe.c @@ -70,8 +70,10 @@ static void stmmac_fpe_configure_pmac(struct ethtool_mmsv *mmsv, bool pmac_enabl struct stmmac_priv *priv = container_of(cfg, struct stmmac_priv, fpe_cfg); const struct stmmac_fpe_reg *reg = cfg->reg; void __iomem *ioaddr = priv->ioaddr; + unsigned long flags; u32 value; + spin_lock_irqsave(&priv->hw->irq_ctrl_lock, flags); value = readl(ioaddr + reg->int_en_reg); if (pmac_enable) { @@ -86,6 +88,7 @@ static void stmmac_fpe_configure_pmac(struct ethtool_mmsv *mmsv, bool pmac_enabl } writel(value, ioaddr + reg->int_en_reg); + spin_unlock_irqrestore(&priv->hw->irq_ctrl_lock, flags); } static void stmmac_fpe_send_mpacket(struct ethtool_mmsv *mmsv, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7b90ecd3a55e6..a862d5f91fce3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -40,12 +40,14 @@ #include #include #include +#include #include #include #include #include "stmmac_ptp.h" #include "stmmac_fpe.h" #include "stmmac.h" +#include "stmmac_pcs.h" #include "stmmac_xdp.h" #include #include @@ -57,8 +59,7 @@ * with fine resolution and binary rollover. This avoid non-monotonic behavior * (clock jumps) when changing timestamping settings at runtime. */ -#define STMMAC_HWTS_ACTIVE (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | \ - PTP_TCR_TSCTRLSSR) +#define STMMAC_HWTS_ACTIVE (PTP_TCR_TSENA | PTP_TCR_TSCTRLSSR) #define STMMAC_ALIGN(x) ALIGN(ALIGN(x, SMP_CACHE_BYTES), 16) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) @@ -147,6 +148,15 @@ static void stmmac_exit_fs(struct net_device *dev); #define STMMAC_COAL_TIMER(x) (ns_to_ktime((x) * NSEC_PER_USEC)) +struct stmmac_devlink_priv { + struct stmmac_priv *stmmac_priv; +}; + +enum stmmac_dl_param_id { + STMMAC_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + STMMAC_DEVLINK_PARAM_ID_TS_COARSE, +}; + /** * stmmac_set_clk_tx_rate() - set the clock rate for the MAC transmit clock * @bsp_priv: BSP private data structure (unused) @@ -445,7 +455,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, if (!priv->hwts_rx_en) return; /* For GMAC4, the valid timestamp is from CTX next desc. */ - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) + if (dwmac_is_xmac(priv->plat->core_type)) desc = np; /* Check if timestamp is available */ @@ -463,6 +473,33 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, } } +static void stmmac_update_subsecond_increment(struct stmmac_priv *priv) +{ + bool xmac = dwmac_is_xmac(priv->plat->core_type); + u32 sec_inc = 0; + u64 temp = 0; + + stmmac_config_hw_tstamping(priv, priv->ptpaddr, priv->systime_flags); + + /* program Sub Second Increment reg */ + stmmac_config_sub_second_increment(priv, priv->ptpaddr, + priv->plat->clk_ptp_rate, + xmac, &sec_inc); + temp = div_u64(1000000000ULL, sec_inc); + + /* Store sub second increment for later use */ + priv->sub_second_inc = sec_inc; + + /* calculate default added value: + * formula is : + * addend = (2^32)/freq_div_ratio; + * where, freq_div_ratio = 1e9ns/sec_inc + */ + temp = (u64)(temp << 32); + priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); + stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); +} + /** * stmmac_hwtstamp_set - control hardware timestamping. * @dev: device pointer. @@ -647,6 +684,8 @@ static int stmmac_hwtstamp_set(struct net_device *dev, priv->hwts_tx_en = config->tx_type == HWTSTAMP_TX_ON; priv->systime_flags = STMMAC_HWTS_ACTIVE; + if (!priv->tsfupdt_coarse) + priv->systime_flags |= PTP_TCR_TSCFUPDT; if (priv->hwts_tx_en || priv->hwts_rx_en) { priv->systime_flags |= tstamp_all | ptp_v2 | @@ -696,10 +735,7 @@ static int stmmac_hwtstamp_get(struct net_device *dev, static int stmmac_init_tstamp_counter(struct stmmac_priv *priv, u32 systime_flags) { - bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; struct timespec64 now; - u32 sec_inc = 0; - u64 temp = 0; if (!priv->plat->clk_ptp_rate) { netdev_err(priv->dev, "Invalid PTP clock rate"); @@ -709,23 +745,7 @@ static int stmmac_init_tstamp_counter(struct stmmac_priv *priv, stmmac_config_hw_tstamping(priv, priv->ptpaddr, systime_flags); priv->systime_flags = systime_flags; - /* program Sub Second Increment reg */ - stmmac_config_sub_second_increment(priv, priv->ptpaddr, - priv->plat->clk_ptp_rate, - xmac, &sec_inc); - temp = div_u64(1000000000ULL, sec_inc); - - /* Store sub second increment for later use */ - priv->sub_second_inc = sec_inc; - - /* calculate default added value: - * formula is : - * addend = (2^32)/freq_div_ratio; - * where, freq_div_ratio = 1e9ns/sec_inc - */ - temp = (u64)(temp << 32); - priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); - stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); + stmmac_update_subsecond_increment(priv); /* initialize system time */ ktime_get_real_ts64(&now); @@ -745,7 +765,7 @@ static int stmmac_init_tstamp_counter(struct stmmac_priv *priv, */ static int stmmac_init_timestamping(struct stmmac_priv *priv) { - bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + bool xmac = dwmac_is_xmac(priv->plat->core_type); int ret; if (priv->plat->ptp_clk_freq_config) @@ -756,7 +776,8 @@ static int stmmac_init_timestamping(struct stmmac_priv *priv) return -EOPNOTSUPP; } - ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE); + ret = stmmac_init_tstamp_counter(priv, STMMAC_HWTS_ACTIVE | + PTP_TCR_TSCFUPDT); if (ret) { netdev_warn(priv->dev, "PTP init failed\n"); return ret; @@ -850,6 +871,13 @@ static struct phylink_pcs *stmmac_mac_select_pcs(struct phylink_config *config, return pcs; } + /* The PCS control register is only relevant for SGMII, TBI and RTBI + * modes. We no longer support TBI or RTBI, so only configure this + * register when operating in SGMII mode with the integrated PCS. + */ + if (priv->hw->pcs & STMMAC_PCS_SGMII && priv->integrated_pcs) + return &priv->integrated_pcs->pcs; + return NULL; } @@ -859,6 +887,18 @@ static void stmmac_mac_config(struct phylink_config *config, unsigned int mode, /* Nothing to do, xpcs_config() handles everything */ } +static int stmmac_mac_finish(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct net_device *ndev = to_net_dev(config->dev); + struct stmmac_priv *priv = netdev_priv(ndev); + + if (priv->plat->mac_finish) + priv->plat->mac_finish(ndev, priv->plat->bsp_priv, mode, interface); + + return 0; +} + static void stmmac_mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface) { @@ -1053,14 +1093,16 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer, return 0; } -static int stmmac_mac_finish(struct phylink_config *config, unsigned int mode, - phy_interface_t interface) +static int stmmac_mac_wol_set(struct phylink_config *config, u32 wolopts, + const u8 *sopass) { - struct net_device *ndev = to_net_dev(config->dev); - struct stmmac_priv *priv = netdev_priv(ndev); + struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev)); - if (priv->plat->mac_finish) - priv->plat->mac_finish(ndev, priv->plat->bsp_priv, mode, interface); + device_set_wakeup_enable(priv->device, !!wolopts); + + mutex_lock(&priv->lock); + priv->wolopts = wolopts; + mutex_unlock(&priv->lock); return 0; } @@ -1069,11 +1111,12 @@ static const struct phylink_mac_ops stmmac_phylink_mac_ops = { .mac_get_caps = stmmac_mac_get_caps, .mac_select_pcs = stmmac_mac_select_pcs, .mac_config = stmmac_mac_config, + .mac_finish = stmmac_mac_finish, .mac_link_down = stmmac_mac_link_down, .mac_link_up = stmmac_mac_link_up, .mac_disable_tx_lpi = stmmac_mac_disable_tx_lpi, .mac_enable_tx_lpi = stmmac_mac_enable_tx_lpi, - .mac_finish = stmmac_mac_finish, + .mac_wol_set = stmmac_mac_wol_set, }; /** @@ -1086,17 +1129,25 @@ static const struct phylink_mac_ops stmmac_phylink_mac_ops = { static void stmmac_check_pcs_mode(struct stmmac_priv *priv) { int interface = priv->plat->phy_interface; + int speed = priv->plat->mac_port_sel_speed; + + if (priv->dma_cap.pcs && interface == PHY_INTERFACE_MODE_SGMII) { + netdev_dbg(priv->dev, "PCS SGMII support enabled\n"); + priv->hw->pcs = STMMAC_PCS_SGMII; - if (priv->dma_cap.pcs) { - if ((interface == PHY_INTERFACE_MODE_RGMII) || - (interface == PHY_INTERFACE_MODE_RGMII_ID) || - (interface == PHY_INTERFACE_MODE_RGMII_RXID) || - (interface == PHY_INTERFACE_MODE_RGMII_TXID)) { - netdev_dbg(priv->dev, "PCS RGMII support enabled\n"); - priv->hw->pcs = STMMAC_PCS_RGMII; - } else if (interface == PHY_INTERFACE_MODE_SGMII) { - netdev_dbg(priv->dev, "PCS SGMII support enabled\n"); - priv->hw->pcs = STMMAC_PCS_SGMII; + switch (speed) { + case SPEED_10: + case SPEED_100: + case SPEED_1000: + priv->hw->reverse_sgmii_enable = true; + break; + + default: + dev_warn(priv->device, "invalid port speed\n"); + fallthrough; + case 0: + priv->hw->reverse_sgmii_enable = false; + break; } } } @@ -1174,18 +1225,10 @@ static int stmmac_init_phy(struct net_device *dev) phylink_ethtool_set_eee(priv->phylink, &eee); } - if (!priv->plat->pmt) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; - - phylink_ethtool_get_wol(priv->phylink, &wol); - device_set_wakeup_capable(priv->device, !!wol.supported); - device_set_wakeup_enable(priv->device, !!wol.wolopts); - } - return 0; } -static int stmmac_phy_setup(struct stmmac_priv *priv) +static int stmmac_phylink_setup(struct stmmac_priv *priv) { struct stmmac_mdio_bus_data *mdio_bus_data; struct phylink_config *config; @@ -1202,7 +1245,11 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) /* Stmmac always requires an RX clock for hardware initialization */ config->mac_requires_rxc = true; - if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI)) + /* Disable EEE RX clock stop to ensure VLAN register access works + * correctly. + */ + if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI) && + !(priv->dev->features & NETIF_F_VLAN_FEATURES)) config->eee_rx_clk_stop_enable = true; /* Set the default transmit clock stop bit based on the platform glue */ @@ -1250,6 +1297,16 @@ static int stmmac_phy_setup(struct stmmac_priv *priv) config->eee_enabled_default = true; } + config->wol_phy_speed_ctrl = true; + if (priv->plat->flags & STMMAC_FLAG_USE_PHY_WOL) { + config->wol_phy_legacy = true; + } else { + if (priv->dma_cap.pmt_remote_wake_up) + config->wol_mac_support |= WAKE_UCAST; + if (priv->dma_cap.pmt_magic_frame) + config->wol_mac_support |= WAKE_MAGIC; + } + fwnode = priv->plat->port_node; if (!fwnode) fwnode = dev_fwnode(priv->device); @@ -1339,9 +1396,9 @@ static unsigned int stmmac_rx_offset(struct stmmac_priv *priv) return NET_SKB_PAD; } -static int stmmac_set_bfsize(int mtu, int bufsize) +static int stmmac_set_bfsize(int mtu) { - int ret = bufsize; + int ret; if (mtu >= BUF_SIZE_8KiB) ret = BUF_SIZE_16KiB; @@ -2397,7 +2454,7 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) txfifosz = priv->dma_cap.tx_fifo_size; /* Split up the shared Tx/Rx FIFO memory on DW QoS Eth and DW XGMAC */ - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { + if (dwmac_is_xmac(priv->plat->core_type)) { rxfifosz /= rx_channels_count; txfifosz /= tx_channels_count; } @@ -3029,6 +3086,56 @@ static void stmmac_check_ether_addr(struct stmmac_priv *priv) } } +int stmmac_get_phy_intf_sel(phy_interface_t interface) +{ + int phy_intf_sel = -EINVAL; + + if (interface == PHY_INTERFACE_MODE_MII || + interface == PHY_INTERFACE_MODE_GMII) + phy_intf_sel = PHY_INTF_SEL_GMII_MII; + else if (phy_interface_mode_is_rgmii(interface)) + phy_intf_sel = PHY_INTF_SEL_RGMII; + else if (interface == PHY_INTERFACE_MODE_SGMII) + phy_intf_sel = PHY_INTF_SEL_SGMII; + else if (interface == PHY_INTERFACE_MODE_RMII) + phy_intf_sel = PHY_INTF_SEL_RMII; + else if (interface == PHY_INTERFACE_MODE_REVMII) + phy_intf_sel = PHY_INTF_SEL_REVMII; + + return phy_intf_sel; +} +EXPORT_SYMBOL_GPL(stmmac_get_phy_intf_sel); + +static int stmmac_prereset_configure(struct stmmac_priv *priv) +{ + struct plat_stmmacenet_data *plat_dat = priv->plat; + phy_interface_t interface; + int phy_intf_sel, ret; + + if (!plat_dat->set_phy_intf_sel) + return 0; + + interface = plat_dat->phy_interface; + phy_intf_sel = stmmac_get_phy_intf_sel(interface); + if (phy_intf_sel < 0) { + netdev_err(priv->dev, + "failed to get phy_intf_sel for %s: %pe\n", + phy_modes(interface), ERR_PTR(phy_intf_sel)); + return phy_intf_sel; + } + + ret = plat_dat->set_phy_intf_sel(plat_dat->bsp_priv, phy_intf_sel); + if (ret == -EINVAL) + netdev_err(priv->dev, "platform does not support %s\n", + phy_modes(interface)); + else if (ret < 0) + netdev_err(priv->dev, + "platform failed to set interface %s: %pe\n", + phy_modes(interface), ERR_PTR(ret)); + + return ret; +} + /** * stmmac_init_dma_engine - DMA init. * @priv: driver private structure @@ -3055,7 +3162,11 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) priv->plat->dma_cfg->atds = 1; - ret = stmmac_reset(priv, priv->ioaddr); + ret = stmmac_prereset_configure(priv); + if (ret) + return ret; + + ret = stmmac_reset(priv); if (ret) { netdev_err(priv->dev, "Failed to reset the dma\n"); return ret; @@ -3443,19 +3554,6 @@ static int stmmac_hw_setup(struct net_device *dev) stmmac_set_umac_addr(priv, priv->hw, dev->dev_addr, 0); phylink_rx_clk_stop_unblock(priv->phylink); - /* PS and related bits will be programmed according to the speed */ - if (priv->hw->pcs) { - int speed = priv->plat->mac_port_sel_speed; - - if ((speed == SPEED_10) || (speed == SPEED_100) || - (speed == SPEED_1000)) { - priv->hw->ps = speed; - } else { - dev_warn(priv->device, "invalid port speed\n"); - priv->hw->ps = 0; - } - } - /* Initialize the MAC Core */ stmmac_core_init(priv, priv->hw, dev); @@ -3492,9 +3590,6 @@ static int stmmac_hw_setup(struct net_device *dev) } } - if (priv->hw->pcs) - stmmac_pcs_ctrl_ane(priv, 1, priv->hw->ps, 0); - /* set TX and RX rings length */ stmmac_set_rings_length(priv); @@ -3867,12 +3962,13 @@ stmmac_setup_dma_desc(struct stmmac_priv *priv, unsigned int mtu) return ERR_PTR(-ENOMEM); } + /* Returns 0 or BUF_SIZE_16KiB if mtu > 8KiB and dwmac4 or ring mode */ bfsize = stmmac_set_16kib_bfsize(priv, mtu); if (bfsize < 0) bfsize = 0; if (bfsize < BUF_SIZE_16KiB) - bfsize = stmmac_set_bfsize(mtu, 0); + bfsize = stmmac_set_bfsize(mtu); dma_conf->dma_buf_sz = bfsize; /* Chose the tx/rx size from the already defined one in the @@ -3963,8 +4059,6 @@ static int __stmmac_open(struct net_device *dev, stmmac_init_coalesce(priv); phylink_start(priv->phylink); - /* We may have called phylink_speed_down before */ - phylink_speed_up(priv->phylink); ret = stmmac_request_irq(dev); if (ret) @@ -4015,6 +4109,9 @@ static int stmmac_open(struct net_device *dev) kfree(dma_conf); + /* We may have called phylink_speed_down before */ + phylink_speed_up(priv->phylink); + return ret; err_disconnect_phy: @@ -4032,13 +4129,6 @@ static void __stmmac_release(struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); u32 chan; - /* If the PHY or MAC has WoL enabled, then the PHY will not be - * suspended when phylink_stop() is called below. Set the PHY - * to its slowest speed to save power. - */ - if (device_may_wakeup(priv->device)) - phylink_speed_down(priv->phylink, false); - /* Stop and disconnect the PHY */ phylink_stop(priv->phylink); @@ -4078,6 +4168,13 @@ static int stmmac_release(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); + /* If the PHY or MAC has WoL enabled, then the PHY will not be + * suspended when phylink_stop() is called below. Set the PHY + * to its slowest speed to save power. + */ + if (device_may_wakeup(priv->device)) + phylink_speed_down(priv->phylink, false); + __stmmac_release(dev); phylink_disconnect_phy(priv->phylink); @@ -4513,7 +4610,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_is_gso(skb) && priv->tso) { if (gso & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) return stmmac_tso_xmit(skb, dev); - if (priv->plat->has_gmac4 && (gso & SKB_GSO_UDP_L4)) + if (priv->plat->core_type == DWMAC_CORE_GMAC4 && + (gso & SKB_GSO_UDP_L4)) return stmmac_tso_xmit(skb, dev); } @@ -5971,7 +6069,7 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) u32 queue; bool xmac; - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + xmac = dwmac_is_xmac(priv->plat->core_type); queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt; if (priv->irq_wake) @@ -5985,7 +6083,7 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) stmmac_fpe_irq_status(priv); /* To handle GMAC own interrupts */ - if ((priv->plat->has_gmac) || xmac) { + if (priv->plat->core_type == DWMAC_CORE_GMAC || xmac) { int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats); if (unlikely(status)) { @@ -5999,15 +6097,6 @@ static void stmmac_common_interrupt(struct stmmac_priv *priv) for (queue = 0; queue < queues_count; queue++) stmmac_host_mtl_irq_status(priv, priv->hw, queue); - /* PCS link status */ - if (priv->hw->pcs && - !(priv->plat->flags & STMMAC_FLAG_HAS_INTEGRATED_PCS)) { - if (priv->xstats.pcs_link) - netif_carrier_on(priv->dev); - else - netif_carrier_off(priv->dev); - } - stmmac_timestamp_interrupt(priv, priv); } } @@ -6355,7 +6444,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.mbps_1000) ? "Y" : "N"); seq_printf(seq, "\tHalf duplex: %s\n", (priv->dma_cap.half_duplex) ? "Y" : "N"); - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { seq_printf(seq, "\tNumber of Additional MAC address registers: %d\n", priv->dma_cap.multi_addr); @@ -6379,7 +6468,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) (priv->dma_cap.time_stamp) ? "Y" : "N"); seq_printf(seq, "\tIEEE 1588-2008 Advanced Time Stamp: %s\n", (priv->dma_cap.atime_stamp) ? "Y" : "N"); - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) seq_printf(seq, "\tTimestamp System Time Source: %s\n", dwxgmac_timestamp_source[priv->dma_cap.tssrc]); seq_printf(seq, "\t802.3az - Energy-Efficient Ethernet (EEE): %s\n", @@ -6388,7 +6477,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) seq_printf(seq, "\tChecksum Offload in TX: %s\n", (priv->dma_cap.tx_coe) ? "Y" : "N"); if (priv->synopsys_id >= DWMAC_CORE_4_00 || - priv->plat->has_xgmac) { + priv->plat->core_type == DWMAC_CORE_XGMAC) { seq_printf(seq, "\tIP Checksum Offload in RX: %s\n", (priv->dma_cap.rx_coe) ? "Y" : "N"); } else { @@ -7240,13 +7329,21 @@ static int stmmac_hw_init(struct stmmac_priv *priv) * has to be disable and this can be done by passing the * riwt_off field from the platform. */ - if (((priv->synopsys_id >= DWMAC_CORE_3_50) || - (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) { + if ((priv->synopsys_id >= DWMAC_CORE_3_50 || + priv->plat->core_type == DWMAC_CORE_XGMAC) && + !priv->plat->riwt_off) { priv->use_riwt = 1; dev_info(priv->device, "Enable RX Mitigation via HW Watchdog Timer\n"); } + /* Unimplemented PCS init (as indicated by stmmac_do_callback() + * perversely returning -EINVAL) is non-fatal. + */ + ret = stmmac_mac_pcs_init(priv); + if (ret != -EINVAL) + return ret; + return 0; } @@ -7355,7 +7452,7 @@ static int stmmac_xdp_rx_timestamp(const struct xdp_md *_ctx, u64 *timestamp) return -ENODATA; /* For GMAC4, the valid timestamp is from CTX next desc. */ - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) + if (dwmac_is_xmac(priv->plat->core_type)) desc_contains_ts = ndesc; /* Check if timestamp is available */ @@ -7373,6 +7470,129 @@ static const struct xdp_metadata_ops stmmac_xdp_metadata_ops = { .xmo_rx_timestamp = stmmac_xdp_rx_timestamp, }; +static int stmmac_dl_ts_coarse_set(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) +{ + struct stmmac_devlink_priv *dl_priv = devlink_priv(dl); + struct stmmac_priv *priv = dl_priv->stmmac_priv; + + priv->tsfupdt_coarse = ctx->val.vbool; + + if (priv->tsfupdt_coarse) + priv->systime_flags &= ~PTP_TCR_TSCFUPDT; + else + priv->systime_flags |= PTP_TCR_TSCFUPDT; + + /* In Coarse mode, we can use a smaller subsecond increment, let's + * reconfigure the systime, subsecond increment and addend. + */ + stmmac_update_subsecond_increment(priv); + + return 0; +} + +static int stmmac_dl_ts_coarse_get(struct devlink *dl, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct stmmac_devlink_priv *dl_priv = devlink_priv(dl); + struct stmmac_priv *priv = dl_priv->stmmac_priv; + + ctx->val.vbool = priv->tsfupdt_coarse; + + return 0; +} + +static const struct devlink_param stmmac_devlink_params[] = { + DEVLINK_PARAM_DRIVER(STMMAC_DEVLINK_PARAM_ID_TS_COARSE, "phc_coarse_adj", + DEVLINK_PARAM_TYPE_BOOL, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + stmmac_dl_ts_coarse_get, + stmmac_dl_ts_coarse_set, NULL), +}; + +/* None of the generic devlink parameters are implemented */ +static const struct devlink_ops stmmac_devlink_ops = {}; + +static int stmmac_register_devlink(struct stmmac_priv *priv) +{ + struct stmmac_devlink_priv *dl_priv; + int ret; + + /* For now, what is exposed over devlink is only relevant when + * timestamping is available and we have a valid ptp clock rate + */ + if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp) || + !priv->plat->clk_ptp_rate) + return 0; + + priv->devlink = devlink_alloc(&stmmac_devlink_ops, sizeof(*dl_priv), + priv->device); + if (!priv->devlink) + return -ENOMEM; + + dl_priv = devlink_priv(priv->devlink); + dl_priv->stmmac_priv = priv; + + ret = devlink_params_register(priv->devlink, stmmac_devlink_params, + ARRAY_SIZE(stmmac_devlink_params)); + if (ret) + goto dl_free; + + devlink_register(priv->devlink); + return 0; + +dl_free: + devlink_free(priv->devlink); + + return ret; +} + +static void stmmac_unregister_devlink(struct stmmac_priv *priv) +{ + if (!priv->devlink) + return; + + devlink_unregister(priv->devlink); + devlink_params_unregister(priv->devlink, stmmac_devlink_params, + ARRAY_SIZE(stmmac_devlink_params)); + devlink_free(priv->devlink); +} + +struct plat_stmmacenet_data *stmmac_plat_dat_alloc(struct device *dev) +{ + struct plat_stmmacenet_data *plat_dat; + int i; + + plat_dat = devm_kzalloc(dev, sizeof(*plat_dat), GFP_KERNEL); + if (!plat_dat) + return NULL; + + /* Set the defaults: + * - phy autodetection + * - determine GMII_Address CR field from CSR clock + * - allow MTU up to JUMBO_LEN + * - hash table size + * - one unicast filter entry + */ + plat_dat->phy_addr = -1; + plat_dat->clk_csr = -1; + plat_dat->maxmtu = JUMBO_LEN; + plat_dat->multicast_filter_bins = HASH_TABLE_SIZE; + plat_dat->unicast_filter_entries = 1; + + /* Set the mtl defaults */ + plat_dat->tx_queues_to_use = 1; + plat_dat->rx_queues_to_use = 1; + + /* Setup the default RX queue channel map */ + for (i = 0; i < ARRAY_SIZE(plat_dat->rx_queues_cfg); i++) + plat_dat->rx_queues_cfg[i].chan = i; + + return plat_dat; +} +EXPORT_SYMBOL_GPL(stmmac_plat_dat_alloc); + /** * stmmac_dvr_probe * @device: device pointer @@ -7511,7 +7731,7 @@ int stmmac_dvr_probe(struct device *device, if ((priv->plat->flags & STMMAC_FLAG_TSO_EN) && (priv->dma_cap.tsoen)) { ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) ndev->hw_features |= NETIF_F_GSO_UDP_L4; priv->tso = true; dev_info(priv->device, "TSO feature enabled\n"); @@ -7564,7 +7784,7 @@ int stmmac_dvr_probe(struct device *device, #ifdef STMMAC_VLAN_TAG_USED /* Both mac100 and gmac support receive VLAN tag detection */ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; - if (priv->plat->has_gmac4 || priv->plat->has_xgmac) { + if (dwmac_is_xmac(priv->plat->core_type)) { ndev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; priv->hw->hw_vlan_en = true; } @@ -7592,22 +7812,23 @@ int stmmac_dvr_probe(struct device *device, /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; - if (priv->plat->has_xgmac) + + if (priv->plat->core_type == DWMAC_CORE_XGMAC) ndev->max_mtu = XGMAC_JUMBO_LEN; - else if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) + else if (priv->plat->enh_desc || priv->synopsys_id >= DWMAC_CORE_4_00) ndev->max_mtu = JUMBO_LEN; else ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN); - /* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu - * as well as plat->maxmtu < ndev->min_mtu which is a invalid range. + + /* Warn if the platform's maxmtu is smaller than the minimum MTU, + * otherwise clamp the maximum MTU above to the platform's maxmtu. */ - if ((priv->plat->maxmtu < ndev->max_mtu) && - (priv->plat->maxmtu >= ndev->min_mtu)) - ndev->max_mtu = priv->plat->maxmtu; - else if (priv->plat->maxmtu < ndev->min_mtu) + if (priv->plat->maxmtu < ndev->min_mtu) dev_warn(priv->device, "%s: warning: maxmtu having invalid value (%d)\n", __func__, priv->plat->maxmtu); + else if (priv->plat->maxmtu < ndev->max_mtu) + ndev->max_mtu = priv->plat->maxmtu; ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE; @@ -7637,12 +7858,16 @@ int stmmac_dvr_probe(struct device *device, if (ret) goto error_pcs_setup; - ret = stmmac_phy_setup(priv); + ret = stmmac_phylink_setup(priv); if (ret) { netdev_err(ndev, "failed to setup phy (%d)\n", ret); goto error_phy_setup; } + ret = stmmac_register_devlink(priv); + if (ret) + goto error_devlink_setup; + ret = register_netdev(ndev); if (ret) { dev_err(priv->device, "%s: ERROR %i registering the device\n", @@ -7665,6 +7890,8 @@ int stmmac_dvr_probe(struct device *device, return ret; error_netdev_register: + stmmac_unregister_devlink(priv); +error_devlink_setup: phylink_destroy(priv->phylink); error_phy_setup: stmmac_pcs_clean(ndev); @@ -7701,6 +7928,8 @@ void stmmac_dvr_remove(struct device *dev) #ifdef CONFIG_DEBUG_FS stmmac_exit_fs(ndev); #endif + stmmac_unregister_devlink(priv); + phylink_destroy(priv->phylink); if (priv->plat->stmmac_rst) reset_control_assert(priv->plat->stmmac_rst); @@ -7755,7 +7984,7 @@ int stmmac_suspend(struct device *dev) priv->plat->serdes_powerdown(ndev, priv->plat->bsp_priv); /* Enable Power down mode by programming the PMT regs */ - if (stmmac_wol_enabled_mac(priv)) { + if (priv->wolopts) { stmmac_pmt(priv, priv->hw, priv->wolopts); priv->irq_wake = 1; } else { @@ -7766,10 +7995,7 @@ int stmmac_suspend(struct device *dev) mutex_unlock(&priv->lock); rtnl_lock(); - if (stmmac_wol_enabled_phy(priv)) - phylink_speed_down(priv->phylink, false); - - phylink_suspend(priv->phylink, stmmac_wol_enabled_mac(priv)); + phylink_suspend(priv->phylink, !!priv->wolopts); rtnl_unlock(); if (stmmac_fpe_supported(priv)) @@ -7845,7 +8071,7 @@ int stmmac_resume(struct device *dev) * this bit because it can generate problems while resuming * from another devices (e.g. serial console). */ - if (stmmac_wol_enabled_mac(priv)) { + if (priv->wolopts) { mutex_lock(&priv->lock); stmmac_pmt(priv, priv->hw, 0); mutex_unlock(&priv->lock); @@ -7907,9 +8133,6 @@ int stmmac_resume(struct device *dev) * workqueue thread, which will race with initialisation. */ phylink_resume(priv->phylink); - if (stmmac_wol_enabled_phy(priv)) - phylink_speed_up(priv->phylink); - rtnl_unlock(); netif_device_attach(ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index f408737f6fc73..1e82850f2a25c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -301,7 +301,7 @@ static int stmmac_mdio_read_c22(struct mii_bus *bus, int phyaddr, int phyreg) struct stmmac_priv *priv = netdev_priv(bus->priv); u32 cmd; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) cmd = MII_GMAC4_READ; else cmd = 0; @@ -344,7 +344,7 @@ static int stmmac_mdio_write_c22(struct mii_bus *bus, int phyaddr, int phyreg, struct stmmac_priv *priv = netdev_priv(bus->priv); u32 cmd; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) cmd = MII_GMAC4_WRITE; else cmd = MII_ADDR_GWRITE; @@ -417,7 +417,7 @@ int stmmac_mdio_reset(struct mii_bus *bus) * on MDC, so perform a dummy mdio read. To be updated for GMAC4 * if needed. */ - if (!priv->plat->has_gmac4) + if (priv->plat->core_type != DWMAC_CORE_GMAC4) writel(0, priv->ioaddr + mii_address); #endif return 0; @@ -528,7 +528,7 @@ static u32 stmmac_clk_csr_set(struct stmmac_priv *priv) value = 0; } - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { if (clk_rate > 400000000) value = 0x5; else if (clk_rate > 350000000) @@ -583,8 +583,9 @@ int stmmac_mdio_register(struct net_device *ndev) struct device_node *mdio_node = priv->plat->mdio_node; struct device *dev = ndev->dev.parent; struct fwnode_handle *fixed_node; + int max_addr = PHY_MAX_ADDR - 1; struct fwnode_handle *fwnode; - int addr, found, max_addr; + struct phy_device *phydev; if (!mdio_bus_data) return 0; @@ -600,7 +601,7 @@ int stmmac_mdio_register(struct net_device *ndev) new_bus->name = "stmmac"; - if (priv->plat->has_xgmac) { + if (priv->plat->core_type == DWMAC_CORE_XGMAC) { new_bus->read = &stmmac_xgmac2_mdio_read_c22; new_bus->write = &stmmac_xgmac2_mdio_write_c22; new_bus->read_c45 = &stmmac_xgmac2_mdio_read_c45; @@ -608,25 +609,20 @@ int stmmac_mdio_register(struct net_device *ndev) if (priv->synopsys_id < DWXGMAC_CORE_2_20) { /* Right now only C22 phys are supported */ - max_addr = MII_XGMAC_MAX_C22ADDR + 1; + max_addr = MII_XGMAC_MAX_C22ADDR; /* Check if DT specified an unsupported phy addr */ if (priv->plat->phy_addr > MII_XGMAC_MAX_C22ADDR) dev_err(dev, "Unsupported phy_addr (max=%d)\n", MII_XGMAC_MAX_C22ADDR); - } else { - /* XGMAC version 2.20 onwards support 32 phy addr */ - max_addr = PHY_MAX_ADDR; } } else { new_bus->read = &stmmac_mdio_read_c22; new_bus->write = &stmmac_mdio_write_c22; - if (priv->plat->has_gmac4) { + if (priv->plat->core_type == DWMAC_CORE_GMAC4) { new_bus->read_c45 = &stmmac_mdio_read_c45; new_bus->write_c45 = &stmmac_mdio_write_c45; } - - max_addr = PHY_MAX_ADDR; } if (mdio_bus_data->needs_reset) @@ -649,7 +645,7 @@ int stmmac_mdio_register(struct net_device *ndev) } /* Looks like we need a dummy read for XGMAC only and C45 PHYs */ - if (priv->plat->has_xgmac) + if (priv->plat->core_type == DWMAC_CORE_XGMAC) stmmac_xgmac2_mdio_read_c45(new_bus, 0, 0, 0); /* If fixed-link is set, skip PHY scanning */ @@ -668,41 +664,31 @@ int stmmac_mdio_register(struct net_device *ndev) if (priv->plat->phy_node || mdio_node) goto bus_register_done; - found = 0; - for (addr = 0; addr < max_addr; addr++) { - struct phy_device *phydev = mdiobus_get_phy(new_bus, addr); - - if (!phydev) - continue; - - /* - * If an IRQ was provided to be assigned after - * the bus probe, do it here. - */ - if (!mdio_bus_data->irqs && - (mdio_bus_data->probed_phy_irq > 0)) { - new_bus->irq[addr] = mdio_bus_data->probed_phy_irq; - phydev->irq = mdio_bus_data->probed_phy_irq; - } - - /* - * If we're going to bind the MAC to this PHY bus, - * and no PHY number was provided to the MAC, - * use the one probed here. - */ - if (priv->plat->phy_addr == -1) - priv->plat->phy_addr = addr; - - phy_attached_info(phydev); - found = 1; - } - - if (!found && !mdio_node) { + phydev = phy_find_first(new_bus); + if (!phydev || phydev->mdio.addr > max_addr) { dev_warn(dev, "No PHY found\n"); err = -ENODEV; goto no_phy_found; } + /* + * If an IRQ was provided to be assigned after + * the bus probe, do it here. + */ + if (!mdio_bus_data->irqs && mdio_bus_data->probed_phy_irq > 0) { + new_bus->irq[phydev->mdio.addr] = mdio_bus_data->probed_phy_irq; + phydev->irq = mdio_bus_data->probed_phy_irq; + } + + /* + * If we're going to bind the MAC to this PHY bus, and no PHY number + * was provided to the MAC, use the one probed here. + */ + if (priv->plat->phy_addr == -1) + priv->plat->phy_addr = phydev->mdio.addr; + + phy_attached_info(phydev); + bus_register_done: priv->mii = new_bus; @@ -734,3 +720,17 @@ int stmmac_mdio_unregister(struct net_device *ndev) return 0; } + +void stmmac_mdio_lock(struct stmmac_priv *priv) +{ + if (priv->mii) + mutex_lock(&priv->mii->mdio_lock); +} +EXPORT_SYMBOL_GPL(stmmac_mdio_lock); + +void stmmac_mdio_unlock(struct stmmac_priv *priv) +{ + if (priv->mii) + mutex_unlock(&priv->mii->mdio_lock); +} +EXPORT_SYMBOL_GPL(stmmac_mdio_unlock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 4e3aa611fda83..2fd4660838bb2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -23,30 +23,10 @@ static void common_default_data(struct plat_stmmacenet_data *plat) { /* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */ plat->clk_csr = STMMAC_CSR_20_35M; - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->force_sf_dma_mode = 1; plat->mdio_bus_data->needs_reset = true; - - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - - /* Set default number of RX and TX queues to use */ - plat->tx_queues_to_use = 1; - plat->rx_queues_to_use = 1; - - /* Disable Priority config by default */ - plat->tx_queues_cfg[0].use_prio = false; - plat->rx_queues_cfg[0].use_prio = false; - - /* Disable RX queues routing by default */ - plat->rx_queues_cfg[0].pkt_route = 0x0; } static int stmmac_default_data(struct pci_dev *pdev, @@ -76,27 +56,17 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, int i; plat->clk_csr = STMMAC_CSR_250_300M; - plat->has_gmac4 = 1; + plat->core_type = DWMAC_CORE_GMAC4; plat->force_sf_dma_mode = 1; plat->flags |= STMMAC_FLAG_TSO_EN; plat->pmt = 1; - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - - /* Set the maxmtu to a default of JUMBO_LEN */ - plat->maxmtu = JUMBO_LEN; - /* Set default number of RX and TX queues to use */ plat->tx_queues_to_use = 4; plat->rx_queues_to_use = 4; plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; for (i = 0; i < plat->tx_queues_to_use; i++) { - plat->tx_queues_cfg[i].use_prio = false; plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; plat->tx_queues_cfg[i].weight = 25; if (i > 0) @@ -104,15 +74,10 @@ static int snps_gmac5_default_data(struct pci_dev *pdev, } plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; - for (i = 0; i < plat->rx_queues_to_use; i++) { - plat->rx_queues_cfg[i].use_prio = false; + for (i = 0; i < plat->rx_queues_to_use; i++) plat->rx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; - plat->rx_queues_cfg[i].pkt_route = 0x0; - plat->rx_queues_cfg[i].chan = i; - } plat->bus_id = 1; - plat->phy_addr = -1; plat->phy_interface = PHY_INTERFACE_MODE_GMII; plat->dma_cfg->pbl = 32; @@ -191,7 +156,7 @@ static int stmmac_pci_probe(struct pci_dev *pdev, int ret; int i; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return -ENOMEM; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.c new file mode 100644 index 0000000000000..e2f531c119868 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include "stmmac.h" +#include "stmmac_pcs.h" + +static int dwmac_integrated_pcs_enable(struct phylink_pcs *pcs) +{ + struct stmmac_pcs *spcs = phylink_pcs_to_stmmac_pcs(pcs); + + stmmac_mac_irq_modify(spcs->priv, 0, spcs->int_mask); + + return 0; +} + +static void dwmac_integrated_pcs_disable(struct phylink_pcs *pcs) +{ + struct stmmac_pcs *spcs = phylink_pcs_to_stmmac_pcs(pcs); + + stmmac_mac_irq_modify(spcs->priv, spcs->int_mask, 0); +} + +static void dwmac_integrated_pcs_get_state(struct phylink_pcs *pcs, + unsigned int neg_mode, + struct phylink_link_state *state) +{ + state->link = false; +} + +static int dwmac_integrated_pcs_config(struct phylink_pcs *pcs, + unsigned int neg_mode, + phy_interface_t interface, + const unsigned long *advertising, + bool permit_pause_to_mac) +{ + struct stmmac_pcs *spcs = phylink_pcs_to_stmmac_pcs(pcs); + + dwmac_ctrl_ane(spcs->base, 0, 1, spcs->priv->hw->reverse_sgmii_enable); + + return 0; +} + +static const struct phylink_pcs_ops dwmac_integrated_pcs_ops = { + .pcs_enable = dwmac_integrated_pcs_enable, + .pcs_disable = dwmac_integrated_pcs_disable, + .pcs_get_state = dwmac_integrated_pcs_get_state, + .pcs_config = dwmac_integrated_pcs_config, +}; + +int stmmac_integrated_pcs_init(struct stmmac_priv *priv, unsigned int offset, + u32 int_mask) +{ + struct stmmac_pcs *spcs; + + spcs = devm_kzalloc(priv->device, sizeof(*spcs), GFP_KERNEL); + if (!spcs) + return -ENOMEM; + + spcs->priv = priv; + spcs->base = priv->ioaddr + offset; + spcs->int_mask = int_mask; + spcs->pcs.ops = &dwmac_integrated_pcs_ops; + + __set_bit(PHY_INTERFACE_MODE_SGMII, spcs->pcs.supported_interfaces); + + priv->integrated_pcs = spcs; + + return 0; +} diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h index 4a684c97dfaeb..cda93894168e2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pcs.h @@ -9,6 +9,7 @@ #ifndef __STMMAC_PCS_H__ #define __STMMAC_PCS_H__ +#include #include #include #include "common.h" @@ -46,6 +47,24 @@ #define GMAC_ANE_RFE_SHIFT 12 #define GMAC_ANE_ACK BIT(14) +struct stmmac_priv; + +struct stmmac_pcs { + struct stmmac_priv *priv; + void __iomem *base; + u32 int_mask; + struct phylink_pcs pcs; +}; + +static inline struct stmmac_pcs * +phylink_pcs_to_stmmac_pcs(struct phylink_pcs *pcs) +{ + return container_of(pcs, struct stmmac_pcs, pcs); +} + +int stmmac_integrated_pcs_init(struct stmmac_priv *priv, unsigned int offset, + u32 int_mask); + /** * dwmac_pcs_isr - TBI, RTBI, or SGMII PHY ISR * @ioaddr: IO registers pointer @@ -82,13 +101,12 @@ static inline void dwmac_pcs_isr(void __iomem *ioaddr, u32 reg, * @reg: Base address of the AN Control Register. * @ane: to enable the auto-negotiation * @srgmi_ral: to manage MAC-2-MAC SGMII connections. - * @loopback: to cause the PHY to loopback tx data into rx path. * Description: this is the main function to configure the AN control register * and init the ANE, select loopback (usually for debugging purpose) and * configure SGMII RAL. */ static inline void dwmac_ctrl_ane(void __iomem *ioaddr, u32 reg, bool ane, - bool srgmi_ral, bool loopback) + bool srgmi_ral) { u32 value = readl(ioaddr + GMAC_AN_CTRL(reg)); @@ -104,9 +122,6 @@ static inline void dwmac_ctrl_ane(void __iomem *ioaddr, u32 reg, bool ane, if (srgmi_ral) value |= GMAC_AN_CTRL_SGMRAL; - if (loopback) - value |= GMAC_AN_CTRL_ELE; - writel(value, ioaddr + GMAC_AN_CTRL(reg)); } #endif /* __STMMAC_PCS_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 27bcaae07a7f2..ab9facc7f53af 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -137,13 +137,6 @@ static int stmmac_mtl_setup(struct platform_device *pdev, u8 queue = 0; int ret = 0; - /* For backwards-compatibility with device trees that don't have any - * snps,mtl-rx-config or snps,mtl-tx-config properties, we fall back - * to one RX and TX queues each. - */ - plat->rx_queues_to_use = 1; - plat->tx_queues_to_use = 1; - /* First Queue must always be in DCB mode. As MTL_QUEUE_DCB = 1 we need * to always set this, otherwise Queue will be classified as AVB * (because MTL_QUEUE_AVB = 0). @@ -162,9 +155,8 @@ static int stmmac_mtl_setup(struct platform_device *pdev, } /* Processing RX queues common config */ - if (of_property_read_u32(rx_node, "snps,rx-queues-to-use", - &plat->rx_queues_to_use)) - plat->rx_queues_to_use = 1; + of_property_read_u32(rx_node, "snps,rx-queues-to-use", + &plat->rx_queues_to_use); if (of_property_read_bool(rx_node, "snps,rx-sched-sp")) plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; @@ -185,18 +177,13 @@ static int stmmac_mtl_setup(struct platform_device *pdev, else plat->rx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; - if (of_property_read_u32(q_node, "snps,map-to-dma-channel", - &plat->rx_queues_cfg[queue].chan)) - plat->rx_queues_cfg[queue].chan = queue; + of_property_read_u32(q_node, "snps,map-to-dma-channel", + &plat->rx_queues_cfg[queue].chan); /* TODO: Dynamic mapping to be included in the future */ - if (of_property_read_u32(q_node, "snps,priority", - &plat->rx_queues_cfg[queue].prio)) { - plat->rx_queues_cfg[queue].prio = 0; - plat->rx_queues_cfg[queue].use_prio = false; - } else { + if (!of_property_read_u32(q_node, "snps,priority", + &plat->rx_queues_cfg[queue].prio)) plat->rx_queues_cfg[queue].use_prio = true; - } /* RX queue specific packet type routing */ if (of_property_read_bool(q_node, "snps,route-avcp")) @@ -209,8 +196,6 @@ static int stmmac_mtl_setup(struct platform_device *pdev, plat->rx_queues_cfg[queue].pkt_route = PACKET_UPQ; else if (of_property_read_bool(q_node, "snps,route-multi-broad")) plat->rx_queues_cfg[queue].pkt_route = PACKET_MCBCQ; - else - plat->rx_queues_cfg[queue].pkt_route = 0x0; queue++; } @@ -221,9 +206,8 @@ static int stmmac_mtl_setup(struct platform_device *pdev, } /* Processing TX queues common config */ - if (of_property_read_u32(tx_node, "snps,tx-queues-to-use", - &plat->tx_queues_to_use)) - plat->tx_queues_to_use = 1; + of_property_read_u32(tx_node, "snps,tx-queues-to-use", + &plat->tx_queues_to_use); if (of_property_read_bool(tx_node, "snps,tx-sched-wrr")) plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; @@ -268,13 +252,9 @@ static int stmmac_mtl_setup(struct platform_device *pdev, plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_DCB; } - if (of_property_read_u32(q_node, "snps,priority", - &plat->tx_queues_cfg[queue].prio)) { - plat->tx_queues_cfg[queue].prio = 0; - plat->tx_queues_cfg[queue].use_prio = false; - } else { + if (!of_property_read_u32(q_node, "snps,priority", + &plat->tx_queues_cfg[queue].prio)) plat->tx_queues_cfg[queue].use_prio = true; - } plat->tx_queues_cfg[queue].coe_unsupported = of_property_read_bool(q_node, "snps,coe-unsupported"); @@ -436,7 +416,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) void *ret; int rc; - plat = devm_kzalloc(&pdev->dev, sizeof(*plat), GFP_KERNEL); + plat = stmmac_plat_dat_alloc(&pdev->dev); if (!plat) return ERR_PTR(-ENOMEM); @@ -480,13 +460,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->bus_id = ++bus_id; } - /* Default to phy auto-detection */ - plat->phy_addr = -1; - - /* Default to get clk_csr from stmmac_clk_csr_set(), - * or get clk_csr from device tree. - */ - plat->clk_csr = -1; if (of_property_read_u32(np, "snps,clk-csr", &plat->clk_csr)) of_property_read_u32(np, "clk_csr", &plat->clk_csr); @@ -515,17 +488,6 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) plat->flags |= STMMAC_FLAG_EN_TX_LPI_CLOCKGATING; } - /* Set the maxmtu to a default of JUMBO_LEN in case the - * parameter is not present in the device tree. - */ - plat->maxmtu = JUMBO_LEN; - - /* Set default value for multicast hash bins */ - plat->multicast_filter_bins = HASH_TABLE_SIZE; - - /* Set default value for unicast filter entries */ - plat->unicast_filter_entries = 1; - /* * Currently only the properties needed on SPEAr600 * are provided. All other properties should be added @@ -552,12 +514,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) &pdev->dev, plat->unicast_filter_entries); plat->multicast_filter_bins = dwmac1000_validate_mcast_bins( &pdev->dev, plat->multicast_filter_bins); - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->pmt = 1; } if (of_device_is_compatible(np, "snps,dwmac-3.40a")) { - plat->has_gmac = 1; + plat->core_type = DWMAC_CORE_GMAC; plat->enh_desc = 1; plat->tx_coe = 1; plat->bugged_jumbo = 1; @@ -565,8 +527,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) } if (of_device_compatible_match(np, stmmac_gmac4_compats)) { - plat->has_gmac4 = 1; - plat->has_gmac = 0; + plat->core_type = DWMAC_CORE_GMAC4; plat->pmt = 1; if (of_property_read_bool(np, "snps,tso")) plat->flags |= STMMAC_FLAG_TSO_EN; @@ -580,7 +541,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) } if (of_device_is_compatible(np, "snps,dwxgmac")) { - plat->has_xgmac = 1; + plat->core_type = DWMAC_CORE_XGMAC; plat->pmt = 1; if (of_property_read_bool(np, "snps,tso")) plat->flags |= STMMAC_FLAG_TSO_EN; @@ -632,7 +593,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) dev_warn(&pdev->dev, "Cannot get CSR clock\n"); plat->stmmac_clk = NULL; } - clk_prepare_enable(plat->stmmac_clk); + rc = clk_prepare_enable(plat->stmmac_clk); + if (rc < 0) + dev_warn(&pdev->dev, "Cannot enable CSR clock: %d\n", rc); } plat->pclk = devm_clk_get_optional(&pdev->dev, "pclk"); @@ -640,7 +603,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac) ret = plat->pclk; goto error_pclk_get; } - clk_prepare_enable(plat->pclk); + rc = clk_prepare_enable(plat->pclk); + if (rc < 0) { + ret = ERR_PTR(rc); + dev_err(&pdev->dev, "Cannot enable pclk: %d\n", rc); + goto error_pclk_get; + } /* Fall-back to main clock in case of no PTP ref is passed */ plat->clk_ptp_ref = devm_clk_get(&pdev->dev, "ptp_ref"); @@ -970,7 +938,7 @@ static int __maybe_unused stmmac_pltfr_noirq_suspend(struct device *dev) if (!netif_running(ndev)) return 0; - if (!stmmac_wol_enabled_mac(priv)) { + if (!priv->wolopts) { /* Disable clock in case of PWM is off */ clk_disable_unprepare(priv->plat->clk_ptp_ref); @@ -991,7 +959,7 @@ static int __maybe_unused stmmac_pltfr_noirq_resume(struct device *dev) if (!netif_running(ndev)) return 0; - if (!stmmac_wol_enabled_mac(priv)) { + if (!priv->wolopts) { /* enable the clk previously disabled */ ret = pm_runtime_force_resume(dev); if (ret) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index 993ff4e87e557..3e30172fa1294 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -57,7 +57,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) bool xmac, est_rst = false; int ret; - xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac; + xmac = dwmac_is_xmac(priv->plat->core_type); if (delta < 0) { neg_adj = 1; @@ -344,7 +344,7 @@ void stmmac_ptp_register(struct stmmac_priv *priv) /* Calculate the clock domain crossing (CDC) error if necessary */ priv->plat->cdc_error_adj = 0; - if (priv->plat->has_gmac4) + if (priv->plat->core_type == DWMAC_CORE_GMAC4) priv->plat->cdc_error_adj = (2 * NSEC_PER_SEC) / priv->plat->clk_ptp_rate; /* Update the ptp clock parameters based on feature discovery, when diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 3b4d4696afe96..d786527185999 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -262,10 +262,10 @@ static int tc_init(struct stmmac_priv *priv) unsigned int count; int ret, i; - if (dma_cap->l3l4fnum) { - priv->flow_entries_max = dma_cap->l3l4fnum; + priv->flow_entries_max = dma_cap->l3l4fnum; + if (priv->flow_entries_max) { priv->flow_entries = devm_kcalloc(priv->device, - dma_cap->l3l4fnum, + priv->flow_entries_max, sizeof(*priv->flow_entries), GFP_KERNEL); if (!priv->flow_entries) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c index ff02a79c00d4f..b18404dd5a8be 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_vlan.c @@ -122,7 +122,8 @@ static int vlan_del_hw_rx_fltr(struct net_device *dev, /* Extended Rx VLAN Filter Enable */ for (i = 0; i < hw->num_vlan; i++) { - if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid) { + if ((hw->vlan_filter[i] & VLAN_TAG_DATA_VEN) && + ((hw->vlan_filter[i] & VLAN_TAG_DATA_VID) == vid)) { ret = vlan_write_filter(dev, hw, i, 0); if (!ret) diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index 93c0a4d0e33a6..6da50f4b7c2ea 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_TI_PRUETH) += icssm-prueth.o -icssm-prueth-y := icssm/icssm_prueth.o +icssm-prueth-y := icssm/icssm_prueth.o icssm/icssm_prueth_switch.o icssm/icssm_switchdev.o obj-$(CONFIG_TI_CPSW) += cpsw-common.o obj-$(CONFIG_TI_DAVINCI_EMAC) += cpsw-common.o diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 110eb2da8dbc1..d5f358ec98205 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -1788,28 +1788,28 @@ static int am65_cpsw_nuss_ndo_slave_set_mac_address(struct net_device *ndev, } static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, - struct ifreq *ifr) + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { struct am65_cpsw_port *port = am65_ndev_to_port(ndev); u32 ts_ctrl, seq_id, ts_ctrl_ltype2, ts_vlan_ltype; - struct hwtstamp_config cfg; - if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS)) + if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS)) { + NL_SET_ERR_MSG(extack, "Time stamping is not supported"); return -EOPNOTSUPP; - - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; + } /* TX HW timestamp */ - switch (cfg.tx_type) { + switch (cfg->tx_type) { case HWTSTAMP_TX_OFF: case HWTSTAMP_TX_ON: break; default: + NL_SET_ERR_MSG(extack, "TX mode is not supported"); return -ERANGE; } - switch (cfg.rx_filter) { + switch (cfg->rx_filter) { case HWTSTAMP_FILTER_NONE: port->rx_ts_enabled = false; break; @@ -1826,17 +1826,19 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: port->rx_ts_enabled = true; - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT; break; case HWTSTAMP_FILTER_ALL: case HWTSTAMP_FILTER_SOME: case HWTSTAMP_FILTER_NTP_ALL: + NL_SET_ERR_MSG(extack, "RX filter is not supported"); return -EOPNOTSUPP; default: + NL_SET_ERR_MSG(extack, "RX filter is not supported"); return -ERANGE; } - port->tx_ts_enabled = (cfg.tx_type == HWTSTAMP_TX_ON); + port->tx_ts_enabled = (cfg->tx_type == HWTSTAMP_TX_ON); /* cfg TX timestamp */ seq_id = (AM65_CPSW_TS_SEQ_ID_OFFSET << @@ -1872,25 +1874,24 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, AM65_CPSW_PORTN_REG_TS_CTL_LTYPE2); writel(ts_ctrl, port->port_base + AM65_CPSW_PORTN_REG_TS_CTL); - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + return 0; } static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev, - struct ifreq *ifr) + struct kernel_hwtstamp_config *cfg) { struct am65_cpsw_port *port = am65_ndev_to_port(ndev); - struct hwtstamp_config cfg; if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS)) return -EOPNOTSUPP; - cfg.flags = 0; - cfg.tx_type = port->tx_ts_enabled ? + cfg->flags = 0; + cfg->tx_type = port->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - cfg.rx_filter = port->rx_ts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT | + cfg->rx_filter = port->rx_ts_enabled ? HWTSTAMP_FILTER_PTP_V2_EVENT | HWTSTAMP_FILTER_PTP_V1_L4_EVENT : HWTSTAMP_FILTER_NONE; - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + return 0; } static int am65_cpsw_nuss_ndo_slave_ioctl(struct net_device *ndev, @@ -1901,13 +1902,6 @@ static int am65_cpsw_nuss_ndo_slave_ioctl(struct net_device *ndev, if (!netif_running(ndev)) return -EINVAL; - switch (cmd) { - case SIOCSHWTSTAMP: - return am65_cpsw_nuss_hwtstamp_set(ndev, req); - case SIOCGHWTSTAMP: - return am65_cpsw_nuss_hwtstamp_get(ndev, req); - } - return phylink_mii_ioctl(port->slave.phylink, req, cmd); } @@ -1991,6 +1985,8 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_set_tx_maxrate = am65_cpsw_qos_ndo_tx_p0_set_maxrate, .ndo_bpf = am65_cpsw_ndo_bpf, .ndo_xdp_xmit = am65_cpsw_ndo_xdp_xmit, + .ndo_hwtstamp_get = am65_cpsw_nuss_hwtstamp_get, + .ndo_hwtstamp_set = am65_cpsw_nuss_hwtstamp_set, }; static void am65_cpsw_disable_phy(struct phy *phy) diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c index 68507126be8e4..48f85a3649b26 100644 --- a/drivers/net/ethernet/ti/davinci_mdio.c +++ b/drivers/net/ethernet/ti/davinci_mdio.c @@ -234,7 +234,6 @@ static int davinci_mdiobb_read_c22(struct mii_bus *bus, int phy, int reg) ret = mdiobb_read_c22(bus, phy, reg); - pm_runtime_mark_last_busy(bus->parent); pm_runtime_put_autosuspend(bus->parent); return ret; @@ -251,7 +250,6 @@ static int davinci_mdiobb_write_c22(struct mii_bus *bus, int phy, int reg, ret = mdiobb_write_c22(bus, phy, reg, val); - pm_runtime_mark_last_busy(bus->parent); pm_runtime_put_autosuspend(bus->parent); return ret; @@ -268,7 +266,6 @@ static int davinci_mdiobb_read_c45(struct mii_bus *bus, int phy, int devad, ret = mdiobb_read_c45(bus, phy, devad, reg); - pm_runtime_mark_last_busy(bus->parent); pm_runtime_put_autosuspend(bus->parent); return ret; @@ -285,7 +282,6 @@ static int davinci_mdiobb_write_c45(struct mii_bus *bus, int phy, int devad, ret = mdiobb_write_c45(bus, phy, devad, reg, val); - pm_runtime_mark_last_busy(bus->parent); pm_runtime_put_autosuspend(bus->parent); return ret; @@ -332,7 +328,6 @@ static int davinci_mdio_common_reset(struct davinci_mdio_data *data) data->bus->phy_mask = phy_mask; done: - pm_runtime_mark_last_busy(data->dev); pm_runtime_put_autosuspend(data->dev); return 0; @@ -441,7 +436,6 @@ static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg) break; } - pm_runtime_mark_last_busy(data->dev); pm_runtime_put_autosuspend(data->dev); return ret; } @@ -478,7 +472,6 @@ static int davinci_mdio_write(struct mii_bus *bus, int phy_id, break; } - pm_runtime_mark_last_busy(data->dev); pm_runtime_put_autosuspend(data->dev); return ret; @@ -548,8 +541,8 @@ static int davinci_mdio_probe(struct platform_device *pdev) struct davinci_mdio_data *data; struct resource *res; struct phy_device *phy; - int ret, addr; int autosuspend_delay_ms = -1; + int ret; data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); if (!data) @@ -652,14 +645,10 @@ static int davinci_mdio_probe(struct platform_device *pdev) goto bail_out; /* scan and dump the bus */ - for (addr = 0; addr < PHY_MAX_ADDR; addr++) { - phy = mdiobus_get_phy(data->bus, addr); - if (phy) { - dev_info(dev, "phy[%d]: device %s, driver %s\n", - phy->mdio.addr, phydev_name(phy), - phy->drv ? phy->drv->name : "unknown"); - } - } + mdiobus_for_each_phy(data->bus, phy) + dev_info(dev, "phy[%d]: device %s, driver %s\n", + phy->mdio.addr, phydev_name(phy), + phy->drv ? phy->drv->name : "unknown"); return 0; diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c index 57e5f1c88f509..0eed29d6187a6 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_common.c +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -1223,15 +1223,13 @@ void icssg_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue) } EXPORT_SYMBOL_GPL(icssg_ndo_tx_timeout); -static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr) +int icssg_ndo_set_ts_config(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) { struct prueth_emac *emac = netdev_priv(ndev); - struct hwtstamp_config config; - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - switch (config.tx_type) { + switch (config->tx_type) { case HWTSTAMP_TX_OFF: emac->tx_ts_enabled = 0; break; @@ -1242,7 +1240,7 @@ static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr) return -ERANGE; } - switch (config.rx_filter) { + switch (config->rx_filter) { case HWTSTAMP_FILTER_NONE: emac->rx_ts_enabled = 0; break; @@ -1262,43 +1260,28 @@ static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: emac->rx_ts_enabled = 1; - config.rx_filter = HWTSTAMP_FILTER_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; break; default: return -ERANGE; } - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; + return 0; } +EXPORT_SYMBOL_GPL(icssg_ndo_set_ts_config); -static int emac_get_ts_config(struct net_device *ndev, struct ifreq *ifr) +int icssg_ndo_get_ts_config(struct net_device *ndev, + struct kernel_hwtstamp_config *config) { struct prueth_emac *emac = netdev_priv(ndev); - struct hwtstamp_config config; - - config.flags = 0; - config.tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - config.rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} -int icssg_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - case SIOCGHWTSTAMP: - return emac_get_ts_config(ndev, ifr); - case SIOCSHWTSTAMP: - return emac_set_ts_config(ndev, ifr); - default: - break; - } + config->flags = 0; + config->tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + config->rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; - return phy_do_ioctl(ndev, ifr, cmd); + return 0; } -EXPORT_SYMBOL_GPL(icssg_ndo_ioctl); +EXPORT_SYMBOL_GPL(icssg_ndo_get_ts_config); void icssg_ndo_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats) diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index e42d0fdefee12..57a7d1ceab088 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -1168,7 +1168,7 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = icssg_ndo_tx_timeout, .ndo_set_rx_mode = emac_ndo_set_rx_mode, - .ndo_eth_ioctl = icssg_ndo_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_get_stats64 = icssg_ndo_get_stats64, .ndo_get_phys_port_name = icssg_ndo_get_phys_port_name, .ndo_fix_features = emac_ndo_fix_features, @@ -1176,6 +1176,8 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_vlan_rx_kill_vid = emac_ndo_vlan_rx_del_vid, .ndo_bpf = emac_ndo_bpf, .ndo_xdp_xmit = emac_xdp_xmit, + .ndo_hwtstamp_get = icssg_ndo_get_ts_config, + .ndo_hwtstamp_set = icssg_ndo_set_ts_config, }; static int prueth_netdev_init(struct prueth *prueth, @@ -1248,8 +1250,7 @@ static int prueth_netdev_init(struct prueth *prueth, } else if (of_phy_is_fixed_link(eth_node)) { ret = of_phy_register_fixed_link(eth_node); if (ret) { - ret = dev_err_probe(prueth->dev, ret, - "failed to register fixed-link phy\n"); + dev_err_probe(prueth->dev, ret, "failed to register fixed-link phy\n"); goto free; } diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index ca8a22a4a5daa..f0fa9688d9a08 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -479,7 +479,11 @@ void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num, void prueth_reset_rx_chan(struct prueth_rx_chn *chn, int num_flows, bool disable); void icssg_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue); -int icssg_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd); +int icssg_ndo_get_ts_config(struct net_device *ndev, + struct kernel_hwtstamp_config *config); +int icssg_ndo_set_ts_config(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); void icssg_ndo_get_stats64(struct net_device *ndev, struct rtnl_link_stats64 *stats); int icssg_ndo_get_phys_port_name(struct net_device *ndev, char *name, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c index 5e225310c9dea..7bb4f0d850cc7 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -747,9 +747,11 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_validate_addr = eth_validate_addr, .ndo_tx_timeout = icssg_ndo_tx_timeout, .ndo_set_rx_mode = emac_ndo_set_rx_mode_sr1, - .ndo_eth_ioctl = icssg_ndo_ioctl, + .ndo_eth_ioctl = phy_do_ioctl, .ndo_get_stats64 = icssg_ndo_get_stats64, .ndo_get_phys_port_name = icssg_ndo_get_phys_port_name, + .ndo_hwtstamp_get = icssg_ndo_get_ts_config, + .ndo_hwtstamp_set = icssg_ndo_set_ts_config, }; static int prueth_netdev_init(struct prueth *prueth, @@ -816,8 +818,7 @@ static int prueth_netdev_init(struct prueth *prueth, } else if (of_phy_is_fixed_link(eth_node)) { ret = of_phy_register_fixed_link(eth_node); if (ret) { - ret = dev_err_probe(prueth->dev, ret, - "failed to register fixed-link phy\n"); + dev_err_probe(prueth->dev, ret, "failed to register fixed-link phy\n"); goto free; } diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth.c b/drivers/net/ethernet/ti/icssm/icssm_prueth.c index 293b7af04263f..6d7e0f5482cc3 100644 --- a/drivers/net/ethernet/ti/icssm/icssm_prueth.c +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth.c @@ -29,6 +29,8 @@ #include #include "icssm_prueth.h" +#include "icssm_prueth_switch.h" +#include "icssm_vlan_mcast_filter_mmap.h" #include "../icssg/icssg_mii_rt.h" #include "../icssg/icss_iep.h" @@ -145,7 +147,7 @@ static const struct prueth_queue_info queue_infos[][NUM_QUEUES] = { }, }; -static const struct prueth_queue_desc queue_descs[][NUM_QUEUES] = { +const struct prueth_queue_desc queue_descs[][NUM_QUEUES] = { [PRUETH_PORT_QUEUE_HOST] = { { .rd_ptr = P0_Q1_BD_OFFSET, .wr_ptr = P0_Q1_BD_OFFSET, }, { .rd_ptr = P0_Q2_BD_OFFSET, .wr_ptr = P0_Q2_BD_OFFSET, }, @@ -205,9 +207,9 @@ static void icssm_prueth_hostconfig(struct prueth *prueth) static void icssm_prueth_mii_init(struct prueth *prueth) { + u32 txcfg_reg, txcfg, txcfg2; struct regmap *mii_rt; u32 rxcfg_reg, rxcfg; - u32 txcfg_reg, txcfg; mii_rt = prueth->mii_rt; @@ -235,17 +237,23 @@ static void icssm_prueth_mii_init(struct prueth *prueth) (TX_START_DELAY << PRUSS_MII_RT_TXCFG_TX_START_DELAY_SHIFT) | (TX_CLK_DELAY_100M << PRUSS_MII_RT_TXCFG_TX_CLK_DELAY_SHIFT); + txcfg2 = txcfg; + if (!PRUETH_IS_EMAC(prueth)) + txcfg2 |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL; + /* Configuration of Port 0 Tx */ txcfg_reg = PRUSS_MII_RT_TXCFG0; - regmap_write(mii_rt, txcfg_reg, txcfg); + regmap_write(mii_rt, txcfg_reg, txcfg2); - txcfg |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL; + txcfg2 = txcfg; + if (PRUETH_IS_EMAC(prueth)) + txcfg2 |= PRUSS_MII_RT_TXCFG_TX_MUX_SEL; /* Configuration of Port 1 Tx */ txcfg_reg = PRUSS_MII_RT_TXCFG1; - regmap_write(mii_rt, txcfg_reg, txcfg); + regmap_write(mii_rt, txcfg_reg, txcfg2); txcfg_reg = PRUSS_MII_RT_RX_FRMS0; @@ -292,7 +300,10 @@ static void icssm_prueth_hostinit(struct prueth *prueth) icssm_prueth_clearmem(prueth, PRUETH_MEM_DRAM1); /* Initialize host queues in shared RAM */ - icssm_prueth_hostconfig(prueth); + if (!PRUETH_IS_EMAC(prueth)) + icssm_prueth_sw_hostconfig(prueth); + else + icssm_prueth_hostconfig(prueth); /* Configure MII_RT */ icssm_prueth_mii_init(prueth); @@ -499,19 +510,24 @@ static int icssm_prueth_tx_enqueue(struct prueth_emac *emac, struct prueth_queue_desc __iomem *queue_desc; const struct prueth_queue_info *txqueue; struct net_device *ndev = emac->ndev; + struct prueth *prueth = emac->prueth; unsigned int buffer_desc_count; int free_blocks, update_block; bool buffer_wrapped = false; int write_block, read_block; void *src_addr, *dst_addr; int pkt_block_size; + void __iomem *sram; void __iomem *dram; int txport, pktlen; u16 update_wr_ptr; u32 wr_buf_desc; void *ocmc_ram; - dram = emac->prueth->mem[emac->dram].va; + if (!PRUETH_IS_EMAC(prueth)) + dram = prueth->mem[PRUETH_MEM_DRAM1].va; + else + dram = emac->prueth->mem[emac->dram].va; if (eth_skb_pad(skb)) { if (netif_msg_tx_err(emac) && net_ratelimit()) netdev_err(ndev, "packet pad failed\n"); @@ -524,7 +540,10 @@ static int icssm_prueth_tx_enqueue(struct prueth_emac *emac, pktlen = skb->len; /* Get the tx queue */ queue_desc = emac->tx_queue_descs + queue_id; - txqueue = &queue_infos[txport][queue_id]; + if (!PRUETH_IS_EMAC(prueth)) + txqueue = &sw_queue_infos[txport][queue_id]; + else + txqueue = &queue_infos[txport][queue_id]; buffer_desc_count = icssm_get_buff_desc_count(txqueue); @@ -590,7 +609,11 @@ static int icssm_prueth_tx_enqueue(struct prueth_emac *emac, /* update first buffer descriptor */ wr_buf_desc = (pktlen << PRUETH_BD_LENGTH_SHIFT) & PRUETH_BD_LENGTH_MASK; - writel(wr_buf_desc, dram + readw(&queue_desc->wr_ptr)); + sram = prueth->mem[PRUETH_MEM_SHARED_RAM].va; + if (!PRUETH_IS_EMAC(prueth)) + writel(wr_buf_desc, sram + readw(&queue_desc->wr_ptr)); + else + writel(wr_buf_desc, dram + readw(&queue_desc->wr_ptr)); /* update the write pointer in this queue descriptor, the firmware * polls for this change so this will signal the start of transmission @@ -604,7 +627,6 @@ static int icssm_prueth_tx_enqueue(struct prueth_emac *emac, void icssm_parse_packet_info(struct prueth *prueth, u32 buffer_descriptor, struct prueth_packet_info *pkt_info) { - pkt_info->shadow = !!(buffer_descriptor & PRUETH_BD_SHADOW_MASK); pkt_info->port = (buffer_descriptor & PRUETH_BD_PORT_MASK) >> PRUETH_BD_PORT_SHIFT; pkt_info->length = (buffer_descriptor & PRUETH_BD_LENGTH_MASK) >> @@ -713,11 +735,19 @@ int icssm_emac_rx_packet(struct prueth_emac *emac, u16 *bd_rd_ptr, src_addr += actual_pkt_len; } + if (PRUETH_IS_SWITCH(emac->prueth)) { + skb->offload_fwd_mark = emac->offload_fwd_mark; + if (!pkt_info->lookup_success) + icssm_prueth_sw_learn_fdb(emac, skb->data + ETH_ALEN); + } + skb_put(skb, actual_pkt_len); /* send packet up the stack */ skb->protocol = eth_type_trans(skb, ndev); + local_bh_disable(); netif_receive_skb(skb); + local_bh_enable(); /* update stats */ emac->stats.rx_bytes += actual_pkt_len; @@ -743,6 +773,7 @@ static int icssm_emac_rx_packets(struct prueth_emac *emac, int budget) shared_ram = emac->prueth->mem[PRUETH_MEM_SHARED_RAM].va; + /* Start and end queue is made common for EMAC, RSTP */ start_queue = emac->rx_queue_start; end_queue = emac->rx_queue_end; @@ -753,8 +784,10 @@ static int icssm_emac_rx_packets(struct prueth_emac *emac, int budget) /* search host queues for packets */ for (i = start_queue; i <= end_queue; i++) { queue_desc = emac->rx_queue_descs + i; - rxqueue = &queue_infos[PRUETH_PORT_HOST][i]; - + if (PRUETH_IS_SWITCH(emac->prueth)) + rxqueue = &sw_queue_infos[PRUETH_PORT_HOST][i]; + else + rxqueue = &queue_infos[PRUETH_PORT_HOST][i]; overflow_cnt = readb(&queue_desc->overflow_cnt); if (overflow_cnt > 0) { emac->stats.rx_over_errors += overflow_cnt; @@ -879,6 +912,13 @@ static int icssm_emac_request_irqs(struct prueth_emac *emac) return ret; } +/* Function to free memory related to sw */ +static void icssm_prueth_free_memory(struct prueth *prueth) +{ + if (PRUETH_IS_SWITCH(prueth)) + icssm_prueth_sw_free_fdb_table(prueth); +} + static void icssm_ptp_dram_init(struct prueth_emac *emac) { void __iomem *sram = emac->prueth->mem[PRUETH_MEM_SHARED_RAM].va; @@ -941,20 +981,38 @@ static int icssm_emac_ndo_open(struct net_device *ndev) if (!prueth->emac_configured) icssm_prueth_init_ethernet_mode(prueth); - icssm_prueth_emac_config(emac); + /* reset and start PRU firmware */ + if (PRUETH_IS_SWITCH(prueth)) { + ret = icssm_prueth_sw_emac_config(emac); + if (ret) + return ret; + + ret = icssm_prueth_sw_init_fdb_table(prueth); + if (ret) + return ret; + } else { + icssm_prueth_emac_config(emac); + } if (!prueth->emac_configured) { icssm_ptp_dram_init(emac); ret = icss_iep_init(prueth->iep, NULL, NULL, 0); if (ret) { netdev_err(ndev, "Failed to initialize iep: %d\n", ret); - goto iep_exit; + goto free_mem; } } - ret = icssm_emac_set_boot_pru(emac, ndev); - if (ret) - goto iep_exit; + if (!PRUETH_IS_EMAC(prueth)) { + ret = icssm_prueth_sw_boot_prus(prueth, ndev); + if (ret) + goto iep_exit; + } else { + /* boot the PRU */ + ret = icssm_emac_set_boot_pru(emac, ndev); + if (ret) + goto iep_exit; + } ret = icssm_emac_request_irqs(emac); if (ret) @@ -969,19 +1027,25 @@ static int icssm_emac_ndo_open(struct net_device *ndev) icssm_prueth_port_enable(emac, true); prueth->emac_configured |= BIT(emac->port_id); - + if (PRUETH_IS_SWITCH(prueth)) + icssm_prueth_sw_port_set_stp_state(prueth, emac->port_id, + BR_STATE_LEARNING); if (netif_msg_drv(emac)) dev_notice(&ndev->dev, "started\n"); return 0; rproc_shutdown: - rproc_shutdown(emac->pru); + if (!PRUETH_IS_EMAC(prueth)) + icssm_prueth_sw_shutdown_prus(emac, ndev); + else + rproc_shutdown(emac->pru); iep_exit: if (!prueth->emac_configured) icss_iep_exit(prueth->iep); - +free_mem: + icssm_prueth_free_memory(emac->prueth); return ret; } @@ -1010,17 +1074,77 @@ static int icssm_emac_ndo_stop(struct net_device *ndev) hrtimer_cancel(&emac->tx_hrtimer); /* stop the PRU */ - rproc_shutdown(emac->pru); + if (!PRUETH_IS_EMAC(prueth)) + icssm_prueth_sw_shutdown_prus(emac, ndev); + else + rproc_shutdown(emac->pru); + + /* free table memory of the switch */ + if (PRUETH_IS_SWITCH(emac->prueth)) + icssm_prueth_sw_free_fdb_table(prueth); /* free rx interrupts */ free_irq(emac->rx_irq, ndev); + /* free memory related to sw */ + icssm_prueth_free_memory(emac->prueth); + + if (!prueth->emac_configured) + icss_iep_exit(prueth->iep); + if (netif_msg_drv(emac)) dev_notice(&ndev->dev, "stopped\n"); return 0; } +static int icssm_prueth_change_mode(struct prueth *prueth, + enum pruss_ethtype mode) +{ + bool portstatus[PRUETH_NUM_MACS]; + struct prueth_emac *emac; + struct net_device *ndev; + int i, ret; + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + emac = prueth->emac[i]; + ndev = emac->ndev; + + portstatus[i] = netif_running(ndev); + if (!portstatus[i]) + continue; + + ret = ndev->netdev_ops->ndo_stop(ndev); + if (ret < 0) { + netdev_err(ndev, "failed to stop: %d", ret); + return ret; + } + } + + if (mode == PRUSS_ETHTYPE_EMAC || mode == PRUSS_ETHTYPE_SWITCH) { + prueth->eth_type = mode; + } else { + dev_err(prueth->dev, "unknown mode\n"); + return -EINVAL; + } + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + emac = prueth->emac[i]; + ndev = emac->ndev; + + if (!portstatus[i]) + continue; + + ret = ndev->netdev_ops->ndo_open(ndev); + if (ret < 0) { + netdev_err(ndev, "failed to start: %d", ret); + return ret; + } + } + + return 0; +} + /* VLAN-tag PCP to priority queue map for EMAC/Switch/HSR/PRP used by driver * Index is PCP val / 2. * low - pcp 0..3 maps to Q4 for Host @@ -1131,11 +1255,183 @@ static void icssm_emac_ndo_get_stats64(struct net_device *ndev, stats->rx_length_errors = emac->stats.rx_length_errors; } +/* enable/disable MC filter */ +static void icssm_emac_mc_filter_ctrl(struct prueth_emac *emac, bool enable) +{ + struct prueth *prueth = emac->prueth; + void __iomem *mc_filter_ctrl; + void __iomem *ram; + u32 reg; + + ram = prueth->mem[emac->dram].va; + mc_filter_ctrl = ram + ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_OFFSET; + + if (enable) + reg = ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_ENABLED; + else + reg = ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_DISABLED; + + writeb(reg, mc_filter_ctrl); +} + +/* reset MC filter bins */ +static void icssm_emac_mc_filter_reset(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + void __iomem *mc_filter_tbl; + u32 mc_filter_tbl_base; + void __iomem *ram; + + ram = prueth->mem[emac->dram].va; + mc_filter_tbl_base = ICSS_EMAC_FW_MULTICAST_FILTER_TABLE; + + mc_filter_tbl = ram + mc_filter_tbl_base; + memset_io(mc_filter_tbl, 0, ICSS_EMAC_FW_MULTICAST_TABLE_SIZE_BYTES); +} + +/* set MC filter hashmask */ +static void icssm_emac_mc_filter_hashmask + (struct prueth_emac *emac, + u8 mask[ICSS_EMAC_FW_MULTICAST_FILTER_MASK_SIZE_BYTES]) +{ + struct prueth *prueth = emac->prueth; + void __iomem *mc_filter_mask; + void __iomem *ram; + + ram = prueth->mem[emac->dram].va; + + mc_filter_mask = ram + ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OFFSET; + memcpy_toio(mc_filter_mask, mask, + ICSS_EMAC_FW_MULTICAST_FILTER_MASK_SIZE_BYTES); +} + +static void icssm_emac_mc_filter_bin_update(struct prueth_emac *emac, u8 hash, + u8 val) +{ + struct prueth *prueth = emac->prueth; + void __iomem *mc_filter_tbl; + void __iomem *ram; + + ram = prueth->mem[emac->dram].va; + + mc_filter_tbl = ram + ICSS_EMAC_FW_MULTICAST_FILTER_TABLE; + writeb(val, mc_filter_tbl + hash); +} + +void icssm_emac_mc_filter_bin_allow(struct prueth_emac *emac, u8 hash) +{ + icssm_emac_mc_filter_bin_update + (emac, hash, + ICSS_EMAC_FW_MULTICAST_FILTER_HOST_RCV_ALLOWED); +} + +void icssm_emac_mc_filter_bin_disallow(struct prueth_emac *emac, u8 hash) +{ + icssm_emac_mc_filter_bin_update + (emac, hash, + ICSS_EMAC_FW_MULTICAST_FILTER_HOST_RCV_NOT_ALLOWED); +} + +u8 icssm_emac_get_mc_hash(u8 *mac, u8 *mask) +{ + u8 hash; + int j; + + for (j = 0, hash = 0; j < ETH_ALEN; j++) + hash ^= (mac[j] & mask[j]); + + return hash; +} + +/** + * icssm_emac_ndo_set_rx_mode - EMAC set receive mode function + * @ndev: The EMAC network adapter + * + * Called when system wants to set the receive mode of the device. + * + */ +static void icssm_emac_ndo_set_rx_mode(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + bool promisc = ndev->flags & IFF_PROMISC; + struct netdev_hw_addr *ha; + struct prueth *prueth; + unsigned long flags; + void __iomem *sram; + u32 mask, reg; + u8 hash; + + prueth = emac->prueth; + sram = prueth->mem[PRUETH_MEM_SHARED_RAM].va; + reg = readl(sram + EMAC_PROMISCUOUS_MODE_OFFSET); + + /* It is a shared table. So lock the access */ + spin_lock_irqsave(&emac->addr_lock, flags); + + /* Disable and reset multicast filter, allows allmulti */ + icssm_emac_mc_filter_ctrl(emac, false); + icssm_emac_mc_filter_reset(emac); + icssm_emac_mc_filter_hashmask(emac, emac->mc_filter_mask); + + if (PRUETH_IS_EMAC(prueth)) { + switch (emac->port_id) { + case PRUETH_PORT_MII0: + mask = EMAC_P1_PROMISCUOUS_BIT; + break; + case PRUETH_PORT_MII1: + mask = EMAC_P2_PROMISCUOUS_BIT; + break; + default: + netdev_err(ndev, "%s: invalid port\n", __func__); + goto unlock; + } + + if (promisc) { + /* Enable promiscuous mode */ + reg |= mask; + } else { + /* Disable promiscuous mode */ + reg &= ~mask; + } + + writel(reg, sram + EMAC_PROMISCUOUS_MODE_OFFSET); + + if (promisc) + goto unlock; + } + + if (ndev->flags & IFF_ALLMULTI && !PRUETH_IS_SWITCH(prueth)) + goto unlock; + + icssm_emac_mc_filter_ctrl(emac, true); /* all multicast blocked */ + + if (netdev_mc_empty(ndev)) + goto unlock; + + netdev_for_each_mc_addr(ha, ndev) { + hash = icssm_emac_get_mc_hash(ha->addr, emac->mc_filter_mask); + icssm_emac_mc_filter_bin_allow(emac, hash); + } + + /* Add bridge device's MC addresses as well */ + if (prueth->hw_bridge_dev) { + netdev_for_each_mc_addr(ha, prueth->hw_bridge_dev) { + hash = icssm_emac_get_mc_hash(ha->addr, + emac->mc_filter_mask); + icssm_emac_mc_filter_bin_allow(emac, hash); + } + } + +unlock: + spin_unlock_irqrestore(&emac->addr_lock, flags); +} + static const struct net_device_ops emac_netdev_ops = { .ndo_open = icssm_emac_ndo_open, .ndo_stop = icssm_emac_ndo_stop, .ndo_start_xmit = icssm_emac_ndo_start_xmit, .ndo_get_stats64 = icssm_emac_ndo_get_stats64, + .ndo_set_rx_mode = icssm_emac_ndo_set_rx_mode, }; /* get emac_port corresponding to eth_node name */ @@ -1188,6 +1484,7 @@ static enum hrtimer_restart icssm_emac_tx_timer_callback(struct hrtimer *timer) static int icssm_prueth_netdev_init(struct prueth *prueth, struct device_node *eth_node) { + const struct prueth_private_data *fw_data = prueth->fw_data; struct prueth_emac *emac; struct net_device *ndev; enum prueth_port port; @@ -1212,6 +1509,7 @@ static int icssm_prueth_netdev_init(struct prueth *prueth, emac->prueth = prueth; emac->ndev = ndev; emac->port_id = port; + memset(&emac->mc_filter_mask[0], 0xff, ETH_ALEN); /* by default eth_type is EMAC */ switch (port) { @@ -1274,6 +1572,14 @@ static int icssm_prueth_netdev_init(struct prueth *prueth, phy_remove_link_mode(emac->phydev, ETHTOOL_LINK_MODE_Pause_BIT); phy_remove_link_mode(emac->phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT); + /* Protocol switching + * Enabling L2 Firmware offloading + */ + if (fw_data->support_switch) { + ndev->features |= NETIF_F_HW_L2FW_DOFFLOAD; + ndev->hw_features |= NETIF_F_HW_L2FW_DOFFLOAD; + } + ndev->dev.of_node = eth_node; ndev->netdev_ops = &emac_netdev_ops; @@ -1310,6 +1616,151 @@ static void icssm_prueth_netdev_exit(struct prueth *prueth, prueth->emac[mac] = NULL; } +bool icssm_prueth_sw_port_dev_check(const struct net_device *ndev) +{ + if (ndev->netdev_ops != &emac_netdev_ops) + return false; + + if (ndev->features & NETIF_F_HW_L2FW_DOFFLOAD) + return true; + + return false; +} + +static int icssm_prueth_port_offload_fwd_mark_update(struct prueth *prueth) +{ + int set_val = 0; + int i, ret = 0; + u8 all_slaves; + + all_slaves = BIT(PRUETH_PORT_MII0) | BIT(PRUETH_PORT_MII1); + + if (prueth->br_members == all_slaves) + set_val = 1; + + dev_dbg(prueth->dev, "set offload_fwd_mark %d, mbrs=0x%x\n", + set_val, prueth->br_members); + + for (i = 0; i < PRUETH_NUM_MACS; i++) + prueth->emac[i]->offload_fwd_mark = set_val; + + /* Bridge is created, load switch firmware, + * if not already in that mode + */ + if (set_val && !PRUETH_IS_SWITCH(prueth)) { + ret = icssm_prueth_change_mode(prueth, PRUSS_ETHTYPE_SWITCH); + if (ret < 0) + dev_err(prueth->dev, "Failed to enable Switch mode\n"); + else + dev_info(prueth->dev, + "TI PRU ethernet now in Switch mode\n"); + } + + /* Bridge is deleted, switch to Dual EMAC mode */ + if (!prueth->br_members && !PRUETH_IS_EMAC(prueth)) { + ret = icssm_prueth_change_mode(prueth, PRUSS_ETHTYPE_EMAC); + if (ret < 0) + dev_err(prueth->dev, "Failed to enable Dual EMAC mode\n"); + else + dev_info(prueth->dev, + "TI PRU ethernet now in Dual EMAC mode\n"); + } + + return ret; +} + +static int icssm_prueth_ndev_port_link(struct net_device *ndev, + struct net_device *br_ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int ret = 0; + + dev_dbg(prueth->dev, "%s: br_mbrs=0x%x %s\n", + __func__, prueth->br_members, ndev->name); + + if (!prueth->br_members) { + prueth->hw_bridge_dev = br_ndev; + } else { + /* This is adding the port to a second bridge, + * this is unsupported + */ + if (prueth->hw_bridge_dev != br_ndev) + return -EOPNOTSUPP; + } + + prueth->br_members |= BIT(emac->port_id); + + ret = icssm_prueth_port_offload_fwd_mark_update(prueth); + + return ret; +} + +static int icssm_prueth_ndev_port_unlink(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int ret = 0; + + dev_dbg(prueth->dev, "emac_sw_ndev_port_unlink\n"); + + prueth->br_members &= ~BIT(emac->port_id); + + ret = icssm_prueth_port_offload_fwd_mark_update(prueth); + + if (!prueth->br_members) + prueth->hw_bridge_dev = NULL; + + return ret; +} + +static int icssm_prueth_ndev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(ptr); + struct netdev_notifier_changeupper_info *info; + int ret = NOTIFY_DONE; + + if (!icssm_prueth_sw_port_dev_check(ndev)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_CHANGEUPPER: + info = ptr; + if (netif_is_bridge_master(info->upper_dev)) { + if (info->linking) + ret = icssm_prueth_ndev_port_link + (ndev, info->upper_dev); + else + ret = icssm_prueth_ndev_port_unlink(ndev); + } + break; + default: + return NOTIFY_DONE; + } + + return notifier_from_errno(ret); +} + +static int icssm_prueth_register_notifiers(struct prueth *prueth) +{ + int ret = 0; + + prueth->prueth_netdevice_nb.notifier_call = icssm_prueth_ndev_event; + ret = register_netdevice_notifier(&prueth->prueth_netdevice_nb); + if (ret) { + dev_err(prueth->dev, + "register netdevice notifier failed ret: %d\n", ret); + return ret; + } + + ret = icssm_prueth_sw_register_notifiers(prueth); + if (ret) + unregister_netdevice_notifier(&prueth->prueth_netdevice_nb); + + return ret; +} + static int icssm_prueth_probe(struct platform_device *pdev) { struct device_node *eth0_node = NULL, *eth1_node = NULL; @@ -1529,6 +1980,12 @@ static int icssm_prueth_probe(struct platform_device *pdev) prueth->emac[PRUETH_MAC1]->ndev; } + ret = icssm_prueth_register_notifiers(prueth); + if (ret) { + dev_err(dev, "can't register switchdev notifiers"); + goto netdev_unregister; + } + dev_info(dev, "TI PRU ethernet driver initialized: %s EMAC mode\n", (!eth0_node || !eth1_node) ? "single" : "dual"); @@ -1589,6 +2046,9 @@ static void icssm_prueth_remove(struct platform_device *pdev) struct device_node *eth_node; int i; + unregister_netdevice_notifier(&prueth->prueth_netdevice_nb); + icssm_prueth_sw_unregister_notifiers(prueth); + for (i = 0; i < PRUETH_NUM_MACS; i++) { if (!prueth->registered_netdevs[i]) continue; @@ -1688,11 +2148,16 @@ static struct prueth_private_data am335x_prueth_pdata = { .fw_pru[PRUSS_PRU0] = { .fw_name[PRUSS_ETHTYPE_EMAC] = "ti-pruss/am335x-pru0-prueth-fw.elf", + .fw_name[PRUSS_ETHTYPE_SWITCH] = + "ti-pruss/am335x-pru0-prusw-fw.elf", }, .fw_pru[PRUSS_PRU1] = { .fw_name[PRUSS_ETHTYPE_EMAC] = "ti-pruss/am335x-pru1-prueth-fw.elf", + .fw_name[PRUSS_ETHTYPE_SWITCH] = + "ti-pruss/am335x-pru1-prusw-fw.elf", }, + .support_switch = true, }; /* AM437x SoC-specific firmware data */ @@ -1701,11 +2166,16 @@ static struct prueth_private_data am437x_prueth_pdata = { .fw_pru[PRUSS_PRU0] = { .fw_name[PRUSS_ETHTYPE_EMAC] = "ti-pruss/am437x-pru0-prueth-fw.elf", + .fw_name[PRUSS_ETHTYPE_SWITCH] = + "ti-pruss/am437x-pru0-prusw-fw.elf", }, .fw_pru[PRUSS_PRU1] = { .fw_name[PRUSS_ETHTYPE_EMAC] = "ti-pruss/am437x-pru1-prueth-fw.elf", + .fw_name[PRUSS_ETHTYPE_SWITCH] = + "ti-pruss/am437x-pru1-prusw-fw.elf", }, + .support_switch = true, }; /* AM57xx SoC-specific firmware data */ @@ -1714,11 +2184,17 @@ static struct prueth_private_data am57xx_prueth_pdata = { .fw_pru[PRUSS_PRU0] = { .fw_name[PRUSS_ETHTYPE_EMAC] = "ti-pruss/am57xx-pru0-prueth-fw.elf", + .fw_name[PRUSS_ETHTYPE_SWITCH] = + "ti-pruss/am57xx-pru0-prusw-fw.elf", }, .fw_pru[PRUSS_PRU1] = { .fw_name[PRUSS_ETHTYPE_EMAC] = "ti-pruss/am57xx-pru1-prueth-fw.elf", + .fw_name[PRUSS_ETHTYPE_SWITCH] = + "ti-pruss/am57xx-pru1-prusw-fw.elf", + }, + .support_switch = true, }; static const struct of_device_id prueth_dt_match[] = { diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth.h b/drivers/net/ethernet/ti/icssm/icssm_prueth.h index 8e7e0af081449..a4e3d0ac96c7e 100644 --- a/drivers/net/ethernet/ti/icssm/icssm_prueth.h +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth.h @@ -15,6 +15,7 @@ #include "icssm_switch.h" #include "icssm_prueth_ptp.h" +#include "icssm_prueth_fdb_tbl.h" /* ICSSM size of redundancy tag */ #define ICSSM_LRE_TAG_SIZE 6 @@ -177,14 +178,23 @@ enum pruss_device { PRUSS_K2G }; +/* Firmware offsets/size information */ +struct prueth_fw_offsets { + u32 mc_ctrl_byte; + u32 mc_filter_mask; + u32 mc_filter_tbl; +}; + /** * struct prueth_private_data - PRU Ethernet private data * @driver_data: PRU Ethernet device name * @fw_pru: firmware names to be used for PRUSS ethernet usecases + * @support_switch: boolean to indicate if switch is enabled */ struct prueth_private_data { enum pruss_device driver_data; const struct prueth_firmware fw_pru[PRUSS_NUM_PRUS]; + bool support_switch; }; struct prueth_emac_stats { @@ -221,15 +231,18 @@ struct prueth_emac { const char *phy_id; u32 msg_enable; u8 mac_addr[6]; + unsigned char mc_filter_mask[ETH_ALEN]; /* for multicast filtering */ phy_interface_t phy_if; /* spin lock used to protect * during link configuration */ spinlock_t lock; + spinlock_t addr_lock; /* serialize access to VLAN/MC filter table */ struct hrtimer tx_hrtimer; struct prueth_emac_stats stats; + int offload_fwd_mark; }; struct prueth { @@ -248,15 +261,27 @@ struct prueth { struct prueth_emac *emac[PRUETH_NUM_MACS]; struct net_device *registered_netdevs[PRUETH_NUM_MACS]; + struct net_device *hw_bridge_dev; + struct fdb_tbl *fdb_tbl; + + struct notifier_block prueth_netdevice_nb; + struct notifier_block prueth_switchdev_nb; + struct notifier_block prueth_switchdev_bl_nb; + unsigned int eth_type; size_t ocmc_ram_size; u8 emac_configured; + u8 br_members; }; +extern const struct prueth_queue_desc queue_descs[][NUM_QUEUES]; + void icssm_parse_packet_info(struct prueth *prueth, u32 buffer_descriptor, struct prueth_packet_info *pkt_info); int icssm_emac_rx_packet(struct prueth_emac *emac, u16 *bd_rd_ptr, struct prueth_packet_info *pkt_info, const struct prueth_queue_info *rxqueue); - +void icssm_emac_mc_filter_bin_allow(struct prueth_emac *emac, u8 hash); +void icssm_emac_mc_filter_bin_disallow(struct prueth_emac *emac, u8 hash); +u8 icssm_emac_get_mc_hash(u8 *mac, u8 *mask); #endif /* __NET_TI_PRUETH_H */ diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth_fdb_tbl.h b/drivers/net/ethernet/ti/icssm/icssm_prueth_fdb_tbl.h new file mode 100644 index 0000000000000..9089259d96ea5 --- /dev/null +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth_fdb_tbl.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2019-2021 Texas Instruments Incorporated - https://www.ti.com */ +#ifndef __NET_TI_PRUSS_FDB_TBL_H +#define __NET_TI_PRUSS_FDB_TBL_H + +#include +#include +#include "icssm_prueth.h" + +/* 4 bytes */ +struct fdb_index_tbl_entry { + /* Bucket Table index of first Bucket with this MAC address */ + u16 bucket_idx; + u16 bucket_entries; /* Number of entries in this bucket */ +}; + +/* 4 * 256 = 1024 = 0x200 bytes */ +struct fdb_index_array { + struct fdb_index_tbl_entry index_tbl_entry[FDB_INDEX_TBL_MAX_ENTRIES]; +}; + +/* 10 bytes */ +struct fdb_mac_tbl_entry { + u8 mac[ETH_ALEN]; + u16 age; + u8 port; /* 0 based: 0=port1, 1=port2 */ + union { + struct { + u8 is_static:1; + u8 active:1; + }; + u8 flags; + }; +}; + +/* 10 * 256 = 2560 = 0xa00 bytes */ +struct fdb_mac_tbl_array { + struct fdb_mac_tbl_entry mac_tbl_entry[FDB_MAC_TBL_MAX_ENTRIES]; +}; + +/* 1 byte */ +struct fdb_stp_config { + u8 state; /* per-port STP state (defined in FW header) */ +}; + +/* 1 byte */ +struct fdb_flood_config { + u8 host_flood_enable:1; + u8 port1_flood_enable:1; + u8 port2_flood_enable:1; +}; + +/* 2 byte */ +struct fdb_arbitration { + u8 host_lock; + u8 pru_locks; +}; + +struct fdb_tbl { + /* fdb index table */ + struct fdb_index_array __iomem *index_a; + /* fdb MAC table */ + struct fdb_mac_tbl_array __iomem *mac_tbl_a; + /* port 1 stp config */ + struct fdb_stp_config __iomem *port1_stp_cfg; + /* port 2 stp config */ + struct fdb_stp_config __iomem *port2_stp_cfg; + /* per-port flood enable */ + struct fdb_flood_config __iomem *flood_enable_flags; + /* fdb locking mechanism */ + struct fdb_arbitration __iomem *locks; + /* total number of entries in hash table */ + u16 total_entries; +}; + +#endif diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth_switch.c b/drivers/net/ethernet/ti/icssm/icssm_prueth_switch.c new file mode 100644 index 0000000000000..5aef2829d8a90 --- /dev/null +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth_switch.c @@ -0,0 +1,1050 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Texas Instruments PRUETH Switch Driver + * + * Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com + */ +#include +#include +#include +#include +#include "icssm_prueth.h" +#include "icssm_prueth_switch.h" +#include "icssm_prueth_fdb_tbl.h" + +#define FDB_IDX_TBL_ENTRY(n) (&prueth->fdb_tbl->index_a->index_tbl_entry[n]) + +#define FDB_MAC_TBL_ENTRY(n) (&prueth->fdb_tbl->mac_tbl_a->mac_tbl_entry[n]) + +#define FLAG_IS_STATIC BIT(0) +#define FLAG_ACTIVE BIT(1) + +#define FDB_LEARN 1 +#define FDB_PURGE 2 + +struct icssm_prueth_sw_fdb_work { + struct work_struct work; + struct prueth_emac *emac; + u8 addr[ETH_ALEN]; + int event; +}; + +const struct prueth_queue_info sw_queue_infos[][NUM_QUEUES] = { + [PRUETH_PORT_QUEUE_HOST] = { + [PRUETH_QUEUE1] = { + P0_Q1_BUFFER_OFFSET, + P0_QUEUE_DESC_OFFSET, + P0_Q1_BD_OFFSET, + P0_Q1_BD_OFFSET + ((HOST_QUEUE_1_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE2] = { + P0_Q2_BUFFER_OFFSET, + P0_QUEUE_DESC_OFFSET + 8, + P0_Q2_BD_OFFSET, + P0_Q2_BD_OFFSET + ((HOST_QUEUE_2_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE3] = { + P0_Q3_BUFFER_OFFSET, + P0_QUEUE_DESC_OFFSET + 16, + P0_Q3_BD_OFFSET, + P0_Q3_BD_OFFSET + ((HOST_QUEUE_3_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE4] = { + P0_Q4_BUFFER_OFFSET, + P0_QUEUE_DESC_OFFSET + 24, + P0_Q4_BD_OFFSET, + P0_Q4_BD_OFFSET + ((HOST_QUEUE_4_SIZE - 1) * BD_SIZE), + }, + }, + [PRUETH_PORT_QUEUE_MII0] = { + [PRUETH_QUEUE1] = { + P1_Q1_BUFFER_OFFSET, + P1_Q1_BUFFER_OFFSET + + ((QUEUE_1_SIZE - 1) * ICSS_BLOCK_SIZE), + P1_Q1_BD_OFFSET, + P1_Q1_BD_OFFSET + ((QUEUE_1_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE2] = { + P1_Q2_BUFFER_OFFSET, + P1_Q2_BUFFER_OFFSET + + ((QUEUE_2_SIZE - 1) * ICSS_BLOCK_SIZE), + P1_Q2_BD_OFFSET, + P1_Q2_BD_OFFSET + ((QUEUE_2_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE3] = { + P1_Q3_BUFFER_OFFSET, + P1_Q3_BUFFER_OFFSET + + ((QUEUE_3_SIZE - 1) * ICSS_BLOCK_SIZE), + P1_Q3_BD_OFFSET, + P1_Q3_BD_OFFSET + ((QUEUE_3_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE4] = { + P1_Q4_BUFFER_OFFSET, + P1_Q4_BUFFER_OFFSET + + ((QUEUE_4_SIZE - 1) * ICSS_BLOCK_SIZE), + P1_Q4_BD_OFFSET, + P1_Q4_BD_OFFSET + ((QUEUE_4_SIZE - 1) * BD_SIZE), + }, + }, + [PRUETH_PORT_QUEUE_MII1] = { + [PRUETH_QUEUE1] = { + P2_Q1_BUFFER_OFFSET, + P2_Q1_BUFFER_OFFSET + + ((QUEUE_1_SIZE - 1) * ICSS_BLOCK_SIZE), + P2_Q1_BD_OFFSET, + P2_Q1_BD_OFFSET + ((QUEUE_1_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE2] = { + P2_Q2_BUFFER_OFFSET, + P2_Q2_BUFFER_OFFSET + + ((QUEUE_2_SIZE - 1) * ICSS_BLOCK_SIZE), + P2_Q2_BD_OFFSET, + P2_Q2_BD_OFFSET + ((QUEUE_2_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE3] = { + P2_Q3_BUFFER_OFFSET, + P2_Q3_BUFFER_OFFSET + + ((QUEUE_3_SIZE - 1) * ICSS_BLOCK_SIZE), + P2_Q3_BD_OFFSET, + P2_Q3_BD_OFFSET + ((QUEUE_3_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE4] = { + P2_Q4_BUFFER_OFFSET, + P2_Q4_BUFFER_OFFSET + + ((QUEUE_4_SIZE - 1) * ICSS_BLOCK_SIZE), + P2_Q4_BD_OFFSET, + P2_Q4_BD_OFFSET + ((QUEUE_4_SIZE - 1) * BD_SIZE), + }, + }, +}; + +static const struct prueth_queue_info rx_queue_infos[][NUM_QUEUES] = { + [PRUETH_PORT_QUEUE_HOST] = { + [PRUETH_QUEUE1] = { + P0_Q1_BUFFER_OFFSET, + HOST_QUEUE_DESC_OFFSET, + P0_Q1_BD_OFFSET, + P0_Q1_BD_OFFSET + ((HOST_QUEUE_1_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE2] = { + P0_Q2_BUFFER_OFFSET, + HOST_QUEUE_DESC_OFFSET + 8, + P0_Q2_BD_OFFSET, + P0_Q2_BD_OFFSET + ((HOST_QUEUE_2_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE3] = { + P0_Q3_BUFFER_OFFSET, + HOST_QUEUE_DESC_OFFSET + 16, + P0_Q3_BD_OFFSET, + P0_Q3_BD_OFFSET + ((HOST_QUEUE_3_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE4] = { + P0_Q4_BUFFER_OFFSET, + HOST_QUEUE_DESC_OFFSET + 24, + P0_Q4_BD_OFFSET, + P0_Q4_BD_OFFSET + ((HOST_QUEUE_4_SIZE - 1) * BD_SIZE), + }, + }, + [PRUETH_PORT_QUEUE_MII0] = { + [PRUETH_QUEUE1] = { + P1_Q1_BUFFER_OFFSET, + P1_QUEUE_DESC_OFFSET, + P1_Q1_BD_OFFSET, + P1_Q1_BD_OFFSET + ((QUEUE_1_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE2] = { + P1_Q2_BUFFER_OFFSET, + P1_QUEUE_DESC_OFFSET + 8, + P1_Q2_BD_OFFSET, + P1_Q2_BD_OFFSET + ((QUEUE_2_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE3] = { + P1_Q3_BUFFER_OFFSET, + P1_QUEUE_DESC_OFFSET + 16, + P1_Q3_BD_OFFSET, + P1_Q3_BD_OFFSET + ((QUEUE_3_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE4] = { + P1_Q4_BUFFER_OFFSET, + P1_QUEUE_DESC_OFFSET + 24, + P1_Q4_BD_OFFSET, + P1_Q4_BD_OFFSET + ((QUEUE_4_SIZE - 1) * BD_SIZE), + }, + }, + [PRUETH_PORT_QUEUE_MII1] = { + [PRUETH_QUEUE1] = { + P2_Q1_BUFFER_OFFSET, + P2_QUEUE_DESC_OFFSET, + P2_Q1_BD_OFFSET, + P2_Q1_BD_OFFSET + ((QUEUE_1_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE2] = { + P2_Q2_BUFFER_OFFSET, + P2_QUEUE_DESC_OFFSET + 8, + P2_Q2_BD_OFFSET, + P2_Q2_BD_OFFSET + ((QUEUE_2_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE3] = { + P2_Q3_BUFFER_OFFSET, + P2_QUEUE_DESC_OFFSET + 16, + P2_Q3_BD_OFFSET, + P2_Q3_BD_OFFSET + ((QUEUE_3_SIZE - 1) * BD_SIZE), + }, + [PRUETH_QUEUE4] = { + P2_Q4_BUFFER_OFFSET, + P2_QUEUE_DESC_OFFSET + 24, + P2_Q4_BD_OFFSET, + P2_Q4_BD_OFFSET + ((QUEUE_4_SIZE - 1) * BD_SIZE), + }, + }, +}; + +void icssm_prueth_sw_free_fdb_table(struct prueth *prueth) +{ + if (prueth->emac_configured) + return; + + kfree(prueth->fdb_tbl); + prueth->fdb_tbl = NULL; +} + +void icssm_prueth_sw_fdb_tbl_init(struct prueth *prueth) +{ + struct fdb_tbl *t = prueth->fdb_tbl; + void __iomem *sram_base; + u8 val; + + sram_base = prueth->mem[PRUETH_MEM_SHARED_RAM].va; + + t->index_a = sram_base + V2_1_FDB_TBL_OFFSET; + t->mac_tbl_a = sram_base + FDB_MAC_TBL_OFFSET; + t->port1_stp_cfg = sram_base + FDB_PORT1_STP_CFG_OFFSET; + t->port2_stp_cfg = sram_base + FDB_PORT2_STP_CFG_OFFSET; + t->flood_enable_flags = sram_base + FDB_FLOOD_ENABLE_FLAGS_OFFSET; + t->locks = sram_base + FDB_LOCKS_OFFSET; + + val = readb(t->flood_enable_flags); + /* host_flood_enable = 1 */ + val |= BIT(0); + /* port1_flood_enable = 1 */ + val |= BIT(1); + /* port2_flood_enable = 1 */ + val |= BIT(2); + writeb(val, t->flood_enable_flags); + + writeb(0, &t->locks->host_lock); + t->total_entries = 0; +} + +static u8 icssm_pru_lock_done(struct fdb_tbl *fdb_tbl) +{ + return readb(&fdb_tbl->locks->pru_locks); +} + +static int icssm_prueth_sw_fdb_spin_lock(struct fdb_tbl *fdb_tbl) +{ + u8 done; + int ret; + + /* Take the host lock */ + writeb(1, &fdb_tbl->locks->host_lock); + + /* Wait for the PRUs to release their locks */ + ret = read_poll_timeout(icssm_pru_lock_done, done, done == 0, + 1, 10, false, fdb_tbl); + return ret; +} + +static void icssm_prueth_sw_fdb_spin_unlock(struct fdb_tbl *fdb_tbl) +{ + writeb(0, &fdb_tbl->locks->host_lock); +} + +static u8 icssm_prueth_sw_fdb_hash(const u8 *mac) +{ + return (mac[0] ^ mac[1] ^ mac[2] ^ mac[3] ^ mac[4] ^ mac[5]); +} + +static int +icssm_prueth_sw_fdb_search(struct fdb_mac_tbl_array __iomem *mac_tbl, + struct fdb_index_tbl_entry __iomem *bucket_info, + const u8 *mac) +{ + u8 tmp_mac[ETH_ALEN]; + u16 bucket_entries; + u16 mac_tbl_idx; + int i; + + mac_tbl_idx = readw(&bucket_info->bucket_idx); + bucket_entries = readw(&bucket_info->bucket_entries); + for (i = 0; i < bucket_entries; i++, mac_tbl_idx++) { + memcpy_fromio(tmp_mac, mac_tbl->mac_tbl_entry[mac_tbl_idx].mac, + ETH_ALEN); + if (ether_addr_equal(mac, tmp_mac)) + return mac_tbl_idx; + } + + return -ENODATA; +} + +static u16 icssm_prueth_sw_fdb_find_open_slot(struct fdb_tbl *fdb_tbl) +{ + u8 flags; + u16 i; + + for (i = 0; i < FDB_MAC_TBL_MAX_ENTRIES; i++) { + flags = readb(&fdb_tbl->mac_tbl_a->mac_tbl_entry[i].flags); + if (!(flags & FLAG_ACTIVE)) + break; + } + + return i; +} + +static int +icssm_prueth_sw_find_fdb_insert(struct fdb_tbl *fdb, struct prueth *prueth, + struct fdb_index_tbl_entry __iomem *bkt_info, + const u8 *mac, const u8 port) +{ + struct fdb_mac_tbl_array __iomem *mac_tbl = fdb->mac_tbl_a; + struct fdb_mac_tbl_entry __iomem *e; + u8 mac_from_hw[ETH_ALEN]; + u16 bucket_entries; + u16 mac_tbl_idx; + int i, ret; + s8 cmp; + + mac_tbl_idx = readw(&bkt_info->bucket_idx); + bucket_entries = readw(&bkt_info->bucket_entries); + + for (i = 0; i < bucket_entries; i++, mac_tbl_idx++) { + e = &mac_tbl->mac_tbl_entry[mac_tbl_idx]; + memcpy_fromio(mac_from_hw, e->mac, ETH_ALEN); + cmp = memcmp(mac, mac_from_hw, ETH_ALEN); + if (cmp < 0) { + return mac_tbl_idx; + } else if (cmp == 0) { + if (readb(&e->port) != port) { + /* MAC is already in FDB, only port is + * different. So just update the port. + * Note: total_entries and bucket_entries + * remain the same. + */ + ret = icssm_prueth_sw_fdb_spin_lock(fdb); + if (ret) { + dev_err(prueth->dev, + "PRU lock timeout %d\n", ret); + return ret; + } + writeb(port, &e->port); + icssm_prueth_sw_fdb_spin_unlock(fdb); + } + + /* MAC and port are the same, touch the fdb */ + writew(0, &e->age); + return -EEXIST; + } + } + + return mac_tbl_idx; +} + +static int +icssm_prueth_sw_fdb_empty_slot_left(struct fdb_mac_tbl_array __iomem *mac_tbl, + u8 mac_tbl_idx) +{ + u8 flags; + s16 i; + + for (i = mac_tbl_idx - 1; i > -1; i--) { + flags = readb(&mac_tbl->mac_tbl_entry[i].flags); + if (!(flags & FLAG_ACTIVE)) + break; + } + + return i; +} + +static int +icssm_prueth_sw_fdb_empty_slot_right(struct fdb_mac_tbl_array __iomem *mac_tbl, + u8 mac_tbl_idx) +{ + u8 flags; + s16 i; + + for (i = mac_tbl_idx; i < FDB_MAC_TBL_MAX_ENTRIES; i++) { + flags = readb(&mac_tbl->mac_tbl_entry[i].flags); + if (!(flags & FLAG_ACTIVE)) + return i; + } + + return -1; +} + +static void icssm_prueth_sw_fdb_move_range_left(struct prueth *prueth, + u16 left, u16 right) +{ + struct fdb_mac_tbl_entry entry; + u32 sz = 0; + u16 i; + + sz = sizeof(struct fdb_mac_tbl_entry); + for (i = left; i < right; i++) { + memcpy_fromio(&entry, FDB_MAC_TBL_ENTRY(i + 1), sz); + memcpy_toio(FDB_MAC_TBL_ENTRY(i), &entry, sz); + } +} + +static void icssm_prueth_sw_fdb_move_range_right(struct prueth *prueth, + u16 left, u16 right) +{ + struct fdb_mac_tbl_entry entry; + u32 sz = 0; + u16 i; + + sz = sizeof(struct fdb_mac_tbl_entry); + for (i = right; i > left; i--) { + memcpy_fromio(&entry, FDB_MAC_TBL_ENTRY(i - 1), sz); + memcpy_toio(FDB_MAC_TBL_ENTRY(i), &entry, sz); + } +} + +static void icssm_prueth_sw_fdb_update_index_tbl(struct prueth *prueth, + u16 left, u16 right) +{ + u8 hash, hash_prev; + u8 mac[ETH_ALEN]; + u16 i; + + /* To ensure we don't improperly update the + * bucket index, initialize with an invalid + * hash in case we are in leftmost slot + */ + hash_prev = 0xff; + + if (left > 0) { + memcpy_fromio(mac, FDB_MAC_TBL_ENTRY(left - 1)->mac, ETH_ALEN); + hash_prev = icssm_prueth_sw_fdb_hash(mac); + } + + /* For each moved element, update the bucket index */ + for (i = left; i <= right; i++) { + memcpy_fromio(mac, FDB_MAC_TBL_ENTRY(i)->mac, ETH_ALEN); + hash = icssm_prueth_sw_fdb_hash(mac); + + /* Only need to update buckets once */ + if (hash != hash_prev) + writew(i, &FDB_IDX_TBL_ENTRY(hash)->bucket_idx); + + hash_prev = hash; + } +} + +static struct fdb_mac_tbl_entry __iomem * +icssm_prueth_sw_find_free_mac(struct prueth *prueth, struct fdb_index_tbl_entry + __iomem *bucket_info, u8 suggested_mac_tbl_idx, + bool *update_indexes, const u8 *mac) +{ + s16 empty_slot_idx = 0, left = 0, right = 0; + struct fdb_mac_tbl_array __iomem *mt; + u8 mti = suggested_mac_tbl_idx; + struct fdb_tbl *fdb; + u8 flags; + + fdb = prueth->fdb_tbl; + mt = fdb->mac_tbl_a; + + flags = readb(&FDB_MAC_TBL_ENTRY(mti)->flags); + if (!(flags & FLAG_ACTIVE)) { + /* Claim the entry */ + flags |= FLAG_ACTIVE; + writeb(flags, &FDB_MAC_TBL_ENTRY(mti)->flags); + + return FDB_MAC_TBL_ENTRY(mti); + } + + if (fdb->total_entries == FDB_MAC_TBL_MAX_ENTRIES) + return NULL; + + empty_slot_idx = icssm_prueth_sw_fdb_empty_slot_left(mt, mti); + if (empty_slot_idx == -1) { + /* Nothing available on the left. But table isn't full + * so there must be space to the right, + */ + empty_slot_idx = icssm_prueth_sw_fdb_empty_slot_right(mt, mti); + + /* Shift right */ + left = mti; + right = empty_slot_idx; + icssm_prueth_sw_fdb_move_range_right(prueth, left, right); + + /* Claim the entry */ + flags = readb(&FDB_MAC_TBL_ENTRY(mti)->flags); + flags |= FLAG_ACTIVE; + writeb(flags, &FDB_MAC_TBL_ENTRY(mti)->flags); + + memcpy_toio(FDB_MAC_TBL_ENTRY(mti)->mac, mac, ETH_ALEN); + + /* There is a chance we moved something in a + * different bucket, update index table + */ + icssm_prueth_sw_fdb_update_index_tbl(prueth, left, right); + + return FDB_MAC_TBL_ENTRY(mti); + } + + if (empty_slot_idx == mti - 1) { + /* There is space immediately left of the open slot, + * which means the inserted MAC address + * must be the lowest-valued MAC address in bucket. + * Update bucket pointer accordingly. + */ + writew(empty_slot_idx, &bucket_info->bucket_idx); + + /* Claim the entry */ + flags = readb(&FDB_MAC_TBL_ENTRY(mti)->flags); + flags |= FLAG_ACTIVE; + writeb(flags, &FDB_MAC_TBL_ENTRY(mti)->flags); + + return FDB_MAC_TBL_ENTRY(empty_slot_idx); + } + + /* There is empty space to the left, shift MAC table entries left */ + left = empty_slot_idx; + right = mti - 1; + icssm_prueth_sw_fdb_move_range_left(prueth, left, right); + + /* Claim the entry */ + flags = readb(&FDB_MAC_TBL_ENTRY(mti - 1)->flags); + flags |= FLAG_ACTIVE; + writeb(flags, &FDB_MAC_TBL_ENTRY(mti - 1)->flags); + + memcpy_toio(FDB_MAC_TBL_ENTRY(mti - 1)->mac, mac, ETH_ALEN); + + /* There is a chance we moved something in a + * different bucket, update index table + */ + icssm_prueth_sw_fdb_update_index_tbl(prueth, left, right); + + return FDB_MAC_TBL_ENTRY(mti - 1); +} + +static int icssm_prueth_sw_insert_fdb_entry(struct prueth_emac *emac, + const u8 *mac, u8 is_static) +{ + struct fdb_index_tbl_entry __iomem *bucket_info; + struct fdb_mac_tbl_entry __iomem *mac_info; + struct prueth *prueth = emac->prueth; + struct prueth_emac *other_emac; + enum prueth_port other_port_id; + u8 hash_val, mac_tbl_idx; + struct fdb_tbl *fdb; + u8 flags; + u16 val; + s16 ret; + int err; + + fdb = prueth->fdb_tbl; + other_port_id = (emac->port_id == PRUETH_PORT_MII0) ? + PRUETH_PORT_MII1 : PRUETH_PORT_MII0; + + other_emac = prueth->emac[other_port_id - 1]; + + if (fdb->total_entries == FDB_MAC_TBL_MAX_ENTRIES) + return -ENOMEM; + + if (ether_addr_equal(mac, emac->mac_addr) || + ether_addr_equal(mac, other_emac->mac_addr)) { + /* Don't insert fdb of own mac addr */ + return -EINVAL; + } + + /* Get the bucket that the mac belongs to */ + hash_val = icssm_prueth_sw_fdb_hash(mac); + bucket_info = FDB_IDX_TBL_ENTRY(hash_val); + + if (!readw(&bucket_info->bucket_entries)) { + mac_tbl_idx = icssm_prueth_sw_fdb_find_open_slot(fdb); + writew(mac_tbl_idx, &bucket_info->bucket_idx); + } + + ret = icssm_prueth_sw_find_fdb_insert(fdb, prueth, bucket_info, mac, + emac->port_id - 1); + if (ret < 0) + /* mac is already in fdb table */ + return 0; + + mac_tbl_idx = ret; + + err = icssm_prueth_sw_fdb_spin_lock(fdb); + if (err) { + dev_err(prueth->dev, "PRU lock timeout %d\n", ret); + return err; + } + + mac_info = icssm_prueth_sw_find_free_mac(prueth, bucket_info, + mac_tbl_idx, NULL, + mac); + if (!mac_info) { + /* Should not happen */ + dev_warn(prueth->dev, "OUT of FDB MEM\n"); + return -ENOMEM; + } + + memcpy_toio(mac_info->mac, mac, ETH_ALEN); + writew(0, &mac_info->age); + writeb(emac->port_id - 1, &mac_info->port); + + flags = readb(&mac_info->flags); + if (is_static) + flags |= FLAG_IS_STATIC; + else + flags &= ~FLAG_IS_STATIC; + + /* bit 1 - active */ + flags |= FLAG_ACTIVE; + writeb(flags, &mac_info->flags); + + val = readw(&bucket_info->bucket_entries); + val++; + writew(val, &bucket_info->bucket_entries); + + fdb->total_entries++; + + icssm_prueth_sw_fdb_spin_unlock(fdb); + + dev_dbg(prueth->dev, "added fdb: %pM port=%d total_entries=%u\n", + mac, emac->port_id, fdb->total_entries); + + return 0; +} + +static int icssm_prueth_sw_delete_fdb_entry(struct prueth_emac *emac, + const u8 *mac, u8 is_static) +{ + struct fdb_index_tbl_entry __iomem *bucket_info; + struct fdb_mac_tbl_entry __iomem *mac_info; + struct fdb_mac_tbl_array __iomem *mt; + u8 hash_val, mac_tbl_idx; + u16 idx, entries, val; + struct prueth *prueth; + s16 ret, left, right; + struct fdb_tbl *fdb; + u8 flags; + int err; + + prueth = emac->prueth; + fdb = prueth->fdb_tbl; + mt = fdb->mac_tbl_a; + + if (fdb->total_entries == 0) + return 0; + + /* Get the bucket that the mac belongs to */ + hash_val = icssm_prueth_sw_fdb_hash(mac); + bucket_info = FDB_IDX_TBL_ENTRY(hash_val); + + ret = icssm_prueth_sw_fdb_search(mt, bucket_info, mac); + if (ret < 0) + return ret; + + mac_tbl_idx = ret; + mac_info = FDB_MAC_TBL_ENTRY(mac_tbl_idx); + + err = icssm_prueth_sw_fdb_spin_lock(fdb); + if (err) { + dev_err(prueth->dev, "PRU lock timeout %d\n", ret); + return ret; + } + + /* Shift all elements in bucket to the left. No need to + * update index table since only shifting within bucket. + */ + left = mac_tbl_idx; + idx = readw(&bucket_info->bucket_idx); + entries = readw(&bucket_info->bucket_entries); + right = idx + entries - 1; + icssm_prueth_sw_fdb_move_range_left(prueth, left, right); + + /* Remove end of bucket from table */ + mac_info = FDB_MAC_TBL_ENTRY(right); + flags = readb(&mac_info->flags); + /* active = 0 */ + flags &= ~FLAG_ACTIVE; + writeb(flags, &mac_info->flags); + val = readw(&bucket_info->bucket_entries); + val--; + writew(val, &bucket_info->bucket_entries); + fdb->total_entries--; + + icssm_prueth_sw_fdb_spin_unlock(fdb); + + dev_dbg(prueth->dev, "del fdb: %pM total_entries=%u\n", + mac, fdb->total_entries); + + return 0; +} + +int icssm_prueth_sw_do_purge_fdb(struct prueth_emac *emac) +{ + struct fdb_index_tbl_entry __iomem *bucket_info; + struct prueth *prueth = emac->prueth; + struct fdb_tbl *fdb; + u8 hash_val, flags; + u8 mac[ETH_ALEN]; + u16 val; + + int ret; + s16 i; + + fdb = prueth->fdb_tbl; + if (fdb->total_entries == 0) + return 0; + + ret = icssm_prueth_sw_fdb_spin_lock(fdb); + if (ret) { + dev_err(prueth->dev, "PRU lock timeout %d\n", ret); + return ret; + } + + for (i = 0; i < FDB_MAC_TBL_MAX_ENTRIES; i++) { + flags = readb(&fdb->mac_tbl_a->mac_tbl_entry[i].flags); + if ((flags & FLAG_ACTIVE) && !(flags & FLAG_IS_STATIC)) { + /* Get the bucket that the mac belongs to */ + memcpy_fromio(mac, FDB_MAC_TBL_ENTRY(i)->mac, + ETH_ALEN); + hash_val = icssm_prueth_sw_fdb_hash(mac); + bucket_info = FDB_IDX_TBL_ENTRY(hash_val); + flags &= ~FLAG_ACTIVE; + writeb(flags, + &fdb->mac_tbl_a->mac_tbl_entry[i].flags); + val = readw(&bucket_info->bucket_entries); + val--; + writew(val, &bucket_info->bucket_entries); + fdb->total_entries--; + } + } + + icssm_prueth_sw_fdb_spin_unlock(fdb); + return 0; +} + +int icssm_prueth_sw_init_fdb_table(struct prueth *prueth) +{ + if (prueth->emac_configured) + return 0; + + prueth->fdb_tbl = kmalloc(sizeof(*prueth->fdb_tbl), GFP_KERNEL); + if (!prueth->fdb_tbl) + return -ENOMEM; + + icssm_prueth_sw_fdb_tbl_init(prueth); + + return 0; +} + +/** + * icssm_prueth_sw_fdb_add - insert fdb entry + * + * @emac: EMAC data structure + * @fdb: fdb info + * + */ +void icssm_prueth_sw_fdb_add(struct prueth_emac *emac, + struct switchdev_notifier_fdb_info *fdb) +{ + icssm_prueth_sw_insert_fdb_entry(emac, fdb->addr, 1); +} + +/** + * icssm_prueth_sw_fdb_del - delete fdb entry + * + * @emac: EMAC data structure + * @fdb: fdb info + * + */ +void icssm_prueth_sw_fdb_del(struct prueth_emac *emac, + struct switchdev_notifier_fdb_info *fdb) +{ + icssm_prueth_sw_delete_fdb_entry(emac, fdb->addr, 1); +} + +static void icssm_prueth_sw_fdb_work(struct work_struct *work) +{ + struct icssm_prueth_sw_fdb_work *fdb_work = + container_of(work, struct icssm_prueth_sw_fdb_work, work); + struct prueth_emac *emac = fdb_work->emac; + + rtnl_lock(); + + /* Interface is not up */ + if (!emac->prueth->fdb_tbl) + goto free; + + switch (fdb_work->event) { + case FDB_LEARN: + icssm_prueth_sw_insert_fdb_entry(emac, fdb_work->addr, 0); + break; + case FDB_PURGE: + icssm_prueth_sw_do_purge_fdb(emac); + break; + default: + break; + } + +free: + rtnl_unlock(); + kfree(fdb_work); + dev_put(emac->ndev); +} + +int icssm_prueth_sw_learn_fdb(struct prueth_emac *emac, u8 *src_mac) +{ + struct icssm_prueth_sw_fdb_work *fdb_work; + + fdb_work = kzalloc(sizeof(*fdb_work), GFP_ATOMIC); + if (WARN_ON(!fdb_work)) + return -ENOMEM; + + INIT_WORK(&fdb_work->work, icssm_prueth_sw_fdb_work); + + fdb_work->event = FDB_LEARN; + fdb_work->emac = emac; + ether_addr_copy(fdb_work->addr, src_mac); + + dev_hold(emac->ndev); + queue_work(system_long_wq, &fdb_work->work); + return 0; +} + +int icssm_prueth_sw_purge_fdb(struct prueth_emac *emac) +{ + struct icssm_prueth_sw_fdb_work *fdb_work; + + fdb_work = kzalloc(sizeof(*fdb_work), GFP_ATOMIC); + if (WARN_ON(!fdb_work)) + return -ENOMEM; + + INIT_WORK(&fdb_work->work, icssm_prueth_sw_fdb_work); + + fdb_work->event = FDB_PURGE; + fdb_work->emac = emac; + + dev_hold(emac->ndev); + queue_work(system_long_wq, &fdb_work->work); + return 0; +} + +void icssm_prueth_sw_hostconfig(struct prueth *prueth) +{ + void __iomem *dram1_base = prueth->mem[PRUETH_MEM_DRAM1].va; + void __iomem *dram; + + /* queue information table */ + dram = dram1_base + P0_Q1_RX_CONTEXT_OFFSET; + memcpy_toio(dram, sw_queue_infos[PRUETH_PORT_QUEUE_HOST], + sizeof(sw_queue_infos[PRUETH_PORT_QUEUE_HOST])); + + /* buffer descriptor offset table*/ + dram = dram1_base + QUEUE_DESCRIPTOR_OFFSET_ADDR; + writew(P0_Q1_BD_OFFSET, dram); + writew(P0_Q2_BD_OFFSET, dram + 2); + writew(P0_Q3_BD_OFFSET, dram + 4); + writew(P0_Q4_BD_OFFSET, dram + 6); + + /* buffer offset table */ + dram = dram1_base + QUEUE_OFFSET_ADDR; + writew(P0_Q1_BUFFER_OFFSET, dram); + writew(P0_Q2_BUFFER_OFFSET, dram + 2); + writew(P0_Q3_BUFFER_OFFSET, dram + 4); + writew(P0_Q4_BUFFER_OFFSET, dram + 6); + + /* queue size lookup table */ + dram = dram1_base + QUEUE_SIZE_ADDR; + writew(HOST_QUEUE_1_SIZE, dram); + writew(HOST_QUEUE_1_SIZE, dram + 2); + writew(HOST_QUEUE_1_SIZE, dram + 4); + writew(HOST_QUEUE_1_SIZE, dram + 6); + + /* queue table */ + dram = dram1_base + P0_QUEUE_DESC_OFFSET; + memcpy_toio(dram, queue_descs[PRUETH_PORT_QUEUE_HOST], + sizeof(queue_descs[PRUETH_PORT_QUEUE_HOST])); +} + +static int icssm_prueth_sw_port_config(struct prueth *prueth, + enum prueth_port port_id) +{ + unsigned int tx_context_ofs_addr, rx_context_ofs, queue_desc_ofs; + void __iomem *dram, *dram_base, *dram_mac; + struct prueth_emac *emac; + void __iomem *dram1_base; + + dram1_base = prueth->mem[PRUETH_MEM_DRAM1].va; + emac = prueth->emac[port_id - 1]; + switch (port_id) { + case PRUETH_PORT_MII0: + tx_context_ofs_addr = TX_CONTEXT_P1_Q1_OFFSET_ADDR; + rx_context_ofs = P1_Q1_RX_CONTEXT_OFFSET; + queue_desc_ofs = P1_QUEUE_DESC_OFFSET; + + /* for switch PORT MII0 mac addr is in DRAM0. */ + dram_mac = prueth->mem[PRUETH_MEM_DRAM0].va; + break; + case PRUETH_PORT_MII1: + tx_context_ofs_addr = TX_CONTEXT_P2_Q1_OFFSET_ADDR; + rx_context_ofs = P2_Q1_RX_CONTEXT_OFFSET; + queue_desc_ofs = P2_QUEUE_DESC_OFFSET; + + /* for switch PORT MII1 mac addr is in DRAM1. */ + dram_mac = prueth->mem[PRUETH_MEM_DRAM1].va; + break; + default: + netdev_err(emac->ndev, "invalid port\n"); + return -EINVAL; + } + + /* setup mac address */ + memcpy_toio(dram_mac + PORT_MAC_ADDR, emac->mac_addr, 6); + + /* Remaining switch port configs are in DRAM1 */ + dram_base = prueth->mem[PRUETH_MEM_DRAM1].va; + + /* queue information table */ + memcpy_toio(dram_base + tx_context_ofs_addr, + sw_queue_infos[port_id], + sizeof(sw_queue_infos[port_id])); + + memcpy_toio(dram_base + rx_context_ofs, + rx_queue_infos[port_id], + sizeof(rx_queue_infos[port_id])); + + /* buffer descriptor offset table*/ + dram = dram_base + QUEUE_DESCRIPTOR_OFFSET_ADDR + + (port_id * NUM_QUEUES * sizeof(u16)); + writew(sw_queue_infos[port_id][PRUETH_QUEUE1].buffer_desc_offset, dram); + writew(sw_queue_infos[port_id][PRUETH_QUEUE2].buffer_desc_offset, + dram + 2); + writew(sw_queue_infos[port_id][PRUETH_QUEUE3].buffer_desc_offset, + dram + 4); + writew(sw_queue_infos[port_id][PRUETH_QUEUE4].buffer_desc_offset, + dram + 6); + + /* buffer offset table */ + dram = dram_base + QUEUE_OFFSET_ADDR + + port_id * NUM_QUEUES * sizeof(u16); + writew(sw_queue_infos[port_id][PRUETH_QUEUE1].buffer_offset, dram); + writew(sw_queue_infos[port_id][PRUETH_QUEUE2].buffer_offset, + dram + 2); + writew(sw_queue_infos[port_id][PRUETH_QUEUE3].buffer_offset, + dram + 4); + writew(sw_queue_infos[port_id][PRUETH_QUEUE4].buffer_offset, + dram + 6); + + /* queue size lookup table */ + dram = dram_base + QUEUE_SIZE_ADDR + + port_id * NUM_QUEUES * sizeof(u16); + writew(QUEUE_1_SIZE, dram); + writew(QUEUE_2_SIZE, dram + 2); + writew(QUEUE_3_SIZE, dram + 4); + writew(QUEUE_4_SIZE, dram + 6); + + /* queue table */ + memcpy_toio(dram_base + queue_desc_ofs, + &queue_descs[port_id][0], + 4 * sizeof(queue_descs[port_id][0])); + + emac->rx_queue_descs = dram1_base + P0_QUEUE_DESC_OFFSET; + emac->tx_queue_descs = dram1_base + + rx_queue_infos[port_id][PRUETH_QUEUE1].queue_desc_offset; + + return 0; +} + +int icssm_prueth_sw_emac_config(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + u32 sharedramaddr, ocmcaddr; + int ret; + + /* PRU needs local shared RAM address for C28 */ + sharedramaddr = ICSS_LOCAL_SHARED_RAM; + /* PRU needs real global OCMC address for C30*/ + ocmcaddr = (u32)prueth->mem[PRUETH_MEM_OCMC].pa; + + if (prueth->emac_configured & BIT(emac->port_id)) + return 0; + + ret = icssm_prueth_sw_port_config(prueth, emac->port_id); + if (ret) + return ret; + + if (!prueth->emac_configured) { + /* Set in constant table C28 of PRUn to ICSS Shared memory */ + pru_rproc_set_ctable(prueth->pru0, PRU_C28, sharedramaddr); + pru_rproc_set_ctable(prueth->pru1, PRU_C28, sharedramaddr); + + /* Set in constant table C30 of PRUn to OCMC memory */ + pru_rproc_set_ctable(prueth->pru0, PRU_C30, ocmcaddr); + pru_rproc_set_ctable(prueth->pru1, PRU_C30, ocmcaddr); + } + return 0; +} + +int icssm_prueth_sw_boot_prus(struct prueth *prueth, struct net_device *ndev) +{ + const struct prueth_firmware *pru_firmwares; + const char *fw_name, *fw_name1; + int ret; + + if (prueth->emac_configured) + return 0; + + pru_firmwares = &prueth->fw_data->fw_pru[PRUSS_PRU0]; + fw_name = pru_firmwares->fw_name[prueth->eth_type]; + pru_firmwares = &prueth->fw_data->fw_pru[PRUSS_PRU1]; + fw_name1 = pru_firmwares->fw_name[prueth->eth_type]; + + ret = rproc_set_firmware(prueth->pru0, fw_name); + if (ret) { + netdev_err(ndev, "failed to set PRU0 firmware %s: %d\n", + fw_name, ret); + return ret; + } + ret = rproc_boot(prueth->pru0); + if (ret) { + netdev_err(ndev, "failed to boot PRU0: %d\n", ret); + return ret; + } + + ret = rproc_set_firmware(prueth->pru1, fw_name1); + if (ret) { + netdev_err(ndev, "failed to set PRU1 firmware %s: %d\n", + fw_name1, ret); + goto rproc0_shutdown; + } + ret = rproc_boot(prueth->pru1); + if (ret) { + netdev_err(ndev, "failed to boot PRU1: %d\n", ret); + goto rproc0_shutdown; + } + + return 0; + +rproc0_shutdown: + rproc_shutdown(prueth->pru0); + return ret; +} + +int icssm_prueth_sw_shutdown_prus(struct prueth_emac *emac, + struct net_device *ndev) +{ + struct prueth *prueth = emac->prueth; + + if (prueth->emac_configured) + return 0; + + rproc_shutdown(prueth->pru0); + rproc_shutdown(prueth->pru1); + + return 0; +} diff --git a/drivers/net/ethernet/ti/icssm/icssm_prueth_switch.h b/drivers/net/ethernet/ti/icssm/icssm_prueth_switch.h new file mode 100644 index 0000000000000..fa71b48ea63ef --- /dev/null +++ b/drivers/net/ethernet/ti/icssm/icssm_prueth_switch.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com + */ + +#ifndef __NET_TI_PRUETH_SWITCH_H +#define __NET_TI_PRUETH_SWITCH_H + +#include + +#include "icssm_prueth.h" +#include "icssm_prueth_fdb_tbl.h" +#include "icssm_switchdev.h" + +void icssm_prueth_sw_port_set_stp_state(struct prueth *prueth, + enum prueth_port port, u8 state); +u8 icssm_prueth_sw_port_get_stp_state(struct prueth *prueth, + enum prueth_port port); + +extern const struct prueth_queue_info sw_queue_infos[][4]; + +void icssm_prueth_sw_fdb_tbl_init(struct prueth *prueth); +int icssm_prueth_sw_init_fdb_table(struct prueth *prueth); +void icssm_prueth_sw_free_fdb_table(struct prueth *prueth); +int icssm_prueth_sw_do_purge_fdb(struct prueth_emac *emac); +void icssm_prueth_sw_fdb_add(struct prueth_emac *emac, + struct switchdev_notifier_fdb_info *fdb); +void icssm_prueth_sw_fdb_del(struct prueth_emac *emac, + struct switchdev_notifier_fdb_info *fdb); +int icssm_prueth_sw_learn_fdb(struct prueth_emac *emac, u8 *src_mac); +int icssm_prueth_sw_purge_fdb(struct prueth_emac *emac); +void icssm_prueth_sw_hostconfig(struct prueth *prueth); +int icssm_prueth_sw_emac_config(struct prueth_emac *emac); +int icssm_prueth_sw_boot_prus(struct prueth *prueth, struct net_device *ndev); +int icssm_prueth_sw_shutdown_prus(struct prueth_emac *emac, + struct net_device *ndev); + +#endif /* __NET_TI_PRUETH_SWITCH_H */ diff --git a/drivers/net/ethernet/ti/icssm/icssm_switch.h b/drivers/net/ethernet/ti/icssm/icssm_switch.h index 8b494ffdcde70..5ba9ce14da445 100644 --- a/drivers/net/ethernet/ti/icssm/icssm_switch.h +++ b/drivers/net/ethernet/ti/icssm/icssm_switch.h @@ -117,6 +117,15 @@ #define STATISTICS_OFFSET 0x1F00 #define STAT_SIZE 0x98 +/* The following offsets indicate which sections of the memory are used + * for switch internal tasks + */ +#define SWITCH_SPECIFIC_DRAM0_START_SIZE 0x100 +#define SWITCH_SPECIFIC_DRAM0_START_OFFSET 0x1F00 + +#define SWITCH_SPECIFIC_DRAM1_START_SIZE 0x300 +#define SWITCH_SPECIFIC_DRAM1_START_OFFSET 0x1D00 + /* Offset for storing * 1. Storm Prevention Params * 2. PHY Speed Offset @@ -146,6 +155,74 @@ /* 4 bytes ? */ #define STP_INVALID_STATE_OFFSET (STATISTICS_OFFSET + STAT_SIZE + 33) +/* DRAM1 Offsets for Switch */ +/* 4 queue descriptors for port 0 (host receive) */ +#define P0_QUEUE_DESC_OFFSET 0x1E7C +#define P1_QUEUE_DESC_OFFSET 0x1E9C +#define P2_QUEUE_DESC_OFFSET 0x1EBC +/* collision descriptor of port 0 */ +#define P0_COL_QUEUE_DESC_OFFSET 0x1E64 +#define P1_COL_QUEUE_DESC_OFFSET 0x1E6C +#define P2_COL_QUEUE_DESC_OFFSET 0x1E74 +/* Collision Status Register + * P0: bit 0 is pending flag, bit 1..2 indicates which queue, + * P1: bit 8 is pending flag, 9..10 is queue number + * P2: bit 16 is pending flag, 17..18 is queue number, remaining bits are 0. + */ +#define COLLISION_STATUS_ADDR 0x1E60 + +#define INTERFACE_MAC_ADDR 0x1E58 +#define P2_MAC_ADDR 0x1E50 +#define P1_MAC_ADDR 0x1E48 + +#define QUEUE_SIZE_ADDR 0x1E30 +#define QUEUE_OFFSET_ADDR 0x1E18 +#define QUEUE_DESCRIPTOR_OFFSET_ADDR 0x1E00 + +#define COL_RX_CONTEXT_P2_OFFSET_ADDR (COL_RX_CONTEXT_P1_OFFSET_ADDR + 12) +#define COL_RX_CONTEXT_P1_OFFSET_ADDR (COL_RX_CONTEXT_P0_OFFSET_ADDR + 12) +#define COL_RX_CONTEXT_P0_OFFSET_ADDR (P2_Q4_RX_CONTEXT_OFFSET + 8) + +/* Port 2 Rx Context */ +#define P2_Q4_RX_CONTEXT_OFFSET (P2_Q3_RX_CONTEXT_OFFSET + 8) +#define P2_Q3_RX_CONTEXT_OFFSET (P2_Q2_RX_CONTEXT_OFFSET + 8) +#define P2_Q2_RX_CONTEXT_OFFSET (P2_Q1_RX_CONTEXT_OFFSET + 8) +#define P2_Q1_RX_CONTEXT_OFFSET RX_CONTEXT_P2_Q1_OFFSET_ADDR +#define RX_CONTEXT_P2_Q1_OFFSET_ADDR (P1_Q4_RX_CONTEXT_OFFSET + 8) + +/* Port 1 Rx Context */ +#define P1_Q4_RX_CONTEXT_OFFSET (P1_Q3_RX_CONTEXT_OFFSET + 8) +#define P1_Q3_RX_CONTEXT_OFFSET (P1_Q2_RX_CONTEXT_OFFSET + 8) +#define P1_Q2_RX_CONTEXT_OFFSET (P1_Q1_RX_CONTEXT_OFFSET + 8) +#define P1_Q1_RX_CONTEXT_OFFSET (RX_CONTEXT_P1_Q1_OFFSET_ADDR) +#define RX_CONTEXT_P1_Q1_OFFSET_ADDR (P0_Q4_RX_CONTEXT_OFFSET + 8) + +/* Host Port Rx Context */ +#define P0_Q4_RX_CONTEXT_OFFSET (P0_Q3_RX_CONTEXT_OFFSET + 8) +#define P0_Q3_RX_CONTEXT_OFFSET (P0_Q2_RX_CONTEXT_OFFSET + 8) +#define P0_Q2_RX_CONTEXT_OFFSET (P0_Q1_RX_CONTEXT_OFFSET + 8) +#define P0_Q1_RX_CONTEXT_OFFSET RX_CONTEXT_P0_Q1_OFFSET_ADDR +#define RX_CONTEXT_P0_Q1_OFFSET_ADDR (COL_TX_CONTEXT_P2_Q1_OFFSET_ADDR + 8) + +/* Port 2 Tx Collision Context */ +#define COL_TX_CONTEXT_P2_Q1_OFFSET_ADDR (COL_TX_CONTEXT_P1_Q1_OFFSET_ADDR + 8) +/* Port 1 Tx Collision Context */ +#define COL_TX_CONTEXT_P1_Q1_OFFSET_ADDR (P2_Q4_TX_CONTEXT_OFFSET + 8) + +/* Port 2 */ +#define P2_Q4_TX_CONTEXT_OFFSET (P2_Q3_TX_CONTEXT_OFFSET + 8) +#define P2_Q3_TX_CONTEXT_OFFSET (P2_Q2_TX_CONTEXT_OFFSET + 8) +#define P2_Q2_TX_CONTEXT_OFFSET (P2_Q1_TX_CONTEXT_OFFSET + 8) +#define P2_Q1_TX_CONTEXT_OFFSET TX_CONTEXT_P2_Q1_OFFSET_ADDR +#define TX_CONTEXT_P2_Q1_OFFSET_ADDR (P1_Q4_TX_CONTEXT_OFFSET + 8) + +/* Port 1 */ +#define P1_Q4_TX_CONTEXT_OFFSET (P1_Q3_TX_CONTEXT_OFFSET + 8) +#define P1_Q3_TX_CONTEXT_OFFSET (P1_Q2_TX_CONTEXT_OFFSET + 8) +#define P1_Q2_TX_CONTEXT_OFFSET (P1_Q1_TX_CONTEXT_OFFSET + 8) +#define P1_Q1_TX_CONTEXT_OFFSET TX_CONTEXT_P1_Q1_OFFSET_ADDR +#define TX_CONTEXT_P1_Q1_OFFSET_ADDR SWITCH_SPECIFIC_DRAM1_START_OFFSET + /* DRAM Offsets for EMAC * Present on Both DRAM0 and DRAM1 */ @@ -254,4 +331,30 @@ #define P0_COL_BUFFER_OFFSET 0xEE00 #define P0_Q1_BUFFER_OFFSET 0x0000 +#define V2_1_FDB_TBL_LOC PRUETH_MEM_SHARED_RAM +#define V2_1_FDB_TBL_OFFSET 0x2000 + +#define FDB_INDEX_TBL_MAX_ENTRIES 256 +#define FDB_MAC_TBL_MAX_ENTRIES 256 + +#define FDB_INDEX_TBL_OFFSET V2_1_FDB_TBL_OFFSET +#define FDB_INDEX_TBL_SIZE (FDB_INDEX_TBL_MAX_ENTRIES * \ + sizeof(struct fdb_index_tbl_entry)) + +#define FDB_MAC_TBL_OFFSET (FDB_INDEX_TBL_OFFSET + FDB_INDEX_TBL_SIZE) +#define FDB_MAC_TBL_SIZE (FDB_MAC_TBL_MAX_ENTRIES * \ + sizeof(struct fdb_mac_tbl_entry)) + +#define FDB_PORT1_STP_CFG_OFFSET (FDB_MAC_TBL_OFFSET + FDB_MAC_TBL_SIZE) +#define FDB_PORT_STP_CFG_SIZE sizeof(struct fdb_stp_config) +#define FDB_PORT2_STP_CFG_OFFSET (FDB_PORT1_STP_CFG_OFFSET + \ + FDB_PORT_STP_CFG_SIZE) + +#define FDB_FLOOD_ENABLE_FLAGS_OFFSET (FDB_PORT2_STP_CFG_OFFSET + \ + FDB_PORT_STP_CFG_SIZE) +#define FDB_FLOOD_ENABLE_FLAGS_SIZE sizeof(struct fdb_flood_config) + +#define FDB_LOCKS_OFFSET (FDB_FLOOD_ENABLE_FLAGS_OFFSET + \ + FDB_FLOOD_ENABLE_FLAGS_SIZE) + #endif /* __ICSS_SWITCH_H */ diff --git a/drivers/net/ethernet/ti/icssm/icssm_switchdev.c b/drivers/net/ethernet/ti/icssm/icssm_switchdev.c new file mode 100644 index 0000000000000..57b83d790ebbf --- /dev/null +++ b/drivers/net/ethernet/ti/icssm/icssm_switchdev.c @@ -0,0 +1,332 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Texas Instruments ICSSM Ethernet Driver + * + * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/ + * + */ + +#include +#include +#include +#include + +#include "icssm_prueth.h" +#include "icssm_prueth_switch.h" +#include "icssm_prueth_fdb_tbl.h" + +/* switchev event work */ +struct icssm_prueth_sw_switchdev_event_work { + struct work_struct work; + struct switchdev_notifier_fdb_info fdb_info; + struct prueth_emac *emac; + unsigned long event; +}; + +void icssm_prueth_sw_port_set_stp_state(struct prueth *prueth, + enum prueth_port port, u8 state) +{ + struct fdb_tbl *t = prueth->fdb_tbl; + + writeb(state, port - 1 ? (void __iomem *)&t->port2_stp_cfg->state : + (void __iomem *)&t->port1_stp_cfg->state); +} + +u8 icssm_prueth_sw_port_get_stp_state(struct prueth *prueth, + enum prueth_port port) +{ + struct fdb_tbl *t = prueth->fdb_tbl; + u8 state; + + state = readb(port - 1 ? (void __iomem *)&t->port2_stp_cfg->state : + (void __iomem *)&t->port1_stp_cfg->state); + return state; +} + +static int icssm_prueth_switchdev_attr_set(struct net_device *ndev, + const void *ctx, + const struct switchdev_attr *attr, + struct netlink_ext_ack *extack) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int err = 0; + u8 o_state; + + /* Interface is not up */ + if (!prueth->fdb_tbl) + return 0; + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: + o_state = icssm_prueth_sw_port_get_stp_state(prueth, + emac->port_id); + icssm_prueth_sw_port_set_stp_state(prueth, emac->port_id, + attr->u.stp_state); + + if (o_state != attr->u.stp_state) + icssm_prueth_sw_purge_fdb(emac); + + dev_dbg(prueth->dev, "attr set: stp state:%u port:%u\n", + attr->u.stp_state, emac->port_id); + break; + default: + err = -EOPNOTSUPP; + break; + } + + return err; +} + +static void +icssm_prueth_sw_fdb_offload_notify(struct net_device *ndev, + struct switchdev_notifier_fdb_info *rcv) +{ + struct switchdev_notifier_fdb_info info; + + info.addr = rcv->addr; + info.vid = rcv->vid; + call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, ndev, &info.info, + NULL); +} + +/** + * icssm_prueth_sw_switchdev_event_work - insert/delete fdb entry + * + * @work: work structure + * + */ +static void icssm_prueth_sw_switchdev_event_work(struct work_struct *work) +{ + struct icssm_prueth_sw_switchdev_event_work *switchdev_work = + container_of(work, + struct icssm_prueth_sw_switchdev_event_work, work); + struct prueth_emac *emac = switchdev_work->emac; + struct switchdev_notifier_fdb_info *fdb; + struct prueth *prueth = emac->prueth; + int port = emac->port_id; + + rtnl_lock(); + + /* Interface is not up */ + if (!emac->prueth->fdb_tbl) { + rtnl_unlock(); + return; + } + + switch (switchdev_work->event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + fdb = &switchdev_work->fdb_info; + dev_dbg(prueth->dev, + "prueth fdb add: MACID = %pM vid = %u flags = %u -- port %d\n", + fdb->addr, fdb->vid, fdb->added_by_user, port); + + if (!fdb->added_by_user) + break; + + if (fdb->is_local) + break; + + icssm_prueth_sw_fdb_add(emac, fdb); + icssm_prueth_sw_fdb_offload_notify(emac->ndev, fdb); + break; + case SWITCHDEV_FDB_DEL_TO_DEVICE: + fdb = &switchdev_work->fdb_info; + dev_dbg(prueth->dev, + "prueth fdb del: MACID = %pM vid = %u flags = %u -- port %d\n", + fdb->addr, fdb->vid, fdb->added_by_user, port); + + if (fdb->is_local) + break; + + icssm_prueth_sw_fdb_del(emac, fdb); + break; + default: + break; + } + rtnl_unlock(); + + kfree(switchdev_work->fdb_info.addr); + kfree(switchdev_work); + dev_put(emac->ndev); +} + +/* called under rcu_read_lock() */ +static int icssm_prueth_sw_switchdev_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *ndev = switchdev_notifier_info_to_dev(ptr); + struct icssm_prueth_sw_switchdev_event_work *switchdev_work; + struct switchdev_notifier_fdb_info *fdb_info = ptr; + struct prueth_emac *emac = netdev_priv(ndev); + int err; + + if (!icssm_prueth_sw_port_dev_check(ndev)) + return NOTIFY_DONE; + + if (event == SWITCHDEV_PORT_ATTR_SET) { + err = switchdev_handle_port_attr_set + (ndev, ptr, icssm_prueth_sw_port_dev_check, + icssm_prueth_switchdev_attr_set); + return notifier_from_errno(err); + } + + switchdev_work = kzalloc(sizeof(*switchdev_work), GFP_ATOMIC); + if (WARN_ON(!switchdev_work)) + return NOTIFY_BAD; + + INIT_WORK(&switchdev_work->work, icssm_prueth_sw_switchdev_event_work); + switchdev_work->emac = emac; + switchdev_work->event = event; + + switch (event) { + case SWITCHDEV_FDB_ADD_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: + memcpy(&switchdev_work->fdb_info, ptr, + sizeof(switchdev_work->fdb_info)); + switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); + if (!switchdev_work->fdb_info.addr) + goto err_addr_alloc; + ether_addr_copy((u8 *)switchdev_work->fdb_info.addr, + fdb_info->addr); + dev_hold(ndev); + break; + default: + kfree(switchdev_work); + return NOTIFY_DONE; + } + + queue_work(system_long_wq, &switchdev_work->work); + + return NOTIFY_DONE; + +err_addr_alloc: + kfree(switchdev_work); + return NOTIFY_BAD; +} + +static int icssm_prueth_switchdev_obj_add(struct net_device *ndev, + const void *ctx, + const struct switchdev_obj *obj, + struct netlink_ext_ack *extack) +{ + struct switchdev_obj_port_mdb *mdb = SWITCHDEV_OBJ_PORT_MDB(obj); + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + int ret = 0; + u8 hash; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_HOST_MDB: + dev_dbg(prueth->dev, "MDB add: %s: vid %u:%pM port: %x\n", + ndev->name, mdb->vid, mdb->addr, emac->port_id); + hash = icssm_emac_get_mc_hash(mdb->addr, emac->mc_filter_mask); + icssm_emac_mc_filter_bin_allow(emac, hash); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +static int icssm_prueth_switchdev_obj_del(struct net_device *ndev, + const void *ctx, + const struct switchdev_obj *obj) +{ + struct switchdev_obj_port_mdb *mdb = SWITCHDEV_OBJ_PORT_MDB(obj); + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + struct netdev_hw_addr *ha; + u8 hash, tmp_hash; + int ret = 0; + + switch (obj->id) { + case SWITCHDEV_OBJ_ID_HOST_MDB: + dev_dbg(prueth->dev, "MDB del: %s: vid %u:%pM port: %x\n", + ndev->name, mdb->vid, mdb->addr, emac->port_id); + hash = icssm_emac_get_mc_hash(mdb->addr, emac->mc_filter_mask); + netdev_for_each_mc_addr(ha, prueth->hw_bridge_dev) { + tmp_hash = icssm_emac_get_mc_hash(ha->addr, + emac->mc_filter_mask); + /* Another MC address is in the bin. Don't disable. */ + if (tmp_hash == hash) + return 0; + } + icssm_emac_mc_filter_bin_disallow(emac, hash); + break; + default: + ret = -EOPNOTSUPP; + break; + } + + return ret; +} + +/* switchdev notifiers */ +static int +icssm_prueth_sw_switchdev_blocking_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *ndev = switchdev_notifier_info_to_dev(ptr); + int err; + + switch (event) { + case SWITCHDEV_PORT_OBJ_ADD: + err = switchdev_handle_port_obj_add + (ndev, ptr, icssm_prueth_sw_port_dev_check, + icssm_prueth_switchdev_obj_add); + return notifier_from_errno(err); + + case SWITCHDEV_PORT_OBJ_DEL: + err = switchdev_handle_port_obj_del + (ndev, ptr, icssm_prueth_sw_port_dev_check, + icssm_prueth_switchdev_obj_del); + return notifier_from_errno(err); + + case SWITCHDEV_PORT_ATTR_SET: + err = switchdev_handle_port_attr_set + (ndev, ptr, icssm_prueth_sw_port_dev_check, + icssm_prueth_switchdev_attr_set); + return notifier_from_errno(err); + + default: + break; + } + + return NOTIFY_DONE; +} + +int icssm_prueth_sw_register_notifiers(struct prueth *prueth) +{ + int ret = 0; + + prueth->prueth_switchdev_nb.notifier_call = + &icssm_prueth_sw_switchdev_event; + ret = register_switchdev_notifier(&prueth->prueth_switchdev_nb); + if (ret) { + dev_err(prueth->dev, + "register switchdev notifier failed ret:%d\n", ret); + return ret; + } + + prueth->prueth_switchdev_bl_nb.notifier_call = + &icssm_prueth_sw_switchdev_blocking_event; + ret = register_switchdev_blocking_notifier + (&prueth->prueth_switchdev_bl_nb); + if (ret) { + dev_err(prueth->dev, + "register switchdev blocking notifier failed ret:%d\n", + ret); + unregister_switchdev_notifier(&prueth->prueth_switchdev_nb); + } + + return ret; +} + +void icssm_prueth_sw_unregister_notifiers(struct prueth *prueth) +{ + unregister_switchdev_blocking_notifier(&prueth->prueth_switchdev_bl_nb); + unregister_switchdev_notifier(&prueth->prueth_switchdev_nb); +} diff --git a/drivers/net/ethernet/ti/icssm/icssm_switchdev.h b/drivers/net/ethernet/ti/icssm/icssm_switchdev.h new file mode 100644 index 0000000000000..b03a98e3472eb --- /dev/null +++ b/drivers/net/ethernet/ti/icssm/icssm_switchdev.h @@ -0,0 +1,13 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (C) 2020-2021 Texas Instruments Incorporated - https://www.ti.com + */ + +#ifndef __NET_TI_ICSSM_SWITCHDEV_H +#define __NET_TI_ICSSM_SWITCHDEV_H + +#include "icssm_prueth.h" + +int icssm_prueth_sw_register_notifiers(struct prueth *prueth); +void icssm_prueth_sw_unregister_notifiers(struct prueth *prueth); +bool icssm_prueth_sw_port_dev_check(const struct net_device *ndev); +#endif /* __NET_TI_ICSSM_SWITCHDEV_H */ diff --git a/drivers/net/ethernet/ti/icssm/icssm_vlan_mcast_filter_mmap.h b/drivers/net/ethernet/ti/icssm/icssm_vlan_mcast_filter_mmap.h new file mode 100644 index 0000000000000..c177c19a36ef2 --- /dev/null +++ b/drivers/net/ethernet/ti/icssm/icssm_vlan_mcast_filter_mmap.h @@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* Copyright (C) 2015-2021 Texas Instruments Incorporated - https://www.ti.com + * + * This file contains VLAN/Multicast filtering feature memory map + * + */ + +#ifndef ICSS_VLAN_MULTICAST_FILTER_MM_H +#define ICSS_VLAN_MULTICAST_FILTER_MM_H + +/* VLAN/Multicast filter defines & offsets, + * present on both PRU0 and PRU1 DRAM + */ + +/* Feature enable/disable values for multicast filtering */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_DISABLED 0x00 +#define ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_ENABLED 0x01 + +/* Feature enable/disable values for VLAN filtering */ +#define ICSS_EMAC_FW_VLAN_FILTER_CTRL_DISABLED 0x00 +#define ICSS_EMAC_FW_VLAN_FILTER_CTRL_ENABLED 0x01 + +/* Add/remove multicast mac id for filtering bin */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_HOST_RCV_ALLOWED 0x01 +#define ICSS_EMAC_FW_MULTICAST_FILTER_HOST_RCV_NOT_ALLOWED 0x00 + +/* Default HASH value for the multicast filtering Mask */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_INIT_VAL 0xFF + +/* Size requirements for Multicast filtering feature */ +#define ICSS_EMAC_FW_MULTICAST_TABLE_SIZE_BYTES 256 +#define ICSS_EMAC_FW_MULTICAST_FILTER_MASK_SIZE_BYTES 6 +#define ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_SIZE_BYTES 1 +#define ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OVERRIDE_STATUS_SIZE_BYTES 1 +#define ICSS_EMAC_FW_MULTICAST_FILTER_DROP_CNT_SIZE_BYTES 4 + +/* Size requirements for VLAN filtering feature : 4096 bits = 512 bytes */ +#define ICSS_EMAC_FW_VLAN_FILTER_TABLE_SIZE_BYTES 512 +#define ICSS_EMAC_FW_VLAN_FILTER_CTRL_SIZE_BYTES 1 +#define ICSS_EMAC_FW_VLAN_FILTER_DROP_CNT_SIZE_BYTES 4 + +/* Mask override set status */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OVERRIDE_SET 1 +/* Mask override not set status */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OVERRIDE_NOT_SET 0 +/* 6 bytes HASH Mask for the MAC */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OFFSET 0xF4 +/* 0 -> multicast filtering disabled | 1 -> multicast filtering enabled */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_OFFSET \ + (ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OFFSET + \ + ICSS_EMAC_FW_MULTICAST_FILTER_MASK_SIZE_BYTES) +/* Status indicating if the HASH override is done or not: 0: no, 1: yes */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_OVERRIDE_STATUS \ + (ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_OFFSET + \ + ICSS_EMAC_FW_MULTICAST_FILTER_CTRL_SIZE_BYTES) +/* Multicast drop statistics */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_DROP_CNT_OFFSET \ + (ICSS_EMAC_FW_MULTICAST_FILTER_OVERRIDE_STATUS +\ + ICSS_EMAC_FW_MULTICAST_FILTER_MASK_OVERRIDE_STATUS_SIZE_BYTES) +/* Multicast table */ +#define ICSS_EMAC_FW_MULTICAST_FILTER_TABLE \ + (ICSS_EMAC_FW_MULTICAST_FILTER_DROP_CNT_OFFSET +\ + ICSS_EMAC_FW_MULTICAST_FILTER_DROP_CNT_SIZE_BYTES) + +/* Multicast filter defines & offsets for LRE + */ +#define ICSS_LRE_FW_MULTICAST_TABLE_SEARCH_OP_CONTROL_BIT 0xE0 +/* one byte field : + * 0 -> multicast filtering disabled + * 1 -> multicast filtering enabled + */ +#define ICSS_LRE_FW_MULTICAST_FILTER_MASK 0xE4 +#define ICSS_LRE_FW_MULTICAST_FILTER_TABLE 0x100 + +/* VLAN table Offsets */ +#define ICSS_EMAC_FW_VLAN_FLTR_TBL_BASE_ADDR 0x200 +#define ICSS_EMAC_FW_VLAN_FILTER_CTRL_BITMAP_OFFSET 0xEF +#define ICSS_EMAC_FW_VLAN_FILTER_DROP_CNT_OFFSET \ + (ICSS_EMAC_FW_VLAN_FILTER_CTRL_BITMAP_OFFSET + \ + ICSS_EMAC_FW_VLAN_FILTER_CTRL_SIZE_BYTES) + +/* VLAN filter Control Bit maps */ +/* one bit field, bit 0: | 0 : VLAN filter disabled (default), + * 1: VLAN filter enabled + */ +#define ICSS_EMAC_FW_VLAN_FILTER_CTRL_ENABLE_BIT 0 +/* one bit field, bit 1: | 0 : untagged host rcv allowed (default), + * 1: untagged host rcv not allowed + */ +#define ICSS_EMAC_FW_VLAN_FILTER_UNTAG_HOST_RCV_ALLOW_CTRL_BIT 1 +/* one bit field, bit 1: | 0 : priotag host rcv allowed (default), + * 1: priotag host rcv not allowed + */ +#define ICSS_EMAC_FW_VLAN_FILTER_PRIOTAG_HOST_RCV_ALLOW_CTRL_BIT 2 +/* one bit field, bit 1: | 0 : skip sv vlan flow + * :1 : take sv vlan flow (not applicable for dual emac ) + */ +#define ICSS_EMAC_FW_VLAN_FILTER_SV_VLAN_FLOW_HOST_RCV_ALLOW_CTRL_BIT 3 + +/* VLAN IDs */ +#define ICSS_EMAC_FW_VLAN_FILTER_PRIOTAG_VID 0 +#define ICSS_EMAC_FW_VLAN_FILTER_VID_MIN 0x0000 +#define ICSS_EMAC_FW_VLAN_FILTER_VID_MAX 0x0FFF + +/* VLAN Filtering Commands */ +#define ICSS_EMAC_FW_VLAN_FILTER_ADD_VLAN_VID_CMD 0x00 +#define ICSS_EMAC_FW_VLAN_FILTER_REMOVE_VLAN_VID_CMD 0x01 + +/* Switch defines for VLAN/MC filtering */ +/* SRAM + * VLAN filter defines & offsets + */ +#define ICSS_LRE_FW_VLAN_FLTR_CTRL_BYTE 0x1FE +/* one bit field | 0 : VLAN filter disabled + * | 1 : VLAN filter enabled + */ +#define ICSS_LRE_FW_VLAN_FLTR_TBL_BASE_ADDR 0x200 + +#endif /* ICSS_MULTICAST_FILTER_MM_H */ diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index 7007eb8bed365..b9cbd3b4a8a22 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -207,6 +207,11 @@ struct netcp_module { int (*del_vid)(void *intf_priv, int vid); int (*ioctl)(void *intf_priv, struct ifreq *req, int cmd); int (*set_rx_mode)(void *intf_priv, bool promisc); + int (*hwtstamp_get)(void *intf_priv, + struct kernel_hwtstamp_config *cfg); + int (*hwtstamp_set)(void *intf_priv, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); /* used internally */ struct list_head module_list; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 5ee13db568f08..5ed1c46bbcb10 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1781,6 +1781,62 @@ static int netcp_ndo_stop(struct net_device *ndev) return 0; } +static int netcp_ndo_hwtstamp_get(struct net_device *ndev, + struct kernel_hwtstamp_config *config) +{ + struct netcp_intf *netcp = netdev_priv(ndev); + struct netcp_intf_modpriv *intf_modpriv; + struct netcp_module *module; + int err = -EOPNOTSUPP; + + if (!netif_running(ndev)) + return -EINVAL; + + for_each_module(netcp, intf_modpriv) { + module = intf_modpriv->netcp_module; + if (!module->hwtstamp_get) + continue; + + err = module->hwtstamp_get(intf_modpriv->module_priv, config); + break; + } + + return err; +} + +static int netcp_ndo_hwtstamp_set(struct net_device *ndev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct netcp_intf *netcp = netdev_priv(ndev); + struct netcp_intf_modpriv *intf_modpriv; + struct netcp_module *module; + int ret = -1, err = -EOPNOTSUPP; + + if (!netif_running(ndev)) + return -EINVAL; + + for_each_module(netcp, intf_modpriv) { + module = intf_modpriv->netcp_module; + if (!module->hwtstamp_set) + continue; + + err = module->hwtstamp_set(intf_modpriv->module_priv, config, + extack); + if ((err < 0) && (err != -EOPNOTSUPP)) { + NL_SET_ERR_MSG_WEAK_MOD(extack, + "At least one module failed to setup HW timestamps"); + ret = err; + goto out; + } + if (err == 0) + ret = err; + } + +out: + return (ret == 0) ? 0 : err; +} + static int netcp_ndo_ioctl(struct net_device *ndev, struct ifreq *req, int cmd) { @@ -1952,6 +2008,8 @@ static const struct net_device_ops netcp_netdev_ops = { .ndo_tx_timeout = netcp_ndo_tx_timeout, .ndo_select_queue = dev_pick_tx_zero, .ndo_setup_tc = netcp_setup_tc, + .ndo_hwtstamp_get = netcp_ndo_hwtstamp_get, + .ndo_hwtstamp_set = netcp_ndo_hwtstamp_set, }; static int netcp_create_interface(struct netcp_device *netcp_device, diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 55a1a96cd8349..4f6cc6cd1f030 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -2591,20 +2591,26 @@ static int gbe_rxtstamp(struct gbe_intf *gbe_intf, struct netcp_packet *p_info) return 0; } -static int gbe_hwtstamp_get(struct gbe_intf *gbe_intf, struct ifreq *ifr) +static int gbe_hwtstamp_get(void *intf_priv, struct kernel_hwtstamp_config *cfg) { - struct gbe_priv *gbe_dev = gbe_intf->gbe_dev; - struct cpts *cpts = gbe_dev->cpts; - struct hwtstamp_config cfg; + struct gbe_intf *gbe_intf = intf_priv; + struct gbe_priv *gbe_dev; + struct phy_device *phy; + + gbe_dev = gbe_intf->gbe_dev; - if (!cpts) + if (!gbe_dev->cpts) + return -EOPNOTSUPP; + + phy = gbe_intf->slave->phy; + if (phy_has_hwtstamp(phy)) return -EOPNOTSUPP; - cfg.flags = 0; - cfg.tx_type = gbe_dev->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - cfg.rx_filter = gbe_dev->rx_ts_enabled; + cfg->flags = 0; + cfg->tx_type = gbe_dev->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + cfg->rx_filter = gbe_dev->rx_ts_enabled; - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + return 0; } static void gbe_hwtstamp(struct gbe_intf *gbe_intf) @@ -2637,19 +2643,23 @@ static void gbe_hwtstamp(struct gbe_intf *gbe_intf) writel(ctl, GBE_REG_ADDR(slave, port_regs, ts_ctl_ltype2)); } -static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) +static int gbe_hwtstamp_set(void *intf_priv, struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { - struct gbe_priv *gbe_dev = gbe_intf->gbe_dev; - struct cpts *cpts = gbe_dev->cpts; - struct hwtstamp_config cfg; + struct gbe_intf *gbe_intf = intf_priv; + struct gbe_priv *gbe_dev; + struct phy_device *phy; - if (!cpts) + gbe_dev = gbe_intf->gbe_dev; + + if (!gbe_dev->cpts) return -EOPNOTSUPP; - if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) - return -EFAULT; + phy = gbe_intf->slave->phy; + if (phy_has_hwtstamp(phy)) + return phy->mii_ts->hwtstamp(phy->mii_ts, cfg, extack); - switch (cfg.tx_type) { + switch (cfg->tx_type) { case HWTSTAMP_TX_OFF: gbe_dev->tx_ts_enabled = 0; break; @@ -2660,7 +2670,7 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) return -ERANGE; } - switch (cfg.rx_filter) { + switch (cfg->rx_filter) { case HWTSTAMP_FILTER_NONE: gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_NONE; break; @@ -2668,7 +2678,7 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; break; case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: @@ -2680,7 +2690,7 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: gbe_dev->rx_ts_enabled = HWTSTAMP_FILTER_PTP_V2_EVENT; - cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + cfg->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; default: return -ERANGE; @@ -2688,7 +2698,7 @@ static int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *ifr) gbe_hwtstamp(gbe_intf); - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; + return 0; } static void gbe_register_cpts(struct gbe_priv *gbe_dev) @@ -2745,12 +2755,15 @@ static inline void gbe_unregister_cpts(struct gbe_priv *gbe_dev) { } -static inline int gbe_hwtstamp_get(struct gbe_intf *gbe_intf, struct ifreq *req) +static inline int gbe_hwtstamp_get(void *intf_priv, + struct kernel_hwtstamp_config *cfg) { return -EOPNOTSUPP; } -static inline int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *req) +static inline int gbe_hwtstamp_set(void *intf_priv, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } @@ -2816,15 +2829,6 @@ static int gbe_ioctl(void *intf_priv, struct ifreq *req, int cmd) struct gbe_intf *gbe_intf = intf_priv; struct phy_device *phy = gbe_intf->slave->phy; - if (!phy_has_hwtstamp(phy)) { - switch (cmd) { - case SIOCGHWTSTAMP: - return gbe_hwtstamp_get(gbe_intf, req); - case SIOCSHWTSTAMP: - return gbe_hwtstamp_set(gbe_intf, req); - } - } - if (phy) return phy_mii_ioctl(phy, req, cmd); @@ -3824,6 +3828,8 @@ static struct netcp_module gbe_module = { .add_vid = gbe_add_vid, .del_vid = gbe_del_vid, .ioctl = gbe_ioctl, + .hwtstamp_get = gbe_hwtstamp_get, + .hwtstamp_set = gbe_hwtstamp_set, }; static struct netcp_module xgbe_module = { @@ -3841,6 +3847,8 @@ static struct netcp_module xgbe_module = { .add_vid = gbe_add_vid, .del_vid = gbe_del_vid, .ioctl = gbe_ioctl, + .hwtstamp_get = gbe_hwtstamp_get, + .hwtstamp_set = gbe_hwtstamp_set, }; static int __init keystone_gbe_init(void) diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.c b/drivers/net/ethernet/toshiba/ps3_gelic_net.c index 5ee8e8980393c..591866fc9055d 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.c +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.c @@ -260,6 +260,7 @@ void gelic_card_down(struct gelic_card *card) if (atomic_dec_if_positive(&card->users) == 0) { pr_debug("%s: real do\n", __func__); napi_disable(&card->napi); + timer_delete_sync(&card->rx_oom_timer); /* * Disable irq. Wireless interrupts will * be disabled later if any @@ -970,7 +971,8 @@ static void gelic_net_pass_skb_up(struct gelic_descr *descr, * gelic_card_decode_one_descr - processes an rx descriptor * @card: card structure * - * returns 1 if a packet has been sent to the stack, otherwise 0 + * returns 1 if a packet has been sent to the stack, -ENOMEM on skb alloc + * failure, otherwise 0 * * processes an rx descriptor by iommu-unmapping the data buffer and passing * the packet up to the stack @@ -981,16 +983,18 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) struct gelic_descr_chain *chain = &card->rx_chain; struct gelic_descr *descr = chain->head; struct net_device *netdev = NULL; - int dmac_chain_ended; + int dmac_chain_ended = 0; + int prepare_rx_ret; status = gelic_descr_get_status(descr); if (status == GELIC_DESCR_DMA_CARDOWNED) return 0; - if (status == GELIC_DESCR_DMA_NOT_IN_USE) { + if (status == GELIC_DESCR_DMA_NOT_IN_USE || !descr->skb) { dev_dbg(ctodev(card), "dormant descr? %p\n", descr); - return 0; + dmac_chain_ended = 1; + goto refill; } /* netdevice select */ @@ -1048,9 +1052,10 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) refill: /* is the current descriptor terminated with next_descr == NULL? */ - dmac_chain_ended = - be32_to_cpu(descr->hw_regs.dmac_cmd_status) & - GELIC_DESCR_RX_DMA_CHAIN_END; + if (!dmac_chain_ended) + dmac_chain_ended = + be32_to_cpu(descr->hw_regs.dmac_cmd_status) & + GELIC_DESCR_RX_DMA_CHAIN_END; /* * So that always DMAC can see the end * of the descriptor chain to avoid @@ -1062,10 +1067,11 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) gelic_descr_set_status(descr, GELIC_DESCR_DMA_NOT_IN_USE); /* - * this call can fail, but for now, just leave this - * descriptor without skb + * this call can fail, propagate the error */ - gelic_descr_prepare_rx(card, descr); + prepare_rx_ret = gelic_descr_prepare_rx(card, descr); + if (prepare_rx_ret) + return prepare_rx_ret; chain->tail = descr; chain->head = descr->next; @@ -1087,6 +1093,13 @@ static int gelic_card_decode_one_descr(struct gelic_card *card) return 1; } +static void gelic_rx_oom_timer(struct timer_list *t) +{ + struct gelic_card *card = timer_container_of(card, t, rx_oom_timer); + + napi_schedule(&card->napi); +} + /** * gelic_net_poll - NAPI poll function called by the stack to return packets * @napi: napi structure @@ -1099,14 +1112,22 @@ static int gelic_net_poll(struct napi_struct *napi, int budget) { struct gelic_card *card = container_of(napi, struct gelic_card, napi); int packets_done = 0; + int work_result = 0; while (packets_done < budget) { - if (!gelic_card_decode_one_descr(card)) + work_result = gelic_card_decode_one_descr(card); + if (work_result != 1) break; packets_done++; } + if (work_result == -ENOMEM) { + napi_complete_done(napi, packets_done); + mod_timer(&card->rx_oom_timer, jiffies + 1); + return packets_done; + } + if (packets_done < budget) { napi_complete_done(napi, packets_done); gelic_card_rx_irq_on(card); @@ -1576,6 +1597,8 @@ static struct gelic_card *gelic_alloc_card_net(struct net_device **netdev) mutex_init(&card->updown_lock); atomic_set(&card->users, 0); + timer_setup(&card->rx_oom_timer, gelic_rx_oom_timer, 0); + return card; } diff --git a/drivers/net/ethernet/toshiba/ps3_gelic_net.h b/drivers/net/ethernet/toshiba/ps3_gelic_net.h index f7d7931e51b77..c10f1984a5a11 100644 --- a/drivers/net/ethernet/toshiba/ps3_gelic_net.h +++ b/drivers/net/ethernet/toshiba/ps3_gelic_net.h @@ -268,6 +268,7 @@ struct gelic_vlan_id { struct gelic_card { struct napi_struct napi; struct net_device *netdev[GELIC_PORT_MAX]; + struct timer_list rx_oom_timer; /* * hypervisor requires irq_status should be * 8 bytes aligned, but u64 member is diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c index 06f401bd975c7..9aa3964187e1d 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c @@ -51,6 +51,11 @@ static const struct wx_stats wx_gstrings_fdir_stats[] = { WX_STAT("fdir_miss", stats.fdirmiss), }; +static const struct wx_stats wx_gstrings_rsc_stats[] = { + WX_STAT("rsc_aggregated", rsc_count), + WX_STAT("rsc_flushed", rsc_flush), +}; + /* drivers allocates num_tx_queues and num_rx_queues symmetrically so * we set the num_rx_queues to evaluate to num_tx_queues. This is * used because we do not have a good way to get the max number of @@ -64,16 +69,21 @@ static const struct wx_stats wx_gstrings_fdir_stats[] = { (sizeof(struct wx_queue_stats) / sizeof(u64))) #define WX_GLOBAL_STATS_LEN ARRAY_SIZE(wx_gstrings_stats) #define WX_FDIR_STATS_LEN ARRAY_SIZE(wx_gstrings_fdir_stats) +#define WX_RSC_STATS_LEN ARRAY_SIZE(wx_gstrings_rsc_stats) #define WX_STATS_LEN (WX_GLOBAL_STATS_LEN + WX_QUEUE_STATS_LEN) int wx_get_sset_count(struct net_device *netdev, int sset) { struct wx *wx = netdev_priv(netdev); + int len = WX_STATS_LEN; switch (sset) { case ETH_SS_STATS: - return (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) ? - WX_STATS_LEN + WX_FDIR_STATS_LEN : WX_STATS_LEN; + if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) + len += WX_FDIR_STATS_LEN; + if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) + len += WX_RSC_STATS_LEN; + return len; default: return -EOPNOTSUPP; } @@ -94,6 +104,10 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data) for (i = 0; i < WX_FDIR_STATS_LEN; i++) ethtool_puts(&p, wx_gstrings_fdir_stats[i].stat_string); } + if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) { + for (i = 0; i < WX_RSC_STATS_LEN; i++) + ethtool_puts(&p, wx_gstrings_rsc_stats[i].stat_string); + } for (i = 0; i < netdev->num_tx_queues; i++) { ethtool_sprintf(&p, "tx_queue_%u_packets", i); ethtool_sprintf(&p, "tx_queue_%u_bytes", i); @@ -131,6 +145,13 @@ void wx_get_ethtool_stats(struct net_device *netdev, } } + if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) { + for (k = 0; k < WX_RSC_STATS_LEN; k++) { + p = (char *)wx + wx_gstrings_rsc_stats[k].stat_offset; + data[i++] = *(u64 *)p; + } + } + for (j = 0; j < netdev->num_tx_queues; j++) { ring = wx->tx_ring[j]; if (!ring) { @@ -322,6 +343,40 @@ int wx_get_coalesce(struct net_device *netdev, } EXPORT_SYMBOL(wx_get_coalesce); +static void wx_update_rsc(struct wx *wx) +{ + struct net_device *netdev = wx->netdev; + bool need_reset = false; + + /* nothing to do if LRO or RSC are not enabled */ + if (!test_bit(WX_FLAG_RSC_CAPABLE, wx->flags) || + !(netdev->features & NETIF_F_LRO)) + return; + + /* check the feature flag value and enable RSC if necessary */ + if (wx->rx_itr_setting == 1 || + wx->rx_itr_setting > WX_MIN_RSC_ITR) { + if (!test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) { + set_bit(WX_FLAG_RSC_ENABLED, wx->flags); + dev_info(&wx->pdev->dev, + "rx-usecs value high enough to re-enable RSC\n"); + + need_reset = true; + } + /* if interrupt rate is too high then disable RSC */ + } else if (test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) { + clear_bit(WX_FLAG_RSC_ENABLED, wx->flags); + dev_info(&wx->pdev->dev, + "rx-usecs set too low, disabling RSC\n"); + + need_reset = true; + } + + /* reset the device to apply the new RSC setting */ + if (need_reset && wx->do_reset) + wx->do_reset(netdev); +} + int wx_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, struct kernel_ethtool_coalesce *kernel_coal, @@ -414,6 +469,8 @@ int wx_set_coalesce(struct net_device *netdev, wx_write_eitr(q_vector); } + wx_update_rsc(wx); + return 0; } EXPORT_SYMBOL(wx_set_coalesce); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index b37d6cfbfbe94..58b8300e3d2cf 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1779,7 +1779,9 @@ EXPORT_SYMBOL(wx_set_rx_mode); static void wx_set_rx_buffer_len(struct wx *wx) { struct net_device *netdev = wx->netdev; + struct wx_ring *rx_ring; u32 mhadd, max_frame; + int i; max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; /* adjust max frame to be at least the size of a standard frame */ @@ -1789,6 +1791,19 @@ static void wx_set_rx_buffer_len(struct wx *wx) mhadd = rd32(wx, WX_PSR_MAX_SZ); if (max_frame != mhadd) wr32(wx, WX_PSR_MAX_SZ, max_frame); + + /* + * Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < wx->num_rx_queues; i++) { + rx_ring = wx->rx_ring[i]; + rx_ring->rx_buf_len = WX_RXBUFFER_2K; +#if (PAGE_SIZE < 8192) + if (test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) + rx_ring->rx_buf_len = WX_RXBUFFER_3K; +#endif + } } /** @@ -1865,11 +1880,27 @@ static void wx_configure_srrctl(struct wx *wx, srrctl |= WX_RXBUFFER_256 << WX_PX_RR_CFG_BHDRSIZE_SHIFT; /* configure the packet buffer length */ - srrctl |= WX_RX_BUFSZ >> WX_PX_RR_CFG_BSIZEPKT_SHIFT; + srrctl |= rx_ring->rx_buf_len >> WX_PX_RR_CFG_BSIZEPKT_SHIFT; wr32(wx, WX_PX_RR_CFG(reg_idx), srrctl); } +static void wx_configure_rscctl(struct wx *wx, + struct wx_ring *ring) +{ + u8 reg_idx = ring->reg_idx; + u32 rscctrl; + + if (!test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) + return; + + rscctrl = rd32(wx, WX_PX_RR_CFG(reg_idx)); + rscctrl |= WX_PX_RR_CFG_RSC; + rscctrl |= WX_PX_RR_CFG_MAX_RSCBUF_16; + + wr32(wx, WX_PX_RR_CFG(reg_idx), rscctrl); +} + static void wx_configure_tx_ring(struct wx *wx, struct wx_ring *ring) { @@ -1905,6 +1936,15 @@ static void wx_configure_tx_ring(struct wx *wx, memset(ring->tx_buffer_info, 0, sizeof(struct wx_tx_buffer) * ring->count); + if (ring->headwb_mem) { + wr32(wx, WX_PX_TR_HEAD_ADDRL(reg_idx), + ring->headwb_dma & DMA_BIT_MASK(32)); + wr32(wx, WX_PX_TR_HEAD_ADDRH(reg_idx), + upper_32_bits(ring->headwb_dma)); + + txdctl |= WX_PX_TR_CFG_HEAD_WB; + } + /* enable queue */ wr32(wx, WX_PX_TR_CFG(reg_idx), txdctl); @@ -1935,6 +1975,10 @@ static void wx_configure_rx_ring(struct wx *wx, rxdctl |= (ring->count / 128) << WX_PX_RR_CFG_RR_SIZE_SHIFT; rxdctl |= 0x1 << WX_PX_RR_CFG_RR_THER_SHIFT; + + if (test_bit(WX_FLAG_RX_MERGE_ENABLED, wx->flags)) + rxdctl |= WX_PX_RR_CFG_DESC_MERGE; + wr32(wx, WX_PX_RR_CFG(reg_idx), rxdctl); /* reset head and tail pointers */ @@ -1943,6 +1987,7 @@ static void wx_configure_rx_ring(struct wx *wx, ring->tail = wx->hw_addr + WX_PX_RR_WP(reg_idx); wx_configure_srrctl(wx, ring); + wx_configure_rscctl(wx, ring); /* initialize rx_buffer_info */ memset(ring->rx_buffer_info, 0, @@ -2181,7 +2226,9 @@ void wx_configure_rx(struct wx *wx) /* RSC Setup */ psrctl = rd32(wx, WX_PSR_CTL); psrctl |= WX_PSR_CTL_RSC_ACK; /* Disable RSC for ACK packets */ - psrctl |= WX_PSR_CTL_RSC_DIS; + psrctl &= ~WX_PSR_CTL_RSC_DIS; + if (!test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) + psrctl |= WX_PSR_CTL_RSC_DIS; wr32(wx, WX_PSR_CTL, psrctl); } @@ -2190,6 +2237,12 @@ void wx_configure_rx(struct wx *wx) /* set_rx_buffer_len must be called before ring initialization */ wx_set_rx_buffer_len(wx); + if (test_bit(WX_FLAG_RX_MERGE_ENABLED, wx->flags)) { + wr32(wx, WX_RDM_DCACHE_CTL, WX_RDM_DCACHE_CTL_EN); + wr32m(wx, WX_RDM_RSC_CTL, + WX_RDM_RSC_CTL_FREE_CTL | WX_RDM_RSC_CTL_FREE_CNT_DIS, + WX_RDM_RSC_CTL_FREE_CTL); + } /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ @@ -2806,6 +2859,18 @@ void wx_update_stats(struct wx *wx) wx->hw_csum_rx_error = hw_csum_rx_error; wx->hw_csum_rx_good = hw_csum_rx_good; + if (test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) { + u64 rsc_count = 0; + u64 rsc_flush = 0; + + for (i = 0; i < wx->num_rx_queues; i++) { + rsc_count += wx->rx_ring[i]->rx_stats.rsc_count; + rsc_flush += wx->rx_ring[i]->rx_stats.rsc_flush; + } + wx->rsc_count = rsc_count; + wx->rsc_flush = rsc_flush; + } + for (i = 0; i < wx->num_tx_queues; i++) { struct wx_ring *tx_ring = wx->tx_ring[i]; diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c index 3adf7048320ae..32cadafa4b3b8 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c @@ -235,7 +235,7 @@ static struct sk_buff *wx_build_skb(struct wx_ring *rx_ring, { unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); #if (PAGE_SIZE < 8192) - unsigned int truesize = WX_RX_BUFSZ; + unsigned int truesize = wx_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); #endif @@ -341,7 +341,7 @@ void wx_alloc_rx_buffers(struct wx_ring *rx_ring, u16 cleaned_count) /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, bi->page_offset, - WX_RX_BUFSZ, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); rx_desc->read.pkt_addr = @@ -404,6 +404,7 @@ static bool wx_is_non_eop(struct wx_ring *rx_ring, union wx_rx_desc *rx_desc, struct sk_buff *skb) { + struct wx *wx = rx_ring->q_vector->wx; u32 ntc = rx_ring->next_to_clean + 1; /* fetch, update, and store next to clean */ @@ -412,6 +413,24 @@ static bool wx_is_non_eop(struct wx_ring *rx_ring, prefetch(WX_RX_DESC(rx_ring, ntc)); + /* update RSC append count if present */ + if (test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) { + __le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data & + cpu_to_le32(WX_RXD_RSCCNT_MASK); + + if (unlikely(rsc_enabled)) { + u32 rsc_cnt = le32_to_cpu(rsc_enabled); + + rsc_cnt >>= WX_RXD_RSCCNT_SHIFT; + WX_CB(skb)->append_cnt += rsc_cnt - 1; + + /* update ntc based on RSC value */ + ntc = le32_to_cpu(rx_desc->wb.upper.status_error); + ntc &= WX_RXD_NEXTP_MASK; + ntc >>= WX_RXD_NEXTP_SHIFT; + } + } + /* if we are the last buffer then there is nothing else to do */ if (likely(wx_test_staterr(rx_desc, WX_RXD_STAT_EOP))) return false; @@ -582,6 +601,33 @@ static void wx_rx_vlan(struct wx_ring *ring, union wx_rx_desc *rx_desc, } } +static void wx_set_rsc_gso_size(struct wx_ring *ring, + struct sk_buff *skb) +{ + u16 hdr_len = skb_headlen(skb); + + /* set gso_size to avoid messing up TCP MSS */ + skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len), + WX_CB(skb)->append_cnt); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; +} + +static void wx_update_rsc_stats(struct wx_ring *rx_ring, + struct sk_buff *skb) +{ + /* if append_cnt is 0 then frame is not RSC */ + if (!WX_CB(skb)->append_cnt) + return; + + rx_ring->rx_stats.rsc_count += WX_CB(skb)->append_cnt; + rx_ring->rx_stats.rsc_flush++; + + wx_set_rsc_gso_size(rx_ring, skb); + + /* gso_size is computed using append_cnt so always clear it last */ + WX_CB(skb)->append_cnt = 0; +} + /** * wx_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on @@ -598,6 +644,9 @@ static void wx_process_skb_fields(struct wx_ring *rx_ring, { struct wx *wx = netdev_priv(rx_ring->netdev); + if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) + wx_update_rsc_stats(rx_ring, skb); + wx_rx_hash(rx_ring, rx_desc, skb); wx_rx_checksum(rx_ring, rx_desc, skb); @@ -735,9 +784,22 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector, /* prevent any other reads prior to eop_desc */ smp_rmb(); - /* if DD is not set pending work has not been completed */ - if (!(eop_desc->wb.status & cpu_to_le32(WX_TXD_STAT_DD))) + if (tx_ring->headwb_mem) { + u32 head = *tx_ring->headwb_mem; + + if (head == tx_ring->next_to_clean) + break; + else if (head > tx_ring->next_to_clean && + !(tx_buffer->next_eop >= tx_ring->next_to_clean && + tx_buffer->next_eop < head)) + break; + else if (!(tx_buffer->next_eop >= tx_ring->next_to_clean || + tx_buffer->next_eop < head)) + break; + } else if (!(eop_desc->wb.status & cpu_to_le32(WX_TXD_STAT_DD))) { + /* if DD is not set pending work has not been completed */ break; + } /* clear next_to_watch to prevent false hangs */ tx_buffer->next_to_watch = NULL; @@ -1075,6 +1137,10 @@ static int wx_tx_map(struct wx_ring *tx_ring, /* set next_to_watch value indicating a packet is present */ first->next_to_watch = tx_desc; + /* set next_eop for amlite tx head wb */ + if (tx_ring->headwb_mem) + first->next_eop = i; + i++; if (i == tx_ring->count) i = 0; @@ -2532,7 +2598,7 @@ static void wx_clean_rx_ring(struct wx_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, rx_buffer->dma, rx_buffer->page_offset, - WX_RX_BUFSZ, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* free resources associated with mapping */ @@ -2683,6 +2749,16 @@ void wx_clean_all_tx_rings(struct wx *wx) } EXPORT_SYMBOL(wx_clean_all_tx_rings); +static void wx_free_headwb_resources(struct wx_ring *tx_ring) +{ + if (!tx_ring->headwb_mem) + return; + + dma_free_coherent(tx_ring->dev, sizeof(u32), + tx_ring->headwb_mem, tx_ring->headwb_dma); + tx_ring->headwb_mem = NULL; +} + /** * wx_free_tx_resources - Free Tx Resources per Queue * @tx_ring: Tx descriptor ring for a specific queue @@ -2702,6 +2778,8 @@ static void wx_free_tx_resources(struct wx_ring *tx_ring) dma_free_coherent(tx_ring->dev, tx_ring->size, tx_ring->desc, tx_ring->dma); tx_ring->desc = NULL; + + wx_free_headwb_resources(tx_ring); } /** @@ -2731,13 +2809,14 @@ static int wx_alloc_page_pool(struct wx_ring *rx_ring) struct page_pool_params pp_params = { .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, - .order = 0, - .pool_size = rx_ring->count, + .order = wx_rx_pg_order(rx_ring), + .pool_size = rx_ring->count * rx_ring->rx_buf_len / + wx_rx_pg_size(rx_ring), .nid = dev_to_node(rx_ring->dev), .dev = rx_ring->dev, .dma_dir = DMA_FROM_DEVICE, .offset = 0, - .max_len = PAGE_SIZE, + .max_len = wx_rx_pg_size(rx_ring), }; rx_ring->page_pool = page_pool_create(&pp_params); @@ -2840,6 +2919,24 @@ static int wx_setup_all_rx_resources(struct wx *wx) return err; } +static void wx_setup_headwb_resources(struct wx_ring *tx_ring) +{ + struct wx *wx = netdev_priv(tx_ring->netdev); + + if (!test_bit(WX_FLAG_TXHEAD_WB_ENABLED, wx->flags)) + return; + + if (!tx_ring->q_vector) + return; + + tx_ring->headwb_mem = dma_alloc_coherent(tx_ring->dev, + sizeof(u32), + &tx_ring->headwb_dma, + GFP_KERNEL); + if (!tx_ring->headwb_mem) + dev_info(tx_ring->dev, "Allocate headwb memory failed, disable it\n"); +} + /** * wx_setup_tx_resources - allocate Tx resources (Descriptors) * @tx_ring: tx descriptor ring (for a specific queue) to setup @@ -2880,6 +2977,8 @@ static int wx_setup_tx_resources(struct wx_ring *tx_ring) if (!tx_ring->desc) goto err; + wx_setup_headwb_resources(tx_ring); + tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -3026,8 +3125,25 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER)) wx_set_rx_mode(netdev); + if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) { + if (!(features & NETIF_F_LRO)) { + if (test_bit(WX_FLAG_RSC_ENABLED, wx->flags)) + need_reset = true; + clear_bit(WX_FLAG_RSC_ENABLED, wx->flags); + } else if (!(test_bit(WX_FLAG_RSC_ENABLED, wx->flags))) { + if (wx->rx_itr_setting == 1 || + wx->rx_itr_setting > WX_MIN_RSC_ITR) { + set_bit(WX_FLAG_RSC_ENABLED, wx->flags); + need_reset = true; + } else if (changed & NETIF_F_LRO) { + dev_info(&wx->pdev->dev, + "rx-usecs set too low, disable RSC\n"); + } + } + } + if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))) - return 0; + goto out; /* Check if Flow Director n-tuple support was enabled or disabled. If * the state changed, we need to reset. @@ -3053,6 +3169,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features) break; } +out: if (need_reset && wx->do_reset) wx->do_reset(netdev); @@ -3102,6 +3219,14 @@ netdev_features_t wx_fix_features(struct net_device *netdev, } } + /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ + if (!(features & NETIF_F_RXCSUM)) + features &= ~NETIF_F_LRO; + + /* Turn off LRO if not RSC capable */ + if (!test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) + features &= ~NETIF_F_LRO; + return features; } EXPORT_SYMBOL(wx_fix_features); diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c index c6d158cd70da3..493da5fffdb6e 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c @@ -122,6 +122,10 @@ static int __wx_enable_sriov(struct wx *wx, u8 num_vfs) WX_CFG_PORT_CTL_NUM_VT_MASK, value); + /* Disable RSC when in SR-IOV mode */ + clear_bit(WX_FLAG_RSC_CAPABLE, wx->flags); + clear_bit(WX_FLAG_RSC_ENABLED, wx->flags); + return ret; } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h index 2f8319e031820..b1a6ef5709a92 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_type.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h @@ -83,8 +83,13 @@ /*********************** Receive DMA registers **************************/ #define WX_RDM_VF_RE(_i) (0x12004 + ((_i) * 4)) +#define WX_RDM_RSC_CTL 0x1200C +#define WX_RDM_RSC_CTL_FREE_CNT_DIS BIT(8) +#define WX_RDM_RSC_CTL_FREE_CTL BIT(7) #define WX_RDM_PF_QDE(_i) (0x12080 + ((_i) * 4)) #define WX_RDM_VFRE_CLR(_i) (0x120A0 + ((_i) * 4)) +#define WX_RDM_DCACHE_CTL 0x120A8 +#define WX_RDM_DCACHE_CTL_EN BIT(0) #define WX_RDM_DRP_PKT 0x12500 #define WX_RDM_PKT_CNT 0x12504 #define WX_RDM_BYTE_CNT_LSB 0x12508 @@ -421,6 +426,7 @@ enum WX_MSCA_CMD_value { #define WX_7K_ITR 595 #define WX_12K_ITR 336 #define WX_20K_ITR 200 +#define WX_MIN_RSC_ITR 24 #define WX_SP_MAX_EITR 0x00000FF8U #define WX_AML_MAX_EITR 0x00000FFFU #define WX_EM_MAX_EITR 0x00007FFCU @@ -431,12 +437,15 @@ enum WX_MSCA_CMD_value { #define WX_PX_TR_WP(_i) (0x03008 + ((_i) * 0x40)) #define WX_PX_TR_RP(_i) (0x0300C + ((_i) * 0x40)) #define WX_PX_TR_CFG(_i) (0x03010 + ((_i) * 0x40)) +#define WX_PX_TR_HEAD_ADDRL(_i) (0x03028 + ((_i) * 0x40)) +#define WX_PX_TR_HEAD_ADDRH(_i) (0x0302C + ((_i) * 0x40)) /* Transmit Config masks */ #define WX_PX_TR_CFG_ENABLE BIT(0) /* Ena specific Tx Queue */ #define WX_PX_TR_CFG_TR_SIZE_SHIFT 1 /* tx desc number per ring */ #define WX_PX_TR_CFG_SWFLSH BIT(26) /* Tx Desc. wr-bk flushing */ #define WX_PX_TR_CFG_WTHRESH_SHIFT 16 /* shift to WTHRESH bits */ #define WX_PX_TR_CFG_THRE_SHIFT 8 +#define WX_PX_TR_CFG_HEAD_WB BIT(27) /* Receive DMA Registers */ #define WX_PX_RR_BAL(_i) (0x01000 + ((_i) * 0x40)) @@ -448,7 +457,10 @@ enum WX_MSCA_CMD_value { /* PX_RR_CFG bit definitions */ #define WX_PX_RR_CFG_VLAN BIT(31) #define WX_PX_RR_CFG_DROP_EN BIT(30) +#define WX_PX_RR_CFG_RSC BIT(29) #define WX_PX_RR_CFG_SPLIT_MODE BIT(26) +#define WX_PX_RR_CFG_MAX_RSCBUF_16 FIELD_PREP(GENMASK(24, 23), 3) +#define WX_PX_RR_CFG_DESC_MERGE BIT(19) #define WX_PX_RR_CFG_RR_THER_SHIFT 16 #define WX_PX_RR_CFG_RR_HDR_SZ GENMASK(15, 12) #define WX_PX_RR_CFG_RR_BUF_SZ GENMASK(11, 8) @@ -544,14 +556,9 @@ enum WX_MSCA_CMD_value { /* Supported Rx Buffer Sizes */ #define WX_RXBUFFER_256 256 /* Used for skb receive header */ #define WX_RXBUFFER_2K 2048 +#define WX_RXBUFFER_3K 3072 #define WX_MAX_RXBUFFER 16384 /* largest size for single descriptor */ -#if MAX_SKB_FRAGS < 8 -#define WX_RX_BUFSZ ALIGN(WX_MAX_RXBUFFER / MAX_SKB_FRAGS, 1024) -#else -#define WX_RX_BUFSZ WX_RXBUFFER_2K -#endif - #define WX_RX_BUFFER_WRITE 16 /* Must be power of 2 */ #define WX_MAX_DATA_PER_TXD BIT(14) @@ -643,6 +650,12 @@ enum wx_l2_ptypes { #define WX_RXD_PKTTYPE(_rxd) \ ((le32_to_cpu((_rxd)->wb.lower.lo_dword.data) >> 9) & 0xFF) + +#define WX_RXD_RSCCNT_MASK GENMASK(20, 17) +#define WX_RXD_RSCCNT_SHIFT 17 +#define WX_RXD_NEXTP_MASK GENMASK(19, 4) +#define WX_RXD_NEXTP_SHIFT 4 + /*********************** Transmit Descriptor Config Masks ****************/ #define WX_TXD_STAT_DD BIT(0) /* Descriptor Done */ #define WX_TXD_DTYP_DATA 0 /* Adv Data Descriptor */ @@ -1005,6 +1018,7 @@ struct wx_tx_buffer { DEFINE_DMA_UNMAP_LEN(len); __be16 protocol; u32 tx_flags; + u32 next_eop; }; struct wx_rx_buffer { @@ -1029,6 +1043,8 @@ struct wx_rx_queue_stats { u64 csum_good_cnt; u64 csum_err; u64 alloc_rx_buff_failed; + u64 rsc_count; + u64 rsc_flush; }; /* iterator for handling rings in ring container */ @@ -1056,6 +1072,8 @@ struct wx_ring { }; u8 __iomem *tail; dma_addr_t dma; /* phys. address of descriptor ring */ + dma_addr_t headwb_dma; + u32 *headwb_mem; unsigned int size; /* length in bytes */ u16 count; /* amount of descriptors */ @@ -1069,6 +1087,7 @@ struct wx_ring { */ u16 next_to_use; u16 next_to_clean; + u16 rx_buf_len; union { u16 next_to_alloc; struct { @@ -1225,6 +1244,7 @@ enum wx_pf_flags { WX_FLAG_FDIR_HASH, WX_FLAG_FDIR_PERFECT, WX_FLAG_RSC_CAPABLE, + WX_FLAG_RSC_ENABLED, WX_FLAG_RX_HWTSTAMP_ENABLED, WX_FLAG_RX_HWTSTAMP_IN_REGISTER, WX_FLAG_PTP_PPS_ENABLED, @@ -1232,6 +1252,8 @@ enum wx_pf_flags { WX_FLAG_NEED_SFP_RESET, WX_FLAG_NEED_UPDATE_LINK, WX_FLAG_NEED_DO_RESET, + WX_FLAG_RX_MERGE_ENABLED, + WX_FLAG_TXHEAD_WB_ENABLED, WX_PF_FLAGS_NBITS /* must be last */ }; @@ -1271,8 +1293,6 @@ struct wx { /* PHY stuff */ bool notify_down; - int adv_speed; - int adv_duplex; unsigned int link; int speed; int duplex; @@ -1340,6 +1360,8 @@ struct wx { u64 hw_csum_rx_good; u64 hw_csum_rx_error; u64 alloc_rx_buff_failed; + u64 rsc_count; + u64 rsc_flush; unsigned int num_vfs; struct vf_data_storage *vfinfo; struct vf_macvlans vf_mvs; @@ -1471,4 +1493,15 @@ static inline int wx_set_state_reset(struct wx *wx) return 0; } +static inline unsigned int wx_rx_pg_order(struct wx_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len == WX_RXBUFFER_3K) + return 1; +#endif + return 0; +} + +#define wx_rx_pg_size(_ring) (PAGE_SIZE << wx_rx_pg_order(_ring)) + #endif /* _WX_TYPE_H_ */ diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf.h b/drivers/net/ethernet/wangxun/libwx/wx_vf.h index 3f16de0fa4272..eb6ca3fe4e97b 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_vf.h +++ b/drivers/net/ethernet/wangxun/libwx/wx_vf.h @@ -74,6 +74,7 @@ #define WX_VXRXDCTL_BUFSZ(f) FIELD_PREP(GENMASK(11, 8), f) #define WX_VXRXDCTL_HDRSZ_MASK GENMASK(15, 12) #define WX_VXRXDCTL_HDRSZ(f) FIELD_PREP(GENMASK(15, 12), f) +#define WX_VXRXDCTL_DESC_MERGE BIT(19) #define WX_VXRXDCTL_RSCMAX_MASK GENMASK(24, 23) #define WX_VXRXDCTL_RSCMAX(f) FIELD_PREP(GENMASK(24, 23), f) #define WX_VXRXDCTL_RSCEN BIT(29) @@ -91,6 +92,9 @@ #define WX_VXTXDCTL_PTHRESH(f) FIELD_PREP(GENMASK(11, 8), f) #define WX_VXTXDCTL_WTHRESH(f) FIELD_PREP(GENMASK(22, 16), f) #define WX_VXTXDCTL_FLUSH BIT(26) +#define WX_VXTXDCTL_HEAD_WB BIT(27) +#define WX_VXTXD_HEAD_ADDRL(r) (0x3028 + (0x40 * (r))) +#define WX_VXTXD_HEAD_ADDRH(r) (0x302C + (0x40 * (r))) #define WX_PFLINK_STATUS(g) FIELD_GET(BIT(0), g) #define WX_PFLINK_SPEED(g) FIELD_GET(GENMASK(31, 1), g) diff --git a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c index a87887b9f8ee3..aa8be036956c0 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_vf_lib.c @@ -132,6 +132,15 @@ static void wx_configure_tx_ring_vf(struct wx *wx, struct wx_ring *ring) txdctl |= WX_VXTXDCTL_BUFLEN(wx_buf_len(ring->count)); txdctl |= WX_VXTXDCTL_ENABLE; + if (ring->headwb_mem) { + wr32(wx, WX_VXTXD_HEAD_ADDRL(reg_idx), + ring->headwb_dma & DMA_BIT_MASK(32)); + wr32(wx, WX_VXTXD_HEAD_ADDRH(reg_idx), + upper_32_bits(ring->headwb_dma)); + + txdctl |= WX_VXTXDCTL_HEAD_WB; + } + /* reinitialize tx_buffer_info */ memset(ring->tx_buffer_info, 0, sizeof(struct wx_tx_buffer) * ring->count); @@ -272,6 +281,9 @@ void wx_configure_rx_ring_vf(struct wx *wx, struct wx_ring *ring) rxdctl |= WX_VXRXDCTL_RSCMAX(0); rxdctl |= WX_VXRXDCTL_RSCEN; + if (test_bit(WX_FLAG_RX_MERGE_ENABLED, wx->flags)) + rxdctl |= WX_VXRXDCTL_DESC_MERGE; + wr32(wx, WX_VXRXDCTL(reg_idx), rxdctl); /* pf/vf reuse */ diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c index dc87ccad96524..35eebdb077616 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_aml.c @@ -19,8 +19,8 @@ void txgbe_gpio_init_aml(struct wx *wx) { u32 status; - wr32(wx, WX_GPIO_INTTYPE_LEVEL, TXGBE_GPIOBIT_2 | TXGBE_GPIOBIT_3); - wr32(wx, WX_GPIO_INTEN, TXGBE_GPIOBIT_2 | TXGBE_GPIOBIT_3); + wr32(wx, WX_GPIO_INTTYPE_LEVEL, TXGBE_GPIOBIT_2); + wr32(wx, WX_GPIO_INTEN, TXGBE_GPIOBIT_2); status = rd32(wx, WX_GPIO_INTSTATUS); for (int i = 0; i < 6; i++) { @@ -42,11 +42,6 @@ irqreturn_t txgbe_gpio_irq_handler_aml(int irq, void *data) wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_2); wx_service_event_schedule(wx); } - if (status & TXGBE_GPIOBIT_3) { - set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags); - wx_service_event_schedule(wx); - wr32(wx, WX_GPIO_EOI, TXGBE_GPIOBIT_3); - } wr32(wx, WX_GPIO_INTMASK, 0); return IRQ_HANDLED; @@ -96,6 +91,9 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int case SPEED_10000: buffer.speed = TXGBE_LINK_SPEED_10GB_FULL; break; + default: + buffer.speed = TXGBE_LINK_SPEED_UNKNOWN; + break; } buffer.fec_mode = TXGBE_PHY_FEC_AUTO; @@ -106,22 +104,21 @@ static int txgbe_set_phy_link_hostif(struct wx *wx, int speed, int autoneg, int WX_HI_COMMAND_TIMEOUT, true); } -static void txgbe_get_link_capabilities(struct wx *wx) +static void txgbe_get_link_capabilities(struct wx *wx, int *speed, int *duplex) { struct txgbe *txgbe = wx->priv; if (test_bit(PHY_INTERFACE_MODE_25GBASER, txgbe->sfp_interfaces)) - wx->adv_speed = SPEED_25000; + *speed = SPEED_25000; else if (test_bit(PHY_INTERFACE_MODE_10GBASER, txgbe->sfp_interfaces)) - wx->adv_speed = SPEED_10000; + *speed = SPEED_10000; else - wx->adv_speed = SPEED_UNKNOWN; + *speed = SPEED_UNKNOWN; - wx->adv_duplex = wx->adv_speed == SPEED_UNKNOWN ? - DUPLEX_HALF : DUPLEX_FULL; + *duplex = *speed == SPEED_UNKNOWN ? DUPLEX_HALF : DUPLEX_FULL; } -static void txgbe_get_phy_link(struct wx *wx, int *speed) +static void txgbe_get_mac_link(struct wx *wx, int *speed) { u32 status; @@ -138,23 +135,11 @@ static void txgbe_get_phy_link(struct wx *wx, int *speed) int txgbe_set_phy_link(struct wx *wx) { - int speed, err; - u32 gpio; - - /* Check RX signal */ - gpio = rd32(wx, WX_GPIO_EXT); - if (gpio & TXGBE_GPIOBIT_3) - return -ENODEV; + int speed, duplex, err; - txgbe_get_link_capabilities(wx); - if (wx->adv_speed == SPEED_UNKNOWN) - return -ENODEV; - - txgbe_get_phy_link(wx, &speed); - if (speed == wx->adv_speed) - return 0; + txgbe_get_link_capabilities(wx, &speed, &duplex); - err = txgbe_set_phy_link_hostif(wx, wx->adv_speed, 0, wx->adv_duplex); + err = txgbe_set_phy_link_hostif(wx, speed, 0, duplex); if (err) { wx_err(wx, "Failed to setup link\n"); return err; @@ -230,14 +215,7 @@ int txgbe_identify_sfp(struct wx *wx) return -ENODEV; } - err = txgbe_sfp_to_linkmodes(wx, id); - if (err) - return err; - - if (gpio & TXGBE_GPIOBIT_3) - set_bit(WX_FLAG_NEED_LINK_CONFIG, wx->flags); - - return 0; + return txgbe_sfp_to_linkmodes(wx, id); } void txgbe_setup_link(struct wx *wx) @@ -256,7 +234,7 @@ static void txgbe_get_link_state(struct phylink_config *config, struct wx *wx = phylink_to_wx(config); int speed; - txgbe_get_phy_link(wx, &speed); + txgbe_get_mac_link(wx, &speed); state->link = speed != SPEED_UNKNOWN; state->speed = speed; state->duplex = state->link ? DUPLEX_FULL : DUPLEX_UNKNOWN; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c index c4c4d70d8466a..daa761e48f9d1 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c @@ -398,6 +398,7 @@ static int txgbe_sw_init(struct wx *wx) wx->configure_fdir = txgbe_configure_fdir; set_bit(WX_FLAG_RSC_CAPABLE, wx->flags); + set_bit(WX_FLAG_RSC_ENABLED, wx->flags); set_bit(WX_FLAG_MULTI_64_FUNC, wx->flags); /* enable itr by default in dynamic mode */ @@ -423,6 +424,8 @@ static int txgbe_sw_init(struct wx *wx) break; case wx_mac_aml: case wx_mac_aml40: + set_bit(WX_FLAG_RX_MERGE_ENABLED, wx->flags); + set_bit(WX_FLAG_TXHEAD_WB_ENABLED, wx->flags); set_bit(WX_FLAG_SWFW_RING, wx->flags); wx->swfw_index = 0; break; @@ -801,6 +804,8 @@ static int txgbe_probe(struct pci_dev *pdev, netdev->features |= NETIF_F_HIGHDMA; netdev->hw_features |= NETIF_F_GRO; netdev->features |= NETIF_F_GRO; + netdev->hw_features |= NETIF_F_LRO; + netdev->features |= NETIF_F_LRO; netdev->features |= NETIF_F_RX_UDP_TUNNEL_PORT; netdev->priv_flags |= IFF_UNICAST_FLT; diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h index 41915d7dd372a..b9a4ba48f5b99 100644 --- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h +++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h @@ -314,6 +314,7 @@ void txgbe_up(struct wx *wx); int txgbe_setup_tc(struct net_device *dev, u8 tc); void txgbe_do_reset(struct net_device *netdev); +#define TXGBE_LINK_SPEED_UNKNOWN 0 #define TXGBE_LINK_SPEED_10GB_FULL 4 #define TXGBE_LINK_SPEED_25GB_FULL 0x10 @@ -352,7 +353,9 @@ struct txgbe_sfp_id { u8 vendor_oui0; /* A0H 0x25 */ u8 vendor_oui1; /* A0H 0x26 */ u8 vendor_oui2; /* A0H 0x27 */ - u8 reserved[3]; + u8 transceiver_type; /* A0H 0x83 */ + u8 sff_opt1; /* A0H 0xC0 */ + u8 reserved[5]; }; struct txgbe_hic_i2c_read { diff --git a/drivers/net/ethernet/wangxun/txgbevf/txgbevf_main.c b/drivers/net/ethernet/wangxun/txgbevf/txgbevf_main.c index 72663e3c4205a..37e4ec487afdd 100644 --- a/drivers/net/ethernet/wangxun/txgbevf/txgbevf_main.c +++ b/drivers/net/ethernet/wangxun/txgbevf/txgbevf_main.c @@ -157,6 +157,18 @@ static int txgbevf_sw_init(struct wx *wx) wx->set_num_queues = txgbevf_set_num_queues; + switch (wx->mac.type) { + case wx_mac_sp: + break; + case wx_mac_aml: + case wx_mac_aml40: + set_bit(WX_FLAG_RX_MERGE_ENABLED, wx->flags); + set_bit(WX_FLAG_TXHEAD_WB_ENABLED, wx->flags); + break; + default: + break; + } + return 0; err_reset_hw: kfree(wx->vfinfo); diff --git a/drivers/net/ethernet/xilinx/ll_temac_mdio.c b/drivers/net/ethernet/xilinx/ll_temac_mdio.c index 07a9fb49eda1a..ab23dc2337683 100644 --- a/drivers/net/ethernet/xilinx/ll_temac_mdio.c +++ b/drivers/net/ethernet/xilinx/ll_temac_mdio.c @@ -98,7 +98,9 @@ int temac_mdio_setup(struct temac_local *lp, struct platform_device *pdev) return -ENOMEM; if (np) { - of_address_to_resource(np, 0, &res); + rc = of_address_to_resource(np, 0, &res); + if (rc) + return rc; snprintf(bus->id, MII_BUS_ID_SIZE, "%.8llx", (unsigned long long)res.start); } else if (pdata) { diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index 5cb59d72bc820..4213c3b2d532b 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -633,7 +633,7 @@ static void gtp1u_build_echo_msg(struct gtp1_header_long *hdr, __u8 msg_type) hdr->tid = 0; /* seq, npdu and next should be counted to the length of the GTP packet - * that's why szie of gtp1_header should be subtracted, + * that's why size of gtp1_header should be subtracted, * not size of gtp1_header_long. */ diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index 245a069970556..8336596b12476 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -149,7 +149,6 @@ static irqreturn_t ipa_isr_thread(int irq, void *dev_id) iowrite32(pending, ipa->reg_virt + reg_offset(reg)); } out_power_put: - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); return IRQ_HANDLED; diff --git a/drivers/net/ipa/ipa_main.c b/drivers/net/ipa/ipa_main.c index 25500c5a6928e..95a61bae3124e 100644 --- a/drivers/net/ipa/ipa_main.c +++ b/drivers/net/ipa/ipa_main.c @@ -903,7 +903,6 @@ static int ipa_probe(struct platform_device *pdev) if (ret) goto err_deconfig; done: - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); return 0; diff --git a/drivers/net/ipa/ipa_modem.c b/drivers/net/ipa/ipa_modem.c index 8fe0d0e1a00fd..9b136f6b8b4ae 100644 --- a/drivers/net/ipa/ipa_modem.c +++ b/drivers/net/ipa/ipa_modem.c @@ -71,7 +71,6 @@ static int ipa_open(struct net_device *netdev) netif_start_queue(netdev); - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); return 0; @@ -102,7 +101,6 @@ static int ipa_stop(struct net_device *netdev) ipa_endpoint_disable_one(priv->rx); ipa_endpoint_disable_one(priv->tx); out_power_put: - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); return 0; @@ -175,7 +173,6 @@ ipa_start_xmit(struct sk_buff *skb, struct net_device *netdev) ret = ipa_endpoint_skb_tx(endpoint, skb); - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); if (ret) { @@ -432,7 +429,6 @@ static void ipa_modem_crashed(struct ipa *ipa) dev_err(dev, "error %d zeroing modem memory regions\n", ret); out_power_put: - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); } diff --git a/drivers/net/ipa/ipa_smp2p.c b/drivers/net/ipa/ipa_smp2p.c index fcaadd111a8a3..420098796eec7 100644 --- a/drivers/net/ipa/ipa_smp2p.c +++ b/drivers/net/ipa/ipa_smp2p.c @@ -171,7 +171,6 @@ static irqreturn_t ipa_smp2p_modem_setup_ready_isr(int irq, void *dev_id) WARN(ret != 0, "error %d from ipa_setup()\n", ret); out_power_put: - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); return IRQ_HANDLED; @@ -213,7 +212,6 @@ static void ipa_smp2p_power_release(struct ipa *ipa) if (!ipa->smp2p->power_on) return; - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); ipa->smp2p->power_on = false; } diff --git a/drivers/net/ipa/ipa_uc.c b/drivers/net/ipa/ipa_uc.c index 2963db83ab6b0..dc7e92f2a4fbb 100644 --- a/drivers/net/ipa/ipa_uc.c +++ b/drivers/net/ipa/ipa_uc.c @@ -158,7 +158,6 @@ static void ipa_uc_response_hdlr(struct ipa *ipa) if (ipa->uc_powered) { ipa->uc_loaded = true; ipa_power_retention(ipa, true); - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); ipa->uc_powered = false; } else { @@ -203,7 +202,6 @@ void ipa_uc_deconfig(struct ipa *ipa) if (!ipa->uc_powered) return; - pm_runtime_mark_last_busy(dev); (void)pm_runtime_put_autosuspend(dev); } diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c index 47cdee5577d46..36a1be4923d61 100644 --- a/drivers/net/netdevsim/ipsec.c +++ b/drivers/net/netdevsim/ipsec.c @@ -277,6 +277,7 @@ void nsim_ipsec_init(struct netdevsim *ns) NETIF_F_GSO_ESP) ns->netdev->features |= NSIM_ESP_FEATURES; + ns->netdev->hw_features |= NSIM_ESP_FEATURES; ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES; ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 02c1c97b70080..af6fcfcda8ba8 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -109,6 +109,11 @@ struct netdevsim { int rq_reset_mode; struct { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; + struct u64_stats_sync syncp; struct psp_dev *dev; u32 spi; u32 assoc_cnt; diff --git a/drivers/net/netdevsim/psp.c b/drivers/net/netdevsim/psp.c index 332b5b744f016..727da06101caa 100644 --- a/drivers/net/netdevsim/psp.c +++ b/drivers/net/netdevsim/psp.c @@ -70,6 +70,13 @@ nsim_do_psp(struct sk_buff *skb, struct netdevsim *ns, *psp_ext = skb->extensions; refcount_inc(&(*psp_ext)->refcnt); skb->decrypted = 1; + + u64_stats_update_begin(&ns->psp.syncp); + ns->psp.tx_packets++; + ns->psp.rx_packets++; + ns->psp.tx_bytes += skb->len - skb_inner_transport_offset(skb); + ns->psp.rx_bytes += skb->len - skb_inner_transport_offset(skb); + u64_stats_update_end(&ns->psp.syncp); } else { struct ipv6hdr *ip6h __maybe_unused; struct iphdr *iph; @@ -164,12 +171,32 @@ static void nsim_assoc_del(struct psp_dev *psd, struct psp_assoc *pas) ns->psp.assoc_cnt--; } +static void nsim_get_stats(struct psp_dev *psd, struct psp_dev_stats *stats) +{ + struct netdevsim *ns = psd->drv_priv; + unsigned int start; + + /* WARNING: do *not* blindly zero stats in real drivers! + * All required stats must be reported by the device! + */ + memset(stats, 0, sizeof(struct psp_dev_stats)); + + do { + start = u64_stats_fetch_begin(&ns->psp.syncp); + stats->rx_bytes = ns->psp.rx_bytes; + stats->rx_packets = ns->psp.rx_packets; + stats->tx_bytes = ns->psp.tx_bytes; + stats->tx_packets = ns->psp.tx_packets; + } while (u64_stats_fetch_retry(&ns->psp.syncp, start)); +} + static struct psp_dev_ops nsim_psp_ops = { .set_config = nsim_psp_set_config, .rx_spi_alloc = nsim_rx_spi_alloc, .tx_key_add = nsim_assoc_add, .tx_key_del = nsim_assoc_del, .key_rotate = nsim_key_rotate, + .get_stats = nsim_get_stats, }; static struct psp_dev_caps nsim_psp_caps = { diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c index 492be60f2e70f..0a2fef7caccb9 100644 --- a/drivers/net/netkit.c +++ b/drivers/net/netkit.c @@ -16,17 +16,19 @@ #define DRV_NAME "netkit" struct netkit { - /* Needed in fast-path */ + __cacheline_group_begin(netkit_fastpath); struct net_device __rcu *peer; struct bpf_mprog_entry __rcu *active; enum netkit_action policy; enum netkit_scrub scrub; struct bpf_mprog_bundle bundle; + __cacheline_group_end(netkit_fastpath); - /* Needed in slow-path */ + __cacheline_group_begin(netkit_slowpath); enum netkit_mode mode; bool primary; u32 headroom; + __cacheline_group_end(netkit_slowpath); }; struct netkit_link { diff --git a/drivers/net/pcs/pcs-xpcs-plat.c b/drivers/net/pcs/pcs-xpcs-plat.c index 9e1ccc319a1d9..c422e8d8b89fc 100644 --- a/drivers/net/pcs/pcs-xpcs-plat.c +++ b/drivers/net/pcs/pcs-xpcs-plat.c @@ -456,5 +456,5 @@ static struct platform_driver xpcs_plat_driver = { module_platform_driver(xpcs_plat_driver); MODULE_DESCRIPTION("Synopsys DesignWare XPCS platform device driver"); -MODULE_AUTHOR("Signed-off-by: Serge Semin "); +MODULE_AUTHOR("Serge Semin "); MODULE_LICENSE("GPL"); diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c index 3d1bd5aac0937..69a6c03fd9e79 100644 --- a/drivers/net/pcs/pcs-xpcs.c +++ b/drivers/net/pcs/pcs-xpcs.c @@ -37,6 +37,16 @@ static const int xpcs_10gkr_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_25gbaser_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const int xpcs_xlgmii_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -67,6 +77,40 @@ static const int xpcs_xlgmii_features[] = { __ETHTOOL_LINK_MODE_MASK_NBITS, }; +static const int xpcs_50gbaser_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT, + ETHTOOL_LINK_MODE_50000baseDR_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + +static const int xpcs_50gbaser2_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + +static const int xpcs_100gbasep_features[] = { + ETHTOOL_LINK_MODE_MII_BIT, + ETHTOOL_LINK_MODE_Pause_BIT, + ETHTOOL_LINK_MODE_Asym_Pause_BIT, + ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT, + ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT, + __ETHTOOL_LINK_MODE_MASK_NBITS, +}; + static const int xpcs_10gbaser_features[] = { ETHTOOL_LINK_MODE_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT, @@ -523,9 +567,56 @@ static int xpcs_get_max_xlgmii_speed(struct dw_xpcs *xpcs, return speed; } -static void xpcs_resolve_pma(struct dw_xpcs *xpcs, - struct phylink_link_state *state) +static int xpcs_c45_read_pcs_speed(struct dw_xpcs *xpcs, + struct phylink_link_state *state) { + int pcs_ctrl1; + + pcs_ctrl1 = xpcs_read(xpcs, MDIO_MMD_PCS, MDIO_CTRL1); + if (pcs_ctrl1 < 0) + return pcs_ctrl1; + + switch (pcs_ctrl1 & MDIO_CTRL1_SPEEDSEL) { + case MDIO_PCS_CTRL1_SPEED25G: + state->speed = SPEED_25000; + break; + case MDIO_PCS_CTRL1_SPEED50G: + state->speed = SPEED_50000; + break; + case MDIO_PCS_CTRL1_SPEED100G: + state->speed = SPEED_100000; + break; + default: + state->speed = SPEED_UNKNOWN; + break; + } + + return 0; +} + +static int xpcs_resolve_pma(struct dw_xpcs *xpcs, + struct phylink_link_state *state) +{ + int pma_stat1, err = 0; + + /* The Meta Platforms FBNIC PMD will go into a training state for + * about 4 seconds when the link first comes up. During this time the + * PCS link will bounce. To avoid reporting link up too soon we include + * the PMA/PMD state provided by the driver. + */ + if (xpcs->info.pma == MP_FBNIC_XPCS_PMA_100G_ID) { + pma_stat1 = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_STAT1); + if (pma_stat1 < 0) { + state->link = false; + return pma_stat1; + } + + if (!(pma_stat1 & MDIO_STAT1_LSTATUS)) { + state->link = false; + return 0; + } + } + state->pause = MLO_PAUSE_TX | MLO_PAUSE_RX; state->duplex = DUPLEX_FULL; @@ -536,10 +627,18 @@ static void xpcs_resolve_pma(struct dw_xpcs *xpcs, case PHY_INTERFACE_MODE_XLGMII: state->speed = xpcs_get_max_xlgmii_speed(xpcs, state); break; + case PHY_INTERFACE_MODE_25GBASER: + case PHY_INTERFACE_MODE_50GBASER: + case PHY_INTERFACE_MODE_LAUI: + case PHY_INTERFACE_MODE_100GBASEP: + err = xpcs_c45_read_pcs_speed(xpcs, state); + break; default: state->speed = SPEED_UNKNOWN; break; } + + return err; } static int xpcs_validate(struct phylink_pcs *pcs, unsigned long *supported, @@ -945,10 +1044,10 @@ static int xpcs_get_state_c73(struct dw_xpcs *xpcs, phylink_resolve_c73(state); } else { - xpcs_resolve_pma(xpcs, state); + ret = xpcs_resolve_pma(xpcs, state); } - return 0; + return ret; } static int xpcs_get_state_c37_sgmii(struct dw_xpcs *xpcs, @@ -1284,17 +1383,16 @@ static int xpcs_read_ids(struct dw_xpcs *xpcs) if (ret < 0) return ret; - id = ret; + id = ret << 16; ret = xpcs_read(xpcs, MDIO_MMD_PMAPMD, MDIO_DEVID2); if (ret < 0) return ret; - /* Note the inverted dword order and masked out Model/Revision numbers - * with respect to what is done with the PCS ID... + /* For now we only record the OUI for the PMAPMD, we may want to + * add the model number at some point in the future. */ - ret = (ret >> 10) & 0x3F; - id |= ret << 16; + id |= ret & MDIO_DEVID2_OUI; /* Set the PMA ID if it hasn't been pre-initialized */ if (xpcs->info.pma == DW_XPCS_PMA_ID_NATIVE) @@ -1312,10 +1410,26 @@ static const struct dw_xpcs_compat synopsys_xpcs_compat[] = { .interface = PHY_INTERFACE_MODE_10GKR, .supported = xpcs_10gkr_features, .an_mode = DW_AN_C73, + }, { + .interface = PHY_INTERFACE_MODE_25GBASER, + .supported = xpcs_25gbaser_features, + .an_mode = DW_AN_C73, }, { .interface = PHY_INTERFACE_MODE_XLGMII, .supported = xpcs_xlgmii_features, .an_mode = DW_AN_C73, + }, { + .interface = PHY_INTERFACE_MODE_50GBASER, + .supported = xpcs_50gbaser_features, + .an_mode = DW_AN_C73, + }, { + .interface = PHY_INTERFACE_MODE_LAUI, + .supported = xpcs_50gbaser2_features, + .an_mode = DW_AN_C73, + }, { + .interface = PHY_INTERFACE_MODE_100GBASEP, + .supported = xpcs_100gbasep_features, + .an_mode = DW_AN_C73, }, { .interface = PHY_INTERFACE_MODE_10GBASER, .supported = xpcs_10gbaser_features, @@ -1495,7 +1609,8 @@ static struct dw_xpcs *xpcs_create(struct mdio_device *mdiodev) xpcs_get_interfaces(xpcs, xpcs->pcs.supported_interfaces); - if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID) + if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID || + xpcs->info.pma == MP_FBNIC_XPCS_PMA_100G_ID) xpcs->pcs.poll = false; else xpcs->need_reset = true; diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index 98700d069191a..a7ade7b95a2ee 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -308,7 +308,7 @@ config MICREL_PHY config MICROCHIP_T1S_PHY tristate "Microchip 10BASE-T1S Ethernet PHYs" help - Currently supports the LAN8670/1/2 Rev.B1/C1/C2 and + Currently supports the LAN8670/1/2 Rev.B1/C1/C2/D0 and LAN8650/1 Rev.B0/B1 Internal PHYs. config MICROCHIP_PHY diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 76e0db40f879c..3a34917adea72 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -3,7 +3,7 @@ libphy-y := phy.o phy-c45.o phy-core.o phy_device.o \ linkmode.o phy_link_topology.o \ - phy_caps.o mdio_bus_provider.o + phy_caps.o mdio_bus_provider.o phy_port.o mdio-bus-y += mdio_bus.o mdio_device.o ifdef CONFIG_PHYLIB diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 33db21251f2ef..f31b6d974d22a 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -811,17 +812,6 @@ static int dp83822_of_init(struct phy_device *phydev) int i, ret; u32 val; - /* Signal detection for the PHY is only enabled if the FX_EN and the - * SD_EN pins are strapped. Signal detection can only enabled if FX_EN - * is strapped otherwise signal detection is disabled for the PHY. - */ - if (dp83822->fx_enabled && dp83822->fx_sd_enable) - dp83822->fx_signal_det_low = device_property_present(dev, - "ti,link-loss-low"); - if (!dp83822->fx_enabled) - dp83822->fx_enabled = device_property_present(dev, - "ti,fiber-mode"); - if (!device_property_read_string(dev, "ti,gpio2-clk-out", &of_val)) { if (strcmp(of_val, "mac-if") == 0) { dp83822->gpio2_clk_out = DP83822_CLK_SRC_MAC_IF; @@ -950,6 +940,55 @@ static int dp83822_read_straps(struct phy_device *phydev) return 0; } +static int dp83822_attach_mdi_port(struct phy_device *phydev, + struct phy_port *port) +{ + struct dp83822_private *dp83822 = phydev->priv; + int ret; + + if (port->mediums) { + if (phy_port_is_fiber(port)) + dp83822->fx_enabled = true; + } else { + ret = dp83822_read_straps(phydev); + if (ret) + return ret; + +#if IS_ENABLED(CONFIG_OF_MDIO) + if (dp83822->fx_enabled && dp83822->fx_sd_enable) + dp83822->fx_signal_det_low = + device_property_present(&phydev->mdio.dev, + "ti,link-loss-low"); + + /* ti,fiber-mode is still used for backwards compatibility, but + * has been replaced with the mdi node definition, see + * ethernet-port.yaml + */ + if (!dp83822->fx_enabled) + dp83822->fx_enabled = + device_property_present(&phydev->mdio.dev, + "ti,fiber-mode"); +#endif /* CONFIG_OF_MDIO */ + + if (dp83822->fx_enabled) { + port->mediums = BIT(ETHTOOL_LINK_MEDIUM_BASEF); + } else { + /* This PHY can only to 100BaseTX max, so on 2 pairs */ + port->pairs = 2; + port->mediums = BIT(ETHTOOL_LINK_MEDIUM_BASET); + } + } + + /* If attached from SFP, is_mii is set, but not the mediums. */ + if (port->is_mii) + dp83822->fx_enabled = true; + + if (dp83822->fx_enabled) + __set_bit(PHY_INTERFACE_MODE_100BASEX, port->interfaces); + + return 0; +} + static int dp8382x_probe(struct phy_device *phydev) { struct dp83822_private *dp83822; @@ -968,27 +1007,13 @@ static int dp8382x_probe(struct phy_device *phydev) static int dp83822_probe(struct phy_device *phydev) { - struct dp83822_private *dp83822; int ret; ret = dp8382x_probe(phydev); if (ret) return ret; - dp83822 = phydev->priv; - - ret = dp83822_read_straps(phydev); - if (ret) - return ret; - - ret = dp83822_of_init(phydev); - if (ret) - return ret; - - if (dp83822->fx_enabled) - phydev->port = PORT_FIBRE; - - return 0; + return dp83822_of_init(phydev); } static int dp83826_probe(struct phy_device *phydev) @@ -1172,6 +1197,7 @@ static int dp83822_led_hw_control_get(struct phy_device *phydev, u8 index, .led_hw_is_supported = dp83822_led_hw_is_supported, \ .led_hw_control_set = dp83822_led_hw_control_set, \ .led_hw_control_get = dp83822_led_hw_control_get, \ + .attach_mdi_port = dp83822_attach_mdi_port \ } #define DP83825_PHY_DRIVER(_id, _name) \ diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c index 23af1ac194fa9..d75dae6071ad6 100644 --- a/drivers/net/phy/dp83td510.c +++ b/drivers/net/phy/dp83td510.c @@ -61,6 +61,7 @@ #define DP83TD510E_MASTER_SLAVE_RESOL_FAIL BIT(15) #define DP83TD510E_MSE_DETECT 0xa85 +#define DP83TD510E_MSE_MAX U16_MAX #define DP83TD510_SQI_MAX 7 @@ -249,6 +250,64 @@ struct dp83td510_priv { #define DP83TD510E_ALCD_COMPLETE BIT(15) #define DP83TD510E_ALCD_CABLE_LENGTH GENMASK(10, 0) +static int dp83td510_get_mse_capability(struct phy_device *phydev, + struct phy_mse_capability *cap) +{ + /* DP83TD510E documents only a single (average) MSE register + * (used to derive SQI); no peak or worst-peak counters are + * described. Advertise only PHY_MSE_CAP_AVG. + */ + cap->supported_caps = PHY_MSE_CAP_AVG; + /* 10BASE-T1L is a single-pair medium, so there are no B/C/D channels. + * We still advertise PHY_MSE_CAP_CHANNEL_A to indicate that the PHY + * can attribute the measurement to a specific pair (the only one), + * rather than exposing it only as a link-aggregate. + * + * Rationale: + * - Keeps the ethtool MSE_GET selection logic consistent: per-channel + * (A/B/C/D) is preferred over WORST/LINK, so userspace receives a + * CHANNEL_A nest instead of LINK. + * - Signals to tools that "per-pair" data is available (even if there's + * just one pair), avoiding the impression that only aggregate values + * are supported. + * - Remains compatible with multi-pair PHYs and uniform UI handling. + * + * Note: WORST and other channels are not advertised on 10BASE-T1L. + */ + cap->supported_caps |= PHY_MSE_CHANNEL_A | PHY_MSE_CAP_LINK; + cap->max_average_mse = DP83TD510E_MSE_MAX; + + /* The datasheet does not specify the refresh rate or symbol count, + * but based on similar PHYs and standards, we can assume a common + * value. For 10BASE-T1L, the symbol rate is 7.5 MBd. A common + * diagnostic interval is around 1ms. + * 7.5e6 symbols/sec * 0.001 sec = 7500 symbols. + */ + cap->refresh_rate_ps = 1000000000; /* 1 ms */ + cap->num_symbols = 7500; + + return 0; +} + +static int dp83td510_get_mse_snapshot(struct phy_device *phydev, + enum phy_mse_channel channel, + struct phy_mse_snapshot *snapshot) +{ + int ret; + + if (channel != PHY_MSE_CHANNEL_LINK && + channel != PHY_MSE_CHANNEL_A) + return -EOPNOTSUPP; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_MSE_DETECT); + if (ret < 0) + return ret; + + snapshot->average_mse = ret; + + return 0; +} + static int dp83td510_led_brightness_set(struct phy_device *phydev, u8 index, enum led_brightness brightness) { @@ -893,6 +952,9 @@ static struct phy_driver dp83td510_driver[] = { .get_phy_stats = dp83td510_get_phy_stats, .update_stats = dp83td510_update_stats, + .get_mse_capability = dp83td510_get_mse_capability, + .get_mse_snapshot = dp83td510_get_mse_snapshot, + .led_brightness_set = dp83td510_led_brightness_set, .led_hw_is_supported = dp83td510_led_hw_is_supported, .led_hw_control_set = dp83td510_led_hw_control_set, diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c index 0e1b28f06f189..1ad77f542c1fa 100644 --- a/drivers/net/phy/fixed_phy.c +++ b/drivers/net/phy/fixed_phy.c @@ -19,7 +19,6 @@ #include #include #include -#include #include "swphy.h" @@ -131,12 +130,6 @@ static int __fixed_phy_add(int phy_addr, return 0; } -void fixed_phy_add(const struct fixed_phy_status *status) -{ - __fixed_phy_add(0, status); -} -EXPORT_SYMBOL_GPL(fixed_phy_add); - static DEFINE_IDA(phy_fixed_ida); static void fixed_phy_del(int phy_addr) @@ -180,41 +173,16 @@ struct phy_device *fixed_phy_register(const struct fixed_phy_status *status, } /* propagate the fixed link values to struct phy_device */ - phy->link = status->link; - if (status->link) { - phy->speed = status->speed; - phy->duplex = status->duplex; - phy->pause = status->pause; - phy->asym_pause = status->asym_pause; - } + phy->link = 1; + phy->speed = status->speed; + phy->duplex = status->duplex; + phy->pause = status->pause; + phy->asym_pause = status->asym_pause; of_node_get(np); phy->mdio.dev.of_node = np; phy->is_pseudo_fixed_link = true; - switch (status->speed) { - case SPEED_1000: - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, - phy->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, - phy->supported); - fallthrough; - case SPEED_100: - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, - phy->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, - phy->supported); - fallthrough; - case SPEED_10: - default: - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, - phy->supported); - linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, - phy->supported); - } - - phy_advertise_supported(phy); - ret = phy_device_register(phy); if (ret) { phy_device_free(phy); @@ -227,6 +195,17 @@ struct phy_device *fixed_phy_register(const struct fixed_phy_status *status, } EXPORT_SYMBOL_GPL(fixed_phy_register); +struct phy_device *fixed_phy_register_100fd(void) +{ + static const struct fixed_phy_status status = { + .speed = SPEED_100, + .duplex = DUPLEX_FULL, + }; + + return fixed_phy_register(&status, NULL); +} +EXPORT_SYMBOL_GPL(fixed_phy_register_100fd); + void fixed_phy_unregister(struct phy_device *phy) { phy_device_remove(phy); diff --git a/drivers/net/phy/marvell-88x2222.c b/drivers/net/phy/marvell-88x2222.c index 894bcee61e655..ba1bbb6c63d64 100644 --- a/drivers/net/phy/marvell-88x2222.c +++ b/drivers/net/phy/marvell-88x2222.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include /* Port PCS Configuration */ @@ -473,89 +473,70 @@ static int mv2222_config_init(struct phy_device *phydev) return 0; } -static int mv2222_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +static int mv2222_configure_serdes(struct phy_port *port, bool enable, + phy_interface_t interface) { - struct phy_device *phydev = upstream; - const struct sfp_module_caps *caps; - phy_interface_t sfp_interface; + struct phy_device *phydev = port_phydev(port); struct mv2222_data *priv; - struct device *dev; - int ret; + int ret = 0; priv = phydev->priv; - dev = &phydev->mdio.dev; - - caps = sfp_get_module_caps(phydev->sfp_bus); - - phydev->port = caps->port; - sfp_interface = sfp_select_interface(phydev->sfp_bus, caps->link_modes); - - dev_info(dev, "%s SFP module inserted\n", phy_modes(sfp_interface)); + priv->line_interface = interface; - if (sfp_interface != PHY_INTERFACE_MODE_10GBASER && - sfp_interface != PHY_INTERFACE_MODE_1000BASEX && - sfp_interface != PHY_INTERFACE_MODE_SGMII) { - dev_err(dev, "Incompatible SFP module inserted\n"); + if (enable) { + linkmode_and(priv->supported, phydev->supported, port->supported); - return -EINVAL; - } - - priv->line_interface = sfp_interface; - linkmode_and(priv->supported, phydev->supported, caps->link_modes); + ret = mv2222_config_line(phydev); + if (ret < 0) + return ret; - ret = mv2222_config_line(phydev); - if (ret < 0) - return ret; + if (mutex_trylock(&phydev->lock)) { + ret = mv2222_config_aneg(phydev); + mutex_unlock(&phydev->lock); + } - if (mutex_trylock(&phydev->lock)) { - ret = mv2222_config_aneg(phydev); - mutex_unlock(&phydev->lock); + } else { + linkmode_zero(priv->supported); } return ret; } -static void mv2222_sfp_remove(void *upstream) +static void mv2222_port_link_up(struct phy_port *port) { - struct phy_device *phydev = upstream; - struct mv2222_data *priv; - - priv = phydev->priv; - - priv->line_interface = PHY_INTERFACE_MODE_NA; - linkmode_zero(priv->supported); - phydev->port = PORT_NONE; -} - -static void mv2222_sfp_link_up(void *upstream) -{ - struct phy_device *phydev = upstream; + struct phy_device *phydev = port_phydev(port); struct mv2222_data *priv; priv = phydev->priv; priv->sfp_link = true; } -static void mv2222_sfp_link_down(void *upstream) +static void mv2222_port_link_down(struct phy_port *port) { - struct phy_device *phydev = upstream; + struct phy_device *phydev = port_phydev(port); struct mv2222_data *priv; priv = phydev->priv; priv->sfp_link = false; } -static const struct sfp_upstream_ops sfp_phy_ops = { - .module_insert = mv2222_sfp_insert, - .module_remove = mv2222_sfp_remove, - .link_up = mv2222_sfp_link_up, - .link_down = mv2222_sfp_link_down, - .attach = phy_sfp_attach, - .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, +static const struct phy_port_ops mv2222_port_ops = { + .link_up = mv2222_port_link_up, + .link_down = mv2222_port_link_down, + .configure_mii = mv2222_configure_serdes, }; +static int mv2222_attach_mii_port(struct phy_device *phydev, struct phy_port *port) +{ + port->ops = &mv2222_port_ops; + + __set_bit(PHY_INTERFACE_MODE_10GBASER, port->interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, port->interfaces); + __set_bit(PHY_INTERFACE_MODE_SGMII, port->interfaces); + + return 0; +} + static int mv2222_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; @@ -591,7 +572,7 @@ static int mv2222_probe(struct phy_device *phydev) priv->line_interface = PHY_INTERFACE_MODE_NA; phydev->priv = priv; - return phy_sfp_probe(phydev, &sfp_phy_ops); + return 0; } static struct phy_driver mv2222_drivers[] = { @@ -608,6 +589,7 @@ static struct phy_driver mv2222_drivers[] = { .suspend = mv2222_suspend, .resume = mv2222_resume, .read_status = mv2222_read_status, + .attach_mii_port = mv2222_attach_mii_port, }, }; module_phy_driver(mv2222_drivers); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index c248c90510ae5..542166cfcb232 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -29,10 +29,10 @@ #include #include #include +#include #include #include #include -#include #include #include @@ -3598,11 +3598,10 @@ static int marvell_probe(struct phy_device *phydev) return marvell_hwmon_probe(phydev); } -static int m88e1510_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +static int m88e1510_port_configure_serdes(struct phy_port *port, bool enable, + phy_interface_t interface) { - struct phy_device *phydev = upstream; - const struct sfp_module_caps *caps; - phy_interface_t interface; + struct phy_device *phydev = port_phydev(port); struct device *dev; int oldpage; int ret = 0; @@ -3610,28 +3609,27 @@ static int m88e1510_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) dev = &phydev->mdio.dev; - caps = sfp_get_module_caps(phydev->sfp_bus); - interface = sfp_select_interface(phydev->sfp_bus, caps->link_modes); + if (enable) { + switch (interface) { + case PHY_INTERFACE_MODE_1000BASEX: + mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_1000X; - dev_info(dev, "%s SFP module inserted\n", phy_modes(interface)); + break; + case PHY_INTERFACE_MODE_100BASEX: + mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_100FX; - switch (interface) { - case PHY_INTERFACE_MODE_1000BASEX: - mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_1000X; + break; + case PHY_INTERFACE_MODE_SGMII: + mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_SGMII; - break; - case PHY_INTERFACE_MODE_100BASEX: - mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_100FX; - - break; - case PHY_INTERFACE_MODE_SGMII: - mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII_SGMII; + break; + default: + dev_err(dev, "Incompatible SFP module inserted\n"); - break; - default: - dev_err(dev, "Incompatible SFP module inserted\n"); - - return -EINVAL; + return -EINVAL; + } + } else { + mode = MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII; } oldpage = phy_select_page(phydev, MII_MARVELL_MODE_PAGE); @@ -3648,49 +3646,24 @@ static int m88e1510_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) error: return phy_restore_page(phydev, oldpage, ret); -} - -static void m88e1510_sfp_remove(void *upstream) -{ - struct phy_device *phydev = upstream; - int oldpage; - int ret = 0; - oldpage = phy_select_page(phydev, MII_MARVELL_MODE_PAGE); - if (oldpage < 0) - goto error; - - ret = __phy_modify(phydev, MII_88E1510_GEN_CTRL_REG_1, - MII_88E1510_GEN_CTRL_REG_1_MODE_MASK, - MII_88E1510_GEN_CTRL_REG_1_MODE_RGMII); - if (ret < 0) - goto error; - - ret = __phy_set_bits(phydev, MII_88E1510_GEN_CTRL_REG_1, - MII_88E1510_GEN_CTRL_REG_1_RESET); - -error: - phy_restore_page(phydev, oldpage, ret); + return 0; } -static const struct sfp_upstream_ops m88e1510_sfp_ops = { - .module_insert = m88e1510_sfp_insert, - .module_remove = m88e1510_sfp_remove, - .attach = phy_sfp_attach, - .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, +static const struct phy_port_ops m88e1510_serdes_port_ops = { + .configure_mii = m88e1510_port_configure_serdes, }; -static int m88e1510_probe(struct phy_device *phydev) +static int m88e1510_attach_mii_port(struct phy_device *phy_device, + struct phy_port *port) { - int err; + port->ops = &m88e1510_serdes_port_ops; - err = marvell_probe(phydev); - if (err) - return err; + __set_bit(PHY_INTERFACE_MODE_SGMII, port->interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, port->interfaces); + __set_bit(PHY_INTERFACE_MODE_100BASEX, port->interfaces); - return phy_sfp_probe(phydev, &m88e1510_sfp_ops); + return 0; } static struct phy_driver marvell_drivers[] = { @@ -3950,7 +3923,7 @@ static struct phy_driver marvell_drivers[] = { .driver_data = DEF_MARVELL_HWMON_OPS(m88e1510_hwmon_ops), .features = PHY_GBIT_FIBRE_FEATURES, .flags = PHY_POLL_CABLE_TEST, - .probe = m88e1510_probe, + .probe = marvell_probe, .config_init = m88e1510_config_init, .config_aneg = m88e1510_config_aneg, .read_status = marvell_read_status, @@ -3976,6 +3949,7 @@ static struct phy_driver marvell_drivers[] = { .led_hw_is_supported = m88e1318_led_hw_is_supported, .led_hw_control_set = m88e1318_led_hw_control_set, .led_hw_control_get = m88e1318_led_hw_control_get, + .attach_mii_port = m88e1510_attach_mii_port, }, { .phy_id = MARVELL_PHY_ID_88E1540, diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c index 8fd42131cdbf9..d4cace758fe8d 100644 --- a/drivers/net/phy/marvell10g.c +++ b/drivers/net/phy/marvell10g.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #define MV_PHY_ALASKA_NBT_QUIRK_MASK 0xfffffffe @@ -463,35 +463,35 @@ static int mv3310_set_edpd(struct phy_device *phydev, u16 edpd) return err; } -static int mv3310_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +static int mv3310_attach_mii_port(struct phy_device *phydev, + struct phy_port *port) { - struct phy_device *phydev = upstream; - const struct sfp_module_caps *caps; - phy_interface_t iface; + __set_bit(PHY_INTERFACE_MODE_10GBASER, port->interfaces); + return 0; +} - caps = sfp_get_module_caps(phydev->sfp_bus); - iface = sfp_select_interface(phydev->sfp_bus, caps->link_modes); +static int mv3310_attach_mdi_port(struct phy_device *phydev, + struct phy_port *port) +{ + /* This PHY can do combo-ports, i.e. 2 MDI outputs, usually one + * of them going to an SFP and the other one to a RJ45 + * connector. If we don't have any representation for the port + * in DT, and we are dealing with a non-SFP port, then we + * mask the port's capabilities to report BaseT-only modes + */ + if (port->not_described) + return phy_port_restrict_mediums(port, + BIT(ETHTOOL_LINK_MEDIUM_BASET)); - if (iface != PHY_INTERFACE_MODE_10GBASER) { - dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n"); - return -EINVAL; - } return 0; } -static const struct sfp_upstream_ops mv3310_sfp_ops = { - .attach = phy_sfp_attach, - .detach = phy_sfp_detach, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, - .module_insert = mv3310_sfp_insert, -}; - static int mv3310_probe(struct phy_device *phydev) { const struct mv3310_chip *chip = to_mv3310_chip(phydev); struct mv3310_priv *priv; u32 mmd_mask = MDIO_DEVS_PMAPMD | MDIO_DEVS_AN; + DECLARE_PHY_INTERFACE_MASK(interfaces); int ret; if (!phydev->is_c45 || @@ -542,9 +542,13 @@ static int mv3310_probe(struct phy_device *phydev) if (ret) return ret; + __set_bit(PHY_INTERFACE_MODE_10GBASER, interfaces); + chip->init_supported_interfaces(priv->supported_interfaces); - return phy_sfp_probe(phydev, &mv3310_sfp_ops); + phydev->max_n_ports = 2; + + return 0; } static void mv3310_remove(struct phy_device *phydev) @@ -1405,6 +1409,8 @@ static struct phy_driver mv3310_drivers[] = { .set_loopback = genphy_c45_loopback, .get_wol = mv3110_get_wol, .set_wol = mv3110_set_wol, + .attach_mii_port = mv3310_attach_mii_port, + .attach_mdi_port = mv3310_attach_mdi_port, }, { .phy_id = MARVELL_PHY_ID_88X3310, @@ -1424,6 +1430,8 @@ static struct phy_driver mv3310_drivers[] = { .set_tunable = mv3310_set_tunable, .remove = mv3310_remove, .set_loopback = genphy_c45_loopback, + .attach_mii_port = mv3310_attach_mii_port, + .attach_mdi_port = mv3310_attach_mdi_port, }, { .phy_id = MARVELL_PHY_ID_88E2110, @@ -1444,6 +1452,8 @@ static struct phy_driver mv3310_drivers[] = { .set_loopback = genphy_c45_loopback, .get_wol = mv3110_get_wol, .set_wol = mv3110_set_wol, + .attach_mii_port = mv3310_attach_mii_port, + .attach_mdi_port = mv3310_attach_mdi_port, }, { .phy_id = MARVELL_PHY_ID_88E2110, @@ -1462,6 +1472,8 @@ static struct phy_driver mv3310_drivers[] = { .set_tunable = mv3310_set_tunable, .remove = mv3310_remove, .set_loopback = genphy_c45_loopback, + .attach_mii_port = mv3310_attach_mii_port, + .attach_mdi_port = mv3310_attach_mdi_port, }, }; diff --git a/drivers/net/phy/mdio-open-alliance.h b/drivers/net/phy/mdio-open-alliance.h index 931e14660d759..6850a3f0b31e2 100644 --- a/drivers/net/phy/mdio-open-alliance.h +++ b/drivers/net/phy/mdio-open-alliance.h @@ -43,4 +43,40 @@ /* Version Identifiers */ #define OATC14_IDM 0x0a00 +/* + * Open Alliance TC14 (10BASE-T1S) - Advanced Diagnostic Features Registers + * + * Refer to the OPEN Alliance documentation: + * https://opensig.org/automotive-ethernet-specifications/ + * + * Specification: + * "10BASE-T1S Advanced Diagnostic PHY Features" + * https://opensig.org/wp-content/uploads/2025/06/OPEN_Alliance_10BASE-T1S_Advanced_PHY_features_for-automotive_Ethernet_V2.1b.pdf + */ +/* Advanced Diagnostic Features Capability Register*/ +#define MDIO_OATC14_ADFCAP 0xcc00 +#define OATC14_ADFCAP_HDD_CAPABILITY GENMASK(10, 8) + +/* Harness Defect Detection Register */ +#define MDIO_OATC14_HDD 0xcc01 +#define OATC14_HDD_CONTROL BIT(15) +#define OATC14_HDD_READY BIT(14) +#define OATC14_HDD_START_CONTROL BIT(13) +#define OATC14_HDD_VALID BIT(2) +#define OATC14_HDD_SHORT_OPEN_STATUS GENMASK(1, 0) + +/* Bus Short/Open Status: + * 0 0 - no fault; everything is ok. (Default) + * 0 1 - detected as an open or missing termination(s) + * 1 0 - detected as a short or extra termination(s) + * 1 1 - fault but fault type not detectable. More details can be available by + * vender specific register if supported. + */ +enum oatc14_hdd_status { + OATC14_HDD_STATUS_CABLE_OK = 0, + OATC14_HDD_STATUS_OPEN, + OATC14_HDD_STATUS_SHORT, + OATC14_HDD_STATUS_NOT_DETECTABLE, +}; + #endif /* __MDIO_OPEN_ALLIANCE__ */ diff --git a/drivers/net/phy/mdio_bus_provider.c b/drivers/net/phy/mdio_bus_provider.c index a2391d4b7e5c8..4b0637405740e 100644 --- a/drivers/net/phy/mdio_bus_provider.c +++ b/drivers/net/phy/mdio_bus_provider.c @@ -249,20 +249,15 @@ static int mdiobus_scan_bus_c45(struct mii_bus *bus) */ static bool mdiobus_prevent_c45_scan(struct mii_bus *bus) { - int i; + struct phy_device *phydev; - for (i = 0; i < PHY_MAX_ADDR; i++) { - struct phy_device *phydev; - u32 oui; - - phydev = mdiobus_get_phy(bus, i); - if (!phydev) - continue; - oui = phydev->phy_id >> 10; + mdiobus_for_each_phy(bus, phydev) { + u32 oui = phydev->phy_id >> 10; if (oui == MICREL_OUI) return true; } + return false; } diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index 01c87c9b77020..5d90ccc20df75 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -101,6 +101,8 @@ #define LAN8814_CABLE_DIAG_VCT_DATA_MASK GENMASK(7, 0) #define LAN8814_PAIR_BIT_SHIFT 12 +#define LAN8814_SKUS 0xB + #define LAN8814_WIRE_PAIR_MASK 0xF /* Lan8814 general Interrupt control/status reg in GPHY specific block. */ @@ -367,6 +369,9 @@ #define LAN8842_REV_8832 0x8832 +#define LAN8814_REV_LAN8814 0x8814 +#define LAN8814_REV_LAN8818 0x8818 + struct kszphy_hw_stat { const char *string; u8 reg; @@ -449,6 +454,7 @@ struct kszphy_priv { bool rmii_ref_clk_sel; bool rmii_ref_clk_sel_val; bool clk_enable; + bool is_ptp_available; u64 stats[ARRAY_SIZE(kszphy_hw_stats)]; struct kszphy_phy_stats phy_stats; }; @@ -1056,7 +1062,7 @@ static int ksz9021_config_init(struct phy_device *phydev) #define TX_CLK_ID 0x1f /* set tx and tx_clk to "No delay adjustment" to keep 0ns - * dealy + * delay */ #define TX_ND 0x7 #define TX_CLK_ND 0xf @@ -1919,7 +1925,7 @@ static int ksz886x_config_aneg(struct phy_device *phydev) return ret; if (phydev->autoneg != AUTONEG_ENABLE) { - /* When autonegotation is disabled, we need to manually force + /* When autonegotiation is disabled, we need to manually force * the link state. If we don't do this, the PHY will keep * sending Fast Link Pulses (FLPs) which are part of the * autonegotiation process. This is not desired when @@ -2101,11 +2107,7 @@ static int ksz9477_phy_errata(struct phy_device *phydev) return err; } - err = genphy_restart_aneg(phydev); - if (err) - return err; - - return err; + return genphy_restart_aneg(phydev); } static int ksz9477_config_init(struct phy_device *phydev) @@ -2329,6 +2331,106 @@ static int kszphy_get_sqi_max(struct phy_device *phydev) return KSZ9477_SQI_MAX; } +static int kszphy_get_mse_capability(struct phy_device *phydev, + struct phy_mse_capability *cap) +{ + /* Capabilities depend on link mode: + * - 1000BASE-T: per-pair SQI registers exist => expose A..D + * and a WORST selector. + * - 100BASE-TX: HW provides a single MSE/SQI reading in the "channel A" + * register, but with auto MDI-X there is no MDI-X resolution bit, + * so we cannot map that register to a specific wire pair reliably. + * To avoid misleading per-channel data, advertise only LINK. + * Other speeds: no MSE exposure via this driver. + * + * Note: WORST is *not* a hardware selector on this family. + * We expose it because the driver computes it in software + * by scanning per-channel readouts (A..D) and picking the + * maximum average MSE. + */ + if (phydev->speed == SPEED_1000) + cap->supported_caps = PHY_MSE_CAP_CHANNEL_A | + PHY_MSE_CAP_CHANNEL_B | + PHY_MSE_CAP_CHANNEL_C | + PHY_MSE_CAP_CHANNEL_D | + PHY_MSE_CAP_WORST_CHANNEL; + else if (phydev->speed == SPEED_100) + cap->supported_caps = PHY_MSE_CAP_LINK; + else + return -EOPNOTSUPP; + + cap->max_average_mse = FIELD_MAX(KSZ9477_MMD_SQI_MASK); + cap->refresh_rate_ps = 2000000; /* 2 us */ + /* Estimated from link modulation (125 MBd per channel) and documented + * refresh rate of 2 us + */ + cap->num_symbols = 250; + + cap->supported_caps |= PHY_MSE_CAP_AVG; + + return 0; +} + +static int kszphy_get_mse_snapshot(struct phy_device *phydev, + enum phy_mse_channel channel, + struct phy_mse_snapshot *snapshot) +{ + u8 num_channels; + int ret; + + if (phydev->speed == SPEED_1000) + num_channels = 4; + else if (phydev->speed == SPEED_100) + num_channels = 1; + else + return -EOPNOTSUPP; + + if (channel == PHY_MSE_CHANNEL_WORST) { + u32 worst_val = 0; + int i; + + /* WORST is implemented in software: select the maximum + * average MSE across the available per-channel registers. + * Only defined when multiple channels exist (1000BASE-T). + */ + if (num_channels < 2) + return -EOPNOTSUPP; + + for (i = 0; i < num_channels; i++) { + ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, + KSZ9477_MMD_SIGNAL_QUALITY_CHAN_A + i); + if (ret < 0) + return ret; + + ret = FIELD_GET(KSZ9477_MMD_SQI_MASK, ret); + if (ret > worst_val) + worst_val = ret; + } + snapshot->average_mse = worst_val; + } else if (channel == PHY_MSE_CHANNEL_LINK && num_channels == 1) { + ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, + KSZ9477_MMD_SIGNAL_QUALITY_CHAN_A); + if (ret < 0) + return ret; + snapshot->average_mse = FIELD_GET(KSZ9477_MMD_SQI_MASK, ret); + } else if (channel >= PHY_MSE_CHANNEL_A && + channel <= PHY_MSE_CHANNEL_D) { + /* Per-channel readouts are valid only for 1000BASE-T. */ + if (phydev->speed != SPEED_1000) + return -EOPNOTSUPP; + + ret = phy_read_mmd(phydev, MDIO_MMD_PMAPMD, + KSZ9477_MMD_SIGNAL_QUALITY_CHAN_A + channel); + if (ret < 0) + return ret; + snapshot->average_mse = FIELD_GET(KSZ9477_MMD_SQI_MASK, ret); + } else { + return -EOPNOTSUPP; + } + + return 0; +} + static void kszphy_enable_clk(struct phy_device *phydev) { struct kszphy_priv *priv = phydev->priv; @@ -2886,6 +2988,8 @@ static int ksz886x_cable_test_get_status(struct phy_device *phydev, #define LAN_EXT_PAGE_ACCESS_ADDRESS_DATA 0x17 #define LAN_EXT_PAGE_ACCESS_CTRL_EP_FUNC 0x4000 +#define LAN8814_QSGMII_TX_CONFIG 0x35 +#define LAN8814_QSGMII_TX_CONFIG_QSGMII BIT(3) #define LAN8814_QSGMII_SOFT_RESET 0x43 #define LAN8814_QSGMII_SOFT_RESET_BIT BIT(0) #define LAN8814_QSGMII_PCS1G_ANEG_CONFIG 0x13 @@ -3557,7 +3661,7 @@ static void lan8814_ptp_disable_event(struct phy_device *phydev, int event) /* Set target to too far in the future, effectively disabling it */ lan8814_ptp_set_target(phydev, event, 0xFFFFFFFF, 0); - /* And then reload once it recheas the target */ + /* And then reload once it reaches the target */ lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, LAN8814_PTP_GENERAL_CONFIG, LAN8814_PTP_GENERAL_CONFIG_RELOAD_ADD_X(event), LAN8814_PTP_GENERAL_CONFIG_RELOAD_ADD_X(event)); @@ -4150,6 +4254,17 @@ static int lan8804_config_intr(struct phy_device *phydev) return 0; } +/* Check if the PHY has 1588 support. There are multiple skus of the PHY and + * some of them support PTP while others don't support it. This function will + * return true is the sku supports it, otherwise will return false. + */ +static bool lan8814_has_ptp(struct phy_device *phydev) +{ + struct kszphy_priv *priv = phydev->priv; + + return priv->is_ptp_available; +} + static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) { int ret = IRQ_NONE; @@ -4166,6 +4281,9 @@ static irqreturn_t lan8814_handle_interrupt(struct phy_device *phydev) ret = IRQ_HANDLED; } + if (!lan8814_has_ptp(phydev)) + return ret; + while (true) { irq_status = lanphy_read_page_reg(phydev, LAN8814_PAGE_PORT_REGS, PTP_TSU_INT_STS); @@ -4227,6 +4345,9 @@ static void lan8814_ptp_init(struct phy_device *phydev) !IS_ENABLED(CONFIG_NETWORK_PHY_TIMESTAMPING)) return; + if (!lan8814_has_ptp(phydev)) + return; + lanphy_write_page_reg(phydev, LAN8814_PAGE_PORT_REGS, TSU_HARD_RESET, TSU_HARD_RESET_); @@ -4356,6 +4477,9 @@ static int __lan8814_ptp_probe_once(struct phy_device *phydev, char *pin_name, static int lan8814_ptp_probe_once(struct phy_device *phydev) { + if (!lan8814_has_ptp(phydev)) + return 0; + return __lan8814_ptp_probe_once(phydev, "lan8814_ptp_pin", LAN8814_PTP_GPIO_NUM); } @@ -4379,12 +4503,24 @@ static void lan8814_setup_led(struct phy_device *phydev, int val) static int lan8814_config_init(struct phy_device *phydev) { struct kszphy_priv *lan8814 = phydev->priv; + int ret; - /* Disable ANEG with QSGMII PCS Host side */ - lanphy_modify_page_reg(phydev, LAN8814_PAGE_PORT_REGS, - LAN8814_QSGMII_PCS1G_ANEG_CONFIG, - LAN8814_QSGMII_PCS1G_ANEG_CONFIG_ANEG_ENA, - 0); + /* Based on the interface type select how the advertise ability is + * encoded, to set as SGMII or as USGMII. + */ + if (phydev->interface == PHY_INTERFACE_MODE_QSGMII) + ret = lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_TX_CONFIG, + LAN8814_QSGMII_TX_CONFIG_QSGMII, + LAN8814_QSGMII_TX_CONFIG_QSGMII); + else + ret = lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_QSGMII_TX_CONFIG, + LAN8814_QSGMII_TX_CONFIG_QSGMII, + 0); + + if (ret < 0) + return ret; /* MDI-X setting for swap A,B transmit */ lanphy_modify_page_reg(phydev, LAN8814_PAGE_PCS_DIGITAL, LAN8814_ALIGN_SWAP, @@ -4421,7 +4557,7 @@ static int lan8814_release_coma_mode(struct phy_device *phydev) static void lan8814_clear_2psp_bit(struct phy_device *phydev) { /* It was noticed that when traffic is passing through the PHY and the - * cable is removed then the LED was still one even though there is no + * cable is removed then the LED was still on even though there is no * link */ lanphy_modify_page_reg(phydev, LAN8814_PAGE_PCS_DIGITAL, LAN8814_EEE_STATE, @@ -4464,6 +4600,18 @@ static int lan8814_probe(struct phy_device *phydev) devm_phy_package_join(&phydev->mdio.dev, phydev, addr, sizeof(struct lan8814_shared_priv)); + /* There are lan8814 SKUs that don't support PTP. Make sure that for + * those skus no PTP device is created. Here we check if the SKU + * supports PTP. + */ + err = lanphy_read_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, + LAN8814_SKUS); + if (err < 0) + return err; + + priv->is_ptp_available = err == LAN8814_REV_LAN8814 || + err == LAN8814_REV_LAN8818; + if (phy_package_init_once(phydev)) { /* Reset the PHY */ lanphy_modify_page_reg(phydev, LAN8814_PAGE_COMMON_REGS, @@ -4567,7 +4715,7 @@ static int lan8841_config_init(struct phy_device *phydev) phy_write_mmd(phydev, KSZ9131RN_MMD_COMMON_CTRL_REG, LAN8841_PTP_TX_VERSION, 0xff00); - /* 100BT Clause 40 improvenent errata */ + /* 100BT Clause 40 improvement errata */ phy_write_mmd(phydev, LAN8841_MMD_ANALOG_REG, LAN8841_ANALOG_CONTROL_1, LAN8841_ANALOG_CONTROL_1_PLL_TRIM(0x2)); @@ -5587,7 +5735,7 @@ static int lan8841_ptp_extts_on(struct kszphy_ptp_priv *ptp_priv, int pin, u16 tmp = 0; int ret; - /* Set GPIO to be intput */ + /* Set GPIO to be input */ ret = phy_set_bits_mmd(phydev, 2, LAN8841_GPIO_EN, BIT(pin)); if (ret) return ret; @@ -6506,6 +6654,8 @@ static struct phy_driver ksphy_driver[] = { .suspend = genphy_suspend, .resume = kszphy_resume, .config_intr = lan8814_config_intr, + .inband_caps = lan8842_inband_caps, + .config_inband = lan8842_config_inband, .handle_interrupt = lan8814_handle_interrupt, .cable_test_start = lan8814_cable_test_start, .cable_test_get_status = ksz886x_cable_test_get_status, @@ -6626,6 +6776,8 @@ static struct phy_driver ksphy_driver[] = { .cable_test_get_status = ksz9x31_cable_test_get_status, .get_sqi = kszphy_get_sqi, .get_sqi_max = kszphy_get_sqi_max, + .get_mse_capability = kszphy_get_mse_capability, + .get_mse_snapshot = kszphy_get_mse_snapshot, } }; module_phy_driver(ksphy_driver); diff --git a/drivers/net/phy/microchip_t1s.c b/drivers/net/phy/microchip_t1s.c index e50a0c102a862..5a0a667789770 100644 --- a/drivers/net/phy/microchip_t1s.c +++ b/drivers/net/phy/microchip_t1s.c @@ -3,7 +3,7 @@ * Driver for Microchip 10BASE-T1S PHYs * * Support: Microchip Phys: - * lan8670/1/2 Rev.B1/C1/C2 + * lan8670/1/2 Rev.B1/C1/C2/D0 * lan8650/1 Rev.B0/B1 Internal PHYs */ @@ -14,6 +14,7 @@ #define PHY_ID_LAN867X_REVB1 0x0007C162 #define PHY_ID_LAN867X_REVC1 0x0007C164 #define PHY_ID_LAN867X_REVC2 0x0007C165 +#define PHY_ID_LAN867X_REVD0 0x0007C166 /* Both Rev.B0 and B1 clause 22 PHYID's are same due to B1 chip limitation */ #define PHY_ID_LAN865X_REVB 0x0007C1B3 @@ -32,6 +33,17 @@ #define COL_DET_ENABLE BIT(15) #define COL_DET_DISABLE 0x0000 +/* LAN8670/1/2 Rev.D0 Link Status Selection Register */ +#define LAN867X_REG_LINK_STATUS_CTRL 0x0012 +#define LINK_STATUS_CONFIGURATION GENMASK(12, 11) +#define LINK_STATUS_SEMAPHORE BIT(0) + +/* Link Status Configuration */ +#define LINK_STATUS_CONFIG_PLCA_STATUS 0x1 +#define LINK_STATUS_CONFIG_SEMAPHORE 0x2 + +#define LINK_STATUS_SEMAPHORE_SET 0x1 + #define LAN865X_CFGPARAM_READ_ENABLE BIT(1) /* The arrays below are pulled from the following table from AN1699 @@ -109,6 +121,21 @@ static const u16 lan865x_revb_sqi_fixup_cfg_regs[3] = { 0x00AD, 0x00AE, 0x00AF, }; +/* LAN867x Rev.D0 configuration parameters from AN1699 + * As per the Configuration Application Note AN1699 published in the below link, + * https://www.microchip.com/en-us/application-notes/an1699 + * Revision G (DS60001699G - October 2025) + */ +static const u16 lan867x_revd0_fixup_regs[8] = { + 0x0037, 0x008A, 0x0118, 0x00D6, + 0x0082, 0x00FD, 0x00FD, 0x0091, +}; + +static const u16 lan867x_revd0_fixup_values[8] = { + 0x0800, 0xBFC0, 0x029C, 0x1001, + 0x001C, 0x0C0B, 0x8C07, 0x9660, +}; + /* Pulled from AN1760 describing 'indirect read' * * write_register(0x4, 0x00D8, addr) @@ -377,6 +404,32 @@ static int lan867x_revb1_config_init(struct phy_device *phydev) return 0; } +static int lan867x_revd0_link_active_selection(struct phy_device *phydev, + bool plca_enabled) +{ + u16 value; + + if (plca_enabled) { + /* 0x1 - When PLCA is enabled: link status reflects plca_status. + */ + value = FIELD_PREP(LINK_STATUS_CONFIGURATION, + LINK_STATUS_CONFIG_PLCA_STATUS); + } else { + /* 0x2 - Link status is controlled by the value written into the + * LINK_STATUS_SEMAPHORE bit written. Here the link semaphore + * bit is written with 0x1 to set the link always active in + * CSMA/CD mode as it doesn't support autoneg. + */ + value = FIELD_PREP(LINK_STATUS_CONFIGURATION, + LINK_STATUS_CONFIG_SEMAPHORE) | + FIELD_PREP(LINK_STATUS_SEMAPHORE, + LINK_STATUS_SEMAPHORE_SET); + } + + return phy_write_mmd(phydev, MDIO_MMD_VEND2, + LAN867X_REG_LINK_STATUS_CTRL, value); +} + /* As per LAN8650/1 Rev.B0/B1 AN1760 (Revision F (DS60001760G - June 2024)) and * LAN8670/1/2 Rev.C1/C2 AN1699 (Revision E (DS60001699F - June 2024)), under * normal operation, the device should be operated in PLCA mode. Disabling @@ -393,6 +446,14 @@ static int lan86xx_plca_set_cfg(struct phy_device *phydev, { int ret; + /* Link status selection must be configured for LAN8670/1/2 Rev.D0 */ + if (phydev->phy_id == PHY_ID_LAN867X_REVD0) { + ret = lan867x_revd0_link_active_selection(phydev, + plca_cfg->enabled); + if (ret) + return ret; + } + ret = genphy_c45_plca_set_cfg(phydev, plca_cfg); if (ret) return ret; @@ -407,6 +468,29 @@ static int lan86xx_plca_set_cfg(struct phy_device *phydev, COL_DET_CTRL0_ENABLE_BIT_MASK, COL_DET_ENABLE); } +static int lan867x_revd0_config_init(struct phy_device *phydev) +{ + int ret; + + ret = lan867x_check_reset_complete(phydev); + if (ret) + return ret; + + for (int i = 0; i < ARRAY_SIZE(lan867x_revd0_fixup_regs); i++) { + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + lan867x_revd0_fixup_regs[i], + lan867x_revd0_fixup_values[i]); + if (ret) + return ret; + } + + /* Initially the PHY will be in CSMA/CD mode by default. So it is + * required to set the link always active as it doesn't support + * autoneg. + */ + return lan867x_revd0_link_active_selection(phydev, false); +} + static int lan86xx_read_status(struct phy_device *phydev) { /* The phy has some limitations, namely: @@ -481,6 +565,17 @@ static struct phy_driver microchip_t1s_driver[] = { .set_plca_cfg = lan86xx_plca_set_cfg, .get_plca_status = genphy_c45_plca_get_status, }, + { + PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVD0), + .name = "LAN867X Rev.D0", + .features = PHY_BASIC_T1S_P2MP_FEATURES, + .config_init = lan867x_revd0_config_init, + .get_plca_cfg = genphy_c45_plca_get_cfg, + .set_plca_cfg = lan86xx_plca_set_cfg, + .get_plca_status = genphy_c45_plca_get_status, + .cable_test_start = genphy_c45_oatc14_cable_test_start, + .cable_test_get_status = genphy_c45_oatc14_cable_test_get_status, + }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN865X_REVB), .name = "LAN865X Rev.B0/B1 Internal Phy", @@ -501,6 +596,7 @@ static const struct mdio_device_id __maybe_unused tbl[] = { { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVB1) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVC1) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVC2) }, + { PHY_ID_MATCH_EXACT(PHY_ID_LAN867X_REVD0) }, { PHY_ID_MATCH_EXACT(PHY_ID_LAN865X_REVB) }, { } }; diff --git a/drivers/net/phy/motorcomm.c b/drivers/net/phy/motorcomm.c index a3593e6630594..89b5b19a9bd28 100644 --- a/drivers/net/phy/motorcomm.c +++ b/drivers/net/phy/motorcomm.c @@ -3048,6 +3048,9 @@ static struct phy_driver motorcomm_phy_drvs[] = { .get_wol = ytphy_get_wol, .set_wol = yt8531_set_wol, .link_change_notify = yt8531_link_change_notify, + .led_hw_is_supported = yt8521_led_hw_is_supported, + .led_hw_control_set = yt8521_led_hw_control_set, + .led_hw_control_get = yt8521_led_hw_control_get, }, { PHY_ID_MATCH_EXACT(PHY_ID_YT8531S), diff --git a/drivers/net/phy/mscc/mscc.h b/drivers/net/phy/mscc/mscc.h index 2d8eca54c40a2..65c9d7bd93150 100644 --- a/drivers/net/phy/mscc/mscc.h +++ b/drivers/net/phy/mscc/mscc.h @@ -85,6 +85,10 @@ enum rgmii_clock_delay { #define LED_MODE_SEL_MASK(x) (GENMASK(3, 0) << LED_MODE_SEL_POS(x)) #define LED_MODE_SEL(x, mode) (((mode) << LED_MODE_SEL_POS(x)) & LED_MODE_SEL_MASK(x)) +#define MSCC_PHY_LED_BEHAVIOR 30 +#define LED_COMBINE_DIS_MASK(x) BIT(x) +#define LED_COMBINE_DIS(x, dis) (((dis) ? 1 : 0) << (x)) + #define MSCC_EXT_PAGE_CSR_CNTL_17 17 #define MSCC_EXT_PAGE_CSR_CNTL_18 18 @@ -289,12 +293,12 @@ enum rgmii_clock_delay { #define PHY_ID_VSC8540 0x00070760 #define PHY_ID_VSC8541 0x00070770 #define PHY_ID_VSC8552 0x000704e0 -#define PHY_ID_VSC856X 0x000707e0 +#define PHY_ID_VSC856X 0x000707e1 #define PHY_ID_VSC8572 0x000704d0 #define PHY_ID_VSC8574 0x000704a0 -#define PHY_ID_VSC8575 0x000707d0 -#define PHY_ID_VSC8582 0x000707b0 -#define PHY_ID_VSC8584 0x000707c0 +#define PHY_ID_VSC8575 0x000707d1 +#define PHY_ID_VSC8582 0x000707b1 +#define PHY_ID_VSC8584 0x000707c1 #define PHY_VENDOR_MSCC 0x00070400 #define MSCC_VDDMAC_1500 1500 diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c index ef0ef1570d392..2b9fb8a675a65 100644 --- a/drivers/net/phy/mscc/mscc_main.c +++ b/drivers/net/phy/mscc/mscc_main.c @@ -22,6 +22,24 @@ #include "mscc_serdes.h" #include "mscc.h" +struct vsc85xx_probe_config { + const struct vsc85xx_hw_stat *hw_stats; + size_t shared_size; + size_t nstats; + u16 supp_led_modes; + u8 nleds; + bool check_rate_magic; + bool use_package; + bool has_ptp; +}; + +static const u32 vsc85xx_default_led_modes_4[] = { + VSC8531_LINK_1000_ACTIVITY, + VSC8531_LINK_100_ACTIVITY, + VSC8531_LINK_ACTIVITY, + VSC8531_DUPLEX_COLLISION +}; + static const struct vsc85xx_hw_stat vsc85xx_hw_stats[] = { { .string = "phy_receive_errors", @@ -177,17 +195,19 @@ static int vsc85xx_led_cntl_set(struct phy_device *phydev, u8 led_num, u8 mode) { - int rc; - u16 reg_val; + u16 mask = LED_MODE_SEL_MASK(led_num); + u16 val = LED_MODE_SEL(led_num, mode); - mutex_lock(&phydev->lock); - reg_val = phy_read(phydev, MSCC_PHY_LED_MODE_SEL); - reg_val &= ~LED_MODE_SEL_MASK(led_num); - reg_val |= LED_MODE_SEL(led_num, (u16)mode); - rc = phy_write(phydev, MSCC_PHY_LED_MODE_SEL, reg_val); - mutex_unlock(&phydev->lock); + return phy_modify(phydev, MSCC_PHY_LED_MODE_SEL, mask, val); +} - return rc; +static int vsc85xx_led_combine_disable_set(struct phy_device *phydev, + u8 led_num, bool combine_disable) +{ + u16 val = LED_COMBINE_DIS(led_num, combine_disable); + u16 mask = LED_COMBINE_DIS_MASK(led_num); + + return phy_modify(phydev, MSCC_PHY_LED_BEHAVIOR, mask, val); } static int vsc85xx_mdix_get(struct phy_device *phydev, u8 *mdix) @@ -443,7 +463,7 @@ static int vsc85xx_dt_led_mode_get(struct phy_device *phydev, #endif /* CONFIG_OF_MDIO */ static int vsc85xx_dt_led_modes_get(struct phy_device *phydev, - u32 *default_mode) + const u32 *default_mode) { struct vsc8531_private *priv = phydev->priv; char led_dt_prop[28]; @@ -1724,12 +1744,6 @@ static int vsc8584_config_init(struct phy_device *phydev) * in this pre-init function. */ if (phy_package_init_once(phydev)) { - /* The following switch statement assumes that the lowest - * nibble of the phy_id_mask is always 0. This works because - * the lowest nibble of the PHY_ID's below are also 0. - */ - WARN_ON(phydev->drv->phy_id_mask & 0xf); - switch (phydev->phy_id & phydev->drv->phy_id_mask) { case PHY_ID_VSC8504: case PHY_ID_VSC8552: @@ -2224,12 +2238,13 @@ static int vsc85xx_config_inband(struct phy_device *phydev, unsigned int modes) reg_val); } -static int vsc8514_probe(struct phy_device *phydev) +static int vsc85xx_probe_common(struct phy_device *phydev, + const struct vsc85xx_probe_config *cfg, + const u32 *default_led_mode) { struct vsc8531_private *vsc8531; - u32 default_mode[4] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY, VSC8531_LINK_ACTIVITY, - VSC8531_DUPLEX_COLLISION}; + struct device_node *np; + int ret; vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); if (!vsc8531) @@ -2237,124 +2252,291 @@ static int vsc8514_probe(struct phy_device *phydev) phydev->priv = vsc8531; - vsc8584_get_base_addr(phydev); - devm_phy_package_join(&phydev->mdio.dev, phydev, - vsc8531->base_addr, 0); + /* Check rate magic if needed (only for non-package PHYs) */ + if (cfg->check_rate_magic) { + ret = vsc85xx_edge_rate_magic_get(phydev); + if (ret < 0) + return ret; - vsc8531->nleds = 4; - vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; - vsc8531->hw_stats = vsc85xx_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); + vsc8531->rate_magic = ret; + } + + /* Set up package if needed */ + if (cfg->use_package) { + vsc8584_get_base_addr(phydev); + ret = devm_phy_package_join(&phydev->mdio.dev, phydev, + vsc8531->base_addr, + cfg->shared_size); + if (ret) + return ret; + } + + /* Configure LED settings */ + vsc8531->nleds = cfg->nleds; + vsc8531->supp_led_modes = cfg->supp_led_modes; + + /* Configure hardware stats */ + vsc8531->hw_stats = cfg->hw_stats; + vsc8531->nstats = cfg->nstats; vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, sizeof(u64), GFP_KERNEL); if (!vsc8531->stats) return -ENOMEM; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + /* PTP setup for VSC8584 */ + if (cfg->has_ptp) { + if (phy_package_probe_once(phydev)) { + ret = vsc8584_ptp_probe_once(phydev); + if (ret) + return ret; + } + + ret = vsc8584_ptp_probe(phydev); + if (ret) + return ret; + } + + /* + * Check for LED configuration in device tree if available + * or fall back to default `vsc8531,led-x-mode` DT properties. + */ + np = of_get_child_by_name(phydev->mdio.dev.of_node, "leds"); + if (np) { + of_node_put(np); + + /* Force to defaults */ + for (unsigned int i = 0; i < vsc8531->nleds; i++) + vsc8531->leds_mode[i] = default_led_mode[i]; + + return 0; + } + + /* Parse LED modes from device tree */ + return vsc85xx_dt_led_modes_get(phydev, default_led_mode); } -static int vsc8574_probe(struct phy_device *phydev) +static int vsc85xx_led_brightness_set(struct phy_device *phydev, + u8 index, enum led_brightness value) { - struct vsc8531_private *vsc8531; - u32 default_mode[4] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY, VSC8531_LINK_ACTIVITY, - VSC8531_DUPLEX_COLLISION}; + struct vsc8531_private *vsc8531 = phydev->priv; - vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); - if (!vsc8531) - return -ENOMEM; + if (index >= vsc8531->nleds) + return -EINVAL; - phydev->priv = vsc8531; + return vsc85xx_led_cntl_set(phydev, index, value == LED_OFF ? + VSC8531_FORCE_LED_OFF : VSC8531_FORCE_LED_ON); +} - vsc8584_get_base_addr(phydev); - devm_phy_package_join(&phydev->mdio.dev, phydev, - vsc8531->base_addr, 0); +static int vsc85xx_led_hw_is_supported(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + static const unsigned long supported = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK) | + BIT(TRIGGER_NETDEV_RX) | + BIT(TRIGGER_NETDEV_TX); + struct vsc8531_private *vsc8531 = phydev->priv; - vsc8531->nleds = 4; - vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; - vsc8531->hw_stats = vsc8584_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); - if (!vsc8531->stats) - return -ENOMEM; + if (index >= vsc8531->nleds) + return -EINVAL; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + if (rules & ~supported) + return -EOPNOTSUPP; + + return 0; } -static int vsc8584_probe(struct phy_device *phydev) +static int vsc85xx_led_hw_control_get(struct phy_device *phydev, u8 index, + unsigned long *rules) { - struct vsc8531_private *vsc8531; - u32 default_mode[4] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY, VSC8531_LINK_ACTIVITY, - VSC8531_DUPLEX_COLLISION}; - int ret; + struct vsc8531_private *vsc8531 = phydev->priv; + u8 mode, behavior; + int rc; - if ((phydev->phy_id & MSCC_DEV_REV_MASK) != VSC8584_REVB) { - dev_err(&phydev->mdio.dev, "Only VSC8584 revB is supported.\n"); - return -ENOTSUPP; - } + if (index >= vsc8531->nleds) + return -EINVAL; - vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); - if (!vsc8531) - return -ENOMEM; + rc = phy_read(phydev, MSCC_PHY_LED_MODE_SEL); + if (rc < 0) + return rc; + mode = (rc & LED_MODE_SEL_MASK(index)) >> LED_MODE_SEL_POS(index); - phydev->priv = vsc8531; + rc = phy_read(phydev, MSCC_PHY_LED_BEHAVIOR); + if (rc < 0) + return rc; + behavior = (rc & LED_COMBINE_DIS_MASK(index)) >> index; - vsc8584_get_base_addr(phydev); - devm_phy_package_join(&phydev->mdio.dev, phydev, vsc8531->base_addr, - sizeof(struct vsc85xx_shared_private)); + switch (mode) { + case VSC8531_LINK_ACTIVITY: + case VSC8531_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK); + break; - vsc8531->nleds = 4; - vsc8531->supp_led_modes = VSC8584_SUPP_LED_MODES; - vsc8531->hw_stats = vsc8584_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc8584_hw_stats); - vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); - if (!vsc8531->stats) - return -ENOMEM; + case VSC8531_LINK_1000_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK); + break; - if (phy_package_probe_once(phydev)) { - ret = vsc8584_ptp_probe_once(phydev); - if (ret) - return ret; + case VSC8531_LINK_100_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_10_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_100_1000_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_10_1000_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_1000) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK); + break; + + case VSC8531_LINK_10_100_ACTIVITY: + *rules = BIT(TRIGGER_NETDEV_LINK_100) | + BIT(TRIGGER_NETDEV_LINK_10) | + BIT(TRIGGER_NETDEV_LINK); + break; + + default: + *rules = 0; + break; } - ret = vsc8584_ptp_probe(phydev); - if (ret) + if (!behavior && *rules) + *rules |= BIT(TRIGGER_NETDEV_RX) | BIT(TRIGGER_NETDEV_TX); + + return 0; +} + +static int vsc85xx_led_hw_control_set(struct phy_device *phydev, u8 index, + unsigned long rules) +{ + struct vsc8531_private *vsc8531 = phydev->priv; + u8 mode = VSC8531_FORCE_LED_ON; + bool combine_disable = false; + bool has_rx, has_tx; + int ret; + + if (index >= vsc8531->nleds) + return -EINVAL; + + if (rules & BIT(TRIGGER_NETDEV_LINK)) + mode = VSC8531_LINK_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_10)) + mode = VSC8531_LINK_10_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_100)) + mode = VSC8531_LINK_100_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = VSC8531_LINK_1000_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_100) && + rules & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = VSC8531_LINK_100_1000_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_10) && + rules & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = VSC8531_LINK_10_1000_ACTIVITY; + + if (rules & BIT(TRIGGER_NETDEV_LINK_10) && + rules & BIT(TRIGGER_NETDEV_LINK_100)) + mode = VSC8531_LINK_10_100_ACTIVITY; + + /* + * The VSC85xx PHYs provides an option to control LED behavior. By + * default, the LEDx combine function is enabled, meaning the LED + * will be on when there is link/activity or duplex/collision. If + * the combine function is disabled, the LED will be on only for + * link or duplex. + * + * To control this behavior, we check the selected rules. If both + * RX and TX activity are not selected, the LED combine function + * is disabled; otherwise, it remains enabled. + */ + has_rx = !!(rules & BIT(TRIGGER_NETDEV_RX)); + has_tx = !!(rules & BIT(TRIGGER_NETDEV_TX)); + if (!has_rx && !has_tx) + combine_disable = true; + + ret = vsc85xx_led_combine_disable_set(phydev, index, combine_disable); + if (ret < 0) return ret; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + return vsc85xx_led_cntl_set(phydev, index, mode); } -static int vsc85xx_probe(struct phy_device *phydev) +static int vsc8514_probe(struct phy_device *phydev) { - struct vsc8531_private *vsc8531; - int rate_magic; - u32 default_mode[2] = {VSC8531_LINK_1000_ACTIVITY, - VSC8531_LINK_100_ACTIVITY}; + static const struct vsc85xx_probe_config vsc8514_cfg = { + .nleds = 4, + .supp_led_modes = VSC85XX_SUPP_LED_MODES, + .hw_stats = vsc85xx_hw_stats, + .nstats = ARRAY_SIZE(vsc85xx_hw_stats), + .use_package = true, + .shared_size = 0, + .has_ptp = false, + .check_rate_magic = false, + }; - rate_magic = vsc85xx_edge_rate_magic_get(phydev); - if (rate_magic < 0) - return rate_magic; + return vsc85xx_probe_common(phydev, &vsc8514_cfg, vsc85xx_default_led_modes_4); +} - vsc8531 = devm_kzalloc(&phydev->mdio.dev, sizeof(*vsc8531), GFP_KERNEL); - if (!vsc8531) - return -ENOMEM; +static int vsc8574_probe(struct phy_device *phydev) +{ + static const struct vsc85xx_probe_config vsc8574_cfg = { + .nleds = 4, + .supp_led_modes = VSC8584_SUPP_LED_MODES, + .hw_stats = vsc8584_hw_stats, + .nstats = ARRAY_SIZE(vsc8584_hw_stats), + .use_package = true, + .shared_size = 0, + .has_ptp = false, + .check_rate_magic = false, + }; - phydev->priv = vsc8531; + return vsc85xx_probe_common(phydev, &vsc8574_cfg, vsc85xx_default_led_modes_4); +} - vsc8531->rate_magic = rate_magic; - vsc8531->nleds = 2; - vsc8531->supp_led_modes = VSC85XX_SUPP_LED_MODES; - vsc8531->hw_stats = vsc85xx_hw_stats; - vsc8531->nstats = ARRAY_SIZE(vsc85xx_hw_stats); - vsc8531->stats = devm_kcalloc(&phydev->mdio.dev, vsc8531->nstats, - sizeof(u64), GFP_KERNEL); - if (!vsc8531->stats) - return -ENOMEM; +static int vsc8584_probe(struct phy_device *phydev) +{ + static const struct vsc85xx_probe_config vsc8584_cfg = { + .nleds = 4, + .supp_led_modes = VSC8584_SUPP_LED_MODES, + .hw_stats = vsc8584_hw_stats, + .nstats = ARRAY_SIZE(vsc8584_hw_stats), + .use_package = true, + .shared_size = sizeof(struct vsc85xx_shared_private), + .has_ptp = true, + .check_rate_magic = false, + }; + + return vsc85xx_probe_common(phydev, &vsc8584_cfg, vsc85xx_default_led_modes_4); +} + +static int vsc85xx_probe(struct phy_device *phydev) +{ + static const struct vsc85xx_probe_config vsc85xx_cfg = { + .nleds = 2, + .supp_led_modes = VSC85XX_SUPP_LED_MODES, + .hw_stats = vsc85xx_hw_stats, + .nstats = ARRAY_SIZE(vsc85xx_hw_stats), + .use_package = false, + .has_ptp = false, + .check_rate_magic = true, + }; - return vsc85xx_dt_led_modes_get(phydev, default_mode); + return vsc85xx_probe_common(phydev, &vsc85xx_cfg, vsc85xx_default_led_modes_4); } static void vsc85xx_remove(struct phy_device *phydev) @@ -2387,6 +2569,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8502, @@ -2411,6 +2597,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8504, @@ -2438,6 +2628,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8514, @@ -2463,6 +2657,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8530, @@ -2487,6 +2685,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8531, @@ -2511,6 +2713,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8540, @@ -2535,6 +2741,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8541, @@ -2559,6 +2769,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_sset_count = &vsc85xx_get_sset_count, .get_strings = &vsc85xx_get_strings, .get_stats = &vsc85xx_get_stats, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8552, @@ -2585,11 +2799,14 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { - .phy_id = PHY_ID_VSC856X, + PHY_ID_MATCH_EXACT(PHY_ID_VSC856X), .name = "Microsemi GE VSC856X SyncE", - .phy_id_mask = 0xfffffff0, /* PHY_GBIT_FEATURES */ .soft_reset = &genphy_soft_reset, .config_init = &vsc8584_config_init, @@ -2609,6 +2826,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8572, @@ -2625,7 +2846,7 @@ static struct phy_driver vsc85xx_driver[] = { .suspend = &genphy_suspend, .resume = &genphy_resume, .remove = &vsc85xx_remove, - .probe = &vsc8574_probe, + .probe = &vsc8584_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, .get_tunable = &vsc85xx_get_tunable, @@ -2637,6 +2858,10 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { .phy_id = PHY_ID_VSC8574, @@ -2648,12 +2873,12 @@ static struct phy_driver vsc85xx_driver[] = { .config_aneg = &vsc85xx_config_aneg, .aneg_done = &genphy_aneg_done, .read_status = &vsc85xx_read_status, - .handle_interrupt = vsc85xx_handle_interrupt, + .handle_interrupt = vsc8584_handle_interrupt, .config_intr = &vsc85xx_config_intr, .suspend = &genphy_suspend, .resume = &genphy_resume, .remove = &vsc85xx_remove, - .probe = &vsc8574_probe, + .probe = &vsc8584_probe, .set_wol = &vsc85xx_wol_set, .get_wol = &vsc85xx_wol_get, .get_tunable = &vsc85xx_get_tunable, @@ -2665,11 +2890,14 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { - .phy_id = PHY_ID_VSC8575, + PHY_ID_MATCH_EXACT(PHY_ID_VSC8575), .name = "Microsemi GE VSC8575 SyncE", - .phy_id_mask = 0xfffffff0, /* PHY_GBIT_FEATURES */ .soft_reset = &genphy_soft_reset, .config_init = &vsc8584_config_init, @@ -2691,11 +2919,14 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { - .phy_id = PHY_ID_VSC8582, + PHY_ID_MATCH_EXACT(PHY_ID_VSC8582), .name = "Microsemi GE VSC8582 SyncE", - .phy_id_mask = 0xfffffff0, /* PHY_GBIT_FEATURES */ .soft_reset = &genphy_soft_reset, .config_init = &vsc8584_config_init, @@ -2717,11 +2948,14 @@ static struct phy_driver vsc85xx_driver[] = { .get_stats = &vsc85xx_get_stats, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, }, { - .phy_id = PHY_ID_VSC8584, + PHY_ID_MATCH_EXACT(PHY_ID_VSC8584), .name = "Microsemi GE VSC8584 SyncE", - .phy_id_mask = 0xfffffff0, /* PHY_GBIT_FEATURES */ .soft_reset = &genphy_soft_reset, .config_init = &vsc8584_config_init, @@ -2744,6 +2978,10 @@ static struct phy_driver vsc85xx_driver[] = { .link_change_notify = &vsc85xx_link_change_notify, .inband_caps = vsc85xx_inband_caps, .config_inband = vsc85xx_config_inband, + .led_brightness_set = vsc85xx_led_brightness_set, + .led_hw_is_supported = vsc85xx_led_hw_is_supported, + .led_hw_control_get = vsc85xx_led_hw_control_get, + .led_hw_control_set = vsc85xx_led_hw_control_set, } }; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index 61670be0f0957..d161fe3fee75b 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "mdio-open-alliance.h" #include "phylib-internal.h" @@ -147,12 +148,12 @@ int genphy_c45_pma_setup_forced(struct phy_device *phydev) ctrl2 |= MDIO_PMA_CTRL2_1000BT; break; case SPEED_2500: - ctrl1 |= MDIO_CTRL1_SPEED2_5G; + ctrl1 |= MDIO_PMA_CTRL1_SPEED2_5G; /* Assume 2.5Gbase-T */ ctrl2 |= MDIO_PMA_CTRL2_2_5GBT; break; case SPEED_5000: - ctrl1 |= MDIO_CTRL1_SPEED5G; + ctrl1 |= MDIO_PMA_CTRL1_SPEED5G; /* Assume 5Gbase-T */ ctrl2 |= MDIO_PMA_CTRL2_5GBT; break; @@ -485,8 +486,8 @@ static int genphy_c45_baset1_read_lpa(struct phy_device *phydev) mii_t1_adv_l_mod_linkmode_t(phydev->lp_advertising, 0); mii_t1_adv_m_mod_linkmode_t(phydev->lp_advertising, 0); - phydev->pause = 0; - phydev->asym_pause = 0; + phydev->pause = false; + phydev->asym_pause = false; return 0; } @@ -498,8 +499,8 @@ static int genphy_c45_baset1_read_lpa(struct phy_device *phydev) return val; mii_t1_adv_l_mod_linkmode_t(phydev->lp_advertising, val); - phydev->pause = val & MDIO_AN_T1_ADV_L_PAUSE_CAP ? 1 : 0; - phydev->asym_pause = val & MDIO_AN_T1_ADV_L_PAUSE_ASYM ? 1 : 0; + phydev->pause = val & MDIO_AN_T1_ADV_L_PAUSE_CAP; + phydev->asym_pause = val & MDIO_AN_T1_ADV_L_PAUSE_ASYM; val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_T1_LP_M); if (val < 0) @@ -536,8 +537,8 @@ int genphy_c45_read_lpa(struct phy_device *phydev) phydev->lp_advertising); mii_10gbt_stat_mod_linkmode_lpa_t(phydev->lp_advertising, 0); mii_adv_mod_linkmode_adv_t(phydev->lp_advertising, 0); - phydev->pause = 0; - phydev->asym_pause = 0; + phydev->pause = false; + phydev->asym_pause = false; return 0; } @@ -551,8 +552,8 @@ int genphy_c45_read_lpa(struct phy_device *phydev) return val; mii_adv_mod_linkmode_adv_t(phydev->lp_advertising, val); - phydev->pause = val & LPA_PAUSE_CAP ? 1 : 0; - phydev->asym_pause = val & LPA_PAUSE_ASYM ? 1 : 0; + phydev->pause = val & LPA_PAUSE_CAP; + phydev->asym_pause = val & LPA_PAUSE_ASYM; /* Read the link partner's 10G advertisement */ val = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_10GBT_STAT); @@ -617,15 +618,24 @@ int genphy_c45_read_pma(struct phy_device *phydev) case MDIO_PMA_CTRL1_SPEED1000: phydev->speed = SPEED_1000; break; - case MDIO_CTRL1_SPEED2_5G: + case MDIO_PMA_CTRL1_SPEED2_5G: phydev->speed = SPEED_2500; break; - case MDIO_CTRL1_SPEED5G: + case MDIO_PMA_CTRL1_SPEED5G: phydev->speed = SPEED_5000; break; case MDIO_CTRL1_SPEED10G: phydev->speed = SPEED_10000; break; + case MDIO_PMA_CTRL1_SPEED25G: + phydev->speed = SPEED_25000; + break; + case MDIO_PMA_CTRL1_SPEED50G: + phydev->speed = SPEED_50000; + break; + case MDIO_PMA_CTRL1_SPEED100G: + phydev->speed = SPEED_100000; + break; default: phydev->speed = SPEED_UNKNOWN; break; @@ -1171,8 +1181,8 @@ int genphy_c45_read_status(struct phy_device *phydev) phydev->speed = SPEED_UNKNOWN; phydev->duplex = DUPLEX_UNKNOWN; - phydev->pause = 0; - phydev->asym_pause = 0; + phydev->pause = false; + phydev->asym_pause = false; if (phydev->autoneg == AUTONEG_ENABLE) { ret = genphy_c45_read_lpa(phydev); @@ -1573,3 +1583,124 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev, return ret; } EXPORT_SYMBOL(genphy_c45_ethtool_set_eee); + +/** + * oatc14_cable_test_get_result_code - Convert hardware cable test status to + * ethtool result code. + * @status: The hardware-reported cable test status + * + * This helper function maps the OATC14 HDD cable test status to the + * corresponding ethtool cable test result code. It provides a translation + * between the device-specific status values and the standardized ethtool + * result codes. + * + * Return: + * * ETHTOOL_A_CABLE_RESULT_CODE_OK - Cable is OK + * * ETHTOOL_A_CABLE_RESULT_CODE_OPEN - Open circuit detected + * * ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT - Short circuit detected + * * ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC - Status not detectable or invalid + */ +static int oatc14_cable_test_get_result_code(enum oatc14_hdd_status status) +{ + switch (status) { + case OATC14_HDD_STATUS_CABLE_OK: + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + case OATC14_HDD_STATUS_OPEN: + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + case OATC14_HDD_STATUS_SHORT: + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + case OATC14_HDD_STATUS_NOT_DETECTABLE: + default: + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + } +} + +/** + * genphy_c45_oatc14_cable_test_get_status - Get status of OATC14 10Base-T1S + * PHY cable test. + * @phydev: pointer to the PHY device structure + * @finished: pointer to a boolean set true if the test is complete + * + * Retrieves the current status of the OATC14 10Base-T1S PHY cable test. + * This function reads the OATC14 HDD register to determine whether the test + * results are valid and whether the test has finished. + * + * If the test is complete, the function reports the cable test result via + * the ethtool cable test interface using ethnl_cable_test_result(), and then + * clears the test control bit in the PHY register to reset the test state. + * + * Return: 0 on success, or a negative error code on failure (e.g. register + * read/write error). + */ +int genphy_c45_oatc14_cable_test_get_status(struct phy_device *phydev, + bool *finished) +{ + int ret; + u8 sts; + + *finished = false; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_HDD); + if (ret < 0) + return ret; + + if (!(ret & OATC14_HDD_VALID)) + return 0; + + *finished = true; + + sts = FIELD_GET(OATC14_HDD_SHORT_OPEN_STATUS, ret); + + ret = ethnl_cable_test_result(phydev, ETHTOOL_A_CABLE_PAIR_A, + oatc14_cable_test_get_result_code(sts)); + if (ret) + return ret; + + return phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, + MDIO_OATC14_HDD, OATC14_HDD_CONTROL); +} +EXPORT_SYMBOL(genphy_c45_oatc14_cable_test_get_status); + +/** + * genphy_c45_oatc14_cable_test_start - Start a cable test on an OATC14 + * 10Base-T1S PHY. + * @phydev: Pointer to the PHY device structure + * + * This function initiates a cable diagnostic test on a Clause 45 OATC14 + * 10Base-T1S capable PHY device. It first reads the PHY’s advanced diagnostic + * capability register to check if High Definition Diagnostics (HDD) mode is + * supported. If the PHY does not report HDD capability, cable testing is not + * supported and the function returns -EOPNOTSUPP. + * + * For PHYs that support HDD, the function sets the appropriate control bits in + * the OATC14_HDD register to enable and start the cable diagnostic test. + * + * Return: + * * 0 on success + * * -EOPNOTSUPP if the PHY does not support HDD capability + * * A negative error code on I/O or register access failures + */ +int genphy_c45_oatc14_cable_test_start(struct phy_device *phydev) +{ + int ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_ADFCAP); + if (ret < 0) + return ret; + + if (!(ret & OATC14_ADFCAP_HDD_CAPABILITY)) + return -EOPNOTSUPP; + + ret = phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_HDD, + OATC14_HDD_CONTROL); + if (ret) + return ret; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_HDD); + if (ret < 0) + return ret; + + return phy_set_bits_mmd(phydev, MDIO_MMD_VEND2, MDIO_OATC14_HDD, + OATC14_HDD_START_CONTROL); +} +EXPORT_SYMBOL(genphy_c45_oatc14_cable_test_start); diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h index b7f0c6a3037a9..c94b9c8525639 100644 --- a/drivers/net/phy/phy-caps.h +++ b/drivers/net/phy/phy-caps.h @@ -60,4 +60,9 @@ const struct link_capabilities * phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported, bool exact); +void phy_caps_medium_get_supported(unsigned long *supported, + enum ethtool_link_medium medium, + int lanes); +u32 phy_caps_mediums_from_linkmodes(unsigned long *linkmodes); + #endif /* __PHY_CAPS_H */ diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 605ca20ae192d..4dfdb902b2e7a 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -4,6 +4,7 @@ */ #include #include +#include #include #include "phylib.h" @@ -101,6 +102,49 @@ const char *phy_rate_matching_to_str(int rate_matching) } EXPORT_SYMBOL_GPL(phy_rate_matching_to_str); +/** + * phy_fix_phy_mode_for_mac_delays - Convenience function for fixing PHY + * mode based on whether mac adds internal delay + * + * @interface: The current interface mode of the port + * @mac_txid: True if the mac adds internal tx delay + * @mac_rxid: True if the mac adds internal rx delay + * + * Return: fixed PHY mode, or PHY_INTERFACE_MODE_NA if the interface can + * not apply the internal delay + */ +phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, + bool mac_txid, bool mac_rxid) +{ + if (!phy_interface_mode_is_rgmii(interface)) + return interface; + + if (mac_txid && mac_rxid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + if (mac_txid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_RXID; + if (interface == PHY_INTERFACE_MODE_RGMII_TXID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + if (mac_rxid) { + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_TXID; + if (interface == PHY_INTERFACE_MODE_RGMII_RXID) + return PHY_INTERFACE_MODE_RGMII; + return PHY_INTERFACE_MODE_NA; + } + + return interface; +} +EXPORT_SYMBOL_GPL(phy_fix_phy_mode_for_mac_delays); + /** * phy_interface_num_ports - Return the number of links that can be carried by * a given MAC-PHY physical link. Returns 0 if this is @@ -163,7 +207,12 @@ EXPORT_SYMBOL_GPL(phy_interface_num_ports); static void __set_phy_supported(struct phy_device *phydev, u32 max_speed) { + struct phy_port *port; + phy_caps_linkmode_max_speed(max_speed, phydev->supported); + + phy_for_each_port(phydev, port) + phy_caps_linkmode_max_speed(max_speed, port->supported); } /** diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c index 23c808b59b6fd..080a09f29311e 100644 --- a/drivers/net/phy/phy_caps.c +++ b/drivers/net/phy/phy_caps.c @@ -78,6 +78,14 @@ int __init phy_caps_init(void) /* Fill the caps array from net/ethtool/common.c */ for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) { linkmode = &link_mode_params[i]; + + /* Sanity check the linkmodes array for number of pairs */ + if (linkmode->pairs < linkmode->min_pairs) { + pr_err("Pairs count must not be under min_pairs for linkmode %d\n", + i); + return -EINVAL; + } + capa = speed_duplex_to_capa(linkmode->speed, linkmode->duplex); if (capa < 0) { @@ -376,3 +384,60 @@ unsigned long phy_caps_from_interface(phy_interface_t interface) return link_caps; } EXPORT_SYMBOL_GPL(phy_caps_from_interface); + +/** + * phy_caps_medium_get_supported() - Returns linkmodes supported on a given medium + * @supported: After this call, contains all possible linkmodes on a given medium, + * and with the given number of pairs, or less. + * @medium: The medium to get the support from + * @pairs: The number of pairs used on the given medium. Only relevant for modes + * that support this notion, such as BaseT. Pass 0 if not applicable. + * + * If no match exists, the supported field is left untouched. + */ +void phy_caps_medium_get_supported(unsigned long *supported, + enum ethtool_link_medium medium, + int pairs) +{ + int i; + + for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) { + /* Special bits such as Autoneg, Pause, Asym_pause, etc. are + * set and will be masked away by the port parent. + */ + if (link_mode_params[i].mediums == BIT(ETHTOOL_LINK_MEDIUM_NONE)) { + linkmode_set_bit(i, supported); + continue; + } + + /* If this medium matches, and had a non-zero min-pairs */ + if (link_mode_params[i].mediums & BIT(medium) && + (!link_mode_params[i].min_pairs || + (link_mode_params[i].min_pairs <= pairs && + link_mode_params[i].pairs >= pairs))) + linkmode_set_bit(i, supported); + } +} +EXPORT_SYMBOL_GPL(phy_caps_medium_get_supported); + +/** + * phy_caps_mediums_from_linkmodes() - Get all mediums from a linkmodes list + * @linkmodes: A bitset of linkmodes to get the mediums from + * + * Returns: A bitset of ETHTOOL_MEDIUM_XXX values corresponding to all medium + * types in the linkmodes list + */ +u32 phy_caps_mediums_from_linkmodes(unsigned long *linkmodes) +{ + const struct link_mode_info *linkmode; + u32 mediums = 0; + int i; + + for_each_set_bit(i, linkmodes, __ETHTOOL_LINK_MODE_MASK_NBITS) { + linkmode = &link_mode_params[i]; + mediums |= linkmode->mediums; + } + + return mediums; +} +EXPORT_SYMBOL_GPL(phy_caps_mediums_from_linkmodes); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 7a67c900e79a5..523a79631f632 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -30,6 +30,7 @@ #include #include #include +#include #include #include #include @@ -251,6 +252,16 @@ static bool phy_drv_wol_enabled(struct phy_device *phydev) return wol.wolopts != 0; } +bool phy_may_wakeup(struct phy_device *phydev) +{ + /* If the PHY is using driver-model based wakeup, use that state. */ + if (phy_can_wakeup(phydev)) + return device_may_wakeup(&phydev->mdio.dev); + + return phy_drv_wol_enabled(phydev); +} +EXPORT_SYMBOL_GPL(phy_may_wakeup); + static void phy_link_change(struct phy_device *phydev, bool up) { struct net_device *netdev = phydev->attached_dev; @@ -302,7 +313,7 @@ static bool mdio_bus_phy_may_suspend(struct phy_device *phydev) /* If the PHY on the mido bus is not attached but has WOL enabled * we cannot suspend the PHY. */ - if (!netdev && phy_drv_wol_enabled(phydev)) + if (!netdev && phy_may_wakeup(phydev)) return false; /* PHY not attached? May suspend if the PHY has not already been @@ -815,8 +826,8 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, dev->speed = SPEED_UNKNOWN; dev->duplex = DUPLEX_UNKNOWN; - dev->pause = 0; - dev->asym_pause = 0; + dev->pause = false; + dev->asym_pause = false; dev->link = 0; dev->port = PORT_TP; dev->interface = PHY_INTERFACE_MODE_GMII; @@ -835,6 +846,13 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, dev->state = PHY_DOWN; INIT_LIST_HEAD(&dev->leds); + INIT_LIST_HEAD(&dev->ports); + + /* The driver's probe function must change that to the real number + * of ports possible on the PHY. We assume by default we are dealing + * with a single-port PHY + */ + dev->max_n_ports = 1; mutex_init(&dev->lock); INIT_DELAYED_WORK(&dev->state_queue, phy_state_machine); @@ -1214,22 +1232,24 @@ int phy_get_c45_ids(struct phy_device *phydev) EXPORT_SYMBOL(phy_get_c45_ids); /** - * phy_find_first - finds the first PHY device on the bus + * phy_find_next - finds the next PHY device on the bus * @bus: the target MII bus + * @pos: cursor + * + * Return: next phy_device on the bus, or NULL */ -struct phy_device *phy_find_first(struct mii_bus *bus) +struct phy_device *phy_find_next(struct mii_bus *bus, struct phy_device *pos) { - struct phy_device *phydev; - int addr; + for (int addr = pos ? pos->mdio.addr + 1 : 0; + addr < PHY_MAX_ADDR; addr++) { + struct phy_device *phydev = mdiobus_get_phy(bus, addr); - for (addr = 0; addr < PHY_MAX_ADDR; addr++) { - phydev = mdiobus_get_phy(bus, addr); if (phydev) return phydev; } return NULL; } -EXPORT_SYMBOL(phy_find_first); +EXPORT_SYMBOL_GPL(phy_find_next); /** * phy_prepare_link - prepares the PHY layer to monitor link status @@ -1512,7 +1532,7 @@ static DEVICE_ATTR_RO(phy_standalone); * * Return: 0 on success, otherwise a negative error code. */ -int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) +static int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) { struct phy_device *phydev = upstream; struct net_device *dev = phydev->attached_dev; @@ -1522,7 +1542,6 @@ int phy_sfp_connect_phy(void *upstream, struct phy_device *phy) return 0; } -EXPORT_SYMBOL(phy_sfp_connect_phy); /** * phy_sfp_disconnect_phy - Disconnect the SFP module's PHY from the upstream PHY @@ -1534,7 +1553,7 @@ EXPORT_SYMBOL(phy_sfp_connect_phy); * will be destroyed, re-inserting the same module will add a new phy with a * new index. */ -void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) +static void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) { struct phy_device *phydev = upstream; struct net_device *dev = phydev->attached_dev; @@ -1542,7 +1561,6 @@ void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy) if (dev) phy_link_topo_del_phy(dev, phy); } -EXPORT_SYMBOL(phy_sfp_disconnect_phy); /** * phy_sfp_attach - attach the SFP bus to the PHY upstream network device @@ -1551,7 +1569,7 @@ EXPORT_SYMBOL(phy_sfp_disconnect_phy); * * This is used to fill in the sfp_upstream_ops .attach member. */ -void phy_sfp_attach(void *upstream, struct sfp_bus *bus) +static void phy_sfp_attach(void *upstream, struct sfp_bus *bus) { struct phy_device *phydev = upstream; @@ -1559,7 +1577,6 @@ void phy_sfp_attach(void *upstream, struct sfp_bus *bus) phydev->attached_dev->sfp_bus = bus; phydev->sfp_bus_attached = true; } -EXPORT_SYMBOL(phy_sfp_attach); /** * phy_sfp_detach - detach the SFP bus from the PHY upstream network device @@ -1568,7 +1585,7 @@ EXPORT_SYMBOL(phy_sfp_attach); * * This is used to fill in the sfp_upstream_ops .detach member. */ -void phy_sfp_detach(void *upstream, struct sfp_bus *bus) +static void phy_sfp_detach(void *upstream, struct sfp_bus *bus) { struct phy_device *phydev = upstream; @@ -1576,15 +1593,158 @@ void phy_sfp_detach(void *upstream, struct sfp_bus *bus) phydev->attached_dev->sfp_bus = NULL; phydev->sfp_bus_attached = false; } -EXPORT_SYMBOL(phy_sfp_detach); + +static int phy_sfp_module_insert(void *upstream, const struct sfp_eeprom_id *id) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); + struct phy_device *phydev = upstream; + const struct sfp_module_caps *caps; + struct phy_port *port; + + phy_interface_t iface; + + linkmode_zero(sfp_support); + + port = phy_get_sfp_port(phydev); + if (!port) + return -EINVAL; + + caps = sfp_get_module_caps(phydev->sfp_bus); + + linkmode_and(sfp_support, port->supported, caps->link_modes); + if (linkmode_empty(sfp_support)) { + dev_err(&phydev->mdio.dev, "incompatible SFP module inserted, no common linkmode\n"); + return -EINVAL; + } + + iface = sfp_select_interface(phydev->sfp_bus, sfp_support); + if (iface == PHY_INTERFACE_MODE_NA) { + dev_err(&phydev->mdio.dev, "PHY %s does not support the SFP module's requested MII interfaces\n", + phydev_name(phydev)); + return -EINVAL; + } + + if (phydev->n_ports == 1) + phydev->port = caps->port; + + if (port->ops && port->ops->configure_mii) + return port->ops->configure_mii(port, true, iface); + + return 0; +} + +static void phy_sfp_module_remove(void *upstream) +{ + struct phy_device *phydev = upstream; + struct phy_port *port = phy_get_sfp_port(phydev); + + if (port && port->ops && port->ops->configure_mii) + port->ops->configure_mii(port, false, PHY_INTERFACE_MODE_NA); + + if (phydev->n_ports == 1) + phydev->port = PORT_NONE; +} + +static void phy_sfp_link_up(void *upstream) +{ + struct phy_device *phydev = upstream; + struct phy_port *port = phy_get_sfp_port(phydev); + + if (port && port->ops && port->ops->link_up) + port->ops->link_up(port); +} + +static void phy_sfp_link_down(void *upstream) +{ + struct phy_device *phydev = upstream; + struct phy_port *port = phy_get_sfp_port(phydev); + + if (port && port->ops && port->ops->link_down) + port->ops->link_down(port); +} + +static const struct sfp_upstream_ops sfp_phydev_ops = { + .attach = phy_sfp_attach, + .detach = phy_sfp_detach, + .module_insert = phy_sfp_module_insert, + .module_remove = phy_sfp_module_remove, + .link_up = phy_sfp_link_up, + .link_down = phy_sfp_link_down, + .connect_phy = phy_sfp_connect_phy, + .disconnect_phy = phy_sfp_disconnect_phy, +}; + +static int phy_add_port(struct phy_device *phydev, struct phy_port *port) +{ + int ret = 0; + + if (phydev->n_ports == phydev->max_n_ports) + return -EBUSY; + + /* We set all ports as active by default, PHY drivers may deactivate + * them (when unused) + */ + port->active = true; + + if (port->is_mii) { + if (phydev->drv && phydev->drv->attach_mii_port) + ret = phydev->drv->attach_mii_port(phydev, port); + } else { + if (phydev->drv && phydev->drv->attach_mdi_port) + ret = phydev->drv->attach_mdi_port(phydev, port); + } + + if (ret) + return ret; + + /* The PHY driver might have added, removed or set medium/pairs info, + * so update the port supported accordingly. + */ + phy_port_update_supported(port); + + list_add(&port->head, &phydev->ports); + + phydev->n_ports++; + + return 0; +} + +static void phy_del_port(struct phy_device *phydev, struct phy_port *port) +{ + if (!phydev->n_ports) + return; + + list_del(&port->head); + + phydev->n_ports--; +} + +static int phy_setup_sfp_port(struct phy_device *phydev) +{ + struct phy_port *port = phy_port_alloc(); + + if (!port) + return -ENOMEM; + + port->parent_type = PHY_PORT_PHY; + port->phy = phydev; + + /* The PHY is a media converter, the port connected to the SFP cage + * is a MII port. + */ + port->is_mii = true; + port->is_sfp = true; + + phy_add_port(phydev, port); + + return 0; +} /** * phy_sfp_probe - probe for a SFP cage attached to this PHY device * @phydev: Pointer to phy_device - * @ops: SFP's upstream operations */ -int phy_sfp_probe(struct phy_device *phydev, - const struct sfp_upstream_ops *ops) +static int phy_sfp_probe(struct phy_device *phydev) { struct sfp_bus *bus; int ret = 0; @@ -1596,12 +1756,15 @@ int phy_sfp_probe(struct phy_device *phydev, phydev->sfp_bus = bus; - ret = sfp_bus_add_upstream(bus, phydev, ops); + ret = sfp_bus_add_upstream(bus, phydev, &sfp_phydev_ops); sfp_bus_put(bus); } + + if (phydev->sfp_bus) + ret = phy_setup_sfp_port(phydev); + return ret; } -EXPORT_SYMBOL(phy_sfp_probe); static bool phy_drv_supports_irq(const struct phy_driver *phydrv) { @@ -1909,7 +2072,7 @@ int phy_suspend(struct phy_device *phydev) if (phydev->suspended || !phydrv) return 0; - phydev->wol_enabled = phy_drv_wol_enabled(phydev) || + phydev->wol_enabled = phy_may_wakeup(phydev) || (netdev && netdev->ethtool->wol_enabled); /* If the device has WOL enabled, we cannot suspend the PHY */ if (phydev->wol_enabled && !(phydrv->flags & PHY_ALWAYS_CALL_SUSPEND)) @@ -2080,8 +2243,8 @@ int genphy_setup_forced(struct phy_device *phydev) { u16 ctl; - phydev->pause = 0; - phydev->asym_pause = 0; + phydev->pause = false; + phydev->asym_pause = false; ctl = mii_bmcr_encode_fixed(phydev->speed, phydev->duplex); @@ -2488,8 +2651,8 @@ int genphy_read_status(struct phy_device *phydev) phydev->master_slave_state = MASTER_SLAVE_STATE_UNSUPPORTED; phydev->speed = SPEED_UNKNOWN; phydev->duplex = DUPLEX_UNKNOWN; - phydev->pause = 0; - phydev->asym_pause = 0; + phydev->pause = false; + phydev->asym_pause = false; if (phydev->is_gigabit_capable) { err = genphy_read_master_slave(phydev); @@ -2542,8 +2705,8 @@ int genphy_c37_read_status(struct phy_device *phydev, bool *changed) /* Signal link has changed */ *changed = true; phydev->duplex = DUPLEX_UNKNOWN; - phydev->pause = 0; - phydev->asym_pause = 0; + phydev->pause = false; + phydev->asym_pause = false; if (phydev->autoneg == AUTONEG_ENABLE && phydev->autoneg_complete) { lpa = phy_read(phydev, MII_LPA); @@ -3313,6 +3476,159 @@ static int of_phy_leds(struct phy_device *phydev) return 0; } +static void phy_cleanup_ports(struct phy_device *phydev) +{ + struct phy_port *tmp, *port; + + list_for_each_entry_safe(port, tmp, &phydev->ports, head) { + phy_del_port(phydev, port); + phy_port_destroy(port); + } +} + +static int phy_default_setup_single_port(struct phy_device *phydev) +{ + struct phy_port *port = phy_port_alloc(); + unsigned long mode; + + if (!port) + return -ENOMEM; + + port->parent_type = PHY_PORT_PHY; + port->phy = phydev; + + /* Let the PHY driver know that this port was never described anywhere. + * This is the usual case, where we assume single-port PHY devices with + * no SFP. In that case, the port supports exactly the same thing as + * the PHY itself. + * + * However, this can also be because we have a combo-port PHY, with + * only one port described in DT, through SFP for example. + * + * In that case, the PHY driver will be in charge of saying what we can + * do on that non-represented port. + */ + port->not_described = true; + linkmode_copy(port->supported, phydev->supported); + port->mediums = phy_caps_mediums_from_linkmodes(port->supported); + + for_each_set_bit(mode, port->supported, __ETHTOOL_LINK_MODE_MASK_NBITS) + port->pairs = max_t(int, port->pairs, + ethtool_linkmode_n_pairs(mode)); + + phy_add_port(phydev, port); + + return 0; +} + +static int of_phy_ports(struct phy_device *phydev) +{ + struct device_node *node = phydev->mdio.dev.of_node; + struct device_node *mdi; + struct phy_port *port; + int err; + + if (!IS_ENABLED(CONFIG_OF_MDIO)) + return 0; + + if (!node) + return 0; + + mdi = of_get_child_by_name(node, "mdi"); + if (!mdi) + return 0; + + for_each_available_child_of_node_scoped(mdi, port_node) { + port = phy_of_parse_port(port_node); + if (IS_ERR(port)) { + err = PTR_ERR(port); + goto out_err; + } + + port->parent_type = PHY_PORT_PHY; + port->phy = phydev; + err = phy_add_port(phydev, port); + if (err) + goto out_err; + } + of_node_put(mdi); + + return 0; + +out_err: + phy_cleanup_ports(phydev); + of_node_put(mdi); + return err; +} + +static int phy_setup_ports(struct phy_device *phydev) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(ports_supported); + struct phy_port *port; + int ret; + + ret = of_phy_ports(phydev); + if (ret) + return ret; + + ret = phy_sfp_probe(phydev); + if (ret) + goto out; + + if (phydev->n_ports < phydev->max_n_ports) { + ret = phy_default_setup_single_port(phydev); + if (ret) + goto out; + } + + linkmode_zero(ports_supported); + + /* Aggregate the supported modes, which are made-up of : + * - What the PHY itself supports + * - What the sum of all ports support + */ + list_for_each_entry(port, &phydev->ports, head) + if (port->active) + linkmode_or(ports_supported, ports_supported, + port->supported); + + if (!linkmode_empty(ports_supported)) + linkmode_and(phydev->supported, phydev->supported, + ports_supported); + + /* For now, the phy->port field is set as the first active port's type */ + list_for_each_entry(port, &phydev->ports, head) + if (port->active) { + phydev->port = phy_port_get_type(port); + break; + } + + return 0; + +out: + phy_cleanup_ports(phydev); + return ret; +} + +/** + * phy_get_sfp_port() - Returns the first valid SFP port of a PHY + * @phydev: pointer to the PHY device to get the SFP port from + * + * Returns: The first active SFP (serdes) port of a PHY device, NULL if none + * exist. + */ +struct phy_port *phy_get_sfp_port(struct phy_device *phydev) +{ + struct phy_port *port; + + list_for_each_entry(port, &phydev->ports, head) + if (port->active && port->is_sfp) + return port; + + return NULL; +} +EXPORT_SYMBOL_GPL(phy_get_sfp_port); + /** * fwnode_mdio_find_device - Given a fwnode, find the mdio_device * @fwnode: pointer to the mdio_device's fwnode @@ -3450,6 +3766,11 @@ static int phy_probe(struct device *dev) phydev->is_gigabit_capable = 1; of_set_phy_supported(phydev); + + err = phy_setup_ports(phydev); + if (err) + goto out; + phy_advertise_supported(phydev); /* Get PHY default EEE advertising modes and handle them as potentially @@ -3525,6 +3846,8 @@ static int phy_remove(struct device *dev) phydev->state = PHY_DOWN; + phy_cleanup_ports(phydev); + sfp_bus_del_upstream(phydev->sfp_bus); phydev->sfp_bus = NULL; diff --git a/drivers/net/phy/phy_port.c b/drivers/net/phy/phy_port.c new file mode 100644 index 0000000000000..d9099196f870e --- /dev/null +++ b/drivers/net/phy/phy_port.c @@ -0,0 +1,212 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Framework to drive Ethernet ports + * + * Copyright (c) 2024 Maxime Chevallier + */ + +#include +#include +#include + +#include "phy-caps.h" + +/** + * phy_port_alloc() - Allocate a new phy_port + * + * Returns: a newly allocated struct phy_port, or NULL. + */ +struct phy_port *phy_port_alloc(void) +{ + struct phy_port *port; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return NULL; + + linkmode_zero(port->supported); + INIT_LIST_HEAD(&port->head); + + return port; +} +EXPORT_SYMBOL_GPL(phy_port_alloc); + +/** + * phy_port_destroy() - Free a struct phy_port + * @port: The port to destroy + */ +void phy_port_destroy(struct phy_port *port) +{ + kfree(port); +} +EXPORT_SYMBOL_GPL(phy_port_destroy); + +/** + * phy_of_parse_port() - Create a phy_port from a firmware representation + * @dn: device_node representation of the port, following the + * ethernet-connector.yaml binding + * + * Returns: a newly allocated and initialized phy_port pointer, or an ERR_PTR. + */ +struct phy_port *phy_of_parse_port(struct device_node *dn) +{ + struct fwnode_handle *fwnode = of_fwnode_handle(dn); + enum ethtool_link_medium medium; + struct phy_port *port; + const char *med_str; + u32 pairs = 0, mediums = 0; + int ret; + + ret = fwnode_property_read_string(fwnode, "media", &med_str); + if (ret) + return ERR_PTR(ret); + + medium = ethtool_str_to_medium(med_str); + if (medium == ETHTOOL_LINK_MEDIUM_NONE) + return ERR_PTR(-EINVAL); + + if (pairs && medium != ETHTOOL_LINK_MEDIUM_BASET) { + pr_err("pairs property is only compatible with BaseT medium\n"); + return ERR_PTR(-EINVAL); + } + + if (medium == ETHTOOL_LINK_MEDIUM_BASET) { + ret = fwnode_property_read_u32(fwnode, "pairs", &pairs); + if (ret) + return ERR_PTR(ret); + + switch (pairs) { + case 1: /* BaseT1 */ + case 2: /* 100BaseTX */ + case 4: + break; + default: + pr_err("%u is not a valid number of pairs\n", pairs); + return ERR_PTR(-EINVAL); + } + } + + mediums |= BIT(medium); + + if (!mediums) + return ERR_PTR(-EINVAL); + + port = phy_port_alloc(); + if (!port) + return ERR_PTR(-ENOMEM); + + port->pairs = pairs; + port->mediums = mediums; + + return port; +} +EXPORT_SYMBOL_GPL(phy_of_parse_port); + +/** + * phy_port_update_supported() - Setup the port->supported field + * @port: the port to update + * + * Once the port's medium list and number of pairs has been configured based + * on firmware, straps and vendor-specific properties, this function may be + * called to update the port's supported linkmodes list. + * + * Any mode that was manually set in the port's supported list remains set. + */ +void phy_port_update_supported(struct phy_port *port) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0 }; + unsigned long mode; + int i; + + for_each_set_bit(i, &port->mediums, __ETHTOOL_LINK_MEDIUM_LAST) { + linkmode_zero(supported); + phy_caps_medium_get_supported(supported, i, port->pairs); + linkmode_or(port->supported, port->supported, supported); + } + + /* If there's no pairs specified, we grab the default number of + * pairs as the max of the default pairs for each linkmode + */ + if (!port->pairs) + for_each_set_bit(mode, port->supported, + __ETHTOOL_LINK_MODE_MASK_NBITS) + port->pairs = max_t(int, port->pairs, + ethtool_linkmode_n_pairs(mode)); + + /* Serdes ports supported through SFP may not have any medium set, + * as they will output PHY_INTERFACE_MODE_XXX modes. In that case, derive + * the supported list based on these interfaces + */ + if (port->is_mii && linkmode_empty(supported)) { + unsigned long interface, link_caps = 0; + + /* Get each interface's caps */ + for_each_set_bit(interface, port->interfaces, + PHY_INTERFACE_MODE_MAX) + link_caps |= phy_caps_from_interface(interface); + + phy_caps_linkmodes(link_caps, port->supported); + } +} +EXPORT_SYMBOL_GPL(phy_port_update_supported); + +/** + * phy_port_filter_supported() - Make sure that port->supported match port->mediums + * @port: The port to filter + * + * After updating a port's mediums to a more restricted subset, this helper will + * make sure that port->supported only contains linkmodes that are compatible + * with port->mediums. + */ +static void phy_port_filter_supported(struct phy_port *port) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0 }; + int i; + + for_each_set_bit(i, &port->mediums, __ETHTOOL_LINK_MEDIUM_LAST) + phy_caps_medium_get_supported(supported, i, port->pairs); + + linkmode_and(port->supported, port->supported, supported); +} + +/** + * phy_port_restrict_mediums - Mask away some of the port's supported mediums + * @port: The port to act upon + * @mediums: A mask of mediums to support on the port + * + * This helper allows removing some mediums from a port's list of supported + * mediums, which occurs once we have enough information about the port to + * know its nature. + * + * Returns: 0 if the change was donne correctly, a negative value otherwise. + */ +int phy_port_restrict_mediums(struct phy_port *port, unsigned long mediums) +{ + /* We forbid ending-up with a port with empty mediums */ + if (!(port->mediums & mediums)) + return -EINVAL; + + port->mediums &= mediums; + + phy_port_filter_supported(port); + + return 0; +} +EXPORT_SYMBOL_GPL(phy_port_restrict_mediums); + +/** + * phy_port_get_type() - get the PORT_* attribute for that port. + * @port: The port we want the information from + * + * Returns: A PORT_XXX value. + */ +int phy_port_get_type(struct phy_port *port) +{ + if (port->mediums & BIT(ETHTOOL_LINK_MEDIUM_BASET)) + return PORT_TP; + + if (phy_port_is_fiber(port)) + return PORT_FIBRE; + + return PORT_OTHER; +} +EXPORT_SYMBOL_GPL(phy_port_get_type); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 9d7799ea1c173..6e1243bf68aab 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -93,6 +93,9 @@ struct phylink { u8 sfp_port; struct eee_config eee_cfg; + + u32 wolopts_mac; + u8 wol_sopass[SOPASS_MAX]; }; #define phylink_printk(level, pl, fmt, ...) \ @@ -2562,6 +2565,23 @@ void phylink_rx_clk_stop_unblock(struct phylink *pl) } EXPORT_SYMBOL_GPL(phylink_rx_clk_stop_unblock); +static bool phylink_mac_supports_wol(struct phylink *pl) +{ + return !!pl->mac_ops->mac_wol_set; +} + +static bool phylink_phy_supports_wol(struct phylink *pl, + struct phy_device *phydev) +{ + return phydev && (pl->config->wol_phy_legacy || phy_can_wakeup(phydev)); +} + +static bool phylink_phy_pm_speed_ctrl(struct phylink *pl) +{ + return pl->config->wol_phy_speed_ctrl && !pl->wolopts_mac && + pl->phydev && phy_may_wakeup(pl->phydev); +} + /** * phylink_suspend() - handle a network device suspend event * @pl: a pointer to a &struct phylink returned from phylink_create() @@ -2575,11 +2595,17 @@ EXPORT_SYMBOL_GPL(phylink_rx_clk_stop_unblock); * can also bring down the link between the MAC and PHY. * - If Wake-on-Lan is active, but being handled by the MAC, the MAC * still needs to receive packets, so we can not bring the link down. + * + * Note: when phylink managed Wake-on-Lan is in use, @mac_wol is ignored. + * (struct phylink_mac_ops.mac_set_wol populated.) */ void phylink_suspend(struct phylink *pl, bool mac_wol) { ASSERT_RTNL(); + if (phylink_mac_supports_wol(pl)) + mac_wol = !!pl->wolopts_mac; + if (mac_wol && (!pl->netdev || pl->netdev->ethtool->wol_enabled)) { /* Wake-on-Lan enabled, MAC handling */ mutex_lock(&pl->state_mutex); @@ -2605,6 +2631,9 @@ void phylink_suspend(struct phylink *pl, bool mac_wol) } else { phylink_stop(pl); } + + if (phylink_phy_pm_speed_ctrl(pl)) + phylink_speed_down(pl, false); } EXPORT_SYMBOL_GPL(phylink_suspend); @@ -2644,6 +2673,9 @@ void phylink_resume(struct phylink *pl) { ASSERT_RTNL(); + if (phylink_phy_pm_speed_ctrl(pl)) + phylink_speed_up(pl); + if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) { /* Wake-on-Lan enabled, MAC handling */ @@ -2689,8 +2721,24 @@ void phylink_ethtool_get_wol(struct phylink *pl, struct ethtool_wolinfo *wol) wol->supported = 0; wol->wolopts = 0; - if (pl->phydev) - phy_ethtool_get_wol(pl->phydev, wol); + if (phylink_mac_supports_wol(pl)) { + if (phylink_phy_supports_wol(pl, pl->phydev)) + phy_ethtool_get_wol(pl->phydev, wol); + + /* Where the MAC augments the WoL support, merge its support and + * current configuration. + */ + if (~wol->wolopts & pl->wolopts_mac & WAKE_MAGICSECURE) + memcpy(wol->sopass, pl->wol_sopass, + sizeof(wol->sopass)); + + wol->supported |= pl->config->wol_mac_support; + wol->wolopts |= pl->wolopts_mac; + } else { + /* Legacy */ + if (pl->phydev) + phy_ethtool_get_wol(pl->phydev, wol); + } } EXPORT_SYMBOL_GPL(phylink_ethtool_get_wol); @@ -2707,12 +2755,48 @@ EXPORT_SYMBOL_GPL(phylink_ethtool_get_wol); */ int phylink_ethtool_set_wol(struct phylink *pl, struct ethtool_wolinfo *wol) { + struct ethtool_wolinfo w = { .cmd = ETHTOOL_GWOL }; int ret = -EOPNOTSUPP; + bool changed; + u32 wolopts; ASSERT_RTNL(); - if (pl->phydev) - ret = phy_ethtool_set_wol(pl->phydev, wol); + if (phylink_mac_supports_wol(pl)) { + wolopts = wol->wolopts; + + if (phylink_phy_supports_wol(pl, pl->phydev)) { + ret = phy_ethtool_set_wol(pl->phydev, wol); + if (ret != 0 && ret != -EOPNOTSUPP) + return ret; + + phy_ethtool_get_wol(pl->phydev, &w); + + /* Any Wake-on-Lan modes which the PHY is handling + * should not be passed on to the MAC. + */ + wolopts &= ~w.wolopts; + } + + wolopts &= pl->config->wol_mac_support; + changed = pl->wolopts_mac != wolopts; + if (wolopts & WAKE_MAGICSECURE) + changed |= !!memcmp(wol->sopass, pl->wol_sopass, + sizeof(wol->sopass)); + memcpy(pl->wol_sopass, wol->sopass, sizeof(pl->wol_sopass)); + + if (changed) { + ret = pl->mac_ops->mac_wol_set(pl->config, wolopts, + wol->sopass); + if (!ret) + pl->wolopts_mac = wolopts; + } else { + ret = 0; + } + } else { + if (pl->phydev) + ret = phy_ethtool_set_wol(pl->phydev, wol); + } return ret; } diff --git a/drivers/net/phy/qcom/at803x.c b/drivers/net/phy/qcom/at803x.c index 338acd11a9b65..2995b08bac963 100644 --- a/drivers/net/phy/qcom/at803x.c +++ b/drivers/net/phy/qcom/at803x.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include "qcom.h" @@ -769,57 +769,44 @@ static int at8031_register_regulators(struct phy_device *phydev) return 0; } -static int at8031_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +static int at803x_configure_mii(struct phy_port *port, bool enable, + phy_interface_t interface) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_support); - __ETHTOOL_DECLARE_LINK_MODE_MASK(sfp_support); - struct phy_device *phydev = upstream; - const struct sfp_module_caps *caps; - phy_interface_t iface; - - linkmode_zero(phy_support); - phylink_set(phy_support, 1000baseX_Full); - phylink_set(phy_support, 1000baseT_Full); - phylink_set(phy_support, Autoneg); - phylink_set(phy_support, Pause); - phylink_set(phy_support, Asym_Pause); - - caps = sfp_get_module_caps(phydev->sfp_bus); - /* Some modules support 10G modes as well as others we support. - * Mask out non-supported modes so the correct interface is picked. - */ - linkmode_and(sfp_support, phy_support, caps->link_modes); + struct phy_device *phydev = port_phydev(port); - if (linkmode_empty(sfp_support)) { - dev_err(&phydev->mdio.dev, "incompatible SFP module inserted\n"); - return -EINVAL; - } + if (interface == PHY_INTERFACE_MODE_SGMII) + dev_warn(&phydev->mdio.dev, + "module may not function if 1000Base-X not supported\n"); + + return 0; +} - iface = sfp_select_interface(phydev->sfp_bus, sfp_support); +static const struct phy_port_ops at803x_port_ops = { + .configure_mii = at803x_configure_mii, +}; - /* Only 1000Base-X is supported by AR8031/8033 as the downstream SerDes - * interface for use with SFP modules. - * However, some copper modules detected as having a preferred SGMII - * interface do default to and function in 1000Base-X mode, so just - * print a warning and allow such modules, as they may have some chance - * of working. +static int at8031_attach_mii_port(struct phy_device *phydev, + struct phy_port *port) +{ + linkmode_zero(port->supported); + phylink_set(port->supported, 1000baseX_Full); + phylink_set(port->supported, 1000baseT_Full); + phylink_set(port->supported, Autoneg); + phylink_set(port->supported, Pause); + phylink_set(port->supported, Asym_Pause); + + /* This device doesn't really support SGMII. However, do our best + * to be compatible with copper modules (that usually require SGMII), + * in a degraded mode as we only allow 1000BaseT Full */ - if (iface == PHY_INTERFACE_MODE_SGMII) - dev_warn(&phydev->mdio.dev, "module may not function if 1000Base-X not supported\n"); - else if (iface != PHY_INTERFACE_MODE_1000BASEX) - return -EINVAL; + __set_bit(PHY_INTERFACE_MODE_SGMII, port->interfaces); + __set_bit(PHY_INTERFACE_MODE_1000BASEX, port->interfaces); + + port->ops = &at803x_port_ops; return 0; } -static const struct sfp_upstream_ops at8031_sfp_ops = { - .attach = phy_sfp_attach, - .detach = phy_sfp_detach, - .module_insert = at8031_sfp_insert, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, -}; - static int at8031_parse_dt(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; @@ -840,8 +827,7 @@ static int at8031_parse_dt(struct phy_device *phydev) return ret; } - /* Only AR8031/8033 support 1000Base-X for SFP modules */ - return phy_sfp_probe(phydev, &at8031_sfp_ops); + return 0; } static int at8031_probe(struct phy_device *phydev) @@ -1172,6 +1158,7 @@ static struct phy_driver at803x_driver[] = { .set_tunable = at803x_set_tunable, .cable_test_start = at8031_cable_test_start, .cable_test_get_status = at8031_cable_test_get_status, + .attach_mii_port = at8031_attach_mii_port, }, { /* Qualcomm Atheros AR8032 */ PHY_ID_MATCH_EXACT(ATH8032_PHY_ID), diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c index 1be8295a95cb5..d8f1ce5a7128d 100644 --- a/drivers/net/phy/qcom/qca807x.c +++ b/drivers/net/phy/qcom/qca807x.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include "../phylib.h" #include "qcom.h" @@ -643,67 +643,54 @@ static int qca807x_phy_package_config_init_once(struct phy_device *phydev) return ret; } -static int qca807x_sfp_insert(void *upstream, const struct sfp_eeprom_id *id) +static int qca807x_configure_serdes(struct phy_port *port, bool enable, + phy_interface_t interface) { - struct phy_device *phydev = upstream; - const struct sfp_module_caps *caps; - phy_interface_t iface; + struct phy_device *phydev = port_phydev(port); int ret; - caps = sfp_get_module_caps(phydev->sfp_bus); - iface = sfp_select_interface(phydev->sfp_bus, caps->link_modes); + if (!phydev) + return -ENODEV; - dev_info(&phydev->mdio.dev, "%s SFP module inserted\n", phy_modes(iface)); - - switch (iface) { - case PHY_INTERFACE_MODE_1000BASEX: - case PHY_INTERFACE_MODE_100BASEX: + if (enable) { /* Set PHY mode to PSGMII combo (1/4 copper + combo ports) mode */ ret = phy_modify(phydev, QCA807X_CHIP_CONFIGURATION, QCA807X_CHIP_CONFIGURATION_MODE_CFG_MASK, QCA807X_CHIP_CONFIGURATION_MODE_PSGMII_FIBER); + if (ret) + return ret; /* Enable fiber mode autodection (1000Base-X or 100Base-FX) */ ret = phy_set_bits_mmd(phydev, MDIO_MMD_AN, QCA807X_MMD7_FIBER_MODE_AUTO_DETECTION, QCA807X_MMD7_FIBER_MODE_AUTO_DETECTION_EN); - /* Select fiber page */ - ret = phy_clear_bits(phydev, - QCA807X_CHIP_CONFIGURATION, - QCA807X_BT_BX_REG_SEL); - - phydev->port = PORT_FIBRE; - break; - default: - dev_err(&phydev->mdio.dev, "Incompatible SFP module inserted\n"); - return -EINVAL; + if (ret) + return ret; } - return ret; + phydev->port = enable ? PORT_FIBRE : PORT_TP; + + return phy_modify(phydev, QCA807X_CHIP_CONFIGURATION, + QCA807X_BT_BX_REG_SEL, + enable ? 0 : QCA807X_BT_BX_REG_SEL); } -static void qca807x_sfp_remove(void *upstream) +static const struct phy_port_ops qca807x_serdes_port_ops = { + .configure_mii = qca807x_configure_serdes, +}; + +static int qca807x_attach_mii_port(struct phy_device *phydev, + struct phy_port *port) { - struct phy_device *phydev = upstream; + __set_bit(PHY_INTERFACE_MODE_1000BASEX, port->interfaces); + __set_bit(PHY_INTERFACE_MODE_100BASEX, port->interfaces); - /* Select copper page */ - phy_set_bits(phydev, - QCA807X_CHIP_CONFIGURATION, - QCA807X_BT_BX_REG_SEL); + port->ops = &qca807x_serdes_port_ops; - phydev->port = PORT_TP; + return 0; } -static const struct sfp_upstream_ops qca807x_sfp_ops = { - .attach = phy_sfp_attach, - .detach = phy_sfp_detach, - .module_insert = qca807x_sfp_insert, - .module_remove = qca807x_sfp_remove, - .connect_phy = phy_sfp_connect_phy, - .disconnect_phy = phy_sfp_disconnect_phy, -}; - static int qca807x_probe(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; @@ -744,9 +731,8 @@ static int qca807x_probe(struct phy_device *phydev) /* Attach SFP bus on combo port*/ if (phy_read(phydev, QCA807X_CHIP_CONFIGURATION)) { - ret = phy_sfp_probe(phydev, &qca807x_sfp_ops); - if (ret) - return ret; + phydev->max_n_ports = 2; + linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->supported); linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, phydev->advertising); } @@ -824,6 +810,7 @@ static struct phy_driver qca807x_drivers[] = { .get_phy_stats = qca807x_get_phy_stats, .set_wol = at8031_set_wol, .get_wol = at803x_get_wol, + .attach_mii_port = qca807x_attach_mii_port, }, { PHY_ID_MATCH_EXACT(PHY_ID_QCA8075), @@ -851,6 +838,7 @@ static struct phy_driver qca807x_drivers[] = { .get_phy_stats = qca807x_get_phy_stats, .set_wol = at8031_set_wol, .get_wol = at803x_get_wol, + .attach_mii_port = qca807x_attach_mii_port, }, }; module_phy_driver(qca807x_drivers); diff --git a/drivers/net/phy/qt2025.rs b/drivers/net/phy/qt2025.rs index 0b9400dcb4c10..aaaead6512a01 100644 --- a/drivers/net/phy/qt2025.rs +++ b/drivers/net/phy/qt2025.rs @@ -12,6 +12,7 @@ use kernel::c_str; use kernel::error::code; use kernel::firmware::Firmware; +use kernel::io::poll::read_poll_timeout; use kernel::net::phy::{ self, reg::{Mmd, C45}, @@ -19,6 +20,7 @@ use kernel::net::phy::{ }; use kernel::prelude::*; use kernel::sizes::{SZ_16K, SZ_8K}; +use kernel::time::Delta; kernel::module_phy_driver! { drivers: [PhyQT2025], @@ -93,7 +95,13 @@ impl Driver for PhyQT2025 { // The micro-controller will start running from SRAM. dev.write(C45::new(Mmd::PCS, 0xe854), 0x0040)?; - // TODO: sleep here until the hw becomes ready. + read_poll_timeout( + || dev.read(C45::new(Mmd::PCS, 0xd7fd)), + |val| *val != 0x00 && *val != 0x10, + Delta::from_millis(50), + Delta::from_secs(3), + )?; + Ok(()) } diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c index 16a347084293e..417f9a88aab66 100644 --- a/drivers/net/phy/realtek/realtek_main.c +++ b/drivers/net/phy/realtek/realtek_main.c @@ -8,6 +8,7 @@ * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #include +#include #include #include #include @@ -127,6 +128,32 @@ */ #define RTL822X_VND2_C22_REG(reg) (0xa400 + 2 * (reg)) +#define RTL8221B_VND2_INER 0xa4d2 +#define RTL8221B_VND2_INER_LINK_STATUS BIT(4) + +#define RTL8221B_VND2_INSR 0xa4d4 + +#define RTL8224_MII_RTCT 0x11 +#define RTL8224_MII_RTCT_ENABLE BIT(0) +#define RTL8224_MII_RTCT_PAIR_A BIT(4) +#define RTL8224_MII_RTCT_PAIR_B BIT(5) +#define RTL8224_MII_RTCT_PAIR_C BIT(6) +#define RTL8224_MII_RTCT_PAIR_D BIT(7) +#define RTL8224_MII_RTCT_DONE BIT(15) + +#define RTL8224_MII_SRAM_ADDR 0x1b +#define RTL8224_MII_SRAM_DATA 0x1c + +#define RTL8224_SRAM_RTCT_FAULT(pair) (0x8026 + (pair) * 4) +#define RTL8224_SRAM_RTCT_FAULT_BUSY BIT(0) +#define RTL8224_SRAM_RTCT_FAULT_OPEN BIT(3) +#define RTL8224_SRAM_RTCT_FAULT_SAME_SHORT BIT(4) +#define RTL8224_SRAM_RTCT_FAULT_OK BIT(5) +#define RTL8224_SRAM_RTCT_FAULT_DONE BIT(6) +#define RTL8224_SRAM_RTCT_FAULT_CROSS_SHORT BIT(7) + +#define RTL8224_SRAM_RTCT_LEN(pair) (0x8028 + (pair) * 4) + #define RTL8366RB_POWER_SAVE 0x15 #define RTL8366RB_POWER_SAVE_ON BIT(12) @@ -1453,6 +1480,168 @@ static int rtl822xb_c45_read_status(struct phy_device *phydev) return 0; } +static int rtl8224_cable_test_start(struct phy_device *phydev) +{ + u32 val; + int ret; + + /* disable auto-negotiation and force 1000/Full */ + ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_C22_REG(MII_BMCR), + BMCR_ANENABLE | BMCR_SPEED100 | BMCR_SPEED10, + BMCR_SPEED1000 | BMCR_FULLDPLX); + if (ret) + return ret; + + mdelay(500); + + /* trigger cable test */ + val = RTL8224_MII_RTCT_ENABLE; + val |= RTL8224_MII_RTCT_PAIR_A; + val |= RTL8224_MII_RTCT_PAIR_B; + val |= RTL8224_MII_RTCT_PAIR_C; + val |= RTL8224_MII_RTCT_PAIR_D; + + return phy_modify_mmd(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_C22_REG(RTL8224_MII_RTCT), + RTL8224_MII_RTCT_DONE, val); +} + +static int rtl8224_sram_read(struct phy_device *phydev, u32 reg) +{ + int ret; + + ret = phy_write_mmd(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_C22_REG(RTL8224_MII_SRAM_ADDR), + reg); + if (ret) + return ret; + + return phy_read_mmd(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_C22_REG(RTL8224_MII_SRAM_DATA)); +} + +static int rtl8224_pair_len_get(struct phy_device *phydev, u32 pair) +{ + int cable_len; + u32 reg_len; + int ret; + u32 cm; + + reg_len = RTL8224_SRAM_RTCT_LEN(pair); + + ret = rtl8224_sram_read(phydev, reg_len); + if (ret < 0) + return ret; + + cable_len = ret & 0xff00; + + ret = rtl8224_sram_read(phydev, reg_len + 1); + if (ret < 0) + return ret; + + cable_len |= (ret & 0xff00) >> 8; + + cable_len -= 620; + cable_len = max(cable_len, 0); + + cm = cable_len * 100 / 78; + + return cm; +} + +static int rtl8224_cable_test_result_trans(u32 result) +{ + if (!(result & RTL8224_SRAM_RTCT_FAULT_DONE)) + return -EBUSY; + + if (result & RTL8224_SRAM_RTCT_FAULT_OK) + return ETHTOOL_A_CABLE_RESULT_CODE_OK; + + if (result & RTL8224_SRAM_RTCT_FAULT_OPEN) + return ETHTOOL_A_CABLE_RESULT_CODE_OPEN; + + if (result & RTL8224_SRAM_RTCT_FAULT_SAME_SHORT) + return ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT; + + if (result & RTL8224_SRAM_RTCT_FAULT_BUSY) + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; + + if (result & RTL8224_SRAM_RTCT_FAULT_CROSS_SHORT) + return ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT; + + return ETHTOOL_A_CABLE_RESULT_CODE_UNSPEC; +} + +static int rtl8224_cable_test_report_pair(struct phy_device *phydev, unsigned int pair) +{ + int fault_rslt; + int ret; + + ret = rtl8224_sram_read(phydev, RTL8224_SRAM_RTCT_FAULT(pair)); + if (ret < 0) + return ret; + + fault_rslt = rtl8224_cable_test_result_trans(ret); + if (fault_rslt < 0) + return 0; + + ret = ethnl_cable_test_result(phydev, pair, fault_rslt); + if (ret < 0) + return ret; + + switch (fault_rslt) { + case ETHTOOL_A_CABLE_RESULT_CODE_OPEN: + case ETHTOOL_A_CABLE_RESULT_CODE_SAME_SHORT: + case ETHTOOL_A_CABLE_RESULT_CODE_CROSS_SHORT: + ret = rtl8224_pair_len_get(phydev, pair); + if (ret < 0) + return ret; + + return ethnl_cable_test_fault_length(phydev, pair, ret); + default: + return 0; + } +} + +static int rtl8224_cable_test_report(struct phy_device *phydev, bool *finished) +{ + unsigned int pair; + int ret; + + for (pair = ETHTOOL_A_CABLE_PAIR_A; pair <= ETHTOOL_A_CABLE_PAIR_D; pair++) { + ret = rtl8224_cable_test_report_pair(phydev, pair); + if (ret == -EBUSY) { + *finished = false; + return 0; + } + + if (ret < 0) + return ret; + } + + return 0; +} + +static int rtl8224_cable_test_get_status(struct phy_device *phydev, bool *finished) +{ + int ret; + + *finished = false; + + ret = phy_read_mmd(phydev, MDIO_MMD_VEND2, + RTL822X_VND2_C22_REG(RTL8224_MII_RTCT)); + if (ret < 0) + return ret; + + if (!(ret & RTL8224_MII_RTCT_DONE)) + return 0; + + *finished = true; + + return rtl8224_cable_test_report(phydev, finished); +} + static bool rtlgen_supports_2_5gbps(struct phy_device *phydev) { int val; @@ -1696,6 +1885,53 @@ static irqreturn_t rtl9000a_handle_interrupt(struct phy_device *phydev) return IRQ_HANDLED; } +static int rtl8221b_ack_interrupt(struct phy_device *phydev) +{ + int err; + + err = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL8221B_VND2_INSR); + + return (err < 0) ? err : 0; +} + +static int rtl8221b_config_intr(struct phy_device *phydev) +{ + int err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + err = rtl8221b_ack_interrupt(phydev); + if (err) + return err; + + err = phy_write_mmd(phydev, MDIO_MMD_VEND2, RTL8221B_VND2_INER, + RTL8221B_VND2_INER_LINK_STATUS); + } else { + err = phy_write_mmd(phydev, MDIO_MMD_VEND2, + RTL8221B_VND2_INER, 0); + if (err) + return err; + + err = rtl8221b_ack_interrupt(phydev); + } + + return err; +} + +static irqreturn_t rtl8221b_handle_interrupt(struct phy_device *phydev) +{ + int err; + + err = rtl8221b_ack_interrupt(phydev); + if (err) { + phy_error(phydev); + return IRQ_NONE; + } + + phy_trigger_machine(phydev); + + return IRQ_HANDLED; +} + static struct phy_driver realtek_drvs[] = { { PHY_ID_MATCH_EXACT(0x00008201), @@ -1870,6 +2106,8 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8221b_vb_cg_c45_match_phy_device, .name = "RTL8221B-VB-CG 2.5Gbps PHY (C45)", + .config_intr = rtl8221b_config_intr, + .handle_interrupt = rtl8221b_handle_interrupt, .probe = rtl822x_probe, .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, @@ -1894,6 +2132,8 @@ static struct phy_driver realtek_drvs[] = { }, { .match_phy_device = rtl8221b_vm_cg_c45_match_phy_device, .name = "RTL8221B-VM-CG 2.5Gbps PHY (C45)", + .config_intr = rtl8221b_config_intr, + .handle_interrupt = rtl8221b_handle_interrupt, .probe = rtl822x_probe, .config_init = rtl822xb_config_init, .get_rate_matching = rtl822xb_get_rate_matching, @@ -1930,11 +2170,14 @@ static struct phy_driver realtek_drvs[] = { }, { PHY_ID_MATCH_EXACT(0x001ccad0), .name = "RTL8224 2.5Gbps PHY", + .flags = PHY_POLL_CABLE_TEST, .get_features = rtl822x_c45_get_features, .config_aneg = rtl822x_c45_config_aneg, .read_status = rtl822x_c45_read_status, .suspend = genphy_c45_pma_suspend, .resume = rtlgen_c45_resume, + .cable_test_start = rtl8224_cable_test_start, + .cable_test_get_status = rtl8224_cable_test_get_status, }, { PHY_ID_MATCH_EXACT(0x001cc961), .name = "RTL8366RB Gigabit Ethernet", diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c index 4ac6afce267b9..4275b393a4544 100644 --- a/drivers/net/ppp/pppoe.c +++ b/drivers/net/ppp/pppoe.c @@ -608,8 +608,8 @@ static int pppoe_release(struct socket *sock) return 0; } -static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr, - int sockaddr_len, int flags) +static int pppoe_connect(struct socket *sock, struct sockaddr_unsized *uservaddr, + int sockaddr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr; diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c index 90737cb718928..b18acd8105619 100644 --- a/drivers/net/ppp/pptp.c +++ b/drivers/net/ppp/pptp.c @@ -382,8 +382,8 @@ static int pptp_rcv(struct sk_buff *skb) return NET_RX_DROP; } -static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, - int sockaddr_len) +static int pptp_bind(struct socket *sock, struct sockaddr_unsized *uservaddr, + int sockaddr_len) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; @@ -415,8 +415,8 @@ static int pptp_bind(struct socket *sock, struct sockaddr *uservaddr, return error; } -static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr, - int sockaddr_len, int flags) +static int pptp_connect(struct socket *sock, struct sockaddr_unsized *uservaddr, + int sockaddr_len, int flags) { struct sock *sk = sock->sk; struct sockaddr_pppox *sp = (struct sockaddr_pppox *) uservaddr; diff --git a/drivers/net/pse-pd/pd692x0.c b/drivers/net/pse-pd/pd692x0.c index f4e91ba64a666..134435e900731 100644 --- a/drivers/net/pse-pd/pd692x0.c +++ b/drivers/net/pse-pd/pd692x0.c @@ -30,6 +30,8 @@ #define PD692X0_FW_MIN_VER 5 #define PD692X0_FW_PATCH_VER 5 +#define PD692X0_USER_BYTE 42 + enum pd692x0_fw_state { PD692X0_FW_UNKNOWN, PD692X0_FW_OK, @@ -80,11 +82,17 @@ enum { PD692X0_MSG_GET_PORT_PARAM, PD692X0_MSG_GET_POWER_BANK, PD692X0_MSG_SET_POWER_BANK, + PD692X0_MSG_SET_USER_BYTE, /* add new message above here */ PD692X0_MSG_CNT }; +struct pd692x0_matrix { + u8 hw_port_a; + u8 hw_port_b; +}; + struct pd692x0_priv { struct i2c_client *client; struct pse_controller_dev pcdev; @@ -98,9 +106,12 @@ struct pd692x0_priv { bool last_cmd_key; unsigned long last_cmd_key_time; + bool cfg_saved; enum ethtool_c33_pse_admin_state admin_state[PD692X0_MAX_PIS]; struct regulator_dev *manager_reg[PD692X0_MAX_MANAGERS]; int manager_pw_budget[PD692X0_MAX_MANAGERS]; + int nmanagers; + struct pd692x0_matrix *port_matrix; }; /* Template list of communication messages. The non-null bytes defined here @@ -186,6 +197,12 @@ static const struct pd692x0_msg pd692x0_msg_template_list[PD692X0_MSG_CNT] = { .key = PD692X0_KEY_CMD, .sub = {0x07, 0x0b, 0x57}, }, + [PD692X0_MSG_SET_USER_BYTE] = { + .key = PD692X0_KEY_PRG, + .sub = {0x41, PD692X0_USER_BYTE}, + .data = {0x4e, 0x4e, 0x4e, 0x4e, + 0x4e, 0x4e, 0x4e, 0x4e}, + }, }; static u8 pd692x0_build_msg(struct pd692x0_msg *msg, u8 echo) @@ -809,11 +826,6 @@ struct pd692x0_manager { int nports; }; -struct pd692x0_matrix { - u8 hw_port_a; - u8 hw_port_b; -}; - static int pd692x0_of_get_ports_manager(struct pd692x0_priv *priv, struct pd692x0_manager *manager, @@ -903,7 +915,8 @@ pd692x0_of_get_managers(struct pd692x0_priv *priv, } of_node_put(managers_node); - return nmanagers; + priv->nmanagers = nmanagers; + return 0; out: for (i = 0; i < nmanagers; i++) { @@ -963,8 +976,7 @@ pd692x0_register_manager_regulator(struct device *dev, char *reg_name, static int pd692x0_register_managers_regulator(struct pd692x0_priv *priv, - const struct pd692x0_manager *manager, - int nmanagers) + const struct pd692x0_manager *manager) { struct device *dev = &priv->client->dev; size_t reg_name_len; @@ -975,7 +987,7 @@ pd692x0_register_managers_regulator(struct pd692x0_priv *priv, */ reg_name_len = strlen(dev_name(dev)) + 23; - for (i = 0; i < nmanagers; i++) { + for (i = 0; i < priv->nmanagers; i++) { static const char * const regulators[] = { "vaux5", "vaux3p3" }; struct regulator_dev *rdev; char *reg_name; @@ -1008,10 +1020,14 @@ pd692x0_register_managers_regulator(struct pd692x0_priv *priv, } static int -pd692x0_conf_manager_power_budget(struct pd692x0_priv *priv, int id, int pw) +pd692x0_conf_manager_power_budget(struct pd692x0_priv *priv, int id) { struct pd692x0_msg msg, buf; - int ret, pw_mW = pw / 1000; + int ret, pw_mW; + + pw_mW = priv->manager_pw_budget[id] / 1000; + if (!pw_mW) + return 0; msg = pd692x0_msg_template_list[PD692X0_MSG_GET_POWER_BANK]; msg.data[0] = id; @@ -1032,11 +1048,11 @@ pd692x0_conf_manager_power_budget(struct pd692x0_priv *priv, int id, int pw) } static int -pd692x0_configure_managers(struct pd692x0_priv *priv, int nmanagers) +pd692x0_req_managers_pw_budget(struct pd692x0_priv *priv) { int i, ret; - for (i = 0; i < nmanagers; i++) { + for (i = 0; i < priv->nmanagers; i++) { struct regulator *supply = priv->manager_reg[i]->supply; int pw_budget; @@ -1053,7 +1069,18 @@ pd692x0_configure_managers(struct pd692x0_priv *priv, int nmanagers) return ret; priv->manager_pw_budget[i] = pw_budget; - ret = pd692x0_conf_manager_power_budget(priv, i, pw_budget); + } + + return 0; +} + +static int +pd692x0_configure_managers(struct pd692x0_priv *priv) +{ + int i, ret; + + for (i = 0; i < priv->nmanagers; i++) { + ret = pd692x0_conf_manager_power_budget(priv, i); if (ret < 0) return ret; } @@ -1101,10 +1128,9 @@ pd692x0_set_port_matrix(const struct pse_pi_pairset *pairset, static int pd692x0_set_ports_matrix(struct pd692x0_priv *priv, - const struct pd692x0_manager *manager, - int nmanagers, - struct pd692x0_matrix port_matrix[PD692X0_MAX_PIS]) + const struct pd692x0_manager *manager) { + struct pd692x0_matrix *port_matrix = priv->port_matrix; struct pse_controller_dev *pcdev = &priv->pcdev; int i, ret; @@ -1117,7 +1143,7 @@ pd692x0_set_ports_matrix(struct pd692x0_priv *priv, /* Update with values for every PSE PIs */ for (i = 0; i < pcdev->nr_lines; i++) { ret = pd692x0_set_port_matrix(&pcdev->pi[i].pairset[0], - manager, nmanagers, + manager, priv->nmanagers, &port_matrix[i]); if (ret) { dev_err(&priv->client->dev, @@ -1126,7 +1152,7 @@ pd692x0_set_ports_matrix(struct pd692x0_priv *priv, } ret = pd692x0_set_port_matrix(&pcdev->pi[i].pairset[1], - manager, nmanagers, + manager, priv->nmanagers, &port_matrix[i]); if (ret) { dev_err(&priv->client->dev, @@ -1139,9 +1165,9 @@ pd692x0_set_ports_matrix(struct pd692x0_priv *priv, } static int -pd692x0_write_ports_matrix(struct pd692x0_priv *priv, - const struct pd692x0_matrix port_matrix[PD692X0_MAX_PIS]) +pd692x0_write_ports_matrix(struct pd692x0_priv *priv) { + struct pd692x0_matrix *port_matrix = priv->port_matrix; struct pd692x0_msg msg, buf; int ret, i; @@ -1166,13 +1192,32 @@ pd692x0_write_ports_matrix(struct pd692x0_priv *priv, return 0; } +static int pd692x0_hw_conf_init(struct pd692x0_priv *priv) +{ + int ret; + + /* Is PD692x0 ready to be configured? */ + if (priv->fw_state != PD692X0_FW_OK && + priv->fw_state != PD692X0_FW_COMPLETE) + return 0; + + ret = pd692x0_configure_managers(priv); + if (ret) + return ret; + + ret = pd692x0_write_ports_matrix(priv); + if (ret) + return ret; + + return 0; +} + static void pd692x0_of_put_managers(struct pd692x0_priv *priv, - struct pd692x0_manager *manager, - int nmanagers) + struct pd692x0_manager *manager) { int i, j; - for (i = 0; i < nmanagers; i++) { + for (i = 0; i < priv->nmanagers; i++) { for (j = 0; j < manager[i].nports; j++) of_node_put(manager[i].port_node[j]); of_node_put(manager[i].node); @@ -1198,50 +1243,71 @@ static void pd692x0_managers_free_pw_budget(struct pd692x0_priv *priv) } } +static int +pd692x0_save_user_byte(struct pd692x0_priv *priv) +{ + struct pd692x0_msg msg, buf; + + msg = pd692x0_msg_template_list[PD692X0_MSG_SET_USER_BYTE]; + return pd692x0_sendrecv_msg(priv, &msg, &buf); +} + static int pd692x0_setup_pi_matrix(struct pse_controller_dev *pcdev) { - struct pd692x0_manager *manager __free(kfree) = NULL; struct pd692x0_priv *priv = to_pd692x0_priv(pcdev); - struct pd692x0_matrix port_matrix[PD692X0_MAX_PIS]; - int ret, nmanagers; - - /* Should we flash the port matrix */ - if (priv->fw_state != PD692X0_FW_OK && - priv->fw_state != PD692X0_FW_COMPLETE) - return 0; + struct pd692x0_matrix *port_matrix; + struct pd692x0_manager *manager; + int ret; manager = kcalloc(PD692X0_MAX_MANAGERS, sizeof(*manager), GFP_KERNEL); if (!manager) return -ENOMEM; + port_matrix = devm_kcalloc(&priv->client->dev, PD692X0_MAX_PIS, + sizeof(*port_matrix), GFP_KERNEL); + if (!port_matrix) { + ret = -ENOMEM; + goto err_free_manager; + } + priv->port_matrix = port_matrix; + ret = pd692x0_of_get_managers(priv, manager); if (ret < 0) - return ret; + goto err_free_manager; - nmanagers = ret; - ret = pd692x0_register_managers_regulator(priv, manager, nmanagers); + ret = pd692x0_register_managers_regulator(priv, manager); if (ret) goto err_of_managers; - ret = pd692x0_configure_managers(priv, nmanagers); + ret = pd692x0_req_managers_pw_budget(priv); if (ret) goto err_of_managers; - ret = pd692x0_set_ports_matrix(priv, manager, nmanagers, port_matrix); + ret = pd692x0_set_ports_matrix(priv, manager); if (ret) goto err_managers_req_pw; - ret = pd692x0_write_ports_matrix(priv, port_matrix); - if (ret) - goto err_managers_req_pw; + /* Do not init the conf if it is already saved */ + if (!priv->cfg_saved) { + ret = pd692x0_hw_conf_init(priv); + if (ret) + goto err_managers_req_pw; - pd692x0_of_put_managers(priv, manager, nmanagers); + ret = pd692x0_save_user_byte(priv); + if (ret) + goto err_managers_req_pw; + } + + pd692x0_of_put_managers(priv, manager); + kfree(manager); return 0; err_managers_req_pw: pd692x0_managers_free_pw_budget(priv); err_of_managers: - pd692x0_of_put_managers(priv, manager, nmanagers); + pd692x0_of_put_managers(priv, manager); +err_free_manager: + kfree(manager); return ret; } @@ -1644,7 +1710,7 @@ static enum fw_upload_err pd692x0_fw_poll_complete(struct fw_upload *fwl) return FW_UPLOAD_ERR_FW_INVALID; } - ret = pd692x0_setup_pi_matrix(&priv->pcdev); + ret = pd692x0_hw_conf_init(priv); if (ret < 0) { dev_err(&client->dev, "Error configuring ports matrix (%pe)\n", ERR_PTR(ret)); @@ -1753,6 +1819,9 @@ static int pd692x0_i2c_probe(struct i2c_client *client) } } + if (buf.data[2] == PD692X0_USER_BYTE) + priv->cfg_saved = true; + priv->np = dev->of_node; priv->pcdev.nr_lines = PD692X0_MAX_PIS; priv->pcdev.owner = THIS_MODULE; diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c index b724b222ab44c..76ec1555d60df 100644 --- a/drivers/net/pse-pd/tps23881.c +++ b/drivers/net/pse-pd/tps23881.c @@ -55,8 +55,6 @@ #define TPS23881_REG_TPON BIT(0) #define TPS23881_REG_FWREV 0x41 #define TPS23881_REG_DEVID 0x43 -#define TPS23881_REG_DEVID_MASK 0xF0 -#define TPS23881_DEVICE_ID 0x02 #define TPS23881_REG_CHAN1_CLASS 0x4c #define TPS23881_REG_SRAM_CTRL 0x60 #define TPS23881_REG_SRAM_DATA 0x61 @@ -1012,8 +1010,28 @@ static const struct pse_controller_ops tps23881_ops = { .pi_get_pw_req = tps23881_pi_get_pw_req, }; -static const char fw_parity_name[] = "ti/tps23881/tps23881-parity-14.bin"; -static const char fw_sram_name[] = "ti/tps23881/tps23881-sram-14.bin"; +struct tps23881_info { + u8 dev_id; /* device ID and silicon revision */ + const char *fw_parity_name; /* parity code firmware file name */ + const char *fw_sram_name; /* SRAM code firmware file name */ +}; + +enum tps23881_model { + TPS23881, + TPS23881B, +}; + +static const struct tps23881_info tps23881_info[] = { + [TPS23881] = { + .dev_id = 0x22, + .fw_parity_name = "ti/tps23881/tps23881-parity-14.bin", + .fw_sram_name = "ti/tps23881/tps23881-sram-14.bin", + }, + [TPS23881B] = { + .dev_id = 0x24, + /* skip SRAM load, ROM provides Clause 145 hardware-level support */ + }, +}; struct tps23881_fw_conf { u8 reg; @@ -1085,16 +1103,17 @@ static int tps23881_flash_sram_fw_part(struct i2c_client *client, return ret; } -static int tps23881_flash_sram_fw(struct i2c_client *client) +static int tps23881_flash_sram_fw(struct i2c_client *client, + const struct tps23881_info *info) { int ret; - ret = tps23881_flash_sram_fw_part(client, fw_parity_name, + ret = tps23881_flash_sram_fw_part(client, info->fw_parity_name, tps23881_fw_parity_conf); if (ret) return ret; - ret = tps23881_flash_sram_fw_part(client, fw_sram_name, + ret = tps23881_flash_sram_fw_part(client, info->fw_sram_name, tps23881_fw_sram_conf); if (ret) return ret; @@ -1412,6 +1431,7 @@ static int tps23881_setup_irq(struct tps23881_priv *priv, int irq) static int tps23881_i2c_probe(struct i2c_client *client) { struct device *dev = &client->dev; + const struct tps23881_info *info; struct tps23881_priv *priv; struct gpio_desc *reset; int ret; @@ -1422,6 +1442,10 @@ static int tps23881_i2c_probe(struct i2c_client *client) return -ENXIO; } + info = i2c_get_match_data(client); + if (!info) + return -EINVAL; + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) return -ENOMEM; @@ -1440,7 +1464,7 @@ static int tps23881_i2c_probe(struct i2c_client *client) * to Load TPS2388x SRAM and Parity Code over I2C" (Rev E)) * indicates we should delay that programming by at least 50ms. So * we'll wait the entire 50ms here to ensure we're safe to go to the - * SRAM loading proceedure. + * SRAM loading procedure. */ msleep(50); } @@ -1449,20 +1473,27 @@ static int tps23881_i2c_probe(struct i2c_client *client) if (ret < 0) return ret; - if (FIELD_GET(TPS23881_REG_DEVID_MASK, ret) != TPS23881_DEVICE_ID) { + if (ret != info->dev_id) { dev_err(dev, "Wrong device ID\n"); return -ENXIO; } - ret = tps23881_flash_sram_fw(client); - if (ret < 0) - return ret; + if (info->fw_sram_name) { + ret = tps23881_flash_sram_fw(client, info); + if (ret < 0) + return ret; + } ret = i2c_smbus_read_byte_data(client, TPS23881_REG_FWREV); if (ret < 0) return ret; - dev_info(&client->dev, "Firmware revision 0x%x\n", ret); + if (ret == 0xFF) { + dev_err(&client->dev, "Device entered safe mode\n"); + return -ENXIO; + } + dev_info(&client->dev, "Firmware revision 0x%x%s\n", ret, + ret == 0x00 ? " (ROM firmware)" : ""); /* Set configuration B, 16 bit access on a single device address */ ret = i2c_smbus_read_byte_data(client, TPS23881_REG_GEN_MASK); @@ -1498,13 +1529,21 @@ static int tps23881_i2c_probe(struct i2c_client *client) } static const struct i2c_device_id tps23881_id[] = { - { "tps23881" }, + { "tps23881", .driver_data = (kernel_ulong_t)&tps23881_info[TPS23881] }, + { "tps23881b", .driver_data = (kernel_ulong_t)&tps23881_info[TPS23881B] }, { } }; MODULE_DEVICE_TABLE(i2c, tps23881_id); static const struct of_device_id tps23881_of_match[] = { - { .compatible = "ti,tps23881", }, + { + .compatible = "ti,tps23881", + .data = &tps23881_info[TPS23881] + }, + { + .compatible = "ti,tps23881b", + .data = &tps23881_info[TPS23881B] + }, { }, }; MODULE_DEVICE_TABLE(of, tps23881_of_match); diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c index 55aa8d0c8e1f2..c10198d44576e 100644 --- a/drivers/net/sungem_phy.c +++ b/drivers/net/sungem_phy.c @@ -1165,7 +1165,7 @@ int sungem_phy_probe(struct mii_phy *phy, int mii_id) int i; /* We do not reset the mii_phy structure as the driver - * may re-probe the PHY regulary + * may re-probe the PHY regularly */ phy->mii_id = mii_id; diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c index 17f07eb0ee52a..94c149e892317 100644 --- a/drivers/net/team/team_core.c +++ b/drivers/net/team/team_core.c @@ -982,63 +982,6 @@ static void team_port_disable(struct team *team, team_lower_state_changed(port); } -#define TEAM_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ - NETIF_F_HIGHDMA | NETIF_F_LRO | \ - NETIF_F_GSO_ENCAP_ALL) - -#define TEAM_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ - NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE) - -static void __team_compute_features(struct team *team) -{ - struct team_port *port; - netdev_features_t vlan_features = TEAM_VLAN_FEATURES; - netdev_features_t enc_features = TEAM_ENC_FEATURES; - unsigned short max_hard_header_len = ETH_HLEN; - unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | - IFF_XMIT_DST_RELEASE_PERM; - - rcu_read_lock(); - if (list_empty(&team->port_list)) - goto done; - - vlan_features = netdev_base_features(vlan_features); - enc_features = netdev_base_features(enc_features); - - list_for_each_entry_rcu(port, &team->port_list, list) { - vlan_features = netdev_increment_features(vlan_features, - port->dev->vlan_features, - TEAM_VLAN_FEATURES); - enc_features = - netdev_increment_features(enc_features, - port->dev->hw_enc_features, - TEAM_ENC_FEATURES); - - dst_release_flag &= port->dev->priv_flags; - if (port->dev->hard_header_len > max_hard_header_len) - max_hard_header_len = port->dev->hard_header_len; - } -done: - rcu_read_unlock(); - - team->dev->vlan_features = vlan_features; - team->dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_STAG_TX; - team->dev->hard_header_len = max_hard_header_len; - - team->dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; - if (dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) - team->dev->priv_flags |= IFF_XMIT_DST_RELEASE; -} - -static void team_compute_features(struct team *team) -{ - __team_compute_features(team); - netdev_change_features(team->dev); -} - static int team_port_enter(struct team *team, struct team_port *port) { int err = 0; @@ -1191,10 +1134,6 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return -EPERM; } - err = team_dev_type_check_change(dev, port_dev); - if (err) - return err; - if (port_dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Device is up. Set it down before adding it as a team port"); netdev_err(dev, "Device %s is up. Set it down before adding it as a team port\n", @@ -1212,10 +1151,12 @@ static int team_port_add(struct team *team, struct net_device *port_dev, INIT_LIST_HEAD(&port->qom_list); port->orig.mtu = port_dev->mtu; - err = dev_set_mtu(port_dev, dev->mtu); - if (err) { - netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); - goto err_set_mtu; + if (dev->type == port_dev->type) { + err = dev_set_mtu(port_dev, dev->mtu); + if (err) { + netdev_dbg(dev, "Error %d calling dev_set_mtu\n", err); + goto err_set_mtu; + } } memcpy(port->orig.dev_addr, port_dev->dev_addr, port_dev->addr_len); @@ -1290,6 +1231,10 @@ static int team_port_add(struct team *team, struct net_device *port_dev, } } + err = team_dev_type_check_change(dev, port_dev); + if (err) + goto err_set_dev_type; + if (dev->flags & IFF_UP) { netif_addr_lock_bh(dev); dev_uc_sync_multiple(port_dev, dev); @@ -1300,7 +1245,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, port->index = -1; list_add_tail_rcu(&port->list, &team->port_list); team_port_enable(team, port); - __team_compute_features(team); + netdev_compute_master_upper_features(team->dev, true); __team_port_change_port_added(port, !!netif_oper_up(port_dev)); __team_options_change_check(team); @@ -1308,6 +1253,7 @@ static int team_port_add(struct team *team, struct net_device *port_dev, return 0; +err_set_dev_type: err_set_slave_promisc: __team_option_inst_del_port(team, port); @@ -1382,7 +1328,7 @@ static int team_port_del(struct team *team, struct net_device *port_dev) dev_set_mtu(port_dev, port->orig.mtu); kfree_rcu(port, rcu); netdev_info(dev, "Port device %s removed\n", portname); - __team_compute_features(team); + netdev_compute_master_upper_features(team->dev, true); return 0; } @@ -1970,33 +1916,19 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev, struct netlink_ext_ack *extack) { struct team *team = netdev_priv(dev); - int err; ASSERT_RTNL(); - err = team_port_add(team, port_dev, extack); - - if (!err) - netdev_change_features(dev); - - return err; + return team_port_add(team, port_dev, extack); } static int team_del_slave(struct net_device *dev, struct net_device *port_dev) { struct team *team = netdev_priv(dev); - int err; ASSERT_RTNL(); - err = team_port_del(team, port_dev); - - if (err) - return err; - - netdev_change_features(dev); - - return err; + return team_port_del(team, port_dev); } static netdev_features_t team_fix_features(struct net_device *dev, @@ -2190,7 +2122,7 @@ static void team_setup(struct net_device *dev) dev->features |= NETIF_F_GRO; - dev->hw_features = TEAM_VLAN_FEATURES | + dev->hw_features = MASTER_UPPER_DEV_VLAN_FEATURES | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_RX | @@ -2994,7 +2926,7 @@ static int team_device_event(struct notifier_block *unused, case NETDEV_FEAT_CHANGE: if (!port->team->notifier_ctx) { port->team->notifier_ctx = true; - team_compute_features(port->team); + netdev_compute_master_upper_features(port->team->dev, true); port->team->notifier_ctx = false; } break; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index a22d4bb2cf3b5..fa51925838607 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -9311,6 +9311,7 @@ static const struct ethtool_ops ops = { .set_ringparam = rtl8152_set_ringparam, .get_pauseparam = rtl8152_get_pauseparam, .set_pauseparam = rtl8152_set_pauseparam, + .get_ts_info = ethtool_op_get_ts_info, }; static int rtl8152_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 697cd9d866d3d..1d9faa70ba3b7 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -142,16 +142,16 @@ int usbnet_get_endpoints(struct usbnet *dev, struct usb_interface *intf) if (alt->desc.bAlternateSetting != 0 || !(dev->driver_info->flags & FLAG_NO_SETINT)) { - tmp = usb_set_interface (dev->udev, alt->desc.bInterfaceNumber, - alt->desc.bAlternateSetting); + tmp = usb_set_interface(dev->udev, alt->desc.bInterfaceNumber, + alt->desc.bAlternateSetting); if (tmp < 0) return tmp; } - dev->in = usb_rcvbulkpipe (dev->udev, - in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); - dev->out = usb_sndbulkpipe (dev->udev, - out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + dev->in = usb_rcvbulkpipe(dev->udev, + in->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); + dev->out = usb_sndbulkpipe(dev->udev, + out->desc.bEndpointAddress & USB_ENDPOINT_NUMBER_MASK); dev->status = status; return 0; } @@ -163,7 +163,7 @@ int usbnet_get_ethernet_addr(struct usbnet *dev, int iMACAddress) int tmp = -1, ret; unsigned char buf [13]; - ret = usb_string(dev->udev, iMACAddress, buf, sizeof buf); + ret = usb_string(dev->udev, iMACAddress, buf, sizeof(buf)); if (ret == 12) tmp = hex2bin(addr, buf, 6); if (tmp < 0) { @@ -189,7 +189,7 @@ static bool usbnet_needs_usb_name_format(struct usbnet *dev, struct net_device * is_local_ether_addr(net->dev_addr)); } -static void intr_complete (struct urb *urb) +static void intr_complete(struct urb *urb) { struct usbnet *dev = urb->context; int status = urb->status; @@ -215,13 +215,13 @@ static void intr_complete (struct urb *urb) break; } - status = usb_submit_urb (urb, GFP_ATOMIC); + status = usb_submit_urb(urb, GFP_ATOMIC); if (status != 0) netif_err(dev, timer, dev->net, "intr resubmit --> %d\n", status); } -static int init_status (struct usbnet *dev, struct usb_interface *intf) +static int init_status(struct usbnet *dev, struct usb_interface *intf) { char *buf = NULL; unsigned pipe = 0; @@ -231,24 +231,24 @@ static int init_status (struct usbnet *dev, struct usb_interface *intf) if (!dev->driver_info->status) return 0; - pipe = usb_rcvintpipe (dev->udev, - dev->status->desc.bEndpointAddress - & USB_ENDPOINT_NUMBER_MASK); + pipe = usb_rcvintpipe(dev->udev, + dev->status->desc.bEndpointAddress + & USB_ENDPOINT_NUMBER_MASK); maxp = usb_maxpacket(dev->udev, pipe); /* avoid 1 msec chatter: min 8 msec poll rate */ period = max ((int) dev->status->desc.bInterval, (dev->udev->speed == USB_SPEED_HIGH) ? 7 : 3); - buf = kmalloc (maxp, GFP_KERNEL); + buf = kmalloc(maxp, GFP_KERNEL); if (buf) { - dev->interrupt = usb_alloc_urb (0, GFP_KERNEL); + dev->interrupt = usb_alloc_urb(0, GFP_KERNEL); if (!dev->interrupt) { - kfree (buf); + kfree(buf); return -ENOMEM; } else { usb_fill_int_urb(dev->interrupt, dev->udev, pipe, - buf, maxp, intr_complete, dev, period); + buf, maxp, intr_complete, dev, period); dev->interrupt->transfer_flags |= URB_FREE_BUFFER; dev_dbg(&intf->dev, "status ep%din, %d bytes period %d\n", @@ -326,7 +326,7 @@ static void __usbnet_status_stop_force(struct usbnet *dev) * Some link protocols batch packets, so their rx_fixup paths * can return clones as well as just modify the original skb. */ -void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) +void usbnet_skb_return(struct usbnet *dev, struct sk_buff *skb) { struct pcpu_sw_netstats *stats64 = this_cpu_ptr(dev->net->tstats); unsigned long flags; @@ -339,7 +339,7 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) /* only update if unset to allow minidriver rx_fixup override */ if (skb->protocol == 0) - skb->protocol = eth_type_trans (skb, dev->net); + skb->protocol = eth_type_trans(skb, dev->net); flags = u64_stats_update_begin_irqsave(&stats64->syncp); u64_stats_inc(&stats64->rx_packets); @@ -347,8 +347,8 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) u64_stats_update_end_irqrestore(&stats64->syncp, flags); netif_dbg(dev, rx_status, dev->net, "< rx, len %zu, type 0x%x\n", - skb->len + sizeof (struct ethhdr), skb->protocol); - memset (skb->cb, 0, sizeof (struct skb_data)); + skb->len + sizeof(struct ethhdr), skb->protocol); + memset(skb->cb, 0, sizeof(struct skb_data)); if (skb_defer_rx_timestamp(skb)) return; @@ -396,7 +396,7 @@ EXPORT_SYMBOL_GPL(usbnet_update_max_qlen); * *-------------------------------------------------------------------------*/ -int usbnet_change_mtu (struct net_device *net, int new_mtu) +int usbnet_change_mtu(struct net_device *net, int new_mtu) { struct usbnet *dev = netdev_priv(net); int ll_mtu = new_mtu + net->hard_header_len; @@ -472,7 +472,7 @@ static enum skb_state defer_bh(struct usbnet *dev, struct sk_buff *skb, * NOTE: annoying asymmetry: if it's active, schedule_work() fails, * but tasklet_schedule() doesn't. hope the failure is rare. */ -void usbnet_defer_kevent (struct usbnet *dev, int work) +void usbnet_defer_kevent(struct usbnet *dev, int work) { set_bit (work, &dev->flags); if (!usbnet_going_away(dev)) { @@ -489,9 +489,9 @@ EXPORT_SYMBOL_GPL(usbnet_defer_kevent); /*-------------------------------------------------------------------------*/ -static void rx_complete (struct urb *urb); +static void rx_complete(struct urb *urb); -static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) +static int rx_submit(struct usbnet *dev, struct urb *urb, gfp_t flags) { struct sk_buff *skb; struct skb_data *entry; @@ -511,8 +511,8 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) skb = __netdev_alloc_skb_ip_align(dev->net, size, flags); if (!skb) { netif_dbg(dev, rx_err, dev->net, "no rx skb\n"); - usbnet_defer_kevent (dev, EVENT_RX_MEMORY); - usb_free_urb (urb); + usbnet_defer_kevent(dev, EVENT_RX_MEMORY); + usb_free_urb(urb); return -ENOMEM; } @@ -521,27 +521,27 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) entry->dev = dev; entry->length = 0; - usb_fill_bulk_urb (urb, dev->udev, dev->in, - skb->data, size, rx_complete, skb); + usb_fill_bulk_urb(urb, dev->udev, dev->in, + skb->data, size, rx_complete, skb); - spin_lock_irqsave (&dev->rxq.lock, lockflags); + spin_lock_irqsave(&dev->rxq.lock, lockflags); - if (netif_running (dev->net) && - netif_device_present (dev->net) && + if (netif_running(dev->net) && + netif_device_present(dev->net) && test_bit(EVENT_DEV_OPEN, &dev->flags) && - !test_bit (EVENT_RX_HALT, &dev->flags) && - !test_bit (EVENT_DEV_ASLEEP, &dev->flags) && + !test_bit(EVENT_RX_HALT, &dev->flags) && + !test_bit(EVENT_DEV_ASLEEP, &dev->flags) && !usbnet_going_away(dev)) { - switch (retval = usb_submit_urb (urb, GFP_ATOMIC)) { + switch (retval = usb_submit_urb(urb, GFP_ATOMIC)) { case -EPIPE: - usbnet_defer_kevent (dev, EVENT_RX_HALT); + usbnet_defer_kevent(dev, EVENT_RX_HALT); break; case -ENOMEM: - usbnet_defer_kevent (dev, EVENT_RX_MEMORY); + usbnet_defer_kevent(dev, EVENT_RX_MEMORY); break; case -ENODEV: netif_dbg(dev, ifdown, dev->net, "device gone\n"); - netif_device_detach (dev->net); + netif_device_detach(dev->net); break; case -EHOSTUNREACH: retval = -ENOLINK; @@ -558,10 +558,10 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) netif_dbg(dev, ifdown, dev->net, "rx: stopped\n"); retval = -ENOLINK; } - spin_unlock_irqrestore (&dev->rxq.lock, lockflags); + spin_unlock_irqrestore(&dev->rxq.lock, lockflags); if (retval) { - dev_kfree_skb_any (skb); - usb_free_urb (urb); + dev_kfree_skb_any(skb); + usb_free_urb(urb); } return retval; } @@ -572,7 +572,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags) static inline int rx_process(struct usbnet *dev, struct sk_buff *skb) { if (dev->driver_info->rx_fixup && - !dev->driver_info->rx_fixup (dev, skb)) { + !dev->driver_info->rx_fixup(dev, skb)) { /* With RX_ASSEMBLE, rx_fixup() must update counters */ if (!(dev->driver_info->flags & FLAG_RX_ASSEMBLE)) dev->net->stats.rx_errors++; @@ -597,7 +597,7 @@ static inline int rx_process(struct usbnet *dev, struct sk_buff *skb) /*-------------------------------------------------------------------------*/ -static void rx_complete (struct urb *urb) +static void rx_complete(struct urb *urb) { struct sk_buff *skb = (struct sk_buff *) urb->context; struct skb_data *entry = (struct skb_data *) skb->cb; @@ -605,7 +605,7 @@ static void rx_complete (struct urb *urb) int urb_status = urb->status; enum skb_state state; - skb_put (skb, urb->actual_length); + skb_put(skb, urb->actual_length); state = rx_done; entry->urb = NULL; @@ -621,7 +621,7 @@ static void rx_complete (struct urb *urb) */ case -EPIPE: dev->net->stats.rx_errors++; - usbnet_defer_kevent (dev, EVENT_RX_HALT); + usbnet_defer_kevent(dev, EVENT_RX_HALT); fallthrough; /* software-driven interface shutdown */ @@ -639,8 +639,8 @@ static void rx_complete (struct urb *urb) case -ETIME: case -EILSEQ: dev->net->stats.rx_errors++; - if (!timer_pending (&dev->delay)) { - mod_timer (&dev->delay, jiffies + THROTTLE_JIFFIES); + if (!timer_pending(&dev->delay)) { + mod_timer(&dev->delay, jiffies + THROTTLE_JIFFIES); netif_dbg(dev, link, dev->net, "rx throttle %d\n", urb_status); } @@ -676,14 +676,14 @@ static void rx_complete (struct urb *urb) state = defer_bh(dev, skb, &dev->rxq, state); if (urb) { - if (netif_running (dev->net) && - !test_bit (EVENT_RX_HALT, &dev->flags) && + if (netif_running(dev->net) && + !test_bit(EVENT_RX_HALT, &dev->flags) && state != unlink_start) { - rx_submit (dev, urb, GFP_ATOMIC); + rx_submit(dev, urb, GFP_ATOMIC); usb_mark_last_busy(dev->udev); return; } - usb_free_urb (urb); + usb_free_urb(urb); } netif_dbg(dev, rx_err, dev->net, "no read resubmitted\n"); } @@ -728,7 +728,7 @@ EXPORT_SYMBOL_GPL(usbnet_purge_paused_rxq); // unlink pending rx/tx; completion handlers do all other cleanup -static int unlink_urbs (struct usbnet *dev, struct sk_buff_head *q) +static int unlink_urbs(struct usbnet *dev, struct sk_buff_head *q) { unsigned long flags; struct sk_buff *skb; @@ -761,7 +761,7 @@ static int unlink_urbs (struct usbnet *dev, struct sk_buff_head *q) spin_unlock_irqrestore(&q->lock, flags); // during some PM-driven resume scenarios, // these (async) unlinks complete immediately - retval = usb_unlink_urb (urb); + retval = usb_unlink_urb(urb); if (retval != -EINPROGRESS && retval != 0) netdev_dbg(dev->net, "unlink urb err, %d\n", retval); else @@ -769,7 +769,7 @@ static int unlink_urbs (struct usbnet *dev, struct sk_buff_head *q) usb_put_urb(urb); spin_lock_irqsave(&q->lock, flags); } - spin_unlock_irqrestore (&q->lock, flags); + spin_unlock_irqrestore(&q->lock, flags); return count; } @@ -823,14 +823,15 @@ static void usbnet_terminate_urbs(struct usbnet *dev) remove_wait_queue(&dev->wait, &wait); } -int usbnet_stop (struct net_device *net) +int usbnet_stop(struct net_device *net) { struct usbnet *dev = netdev_priv(net); const struct driver_info *info = dev->driver_info; int retval, pm, mpn; clear_bit(EVENT_DEV_OPEN, &dev->flags); - netif_stop_queue (net); + netif_stop_queue(net); + netdev_reset_queue(net); netif_info(dev, ifdown, dev->net, "stop stats: rx/tx %lu/%lu, errs %lu/%lu\n", @@ -892,7 +893,7 @@ EXPORT_SYMBOL_GPL(usbnet_stop); // precondition: never called in_interrupt -int usbnet_open (struct net_device *net) +int usbnet_open(struct net_device *net) { struct usbnet *dev = netdev_priv(net); int retval; @@ -909,23 +910,29 @@ int usbnet_open (struct net_device *net) } // put into "known safe" state - if (info->reset && (retval = info->reset (dev)) < 0) { - netif_info(dev, ifup, dev->net, - "open reset fail (%d) usbnet usb-%s-%s, %s\n", - retval, - dev->udev->bus->bus_name, - dev->udev->devpath, - info->description); - goto done; + if (info->reset) { + retval = info->reset(dev); + if (retval < 0) { + netif_info(dev, ifup, dev->net, + "open reset fail (%d) usbnet usb-%s-%s, %s\n", + retval, + dev->udev->bus->bus_name, + dev->udev->devpath, + info->description); + goto done; + } } /* hard_mtu or rx_urb_size may change in reset() */ usbnet_update_max_qlen(dev); // insist peer be connected - if (info->check_connect && (retval = info->check_connect (dev)) < 0) { - netif_err(dev, ifup, dev->net, "can't open; %d\n", retval); - goto done; + if (info->check_connect) { + retval = info->check_connect(dev); + if (retval < 0) { + netif_err(dev, ifup, dev->net, "can't open; %d\n", retval); + goto done; + } } /* start any status interrupt transfer */ @@ -939,6 +946,7 @@ int usbnet_open (struct net_device *net) } set_bit(EVENT_DEV_OPEN, &dev->flags); + netdev_reset_queue(net); netif_start_queue (net); netif_info(dev, ifup, dev->net, "open: enable queueing (rx %d, tx %d) mtu %d %s framing\n", @@ -1048,13 +1056,13 @@ int usbnet_set_link_ksettings_mii(struct net_device *net, } EXPORT_SYMBOL_GPL(usbnet_set_link_ksettings_mii); -u32 usbnet_get_link (struct net_device *net) +u32 usbnet_get_link(struct net_device *net) { struct usbnet *dev = netdev_priv(net); /* If a check_connect is defined, return its result */ if (dev->driver_info->check_connect) - return dev->driver_info->check_connect (dev) == 0; + return dev->driver_info->check_connect(dev) == 0; /* if the device has mii operations, use those */ if (dev->mii.mdio_read) @@ -1076,18 +1084,18 @@ int usbnet_nway_reset(struct net_device *net) } EXPORT_SYMBOL_GPL(usbnet_nway_reset); -void usbnet_get_drvinfo (struct net_device *net, struct ethtool_drvinfo *info) +void usbnet_get_drvinfo(struct net_device *net, struct ethtool_drvinfo *info) { struct usbnet *dev = netdev_priv(net); strscpy(info->driver, dev->driver_name, sizeof(info->driver)); strscpy(info->fw_version, dev->driver_info->description, sizeof(info->fw_version)); - usb_make_path (dev->udev, info->bus_info, sizeof info->bus_info); + usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } EXPORT_SYMBOL_GPL(usbnet_get_drvinfo); -u32 usbnet_get_msglevel (struct net_device *net) +u32 usbnet_get_msglevel(struct net_device *net) { struct usbnet *dev = netdev_priv(net); @@ -1095,7 +1103,7 @@ u32 usbnet_get_msglevel (struct net_device *net) } EXPORT_SYMBOL_GPL(usbnet_get_msglevel); -void usbnet_set_msglevel (struct net_device *net, u32 level) +void usbnet_set_msglevel(struct net_device *net, u32 level) { struct usbnet *dev = netdev_priv(net); @@ -1166,71 +1174,71 @@ static void __handle_set_rx_mode(struct usbnet *dev) * especially now that control transfers can be queued. */ static void -usbnet_deferred_kevent (struct work_struct *work) +usbnet_deferred_kevent(struct work_struct *work) { struct usbnet *dev = container_of(work, struct usbnet, kevent); int status; /* usb_clear_halt() needs a thread context */ - if (test_bit (EVENT_TX_HALT, &dev->flags)) { - unlink_urbs (dev, &dev->txq); + if (test_bit(EVENT_TX_HALT, &dev->flags)) { + unlink_urbs(dev, &dev->txq); status = usb_autopm_get_interface(dev->intf); if (status < 0) goto fail_pipe; - status = usb_clear_halt (dev->udev, dev->out); + status = usb_clear_halt(dev->udev, dev->out); usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { - if (netif_msg_tx_err (dev)) + if (netif_msg_tx_err(dev)) fail_pipe: netdev_err(dev->net, "can't clear tx halt, status %d\n", status); } else { - clear_bit (EVENT_TX_HALT, &dev->flags); + clear_bit(EVENT_TX_HALT, &dev->flags); if (status != -ESHUTDOWN) - netif_wake_queue (dev->net); + netif_wake_queue(dev->net); } } - if (test_bit (EVENT_RX_HALT, &dev->flags)) { - unlink_urbs (dev, &dev->rxq); + if (test_bit(EVENT_RX_HALT, &dev->flags)) { + unlink_urbs(dev, &dev->rxq); status = usb_autopm_get_interface(dev->intf); if (status < 0) goto fail_halt; - status = usb_clear_halt (dev->udev, dev->in); + status = usb_clear_halt(dev->udev, dev->in); usb_autopm_put_interface(dev->intf); if (status < 0 && status != -EPIPE && status != -ESHUTDOWN) { - if (netif_msg_rx_err (dev)) + if (netif_msg_rx_err(dev)) fail_halt: netdev_err(dev->net, "can't clear rx halt, status %d\n", status); } else { - clear_bit (EVENT_RX_HALT, &dev->flags); + clear_bit(EVENT_RX_HALT, &dev->flags); if (!usbnet_going_away(dev)) queue_work(system_bh_wq, &dev->bh_work); } } /* work could resubmit itself forever if memory is tight */ - if (test_bit (EVENT_RX_MEMORY, &dev->flags)) { + if (test_bit(EVENT_RX_MEMORY, &dev->flags)) { struct urb *urb = NULL; int resched = 1; - if (netif_running (dev->net)) - urb = usb_alloc_urb (0, GFP_KERNEL); + if (netif_running(dev->net)) + urb = usb_alloc_urb(0, GFP_KERNEL); else - clear_bit (EVENT_RX_MEMORY, &dev->flags); + clear_bit(EVENT_RX_MEMORY, &dev->flags); if (urb != NULL) { - clear_bit (EVENT_RX_MEMORY, &dev->flags); + clear_bit(EVENT_RX_MEMORY, &dev->flags); status = usb_autopm_get_interface(dev->intf); if (status < 0) { usb_free_urb(urb); goto fail_lowmem; } - if (rx_submit (dev, urb, GFP_KERNEL) == -ENOLINK) + if (rx_submit(dev, urb, GFP_KERNEL) == -ENOLINK) resched = 0; usb_autopm_put_interface(dev->intf); fail_lowmem: @@ -1244,7 +1252,7 @@ usbnet_deferred_kevent (struct work_struct *work) const struct driver_info *info = dev->driver_info; int retval = 0; - clear_bit (EVENT_LINK_RESET, &dev->flags); + clear_bit(EVENT_LINK_RESET, &dev->flags); status = usb_autopm_get_interface(dev->intf); if (status < 0) goto skip_reset; @@ -1264,10 +1272,10 @@ usbnet_deferred_kevent (struct work_struct *work) __handle_link_change(dev); } - if (test_bit (EVENT_LINK_CHANGE, &dev->flags)) + if (test_bit(EVENT_LINK_CHANGE, &dev->flags)) __handle_link_change(dev); - if (test_bit (EVENT_SET_RX_MODE, &dev->flags)) + if (test_bit(EVENT_SET_RX_MODE, &dev->flags)) __handle_set_rx_mode(dev); @@ -1277,7 +1285,7 @@ usbnet_deferred_kevent (struct work_struct *work) /*-------------------------------------------------------------------------*/ -static void tx_complete (struct urb *urb) +static void tx_complete(struct urb *urb) { struct sk_buff *skb = (struct sk_buff *) urb->context; struct skb_data *entry = (struct skb_data *) skb->cb; @@ -1296,7 +1304,7 @@ static void tx_complete (struct urb *urb) switch (urb->status) { case -EPIPE: - usbnet_defer_kevent (dev, EVENT_TX_HALT); + usbnet_defer_kevent(dev, EVENT_TX_HALT); break; /* software-driven interface shutdown */ @@ -1311,13 +1319,13 @@ static void tx_complete (struct urb *urb) case -ETIME: case -EILSEQ: usb_mark_last_busy(dev->udev); - if (!timer_pending (&dev->delay)) { - mod_timer (&dev->delay, - jiffies + THROTTLE_JIFFIES); + if (!timer_pending(&dev->delay)) { + mod_timer(&dev->delay, + jiffies + THROTTLE_JIFFIES); netif_dbg(dev, link, dev->net, "tx throttle %d\n", urb->status); } - netif_stop_queue (dev->net); + netif_stop_queue(dev->net); break; default: netif_dbg(dev, tx_err, dev->net, @@ -1332,11 +1340,11 @@ static void tx_complete (struct urb *urb) /*-------------------------------------------------------------------------*/ -void usbnet_tx_timeout (struct net_device *net, unsigned int txqueue) +void usbnet_tx_timeout(struct net_device *net, unsigned int txqueue) { struct usbnet *dev = netdev_priv(net); - unlink_urbs (dev, &dev->txq); + unlink_urbs(dev, &dev->txq); queue_work(system_bh_wq, &dev->bh_work); /* this needs to be handled individually because the generic layer * doesn't know what is sufficient and could not restore private @@ -1382,8 +1390,7 @@ static int build_dma_sg(const struct sk_buff *skb, struct urb *urb) return 1; } -netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, - struct net_device *net) +netdev_tx_t usbnet_start_xmit(struct sk_buff *skb, struct net_device *net) { struct usbnet *dev = netdev_priv(net); unsigned int length; @@ -1399,7 +1406,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, // some devices want funky USB-level framing, for // win32 driver (usually) and/or hardware quirks if (info->tx_fixup) { - skb = info->tx_fixup (dev, skb, GFP_ATOMIC); + skb = info->tx_fixup(dev, skb, GFP_ATOMIC); if (!skb) { /* packet collected; minidriver waiting for more */ if (info->flags & FLAG_MULTI_PACKET) @@ -1409,7 +1416,8 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, } } - if (!(urb = usb_alloc_urb (0, GFP_ATOMIC))) { + urb = usb_alloc_urb(0, GFP_ATOMIC); + if (!urb) { netif_dbg(dev, tx_err, dev->net, "no urb\n"); goto drop; } @@ -1418,8 +1426,8 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, entry->urb = urb; entry->dev = dev; - usb_fill_bulk_urb (urb, dev->udev, dev->out, - skb->data, skb->len, tx_complete, skb); + usb_fill_bulk_urb(urb, dev->udev, dev->out, + skb->data, skb->len, tx_complete, skb); if (dev->can_dma_sg) { if (build_dma_sg(skb, urb) < 0) goto drop; @@ -1489,8 +1497,8 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, switch ((retval = usb_submit_urb (urb, GFP_ATOMIC))) { case -EPIPE: - netif_stop_queue (net); - usbnet_defer_kevent (dev, EVENT_TX_HALT); + netif_stop_queue(net); + usbnet_defer_kevent(dev, EVENT_TX_HALT); usb_autopm_put_interface_async(dev->intf); break; default: @@ -1501,10 +1509,11 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, case 0: netif_trans_update(net); __usbnet_queue_skb(&dev->txq, skb, tx_start); + netdev_sent_queue(net, skb->len); if (dev->txq.qlen >= TX_QLEN (dev)) netif_stop_queue (net); } - spin_unlock_irqrestore (&dev->txq.lock, flags); + spin_unlock_irqrestore(&dev->txq.lock, flags); if (retval) { netif_dbg(dev, tx_err, dev->net, "drop, code %d\n", retval); @@ -1512,7 +1521,7 @@ netdev_tx_t usbnet_start_xmit (struct sk_buff *skb, dev->net->stats.tx_dropped++; not_drop: if (skb) - dev_kfree_skb_any (skb); + dev_kfree_skb_any(skb); if (urb) { kfree(urb->sg); usb_free_urb(urb); @@ -1561,9 +1570,10 @@ static inline void usb_free_skb(struct sk_buff *skb) // work (work deferred from completions, in_irq) or timer -static void usbnet_bh (struct timer_list *t) +static void usbnet_bh(struct timer_list *t) { struct usbnet *dev = timer_container_of(dev, t, delay); + unsigned int bytes_compl = 0, pkts_compl = 0; struct sk_buff *skb; struct skb_data *entry; @@ -1575,6 +1585,8 @@ static void usbnet_bh (struct timer_list *t) usb_free_skb(skb); continue; case tx_done: + bytes_compl += skb->len; + pkts_compl++; kfree(entry->urb->sg); fallthrough; case rx_cleanup: @@ -1585,6 +1597,10 @@ static void usbnet_bh (struct timer_list *t) } } + spin_lock_bh(&dev->bql_spinlock); + netdev_completed_queue(dev->net, pkts_compl, bytes_compl); + spin_unlock_bh(&dev->bql_spinlock); + /* restart RX again after disabling due to high error rate */ clear_bit(EVENT_RX_KILL, &dev->flags); @@ -1616,7 +1632,7 @@ static void usbnet_bh (struct timer_list *t) queue_work(system_bh_wq, &dev->bh_work); } if (dev->txq.qlen < TX_QLEN (dev)) - netif_wake_queue (dev->net); + netif_wake_queue(dev->net); } } @@ -1636,7 +1652,7 @@ static void usbnet_bh_work(struct work_struct *work) // precondition: never called in_interrupt -void usbnet_disconnect (struct usb_interface *intf) +void usbnet_disconnect(struct usb_interface *intf) { struct usbnet *dev; struct usb_device *xdev; @@ -1649,7 +1665,7 @@ void usbnet_disconnect (struct usb_interface *intf) return; usbnet_mark_going_away(dev); - xdev = interface_to_usbdev (intf); + xdev = interface_to_usbdev(intf); netif_info(dev, probe, dev->net, "unregister '%s' usb-%s-%s, %s\n", intf->dev.driver->name, @@ -1657,7 +1673,7 @@ void usbnet_disconnect (struct usb_interface *intf) dev->driver_info->description); net = dev->net; - unregister_netdev (net); + unregister_netdev(net); cancel_work_sync(&dev->kevent); @@ -1702,7 +1718,7 @@ static const struct device_type wwan_type = { }; int -usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) +usbnet_probe(struct usb_interface *udev, const struct usb_device_id *prod) { struct usbnet *dev; struct net_device *net; @@ -1728,7 +1744,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) dev_dbg (&udev->dev, "blacklisted by %s\n", name); return -ENODEV; } - xdev = interface_to_usbdev (udev); + xdev = interface_to_usbdev(udev); interface = udev->cur_altsetting; status = -ENOMEM; @@ -1756,11 +1772,12 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) skb_queue_head_init (&dev->txq); skb_queue_head_init (&dev->done); skb_queue_head_init(&dev->rxq_pause); + spin_lock_init(&dev->bql_spinlock); INIT_WORK(&dev->bh_work, usbnet_bh_work); - INIT_WORK (&dev->kevent, usbnet_deferred_kevent); + INIT_WORK(&dev->kevent, usbnet_deferred_kevent); init_usb_anchor(&dev->deferred); timer_setup(&dev->delay, usbnet_bh, 0); - mutex_init (&dev->phy_mutex); + mutex_init(&dev->phy_mutex); mutex_init(&dev->interrupt_mutex); dev->interrupt_count = 0; @@ -1782,7 +1799,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) // allow device-specific bind/init procedures // NOTE net->name still not usable ... if (info->bind) { - status = info->bind (dev, udev); + status = info->bind(dev, udev); if (status < 0) goto out1; @@ -1807,18 +1824,18 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if (net->mtu > (dev->hard_mtu - net->hard_header_len)) net->mtu = dev->hard_mtu - net->hard_header_len; } else if (!info->in || !info->out) - status = usbnet_get_endpoints (dev, udev); + status = usbnet_get_endpoints(dev, udev); else { u8 ep_addrs[3] = { info->in + USB_DIR_IN, info->out + USB_DIR_OUT, 0 }; - dev->in = usb_rcvbulkpipe (xdev, info->in); - dev->out = usb_sndbulkpipe (xdev, info->out); + dev->in = usb_rcvbulkpipe(xdev, info->in); + dev->out = usb_sndbulkpipe(xdev, info->out); if (!(info->flags & FLAG_NO_SETINT)) - status = usb_set_interface (xdev, - interface->desc.bInterfaceNumber, - interface->desc.bAlternateSetting); + status = usb_set_interface(xdev, + interface->desc.bInterfaceNumber, + interface->desc.bAlternateSetting); else status = 0; @@ -1826,7 +1843,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) status = -EINVAL; } if (status >= 0 && dev->status) - status = init_status (dev, udev); + status = init_status(dev, udev); if (status < 0) goto out3; @@ -1860,7 +1877,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) } } - status = register_netdev (net); + status = register_netdev(net); if (status) goto out5; netif_info(dev, probe, dev->net, @@ -1871,9 +1888,9 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) net->dev_addr); // ok, it's ready to go. - usb_set_intfdata (udev, dev); + usb_set_intfdata(udev, dev); - netif_device_attach (net); + netif_device_attach(net); if (dev->driver_info->flags & FLAG_LINK_INTR) usbnet_link_change(dev, 0, 0); @@ -1886,7 +1903,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) usb_free_urb(dev->interrupt); out3: if (info->unbind) - info->unbind (dev, udev); + info->unbind(dev, udev); out1: /* subdrivers must undo all they did in bind() if they * fail it, but we may fail later and a deferred kevent @@ -1909,7 +1926,7 @@ EXPORT_SYMBOL_GPL(usbnet_probe); * resume only when the last interface is resumed */ -int usbnet_suspend (struct usb_interface *intf, pm_message_t message) +int usbnet_suspend(struct usb_interface *intf, pm_message_t message) { struct usbnet *dev = usb_get_intfdata(intf); @@ -1928,7 +1945,7 @@ int usbnet_suspend (struct usb_interface *intf, pm_message_t message) * accelerate emptying of the rx and queues, to avoid * having everything error out. */ - netif_device_detach (dev->net); + netif_device_detach(dev->net); usbnet_terminate_urbs(dev); __usbnet_status_stop_force(dev); @@ -1936,13 +1953,13 @@ int usbnet_suspend (struct usb_interface *intf, pm_message_t message) * reattach so runtime management can use and * wake the device */ - netif_device_attach (dev->net); + netif_device_attach(dev->net); } return 0; } EXPORT_SYMBOL_GPL(usbnet_suspend); -int usbnet_resume (struct usb_interface *intf) +int usbnet_resume(struct usb_interface *intf) { struct usbnet *dev = usb_get_intfdata(intf); struct sk_buff *skb; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index a3046142cb8e2..056f7f79f13d6 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -392,14 +392,12 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev) } /* Restore Eth hdr pulled by dev_forward_skb/eth_type_trans */ __skb_push(skb, ETH_HLEN); - /* Depend on prior success packets started NAPI consumer via - * __veth_xdp_flush(). Cancel TXQ stop if consumer stopped, - * paired with empty check in veth_poll(). - */ netif_tx_stop_queue(txq); - smp_mb__after_atomic(); - if (unlikely(__ptr_ring_empty(&rq->xdp_ring))) - netif_tx_wake_queue(txq); + /* Makes sure NAPI peer consumer runs. Consumer is responsible + * for starting txq again, until then ndo_start_xmit (this + * function) will not be invoked by the netstack again. + */ + __veth_xdp_flush(rq); break; case NET_RX_DROP: /* same as NET_XMIT_DROP */ drop: @@ -900,17 +898,9 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, struct veth_xdp_tx_bq *bq, struct veth_stats *stats) { - struct veth_priv *priv = netdev_priv(rq->dev); - int queue_idx = rq->xdp_rxq.queue_index; - struct netdev_queue *peer_txq; - struct net_device *peer_dev; int i, done = 0, n_xdpf = 0; void *xdpf[VETH_XDP_BATCH]; - /* NAPI functions as RCU section */ - peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); - peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; - for (i = 0; i < budget; i++) { void *ptr = __ptr_ring_consume(&rq->xdp_ring); @@ -959,9 +949,6 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, rq->stats.vs.xdp_packets += done; u64_stats_update_end(&rq->stats.syncp); - if (peer_txq && unlikely(netif_tx_queue_stopped(peer_txq))) - netif_tx_wake_queue(peer_txq); - return done; } @@ -969,12 +956,20 @@ static int veth_poll(struct napi_struct *napi, int budget) { struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); + struct veth_priv *priv = netdev_priv(rq->dev); + int queue_idx = rq->xdp_rxq.queue_index; + struct netdev_queue *peer_txq; struct veth_stats stats = {}; + struct net_device *peer_dev; struct veth_xdp_tx_bq bq; int done; bq.count = 0; + /* NAPI functions as RCU section */ + peer_dev = rcu_dereference_check(priv->peer, rcu_read_lock_bh_held()); + peer_txq = peer_dev ? netdev_get_tx_queue(peer_dev, queue_idx) : NULL; + xdp_set_return_frame_no_direct(); done = veth_xdp_rcv(rq, budget, &bq, &stats); @@ -996,6 +991,13 @@ static int veth_poll(struct napi_struct *napi, int budget) veth_xdp_flush(rq, &bq); xdp_clear_return_frame_no_direct(); + /* Release backpressure per NAPI poll */ + smp_rmb(); /* Paired with netif_tx_stop_queue set_bit */ + if (peer_txq && netif_tx_queue_stopped(peer_txq)) { + txq_trans_cond_update(peer_txq); + netif_tx_wake_queue(peer_txq); + } + return done; } @@ -1323,7 +1325,7 @@ static int veth_set_channels(struct net_device *dev, if (peer) netif_carrier_off(peer); - /* try to allocate new resurces, as needed*/ + /* try to allocate new resources, as needed*/ err = veth_enable_range_safe(dev, old_rx_count, new_rx_count); if (err) goto out; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 0369dda5ed606..71fa68b9364fe 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -26,6 +26,9 @@ #include #include #include +#include +#include +#include static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); @@ -281,6 +284,36 @@ static const struct virtnet_stat_desc virtnet_stats_tx_speed_desc_qstat[] = { VIRTNET_STATS_DESC_TX_QSTAT(speed, ratelimit_packets, hw_drop_ratelimits), }; +struct virtnet_ethtool_ff { + struct xarray rules; + int num_rules; +}; + +#define VIRTNET_FF_ETHTOOL_GROUP_PRIORITY 1 +#define VIRTNET_FF_MAX_GROUPS 1 + +struct virtnet_ff { + struct virtio_device *vdev; + bool ff_supported; + struct virtio_net_ff_cap_data *ff_caps; + struct virtio_net_ff_cap_mask_data *ff_mask; + struct virtio_net_ff_actions *ff_actions; + struct xarray classifiers; + struct virtnet_ethtool_ff ethtool; +}; + +static int virtnet_ethtool_flow_insert(struct virtnet_ff *ff, + struct ethtool_rx_flow_spec *fs, + u16 curr_queue_pairs); +static int virtnet_ethtool_flow_remove(struct virtnet_ff *ff, int location); +static int virtnet_ethtool_get_flow_count(struct virtnet_ff *ff, + struct ethtool_rxnfc *info); +static int virtnet_ethtool_get_flow(struct virtnet_ff *ff, + struct ethtool_rxnfc *info); +static int +virtnet_ethtool_get_all_flows(struct virtnet_ff *ff, + struct ethtool_rxnfc *info, u32 *rule_locs); + #define VIRTNET_Q_TYPE_RX 0 #define VIRTNET_Q_TYPE_TX 1 #define VIRTNET_Q_TYPE_CQ 2 @@ -493,6 +526,8 @@ struct virtnet_info { struct failover *failover; u64 device_stats_cap; + + struct virtnet_ff ff; }; struct padded_vnet_hdr { @@ -3776,7 +3811,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs) * (2) no user configuration. * * During rss command processing, device updates queue_pairs using rss.max_tx_vq. That is, - * the device updates queue_pairs together with rss, so we can skip the sperate queue_pairs + * the device updates queue_pairs together with rss, so we can skip the separate queue_pairs * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly. */ if (vi->has_rss && !netif_is_rxfh_configured(dev)) { @@ -5637,6 +5672,43 @@ static u32 virtnet_get_rx_ring_count(struct net_device *dev) return vi->curr_queue_pairs; } +static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) +{ + struct virtnet_info *vi = netdev_priv(dev); + int rc = 0; + + switch (info->cmd) { + case ETHTOOL_GRXCLSRLCNT: + rc = virtnet_ethtool_get_flow_count(&vi->ff, info); + break; + case ETHTOOL_GRXCLSRULE: + rc = virtnet_ethtool_get_flow(&vi->ff, info); + break; + case ETHTOOL_GRXCLSRLALL: + rc = virtnet_ethtool_get_all_flows(&vi->ff, info, rule_locs); + break; + default: + rc = -EOPNOTSUPP; + } + + return rc; +} + +static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) +{ + struct virtnet_info *vi = netdev_priv(dev); + + switch (info->cmd) { + case ETHTOOL_SRXCLSRLINS: + return virtnet_ethtool_flow_insert(&vi->ff, &info->fs, + vi->curr_queue_pairs); + case ETHTOOL_SRXCLSRLDEL: + return virtnet_ethtool_flow_remove(&vi->ff, info->fs.location); + } + + return -EOPNOTSUPP; +} + static const struct ethtool_ops virtnet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, @@ -5663,6 +5735,8 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .get_rxfh_fields = virtnet_get_hashflow, .set_rxfh_fields = virtnet_set_hashflow, .get_rx_ring_count = virtnet_get_rx_ring_count, + .get_rxnfc = virtnet_get_rxnfc, + .set_rxnfc = virtnet_set_rxnfc, }; static void virtnet_get_queue_stats_rx(struct net_device *dev, int i, @@ -6774,6 +6848,1068 @@ static const struct xdp_metadata_ops virtnet_xdp_metadata_ops = { .xmo_rx_hash = virtnet_xdp_rx_hash, }; +struct virtnet_ethtool_rule { + struct ethtool_rx_flow_spec flow_spec; + u32 classifier_id; +}; + +/* The classifier struct must be the last field in this struct */ +struct virtnet_classifier { + size_t size; + refcount_t refcount; + u32 id; + struct virtio_net_resource_obj_ff_classifier classifier; +}; + +static_assert(sizeof(struct virtnet_classifier) == + ALIGN(offsetofend(struct virtnet_classifier, classifier), + __alignof__(struct virtnet_classifier)), + "virtnet_classifier: classifier must be the last member"); + +static bool check_mask_vs_cap(const void *m, const void *c, + u16 len, bool partial) +{ + const u8 *mask = m; + const u8 *cap = c; + int i; + + for (i = 0; i < len; i++) { + if (partial && ((mask[i] & cap[i]) != mask[i])) + return false; + if (!partial && mask[i] != cap[i]) + return false; + } + + return true; +} + +static +struct virtio_net_ff_selector *get_selector_cap(const struct virtnet_ff *ff, + u8 selector_type) +{ + struct virtio_net_ff_selector *sel; + void *buf; + int i; + + buf = &ff->ff_mask->selectors; + sel = buf; + + for (i = 0; i < ff->ff_mask->count; i++) { + if (sel->type == selector_type) + return sel; + + buf += sizeof(struct virtio_net_ff_selector) + sel->length; + sel = buf; + } + + return NULL; +} + +static bool validate_eth_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct ethhdr *cap, *mask; + struct ethhdr zeros = {}; + + cap = (struct ethhdr *)&sel_cap->mask; + mask = (struct ethhdr *)&sel->mask; + + if (memcmp(&zeros.h_dest, mask->h_dest, sizeof(zeros.h_dest)) && + !check_mask_vs_cap(mask->h_dest, cap->h_dest, + sizeof(mask->h_dest), partial_mask)) + return false; + + if (memcmp(&zeros.h_source, mask->h_source, sizeof(zeros.h_source)) && + !check_mask_vs_cap(mask->h_source, cap->h_source, + sizeof(mask->h_source), partial_mask)) + return false; + + if (mask->h_proto && + !check_mask_vs_cap(&mask->h_proto, &cap->h_proto, + sizeof(__be16), partial_mask)) + return false; + + return true; +} + +static bool validate_ip4_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct iphdr *cap, *mask; + + cap = (struct iphdr *)&sel_cap->mask; + mask = (struct iphdr *)&sel->mask; + + if (mask->saddr && + !check_mask_vs_cap(&mask->saddr, &cap->saddr, + sizeof(__be32), partial_mask)) + return false; + + if (mask->daddr && + !check_mask_vs_cap(&mask->daddr, &cap->daddr, + sizeof(__be32), partial_mask)) + return false; + + if (mask->protocol && + !check_mask_vs_cap(&mask->protocol, &cap->protocol, + sizeof(u8), partial_mask)) + return false; + + return true; +} + +static bool validate_ip6_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct ipv6hdr *cap, *mask; + + cap = (struct ipv6hdr *)&sel_cap->mask; + mask = (struct ipv6hdr *)&sel->mask; + + if (!ipv6_addr_any(&mask->saddr) && + !check_mask_vs_cap(&mask->saddr, &cap->saddr, + sizeof(cap->saddr), partial_mask)) + return false; + + if (!ipv6_addr_any(&mask->daddr) && + !check_mask_vs_cap(&mask->daddr, &cap->daddr, + sizeof(cap->daddr), partial_mask)) + return false; + + if (mask->nexthdr && + !check_mask_vs_cap(&mask->nexthdr, &cap->nexthdr, + sizeof(cap->nexthdr), partial_mask)) + return false; + + return true; +} + +static bool validate_tcp_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct tcphdr *cap, *mask; + + cap = (struct tcphdr *)&sel_cap->mask; + mask = (struct tcphdr *)&sel->mask; + + if (mask->source && + !check_mask_vs_cap(&mask->source, &cap->source, + sizeof(cap->source), partial_mask)) + return false; + + if (mask->dest && + !check_mask_vs_cap(&mask->dest, &cap->dest, + sizeof(cap->dest), partial_mask)) + return false; + + return true; +} + +static bool validate_udp_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct udphdr *cap, *mask; + + cap = (struct udphdr *)&sel_cap->mask; + mask = (struct udphdr *)&sel->mask; + + if (mask->source && + !check_mask_vs_cap(&mask->source, &cap->source, + sizeof(cap->source), partial_mask)) + return false; + + if (mask->dest && + !check_mask_vs_cap(&mask->dest, &cap->dest, + sizeof(cap->dest), partial_mask)) + return false; + + return true; +} + +static bool validate_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel) +{ + struct virtio_net_ff_selector *sel_cap = get_selector_cap(ff, sel->type); + + if (!sel_cap) + return false; + + switch (sel->type) { + case VIRTIO_NET_FF_MASK_TYPE_ETH: + return validate_eth_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_IPV4: + return validate_ip4_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_IPV6: + return validate_ip6_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_TCP: + return validate_tcp_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_UDP: + return validate_udp_mask(ff, sel, sel_cap); + } + + return false; +} + +static void set_tcp(struct tcphdr *mask, struct tcphdr *key, + __be16 psrc_m, __be16 psrc_k, + __be16 pdst_m, __be16 pdst_k) +{ + if (psrc_m) { + mask->source = psrc_m; + key->source = psrc_k; + } + if (pdst_m) { + mask->dest = pdst_m; + key->dest = pdst_k; + } +} + +static void set_udp(struct udphdr *mask, struct udphdr *key, + __be16 psrc_m, __be16 psrc_k, + __be16 pdst_m, __be16 pdst_k) +{ + if (psrc_m) { + mask->source = psrc_m; + key->source = psrc_k; + } + if (pdst_m) { + mask->dest = pdst_m; + key->dest = pdst_k; + } +} + +static void parse_ip4(struct iphdr *mask, struct iphdr *key, + const struct ethtool_rx_flow_spec *fs) +{ + const struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec; + const struct ethtool_usrip4_spec *l3_val = &fs->h_u.usr_ip4_spec; + + mask->saddr = l3_mask->ip4src; + mask->daddr = l3_mask->ip4dst; + key->saddr = l3_val->ip4src; + key->daddr = l3_val->ip4dst; + + if (l3_mask->proto) { + mask->protocol = l3_mask->proto; + key->protocol = l3_val->proto; + } +} + +static void parse_ip6(struct ipv6hdr *mask, struct ipv6hdr *key, + const struct ethtool_rx_flow_spec *fs) +{ + const struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec; + const struct ethtool_usrip6_spec *l3_val = &fs->h_u.usr_ip6_spec; + + if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6src)) { + memcpy(&mask->saddr, l3_mask->ip6src, sizeof(mask->saddr)); + memcpy(&key->saddr, l3_val->ip6src, sizeof(key->saddr)); + } + + if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6dst)) { + memcpy(&mask->daddr, l3_mask->ip6dst, sizeof(mask->daddr)); + memcpy(&key->daddr, l3_val->ip6dst, sizeof(key->daddr)); + } + + if (l3_mask->l4_proto) { + mask->nexthdr = l3_mask->l4_proto; + key->nexthdr = l3_val->l4_proto; + } +} + +static bool has_ipv4(u32 flow_type) +{ + return flow_type == TCP_V4_FLOW || + flow_type == UDP_V4_FLOW || + flow_type == IP_USER_FLOW; +} + +static bool has_ipv6(u32 flow_type) +{ + return flow_type == TCP_V6_FLOW || + flow_type == UDP_V6_FLOW || + flow_type == IPV6_USER_FLOW; +} + +static bool has_tcp(u32 flow_type) +{ + return flow_type == TCP_V4_FLOW || flow_type == TCP_V6_FLOW; +} + +static bool has_udp(u32 flow_type) +{ + return flow_type == UDP_V4_FLOW || flow_type == UDP_V6_FLOW; +} + +static int setup_classifier(struct virtnet_ff *ff, + struct virtnet_classifier **c) +{ + struct virtnet_classifier *tmp; + unsigned long i; + int err; + + xa_for_each(&ff->classifiers, i, tmp) { + if ((*c)->size == tmp->size && + !memcmp(&tmp->classifier, &(*c)->classifier, tmp->size)) { + refcount_inc(&tmp->refcount); + kfree(*c); + *c = tmp; + goto out; + } + } + + err = xa_alloc(&ff->classifiers, &(*c)->id, *c, + XA_LIMIT(0, le32_to_cpu(ff->ff_caps->classifiers_limit) - 1), + GFP_KERNEL); + if (err) + return err; + + err = virtio_admin_obj_create(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER, + (*c)->id, + VIRTIO_ADMIN_GROUP_TYPE_SELF, + 0, + &(*c)->classifier, + (*c)->size); + if (err) + goto err_xarray; + + refcount_set(&(*c)->refcount, 1); +out: + return 0; + +err_xarray: + xa_erase(&ff->classifiers, (*c)->id); + + return err; +} + +static void try_destroy_classifier(struct virtnet_ff *ff, u32 classifier_id) +{ + struct virtnet_classifier *c; + + c = xa_load(&ff->classifiers, classifier_id); + if (c && refcount_dec_and_test(&c->refcount)) { + virtio_admin_obj_destroy(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER, + c->id, + VIRTIO_ADMIN_GROUP_TYPE_SELF, + 0); + + xa_erase(&ff->classifiers, c->id); + kfree(c); + } +} + +static void destroy_ethtool_rule(struct virtnet_ff *ff, + struct virtnet_ethtool_rule *eth_rule) +{ + ff->ethtool.num_rules--; + + virtio_admin_obj_destroy(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_RULE, + eth_rule->flow_spec.location, + VIRTIO_ADMIN_GROUP_TYPE_SELF, + 0); + + xa_erase(&ff->ethtool.rules, eth_rule->flow_spec.location); + try_destroy_classifier(ff, eth_rule->classifier_id); + kfree(eth_rule); +} + +static int insert_rule(struct virtnet_ff *ff, + struct virtnet_ethtool_rule *eth_rule, + u32 classifier_id, + const u8 *key, + size_t key_size) +{ + struct ethtool_rx_flow_spec *fs = ð_rule->flow_spec; + struct virtio_net_resource_obj_ff_rule *ff_rule; + int err; + + ff_rule = kzalloc(sizeof(*ff_rule) + key_size, GFP_KERNEL); + if (!ff_rule) + return -ENOMEM; + + /* Intentionally leave the priority as 0. All rules have the same + * priority. + */ + ff_rule->group_id = cpu_to_le32(VIRTNET_FF_ETHTOOL_GROUP_PRIORITY); + ff_rule->classifier_id = cpu_to_le32(classifier_id); + ff_rule->key_length = (u8)key_size; + ff_rule->action = fs->ring_cookie == RX_CLS_FLOW_DISC ? + VIRTIO_NET_FF_ACTION_DROP : + VIRTIO_NET_FF_ACTION_RX_VQ; + ff_rule->vq_index = fs->ring_cookie != RX_CLS_FLOW_DISC ? + cpu_to_le16(fs->ring_cookie) : 0; + memcpy(&ff_rule->keys, key, key_size); + + err = virtio_admin_obj_create(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_RULE, + fs->location, + VIRTIO_ADMIN_GROUP_TYPE_SELF, + 0, + ff_rule, + sizeof(*ff_rule) + key_size); + if (err) + goto err_ff_rule; + + eth_rule->classifier_id = classifier_id; + ff->ethtool.num_rules++; + kfree(ff_rule); + + return 0; + +err_ff_rule: + kfree(ff_rule); + + return err; +} + +static u32 flow_type_mask(u32 flow_type) +{ + return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); +} + +static bool supported_flow_type(const struct ethtool_rx_flow_spec *fs) +{ + switch (fs->flow_type) { + case ETHER_FLOW: + case IP_USER_FLOW: + case IPV6_USER_FLOW: + case TCP_V4_FLOW: + case TCP_V6_FLOW: + case UDP_V4_FLOW: + case UDP_V6_FLOW: + return true; + } + + return false; +} + +static int validate_flow_input(struct virtnet_ff *ff, + const struct ethtool_rx_flow_spec *fs, + u16 curr_queue_pairs) +{ + /* Force users to use RX_CLS_LOC_ANY - don't allow specific locations */ + if (fs->location != RX_CLS_LOC_ANY) + return -EOPNOTSUPP; + + if (fs->ring_cookie != RX_CLS_FLOW_DISC && + fs->ring_cookie >= curr_queue_pairs) + return -EINVAL; + + if (fs->flow_type != flow_type_mask(fs->flow_type)) + return -EOPNOTSUPP; + + if (!supported_flow_type(fs)) + return -EOPNOTSUPP; + + return 0; +} + +static void calculate_flow_sizes(struct ethtool_rx_flow_spec *fs, + size_t *key_size, size_t *classifier_size, + int *num_hdrs) +{ + size_t size = sizeof(struct ethhdr); + + *num_hdrs = 1; + *key_size = sizeof(struct ethhdr); + + if (fs->flow_type == ETHER_FLOW) + goto done; + + ++(*num_hdrs); + if (has_ipv4(fs->flow_type)) + size += sizeof(struct iphdr); + else if (has_ipv6(fs->flow_type)) + size += sizeof(struct ipv6hdr); + + if (has_tcp(fs->flow_type) || has_udp(fs->flow_type)) { + ++(*num_hdrs); + size += has_tcp(fs->flow_type) ? sizeof(struct tcphdr) : + sizeof(struct udphdr); + } +done: + *key_size = size; + /* + * The classifier size is the size of the classifier header, a selector + * header for each type of header in the match criteria, and each header + * providing the mask for matching against. + */ + *classifier_size = *key_size + + sizeof(struct virtio_net_resource_obj_ff_classifier) + + sizeof(struct virtio_net_ff_selector) * (*num_hdrs); +} + +static void setup_eth_hdr_key_mask(struct virtio_net_ff_selector *selector, + u8 *key, + const struct ethtool_rx_flow_spec *fs, + int num_hdrs) +{ + struct ethhdr *eth_m = (struct ethhdr *)&selector->mask; + struct ethhdr *eth_k = (struct ethhdr *)key; + + selector->type = VIRTIO_NET_FF_MASK_TYPE_ETH; + selector->length = sizeof(struct ethhdr); + + if (num_hdrs > 1) { + eth_m->h_proto = cpu_to_be16(0xffff); + eth_k->h_proto = cpu_to_be16(ETH_P_IP); + } else { + memcpy(eth_m, &fs->m_u.ether_spec, sizeof(*eth_m)); + memcpy(eth_k, &fs->h_u.ether_spec, sizeof(*eth_k)); + } +} + +static int setup_ip_key_mask(struct virtio_net_ff_selector *selector, + u8 *key, + const struct ethtool_rx_flow_spec *fs, + int num_hdrs) +{ + struct ipv6hdr *v6_m = (struct ipv6hdr *)&selector->mask; + struct iphdr *v4_m = (struct iphdr *)&selector->mask; + struct ipv6hdr *v6_k = (struct ipv6hdr *)key; + struct iphdr *v4_k = (struct iphdr *)key; + + if (has_ipv6(fs->flow_type)) { + selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV6; + selector->length = sizeof(struct ipv6hdr); + + if (num_hdrs == 2 && (fs->h_u.usr_ip6_spec.l4_4_bytes || + fs->h_u.usr_ip6_spec.tclass)) + return -EOPNOTSUPP; + + parse_ip6(v6_m, v6_k, fs); + + if (num_hdrs > 2) { + v6_m->nexthdr = 0xff; + if (has_tcp(fs->flow_type)) + v6_k->nexthdr = IPPROTO_TCP; + else + v6_k->nexthdr = IPPROTO_UDP; + } + } else { + selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV4; + selector->length = sizeof(struct iphdr); + + if (num_hdrs == 2 && + (fs->h_u.usr_ip4_spec.l4_4_bytes || + fs->h_u.usr_ip4_spec.tos || + fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)) + return -EOPNOTSUPP; + + parse_ip4(v4_m, v4_k, fs); + + if (num_hdrs > 2) { + v4_m->protocol = 0xff; + if (has_tcp(fs->flow_type)) + v4_k->protocol = IPPROTO_TCP; + else + v4_k->protocol = IPPROTO_UDP; + } + } + + return 0; +} + +static int setup_transport_key_mask(struct virtio_net_ff_selector *selector, + u8 *key, + struct ethtool_rx_flow_spec *fs) +{ + struct tcphdr *tcp_m = (struct tcphdr *)&selector->mask; + struct udphdr *udp_m = (struct udphdr *)&selector->mask; + const struct ethtool_tcpip6_spec *v6_l4_mask; + const struct ethtool_tcpip4_spec *v4_l4_mask; + const struct ethtool_tcpip6_spec *v6_l4_key; + const struct ethtool_tcpip4_spec *v4_l4_key; + struct tcphdr *tcp_k = (struct tcphdr *)key; + struct udphdr *udp_k = (struct udphdr *)key; + + if (has_tcp(fs->flow_type)) { + selector->type = VIRTIO_NET_FF_MASK_TYPE_TCP; + selector->length = sizeof(struct tcphdr); + + if (has_ipv6(fs->flow_type)) { + v6_l4_mask = &fs->m_u.tcp_ip6_spec; + v6_l4_key = &fs->h_u.tcp_ip6_spec; + + set_tcp(tcp_m, tcp_k, v6_l4_mask->psrc, v6_l4_key->psrc, + v6_l4_mask->pdst, v6_l4_key->pdst); + } else { + v4_l4_mask = &fs->m_u.tcp_ip4_spec; + v4_l4_key = &fs->h_u.tcp_ip4_spec; + + set_tcp(tcp_m, tcp_k, v4_l4_mask->psrc, v4_l4_key->psrc, + v4_l4_mask->pdst, v4_l4_key->pdst); + } + + } else if (has_udp(fs->flow_type)) { + selector->type = VIRTIO_NET_FF_MASK_TYPE_UDP; + selector->length = sizeof(struct udphdr); + + if (has_ipv6(fs->flow_type)) { + v6_l4_mask = &fs->m_u.udp_ip6_spec; + v6_l4_key = &fs->h_u.udp_ip6_spec; + + set_udp(udp_m, udp_k, v6_l4_mask->psrc, v6_l4_key->psrc, + v6_l4_mask->pdst, v6_l4_key->pdst); + } else { + v4_l4_mask = &fs->m_u.udp_ip4_spec; + v4_l4_key = &fs->h_u.udp_ip4_spec; + + set_udp(udp_m, udp_k, v4_l4_mask->psrc, v4_l4_key->psrc, + v4_l4_mask->pdst, v4_l4_key->pdst); + } + } else { + return -EOPNOTSUPP; + } + + return 0; +} + +static int +validate_classifier_selectors(struct virtnet_ff *ff, + struct virtio_net_resource_obj_ff_classifier *classifier, + int num_hdrs) +{ + struct virtio_net_ff_selector *selector = (void *)classifier->selectors; + int i; + + for (i = 0; i < num_hdrs; i++) { + if (!validate_mask(ff, selector)) + return -EINVAL; + + selector = (((void *)selector) + sizeof(*selector) + + selector->length); + } + + return 0; +} + +static +struct virtio_net_ff_selector *next_selector(struct virtio_net_ff_selector *sel) +{ + return (void *)sel + sizeof(struct virtio_net_ff_selector) + + sel->length; +} + +static int build_and_insert(struct virtnet_ff *ff, + struct virtnet_ethtool_rule *eth_rule) +{ + struct virtio_net_resource_obj_ff_classifier *classifier; + struct ethtool_rx_flow_spec *fs = ð_rule->flow_spec; + struct virtio_net_ff_selector *selector; + struct virtnet_classifier *c; + size_t classifier_size; + size_t key_offset; + size_t key_size; + int num_hdrs; + u8 *key; + int err; + + calculate_flow_sizes(fs, &key_size, &classifier_size, &num_hdrs); + + key = kzalloc(key_size, GFP_KERNEL); + if (!key) + return -ENOMEM; + + /* + * virtio_net_ff_obj_ff_classifier is already included in the + * classifier_size. + */ + c = kzalloc(classifier_size + + sizeof(struct virtnet_classifier) - + sizeof(struct virtio_net_resource_obj_ff_classifier), + GFP_KERNEL); + if (!c) { + kfree(key); + return -ENOMEM; + } + + c->size = classifier_size; + classifier = &c->classifier; + classifier->count = num_hdrs; + selector = (void *)&classifier->selectors[0]; + + setup_eth_hdr_key_mask(selector, key, fs, num_hdrs); + if (num_hdrs == 1) + goto validate; + + key_offset = selector->length; + selector = next_selector(selector); + + err = setup_ip_key_mask(selector, key + key_offset, fs, num_hdrs); + if (err) + goto err_classifier; + + if (num_hdrs == 2) + goto validate; + + key_offset += selector->length; + selector = next_selector(selector); + + err = setup_transport_key_mask(selector, key + key_offset, fs); + if (err) + goto err_classifier; + +validate: + err = validate_classifier_selectors(ff, classifier, num_hdrs); + if (err) + goto err_key; + + err = setup_classifier(ff, &c); + if (err) + goto err_classifier; + + err = insert_rule(ff, eth_rule, c->id, key, key_size); + if (err) { + /* destroy_classifier will free the classifier */ + try_destroy_classifier(ff, c->id); + goto err_key; + } + + return 0; + +err_classifier: + kfree(c); +err_key: + kfree(key); + + return err; +} + +static int virtnet_ethtool_flow_insert(struct virtnet_ff *ff, + struct ethtool_rx_flow_spec *fs, + u16 curr_queue_pairs) +{ + struct virtnet_ethtool_rule *eth_rule; + int err; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + err = validate_flow_input(ff, fs, curr_queue_pairs); + if (err) + return err; + + eth_rule = kzalloc(sizeof(*eth_rule), GFP_KERNEL); + if (!eth_rule) + return -ENOMEM; + + err = xa_alloc(&ff->ethtool.rules, &fs->location, eth_rule, + XA_LIMIT(0, le32_to_cpu(ff->ff_caps->rules_limit) - 1), + GFP_KERNEL); + if (err) + goto err_rule; + + eth_rule->flow_spec = *fs; + + err = build_and_insert(ff, eth_rule); + if (err) + goto err_xa; + + return err; + +err_xa: + xa_erase(&ff->ethtool.rules, eth_rule->flow_spec.location); + +err_rule: + fs->location = RX_CLS_LOC_ANY; + kfree(eth_rule); + + return err; +} + +static int virtnet_ethtool_flow_remove(struct virtnet_ff *ff, int location) +{ + struct virtnet_ethtool_rule *eth_rule; + int err = 0; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + eth_rule = xa_load(&ff->ethtool.rules, location); + if (!eth_rule) { + err = -ENOENT; + goto out; + } + + destroy_ethtool_rule(ff, eth_rule); +out: + return err; +} + +static int virtnet_ethtool_get_flow_count(struct virtnet_ff *ff, + struct ethtool_rxnfc *info) +{ + if (!ff->ff_supported) + return -EOPNOTSUPP; + + info->rule_cnt = ff->ethtool.num_rules; + info->data = le32_to_cpu(ff->ff_caps->rules_limit) | RX_CLS_LOC_SPECIAL; + + return 0; +} + +static int virtnet_ethtool_get_flow(struct virtnet_ff *ff, + struct ethtool_rxnfc *info) +{ + struct virtnet_ethtool_rule *eth_rule; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + eth_rule = xa_load(&ff->ethtool.rules, info->fs.location); + if (!eth_rule) + return -ENOENT; + + info->fs = eth_rule->flow_spec; + + return 0; +} + +static int +virtnet_ethtool_get_all_flows(struct virtnet_ff *ff, + struct ethtool_rxnfc *info, u32 *rule_locs) +{ + struct virtnet_ethtool_rule *eth_rule; + unsigned long i = 0; + int idx = 0; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + xa_for_each(&ff->ethtool.rules, i, eth_rule) + rule_locs[idx++] = i; + + info->data = le32_to_cpu(ff->ff_caps->rules_limit); + + return 0; +} + +static size_t get_mask_size(u16 type) +{ + switch (type) { + case VIRTIO_NET_FF_MASK_TYPE_ETH: + return sizeof(struct ethhdr); + case VIRTIO_NET_FF_MASK_TYPE_IPV4: + return sizeof(struct iphdr); + case VIRTIO_NET_FF_MASK_TYPE_IPV6: + return sizeof(struct ipv6hdr); + case VIRTIO_NET_FF_MASK_TYPE_TCP: + return sizeof(struct tcphdr); + case VIRTIO_NET_FF_MASK_TYPE_UDP: + return sizeof(struct udphdr); + } + + return 0; +} + +#define MAX_SEL_LEN (sizeof(struct ipv6hdr)) + +static int virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) +{ + size_t ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data) + + sizeof(struct virtio_net_ff_selector) * + VIRTIO_NET_FF_MASK_TYPE_MAX; + struct virtio_net_resource_obj_ff_group ethtool_group = {}; + struct virtio_admin_cmd_query_cap_id_result *cap_id_list; + struct virtio_net_ff_selector *sel; + size_t real_ff_mask_size; + int err; + int i; + + if (!vdev->config->admin_cmd_exec) + return -EOPNOTSUPP; + + cap_id_list = kzalloc(sizeof(*cap_id_list), GFP_KERNEL); + if (!cap_id_list) + return -ENOMEM; + + err = virtio_admin_cap_id_list_query(vdev, cap_id_list); + if (err) + goto err_cap_list; + + if (!(VIRTIO_CAP_IN_LIST(cap_id_list, + VIRTIO_NET_FF_RESOURCE_CAP) && + VIRTIO_CAP_IN_LIST(cap_id_list, + VIRTIO_NET_FF_SELECTOR_CAP) && + VIRTIO_CAP_IN_LIST(cap_id_list, + VIRTIO_NET_FF_ACTION_CAP))) { + err = -EOPNOTSUPP; + goto err_cap_list; + } + + ff->ff_caps = kzalloc(sizeof(*ff->ff_caps), GFP_KERNEL); + if (!ff->ff_caps) { + err = -ENOMEM; + goto err_cap_list; + } + + err = virtio_admin_cap_get(vdev, + VIRTIO_NET_FF_RESOURCE_CAP, + ff->ff_caps, + sizeof(*ff->ff_caps)); + + if (err) + goto err_ff; + + /* VIRTIO_NET_FF_MASK_TYPE start at 1 */ + for (i = 1; i <= VIRTIO_NET_FF_MASK_TYPE_MAX; i++) + ff_mask_size += get_mask_size(i); + + ff->ff_mask = kzalloc(ff_mask_size, GFP_KERNEL); + if (!ff->ff_mask) { + err = -ENOMEM; + goto err_ff; + } + + err = virtio_admin_cap_get(vdev, + VIRTIO_NET_FF_SELECTOR_CAP, + ff->ff_mask, + ff_mask_size); + + if (err) + goto err_ff_mask; + + ff->ff_actions = kzalloc(sizeof(*ff->ff_actions) + + VIRTIO_NET_FF_ACTION_MAX, + GFP_KERNEL); + if (!ff->ff_actions) { + err = -ENOMEM; + goto err_ff_mask; + } + + err = virtio_admin_cap_get(vdev, + VIRTIO_NET_FF_ACTION_CAP, + ff->ff_actions, + sizeof(*ff->ff_actions) + VIRTIO_NET_FF_ACTION_MAX); + + if (err) + goto err_ff_action; + + if (le32_to_cpu(ff->ff_caps->groups_limit) < VIRTNET_FF_MAX_GROUPS) { + err = -ENOSPC; + goto err_ff_action; + } + ff->ff_caps->groups_limit = cpu_to_le32(VIRTNET_FF_MAX_GROUPS); + + err = virtio_admin_cap_set(vdev, + VIRTIO_NET_FF_RESOURCE_CAP, + ff->ff_caps, + sizeof(*ff->ff_caps)); + if (err) + goto err_ff_action; + + real_ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data); + sel = (void *)&ff->ff_mask->selectors[0]; + + for (i = 0; i < ff->ff_mask->count; i++) { + if (sel->length > MAX_SEL_LEN) { + err = -EINVAL; + goto err_ff_action; + } + real_ff_mask_size += sizeof(struct virtio_net_ff_selector) + sel->length; + sel = (void *)sel + sizeof(*sel) + sel->length; + } + + if (real_ff_mask_size > ff_mask_size) { + err = -EINVAL; + goto err_ff_action; + } + + err = virtio_admin_cap_set(vdev, + VIRTIO_NET_FF_SELECTOR_CAP, + ff->ff_mask, + real_ff_mask_size); + if (err) + goto err_ff_action; + + err = virtio_admin_cap_set(vdev, + VIRTIO_NET_FF_ACTION_CAP, + ff->ff_actions, + sizeof(*ff->ff_actions) + VIRTIO_NET_FF_ACTION_MAX); + if (err) + goto err_ff_action; + + ethtool_group.group_priority = cpu_to_le16(VIRTNET_FF_ETHTOOL_GROUP_PRIORITY); + + /* Use priority for the object ID. */ + err = virtio_admin_obj_create(vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_GROUP, + VIRTNET_FF_ETHTOOL_GROUP_PRIORITY, + VIRTIO_ADMIN_GROUP_TYPE_SELF, + 0, + ðtool_group, + sizeof(ethtool_group)); + if (err) + goto err_ff_action; + + xa_init_flags(&ff->classifiers, XA_FLAGS_ALLOC); + xa_init_flags(&ff->ethtool.rules, XA_FLAGS_ALLOC); + ff->vdev = vdev; + ff->ff_supported = true; + + kfree(cap_id_list); + + return 0; + +err_ff_action: + kfree(ff->ff_actions); + ff->ff_actions = NULL; +err_ff_mask: + kfree(ff->ff_mask); + ff->ff_mask = NULL; +err_ff: + kfree(ff->ff_caps); + ff->ff_caps = NULL; +err_cap_list: + kfree(cap_id_list); + + return err; +} + +static void virtnet_ff_cleanup(struct virtnet_ff *ff) +{ + struct virtnet_ethtool_rule *eth_rule; + unsigned long i; + + if (!ff->ff_supported) + return; + + xa_for_each(&ff->ethtool.rules, i, eth_rule) + destroy_ethtool_rule(ff, eth_rule); + + xa_destroy(&ff->ethtool.rules); + xa_destroy(&ff->classifiers); + + virtio_admin_obj_destroy(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_GROUP, + VIRTNET_FF_ETHTOOL_GROUP_PRIORITY, + VIRTIO_ADMIN_GROUP_TYPE_SELF, + 0); + + kfree(ff->ff_actions); + kfree(ff->ff_mask); + kfree(ff->ff_caps); +} + static int virtnet_probe(struct virtio_device *vdev) { int i, err = -ENOMEM; @@ -7137,6 +8273,15 @@ static int virtnet_probe(struct virtio_device *vdev) } vi->guest_offloads_capable = vi->guest_offloads; + /* Initialize flow filters. Not supported is an acceptable and common + * return code + */ + err = virtnet_ff_init(&vi->ff, vi->vdev); + if (err && err != -EOPNOTSUPP) { + rtnl_unlock(); + goto free_unregister_netdev; + } + rtnl_unlock(); err = virtnet_cpu_notif_add(vi); @@ -7152,6 +8297,7 @@ static int virtnet_probe(struct virtio_device *vdev) free_unregister_netdev: unregister_netdev(dev); + virtnet_ff_cleanup(&vi->ff); free_failover: net_failover_destroy(vi->failover); free_vqs: @@ -7201,6 +8347,7 @@ static void virtnet_remove(struct virtio_device *vdev) virtnet_free_irq_moder(vi); unregister_netdev(vi->dev); + virtnet_ff_cleanup(&vi->ff); net_failover_destroy(vi->failover); diff --git a/drivers/net/vxlan/vxlan_private.h b/drivers/net/vxlan/vxlan_private.h index 99fe772ad6791..b1eec22163608 100644 --- a/drivers/net/vxlan/vxlan_private.h +++ b/drivers/net/vxlan/vxlan_private.h @@ -188,8 +188,6 @@ int __vxlan_fdb_delete(struct vxlan_dev *vxlan, const unsigned char *addr, union vxlan_addr ip, __be16 port, __be32 src_vni, __be32 vni, u32 ifindex, bool swdev_notify); -u32 eth_vni_hash(const unsigned char *addr, __be32 vni); -u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni); int vxlan_fdb_update(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __u16 flags, diff --git a/drivers/net/wan/hdlc_ppp.c b/drivers/net/wan/hdlc_ppp.c index 7496a2e9a2820..159295c4bd6d8 100644 --- a/drivers/net/wan/hdlc_ppp.c +++ b/drivers/net/wan/hdlc_ppp.c @@ -126,14 +126,12 @@ static inline struct proto *get_proto(struct net_device *dev, u16 pid) static inline const char *proto_name(u16 pid) { switch (pid) { - case PID_LCP: - return "LCP"; case PID_IPCP: return "IPCP"; case PID_IPV6CP: return "IPV6CP"; default: - return NULL; + return "LCP"; } } diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c index 6f78f1752cd6f..7c2939cbde5f0 100644 --- a/drivers/net/wireless/ath/ath10k/core.c +++ b/drivers/net/wireless/ath/ath10k/core.c @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1187,7 +1186,7 @@ static int ath10k_download_fw(struct ath10k *ar) u32 address, data_len; const void *data; int ret; - struct pm_qos_request latency_qos; + struct pm_qos_request latency_qos = {}; address = ar->hw_params.patch_load_addr; @@ -1221,7 +1220,6 @@ static int ath10k_download_fw(struct ath10k *ar) ret); } - memset(&latency_qos, 0, sizeof(latency_qos)); cpu_latency_qos_add_request(&latency_qos, 0); ret = ath10k_bmi_fast_download(ar, address, data, data_len); @@ -2493,8 +2491,9 @@ static int ath10k_init_hw_params(struct ath10k *ar) return 0; } -static bool ath10k_core_needs_recovery(struct ath10k *ar) +static void ath10k_core_recovery_check_work(struct work_struct *work) { + struct ath10k *ar = container_of(work, struct ath10k, recovery_check_work); long time_left; /* Sometimes the recovery will fail and then the next all recovery fail, @@ -2504,7 +2503,7 @@ static bool ath10k_core_needs_recovery(struct ath10k *ar) ath10k_err(ar, "consecutive fail %d times, will shutdown driver!", atomic_read(&ar->fail_cont_count)); ar->state = ATH10K_STATE_WEDGED; - return false; + return; } ath10k_dbg(ar, ATH10K_DBG_BOOT, "total recovery count: %d", ++ar->recovery_count); @@ -2518,27 +2517,24 @@ static bool ath10k_core_needs_recovery(struct ath10k *ar) ATH10K_RECOVERY_TIMEOUT_HZ); if (time_left) { ath10k_warn(ar, "previous recovery succeeded, skip this!\n"); - return false; + return; } /* Record the continuous recovery fail count when recovery failed. */ atomic_inc(&ar->fail_cont_count); /* Avoid having multiple recoveries at the same time. */ - return false; + return; } atomic_inc(&ar->pending_recovery); - - return true; + queue_work(ar->workqueue, &ar->restart_work); } void ath10k_core_start_recovery(struct ath10k *ar) { - if (!ath10k_core_needs_recovery(ar)) - return; - - queue_work(ar->workqueue, &ar->restart_work); + /* Use workqueue_aux to avoid blocking recovery tracking */ + queue_work(ar->workqueue_aux, &ar->recovery_check_work); } EXPORT_SYMBOL(ath10k_core_start_recovery); @@ -3356,7 +3352,7 @@ EXPORT_SYMBOL(ath10k_core_stop); */ static int ath10k_core_probe_fw(struct ath10k *ar) { - struct bmi_target_info target_info; + struct bmi_target_info target_info = {}; int ret = 0; ret = ath10k_hif_power_up(ar, ATH10K_FIRMWARE_MODE_NORMAL); @@ -3367,7 +3363,6 @@ static int ath10k_core_probe_fw(struct ath10k *ar) switch (ar->hif.bus) { case ATH10K_BUS_SDIO: - memset(&target_info, 0, sizeof(target_info)); ret = ath10k_bmi_get_target_info_sdio(ar, &target_info); if (ret) { ath10k_err(ar, "could not get target info (%d)\n", ret); @@ -3379,7 +3374,6 @@ static int ath10k_core_probe_fw(struct ath10k *ar) case ATH10K_BUS_PCI: case ATH10K_BUS_AHB: case ATH10K_BUS_USB: - memset(&target_info, 0, sizeof(target_info)); ret = ath10k_bmi_get_target_info(ar, &target_info); if (ret) { ath10k_err(ar, "could not get target info (%d)\n", ret); @@ -3389,7 +3383,6 @@ static int ath10k_core_probe_fw(struct ath10k *ar) ar->hw->wiphy->hw_version = target_info.version; break; case ATH10K_BUS_SNOC: - memset(&target_info, 0, sizeof(target_info)); ret = ath10k_hif_get_target_info(ar, &target_info); if (ret) { ath10k_err(ar, "could not get target info (%d)\n", ret); @@ -3734,6 +3727,7 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev, INIT_WORK(&ar->register_work, ath10k_core_register_work); INIT_WORK(&ar->restart_work, ath10k_core_restart); + INIT_WORK(&ar->recovery_check_work, ath10k_core_recovery_check_work); INIT_WORK(&ar->set_coverage_class_work, ath10k_core_set_coverage_class_work); diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h index 8c72ed386edb7..73a9db302245d 100644 --- a/drivers/net/wireless/ath/ath10k/core.h +++ b/drivers/net/wireless/ath/ath10k/core.h @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1208,6 +1207,7 @@ struct ath10k { struct work_struct register_work; struct work_struct restart_work; + struct work_struct recovery_check_work; struct work_struct bundle_tx_work; struct work_struct tx_complete_work; @@ -1259,9 +1259,13 @@ struct ath10k { struct { /* protected by conf_mutex */ struct ath10k_fw_components utf_mode_fw; + u8 ftm_msgref; /* protected by data_lock */ bool utf_monitor; + u32 data_pos; + u32 expected_seq; + u8 *eventdata; } testmode; struct { diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c index 154ac7a709824..da6f7957a0ae7 100644 --- a/drivers/net/wireless/ath/ath10k/mac.c +++ b/drivers/net/wireless/ath/ath10k/mac.c @@ -3,7 +3,6 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -5428,6 +5427,7 @@ static void ath10k_stop(struct ieee80211_hw *hw, bool suspend) cancel_work_sync(&ar->set_coverage_class_work); cancel_delayed_work_sync(&ar->scan.timeout); cancel_work_sync(&ar->restart_work); + cancel_work_sync(&ar->recovery_check_work); } static int ath10k_config_ps(struct ath10k *ar) diff --git a/drivers/net/wireless/ath/ath10k/qmi.c b/drivers/net/wireless/ath/ath10k/qmi.c index f1f33af0170a0..8275345631a0b 100644 --- a/drivers/net/wireless/ath/ath10k/qmi.c +++ b/drivers/net/wireless/ath/ath10k/qmi.c @@ -986,7 +986,7 @@ static int ath10k_qmi_new_server(struct qmi_handle *qmi_hdl, ath10k_dbg(ar, ATH10K_DBG_QMI, "wifi fw qmi service found\n"); - ret = kernel_connect(qmi_hdl->sock, (struct sockaddr *)&qmi->sq, + ret = kernel_connect(qmi_hdl->sock, (struct sockaddr_unsized *)&qmi->sq, sizeof(qmi->sq), 0); if (ret) { ath10k_err(ar, "failed to connect to a remote QMI service port\n"); diff --git a/drivers/net/wireless/ath/ath10k/testmode.c b/drivers/net/wireless/ath/ath10k/testmode.c index 3fcefc55b74f2..d3bd385694d6e 100644 --- a/drivers/net/wireless/ath/ath10k/testmode.c +++ b/drivers/net/wireless/ath/ath10k/testmode.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: ISC /* * Copyright (c) 2014-2017 Qualcomm Atheros, Inc. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include "testmode.h" @@ -10,12 +11,17 @@ #include "debug.h" #include "wmi.h" +#include "wmi-tlv.h" #include "hif.h" #include "hw.h" #include "core.h" #include "testmode_i.h" +#define ATH10K_FTM_SEG_NONE ((u32)-1) +#define ATH10K_FTM_SEGHDR_CURRENT_SEQ GENMASK(3, 0) +#define ATH10K_FTM_SEGHDR_TOTAL_SEGMENTS GENMASK(7, 4) + static const struct nla_policy ath10k_tm_policy[ATH10K_TM_ATTR_MAX + 1] = { [ATH10K_TM_ATTR_CMD] = { .type = NLA_U32 }, [ATH10K_TM_ATTR_DATA] = { .type = NLA_BINARY, @@ -25,41 +31,19 @@ static const struct nla_policy ath10k_tm_policy[ATH10K_TM_ATTR_MAX + 1] = { [ATH10K_TM_ATTR_VERSION_MINOR] = { .type = NLA_U32 }, }; -/* Returns true if callee consumes the skb and the skb should be discarded. - * Returns false if skb is not used. Does not sleep. - */ -bool ath10k_tm_event_wmi(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb) +static void ath10k_tm_event_unsegmented(struct ath10k *ar, u32 cmd_id, + struct sk_buff *skb) { struct sk_buff *nl_skb; - bool consumed; int ret; - ath10k_dbg(ar, ATH10K_DBG_TESTMODE, - "testmode event wmi cmd_id %d skb %p skb->len %d\n", - cmd_id, skb, skb->len); - - ath10k_dbg_dump(ar, ATH10K_DBG_TESTMODE, NULL, "", skb->data, skb->len); - - spin_lock_bh(&ar->data_lock); - - if (!ar->testmode.utf_monitor) { - consumed = false; - goto out; - } - - /* Only testmode.c should be handling events from utf firmware, - * otherwise all sort of problems will arise as mac80211 operations - * are not initialised. - */ - consumed = true; - nl_skb = cfg80211_testmode_alloc_event_skb(ar->hw->wiphy, 2 * sizeof(u32) + skb->len, GFP_ATOMIC); if (!nl_skb) { ath10k_warn(ar, "failed to allocate skb for testmode wmi event\n"); - goto out; + return; } ret = nla_put_u32(nl_skb, ATH10K_TM_ATTR_CMD, ATH10K_TM_CMD_WMI); @@ -68,7 +52,7 @@ bool ath10k_tm_event_wmi(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb) "failed to put testmode wmi event cmd attribute: %d\n", ret); kfree_skb(nl_skb); - goto out; + return; } ret = nla_put_u32(nl_skb, ATH10K_TM_ATTR_WMI_CMDID, cmd_id); @@ -77,7 +61,7 @@ bool ath10k_tm_event_wmi(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb) "failed to put testmode wmi event cmd_id: %d\n", ret); kfree_skb(nl_skb); - goto out; + return; } ret = nla_put(nl_skb, ATH10K_TM_ATTR_DATA, skb->len, skb->data); @@ -86,10 +70,122 @@ bool ath10k_tm_event_wmi(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb) "failed to copy skb to testmode wmi event: %d\n", ret); kfree_skb(nl_skb); - goto out; + return; + } + + cfg80211_testmode_event(nl_skb, GFP_ATOMIC); +} + +static void ath10k_tm_event_segmented(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb) +{ + struct wmi_ftm_cmd *ftm = (struct wmi_ftm_cmd *)skb->data; + u8 total_segments, current_seq; + struct sk_buff *nl_skb; + u8 const *buf_pos; + u16 datalen; + u32 data_pos; + int ret; + + if (skb->len < sizeof(*ftm)) { + ath10k_warn(ar, "Invalid ftm event length: %d\n", skb->len); + return; + } + + current_seq = FIELD_GET(ATH10K_FTM_SEGHDR_CURRENT_SEQ, + __le32_to_cpu(ftm->seg_hdr.segmentinfo)); + total_segments = FIELD_GET(ATH10K_FTM_SEGHDR_TOTAL_SEGMENTS, + __le32_to_cpu(ftm->seg_hdr.segmentinfo)); + datalen = skb->len - sizeof(*ftm); + buf_pos = ftm->data; + + if (current_seq == 0) { + ar->testmode.expected_seq = 0; + ar->testmode.data_pos = 0; + } + + data_pos = ar->testmode.data_pos; + + if ((data_pos + datalen) > ATH_FTM_EVENT_MAX_BUF_LENGTH) { + ath10k_warn(ar, "Invalid ftm event length at %u: %u\n", + data_pos, datalen); + ret = -EINVAL; + return; + } + + memcpy(&ar->testmode.eventdata[data_pos], buf_pos, datalen); + data_pos += datalen; + + if (++ar->testmode.expected_seq != total_segments) { + ar->testmode.data_pos = data_pos; + ath10k_dbg(ar, ATH10K_DBG_TESTMODE, "partial data received %u/%u\n", + current_seq + 1, total_segments); + return; + } + + ath10k_dbg(ar, ATH10K_DBG_TESTMODE, "total data length %u\n", data_pos); + + nl_skb = cfg80211_testmode_alloc_event_skb(ar->hw->wiphy, + 2 * sizeof(u32) + data_pos, + GFP_ATOMIC); + if (!nl_skb) { + ath10k_warn(ar, "failed to allocate skb for testmode wmi event\n"); + return; + } + + ret = nla_put_u32(nl_skb, ATH10K_TM_ATTR_CMD, ATH10K_TM_CMD_TLV); + if (ret) { + ath10k_warn(ar, "failed to put testmode wmi event attribute: %d\n", ret); + kfree_skb(nl_skb); + return; + } + + ret = nla_put_u32(nl_skb, ATH10K_TM_ATTR_WMI_CMDID, cmd_id); + if (ret) { + ath10k_warn(ar, "failed to put testmode wmi event cmd_id: %d\n", ret); + kfree_skb(nl_skb); + return; + } + + ret = nla_put(nl_skb, ATH10K_TM_ATTR_DATA, data_pos, &ar->testmode.eventdata[0]); + if (ret) { + ath10k_warn(ar, "failed to copy skb to testmode wmi event: %d\n", ret); + kfree_skb(nl_skb); + return; } cfg80211_testmode_event(nl_skb, GFP_ATOMIC); +} + +/* Returns true if callee consumes the skb and the skb should be discarded. + * Returns false if skb is not used. Does not sleep. + */ +bool ath10k_tm_event_wmi(struct ath10k *ar, u32 cmd_id, struct sk_buff *skb) +{ + bool consumed; + + ath10k_dbg(ar, ATH10K_DBG_TESTMODE, + "testmode event wmi cmd_id %d skb %p skb->len %d\n", + cmd_id, skb, skb->len); + + ath10k_dbg_dump(ar, ATH10K_DBG_TESTMODE, NULL, "", skb->data, skb->len); + + spin_lock_bh(&ar->data_lock); + + if (!ar->testmode.utf_monitor) { + consumed = false; + goto out; + } + + /* Only testmode.c should be handling events from utf firmware, + * otherwise all sort of problems will arise as mac80211 operations + * are not initialised. + */ + consumed = true; + + if (ar->testmode.expected_seq != ATH10K_FTM_SEG_NONE) + ath10k_tm_event_segmented(ar, cmd_id, skb); + else + ath10k_tm_event_unsegmented(ar, cmd_id, skb); out: spin_unlock_bh(&ar->data_lock); @@ -281,12 +377,18 @@ static int ath10k_tm_cmd_utf_start(struct ath10k *ar, struct nlattr *tb[]) goto err_release_utf_mode_fw; } + ar->testmode.eventdata = kzalloc(ATH_FTM_EVENT_MAX_BUF_LENGTH, GFP_KERNEL); + if (!ar->testmode.eventdata) { + ret = -ENOMEM; + goto err_power_down; + } + ret = ath10k_core_start(ar, ATH10K_FIRMWARE_MODE_UTF, &ar->testmode.utf_mode_fw); if (ret) { ath10k_err(ar, "failed to start core (testmode): %d\n", ret); ar->state = ATH10K_STATE_OFF; - goto err_power_down; + goto err_release_eventdata; } ar->state = ATH10K_STATE_UTF; @@ -302,6 +404,10 @@ static int ath10k_tm_cmd_utf_start(struct ath10k *ar, struct nlattr *tb[]) return 0; +err_release_eventdata: + kfree(ar->testmode.eventdata); + ar->testmode.eventdata = NULL; + err_power_down: ath10k_hif_power_down(ar); @@ -341,6 +447,9 @@ static void __ath10k_tm_cmd_utf_stop(struct ath10k *ar) release_firmware(ar->testmode.utf_mode_fw.fw_file.firmware); ar->testmode.utf_mode_fw.fw_file.firmware = NULL; + kfree(ar->testmode.eventdata); + ar->testmode.eventdata = NULL; + ar->state = ATH10K_STATE_OFF; } @@ -424,6 +533,85 @@ static int ath10k_tm_cmd_wmi(struct ath10k *ar, struct nlattr *tb[]) return ret; } +static int ath10k_tm_cmd_tlv(struct ath10k *ar, struct nlattr *tb[]) +{ + u16 total_bytes, num_segments; + u32 cmd_id, buf_len; + u8 segnumber = 0; + u8 *bufpos; + void *buf; + int ret; + + mutex_lock(&ar->conf_mutex); + + if (ar->state != ATH10K_STATE_UTF) { + ret = -ENETDOWN; + goto out; + } + + buf = nla_data(tb[ATH10K_TM_ATTR_DATA]); + buf_len = nla_len(tb[ATH10K_TM_ATTR_DATA]); + cmd_id = WMI_PDEV_UTF_CMDID; + + ath10k_dbg(ar, ATH10K_DBG_TESTMODE, + "cmd wmi ftm cmd_id %d buffer length %d\n", + cmd_id, buf_len); + ath10k_dbg_dump(ar, ATH10K_DBG_TESTMODE, NULL, "", buf, buf_len); + + bufpos = buf; + total_bytes = buf_len; + num_segments = total_bytes / MAX_WMI_UTF_LEN; + ar->testmode.expected_seq = 0; + + if (buf_len - (num_segments * MAX_WMI_UTF_LEN)) + num_segments++; + + while (buf_len) { + u16 chunk_len = min_t(u16, buf_len, MAX_WMI_UTF_LEN); + struct wmi_ftm_cmd *ftm_cmd; + struct sk_buff *skb; + u32 hdr_info; + u8 seginfo; + + skb = ath10k_wmi_alloc_skb(ar, (chunk_len + + sizeof(struct wmi_ftm_cmd))); + if (!skb) { + ret = -ENOMEM; + goto out; + } + + ftm_cmd = (struct wmi_ftm_cmd *)skb->data; + hdr_info = FIELD_PREP(WMI_TLV_TAG, WMI_TLV_TAG_ARRAY_BYTE) | + FIELD_PREP(WMI_TLV_LEN, (chunk_len + + sizeof(struct wmi_ftm_seg_hdr))); + ftm_cmd->tlv_header = __cpu_to_le32(hdr_info); + ftm_cmd->seg_hdr.len = __cpu_to_le32(total_bytes); + ftm_cmd->seg_hdr.msgref = __cpu_to_le32(ar->testmode.ftm_msgref); + seginfo = FIELD_PREP(ATH10K_FTM_SEGHDR_TOTAL_SEGMENTS, num_segments) | + FIELD_PREP(ATH10K_FTM_SEGHDR_CURRENT_SEQ, segnumber); + ftm_cmd->seg_hdr.segmentinfo = __cpu_to_le32(seginfo); + segnumber++; + + memcpy(&ftm_cmd->data, bufpos, chunk_len); + + ret = ath10k_wmi_cmd_send(ar, skb, cmd_id); + if (ret) { + ath10k_warn(ar, "failed to send wmi ftm command: %d\n", ret); + goto out; + } + + buf_len -= chunk_len; + bufpos += chunk_len; + } + + ar->testmode.ftm_msgref++; + ret = 0; + +out: + mutex_unlock(&ar->conf_mutex); + return ret; +} + int ath10k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif, void *data, int len) { @@ -439,9 +627,14 @@ int ath10k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif, if (!tb[ATH10K_TM_ATTR_CMD]) return -EINVAL; + ar->testmode.expected_seq = ATH10K_FTM_SEG_NONE; + switch (nla_get_u32(tb[ATH10K_TM_ATTR_CMD])) { case ATH10K_TM_CMD_GET_VERSION: - return ath10k_tm_cmd_get_version(ar, tb); + if (!tb[ATH10K_TM_ATTR_DATA]) + return ath10k_tm_cmd_get_version(ar, tb); + else /* ATH10K_TM_CMD_TLV */ + return ath10k_tm_cmd_tlv(ar, tb); case ATH10K_TM_CMD_UTF_START: return ath10k_tm_cmd_utf_start(ar, tb); case ATH10K_TM_CMD_UTF_STOP: diff --git a/drivers/net/wireless/ath/ath10k/testmode_i.h b/drivers/net/wireless/ath/ath10k/testmode_i.h index ee1cb27c1d600..1603f52766825 100644 --- a/drivers/net/wireless/ath/ath10k/testmode_i.h +++ b/drivers/net/wireless/ath/ath10k/testmode_i.h @@ -1,6 +1,7 @@ /* SPDX-License-Identifier: ISC */ /* * Copyright (c) 2014,2017 Qualcomm Atheros, Inc. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ /* "API" level of the ath10k testmode interface. Bump it after every @@ -14,6 +15,7 @@ #define ATH10K_TESTMODE_VERSION_MINOR 0 #define ATH10K_TM_DATA_MAX_LEN 5000 +#define ATH_FTM_EVENT_MAX_BUF_LENGTH 2048 enum ath10k_tm_attr { __ATH10K_TM_ATTR_INVALID = 0, @@ -57,4 +59,17 @@ enum ath10k_tm_cmd { * ATH10K_TM_ATTR_DATA. */ ATH10K_TM_CMD_WMI = 3, + + /* The command used to transmit a test command to the firmware + * and the event to receive test events from the firmware. The data + * received only contain the TLV payload, need to add the tlv header + * and send the cmd to firmware with command id WMI_PDEV_UTF_CMDID. + * The data payload size could be large and the driver needs to + * send segmented data to firmware. + * + * This legacy testmode command shares the same value as the get-version + * command. To distinguish between them, we check whether the data attribute + * is present. + */ + ATH10K_TM_CMD_TLV = ATH10K_TM_CMD_GET_VERSION, }; diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h index 0faefc0a9a405..7f50a1de6b978 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.h +++ b/drivers/net/wireless/ath/ath10k/wmi.h @@ -3,7 +3,7 @@ * Copyright (c) 2005-2011 Atheros Communications Inc. * Copyright (c) 2011-2017 Qualcomm Atheros, Inc. * Copyright (c) 2018-2019, The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef _WMI_H_ @@ -7418,6 +7418,23 @@ struct wmi_pdev_bb_timing_cfg_cmd { __le32 bb_xpa_timing; } __packed; +struct wmi_ftm_seg_hdr { + __le32 len; + __le32 msgref; + __le32 segmentinfo; + __le32 pdev_id; +} __packed; + +struct wmi_ftm_cmd { + __le32 tlv_header; + struct wmi_ftm_seg_hdr seg_hdr; + u8 data[]; +} __packed; + +#define WMI_TLV_LEN GENMASK(15, 0) +#define WMI_TLV_TAG GENMASK(31, 16) +#define MAX_WMI_UTF_LEN 252 + struct ath10k; struct ath10k_vif; struct ath10k_fw_stats_pdev; diff --git a/drivers/net/wireless/ath/ath11k/hal.h b/drivers/net/wireless/ath/ath11k/hal.h index 839095af9267e..82603a389bb92 100644 --- a/drivers/net/wireless/ath/ath11k/hal.h +++ b/drivers/net/wireless/ath/ath11k/hal.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef ATH11K_HAL_H @@ -43,14 +43,14 @@ struct ath11k_base; #define HAL_SEQ_WCSS_UMAC_OFFSET 0x00a00000 #define HAL_SEQ_WCSS_UMAC_REO_REG 0x00a38000 #define HAL_SEQ_WCSS_UMAC_TCL_REG 0x00a44000 -#define HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(x) \ - (ab->hw_params.regs->hal_seq_wcss_umac_ce0_src_reg) -#define HAL_SEQ_WCSS_UMAC_CE0_DST_REG(x) \ - (ab->hw_params.regs->hal_seq_wcss_umac_ce0_dst_reg) -#define HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(x) \ - (ab->hw_params.regs->hal_seq_wcss_umac_ce1_src_reg) -#define HAL_SEQ_WCSS_UMAC_CE1_DST_REG(x) \ - (ab->hw_params.regs->hal_seq_wcss_umac_ce1_dst_reg) +#define HAL_SEQ_WCSS_UMAC_CE0_SRC_REG(ab) \ + ((ab)->hw_params.regs->hal_seq_wcss_umac_ce0_src_reg) +#define HAL_SEQ_WCSS_UMAC_CE0_DST_REG(ab) \ + ((ab)->hw_params.regs->hal_seq_wcss_umac_ce0_dst_reg) +#define HAL_SEQ_WCSS_UMAC_CE1_SRC_REG(ab) \ + ((ab)->hw_params.regs->hal_seq_wcss_umac_ce1_src_reg) +#define HAL_SEQ_WCSS_UMAC_CE1_DST_REG(ab) \ + ((ab)->hw_params.regs->hal_seq_wcss_umac_ce1_dst_reg) #define HAL_SEQ_WCSS_UMAC_WBM_REG 0x00a34000 #define HAL_CE_WFSS_CE_REG_BASE 0x01b80000 @@ -209,10 +209,10 @@ struct ath11k_base; #define HAL_REO_STATUS_HP(ab) ab->hw_params.regs->hal_reo_status_hp /* WBM Idle R0 address */ -#define HAL_WBM_IDLE_LINK_RING_BASE_LSB(x) \ - (ab->hw_params.regs->hal_wbm_idle_link_ring_base_lsb) -#define HAL_WBM_IDLE_LINK_RING_MISC_ADDR(x) \ - (ab->hw_params.regs->hal_wbm_idle_link_ring_misc) +#define HAL_WBM_IDLE_LINK_RING_BASE_LSB(ab) \ + ((ab)->hw_params.regs->hal_wbm_idle_link_ring_base_lsb) +#define HAL_WBM_IDLE_LINK_RING_MISC_ADDR(ab) \ + ((ab)->hw_params.regs->hal_wbm_idle_link_ring_misc) #define HAL_WBM_R0_IDLE_LIST_CONTROL_ADDR 0x00000048 #define HAL_WBM_R0_IDLE_LIST_SIZE_ADDR 0x0000004c #define HAL_WBM_SCATTERED_RING_BASE_LSB 0x00000058 @@ -227,17 +227,17 @@ struct ath11k_base; #define HAL_WBM_IDLE_LINK_RING_HP 0x000030b0 /* SW2WBM R0 release address */ -#define HAL_WBM_RELEASE_RING_BASE_LSB(x) \ - (ab->hw_params.regs->hal_wbm_release_ring_base_lsb) +#define HAL_WBM_RELEASE_RING_BASE_LSB(ab) \ + ((ab)->hw_params.regs->hal_wbm_release_ring_base_lsb) /* SW2WBM R2 release address */ #define HAL_WBM_RELEASE_RING_HP 0x00003018 /* WBM2SW R0 release address */ -#define HAL_WBM0_RELEASE_RING_BASE_LSB(x) \ - (ab->hw_params.regs->hal_wbm0_release_ring_base_lsb) -#define HAL_WBM1_RELEASE_RING_BASE_LSB(x) \ - (ab->hw_params.regs->hal_wbm1_release_ring_base_lsb) +#define HAL_WBM0_RELEASE_RING_BASE_LSB(ab) \ + ((ab)->hw_params.regs->hal_wbm0_release_ring_base_lsb) +#define HAL_WBM1_RELEASE_RING_BASE_LSB(ab) \ + ((ab)->hw_params.regs->hal_wbm1_release_ring_base_lsb) /* WBM2SW R2 release address */ #define HAL_WBM0_RELEASE_RING_HP 0x000030c0 diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 0e41b5a91d66d..3276fe443502f 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -2235,9 +2235,9 @@ static void ath11k_peer_assoc_h_vht(struct ath11k *ar, arg->peer_nss = min(sta->deflink.rx_nss, max_nss); arg->rx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.rx_highest); arg->rx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); + arg->rx_mcs_set = ath11k_peer_assoc_h_vht_limit(arg->rx_mcs_set, vht_mcs_mask); arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); - arg->tx_mcs_set = ath11k_peer_assoc_h_vht_limit( - __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map), vht_mcs_mask); + arg->tx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); /* In IPQ8074 platform, VHT mcs rate 10 and 11 is enabled by default. * VHT mcs rate 10 and 11 is not supported in 11ac standard. @@ -2522,10 +2522,10 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, he_tx_mcs = v; } v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); + v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_160); - v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; arg->peer_he_mcs_count++; @@ -2535,10 +2535,10 @@ static void ath11k_peer_assoc_h_he(struct ath11k *ar, default: v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_80); - v = ath11k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; arg->peer_he_mcs_count++; @@ -4028,6 +4028,150 @@ static int ath11k_start_scan(struct ath11k *ar, return 0; } +static void ath11k_mac_fw_stats_reset(struct ath11k *ar) +{ + spin_lock_bh(&ar->data_lock); + ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs); + ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs); + ar->fw_stats.num_vdev_recvd = 0; + ar->fw_stats.num_bcn_recvd = 0; + spin_unlock_bh(&ar->data_lock); +} + +int ath11k_mac_fw_stats_request(struct ath11k *ar, + struct stats_request_params *req_param) +{ + struct ath11k_base *ab = ar->ab; + unsigned long time_left; + int ret; + + lockdep_assert_held(&ar->conf_mutex); + + ath11k_mac_fw_stats_reset(ar); + + reinit_completion(&ar->fw_stats_complete); + reinit_completion(&ar->fw_stats_done); + + ret = ath11k_wmi_send_stats_request_cmd(ar, req_param); + + if (ret) { + ath11k_warn(ab, "could not request fw stats (%d)\n", + ret); + return ret; + } + + time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ); + if (!time_left) + return -ETIMEDOUT; + + /* FW stats can get split when exceeding the stats data buffer limit. + * In that case, since there is no end marking for the back-to-back + * received 'update stats' event, we keep a 3 seconds timeout in case, + * fw_stats_done is not marked yet + */ + time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ); + if (!time_left) + return -ETIMEDOUT; + + return 0; +} + +static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id, + u32 vdev_id, u32 stats_id) +{ + struct ath11k_base *ab = ar->ab; + struct stats_request_params req_param; + int ret; + + lockdep_assert_held(&ar->conf_mutex); + + if (ar->state != ATH11K_STATE_ON) + return -ENETDOWN; + + req_param.pdev_id = pdev_id; + req_param.vdev_id = vdev_id; + req_param.stats_id = stats_id; + + ret = ath11k_mac_fw_stats_request(ar, &req_param); + if (ret) + ath11k_warn(ab, "failed to request fw stats: %d\n", ret); + + ath11k_dbg(ab, ATH11K_DBG_WMI, + "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n", + pdev_id, vdev_id, stats_id); + + return ret; +} + +static int ath11k_mac_handle_get_txpower(struct ath11k *ar, + struct ieee80211_vif *vif, + int *dbm) +{ + struct ath11k_base *ab = ar->ab; + struct ath11k_fw_stats_pdev *pdev; + int ret; + + /* Final Tx power is minimum of Target Power, CTL power, Regulatory + * Power, PSD EIRP Power. We just know the Regulatory power from the + * regulatory rules obtained. FW knows all these power and sets the min + * of these. Hence, we request the FW pdev stats in which FW reports + * the minimum of all vdev's channel Tx power. + */ + lockdep_assert_held(&ar->conf_mutex); + + /* Firmware doesn't provide Tx power during CAC hence no need to fetch + * the stats. + */ + if (test_bit(ATH11K_CAC_RUNNING, &ar->dev_flags)) + return -EAGAIN; + + ret = ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0, + WMI_REQUEST_PDEV_STAT); + if (ret) { + ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret); + goto err_fallback; + } + + spin_lock_bh(&ar->data_lock); + pdev = list_first_entry_or_null(&ar->fw_stats.pdevs, + struct ath11k_fw_stats_pdev, list); + if (!pdev) { + spin_unlock_bh(&ar->data_lock); + goto err_fallback; + } + + /* tx power is set as 2 units per dBm in FW. */ + *dbm = pdev->chan_tx_power / 2; + + spin_unlock_bh(&ar->data_lock); + + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "txpower from firmware %d, reported %d dBm\n", + pdev->chan_tx_power, *dbm); + return 0; + +err_fallback: + /* We didn't get txpower from FW. Hence, relying on vif->bss_conf.txpower */ + *dbm = vif->bss_conf.txpower; + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "txpower from firmware NaN, reported %d dBm\n", + *dbm); + return 0; +} + +static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + unsigned int link_id, + int *dbm) +{ + struct ath11k *ar = hw->priv; + int ret; + + mutex_lock(&ar->conf_mutex); + ret = ath11k_mac_handle_get_txpower(ar, vif, dbm); + mutex_unlock(&ar->conf_mutex); + + return ret; +} + static int ath11k_mac_op_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_scan_request *hw_req) @@ -6107,6 +6251,159 @@ static void ath11k_mgmt_over_wmi_tx_purge(struct ath11k *ar) ath11k_mgmt_over_wmi_tx_drop(ar, skb); } +static int ath11k_mac_mgmt_action_frame_fill_elem_data(struct ath11k_vif *arvif, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + u8 category, *buf, iv_len, action_code, dialog_token; + int cur_tx_power, max_tx_power; + struct ath11k *ar = arvif->ar; + struct cfg80211_chan_def def; + struct ath11k_skb_cb *skb_cb; + struct ieee80211_mgmt *mgmt; + unsigned int remaining_len; + bool has_protected; + + lockdep_assert_held(&ar->conf_mutex); + + /* make sure category field is present */ + if (skb->len < IEEE80211_MIN_ACTION_SIZE) + return -EINVAL; + + remaining_len = skb->len - IEEE80211_MIN_ACTION_SIZE; + has_protected = ieee80211_has_protected(hdr->frame_control); + + /* In case of SW crypto and hdr protected (PMF), packet will already be encrypted, + * we can't put in data in this case + */ + if (test_bit(ATH11K_FLAG_HW_CRYPTO_DISABLED, &ar->ab->dev_flags) && + has_protected) + return 0; + + mgmt = (struct ieee80211_mgmt *)hdr; + buf = (u8 *)&mgmt->u.action; + + /* FCTL_PROTECTED frame might have extra space added for HDR_LEN. Offset that + * many bytes if it is there + */ + if (has_protected) { + skb_cb = ATH11K_SKB_CB(skb); + + switch (skb_cb->cipher) { + /* Cipher suite having flag %IEEE80211_KEY_FLAG_GENERATE_IV_MGMT set in + * key needs to be processed. See ath11k_install_key() + */ + case WLAN_CIPHER_SUITE_CCMP: + case WLAN_CIPHER_SUITE_CCMP_256: + case WLAN_CIPHER_SUITE_GCMP: + case WLAN_CIPHER_SUITE_GCMP_256: + iv_len = IEEE80211_CCMP_HDR_LEN; + break; + case WLAN_CIPHER_SUITE_TKIP: + iv_len = 0; + break; + default: + return -EINVAL; + } + + if (remaining_len < iv_len) + return -EINVAL; + + buf += iv_len; + remaining_len -= iv_len; + } + + category = *buf++; + /* category code is already taken care in %IEEE80211_MIN_ACTION_SIZE hence + * no need to adjust remaining_len + */ + + switch (category) { + case WLAN_CATEGORY_RADIO_MEASUREMENT: + /* need action code and dialog token */ + if (remaining_len < 2) + return -EINVAL; + + /* Packet Format: + * Action Code | Dialog Token | Variable Len (based on Action Code) + */ + action_code = *buf++; + dialog_token = *buf++; + remaining_len -= 2; + + if (ath11k_mac_vif_chan(arvif->vif, &def)) + return -ENOENT; + + cur_tx_power = arvif->vif->bss_conf.txpower; + max_tx_power = min(def.chan->max_reg_power, (int)ar->max_tx_power / 2); + ath11k_mac_handle_get_txpower(ar, arvif->vif, &cur_tx_power); + + switch (action_code) { + case WLAN_RM_ACTION_LINK_MEASUREMENT_REQUEST: + /* need variable fields to be present in len */ + if (remaining_len < 2) + return -EINVAL; + + /* Variable length format as defined in IEEE 802.11-2024, + * Figure 9-1187-Link Measurement Request frame Action field + * format. + * Transmit Power | Max Tx Power + * We fill both of these. + */ + *buf++ = cur_tx_power; + *buf = max_tx_power; + + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "RRM: Link Measurement Req dialog_token %u cur_tx_power %d max_tx_power %d\n", + dialog_token, cur_tx_power, max_tx_power); + break; + case WLAN_RM_ACTION_LINK_MEASUREMENT_REPORT: + /* need variable fields to be present in len */ + if (remaining_len < 3) + return -EINVAL; + + /* Variable length format as defined in IEEE 802.11-2024, + * Figure 9-1188-Link Measurement Report frame Action field format + * TPC Report | Variable Fields + * + * TPC Report Format: + * Element ID | Len | Tx Power | Link Margin + * + * We fill Tx power in the TPC Report (2nd index) + */ + buf[2] = cur_tx_power; + + /* TODO: At present, Link margin data is not present so can't + * really fill it now. Once it is available, it can be added + * here + */ + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "RRM: Link Measurement Report dialog_token %u cur_tx_power %d\n", + dialog_token, cur_tx_power); + break; + default: + return -EINVAL; + } + break; + default: + /* nothing to fill */ + return 0; + } + + return 0; +} + +static int ath11k_mac_mgmt_frame_fill_elem_data(struct ath11k_vif *arvif, + struct sk_buff *skb) +{ + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + + if (!ieee80211_is_action(hdr->frame_control)) + return 0; + + return ath11k_mac_mgmt_action_frame_fill_elem_data(arvif, skb); +} + static void ath11k_mgmt_over_wmi_tx_work(struct work_struct *work) { struct ath11k *ar = container_of(work, struct ath11k, wmi_mgmt_tx_work); @@ -6126,6 +6423,19 @@ static void ath11k_mgmt_over_wmi_tx_work(struct work_struct *work) arvif = ath11k_vif_to_arvif(skb_cb->vif); mutex_lock(&ar->conf_mutex); if (ar->allocated_vdev_map & (1LL << arvif->vdev_id)) { + /* Fill in the data which is required to be filled by the driver + * For example: Max Tx power in Link Measurement Request/Report + */ + ret = ath11k_mac_mgmt_frame_fill_elem_data(arvif, skb); + if (ret) { + /* If we couldn't fill the data due to any reason, + * let's not discard transmitting the packet. + */ + ath11k_dbg(ar->ab, ATH11K_DBG_MAC, + "Failed to fill the required data for the mgmt packet err %d\n", + ret); + } + ret = ath11k_mac_mgmt_tx_wmi(ar, arvif, skb); if (ret) { ath11k_warn(ar->ab, "failed to tx mgmt frame, vdev_id %d :%d\n", @@ -9079,81 +9389,6 @@ static void ath11k_mac_put_chain_rssi(struct station_info *sinfo, } } -static void ath11k_mac_fw_stats_reset(struct ath11k *ar) -{ - spin_lock_bh(&ar->data_lock); - ath11k_fw_stats_pdevs_free(&ar->fw_stats.pdevs); - ath11k_fw_stats_vdevs_free(&ar->fw_stats.vdevs); - ar->fw_stats.num_vdev_recvd = 0; - ar->fw_stats.num_bcn_recvd = 0; - spin_unlock_bh(&ar->data_lock); -} - -int ath11k_mac_fw_stats_request(struct ath11k *ar, - struct stats_request_params *req_param) -{ - struct ath11k_base *ab = ar->ab; - unsigned long time_left; - int ret; - - lockdep_assert_held(&ar->conf_mutex); - - ath11k_mac_fw_stats_reset(ar); - - reinit_completion(&ar->fw_stats_complete); - reinit_completion(&ar->fw_stats_done); - - ret = ath11k_wmi_send_stats_request_cmd(ar, req_param); - - if (ret) { - ath11k_warn(ab, "could not request fw stats (%d)\n", - ret); - return ret; - } - - time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ); - if (!time_left) - return -ETIMEDOUT; - - /* FW stats can get split when exceeding the stats data buffer limit. - * In that case, since there is no end marking for the back-to-back - * received 'update stats' event, we keep a 3 seconds timeout in case, - * fw_stats_done is not marked yet - */ - time_left = wait_for_completion_timeout(&ar->fw_stats_done, 3 * HZ); - if (!time_left) - return -ETIMEDOUT; - - return 0; -} - -static int ath11k_mac_get_fw_stats(struct ath11k *ar, u32 pdev_id, - u32 vdev_id, u32 stats_id) -{ - struct ath11k_base *ab = ar->ab; - struct stats_request_params req_param; - int ret; - - lockdep_assert_held(&ar->conf_mutex); - - if (ar->state != ATH11K_STATE_ON) - return -ENETDOWN; - - req_param.pdev_id = pdev_id; - req_param.vdev_id = vdev_id; - req_param.stats_id = stats_id; - - ret = ath11k_mac_fw_stats_request(ar, &req_param); - if (ret) - ath11k_warn(ab, "failed to request fw stats: %d\n", ret); - - ath11k_dbg(ab, ATH11K_DBG_WMI, - "debug get fw stat pdev id %d vdev id %d stats id 0x%x\n", - pdev_id, vdev_id, stats_id); - - return ret; -} - static void ath11k_mac_op_sta_statistics(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta, @@ -9539,66 +9774,6 @@ static int ath11k_mac_op_remain_on_channel(struct ieee80211_hw *hw, return ret; } -static int ath11k_mac_op_get_txpower(struct ieee80211_hw *hw, - struct ieee80211_vif *vif, - unsigned int link_id, - int *dbm) -{ - struct ath11k *ar = hw->priv; - struct ath11k_base *ab = ar->ab; - struct ath11k_fw_stats_pdev *pdev; - int ret; - - /* Final Tx power is minimum of Target Power, CTL power, Regulatory - * Power, PSD EIRP Power. We just know the Regulatory power from the - * regulatory rules obtained. FW knows all these power and sets the min - * of these. Hence, we request the FW pdev stats in which FW reports - * the minimum of all vdev's channel Tx power. - */ - mutex_lock(&ar->conf_mutex); - - /* Firmware doesn't provide Tx power during CAC hence no need to fetch - * the stats. - */ - if (test_bit(ATH11K_CAC_RUNNING, &ar->dev_flags)) { - mutex_unlock(&ar->conf_mutex); - return -EAGAIN; - } - - ret = ath11k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0, - WMI_REQUEST_PDEV_STAT); - if (ret) { - ath11k_warn(ab, "failed to request fw pdev stats: %d\n", ret); - goto err_fallback; - } - - spin_lock_bh(&ar->data_lock); - pdev = list_first_entry_or_null(&ar->fw_stats.pdevs, - struct ath11k_fw_stats_pdev, list); - if (!pdev) { - spin_unlock_bh(&ar->data_lock); - goto err_fallback; - } - - /* tx power is set as 2 units per dBm in FW. */ - *dbm = pdev->chan_tx_power / 2; - - spin_unlock_bh(&ar->data_lock); - mutex_unlock(&ar->conf_mutex); - - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "txpower from firmware %d, reported %d dBm\n", - pdev->chan_tx_power, *dbm); - return 0; - -err_fallback: - mutex_unlock(&ar->conf_mutex); - /* We didn't get txpower from FW. Hence, relying on vif->bss_conf.txpower */ - *dbm = vif->bss_conf.txpower; - ath11k_dbg(ar->ab, ATH11K_DBG_MAC, "txpower from firmware NaN, reported %d dBm\n", - *dbm); - return 0; -} - static int ath11k_mac_station_add(struct ath11k *ar, struct ieee80211_vif *vif, struct ieee80211_sta *sta) @@ -10368,6 +10543,8 @@ static int __ath11k_mac_register(struct ath11k *ar) ar->hw->wiphy->features |= NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE | NL80211_FEATURE_AP_SCAN; + ar->hw->wiphy->features |= NL80211_FEATURE_TX_POWER_INSERTION; + ar->max_num_stations = TARGET_NUM_STATIONS(ab); ar->max_num_peers = TARGET_NUM_PEERS_PDEV(ab); diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index d8655badd96d0..7114eca8810db 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -177,6 +177,19 @@ static inline void ath11k_pci_select_static_window(struct ath11k_pci *ab_pci) ab_pci->ab->mem + ATH11K_PCI_WINDOW_REG_ADDRESS); } +static void ath11k_pci_restore_window(struct ath11k_base *ab) +{ + struct ath11k_pci *ab_pci = ath11k_pci_priv(ab); + + spin_lock_bh(&ab_pci->window_lock); + + iowrite32(ATH11K_PCI_WINDOW_ENABLE_BIT | ab_pci->register_window, + ab->mem + ATH11K_PCI_WINDOW_REG_ADDRESS); + ioread32(ab->mem + ATH11K_PCI_WINDOW_REG_ADDRESS); + + spin_unlock_bh(&ab_pci->window_lock); +} + static void ath11k_pci_soc_global_reset(struct ath11k_base *ab) { u32 val, delay; @@ -201,6 +214,11 @@ static void ath11k_pci_soc_global_reset(struct ath11k_base *ab) val = ath11k_pcic_read32(ab, PCIE_SOC_GLOBAL_RESET); if (val == 0xffffffff) ath11k_warn(ab, "link down error during global reset\n"); + + /* Restore window register as its content is cleared during + * hardware global reset, such that it aligns with host cache. + */ + ath11k_pci_restore_window(ab); } static void ath11k_pci_clear_dbg_registers(struct ath11k_base *ab) diff --git a/drivers/net/wireless/ath/ath11k/pci.h b/drivers/net/wireless/ath/ath11k/pci.h index c33c7865145cc..1e3005a4b64c6 100644 --- a/drivers/net/wireless/ath/ath11k/pci.h +++ b/drivers/net/wireless/ath/ath11k/pci.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2022,2024 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef _ATH11K_PCI_H #define _ATH11K_PCI_H @@ -35,18 +35,18 @@ #define PCIE_SMLH_REQ_RST_LINK_DOWN 0x2 #define PCIE_INT_CLEAR_ALL 0xffffffff -#define PCIE_QSERDES_COM_SYSCLK_EN_SEL_REG(x) \ - (ab->hw_params.regs->pcie_qserdes_sysclk_en_sel) +#define PCIE_QSERDES_COM_SYSCLK_EN_SEL_REG(ab) \ + ((ab)->hw_params.regs->pcie_qserdes_sysclk_en_sel) #define PCIE_QSERDES_COM_SYSCLK_EN_SEL_VAL 0x10 #define PCIE_QSERDES_COM_SYSCLK_EN_SEL_MSK 0xffffffff -#define PCIE_PCS_OSC_DTCT_CONFIG1_REG(x) \ - (ab->hw_params.regs->pcie_pcs_osc_dtct_config_base) +#define PCIE_PCS_OSC_DTCT_CONFIG1_REG(ab) \ + ((ab)->hw_params.regs->pcie_pcs_osc_dtct_config_base) #define PCIE_PCS_OSC_DTCT_CONFIG1_VAL 0x02 -#define PCIE_PCS_OSC_DTCT_CONFIG2_REG(x) \ - (ab->hw_params.regs->pcie_pcs_osc_dtct_config_base + 0x4) +#define PCIE_PCS_OSC_DTCT_CONFIG2_REG(ab) \ + ((ab)->hw_params.regs->pcie_pcs_osc_dtct_config_base + 0x4) #define PCIE_PCS_OSC_DTCT_CONFIG2_VAL 0x52 -#define PCIE_PCS_OSC_DTCT_CONFIG4_REG(x) \ - (ab->hw_params.regs->pcie_pcs_osc_dtct_config_base + 0xc) +#define PCIE_PCS_OSC_DTCT_CONFIG4_REG(ab) \ + ((ab)->hw_params.regs->pcie_pcs_osc_dtct_config_base + 0xc) #define PCIE_PCS_OSC_DTCT_CONFIG4_VAL 0xff #define PCIE_PCS_OSC_DTCT_CONFIG_MSK 0x000000ff diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c index aea56c38bf8f3..ff6a97e328b88 100644 --- a/drivers/net/wireless/ath/ath11k/qmi.c +++ b/drivers/net/wireless/ath/ath11k/qmi.c @@ -3177,7 +3177,7 @@ static int ath11k_qmi_ops_new_server(struct qmi_handle *qmi_hdl, sq->sq_node = service->node; sq->sq_port = service->port; - ret = kernel_connect(qmi_hdl->sock, (struct sockaddr *)sq, + ret = kernel_connect(qmi_hdl->sock, (struct sockaddr_unsized *)sq, sizeof(*sq), 0); if (ret) { ath11k_warn(ab, "failed to connect to qmi remote service: %d\n", ret); diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c index e3b444333deed..110035dae8a61 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.c +++ b/drivers/net/wireless/ath/ath11k/wmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include #include @@ -2061,10 +2061,13 @@ int ath11k_wmi_send_peer_assoc_cmd(struct ath11k *ar, cmd->peer_bw_rxnss_override |= param->peer_bw_rxnss_override; if (param->vht_capable) { - mcs->rx_max_rate = param->rx_max_rate; - mcs->rx_mcs_set = param->rx_mcs_set; - mcs->tx_max_rate = param->tx_max_rate; - mcs->tx_mcs_set = param->tx_mcs_set; + /* firmware interprets mcs->tx_mcs_set field as peer's + * RX capability + */ + mcs->tx_max_rate = param->rx_max_rate; + mcs->tx_mcs_set = param->rx_mcs_set; + mcs->rx_max_rate = param->tx_max_rate; + mcs->rx_mcs_set = param->tx_mcs_set; } /* HE Rates */ @@ -2088,8 +2091,11 @@ int ath11k_wmi_send_peer_assoc_cmd(struct ath11k *ar, FIELD_PREP(WMI_TLV_LEN, sizeof(*he_mcs) - TLV_HDR_SIZE); - he_mcs->rx_mcs_set = param->peer_he_tx_mcs_set[i]; - he_mcs->tx_mcs_set = param->peer_he_rx_mcs_set[i]; + /* firmware interprets mcs->rx_mcs_set field as peer's + * RX capability + */ + he_mcs->rx_mcs_set = param->peer_he_rx_mcs_set[i]; + he_mcs->tx_mcs_set = param->peer_he_tx_mcs_set[i]; ptr += sizeof(*he_mcs); } diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h index 9fcffaa2f383c..0f0de24a38408 100644 --- a/drivers/net/wireless/ath/ath11k/wmi.h +++ b/drivers/net/wireless/ath/ath11k/wmi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef ATH11K_WMI_H @@ -3463,20 +3463,6 @@ struct scan_cancel_param { u32 pdev_id; }; -struct wmi_bcn_send_from_host_cmd { - u32 tlv_header; - u32 vdev_id; - u32 data_len; - union { - u32 frag_ptr; - u32 frag_ptr_lo; - }; - u32 frame_ctrl; - u32 dtim_flag; - u32 bcn_antenna; - u32 frag_ptr_hi; -}; - #define WMI_CHAN_INFO_MODE GENMASK(5, 0) #define WMI_CHAN_INFO_HT40_PLUS BIT(6) #define WMI_CHAN_INFO_PASSIVE BIT(7) @@ -4133,8 +4119,10 @@ struct wmi_rate_set { struct wmi_vht_rate_set { u32 tlv_header; u32 rx_max_rate; + /* MCS at which the peer can transmit */ u32 rx_mcs_set; u32 tx_max_rate; + /* MCS at which the peer can receive */ u32 tx_mcs_set; u32 tx_max_mcs_nss; } __packed; diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c index 5d494c5cdc0da..cc352eef19399 100644 --- a/drivers/net/wireless/ath/ath12k/core.c +++ b/drivers/net/wireless/ath/ath12k/core.c @@ -1,7 +1,6 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ @@ -1250,7 +1249,6 @@ void ath12k_fw_stats_reset(struct ath12k *ar) spin_lock_bh(&ar->data_lock); ath12k_fw_stats_free(&ar->fw_stats); ar->fw_stats.num_vdev_recvd = 0; - ar->fw_stats.num_bcn_recvd = 0; spin_unlock_bh(&ar->data_lock); } @@ -2106,14 +2104,27 @@ static int ath12k_core_hw_group_create(struct ath12k_hw_group *ag) ret = ath12k_core_soc_create(ab); if (ret) { mutex_unlock(&ab->core_lock); - ath12k_err(ab, "failed to create soc core: %d\n", ret); - return ret; + ath12k_err(ab, "failed to create soc %d core: %d\n", i, ret); + goto destroy; } mutex_unlock(&ab->core_lock); } return 0; + +destroy: + for (i--; i >= 0; i--) { + ab = ag->ab[i]; + if (!ab) + continue; + + mutex_lock(&ab->core_lock); + ath12k_core_soc_destroy(ab); + mutex_unlock(&ab->core_lock); + } + + return ret; } void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag) @@ -2188,7 +2199,7 @@ int ath12k_core_init(struct ath12k_base *ab) if (ret) { mutex_unlock(&ag->mutex); ath12k_warn(ab, "unable to create hw group\n"); - goto err_destroy_hw_group; + goto err_unassign_hw_group; } } @@ -2196,8 +2207,7 @@ int ath12k_core_init(struct ath12k_base *ab) return 0; -err_destroy_hw_group: - ath12k_core_hw_group_destroy(ab->ag); +err_unassign_hw_group: ath12k_core_hw_group_unassign(ab); err_unregister_notifier: ath12k_core_panic_notifier_unregister(ab); diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h index 3d1956966a485..3c1e0069be1e7 100644 --- a/drivers/net/wireless/ath/ath12k/core.h +++ b/drivers/net/wireless/ath/ath12k/core.h @@ -355,6 +355,8 @@ struct ath12k_link_vif { struct wmi_vdev_install_key_arg group_key; bool pairwise_key_done; u16 num_stations; + bool is_csa_in_progress; + struct wiphy_work bcn_tx_work; }; struct ath12k_vif { @@ -644,7 +646,6 @@ struct ath12k_fw_stats { struct list_head vdevs; struct list_head bcn; u32 num_vdev_recvd; - u32 num_bcn_recvd; }; struct ath12k_dbg_htt_stats { @@ -963,6 +964,7 @@ struct ath12k_device_dp_stats { u32 tx_wbm_rel_source[HAL_WBM_REL_SRC_MODULE_MAX]; u32 tx_enqueued[DP_TCL_NUM_RING_MAX]; u32 tx_completed[DP_TCL_NUM_RING_MAX]; + u32 reo_excep_msdu_buf_type; }; struct ath12k_reg_freq { diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c index 16601a8c36448..d6a86f075d73b 100644 --- a/drivers/net/wireless/ath/ath12k/debugfs.c +++ b/drivers/net/wireless/ath/ath12k/debugfs.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include "core.h" @@ -1178,6 +1178,9 @@ static ssize_t ath12k_debugfs_dump_device_dp_stats(struct file *file, len += scnprintf(buf + len, size - len, "\n"); } + len += scnprintf(buf + len, size - len, "\nREO excep MSDU buf type:%u\n", + device_stats->reo_excep_msdu_buf_type); + len += scnprintf(buf + len, size - len, "\nRx WBM REL SRC Errors:\n"); for (i = 0; i < HAL_WBM_REL_SRC_MODULE_MAX; i++) { @@ -1283,6 +1286,7 @@ static int ath12k_open_vdev_stats(struct inode *inode, struct file *file) ath12k_wmi_fw_stats_dump(ar, &ar->fw_stats, param.stats_id, buf); + ath12k_fw_stats_reset(ar); file->private_data = no_free_ptr(buf); @@ -1349,12 +1353,7 @@ static int ath12k_open_bcn_stats(struct inode *inode, struct file *file) ath12k_wmi_fw_stats_dump(ar, &ar->fw_stats, param.stats_id, buf); - /* since beacon stats request is looped for all active VDEVs, saved fw - * stats is not freed for each request until done for all active VDEVs - */ - spin_lock_bh(&ar->data_lock); - ath12k_fw_stats_bcn_free(&ar->fw_stats.bcn); - spin_unlock_bh(&ar->data_lock); + ath12k_fw_stats_reset(ar); file->private_data = no_free_ptr(buf); @@ -1415,6 +1414,7 @@ static int ath12k_open_pdev_stats(struct inode *inode, struct file *file) ath12k_wmi_fw_stats_dump(ar, &ar->fw_stats, param.stats_id, buf); + ath12k_fw_stats_reset(ar); file->private_data = no_free_ptr(buf); diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c index 009c495021489..39d1967584db8 100644 --- a/drivers/net/wireless/ath/ath12k/dp_mon.c +++ b/drivers/net/wireless/ath/ath12k/dp_mon.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include "dp_mon.h" @@ -105,7 +105,7 @@ static void ath12k_dp_mon_parse_vht_sig_a(const struct hal_rx_vht_sig_a_info *vh if (ppdu_info->is_stbc && nsts > 0) nsts = ((nsts + 1) >> 1) - 1; - ppdu_info->nss = u32_get_bits(nsts, VHT_SIG_SU_NSS_MASK); + ppdu_info->nss = u32_get_bits(nsts, VHT_SIG_SU_NSS_MASK) + 1; ppdu_info->bw = u32_get_bits(info0, HAL_RX_VHT_SIG_A_INFO_INFO0_BW); ppdu_info->beamformed = u32_get_bits(info1, HAL_RX_VHT_SIG_A_INFO_INFO1_BEAMFORMED); @@ -129,7 +129,7 @@ static void ath12k_dp_mon_parse_ht_sig(const struct hal_rx_ht_sig_info *ht_sig, ppdu_info->is_stbc = u32_get_bits(info1, HAL_RX_HT_SIG_INFO_INFO1_STBC); ppdu_info->ldpc = u32_get_bits(info1, HAL_RX_HT_SIG_INFO_INFO1_FEC_CODING); ppdu_info->gi = u32_get_bits(info1, HAL_RX_HT_SIG_INFO_INFO1_GI); - ppdu_info->nss = (ppdu_info->mcs >> 3); + ppdu_info->nss = (ppdu_info->mcs >> 3) + 1; } static void ath12k_dp_mon_parse_l_sig_b(const struct hal_rx_lsig_b_info *lsigb, @@ -233,7 +233,9 @@ ath12k_dp_mon_parse_he_sig_b2_ofdma(const struct hal_rx_he_sig_b2_ofdma_info *of value = value << HE_STA_ID_SHIFT; ppdu_info->he_data4 |= value; - ppdu_info->nss = u32_get_bits(info0, HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_NSTS); + ppdu_info->nss = + u32_get_bits(info0, + HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_NSTS) + 1; ppdu_info->beamformed = u32_get_bits(info0, HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_TXBF); } @@ -261,7 +263,9 @@ ath12k_dp_mon_parse_he_sig_b2_mu(const struct hal_rx_he_sig_b2_mu_info *he_sig_b value = value << HE_STA_ID_SHIFT; ppdu_info->he_data4 |= value; - ppdu_info->nss = u32_get_bits(info0, HAL_RX_HE_SIG_B2_MU_INFO_INFO0_STA_NSTS); + ppdu_info->nss = + u32_get_bits(info0, + HAL_RX_HE_SIG_B2_MU_INFO_INFO0_STA_NSTS) + 1; } static void @@ -553,7 +557,8 @@ static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info * ppdu_info->is_stbc = u32_get_bits(info1, HAL_RX_HE_SIG_A_SU_INFO_INFO1_STBC); ppdu_info->beamformed = u32_get_bits(info1, HAL_RX_HE_SIG_A_SU_INFO_INFO1_TXBF); dcm = u32_get_bits(info0, HAL_RX_HE_SIG_A_SU_INFO_INFO0_DCM); - ppdu_info->nss = u32_get_bits(info0, HAL_RX_HE_SIG_A_SU_INFO_INFO0_NSTS); + ppdu_info->nss = u32_get_bits(info0, + HAL_RX_HE_SIG_A_SU_INFO_INFO0_NSTS) + 1; ppdu_info->dcm = dcm; } @@ -2179,7 +2184,7 @@ static void ath12k_dp_mon_update_radiotap(struct ath12k *ar, spin_unlock_bh(&ar->data_lock); rxs->flag |= RX_FLAG_MACTIME_START; - rxs->nss = ppduinfo->nss + 1; + rxs->nss = ppduinfo->nss; if (test_bit(WMI_TLV_SERVICE_HW_DB2DBM_CONVERSION_SUPPORT, ar->ab->wmi_ab.svc_map)) rxs->signal = ppduinfo->rssi_comb; diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c index 5e5c14a70316d..d28d8ffec0f83 100644 --- a/drivers/net/wireless/ath/ath12k/dp_rx.c +++ b/drivers/net/wireless/ath/ath12k/dp_rx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -1089,6 +1089,8 @@ static int ath12k_dp_prepare_reo_update_elem(struct ath12k_dp *dp, { struct dp_reo_update_rx_queue_elem *elem; + lockdep_assert_held(&dp->ab->base_lock); + elem = kzalloc(sizeof(*elem), GFP_ATOMIC); if (!elem) return -ENOMEM; @@ -3781,6 +3783,50 @@ ath12k_dp_process_rx_err_buf(struct ath12k *ar, struct hal_reo_dest_ring *desc, return 0; } +static int ath12k_dp_h_msdu_buffer_type(struct ath12k_base *ab, + struct list_head *list, + struct hal_reo_dest_ring *desc) +{ + struct ath12k_rx_desc_info *desc_info; + struct ath12k_skb_rxcb *rxcb; + struct sk_buff *msdu; + u64 desc_va; + + ab->device_stats.reo_excep_msdu_buf_type++; + + desc_va = (u64)le32_to_cpu(desc->buf_va_hi) << 32 | + le32_to_cpu(desc->buf_va_lo); + desc_info = (struct ath12k_rx_desc_info *)(uintptr_t)desc_va; + if (!desc_info) { + u32 cookie; + + cookie = le32_get_bits(desc->buf_addr_info.info1, + BUFFER_ADDR_INFO1_SW_COOKIE); + desc_info = ath12k_dp_get_rx_desc(ab, cookie); + if (!desc_info) { + ath12k_warn(ab, "Invalid cookie in manual descriptor retrieval: 0x%x\n", + cookie); + return -EINVAL; + } + } + + if (desc_info->magic != ATH12K_DP_RX_DESC_MAGIC) { + ath12k_warn(ab, "rx exception, magic check failed with value: %u\n", + desc_info->magic); + return -EINVAL; + } + + msdu = desc_info->skb; + desc_info->skb = NULL; + list_add_tail(&desc_info->list, list); + rxcb = ATH12K_SKB_RXCB(msdu); + dma_unmap_single(ab->dev, rxcb->paddr, msdu->len + skb_tailroom(msdu), + DMA_FROM_DEVICE); + dev_kfree_skb_any(msdu); + + return 0; +} + int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, int budget) { @@ -3825,6 +3871,26 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, drop = false; ab->device_stats.err_ring_pkts++; + hw_link_id = le32_get_bits(reo_desc->info0, + HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); + device_id = hw_links[hw_link_id].device_id; + partner_ab = ath12k_ag_to_ab(ag, device_id); + + /* Below case is added to handle data packet from un-associated clients. + * As it is expected that AST lookup will fail for + * un-associated station's data packets. + */ + if (le32_get_bits(reo_desc->info0, HAL_REO_DEST_RING_INFO0_BUFFER_TYPE) == + HAL_REO_DEST_RING_BUFFER_TYPE_MSDU) { + if (!ath12k_dp_h_msdu_buffer_type(partner_ab, + &rx_desc_used_list[device_id], + reo_desc)) { + num_buffs_reaped[device_id]++; + tot_n_bufs_reaped++; + } + goto next_desc; + } + ret = ath12k_hal_desc_reo_parse_err(ab, reo_desc, &paddr, &desc_bank); if (ret) { @@ -3833,11 +3899,6 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, continue; } - hw_link_id = le32_get_bits(reo_desc->info0, - HAL_REO_DEST_RING_INFO0_SRC_LINK_ID); - device_id = hw_links[hw_link_id].device_id; - partner_ab = ath12k_ag_to_ab(ag, device_id); - pdev_id = ath12k_hw_mac_id_to_pdev_id(partner_ab->hw_params, hw_links[hw_link_id].pdev_idx); ar = partner_ab->pdevs[pdev_id].ar; @@ -3886,6 +3947,7 @@ int ath12k_dp_rx_process_err(struct ath12k_base *ab, struct napi_struct *napi, } } +next_desc: if (tot_n_bufs_reaped >= quota) { tot_n_bufs_reaped = quota; goto exit; diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.c b/drivers/net/wireless/ath/ath12k/hal_rx.c index 669096278fdd4..c4443ca05cd65 100644 --- a/drivers/net/wireless/ath/ath12k/hal_rx.c +++ b/drivers/net/wireless/ath/ath12k/hal_rx.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include "debug.h" @@ -323,7 +323,7 @@ int ath12k_hal_desc_reo_parse_err(struct ath12k_base *ab, { enum hal_reo_dest_ring_push_reason push_reason; enum hal_reo_dest_ring_error_code err_code; - u32 cookie, val; + u32 cookie; push_reason = le32_get_bits(desc->info0, HAL_REO_DEST_RING_INFO0_PUSH_REASON); @@ -338,12 +338,6 @@ int ath12k_hal_desc_reo_parse_err(struct ath12k_base *ab, return -EINVAL; } - val = le32_get_bits(desc->info0, HAL_REO_DEST_RING_INFO0_BUFFER_TYPE); - if (val != HAL_REO_DEST_RING_BUFFER_TYPE_LINK_DESC) { - ath12k_warn(ab, "expected buffer type link_desc"); - return -EINVAL; - } - ath12k_hal_rx_reo_ent_paddr_get(ab, &desc->buf_addr_info, paddr, &cookie); *desc_bank = u32_get_bits(cookie, DP_LINK_DESC_BANK_MASK); diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c index db351c9220181..f7a2a544bef20 100644 --- a/drivers/net/wireless/ath/ath12k/mac.c +++ b/drivers/net/wireless/ath/ath12k/mac.c @@ -533,6 +533,30 @@ ath12k_mac_max_he_nss(const u16 he_mcs_mask[NL80211_HE_NSS_MAX]) return 1; } +static u32 +ath12k_mac_max_eht_nss(const u16 eht_mcs_mask[NL80211_EHT_NSS_MAX]) +{ + int nss; + + for (nss = NL80211_EHT_NSS_MAX - 1; nss >= 0; nss--) + if (eht_mcs_mask[nss]) + return nss + 1; + + return 1; +} + +static u32 +ath12k_mac_max_eht_mcs_nss(const u8 *eht_mcs, int eht_mcs_set_size) +{ + int i; + u8 nss = 0; + + for (i = 0; i < eht_mcs_set_size; i++) + nss = max(nss, u8_get_bits(eht_mcs[i], IEEE80211_EHT_MCS_NSS_RX)); + + return nss; +} + static u8 ath12k_parse_mpdudensity(u8 mpdudensity) { /* From IEEE Std 802.11-2020 defined values for "Minimum MPDU Start Spacing": @@ -2249,7 +2273,6 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, struct cfg80211_chan_def def; enum nl80211_band band; u16 *vht_mcs_mask; - u16 tx_mcs_map; u8 ampdu_factor; u8 max_nss, vht_mcs; int i, vht_nss, nss_idx; @@ -2340,10 +2363,10 @@ static void ath12k_peer_assoc_h_vht(struct ath12k *ar, arg->peer_nss = min(link_sta->rx_nss, max_nss); arg->rx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.rx_highest); arg->rx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map); - arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); + arg->rx_mcs_set = ath12k_peer_assoc_h_vht_limit(arg->rx_mcs_set, vht_mcs_mask); - tx_mcs_map = __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); - arg->tx_mcs_set = ath12k_peer_assoc_h_vht_limit(tx_mcs_map, vht_mcs_mask); + arg->tx_max_rate = __le16_to_cpu(vht_cap->vht_mcs.tx_highest); + arg->tx_mcs_set = __le16_to_cpu(vht_cap->vht_mcs.tx_mcs_map); /* In QCN9274 platform, VHT MCS rate 10 and 11 is enabled by default. * VHT MCS rate 10 and 11 is not supported in 11ac standard. @@ -2625,9 +2648,10 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, switch (link_sta->bandwidth) { case IEEE80211_STA_RX_BW_160: v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160); + v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; - v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); + v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_160); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_160] = v; arg->peer_he_mcs_count++; @@ -2637,10 +2661,10 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar, default: v = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80); + v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_rx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; v = le16_to_cpu(he_cap->he_mcs_nss_supp.tx_mcs_80); - v = ath12k_peer_assoc_h_he_limit(v, he_mcs_mask); arg->peer_he_tx_mcs_set[WMI_HECAP_TXRX_MCS_NSS_IDX_80] = v; arg->peer_he_mcs_count++; @@ -3004,6 +3028,18 @@ static enum wmi_phy_mode ath12k_mac_get_phymode_eht(struct ath12k *ar, return MODE_UNKNOWN; } +static bool +ath12k_peer_assoc_h_eht_masked(const u16 eht_mcs_mask[NL80211_EHT_NSS_MAX]) +{ + int nss; + + for (nss = 0; nss < NL80211_EHT_NSS_MAX; nss++) + if (eht_mcs_mask[nss]) + return false; + + return true; +} + static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, struct ath12k_link_vif *arvif, struct ath12k_link_sta *arsta, @@ -3015,6 +3051,7 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, const u8 *ht_mcs_mask; const u16 *vht_mcs_mask; const u16 *he_mcs_mask; + const u16 *eht_mcs_mask; enum wmi_phy_mode phymode = MODE_UNKNOWN; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -3029,6 +3066,7 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, ht_mcs_mask = arvif->bitrate_mask.control[band].ht_mcs; vht_mcs_mask = arvif->bitrate_mask.control[band].vht_mcs; he_mcs_mask = arvif->bitrate_mask.control[band].he_mcs; + eht_mcs_mask = arvif->bitrate_mask.control[band].eht_mcs; link_sta = ath12k_mac_get_link_sta(arsta); if (!link_sta) { @@ -3039,7 +3077,8 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, switch (band) { case NL80211_BAND_2GHZ: - if (link_sta->eht_cap.has_eht) { + if (link_sta->eht_cap.has_eht && + !ath12k_peer_assoc_h_eht_masked(eht_mcs_mask)) { if (link_sta->bandwidth == IEEE80211_STA_RX_BW_40) phymode = MODE_11BE_EHT40_2G; else @@ -3102,37 +3141,50 @@ static void ath12k_peer_assoc_h_phymode(struct ath12k *ar, WARN_ON(phymode == MODE_UNKNOWN); } +#define ATH12K_EHT_MCS_7_ENABLED 0x00FF +#define ATH12K_EHT_MCS_9_ENABLED 0x0300 +#define ATH12K_EHT_MCS_11_ENABLED 0x0C00 +#define ATH12K_EHT_MCS_13_ENABLED 0x3000 + static void ath12k_mac_set_eht_mcs(u8 rx_tx_mcs7, u8 rx_tx_mcs9, u8 rx_tx_mcs11, u8 rx_tx_mcs13, - u32 *rx_mcs, u32 *tx_mcs) -{ - *rx_mcs = 0; - u32p_replace_bits(rx_mcs, - u8_get_bits(rx_tx_mcs7, IEEE80211_EHT_MCS_NSS_RX), - WMI_EHT_MCS_NSS_0_7); - u32p_replace_bits(rx_mcs, - u8_get_bits(rx_tx_mcs9, IEEE80211_EHT_MCS_NSS_RX), - WMI_EHT_MCS_NSS_8_9); - u32p_replace_bits(rx_mcs, - u8_get_bits(rx_tx_mcs11, IEEE80211_EHT_MCS_NSS_RX), - WMI_EHT_MCS_NSS_10_11); - u32p_replace_bits(rx_mcs, - u8_get_bits(rx_tx_mcs13, IEEE80211_EHT_MCS_NSS_RX), - WMI_EHT_MCS_NSS_12_13); - - *tx_mcs = 0; - u32p_replace_bits(tx_mcs, - u8_get_bits(rx_tx_mcs7, IEEE80211_EHT_MCS_NSS_TX), - WMI_EHT_MCS_NSS_0_7); - u32p_replace_bits(tx_mcs, - u8_get_bits(rx_tx_mcs9, IEEE80211_EHT_MCS_NSS_TX), - WMI_EHT_MCS_NSS_8_9); - u32p_replace_bits(tx_mcs, - u8_get_bits(rx_tx_mcs11, IEEE80211_EHT_MCS_NSS_TX), - WMI_EHT_MCS_NSS_10_11); - u32p_replace_bits(tx_mcs, - u8_get_bits(rx_tx_mcs13, IEEE80211_EHT_MCS_NSS_TX), - WMI_EHT_MCS_NSS_12_13); + u32 *rx_mcs, u32 *tx_mcs, + const u16 eht_mcs_limit[NL80211_EHT_NSS_MAX]) +{ + int nss; + u8 mcs_7 = 0, mcs_9 = 0, mcs_11 = 0, mcs_13 = 0; + u8 peer_mcs_7, peer_mcs_9, peer_mcs_11, peer_mcs_13; + + for (nss = 0; nss < NL80211_EHT_NSS_MAX; nss++) { + if (eht_mcs_limit[nss] & ATH12K_EHT_MCS_7_ENABLED) + mcs_7++; + if (eht_mcs_limit[nss] & ATH12K_EHT_MCS_9_ENABLED) + mcs_9++; + if (eht_mcs_limit[nss] & ATH12K_EHT_MCS_11_ENABLED) + mcs_11++; + if (eht_mcs_limit[nss] & ATH12K_EHT_MCS_13_ENABLED) + mcs_13++; + } + + peer_mcs_7 = u8_get_bits(rx_tx_mcs7, IEEE80211_EHT_MCS_NSS_RX); + peer_mcs_9 = u8_get_bits(rx_tx_mcs9, IEEE80211_EHT_MCS_NSS_RX); + peer_mcs_11 = u8_get_bits(rx_tx_mcs11, IEEE80211_EHT_MCS_NSS_RX); + peer_mcs_13 = u8_get_bits(rx_tx_mcs13, IEEE80211_EHT_MCS_NSS_RX); + + *rx_mcs = u32_encode_bits(min(peer_mcs_7, mcs_7), WMI_EHT_MCS_NSS_0_7) | + u32_encode_bits(min(peer_mcs_9, mcs_9), WMI_EHT_MCS_NSS_8_9) | + u32_encode_bits(min(peer_mcs_11, mcs_11), WMI_EHT_MCS_NSS_10_11) | + u32_encode_bits(min(peer_mcs_13, mcs_13), WMI_EHT_MCS_NSS_12_13); + + peer_mcs_7 = u8_get_bits(rx_tx_mcs7, IEEE80211_EHT_MCS_NSS_TX); + peer_mcs_9 = u8_get_bits(rx_tx_mcs9, IEEE80211_EHT_MCS_NSS_TX); + peer_mcs_11 = u8_get_bits(rx_tx_mcs11, IEEE80211_EHT_MCS_NSS_TX); + peer_mcs_13 = u8_get_bits(rx_tx_mcs13, IEEE80211_EHT_MCS_NSS_TX); + + *tx_mcs = u32_encode_bits(min(peer_mcs_7, mcs_7), WMI_EHT_MCS_NSS_0_7) | + u32_encode_bits(min(peer_mcs_9, mcs_9), WMI_EHT_MCS_NSS_8_9) | + u32_encode_bits(min(peer_mcs_11, mcs_11), WMI_EHT_MCS_NSS_10_11) | + u32_encode_bits(min(peer_mcs_13, mcs_13), WMI_EHT_MCS_NSS_12_13); } static void ath12k_mac_set_eht_ppe_threshold(const u8 *ppe_thres, @@ -3171,13 +3223,22 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, struct ath12k_wmi_peer_assoc_arg *arg) { struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta); + struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + const struct ieee80211_eht_mcs_nss_supp *own_eht_mcs_nss_supp; const struct ieee80211_eht_mcs_nss_supp_20mhz_only *bw_20; + const struct ieee80211_sta_eht_cap *eht_cap, *own_eht_cap; + const struct ieee80211_sband_iftype_data *iftd; const struct ieee80211_eht_mcs_nss_supp_bw *bw; - const struct ieee80211_sta_eht_cap *eht_cap; const struct ieee80211_sta_he_cap *he_cap; struct ieee80211_link_sta *link_sta; struct ieee80211_bss_conf *link_conf; + struct cfg80211_chan_def def; + bool user_rate_valid = true; + enum nl80211_band band; + int eht_nss, nss_idx; u32 *rx_mcs, *tx_mcs; + u16 *eht_mcs_mask; + u8 max_nss = 0; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -3199,6 +3260,22 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, if (!he_cap->has_he || !eht_cap->has_eht) return; + if (WARN_ON(ath12k_mac_vif_link_chan(vif, arvif->link_id, &def))) + return; + + band = def.chan->band; + eht_mcs_mask = arvif->bitrate_mask.control[band].eht_mcs; + + iftd = ieee80211_get_sband_iftype_data(&ar->mac.sbands[band], vif->type); + if (!iftd) { + ath12k_warn(ar->ab, + "unable to access iftype_data in struct ieee80211_supported_band\n"); + return; + } + + own_eht_cap = &iftd->eht_cap; + own_eht_mcs_nss_supp = &own_eht_cap->eht_mcs_nss_supp; + arg->eht_flag = true; if ((eht_cap->eht_cap_elem.phy_cap_info[5] & @@ -3215,6 +3292,28 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, rx_mcs = arg->peer_eht_rx_mcs_set; tx_mcs = arg->peer_eht_tx_mcs_set; + eht_nss = ath12k_mac_max_eht_mcs_nss((void *)own_eht_mcs_nss_supp, + sizeof(*own_eht_mcs_nss_supp)); + if (eht_nss > link_sta->rx_nss) { + user_rate_valid = false; + for (nss_idx = (link_sta->rx_nss - 1); nss_idx >= 0; nss_idx--) { + if (eht_mcs_mask[nss_idx]) { + user_rate_valid = true; + break; + } + } + } + + if (!user_rate_valid) { + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, + "Setting eht range MCS value to peer supported nss %d for peer %pM\n", + link_sta->rx_nss, arsta->addr); + eht_mcs_mask[link_sta->rx_nss - 1] = eht_mcs_mask[eht_nss - 1]; + } + + bw_20 = &eht_cap->eht_mcs_nss_supp.only_20mhz; + bw = &eht_cap->eht_mcs_nss_supp.bw._80; + switch (link_sta->bandwidth) { case IEEE80211_STA_RX_BW_320: bw = &eht_cap->eht_mcs_nss_supp.bw._320; @@ -3223,7 +3322,8 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, bw->rx_tx_mcs11_max_nss, bw->rx_tx_mcs13_max_nss, &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_320], - &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_320]); + &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_320], + eht_mcs_mask); arg->peer_eht_mcs_count++; fallthrough; case IEEE80211_STA_RX_BW_160: @@ -3233,15 +3333,13 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, bw->rx_tx_mcs11_max_nss, bw->rx_tx_mcs13_max_nss, &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_160], - &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_160]); + &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_160], + eht_mcs_mask); arg->peer_eht_mcs_count++; fallthrough; default: - if ((he_cap->he_cap_elem.phy_cap_info[0] & - (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G | - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)) == 0) { + if (!(link_sta->he_cap.he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) { bw_20 = &eht_cap->eht_mcs_nss_supp.only_20mhz; ath12k_mac_set_eht_mcs(bw_20->rx_tx_mcs7_max_nss, @@ -3249,7 +3347,8 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, bw_20->rx_tx_mcs11_max_nss, bw_20->rx_tx_mcs13_max_nss, &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80], - &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80]); + &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80], + eht_mcs_mask); } else { bw = &eht_cap->eht_mcs_nss_supp.bw._80; ath12k_mac_set_eht_mcs(bw->rx_tx_mcs9_max_nss, @@ -3257,7 +3356,8 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, bw->rx_tx_mcs11_max_nss, bw->rx_tx_mcs13_max_nss, &rx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80], - &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80]); + &tx_mcs[WMI_EHTCAP_TXRX_MCS_NSS_IDX_80], + eht_mcs_mask); } arg->peer_eht_mcs_count++; @@ -3266,6 +3366,41 @@ static void ath12k_peer_assoc_h_eht(struct ath12k *ar, arg->punct_bitmap = ~arvif->punct_bitmap; arg->eht_disable_mcs15 = link_conf->eht_disable_mcs15; + + if (!(link_sta->he_cap.he_cap_elem.phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) { + if (bw_20->rx_tx_mcs13_max_nss) + max_nss = max(max_nss, u8_get_bits(bw_20->rx_tx_mcs13_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + if (bw_20->rx_tx_mcs11_max_nss) + max_nss = max(max_nss, u8_get_bits(bw_20->rx_tx_mcs11_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + if (bw_20->rx_tx_mcs9_max_nss) + max_nss = max(max_nss, u8_get_bits(bw_20->rx_tx_mcs9_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + if (bw_20->rx_tx_mcs7_max_nss) + max_nss = max(max_nss, u8_get_bits(bw_20->rx_tx_mcs7_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + } else { + if (bw->rx_tx_mcs13_max_nss) + max_nss = max(max_nss, u8_get_bits(bw->rx_tx_mcs13_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + if (bw->rx_tx_mcs11_max_nss) + max_nss = max(max_nss, u8_get_bits(bw->rx_tx_mcs11_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + if (bw->rx_tx_mcs9_max_nss) + max_nss = max(max_nss, u8_get_bits(bw->rx_tx_mcs9_max_nss, + IEEE80211_EHT_MCS_NSS_RX)); + } + + max_nss = min(max_nss, (uint8_t)eht_nss); + + arg->peer_nss = min(link_sta->rx_nss, max_nss); + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, + "mac eht peer %pM nss %d mcs cnt %d ru_punct_bitmap 0x%x\n", + arsta->addr, arg->peer_nss, arg->peer_eht_mcs_count, + arg->punct_bitmap); } static void ath12k_peer_assoc_h_mlo(struct ath12k_link_sta *arsta, @@ -3834,6 +3969,38 @@ static void ath12k_recalculate_mgmt_rate(struct ath12k *ar, ath12k_warn(ar->ab, "failed to set beacon tx rate %d\n", ret); } +static void ath12k_mac_bcn_tx_event(struct ath12k_link_vif *arvif) +{ + struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif); + struct ieee80211_bss_conf *link_conf; + + link_conf = ath12k_mac_get_link_bss_conf(arvif); + if (!link_conf) { + ath12k_warn(arvif->ar->ab, "failed to get link conf for vdev %u\n", + arvif->vdev_id); + return; + } + + if (link_conf->color_change_active) { + if (ieee80211_beacon_cntdwn_is_complete(vif, arvif->link_id)) { + ieee80211_color_change_finish(vif, arvif->link_id); + return; + } + + ieee80211_beacon_update_cntdwn(vif, arvif->link_id); + ath12k_mac_setup_bcn_tmpl(arvif); + } +} + +static void ath12k_mac_bcn_tx_work(struct wiphy *wiphy, struct wiphy_work *work) +{ + struct ath12k_link_vif *arvif = container_of(work, struct ath12k_link_vif, + bcn_tx_work); + + lockdep_assert_wiphy(wiphy); + ath12k_mac_bcn_tx_event(arvif); +} + static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif, struct ath12k_link_vif *arvif, int link_id) { @@ -3863,6 +4030,7 @@ static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif, INIT_LIST_HEAD(&arvif->list); INIT_DELAYED_WORK(&arvif->connection_loss_work, ath12k_mac_vif_sta_connection_loss_work); + wiphy_work_init(&arvif->bcn_tx_work, ath12k_mac_bcn_tx_work); arvif->num_stations = 0; @@ -3875,6 +4043,8 @@ static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif, sizeof(arvif->bitrate_mask.control[i].vht_mcs)); memset(arvif->bitrate_mask.control[i].he_mcs, 0xff, sizeof(arvif->bitrate_mask.control[i].he_mcs)); + memset(arvif->bitrate_mask.control[i].eht_mcs, 0xff, + sizeof(arvif->bitrate_mask.control[i].eht_mcs)); } /* Handle MLO related assignments */ @@ -3900,6 +4070,7 @@ static void ath12k_mac_remove_link_interface(struct ieee80211_hw *hw, lockdep_assert_wiphy(ah->hw->wiphy); cancel_delayed_work_sync(&arvif->connection_loss_work); + wiphy_work_cancel(ath12k_ar_to_hw(ar)->wiphy, &arvif->bcn_tx_work); ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac remove link interface (vdev %d link id %d)", arvif->vdev_id, arvif->link_id); @@ -4202,6 +4373,30 @@ static bool ath12k_mac_supports_tpc(struct ath12k *ar, struct ath12k_vif *ahvif, chandef->chan->band == NL80211_BAND_6GHZ; } +static void ath12k_wmi_vdev_params_up(struct ath12k *ar, + struct ath12k_link_vif *arvif, + struct ath12k_link_vif *tx_arvif, + struct ieee80211_bss_conf *info, u16 aid) +{ + struct ath12k_wmi_vdev_up_params params = { + .vdev_id = arvif->vdev_id, + .aid = aid, + .bssid = arvif->bssid + }; + int ret; + + if (tx_arvif) { + params.tx_bssid = tx_arvif->bssid; + params.nontx_profile_idx = info->bssid_index; + params.nontx_profile_cnt = 1 << info->bssid_indicator; + } + + ret = ath12k_wmi_vdev_up(arvif->ar, ¶ms); + if (ret) + ath12k_warn(ar->ab, "failed to bring vdev up %d: %d\n", + arvif->vdev_id, ret); +} + static void ath12k_mac_bss_info_changed(struct ath12k *ar, struct ath12k_link_vif *arvif, struct ieee80211_bss_conf *info, @@ -4210,6 +4405,7 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, struct ath12k_vif *ahvif = arvif->ahvif; struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif); struct ieee80211_vif_cfg *vif_cfg = &vif->cfg; + struct ath12k_link_vif *tx_arvif; struct cfg80211_chan_def def; u32 param_id, param_value; enum nl80211_band band; @@ -4218,9 +4414,9 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, u32 preamble; u16 hw_value; u16 bitrate; - int ret; u8 rateidx; u32 rate; + int ret; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -4253,12 +4449,41 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, "Set burst beacon mode for VDEV: %d\n", arvif->vdev_id); + /* In MBSSID case, need to install transmitting VIF's template first */ + ret = ath12k_mac_setup_bcn_tmpl(arvif); if (ret) ath12k_warn(ar->ab, "failed to update bcn template: %d\n", ret); + + if (!arvif->is_csa_in_progress) + goto skip_vdev_up; + + tx_arvif = ath12k_mac_get_tx_arvif(arvif, info); + if (tx_arvif && arvif != tx_arvif && tx_arvif->is_csa_in_progress) + /* skip non tx vif's */ + goto skip_vdev_up; + + ath12k_wmi_vdev_params_up(ar, arvif, tx_arvif, info, ahvif->aid); + + arvif->is_csa_in_progress = false; + + if (tx_arvif && arvif == tx_arvif) { + struct ath12k_link_vif *arvif_itr; + + list_for_each_entry(arvif_itr, &ar->arvifs, list) { + if (!arvif_itr->is_csa_in_progress) + continue; + + ath12k_wmi_vdev_params_up(ar, arvif, tx_arvif, + info, ahvif->aid); + arvif_itr->is_csa_in_progress = false; + } + } } +skip_vdev_up: + if (changed & (BSS_CHANGED_BEACON_INFO | BSS_CHANGED_BEACON)) { arvif->dtim_period = info->dtim_period; @@ -4475,8 +4700,25 @@ static void ath12k_mac_bss_info_changed(struct ath12k *ar, ATH12K_BSS_COLOR_AP_PERIODS, info->he_bss_color.enabled); if (ret) - ath12k_warn(ar->ab, "failed to set bss color collision on vdev %i: %d\n", + ath12k_warn(ar->ab, "failed to set bss color collision on vdev %u: %d\n", arvif->vdev_id, ret); + + param_id = WMI_VDEV_PARAM_BSS_COLOR; + if (info->he_bss_color.enabled) + param_value = info->he_bss_color.color << + IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET; + else + param_value = IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED; + + ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, + param_id, + param_value); + if (ret) + ath12k_warn(ar->ab, "failed to set bss color param on vdev %u: %d\n", + arvif->vdev_id, ret); + else + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "bss color param 0x%x set on vdev %u\n", + param_value, arvif->vdev_id); } else if (vif->type == NL80211_IFTYPE_STATION) { ret = ath12k_wmi_send_bss_color_change_enable_cmd(ar, arvif->vdev_id, @@ -4837,8 +5079,6 @@ int ath12k_mac_get_fw_stats(struct ath12k *ar, if (ah->state != ATH12K_HW_STATE_ON) return -ENETDOWN; - ath12k_fw_stats_reset(ar); - reinit_completion(&ar->fw_stats_complete); reinit_completion(&ar->fw_stats_done); @@ -4936,6 +5176,7 @@ static int ath12k_mac_op_get_txpower(struct ieee80211_hw *hw, ar->chan_tx_pwr = pdev->chan_tx_power / 2; spin_unlock_bh(&ar->data_lock); ar->last_tx_power_update = jiffies; + ath12k_fw_stats_reset(ar); send_tx_power: *dbm = ar->chan_tx_pwr; @@ -5059,7 +5300,8 @@ static int ath12k_mac_initiate_hw_scan(struct ieee80211_hw *hw, ret = ath12k_mac_vdev_create(ar, arvif); if (ret) { ath12k_warn(ar->ab, "unable to create scan vdev %d\n", ret); - return -EINVAL; + ath12k_mac_unassign_link_vif(arvif); + return ret; } } @@ -5718,6 +5960,20 @@ ath12k_mac_bitrate_mask_num_he_rates(struct ath12k *ar, return num_rates; } +static int +ath12k_mac_bitrate_mask_num_eht_rates(struct ath12k *ar, + enum nl80211_band band, + const struct cfg80211_bitrate_mask *mask) +{ + int num_rates = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(mask->control[band].eht_mcs); i++) + num_rates += hweight16(mask->control[band].eht_mcs[i]); + + return num_rates; +} + static int ath12k_mac_set_peer_vht_fixed_rate(struct ath12k_link_vif *arvif, struct ath12k_link_sta *arsta, @@ -5818,6 +6074,65 @@ ath12k_mac_set_peer_he_fixed_rate(struct ath12k_link_vif *arvif, return ret; } +static int +ath12k_mac_set_peer_eht_fixed_rate(struct ath12k_link_vif *arvif, + struct ath12k_link_sta *arsta, + const struct cfg80211_bitrate_mask *mask, + enum nl80211_band band) +{ + struct ath12k_sta *ahsta = arsta->ahsta; + struct ath12k *ar = arvif->ar; + struct ieee80211_sta *sta; + struct ieee80211_link_sta *link_sta; + u8 eht_rate, nss = 0; + u32 rate_code; + int ret, i; + + lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); + + sta = ath12k_ahsta_to_sta(ahsta); + + for (i = 0; i < ARRAY_SIZE(mask->control[band].eht_mcs); i++) { + if (hweight16(mask->control[band].eht_mcs[i]) == 1) { + nss = i + 1; + eht_rate = ffs(mask->control[band].eht_mcs[i]) - 1; + } + } + + if (!nss) { + ath12k_warn(ar->ab, "No single EHT Fixed rate found to set for %pM\n", + arsta->addr); + return -EINVAL; + } + + /* Avoid updating invalid nss as fixed rate*/ + link_sta = ath12k_mac_get_link_sta(arsta); + if (!link_sta || nss > link_sta->rx_nss) { + ath12k_warn(ar->ab, + "unable to access link sta for sta %pM link %u or fixed nss of %u is not supported by sta\n", + sta->addr, arsta->link_id, nss); + return -EINVAL; + } + + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, + "Setting Fixed EHT Rate for peer %pM. Device will not switch to any other selected rates\n", + arsta->addr); + + rate_code = ATH12K_HW_RATE_CODE(eht_rate, nss - 1, + WMI_RATE_PREAMBLE_EHT); + + ret = ath12k_wmi_set_peer_param(ar, arsta->addr, + arvif->vdev_id, + WMI_PEER_PARAM_FIXED_RATE, + rate_code); + if (ret) + ath12k_warn(ar->ab, + "failed to update STA %pM Fixed Rate %d: %d\n", + arsta->addr, rate_code, ret); + + return ret; +} + static int ath12k_mac_station_assoc(struct ath12k *ar, struct ath12k_link_vif *arvif, struct ath12k_link_sta *arsta, @@ -5830,7 +6145,7 @@ static int ath12k_mac_station_assoc(struct ath12k *ar, struct cfg80211_chan_def def; enum nl80211_band band; struct cfg80211_bitrate_mask *mask; - u8 num_vht_rates, num_he_rates; + u8 num_vht_rates, num_he_rates, num_eht_rates; u8 link_id = arvif->link_id; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -5873,10 +6188,11 @@ static int ath12k_mac_station_assoc(struct ath12k *ar, num_vht_rates = ath12k_mac_bitrate_mask_num_vht_rates(ar, band, mask); num_he_rates = ath12k_mac_bitrate_mask_num_he_rates(ar, band, mask); + num_eht_rates = ath12k_mac_bitrate_mask_num_eht_rates(ar, band, mask); - /* If single VHT/HE rate is configured (by set_bitrate_mask()), - * peer_assoc will disable VHT/HE. This is now enabled by a peer specific - * fixed param. + /* If single VHT/HE/EHT rate is configured (by set_bitrate_mask()), + * peer_assoc will disable VHT/HE/EHT. This is now enabled by a peer + * specific fixed param. * Note that all other rates and NSS will be disabled for this peer. */ link_sta = ath12k_mac_get_link_sta(arsta); @@ -5896,6 +6212,10 @@ static int ath12k_mac_station_assoc(struct ath12k *ar, ret = ath12k_mac_set_peer_he_fixed_rate(arvif, arsta, mask, band); if (ret) return ret; + } else if (link_sta->eht_cap.has_eht && num_eht_rates == 1) { + ret = ath12k_mac_set_peer_eht_fixed_rate(arvif, arsta, mask, band); + if (ret) + return ret; } /* Re-assoc is run only to update supported rates for given station. It @@ -5958,8 +6278,9 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) const u8 *ht_mcs_mask; const u16 *vht_mcs_mask; const u16 *he_mcs_mask; + const u16 *eht_mcs_mask; u32 changed, bw, nss, mac_nss, smps, bw_prev; - int err, num_vht_rates, num_he_rates; + int err, num_vht_rates, num_he_rates, num_eht_rates; const struct cfg80211_bitrate_mask *mask; enum wmi_phy_mode peer_phymode; struct ath12k_link_sta *arsta; @@ -5980,6 +6301,7 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) ht_mcs_mask = arvif->bitrate_mask.control[band].ht_mcs; vht_mcs_mask = arvif->bitrate_mask.control[band].vht_mcs; he_mcs_mask = arvif->bitrate_mask.control[band].he_mcs; + eht_mcs_mask = arvif->bitrate_mask.control[band].eht_mcs; spin_lock_bh(&ar->data_lock); @@ -5997,6 +6319,7 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) mac_nss = max3(ath12k_mac_max_ht_nss(ht_mcs_mask), ath12k_mac_max_vht_nss(vht_mcs_mask), ath12k_mac_max_he_nss(he_mcs_mask)); + mac_nss = max(mac_nss, ath12k_mac_max_eht_nss(eht_mcs_mask)); nss = min(nss, mac_nss); struct ath12k_wmi_peer_assoc_arg *peer_arg __free(kfree) = @@ -6082,6 +6405,8 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) mask); num_he_rates = ath12k_mac_bitrate_mask_num_he_rates(ar, band, mask); + num_eht_rates = ath12k_mac_bitrate_mask_num_eht_rates(ar, band, + mask); /* Peer_assoc_prepare will reject vht rates in * bitrate_mask if its not available in range format and @@ -6106,9 +6431,18 @@ static void ath12k_sta_rc_update_wk(struct wiphy *wiphy, struct wiphy_work *wk) band); } else if (link_sta->he_cap.has_he && num_he_rates == 1) { ath12k_mac_set_peer_he_fixed_rate(arvif, arsta, mask, band); + } else if (link_sta->eht_cap.has_eht && num_eht_rates == 1) { + err = ath12k_mac_set_peer_eht_fixed_rate(arvif, arsta, + mask, band); + if (err) { + ath12k_warn(ar->ab, + "failed to set peer EHT fixed rate for STA %pM ret %d\n", + arsta->addr, err); + return; + } } else { - /* If the peer is non-VHT/HE or no fixed VHT/HE rate - * is provided in the new bitrate mask we set the + /* If the peer is non-VHT/HE/EHT or no fixed VHT/HE/EHT + * rate is provided in the new bitrate mask we set the * other rates using peer_assoc command. Also clear * the peer fixed rate settings as it has higher proprity * than peer assoc @@ -9687,6 +10021,12 @@ int ath12k_mac_vdev_create(struct ath12k *ar, struct ath12k_link_vif *arvif) if (vif->type == NL80211_IFTYPE_MONITOR && ar->monitor_vdev_created) return -EINVAL; + if (ar->num_created_vdevs >= TARGET_NUM_VDEVS(ab)) { + ath12k_warn(ab, "failed to create vdev, reached max vdev limit %d\n", + TARGET_NUM_VDEVS(ab)); + return -ENOSPC; + } + link_id = arvif->link_id; if (link_id < IEEE80211_MLD_MAX_NUM_LINKS) { @@ -10046,12 +10386,6 @@ static struct ath12k *ath12k_mac_assign_vif_to_vdev(struct ieee80211_hw *hw, if (arvif->is_created) goto flush; - if (ar->num_created_vdevs > (TARGET_NUM_VDEVS(ab) - 1)) { - ath12k_warn(ab, "failed to create vdev, reached max vdev limit %d\n", - TARGET_NUM_VDEVS(ab)); - goto unlock; - } - ret = ath12k_mac_vdev_create(ar, arvif); if (ret) { ath12k_warn(ab, "failed to create vdev %pM ret %d", vif->addr, ret); @@ -10852,9 +11186,9 @@ ath12k_mac_update_vif_chan(struct ath12k *ar, int n_vifs) { struct ath12k_wmi_vdev_up_params params = {}; - struct ath12k_link_vif *arvif; struct ieee80211_bss_conf *link_conf; struct ath12k_base *ab = ar->ab; + struct ath12k_link_vif *arvif; struct ieee80211_vif *vif; struct ath12k_vif *ahvif; u8 link_id; @@ -10915,6 +11249,28 @@ ath12k_mac_update_vif_chan(struct ath12k *ar, continue; } + ret = ath12k_mac_update_peer_puncturing_width(arvif->ar, arvif, + vifs[i].new_ctx->def); + if (ret) { + ath12k_warn(ar->ab, + "failed to update puncturing bitmap %02x and width %d: %d\n", + vifs[i].new_ctx->def.punctured, + vifs[i].new_ctx->def.width, ret); + continue; + } + + /* Defer VDEV bring-up during CSA to avoid installing stale + * beacon templates. The beacon content is updated only + * after CSA finalize, so we mark CSA in progress and skip + * VDEV_UP for now. It will be handled later in + * bss_info_changed(). + */ + if (link_conf->csa_active && + arvif->ahvif->vdev_type == WMI_VDEV_TYPE_AP) { + arvif->is_csa_in_progress = true; + continue; + } + ret = ath12k_mac_setup_bcn_tmpl(arvif); if (ret) ath12k_warn(ab, "failed to update bcn tmpl during csa: %d\n", @@ -10935,16 +11291,6 @@ ath12k_mac_update_vif_chan(struct ath12k *ar, arvif->vdev_id, ret); continue; } - - ret = ath12k_mac_update_peer_puncturing_width(arvif->ar, arvif, - vifs[i].new_ctx->def); - if (ret) { - ath12k_warn(ar->ab, - "failed to update puncturing bitmap %02x and width %d: %d\n", - vifs[i].new_ctx->def.punctured, - vifs[i].new_ctx->def.width, ret); - continue; - } } /* Restart the internal monitor vdev on new channel */ @@ -11849,6 +12195,9 @@ ath12k_mac_has_single_legacy_rate(struct ath12k *ar, if (ath12k_mac_bitrate_mask_num_he_rates(ar, band, mask)) return false; + if (ath12k_mac_bitrate_mask_num_eht_rates(ar, band, mask)) + return false; + return num_rates == 1; } @@ -11871,11 +12220,15 @@ ath12k_mac_bitrate_mask_get_single_nss(struct ath12k *ar, { struct ieee80211_supported_band *sband = &ar->mac.sbands[band]; u16 vht_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map); + const struct ieee80211_sband_iftype_data *data; const struct ieee80211_sta_he_cap *he_cap; u16 he_mcs_map = 0; + u16 eht_mcs_map = 0; u8 ht_nss_mask = 0; u8 vht_nss_mask = 0; u8 he_nss_mask = 0; + u8 eht_nss_mask = 0; + u8 mcs_nss_len; int i; /* No need to consider legacy here. Basic rates are always present @@ -11919,7 +12272,60 @@ ath12k_mac_bitrate_mask_get_single_nss(struct ath12k *ar, return false; } - if (ht_nss_mask != vht_nss_mask || ht_nss_mask != he_nss_mask) + data = ieee80211_get_sband_iftype_data(sband, vif->type); + + mcs_nss_len = ieee80211_eht_mcs_nss_size(&data->he_cap.he_cap_elem, + &data->eht_cap.eht_cap_elem, + false); + if (mcs_nss_len == 4) { + /* 20 MHz only STA case */ + const struct ieee80211_eht_mcs_nss_supp_20mhz_only *eht_mcs_nss = + &data->eht_cap.eht_mcs_nss_supp.only_20mhz; + if (eht_mcs_nss->rx_tx_mcs13_max_nss) + eht_mcs_map = 0x1fff; + else if (eht_mcs_nss->rx_tx_mcs11_max_nss) + eht_mcs_map = 0x07ff; + else if (eht_mcs_nss->rx_tx_mcs9_max_nss) + eht_mcs_map = 0x01ff; + else + eht_mcs_map = 0x007f; + } else { + const struct ieee80211_eht_mcs_nss_supp_bw *eht_mcs_nss; + + switch (mcs_nss_len) { + case 9: + eht_mcs_nss = &data->eht_cap.eht_mcs_nss_supp.bw._320; + break; + case 6: + eht_mcs_nss = &data->eht_cap.eht_mcs_nss_supp.bw._160; + break; + case 3: + eht_mcs_nss = &data->eht_cap.eht_mcs_nss_supp.bw._80; + break; + default: + return false; + } + + if (eht_mcs_nss->rx_tx_mcs13_max_nss) + eht_mcs_map = 0x1fff; + else if (eht_mcs_nss->rx_tx_mcs11_max_nss) + eht_mcs_map = 0x7ff; + else + eht_mcs_map = 0x1ff; + } + + for (i = 0; i < ARRAY_SIZE(mask->control[band].eht_mcs); i++) { + if (mask->control[band].eht_mcs[i] == 0) + continue; + + if (mask->control[band].eht_mcs[i] < eht_mcs_map) + eht_nss_mask |= BIT(i); + else + return false; + } + + if (ht_nss_mask != vht_nss_mask || ht_nss_mask != he_nss_mask || + ht_nss_mask != eht_nss_mask) return false; if (ht_nss_mask == 0) @@ -11967,7 +12373,8 @@ ath12k_mac_get_single_legacy_rate(struct ath12k *ar, } static int -ath12k_mac_set_fixed_rate_gi_ltf(struct ath12k_link_vif *arvif, u8 he_gi, u8 he_ltf) +ath12k_mac_set_fixed_rate_gi_ltf(struct ath12k_link_vif *arvif, u8 gi, u8 ltf, + u32 param) { struct ath12k *ar = arvif->ar; int ret; @@ -11975,47 +12382,54 @@ ath12k_mac_set_fixed_rate_gi_ltf(struct ath12k_link_vif *arvif, u8 he_gi, u8 he_ lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); /* 0.8 = 0, 1.6 = 2 and 3.2 = 3. */ - if (he_gi && he_gi != 0xFF) - he_gi += 1; + if (gi && gi != 0xFF) + gi += 1; ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, - WMI_VDEV_PARAM_SGI, he_gi); + WMI_VDEV_PARAM_SGI, gi); if (ret) { - ath12k_warn(ar->ab, "failed to set HE GI:%d, error:%d\n", - he_gi, ret); + ath12k_warn(ar->ab, "failed to set GI:%d, error:%d\n", + gi, ret); return ret; } - /* start from 1 */ - if (he_ltf != 0xFF) - he_ltf += 1; + + if (param == WMI_VDEV_PARAM_HE_LTF) { + /* HE values start from 1 */ + if (ltf != 0xFF) + ltf += 1; + } else { + /* EHT values start from 5 */ + if (ltf != 0xFF) + ltf += 4; + } ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, - WMI_VDEV_PARAM_HE_LTF, he_ltf); + param, ltf); if (ret) { - ath12k_warn(ar->ab, "failed to set HE LTF:%d, error:%d\n", - he_ltf, ret); + ath12k_warn(ar->ab, "failed to set LTF:%d, error:%d\n", + ltf, ret); return ret; } return 0; } static int -ath12k_mac_set_auto_rate_gi_ltf(struct ath12k_link_vif *arvif, u16 he_gi, u8 he_ltf) +ath12k_mac_set_auto_rate_gi_ltf(struct ath12k_link_vif *arvif, u16 gi, u8 ltf) { struct ath12k *ar = arvif->ar; int ret; - u32 he_ar_gi_ltf; + u32 ar_gi_ltf; - if (he_gi != 0xFF) { - switch (he_gi) { - case NL80211_RATE_INFO_HE_GI_0_8: - he_gi = WMI_AUTORATE_800NS_GI; + if (gi != 0xFF) { + switch (gi) { + case ATH12K_RATE_INFO_GI_0_8: + gi = WMI_AUTORATE_800NS_GI; break; - case NL80211_RATE_INFO_HE_GI_1_6: - he_gi = WMI_AUTORATE_1600NS_GI; + case ATH12K_RATE_INFO_GI_1_6: + gi = WMI_AUTORATE_1600NS_GI; break; - case NL80211_RATE_INFO_HE_GI_3_2: - he_gi = WMI_AUTORATE_3200NS_GI; + case ATH12K_RATE_INFO_GI_3_2: + gi = WMI_AUTORATE_3200NS_GI; break; default: ath12k_warn(ar->ab, "Invalid GI\n"); @@ -12023,16 +12437,16 @@ ath12k_mac_set_auto_rate_gi_ltf(struct ath12k_link_vif *arvif, u16 he_gi, u8 he_ } } - if (he_ltf != 0xFF) { - switch (he_ltf) { - case NL80211_RATE_INFO_HE_1XLTF: - he_ltf = WMI_HE_AUTORATE_LTF_1X; + if (ltf != 0xFF) { + switch (ltf) { + case ATH12K_RATE_INFO_1XLTF: + ltf = WMI_AUTORATE_LTF_1X; break; - case NL80211_RATE_INFO_HE_2XLTF: - he_ltf = WMI_HE_AUTORATE_LTF_2X; + case ATH12K_RATE_INFO_2XLTF: + ltf = WMI_AUTORATE_LTF_2X; break; - case NL80211_RATE_INFO_HE_4XLTF: - he_ltf = WMI_HE_AUTORATE_LTF_4X; + case ATH12K_RATE_INFO_4XLTF: + ltf = WMI_AUTORATE_LTF_4X; break; default: ath12k_warn(ar->ab, "Invalid LTF\n"); @@ -12040,15 +12454,15 @@ ath12k_mac_set_auto_rate_gi_ltf(struct ath12k_link_vif *arvif, u16 he_gi, u8 he_ } } - he_ar_gi_ltf = he_gi | he_ltf; + ar_gi_ltf = gi | ltf; ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, WMI_VDEV_PARAM_AUTORATE_MISC_CFG, - he_ar_gi_ltf); + ar_gi_ltf); if (ret) { ath12k_warn(ar->ab, - "failed to set HE autorate GI:%u, LTF:%u params, error:%d\n", - he_gi, he_ltf, ret); + "failed to set autorate GI:%u, LTF:%u params, error:%d\n", + gi, ltf, ret); return ret; } @@ -12069,14 +12483,16 @@ static u32 ath12k_mac_nlgi_to_wmigi(enum nl80211_txrate_gi gi) static int ath12k_mac_set_rate_params(struct ath12k_link_vif *arvif, u32 rate, u8 nss, u8 sgi, u8 ldpc, - u8 he_gi, u8 he_ltf, bool he_fixed_rate) + u8 he_gi, u8 he_ltf, bool he_fixed_rate, + u8 eht_gi, u8 eht_ltf, + bool eht_fixed_rate) { struct ieee80211_bss_conf *link_conf; struct ath12k *ar = arvif->ar; + bool he_support, eht_support, gi_ltf_set = false; u32 vdev_param; u32 param_value; int ret; - bool he_support; lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy); @@ -12085,6 +12501,7 @@ static int ath12k_mac_set_rate_params(struct ath12k_link_vif *arvif, return -EINVAL; he_support = link_conf->he_support; + eht_support = link_conf->eht_support; ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac set rate params vdev %i rate 0x%02x nss 0x%02x sgi 0x%02x ldpc 0x%02x\n", @@ -12094,7 +12511,11 @@ static int ath12k_mac_set_rate_params(struct ath12k_link_vif *arvif, "he_gi 0x%02x he_ltf 0x%02x he_fixed_rate %d\n", he_gi, he_ltf, he_fixed_rate); - if (!he_support) { + ath12k_dbg(ar->ab, ATH12K_DBG_MAC, + "eht_gi 0x%02x eht_ltf 0x%02x eht_fixed_rate %d\n", + eht_gi, eht_ltf, eht_fixed_rate); + + if (!he_support && !eht_support) { vdev_param = WMI_VDEV_PARAM_FIXED_RATE; ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, vdev_param, rate); @@ -12123,14 +12544,34 @@ static int ath12k_mac_set_rate_params(struct ath12k_link_vif *arvif, return ret; } + if (eht_support) { + if (eht_fixed_rate) + ret = ath12k_mac_set_fixed_rate_gi_ltf(arvif, eht_gi, eht_ltf, + WMI_VDEV_PARAM_EHT_LTF); + else + ret = ath12k_mac_set_auto_rate_gi_ltf(arvif, eht_gi, eht_ltf); + + if (ret) { + ath12k_warn(ar->ab, + "failed to set EHT LTF/GI params %d/%d: %d\n", + eht_gi, eht_ltf, ret); + return ret; + } + gi_ltf_set = true; + } + if (he_support) { if (he_fixed_rate) - ret = ath12k_mac_set_fixed_rate_gi_ltf(arvif, he_gi, he_ltf); + ret = ath12k_mac_set_fixed_rate_gi_ltf(arvif, he_gi, he_ltf, + WMI_VDEV_PARAM_HE_LTF); else ret = ath12k_mac_set_auto_rate_gi_ltf(arvif, he_gi, he_ltf); if (ret) return ret; - } else { + gi_ltf_set = true; + } + + if (!gi_ltf_set) { vdev_param = WMI_VDEV_PARAM_SGI; param_value = ath12k_mac_nlgi_to_wmigi(sgi); ret = ath12k_wmi_vdev_set_param_cmd(ar, arvif->vdev_id, @@ -12195,6 +12636,38 @@ ath12k_mac_he_mcs_range_present(struct ath12k *ar, return true; } +static bool +ath12k_mac_eht_mcs_range_present(struct ath12k *ar, + enum nl80211_band band, + const struct cfg80211_bitrate_mask *mask) +{ + u16 eht_mcs; + int i; + + for (i = 0; i < NL80211_EHT_NSS_MAX; i++) { + eht_mcs = mask->control[band].eht_mcs[i]; + + switch (eht_mcs) { + case 0: + case BIT(8) - 1: + case BIT(10) - 1: + case BIT(12) - 1: + case BIT(14) - 1: + break; + case BIT(15) - 1: + case BIT(16) - 1: + case BIT(16) - BIT(14) - 1: + if (i != 0) + return false; + break; + default: + return false; + } + } + + return true; +} + static void ath12k_mac_set_bitrate_mask_iter(void *data, struct ieee80211_sta *sta) { @@ -12249,15 +12722,16 @@ ath12k_mac_validate_fixed_rate_settings(struct ath12k *ar, enum nl80211_band ban const struct cfg80211_bitrate_mask *mask, unsigned int link_id) { - bool he_fixed_rate = false, vht_fixed_rate = false; - const u16 *vht_mcs_mask, *he_mcs_mask; + bool eht_fixed_rate = false, he_fixed_rate = false, vht_fixed_rate = false; + const u16 *vht_mcs_mask, *he_mcs_mask, *eht_mcs_mask; struct ieee80211_link_sta *link_sta; struct ath12k_peer *peer, *tmp; - u8 vht_nss, he_nss; + u8 vht_nss, he_nss, eht_nss; int ret = true; vht_mcs_mask = mask->control[band].vht_mcs; he_mcs_mask = mask->control[band].he_mcs; + eht_mcs_mask = mask->control[band].eht_mcs; if (ath12k_mac_bitrate_mask_num_vht_rates(ar, band, mask) == 1) vht_fixed_rate = true; @@ -12265,11 +12739,15 @@ ath12k_mac_validate_fixed_rate_settings(struct ath12k *ar, enum nl80211_band ban if (ath12k_mac_bitrate_mask_num_he_rates(ar, band, mask) == 1) he_fixed_rate = true; - if (!vht_fixed_rate && !he_fixed_rate) + if (ath12k_mac_bitrate_mask_num_eht_rates(ar, band, mask) == 1) + eht_fixed_rate = true; + + if (!vht_fixed_rate && !he_fixed_rate && !eht_fixed_rate) return true; vht_nss = ath12k_mac_max_vht_nss(vht_mcs_mask); he_nss = ath12k_mac_max_he_nss(he_mcs_mask); + eht_nss = ath12k_mac_max_eht_nss(eht_mcs_mask); rcu_read_lock(); spin_lock_bh(&ar->ab->base_lock); @@ -12291,6 +12769,11 @@ ath12k_mac_validate_fixed_rate_settings(struct ath12k *ar, enum nl80211_band ban ret = false; goto exit; } + if (eht_fixed_rate && (!link_sta->eht_cap.has_eht || + link_sta->rx_nss < eht_nss)) { + ret = false; + goto exit; + } } } exit: @@ -12312,8 +12795,10 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, const u8 *ht_mcs_mask; const u16 *vht_mcs_mask; const u16 *he_mcs_mask; + const u16 *eht_mcs_mask; u8 he_ltf = 0; u8 he_gi = 0; + u8 eht_ltf = 0, eht_gi = 0; u32 rate; u8 nss, mac_nss; u8 sgi; @@ -12322,6 +12807,7 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, int ret; int num_rates; bool he_fixed_rate = false; + bool eht_fixed_rate = false; lockdep_assert_wiphy(hw->wiphy); @@ -12337,6 +12823,7 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, ht_mcs_mask = mask->control[band].ht_mcs; vht_mcs_mask = mask->control[band].vht_mcs; he_mcs_mask = mask->control[band].he_mcs; + eht_mcs_mask = mask->control[band].eht_mcs; ldpc = !!(ar->ht_cap_info & WMI_HT_CAP_LDPC); sgi = mask->control[band].gi; @@ -12348,6 +12835,9 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, he_gi = mask->control[band].he_gi; he_ltf = mask->control[band].he_ltf; + eht_gi = mask->control[band].eht_gi; + eht_ltf = mask->control[band].eht_ltf; + /* mac80211 doesn't support sending a fixed HT/VHT MCS alone, rather it * requires passing at least one of used basic rates along with them. * Fixed rate setting across different preambles(legacy, HT, VHT) is @@ -12385,9 +12875,10 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, ath12k_warn(ar->ab, "failed to update fixed rate settings due to mcs/nss incompatibility\n"); - mac_nss = max3(ath12k_mac_max_ht_nss(ht_mcs_mask), - ath12k_mac_max_vht_nss(vht_mcs_mask), - ath12k_mac_max_he_nss(he_mcs_mask)); + mac_nss = max(max3(ath12k_mac_max_ht_nss(ht_mcs_mask), + ath12k_mac_max_vht_nss(vht_mcs_mask), + ath12k_mac_max_he_nss(he_mcs_mask)), + ath12k_mac_max_eht_nss(eht_mcs_mask)); nss = min_t(u32, ar->num_tx_chains, mac_nss); /* If multiple rates across different preambles are given @@ -12435,6 +12926,20 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, ret = -EINVAL; goto out; } + + num_rates = ath12k_mac_bitrate_mask_num_eht_rates(ar, band, + mask); + if (num_rates == 1) + eht_fixed_rate = true; + + if (!ath12k_mac_eht_mcs_range_present(ar, band, mask) && + num_rates > 1) { + ath12k_warn(ar->ab, + "Setting more than one EHT MCS Value in bitrate mask not supported\n"); + ret = -EINVAL; + goto out; + } + ieee80211_iterate_stations_mtx(hw, ath12k_mac_disable_peer_fixed_rate, arvif); @@ -12446,7 +12951,8 @@ ath12k_mac_op_set_bitrate_mask(struct ieee80211_hw *hw, } ret = ath12k_mac_set_rate_params(arvif, rate, nss, sgi, ldpc, he_gi, - he_ltf, he_fixed_rate); + he_ltf, he_fixed_rate, eht_gi, eht_ltf, + eht_fixed_rate); if (ret) { ath12k_warn(ar->ab, "failed to set rate params on vdev %i: %d\n", arvif->vdev_id, ret); @@ -12701,14 +13207,18 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw, if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA && - !(ath12k_mac_get_fw_stats(ar, ¶ms))) + !(ath12k_mac_get_fw_stats(ar, ¶ms))) { signal = arsta->rssi_beacon; + ath12k_fw_stats_reset(ar); + } params.stats_id = WMI_REQUEST_RSSI_PER_CHAIN_STAT; if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA && - !(ath12k_mac_get_fw_stats(ar, ¶ms))) + !(ath12k_mac_get_fw_stats(ar, ¶ms))) { ath12k_mac_put_chain_rssi(sinfo, arsta); + ath12k_fw_stats_reset(ar); + } spin_lock_bh(&ar->data_lock); noise_floor = ath12k_pdev_get_noise_floor(ar); @@ -12792,8 +13302,10 @@ static void ath12k_mac_op_link_sta_statistics(struct ieee80211_hw *hw, if (!signal && ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA && - !(ath12k_mac_get_fw_stats(ar, ¶ms))) + !(ath12k_mac_get_fw_stats(ar, ¶ms))) { signal = arsta->rssi_beacon; + ath12k_fw_stats_reset(ar); + } if (signal) { link_sinfo->signal = @@ -12895,6 +13407,7 @@ static int ath12k_mac_op_remain_on_channel(struct ieee80211_hw *hw, if (ret) { ath12k_warn(ar->ab, "unable to create scan vdev for roc: %d\n", ret); + ath12k_mac_unassign_link_vif(arvif); return ret; } } @@ -13894,6 +14407,11 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah) wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR); wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_ACK_SIGNAL_SUPPORT); + if (test_bit(WMI_TLV_SERVICE_BSS_COLOR_OFFLOAD, + ab->wmi_ab.svc_map)) { + wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BSS_COLOR); + ieee80211_hw_set(hw, DETECTS_COLOR_COLLISION); + } wiphy->cipher_suites = cipher_suites; wiphy->n_cipher_suites = ARRAY_SIZE(cipher_suites); diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h index c05af40bd7a20..1f689e367c8a1 100644 --- a/drivers/net/wireless/ath/ath12k/mac.h +++ b/drivers/net/wireless/ath/ath12k/mac.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef ATH12K_MAC_H @@ -84,6 +84,18 @@ enum ath12k_supported_bw { ATH12K_BW_320 = 4, }; +enum ath12k_gi { + ATH12K_RATE_INFO_GI_0_8, + ATH12K_RATE_INFO_GI_1_6, + ATH12K_RATE_INFO_GI_3_2, +}; + +enum ath12k_ltf { + ATH12K_RATE_INFO_1XLTF, + ATH12K_RATE_INFO_2XLTF, + ATH12K_RATE_INFO_4XLTF, +}; + struct ath12k_mac_get_any_chanctx_conf_arg { struct ath12k *ar; struct ieee80211_chanctx_conf *chanctx_conf; diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c index c729d5526c753..a12c8379cb466 100644 --- a/drivers/net/wireless/ath/ath12k/pci.c +++ b/drivers/net/wireless/ath/ath12k/pci.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -218,6 +218,19 @@ static inline bool ath12k_pci_is_offset_within_mhi_region(u32 offset) return (offset >= PCI_MHIREGLEN_REG && offset <= PCI_MHI_REGION_END); } +static void ath12k_pci_restore_window(struct ath12k_base *ab) +{ + struct ath12k_pci *ab_pci = ath12k_pci_priv(ab); + + spin_lock_bh(&ab_pci->window_lock); + + iowrite32(WINDOW_ENABLE_BIT | ab_pci->register_window, + ab->mem + WINDOW_REG_ADDRESS); + ioread32(ab->mem + WINDOW_REG_ADDRESS); + + spin_unlock_bh(&ab_pci->window_lock); +} + static void ath12k_pci_soc_global_reset(struct ath12k_base *ab) { u32 val, delay; @@ -242,6 +255,11 @@ static void ath12k_pci_soc_global_reset(struct ath12k_base *ab) val = ath12k_pci_read32(ab, PCIE_SOC_GLOBAL_RESET); if (val == 0xffffffff) ath12k_warn(ab, "link down error during global reset\n"); + + /* Restore window register as its content is cleared during + * hardware global reset, such that it aligns with host cache. + */ + ath12k_pci_restore_window(ab); } static void ath12k_pci_clear_dbg_registers(struct ath12k_base *ab) @@ -1871,3 +1889,7 @@ void ath12k_pci_exit(void) { pci_unregister_driver(&ath12k_pci_driver); } + +/* firmware files */ +MODULE_FIRMWARE(ATH12K_FW_DIR "/QCN9274/hw2.0/*"); +MODULE_FIRMWARE(ATH12K_FW_DIR "/WCN7850/hw2.0/*"); diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c index 36325e62aa242..b7c48b6706dfc 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.c +++ b/drivers/net/wireless/ath/ath12k/qmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include @@ -3114,9 +3114,10 @@ static void ath12k_qmi_m3_free(struct ath12k_base *ab) if (!m3_mem->vaddr) return; - dma_free_coherent(ab->dev, m3_mem->size, + dma_free_coherent(ab->dev, m3_mem->total_size, m3_mem->vaddr, m3_mem->paddr); m3_mem->vaddr = NULL; + m3_mem->total_size = 0; m3_mem->size = 0; } @@ -3152,7 +3153,7 @@ static int ath12k_qmi_m3_load(struct ath12k_base *ab) /* In recovery/resume cases, M3 buffer is not freed, try to reuse that */ if (m3_mem->vaddr) { - if (m3_mem->size >= m3_len) + if (m3_mem->total_size >= m3_len) goto skip_m3_alloc; /* Old buffer is too small, free and reallocate */ @@ -3164,11 +3165,13 @@ static int ath12k_qmi_m3_load(struct ath12k_base *ab) GFP_KERNEL); if (!m3_mem->vaddr) { ath12k_err(ab, "failed to allocate memory for M3 with size %zu\n", - fw->size); + m3_len); ret = -ENOMEM; goto out; } + m3_mem->total_size = m3_len; + skip_m3_alloc: memcpy(m3_mem->vaddr, m3_data, m3_len); m3_mem->size = m3_len; @@ -3740,7 +3743,7 @@ static int ath12k_qmi_ops_new_server(struct qmi_handle *qmi_hdl, sq->sq_node = service->node; sq->sq_port = service->port; - ret = kernel_connect(qmi_hdl->sock, (struct sockaddr *)sq, + ret = kernel_connect(qmi_hdl->sock, (struct sockaddr_unsized *)sq, sizeof(*sq), 0); if (ret) { ath12k_warn(ab, "qmi failed to connect to remote service %d\n", ret); diff --git a/drivers/net/wireless/ath/ath12k/qmi.h b/drivers/net/wireless/ath/ath12k/qmi.h index 4767d9a2e309e..7a88268aa1e9e 100644 --- a/drivers/net/wireless/ath/ath12k/qmi.h +++ b/drivers/net/wireless/ath/ath12k/qmi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef ATH12K_QMI_H @@ -120,6 +120,9 @@ struct target_info { }; struct m3_mem_region { + /* total memory allocated */ + u32 total_size; + /* actual memory being used */ u32 size; dma_addr_t paddr; void *vaddr; diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c index ff6b3d4ea8208..be8b2943094f8 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.c +++ b/drivers/net/wireless/ath/ath12k/wmi.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: BSD-3-Clause-Clear /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #include #include @@ -14,6 +14,7 @@ #include #include #include +#include #include "core.h" #include "debugfs.h" #include "debug.h" @@ -190,6 +191,8 @@ static const struct ath12k_wmi_tlv_policy ath12k_wmi_tlv_policies[] = { .min_len = sizeof(struct wmi_11d_new_cc_event) }, [WMI_TAG_PER_CHAIN_RSSI_STATS] = { .min_len = sizeof(struct wmi_per_chain_rssi_stat_params) }, + [WMI_TAG_OBSS_COLOR_COLLISION_EVT] = { + .min_len = sizeof(struct wmi_obss_color_collision_event) }, }; __le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len) @@ -2367,10 +2370,13 @@ int ath12k_wmi_send_peer_assoc_cmd(struct ath12k *ar, cmd->peer_bw_rxnss_override |= cpu_to_le32(arg->peer_bw_rxnss_override); if (arg->vht_capable) { - mcs->rx_max_rate = cpu_to_le32(arg->rx_max_rate); - mcs->rx_mcs_set = cpu_to_le32(arg->rx_mcs_set); - mcs->tx_max_rate = cpu_to_le32(arg->tx_max_rate); - mcs->tx_mcs_set = cpu_to_le32(arg->tx_mcs_set); + /* Firmware interprets mcs->tx_mcs_set field as peer's + * RX capability + */ + mcs->rx_max_rate = cpu_to_le32(arg->tx_max_rate); + mcs->rx_mcs_set = cpu_to_le32(arg->tx_mcs_set); + mcs->tx_max_rate = cpu_to_le32(arg->rx_max_rate); + mcs->tx_mcs_set = cpu_to_le32(arg->rx_mcs_set); } /* HE Rates */ @@ -3847,6 +3853,58 @@ int ath12k_wmi_fils_discovery(struct ath12k *ar, u32 vdev_id, u32 interval, return ret; } +static void +ath12k_wmi_obss_color_collision_event(struct ath12k_base *ab, struct sk_buff *skb) +{ + const struct wmi_obss_color_collision_event *ev; + struct ath12k_link_vif *arvif; + u32 vdev_id, evt_type; + u64 bitmap; + + const void **tb __free(kfree) = ath12k_wmi_tlv_parse_alloc(ab, skb, GFP_ATOMIC); + if (IS_ERR(tb)) { + ath12k_warn(ab, "failed to parse OBSS color collision tlv %ld\n", + PTR_ERR(tb)); + return; + } + + ev = tb[WMI_TAG_OBSS_COLOR_COLLISION_EVT]; + if (!ev) { + ath12k_warn(ab, "failed to fetch OBSS color collision event\n"); + return; + } + + vdev_id = le32_to_cpu(ev->vdev_id); + evt_type = le32_to_cpu(ev->evt_type); + bitmap = le64_to_cpu(ev->obss_color_bitmap); + + guard(rcu)(); + + arvif = ath12k_mac_get_arvif_by_vdev_id(ab, vdev_id); + if (!arvif) { + ath12k_warn(ab, "no arvif found for vdev %u in OBSS color collision event\n", + vdev_id); + return; + } + + switch (evt_type) { + case WMI_BSS_COLOR_COLLISION_DETECTION: + ieee80211_obss_color_collision_notify(arvif->ahvif->vif, + bitmap, + arvif->link_id); + ath12k_dbg(ab, ATH12K_DBG_WMI, + "obss color collision detected vdev %u event %d bitmap %016llx\n", + vdev_id, evt_type, bitmap); + break; + case WMI_BSS_COLOR_COLLISION_DISABLE: + case WMI_BSS_COLOR_FREE_SLOT_TIMER_EXPIRY: + case WMI_BSS_COLOR_FREE_SLOT_AVAILABLE: + break; + default: + ath12k_warn(ab, "unknown OBSS color collision event type %d\n", evt_type); + } +} + static void ath12k_fill_band_to_mac_param(struct ath12k_base *soc, struct ath12k_wmi_pdev_band_arg *arg) @@ -7011,12 +7069,26 @@ static void ath12k_vdev_start_resp_event(struct ath12k_base *ab, struct sk_buff static void ath12k_bcn_tx_status_event(struct ath12k_base *ab, struct sk_buff *skb) { + struct ath12k_link_vif *arvif; + struct ath12k *ar; u32 vdev_id, tx_status; if (ath12k_pull_bcn_tx_status_ev(ab, skb, &vdev_id, &tx_status) != 0) { ath12k_warn(ab, "failed to extract bcn tx status"); return; } + + guard(rcu)(); + + arvif = ath12k_mac_get_arvif_by_vdev_id(ab, vdev_id); + if (!arvif) { + ath12k_warn(ab, "invalid vdev %u in bcn tx status\n", + vdev_id); + return; + } + + ar = arvif->ar; + wiphy_work_queue(ath12k_ar_to_hw(ar)->wiphy, &arvif->bcn_tx_work); } static void ath12k_vdev_stopped_event(struct ath12k_base *ab, struct sk_buff *skb) @@ -8017,8 +8089,6 @@ void ath12k_wmi_fw_stats_dump(struct ath12k *ar, buf[len - 1] = 0; else buf[len] = 0; - - ath12k_fw_stats_reset(ar); } static void @@ -8415,18 +8485,10 @@ static void ath12k_wmi_fw_stats_process(struct ath12k *ar, ath12k_warn(ab, "empty beacon stats"); return; } - /* Mark end until we reached the count of all started VDEVs - * within the PDEV - */ - if (ar->num_started_vdevs) - is_end = ((++ar->fw_stats.num_bcn_recvd) == - ar->num_started_vdevs); list_splice_tail_init(&stats->bcn, &ar->fw_stats.bcn); - - if (is_end) - complete(&ar->fw_stats_done); + complete(&ar->fw_stats_done); } } @@ -9874,6 +9936,9 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb) case WMI_PDEV_RSSI_DBM_CONVERSION_PARAMS_INFO_EVENTID: ath12k_wmi_rssi_dbm_conversion_params_info_event(ab, skb); break; + case WMI_OBSS_COLOR_COLLISION_DETECTION_EVENTID: + ath12k_wmi_obss_color_collision_event(ab, skb); + break; /* add Unsupported events (rare) here */ case WMI_TBTTOFFSET_EXT_UPDATE_EVENTID: case WMI_PEER_OPER_MODE_CHANGE_EVENTID: @@ -9884,7 +9949,6 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb) /* add Unsupported events (frequent) here */ case WMI_PDEV_GET_HALPHY_CAL_STATUS_EVENTID: case WMI_MGMT_RX_FW_CONSUMED_EVENTID: - case WMI_OBSS_COLOR_COLLISION_DETECTION_EVENTID: /* debug might flood hence silently ignore (no-op) */ break; case WMI_PDEV_UTF_EVENTID: diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h index a8c3190e8ad95..f99fced1610e6 100644 --- a/drivers/net/wireless/ath/ath12k/wmi.h +++ b/drivers/net/wireless/ath/ath12k/wmi.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: BSD-3-Clause-Clear */ /* * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved. - * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved. + * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. */ #ifndef ATH12K_WMI_H @@ -223,15 +223,15 @@ enum WMI_HOST_WLAN_BAND { }; /* Parameters used for WMI_VDEV_PARAM_AUTORATE_MISC_CFG command. - * Used only for HE auto rate mode. + * Used for HE and EHT auto rate mode. */ enum { - /* HE LTF related configuration */ - WMI_HE_AUTORATE_LTF_1X = BIT(0), - WMI_HE_AUTORATE_LTF_2X = BIT(1), - WMI_HE_AUTORATE_LTF_4X = BIT(2), + /* LTF related configuration */ + WMI_AUTORATE_LTF_1X = BIT(0), + WMI_AUTORATE_LTF_2X = BIT(1), + WMI_AUTORATE_LTF_4X = BIT(2), - /* HE GI related configuration */ + /* GI related configuration */ WMI_AUTORATE_400NS_GI = BIT(8), WMI_AUTORATE_800NS_GI = BIT(9), WMI_AUTORATE_1600NS_GI = BIT(10), @@ -1197,6 +1197,7 @@ enum wmi_tlv_vdev_param { WMI_VDEV_PARAM_SET_HEMU_MODE, WMI_VDEV_PARAM_HEOPS_0_31 = 0x8003, WMI_VDEV_PARAM_SET_EHT_MU_MODE = 0x8005, + WMI_VDEV_PARAM_EHT_LTF, }; enum wmi_tlv_peer_flags { @@ -3609,20 +3610,6 @@ struct ath12k_wmi_scan_cancel_arg { u32 pdev_id; }; -struct wmi_bcn_send_from_host_cmd { - __le32 tlv_header; - __le32 vdev_id; - __le32 data_len; - union { - __le32 frag_ptr; - __le32 frag_ptr_lo; - }; - __le32 frame_ctrl; - __le32 dtim_flag; - __le32 bcn_antenna; - __le32 frag_ptr_hi; -}; - #define WMI_CHAN_INFO_MODE GENMASK(5, 0) #define WMI_CHAN_INFO_HT40_PLUS BIT(6) #define WMI_CHAN_INFO_PASSIVE BIT(7) @@ -4218,8 +4205,10 @@ struct wmi_unit_test_cmd { struct ath12k_wmi_vht_rate_set_params { __le32 tlv_header; __le32 rx_max_rate; + /* MCS at which the peer can transmit */ __le32 rx_mcs_set; __le32 tx_max_rate; + /* MCS at which the peer can receive */ __le32 tx_mcs_set; __le32 tx_max_mcs_nss; } __packed; @@ -4940,6 +4929,24 @@ struct wmi_obss_spatial_reuse_params_cmd { #define ATH12K_BSS_COLOR_STA_PERIODS 10000 #define ATH12K_BSS_COLOR_AP_PERIODS 5000 +/** + * enum wmi_bss_color_collision - Event types for BSS color collision handling + * @WMI_BSS_COLOR_COLLISION_DISABLE: Indicates that BSS color collision detection + * is disabled. + * @WMI_BSS_COLOR_COLLISION_DETECTION: Event triggered when a BSS color collision + * is detected. + * @WMI_BSS_COLOR_FREE_SLOT_TIMER_EXPIRY: Event indicating that the timer for waiting + * on a free BSS color slot has expired. + * @WMI_BSS_COLOR_FREE_SLOT_AVAILABLE: Event indicating that a free BSS color slot + * has become available. + */ +enum wmi_bss_color_collision { + WMI_BSS_COLOR_COLLISION_DISABLE = 0, + WMI_BSS_COLOR_COLLISION_DETECTION, + WMI_BSS_COLOR_FREE_SLOT_TIMER_EXPIRY, + WMI_BSS_COLOR_FREE_SLOT_AVAILABLE, +}; + struct wmi_obss_color_collision_cfg_params_cmd { __le32 tlv_header; __le32 vdev_id; @@ -4957,6 +4964,12 @@ struct wmi_bss_color_change_enable_params_cmd { __le32 enable; } __packed; +struct wmi_obss_color_collision_event { + __le32 vdev_id; + __le32 evt_type; + __le64 obss_color_bitmap; +} __packed; + #define ATH12K_IPV4_TH_SEED_SIZE 5 #define ATH12K_IPV6_TH_SEED_SIZE 11 diff --git a/drivers/net/wireless/ath/ath12k/wow.c b/drivers/net/wireless/ath/ath12k/wow.c index dce9bd0bcaefb..e8481626f1940 100644 --- a/drivers/net/wireless/ath/ath12k/wow.c +++ b/drivers/net/wireless/ath/ath12k/wow.c @@ -758,6 +758,7 @@ static int ath12k_wow_arp_ns_offload(struct ath12k *ar, bool enable) if (ret) { ath12k_warn(ar->ab, "failed to set arp ns offload vdev %i: enable %d, ret %d\n", arvif->vdev_id, enable, ret); + kfree(offload); return ret; } } diff --git a/drivers/net/wireless/ath/wcn36xx/hal.h b/drivers/net/wireless/ath/wcn36xx/hal.h index d3a9d00e65e13..ef9ea4ff891b3 100644 --- a/drivers/net/wireless/ath/wcn36xx/hal.h +++ b/drivers/net/wireless/ath/wcn36xx/hal.h @@ -4484,80 +4484,6 @@ struct set_rssi_filter_resp { u32 status; }; -/* Update scan params - sent from host to PNO to be used during PNO - * scanningx */ -struct wcn36xx_hal_update_scan_params_req { - - struct wcn36xx_hal_msg_header header; - - /* Host setting for 11d */ - u8 dot11d_enabled; - - /* Lets PNO know that host has determined the regulatory domain */ - u8 dot11d_resolved; - - /* Channels on which PNO is allowed to scan */ - u8 channel_count; - u8 channels[WCN36XX_HAL_PNO_MAX_NETW_CHANNELS]; - - /* Minimum channel time */ - u16 active_min_ch_time; - - /* Maximum channel time */ - u16 active_max_ch_time; - - /* Minimum channel time */ - u16 passive_min_ch_time; - - /* Maximum channel time */ - u16 passive_max_ch_time; - - /* Cb State */ - enum phy_chan_bond_state state; -} __packed; - -/* Update scan params - sent from host to PNO to be used during PNO - * scanningx */ -struct wcn36xx_hal_update_scan_params_req_ex { - - struct wcn36xx_hal_msg_header header; - - /* Host setting for 11d */ - u8 dot11d_enabled; - - /* Lets PNO know that host has determined the regulatory domain */ - u8 dot11d_resolved; - - /* Channels on which PNO is allowed to scan */ - u8 channel_count; - u8 channels[WCN36XX_HAL_PNO_MAX_NETW_CHANNELS_EX]; - - /* Minimum channel time */ - u16 active_min_ch_time; - - /* Maximum channel time */ - u16 active_max_ch_time; - - /* Minimum channel time */ - u16 passive_min_ch_time; - - /* Maximum channel time */ - u16 passive_max_ch_time; - - /* Cb State */ - enum phy_chan_bond_state state; -} __packed; - -/* Update scan params - sent from host to PNO to be used during PNO - * scanningx */ -struct wcn36xx_hal_update_scan_params_resp { - - struct wcn36xx_hal_msg_header header; - - /* status of the request */ - u32 status; -} __packed; - struct wcn36xx_hal_set_tx_per_tracking_req_msg { struct wcn36xx_hal_msg_header header; diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c index 2cf86fc3f8fe0..136acc414714c 100644 --- a/drivers/net/wireless/ath/wcn36xx/smd.c +++ b/drivers/net/wireless/ath/wcn36xx/smd.c @@ -1127,66 +1127,6 @@ int wcn36xx_smd_process_ptt_msg(struct wcn36xx *wcn, return ret; } -static int wcn36xx_smd_update_scan_params_rsp(void *buf, size_t len) -{ - struct wcn36xx_hal_update_scan_params_resp *rsp; - - rsp = buf; - - /* Remove the PNO version bit */ - rsp->status &= (~(WCN36XX_FW_MSG_PNO_VERSION_MASK)); - - if (WCN36XX_FW_MSG_RESULT_SUCCESS != rsp->status) { - wcn36xx_warn("error response from update scan\n"); - return rsp->status; - } - - return 0; -} - -int wcn36xx_smd_update_scan_params(struct wcn36xx *wcn, - u8 *channels, size_t channel_count) -{ - struct wcn36xx_hal_update_scan_params_req_ex msg_body; - int ret; - - mutex_lock(&wcn->hal_mutex); - INIT_HAL_MSG(msg_body, WCN36XX_HAL_UPDATE_SCAN_PARAM_REQ); - - msg_body.dot11d_enabled = false; - msg_body.dot11d_resolved = true; - - msg_body.channel_count = channel_count; - memcpy(msg_body.channels, channels, channel_count); - msg_body.active_min_ch_time = 60; - msg_body.active_max_ch_time = 120; - msg_body.passive_min_ch_time = 60; - msg_body.passive_max_ch_time = 110; - msg_body.state = PHY_SINGLE_CHANNEL_CENTERED; - - PREPARE_HAL_BUF(wcn->hal_buf, msg_body); - - wcn36xx_dbg(WCN36XX_DBG_HAL, - "hal update scan params channel_count %d\n", - msg_body.channel_count); - - ret = wcn36xx_smd_send_and_wait(wcn, msg_body.header.len); - if (ret) { - wcn36xx_err("Sending hal_update_scan_params failed\n"); - goto out; - } - ret = wcn36xx_smd_update_scan_params_rsp(wcn->hal_buf, - wcn->hal_rsp_len); - if (ret) { - wcn36xx_err("hal_update_scan_params response failed err=%d\n", - ret); - goto out; - } -out: - mutex_unlock(&wcn->hal_mutex); - return ret; -} - static int wcn36xx_smd_add_sta_self_rsp(struct wcn36xx *wcn, struct ieee80211_vif *vif, void *buf, diff --git a/drivers/net/wireless/ath/wcn36xx/smd.h b/drivers/net/wireless/ath/wcn36xx/smd.h index 2c1ed9e570bfd..4e39df5589b31 100644 --- a/drivers/net/wireless/ath/wcn36xx/smd.h +++ b/drivers/net/wireless/ath/wcn36xx/smd.h @@ -66,7 +66,6 @@ int wcn36xx_smd_finish_scan(struct wcn36xx *wcn, enum wcn36xx_hal_sys_mode mode, int wcn36xx_smd_init_scan(struct wcn36xx *wcn, enum wcn36xx_hal_sys_mode mode, struct ieee80211_vif *vif); -int wcn36xx_smd_update_scan_params(struct wcn36xx *wcn, u8 *channels, size_t channel_count); int wcn36xx_smd_start_hw_scan(struct wcn36xx *wcn, struct ieee80211_vif *vif, struct cfg80211_scan_request *req); int wcn36xx_smd_stop_hw_scan(struct wcn36xx *wcn); diff --git a/drivers/net/wireless/ath/wil6210/pm.c b/drivers/net/wireless/ath/wil6210/pm.c index f521af575e9ba..c866cfd144c76 100644 --- a/drivers/net/wireless/ath/wil6210/pm.c +++ b/drivers/net/wireless/ath/wil6210/pm.c @@ -458,6 +458,5 @@ void wil_pm_runtime_put(struct wil6210_priv *wil) { struct device *dev = wil_to_dev(wil); - pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); } diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c index ca488931a33c5..f0453f3f6ba63 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c @@ -38,7 +38,6 @@ static const struct iwl_family_base_params iwl_22000_base = { .features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM, .apmg_not_supported = true, .mac_addr_from_csr = 0x380, - .min_umac_error_event_table = 0x400000, .d3_debug_data_base_addr = 0x401000, .d3_debug_data_length = 60 * 1024, .mon_smem_regs = { diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c index b56574006ee0f..3c844cd419e89 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c @@ -50,7 +50,6 @@ static const struct iwl_family_base_params iwl8000_base = { .smem_offset = IWL8260_SMEM_OFFSET, .smem_len = IWL8260_SMEM_LEN, .apmg_not_supported = true, - .min_umac_error_event_table = 0x800000, }; static const struct iwl_tt_params iwl8000_tt_params = { diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c index ac1fa291cf2f0..5872fc9b8caf4 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c @@ -41,7 +41,6 @@ static const struct iwl_family_base_params iwl9000_base = { .features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM, .apmg_not_supported = true, .mac_addr_from_csr = 0x380, - .min_umac_error_event_table = 0x800000, .d3_debug_data_base_addr = 0x401000, .d3_debug_data_length = 92 * 1024, .nvm_hw_section_num = 10, diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c index ddf3d313da5a6..582f61661062e 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c @@ -33,7 +33,6 @@ static const struct iwl_family_base_params iwl_ax210_base = { .features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM, .apmg_not_supported = true, .mac_addr_from_csr = 0x380, - .min_umac_error_event_table = 0x400000, .d3_debug_data_base_addr = 0x401000, .d3_debug_data_length = 60 * 1024, .mon_smem_regs = { diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c index 3e6206e739f65..d25445bd1e5c3 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c @@ -10,7 +10,7 @@ #include "fw/api/txq.h" /* Highest firmware core release supported */ -#define IWL_BZ_UCODE_CORE_MAX 99 +#define IWL_BZ_UCODE_CORE_MAX 101 /* Lowest firmware API version supported */ #define IWL_BZ_UCODE_API_MIN 100 @@ -38,7 +38,6 @@ static const struct iwl_family_base_params iwl_bz_base = { .smem_len = IWL_BZ_SMEM_LEN, .apmg_not_supported = true, .mac_addr_from_csr = 0x30, - .min_umac_error_event_table = 0xD0000, .d3_debug_data_base_addr = 0x401000, .d3_debug_data_length = 60 * 1024, .mon_smem_regs = { @@ -90,6 +89,7 @@ const struct iwl_mac_cfg iwl_bz_mac_cfg = { .low_latency_xtal = true, .ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US, }; +EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_bz_mac_cfg); const struct iwl_mac_cfg iwl_gl_mac_cfg = { .device_family = IWL_DEVICE_FAMILY_BZ, diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c index e53a785686c89..a279dcfd3083e 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c @@ -9,7 +9,7 @@ #include "fw/api/txq.h" /* Highest firmware core release supported */ -#define IWL_DR_UCODE_CORE_MAX 99 +#define IWL_DR_UCODE_CORE_MAX 101 /* Lowest firmware API version supported */ #define IWL_DR_UCODE_API_MIN 100 @@ -33,7 +33,6 @@ static const struct iwl_family_base_params iwl_dr_base = { .smem_len = IWL_DR_SMEM_LEN, .apmg_not_supported = true, .mac_addr_from_csr = 0x30, - .min_umac_error_event_table = 0xD0000, .d3_debug_data_base_addr = 0x401000, .d3_debug_data_length = 60 * 1024, .mon_smem_regs = { diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c index 456a666c8dfdf..fd82050e33a3c 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-fm.c @@ -19,6 +19,7 @@ .non_shared_ant = ANT_B, \ .vht_mu_mimo_supported = true, \ .uhb_supported = true, \ + .eht_supported = true, \ .num_rbds = IWL_NUM_RBDS_EHT, \ .nvm_ver = IWL_FM_NVM_VERSION, \ .nvm_type = IWL_NVM_EXT diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c index 483f21659effc..408b9850bd104 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-pe.c @@ -12,5 +12,6 @@ const char iwl_killer_bn1850i_name[] = "Killer(R) Wi-Fi 8 BN1850i 320MHz Wireless Network Adapter (BN201.NGW)"; const char iwl_bn201_name[] = "Intel(R) Wi-Fi 8 BN201"; +const char iwl_bn203_name[] = "Intel(R) Wi-Fi 8 BN203"; const char iwl_be221_name[] = "Intel(R) Wi-Fi 7 BE221"; const char iwl_be223_name[] = "Intel(R) Wi-Fi 7 BE223"; diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c b/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c index 97735175cb0ea..b5803ea1eb782 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/rf-wh.c @@ -4,8 +4,31 @@ */ #include "iwl-config.h" +/* NVM versions */ +#define IWL_WH_NVM_VERSION 0x0a1d + +#define IWL_DEVICE_WH \ + .ht_params = { \ + .stbc = true, \ + .ldpc = true, \ + .ht40_bands = BIT(NL80211_BAND_2GHZ) | \ + BIT(NL80211_BAND_5GHZ), \ + }, \ + .led_mode = IWL_LED_RF_STATE, \ + .non_shared_ant = ANT_B, \ + .vht_mu_mimo_supported = true, \ + .uhb_supported = true, \ + .num_rbds = IWL_NUM_RBDS_EHT, \ + .nvm_ver = IWL_WH_NVM_VERSION, \ + .nvm_type = IWL_NVM_EXT + /* currently iwl_rf_wh/iwl_rf_wh_160mhz are just defines for the FM ones */ +const struct iwl_rf_cfg iwl_rf_wh_non_eht = { + IWL_DEVICE_WH, + .eht_supported = false, +}; + const char iwl_killer_be1775s_name[] = "Killer(R) Wi-Fi 7 BE1775s 320MHz Wireless Network Adapter (BE211D2W)"; const char iwl_killer_be1775i_name[] = @@ -13,3 +36,4 @@ const char iwl_killer_be1775i_name[] = const char iwl_be211_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz"; const char iwl_be213_name[] = "Intel(R) Wi-Fi 7 BE213 160MHz"; +const char iwl_ax221_name[] = "Intel(R) Wi-Fi 6E AX221 160MHz"; diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c index e9449b59114ac..ee00b2af7a1d4 100644 --- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c +++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c @@ -10,7 +10,7 @@ #include "fw/api/txq.h" /* Highest firmware core release supported */ -#define IWL_SC_UCODE_CORE_MAX 99 +#define IWL_SC_UCODE_CORE_MAX 101 /* Lowest firmware API version supported */ #define IWL_SC_UCODE_API_MIN 100 @@ -41,7 +41,6 @@ static const struct iwl_family_base_params iwl_sc_base = { .smem_len = IWL_SC_SMEM_LEN, .apmg_not_supported = true, .mac_addr_from_csr = 0x30, - .min_umac_error_event_table = 0xD0000, .d3_debug_data_base_addr = 0x401000, .d3_debug_data_length = 60 * 1024, .mon_smem_regs = { diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h index 20bc6671f4eb2..06cece4ea6d95 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.h @@ -151,6 +151,7 @@ union acpi_object *iwl_acpi_get_dsm_object(struct device *dev, int rev, * @mcc: output buffer (3 bytes) that will get the MCC * * This function tries to read the current MCC from ACPI if available. + * Return: 0 on success, or a negative error code */ int iwl_acpi_get_mcc(struct iwl_fw_runtime *fwrt, char *mcc); diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h index ad5b95cad0bf7..ea2ba4b4cb7b0 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h @@ -88,7 +88,7 @@ struct iwl_imr_alive_info { __le32 enabled; } __packed; /* IMR_ALIVE_INFO_API_S_VER_1 */ -struct iwl_alive_ntf_v6 { +struct iwl_alive_ntf_v7 { __le16 status; __le16 flags; struct iwl_lmac_alive lmac_data[2]; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/cmdhdr.h b/drivers/net/wireless/intel/iwlwifi/fw/api/cmdhdr.h index d130d4f854447..073f003bdc5d2 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/cmdhdr.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/cmdhdr.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014 Intel Corporation + * Copyright (C) 2005-2014, 2025 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -98,7 +98,7 @@ struct iwl_cmd_header { } __packed; /** - * struct iwl_cmd_header_wide + * struct iwl_cmd_header_wide - wide command header * * This header format appears in the beginning of each command sent from the * driver, and each response/notification received from uCode. diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h index ddc84430d8959..616f00a8b6034 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/coex.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2023-2024 Intel Corporation + * Copyright (C) 2023-2025 Intel Corporation * Copyright (C) 2013-2014, 2018-2019 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH @@ -52,7 +52,7 @@ struct iwl_bt_coex_cmd { } __packed; /* BT_COEX_CMD_API_S_VER_6 */ /** - * struct iwl_bt_coex_reduced_txp_update_cmd + * struct iwl_bt_coex_reduced_txp_update_cmd - reduced TX power command * @reduced_txp: bit BT_REDUCED_TX_POWER_BIT to enable / disable, rest of the * bits are the sta_id (value) */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h index 997b0c9ce9840..8d64a271bb945 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h @@ -60,7 +60,7 @@ enum iwl_legacy_cmds { * @UCODE_ALIVE_NTFY: * Alive data from the firmware, as described in * &struct iwl_alive_ntf_v3 or &struct iwl_alive_ntf_v4 or - * &struct iwl_alive_ntf_v5 or &struct iwl_alive_ntf_v6. + * &struct iwl_alive_ntf_v5 or &struct iwl_alive_ntf_v7. */ UCODE_ALIVE_NTFY = 0x1, diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h index b1c6ee8ae2dfd..6a6e11a57dbf3 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h @@ -123,6 +123,11 @@ enum iwl_data_path_subcmd_ids { */ BEACON_FILTER_IN_NOTIF = 0xF8, + /** + * @PHY_AIR_SNIFFER_NOTIF: &struct iwl_rx_phy_air_sniffer_ntfy + */ + PHY_AIR_SNIFFER_NOTIF = 0xF9, + /** * @STA_PM_NOTIF: &struct iwl_mvm_pm_state_notification */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h index 3173fa96cb489..b62f0687327a6 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h @@ -16,7 +16,7 @@ #define IWL_FW_INI_PRESET_DISABLE 0xff /** - * struct iwl_fw_ini_hcmd + * struct iwl_fw_ini_hcmd - debug configuration host command * * @id: the debug configuration command type for instance: 0xf6 / 0xf5 / DHC * @group: the desired cmd group @@ -199,7 +199,7 @@ struct iwl_fw_ini_region_tlv { } __packed; /* FW_TLV_DEBUG_REGION_API_S_VER_1 */ /** - * struct iwl_fw_ini_debug_info_tlv + * struct iwl_fw_ini_debug_info_tlv - debug info TLV * * debug configuration name for a specific image * @@ -311,7 +311,7 @@ struct iwl_fw_ini_conf_set_tlv { } __packed; /* FW_TLV_DEBUG_CONFIG_SET_API_S_VER_1 */ /** - * enum iwl_fw_ini_config_set_type + * enum iwl_fw_ini_config_set_type - configuration set type * * @IWL_FW_INI_CONFIG_SET_TYPE_INVALID: invalid config set * @IWL_FW_INI_CONFIG_SET_TYPE_DEVICE_PERIPHERY_MAC: for PERIPHERY MAC configuration @@ -337,7 +337,7 @@ enum iwl_fw_ini_config_set_type { } __packed; /** - * enum iwl_fw_ini_allocation_id + * enum iwl_fw_ini_allocation_id - allocation ID * * @IWL_FW_INI_ALLOCATION_INVALID: invalid * @IWL_FW_INI_ALLOCATION_ID_DBGC1: allocation meant for DBGC1 configuration @@ -356,7 +356,7 @@ enum iwl_fw_ini_allocation_id { }; /* FW_DEBUG_TLV_ALLOCATION_ID_E_VER_1 */ /** - * enum iwl_fw_ini_buffer_location + * enum iwl_fw_ini_buffer_location - buffer location * * @IWL_FW_INI_LOCATION_INVALID: invalid * @IWL_FW_INI_LOCATION_SRAM_PATH: SRAM location @@ -373,7 +373,7 @@ enum iwl_fw_ini_buffer_location { }; /* FW_DEBUG_TLV_BUFFER_LOCATION_E_VER_1 */ /** - * enum iwl_fw_ini_region_type + * enum iwl_fw_ini_region_type - region type * * @IWL_FW_INI_REGION_INVALID: invalid * @IWL_FW_INI_REGION_TLV: uCode and debug TLVs @@ -437,7 +437,7 @@ enum iwl_fw_ini_region_device_memory_subtype { }; /* FW_TLV_DEBUG_REGION_DEVICE_MEMORY_SUBTYPE_API_E */ /** - * enum iwl_fw_ini_time_point + * enum iwl_fw_ini_time_point - time point type * * Hard coded time points in which the driver can send hcmd or perform dump * collection diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h index 0cf1e5124fba7..61a850de26fcc 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h @@ -421,7 +421,7 @@ struct iwl_dbgc1_info { } __packed; /* INIT_DRAM_FRAGS_ALLOCATIONS_S_VER_1 */ /** - * struct iwl_dbg_host_event_cfg_cmd + * struct iwl_dbg_host_event_cfg_cmd - host event config command * @enabled_severities: enabled severities */ struct iwl_dbg_host_event_cfg_cmd { diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h index 33541f92c7c73..2ee3a48aa5dfe 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h @@ -1092,7 +1092,7 @@ struct iwl_tof_range_req_ap_entry { } __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_9 */ /** - * enum iwl_tof_response_mode + * enum iwl_tof_response_mode - TOF response mode * @IWL_MVM_TOF_RESPONSE_ASAP: report each AP measurement separately as soon as * possible (not supported for this release) * @IWL_MVM_TOF_RESPONSE_TIMEOUT: report all AP measurements as a batch upon @@ -1108,7 +1108,7 @@ enum iwl_tof_response_mode { }; /** - * enum iwl_tof_initiator_flags + * enum iwl_tof_initiator_flags - TOF initiator flags * * @IWL_TOF_INITIATOR_FLAGS_FAST_ALGO_DISABLED: disable fast algo, meaning run * the algo on ant A+B, instead of only one of them. @@ -1409,7 +1409,7 @@ enum iwl_tof_range_request_status { }; /** - * enum iwl_tof_entry_status + * enum iwl_tof_entry_status - TOF entry status * * @IWL_TOF_ENTRY_SUCCESS: successful measurement. * @IWL_TOF_ENTRY_GENERAL_FAILURE: General failure. @@ -1856,7 +1856,7 @@ struct iwl_tof_mcsi_notif { } __packed; /** - * struct iwl_tof_range_abort_cmd + * struct iwl_tof_range_abort_cmd - TOF range abort command * @request_id: corresponds to a range request * @reserved: reserved */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h index e90f3187e55c4..4644fc1aa1ec9 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h @@ -18,13 +18,8 @@ enum iwl_regulatory_and_nvm_subcmd_ids { /** * @LARI_CONFIG_CHANGE: &struct iwl_lari_config_change_cmd_v1, - * &struct iwl_lari_config_change_cmd_v2, - * &struct iwl_lari_config_change_cmd_v3, - * &struct iwl_lari_config_change_cmd_v4, - * &struct iwl_lari_config_change_cmd_v5, * &struct iwl_lari_config_change_cmd_v6, - * &struct iwl_lari_config_change_cmd_v7, - * &struct iwl_lari_config_change_cmd_v10 or + * &struct iwl_lari_config_change_cmd_v8, * &struct iwl_lari_config_change_cmd */ LARI_CONFIG_CHANGE = 0x1, @@ -564,74 +559,6 @@ struct iwl_lari_config_change_cmd_v1 { __le32 config_bitmap; } __packed; /* LARI_CHANGE_CONF_CMD_S_VER_1 */ -/** - * struct iwl_lari_config_change_cmd_v2 - change LARI configuration - * @config_bitmap: bit map of the config commands. each bit will trigger a - * different predefined FW config operation - * @oem_uhb_allow_bitmap: bitmap of UHB enabled MCC sets - */ -struct iwl_lari_config_change_cmd_v2 { - __le32 config_bitmap; - __le32 oem_uhb_allow_bitmap; -} __packed; /* LARI_CHANGE_CONF_CMD_S_VER_2 */ - -/** - * struct iwl_lari_config_change_cmd_v3 - change LARI configuration - * @config_bitmap: bit map of the config commands. each bit will trigger a - * different predefined FW config operation - * @oem_uhb_allow_bitmap: bitmap of UHB enabled MCC sets - * @oem_11ax_allow_bitmap: bitmap of 11ax allowed MCCs. - * For each supported country, a pair of regulatory override bit and 11ax mode exist - * in the bit field. - */ -struct iwl_lari_config_change_cmd_v3 { - __le32 config_bitmap; - __le32 oem_uhb_allow_bitmap; - __le32 oem_11ax_allow_bitmap; -} __packed; /* LARI_CHANGE_CONF_CMD_S_VER_3 */ - -/** - * struct iwl_lari_config_change_cmd_v4 - change LARI configuration - * @config_bitmap: Bitmap of the config commands. Each bit will trigger a - * different predefined FW config operation. - * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets. - * @oem_11ax_allow_bitmap: Bitmap of 11ax allowed MCCs. There are two bits - * per country, one to indicate whether to override and the other to - * indicate the value to use. - * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits - * per country, one to indicate whether to override and the other to - * indicate allow/disallow unii4 channels. - */ -struct iwl_lari_config_change_cmd_v4 { - __le32 config_bitmap; - __le32 oem_uhb_allow_bitmap; - __le32 oem_11ax_allow_bitmap; - __le32 oem_unii4_allow_bitmap; -} __packed; /* LARI_CHANGE_CONF_CMD_S_VER_4 */ - -/** - * struct iwl_lari_config_change_cmd_v5 - change LARI configuration - * @config_bitmap: Bitmap of the config commands. Each bit will trigger a - * different predefined FW config operation. - * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets. - * @oem_11ax_allow_bitmap: Bitmap of 11ax allowed MCCs. There are two bits - * per country, one to indicate whether to override and the other to - * indicate the value to use. - * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits - * per country, one to indicate whether to override and the other to - * indicate allow/disallow unii4 channels. - * @chan_state_active_bitmap: Bitmap for overriding channel state to active. - * Each bit represents a country or region to activate, according to the BIOS - * definitions. - */ -struct iwl_lari_config_change_cmd_v5 { - __le32 config_bitmap; - __le32 oem_uhb_allow_bitmap; - __le32 oem_11ax_allow_bitmap; - __le32 oem_unii4_allow_bitmap; - __le32 chan_state_active_bitmap; -} __packed; /* LARI_CHANGE_CONF_CMD_S_VER_5 */ - /** * struct iwl_lari_config_change_cmd_v6 - change LARI configuration * @config_bitmap: Bitmap of the config commands. Each bit will trigger a @@ -659,8 +586,7 @@ struct iwl_lari_config_change_cmd_v6 { } __packed; /* LARI_CHANGE_CONF_CMD_S_VER_6 */ /** - * struct iwl_lari_config_change_cmd_v7 - change LARI configuration - * This structure is used also for lari cmd version 8 and 9. + * struct iwl_lari_config_change_cmd_v8 - change LARI configuration * @config_bitmap: Bitmap of the config commands. Each bit will trigger a * different predefined FW config operation. * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets. @@ -670,21 +596,19 @@ struct iwl_lari_config_change_cmd_v6 { * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits * per country, one to indicate whether to override and the other to * indicate allow/disallow unii4 channels. - * For LARI cmd version 4 to 8 - bits 0:3 are supported. - * For LARI cmd version 9 - bits 0:5 are supported. + * bit 0 - 3: supported. * @chan_state_active_bitmap: Bitmap to enable different bands per country * or region. * Each bit represents a country or region, and a band to activate * according to the BIOS definitions. - * For LARI cmd version 7 - bits 0:3 are supported. - * For LARI cmd version 8 - bits 0:4 are supported. + * bit 0 - 4: supported. * @force_disable_channels_bitmap: Bitmap of disabled bands/channels. * Each bit represents a set of channels in a specific band that should be * disabled * @edt_bitmap: Bitmap of energy detection threshold table. * Disable/enable the EDT optimization method for different band. */ -struct iwl_lari_config_change_cmd_v7 { +struct iwl_lari_config_change_cmd_v8 { __le32 config_bitmap; __le32 oem_uhb_allow_bitmap; __le32 oem_11ax_allow_bitmap; @@ -693,48 +617,8 @@ struct iwl_lari_config_change_cmd_v7 { __le32 force_disable_channels_bitmap; __le32 edt_bitmap; } __packed; -/* LARI_CHANGE_CONF_CMD_S_VER_7 */ /* LARI_CHANGE_CONF_CMD_S_VER_8 */ -/* LARI_CHANGE_CONF_CMD_S_VER_9 */ -/** - * struct iwl_lari_config_change_cmd_v10 - change LARI configuration - * @config_bitmap: Bitmap of the config commands. Each bit will trigger a - * different predefined FW config operation. - * @oem_uhb_allow_bitmap: Bitmap of UHB enabled MCC sets. - * @oem_11ax_allow_bitmap: Bitmap of 11ax allowed MCCs. There are two bits - * per country, one to indicate whether to override and the other to - * indicate the value to use. - * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits - * per country, one to indicate whether to override and the other to - * indicate allow/disallow unii4 channels. - * For LARI cmd version 10 - bits 0:5 are supported. - * @chan_state_active_bitmap: Bitmap to enable different bands per country - * or region. - * Each bit represents a country or region, and a band to activate - * according to the BIOS definitions. - * For LARI cmd version 10 - bits 0:4 are supported. - * @force_disable_channels_bitmap: Bitmap of disabled bands/channels. - * Each bit represents a set of channels in a specific band that should be - * disabled - * @edt_bitmap: Bitmap of energy detection threshold table. - * Disable/enable the EDT optimization method for different band. - * @oem_320mhz_allow_bitmap: 320Mhz bandwidth enablement bitmap per MCC. - * bit0: enable 320Mhz in Japan. - * bit1: enable 320Mhz in South Korea. - * bit 2 - 31: reserved. - */ -struct iwl_lari_config_change_cmd_v10 { - __le32 config_bitmap; - __le32 oem_uhb_allow_bitmap; - __le32 oem_11ax_allow_bitmap; - __le32 oem_unii4_allow_bitmap; - __le32 chan_state_active_bitmap; - __le32 force_disable_channels_bitmap; - __le32 edt_bitmap; - __le32 oem_320mhz_allow_bitmap; -} __packed; -/* LARI_CHANGE_CONF_CMD_S_VER_10 */ /** * struct iwl_lari_config_change_cmd - change LARI configuration @@ -747,14 +631,11 @@ struct iwl_lari_config_change_cmd_v10 { * @oem_unii4_allow_bitmap: Bitmap of unii4 allowed MCCs.There are two bits * per country, one to indicate whether to override and the other to * indicate allow/disallow unii4 channels. - * For LARI cmd version 11 - bits 0:5 are supported. * @chan_state_active_bitmap: Bitmap to enable different bands per country * or region. * Each bit represents a country or region, and a band to activate * according to the BIOS definitions. - * For LARI cmd version 11 - bits 0:4 are supported. - * For LARI cmd version 12 - bits 0:6 are supported and bits 7:31 are - * reserved. + * bit 0 - 6: supported. * @force_disable_channels_bitmap: Bitmap of disabled bands/channels. * Each bit represents a set of channels in a specific band that should be * disabled @@ -781,12 +662,11 @@ struct iwl_lari_config_change_cmd { __le32 oem_320mhz_allow_bitmap; __le32 oem_11be_allow_bitmap; } __packed; -/* LARI_CHANGE_CONF_CMD_S_VER_11 */ /* LARI_CHANGE_CONF_CMD_S_VER_12 */ /* Activate UNII-1 (5.2GHz) for World Wide */ #define ACTIVATE_5G2_IN_WW_MASK BIT(4) -#define CHAN_STATE_ACTIVE_BITMAP_CMD_V11 0x1F +#define CHAN_STATE_ACTIVE_BITMAP_CMD_V8 0x1F #define CHAN_STATE_ACTIVE_BITMAP_CMD_V12 0x7F /** diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h index 5eb8d10678fd4..535864e226260 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/power.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/power.h @@ -620,7 +620,7 @@ struct iwl_sar_offset_mapping_cmd { } __packed; /*SAR_OFFSET_MAPPING_TABLE_CMD_API_S*/ /** - * struct iwl_beacon_filter_cmd + * struct iwl_beacon_filter_cmd - beacon filter command * REPLY_BEACON_FILTERING_CMD = 0xd2 (command) * @bf_energy_delta: Used for RSSI filtering, if in 'normal' state. Send beacon * to driver if delta in Energy values calculated for this and last @@ -762,7 +762,7 @@ enum iwl_6ghz_ap_type { }; /* PHY_AP_TYPE_API_E_VER_1 */ /** - * struct iwl_txpower_constraints_cmd + * struct iwl_txpower_constraints_cmd - TX power constraints command * AP_TX_POWER_CONSTRAINTS_CMD * Used for VLP/LPI/AFC Access Point power constraints for 6GHz channels * @link_id: linkId @@ -786,4 +786,5 @@ struct iwl_txpower_constraints_cmd { __s8 psd_pwr[IWL_MAX_TX_EIRP_PSD_PWR_MAX_SIZE]; u8 reserved[3]; } __packed; /* PHY_AP_TX_POWER_CONSTRAINTS_CMD_API_S_VER_1 */ + #endif /* __iwl_fw_api_power_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h index d751789998ac8..3ed7e0807b90b 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h @@ -262,6 +262,7 @@ enum iwl_rx_mpdu_reorder_data { }; enum iwl_rx_mpdu_phy_info { + IWL_RX_MPDU_PHY_EOF_INDICATION = BIT(0), IWL_RX_MPDU_PHY_AMPDU = BIT(5), IWL_RX_MPDU_PHY_AMPDU_TOGGLE = BIT(6), IWL_RX_MPDU_PHY_SHORT_PREAMBLE = BIT(7), @@ -1041,4 +1042,289 @@ struct iwl_beacon_filter_notif { __le32 link_id; } __packed; /* BEACON_FILTER_IN_NTFY_API_S_VER_2 */ +union iwl_legacy_sig { +#define OFDM_RX_LEGACY_LENGTH 0x00000fff +#define OFDM_RX_RATE 0x0000f000 + __le32 ofdm; +#define CCK_CRFR_SHORT_PREAMBLE 0x00000040 + __le32 cck; +}; + +struct iwl_ht_sigs { +#define OFDM_RX_FRAME_HT_MCS 0x0000007f +#define OFDM_RX_FRAME_HT_BANDWIDTH 0x00000080 +#define OFDM_RX_FRAME_HT_LENGTH 0x03ffff00 + __le32 a1; + __le32 a2; +}; + +struct iwl_vht_sigs { +#define OFDM_RX_FRAME_VHT_NUM_OF_DATA_SYM 0x000007ff +#define OFDM_RX_FRAME_VHT_NUM_OF_DATA_SYM_VALID 0x80000000 + __le32 a0; + __le32 a1, a2; +}; + +struct iwl_he_sigs { +#define OFDM_RX_FRAME_HE_BEAM_CHANGE 0x00000001 +#define OFDM_RX_FRAME_HE_UL_FLAG 0x00000002 +#define OFDM_RX_FRAME_HE_MCS 0x0000003c +#define OFDM_RX_FRAME_HE_DCM 0x00000040 +#define OFDM_RX_FRAME_HE_BSS_COLOR 0x00001f80 +#define OFDM_RX_FRAME_HE_SPATIAL_REUSE 0x0001e000 +#define OFDM_RX_FRAME_HE_BANDWIDTH 0x00060000 +#define OFDM_RX_FRAME_HE_SU_EXT_BW10 0x00080000 +#define OFDM_RX_FRAME_HE_GI_LTF_TYPE 0x00700000 +#define OFDM_RX_FRAME_HE_NSTS 0x03800000 +#define OFDM_RX_FRAME_HE_PRMBL_PUNC_TYPE 0x0c000000 + __le32 a1; +#define OFDM_RX_FRAME_HE_TXOP_DURATION 0x0000007f +#define OFDM_RX_FRAME_HE_CODING 0x00000080 +#define OFDM_RX_FRAME_HE_CODING_EXTRA_SYM 0x00000100 +#define OFDM_RX_FRAME_HE_STBC 0x00000200 +#define OFDM_RX_FRAME_HE_BF 0x00000400 +#define OFDM_RX_FRAME_HE_PRE_FEC_PAD_FACTOR 0x00001800 +#define OFDM_RX_FRAME_HE_PE_DISAMBIG 0x00002000 +#define OFDM_RX_FRAME_HE_DOPPLER 0x00004000 +#define OFDM_RX_FRAME_HE_TYPE 0x00038000 +#define OFDM_RX_FRAME_HE_MU_NUM_OF_SIGB_SYM_OR_USER_NUM 0x003c0000 +#define OFDM_RX_FRAME_HE_MU_SIGB_COMP 0x00400000 +#define OFDM_RX_FRAME_HE_MU_NUM_OF_LTF_SYM 0x03800000 + __le32 a2; +#define OFDM_RX_FRAME_HE_NUM_OF_DATA_SYM 0x000007ff +#define OFDM_RX_FRAME_HE_PE_DURATION 0x00003800 +#define OFDM_RX_FRAME_HE_NUM_OF_DATA_SYM_VALID 0x80000000 + __le32 a3; +#define OFDM_RX_FRAME_HE_SIGB_STA_ID_FOUND 0x00000001 +#define OFDM_RX_FRAME_HE_SIGB_STA_ID_INDX 0x0000000e +#define OFDM_RX_FRAME_HE_SIGB_NSTS 0x00000070 +#define OFDM_RX_FRAME_HE_SIGB_BF 0x00000080 +#define OFDM_RX_FRAME_HE_SIGB_MCS 0x00000f00 +#define OFDM_RX_FRAME_HE_SIGB_DCM 0x00001000 +#define OFDM_RX_FRAME_HE_SIGB_CODING 0x00002000 +#define OFDM_RX_FRAME_HE_SIGB_SPATIAL_CONFIG 0x0003c000 +#define OFDM_RX_FRAME_HE_SIGB_STA_RU 0x03fc0000 +#define OFDM_RX_FRAME_HE_SIGB_NUM_OF_SYM 0x3c000000 +#define OFDM_RX_FRAME_HE_SIGB_CRC_OK 0x40000000 + __le32 b; +/* index 0 */ +#define OFDM_RX_FRAME_HE_RU_ALLOC_0_A1 0x000000ff +#define OFDM_RX_FRAME_HE_RU_ALLOC_0_A2 0x0000ff00 +#define OFDM_RX_FRAME_HE_RU_ALLOC_0_B1 0x00ff0000 +#define OFDM_RX_FRAME_HE_RU_ALLOC_0_B2 0xff000000 +/* index 1 */ +#define OFDM_RX_FRAME_HE_RU_ALLOC_1_C1 0x000000ff +#define OFDM_RX_FRAME_HE_RU_ALLOC_1_C2 0x0000ff00 +#define OFDM_RX_FRAME_HE_RU_ALLOC_1_D1 0x00ff0000 +#define OFDM_RX_FRAME_HE_RU_ALLOC_1_D2 0xff000000 +/* index 2 */ +#define OFDM_RX_FRAME_HE_CENTER_RU_CC1 0x00000001 +#define OFDM_RX_FRAME_HE_CENTER_RU_CC2 0x00000002 +#define OFDM_RX_FRAME_HE_COMMON_CC1_CRC_OK 0x00000004 +#define OFDM_RX_FRAME_HE_COMMON_CC2_CRC_OK 0x00000008 + __le32 cmn[3]; +}; + +struct iwl_he_tb_sigs { +#define OFDM_RX_HE_TRIG_FORMAT 0x00000001 +#define OFDM_RX_HE_TRIG_BSS_COLOR 0x0000007e +#define OFDM_RX_HE_TRIG_SPATIAL_REUSE_1 0x00000780 +#define OFDM_RX_HE_TRIG_SPATIAL_REUSE_2 0x00007800 +#define OFDM_RX_HE_TRIG_SPATIAL_REUSE_3 0x00078000 +#define OFDM_RX_HE_TRIG_SPATIAL_REUSE_4 0x00780000 +#define OFDM_RX_HE_TRIG_BANDWIDTH 0x03000000 + __le32 a1; +#define OFDM_RX_HE_TRIG_TXOP_DURATION 0x0000007f +#define OFDM_RX_HE_TRIG_SIG2_RESERVED 0x0000ff80 +#define OFDM_RX_HE_TRIG_FORMAT_ERR 0x08000000 +#define OFDM_RX_HE_TRIG_BW_ERR 0x10000000 +#define OFDM_RX_HE_TRIG_LEGACY_LENGTH_ERR 0x20000000 +#define OFDM_RX_HE_TRIG_CRC_OK 0x40000000 + __le32 a2; +#define OFDM_UCODE_TRIG_BASE_RX_LGCY_LENGTH 0x00000fff +#define OFDM_UCODE_TRIG_BASE_RX_BANDWIDTH 0x00007000 +#define OFDM_UCODE_TRIG_BASE_PS160 0x00008000 +#define OFDM_UCODE_EHT_TRIG_CONTROL_CHANNEL 0x000f0000 + __le32 tb_rx0; +#define OFDM_UCODE_TRIG_BASE_RX_MCS 0x0000000f +#define OFDM_UCODE_TRIG_BASE_RX_DCM 0x00000010 +#define OFDM_UCODE_TRIG_BASE_RX_GI_LTF_TYPE 0x00000060 +#define OFDM_UCODE_TRIG_BASE_RX_NSTS 0x00000380 +#define OFDM_UCODE_TRIG_BASE_RX_CODING 0x00000400 +#define OFDM_UCODE_TRIG_BASE_RX_CODING_EXTRA_SYM 0x00000800 +#define OFDM_UCODE_TRIG_BASE_RX_STBC 0x00001000 +#define OFDM_UCODE_TRIG_BASE_RX_PRE_FEC_PAD_FACTOR 0x00006000 +#define OFDM_UCODE_TRIG_BASE_RX_PE_DISAMBIG 0x00008000 +#define OFDM_UCODE_TRIG_BASE_RX_DOPPLER 0x00010000 +#define OFDM_UCODE_TRIG_BASE_RX_RU 0x01fe0000 +#define OFDM_UCODE_TRIG_BASE_RX_RU_P80 0x00020000 +#define OFDM_UCODE_TRIG_BASE_RX_NUM_OF_LTF_SYM 0x0e000000 +#define OFDM_UCODE_TRIG_BASE_RX_LTF_PILOT_TYPE 0x10000000 +#define OFDM_UCODE_TRIG_BASE_RX_LOWEST_SS_ALLOCATION 0xe0000000 + __le32 tb_rx1; +}; + +struct iwl_eht_sigs { +#define OFDM_RX_FRAME_ENHANCED_WIFI_VER_ID 0x00000007 +#define OFDM_RX_FRAME_ENHANCED_WIFI_BANDWIDTH 0x00000038 +#define OFDM_RX_FRAME_ENHANCED_WIFI_UL_FLAG 0x00000040 +#define OFDM_RX_FRAME_ENHANCED_WIFI_BSS_COLOR 0x00001f80 +#define OFDM_RX_FRAME_ENHANCED_WIFI_TXOP_DURATION 0x000fe000 +#define OFDM_RX_FRAME_EHT_USIG1_DISREGARD 0x01f00000 +#define OFDM_RX_FRAME_EHT_USIG1_VALIDATE 0x02000000 +#define OFDM_RX_FRAME_EHT_BW320_SLOT 0x04000000 +#define OFDM_RX_FRAME_EHT_TYPE 0x18000000 +#define OFDM_RX_FRAME_ENHANCED_ER_NO_STREAMS 0x20000000 + __le32 usig_a1; +#define OFDM_RX_FRAME_EHT_PPDU_TYPE 0x00000003 +#define OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B2 0x00000004 +#define OFDM_RX_FRAME_EHT_PUNC_CHANNEL 0x000000f8 +#define OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B8 0x00000100 +#define OFDM_RX_FRAME_EHT_SIG_MCS 0x00000600 +#define OFDM_RX_FRAME_EHT_SIG_SYM_NUM 0x0000f800 +#define OFDM_RX_FRAME_EHT_TRIG_SPATIAL_REUSE_1 0x000f0000 +#define OFDM_RX_FRAME_EHT_TRIG_SPATIAL_REUSE_2 0x00f00000 +#define OFDM_RX_FRAME_EHT_TRIG_USIG2_DISREGARD 0x1f000000 +#define OFDM_RX_FRAME_EHT_TRIG_NO_STREAMS 0x20000000 +#define OFDM_RX_USIG_CRC_OK 0x40000000 + __le32 usig_a2_eht; +#define OFDM_RX_FRAME_EHT_SPATIAL_REUSE 0x0000000f +#define OFDM_RX_FRAME_EHT_GI_LTF_TYPE 0x00000030 +#define OFDM_RX_FRAME_EHT_NUM_OF_LTF_SYM 0x000001c0 +#define OFDM_RX_FRAME_EHT_CODING_EXTRA_SYM 0x00000200 +#define OFDM_RX_FRAME_EHT_PRE_FEC_PAD_FACTOR 0x00000c00 +#define OFDM_RX_FRAME_EHT_PE_DISAMBIG 0x00001000 +#define OFDM_RX_FRAME_EHT_USIG_OVF_DISREGARD 0x0001e000 +#define OFDM_RX_FRAME_EHT_NUM_OF_USERS 0x000e0000 +#define OFDM_RX_FRAME_EHT_NSTS 0x00f00000 +#define OFDM_RX_FRAME_EHT_BF 0x01000000 +#define OFDM_RX_FRAME_EHT_USIG_OVF_NDP_DISREGARD 0x06000000 +#define OFDM_RX_FRAME_EHTSIG_COMM_CC1_CRC_OK 0x08000000 +#define OFDM_RX_FRAME_EHTSIG_COMM_CC2_CRC_OK 0x10000000 +#define OFDM_RX_FRAME_EHT_NON_VALID_RU_ALLOC 0x20000000 +#define OFDM_RX_FRAME_EHT_NO_STREAMS 0x40000000 + __le32 b1; +#define OFDM_RX_FRAME_EHT_MATCH_ID_FOUND 0x00000001 +#define OFDM_RX_FRAME_EHT_ID_INDX 0x0000000e +#define OFDM_RX_FRAME_EHT_MCS 0x000000f0 +#define OFDM_RX_FRAME_EHT_CODING 0x00000100 +#define OFDM_RX_FRAME_EHT_SPATIAL_CONFIG 0x00007e00 +#define OFDM_RX_FRAME_EHT_STA_RU 0x007f8000 +#define OFDM_RX_FRAME_EHT_STA_RU_P80 0x00008000 +#define OFDM_RX_FRAME_EHT_STA_RU_PS160 0x00800000 +#define OFDM_RX_FRAME_EHT_USER_FIELD_CRC_OK 0x40000000 + __le32 b2; +#define OFDM_RX_FRAME_EHT_NUM_OF_DATA_SYM 0x000007ff +#define OFDM_RX_FRAME_EHT_PE_DURATION 0x00003800 +#define OFDM_RX_FRAME_EHT_NUM_OF_DATA_SYM_VALID 0x80000000 + __le32 sig2; +#define OFDM_RX_FRAME_EHT_RU_ALLOC_0_A1 0x000001ff +#define OFDM_RX_FRAME_EHT_RU_ALLOC_0_A2 0x0003fe00 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_0_A3 0x07fc0000 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_1_B1 0x000001ff +#define OFDM_RX_FRAME_EHT_RU_ALLOC_1_B2 0x0003fe00 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_1_B3 0x07fc0000 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_2_C1 0x000001ff +#define OFDM_RX_FRAME_EHT_RU_ALLOC_2_C2 0x0003fe00 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_2_C3 0x07fc0000 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_3_D1 0x000001ff +#define OFDM_RX_FRAME_EHT_RU_ALLOC_3_D2 0x0003fe00 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_3_D3 0x07fc0000 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_4_A4 0x000001ff +#define OFDM_RX_FRAME_EHT_RU_ALLOC_4_B4 0x0003fe00 +#define OFDM_RX_FRAME_EHT_RU_ALLOC_5_C4 0x000001ff +#define OFDM_RX_FRAME_EHT_RU_ALLOC_5_D4 0x0003fe00 + __le32 cmn[6]; +#define OFDM_RX_FRAME_EHT_USER_FIELD_ID 0x000007ff + __le32 user_id; +}; + +struct iwl_eht_tb_sigs { + /* same as non-TB above */ + __le32 usig_a1, usig_a2_eht; + /* same as HE TB above */ + __le32 tb_rx0, tb_rx1; +}; + +struct iwl_uhr_sigs { + __le32 usig_a1, usig_a1_uhr, usig_a2_uhr, b1, b2; + __le32 sig2; + __le32 cmn[6]; + __le32 user_id; +}; + +struct iwl_uhr_tb_sigs { + __le32 usig_a1, usig_a2_uhr, tb_rx0, tb_rx1; +}; + +struct iwl_uhr_elr_sigs { + __le32 usig_a1, usig_a2_uhr; + __le32 uhr_sig_elr1, uhr_sig_elr2; +}; + +union iwl_sigs { + struct iwl_ht_sigs ht; + struct iwl_vht_sigs vht; + struct iwl_he_sigs he; + struct iwl_he_tb_sigs he_tb; + struct iwl_eht_sigs eht; + struct iwl_eht_tb_sigs eht_tb; + struct iwl_uhr_sigs uhr; + struct iwl_uhr_tb_sigs uhr_tb; + struct iwl_uhr_elr_sigs uhr_elr; +}; + +enum iwl_sniffer_status { + IWL_SNIF_STAT_PLCP_RX_OK = 0, + IWL_SNIF_STAT_AID_NOT_FOR_US = 1, + IWL_SNIF_STAT_PLCP_RX_LSIG_ERR = 2, + IWL_SNIF_STAT_PLCP_RX_SIGA_ERR = 3, + IWL_SNIF_STAT_PLCP_RX_SIGB_ERR = 4, + IWL_SNIF_STAT_UNEXPECTED_TB = 5, + IWL_SNIF_STAT_UNSUPPORTED_RATE = 6, + IWL_SNIF_STAT_UNKNOWN_ERROR = 7, +}; /* AIR_SNIFFER_STATUS_E_VER_1 */ + +enum iwl_sniffer_flags { + IWL_SNIF_FLAG_VALID_TB_RX = BIT(0), + IWL_SNIF_FLAG_VALID_RU = BIT(1), +}; /* AIR_SNIFFER_FLAGS_E_VER_1 */ + +/** + * struct iwl_rx_phy_air_sniffer_ntfy - air sniffer notification + * + * @status: &enum iwl_sniffer_status + * @flags: &enum iwl_sniffer_flags + * @reserved1: reserved + * @rssi_a: energy chain-A in negative dBm, measured at FINA time + * @rssi_b: energy chain-B in negative dBm, measured at FINA time + * @channel: channel number + * @band: band information, PHY_BAND_* + * @on_air_rise_time: GP2 at on air rise + * @frame_time: frame time in us + * @rate: RATE_MCS_* + * @bytecount: byte count for legay and HT, otherwise number of symbols + * @legacy_sig: CCK signal information if %RATE_MCS_MOD_TYPE_MSK in @rate is + * %RATE_MCS_MOD_TYPE_CCK, otherwise OFDM signal information + * @sigs: PHY signal information, depending on %RATE_MCS_MOD_TYPE_MSK in @rate + * @reserved2: reserved + * + * Sent for every frame and before the normal RX command if data is included. + */ +struct iwl_rx_phy_air_sniffer_ntfy { + u8 status; + u8 flags; + u8 reserved1[2]; + u8 rssi_a, rssi_b; + u8 channel, band; + __le32 on_air_rise_time; + __le32 frame_time; + /* note: MCS in rate is not valid for MU-VHT */ + __le32 rate; + __le32 bytecount; + union iwl_legacy_sig legacy_sig; + union iwl_sigs sigs; + __le32 reserved2; +}; /* RX_PHY_AIR_SNIFFER_NTFY_API_S_VER_1 */ + #endif /* __iwl_fw_api_rx_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h index f486d624500be..60f0a4924ddfb 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/scan.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2012-2014, 2018-2024 Intel Corporation + * Copyright (C) 2012-2014, 2018-2025 Intel Corporation * Copyright (C) 2013-2015 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -129,7 +129,7 @@ struct iwl_scan_offload_profile { } __packed; /** - * struct iwl_scan_offload_profile_cfg_data + * struct iwl_scan_offload_profile_cfg_data - scan offload profile configs * @blocklist_len: length of blocklist * @num_profiles: num of profiles in the list * @match_notify: clients waiting for match found notification @@ -159,7 +159,7 @@ struct iwl_scan_offload_profile_cfg_v1 { } __packed; /* SCAN_OFFLOAD_PROFILES_CFG_API_S_VER_1-2*/ /** - * struct iwl_scan_offload_profile_cfg + * struct iwl_scan_offload_profile_cfg - scan offload profile config * @profiles: profiles to search for match * @data: the rest of the data for profile_cfg */ @@ -507,7 +507,7 @@ enum iwl_uhb_chan_cfg_flags { IWL_UHB_CHAN_CFG_FLAG_FORCE_PASSIVE = BIT(26), }; /** - * struct iwl_scan_dwell + * struct iwl_scan_dwell - scan dwell configuration * @active: default dwell time for active scan * @passive: default dwell time for passive scan * @fragmented: default dwell time for fragmented scan @@ -728,7 +728,7 @@ enum iwl_umac_scan_general_params_flags2 { }; /** - * struct iwl_scan_channel_cfg_umac + * struct iwl_scan_channel_cfg_umac - scan channel config * @flags: bitmap - 0-19: directed scan to i'th ssid. * @channel_num: channel number 1-13 etc. * @v1: command version 1 @@ -774,7 +774,7 @@ struct iwl_scan_channel_cfg_umac { } __packed; /** - * struct iwl_scan_umac_schedule + * struct iwl_scan_umac_schedule - scan schedule parameters * @interval: interval in seconds between scan iterations * @iter_count: num of scan iterations for schedule plan, 0xff for infinite loop * @reserved: for alignment and future use @@ -815,7 +815,7 @@ struct iwl_scan_req_umac_tail_v2 { } __packed; /** - * struct iwl_scan_umac_chan_param + * struct iwl_scan_umac_chan_param - scan channel parameters * @flags: channel flags &enum iwl_scan_channel_flags * @count: num of channels in scan request * @reserved: for future use and alignment @@ -827,33 +827,37 @@ struct iwl_scan_umac_chan_param { } __packed; /*SCAN_CHANNEL_PARAMS_API_S_VER_1 */ /** - * struct iwl_scan_req_umac + * struct iwl_scan_req_umac - scan request command * @flags: &enum iwl_umac_scan_flags * @uid: scan id, &enum iwl_umac_scan_uid_offsets * @ooc_priority: out of channel priority - &enum iwl_scan_priority * @general_flags: &enum iwl_umac_scan_general_flags + * @reserved: reserved * @scan_start_mac_id: report the scan start TSF time according to this mac TSF - * @extended_dwell: dwell time for channels 1, 6 and 11 - * @active_dwell: dwell time for active scan per LMAC - * @passive_dwell: dwell time for passive scan per LMAC - * @fragmented_dwell: dwell time for fragmented passive scan - * @adwell_default_n_aps: for adaptive dwell the default number of APs + * @v1: version 1 command data + * @v6: version 6 command data + * @v7: version 7 command data + * @v8: version 8 command data + * @v9: version 9 command data + * @v1.extended_dwell: dwell time for channels 1, 6 and 11 + * @v1.active_dwell: dwell time for active scan per LMAC + * @v1.passive_dwell: dwell time for passive scan per LMAC + * @v1.fragmented_dwell: dwell time for fragmented passive scan + * @v7.adwell_default_n_aps: for adaptive dwell the default number of APs * per channel - * @adwell_default_n_aps_social: for adaptive dwell the default + * @v7.adwell_default_n_aps_social: for adaptive dwell the default * number of APs per social (1,6,11) channel - * @general_flags2: &enum iwl_umac_scan_general_flags2 - * @adwell_max_budget: for adaptive dwell the maximal budget of TU to be added - * to total scan time - * @max_out_time: max out of serving channel time, per LMAC - for CDB there - * are 2 LMACs - * @suspend_time: max suspend time, per LMAC - for CDB there are 2 LMACs - * @scan_priority: scan internal prioritization &enum iwl_scan_priority - * @num_of_fragments: Number of fragments needed for full coverage per band. + * @v8.general_flags2: &enum iwl_umac_scan_general_flags2 + * @v7.adwell_max_budget: for adaptive dwell the maximal budget of TU to be + * added to total scan time + * @v1.max_out_time: max out of serving channel time, per LMAC - for CDB + * there are 2 LMACs + * @v1.suspend_time: max suspend time, per LMAC - for CDB there are 2 LMACs + * @v1.scan_priority: scan internal prioritization &enum iwl_scan_priority + * @v8.num_of_fragments: Number of fragments needed for full coverage per band. * Relevant only for fragmented scan. - * @channel: &struct iwl_scan_umac_chan_param - * @reserved: for future use and alignment - * @reserved3: for future use and alignment - * @data: &struct iwl_scan_channel_cfg_umac and + * @v1.channel: &struct iwl_scan_umac_chan_param + * @v1.data: &struct iwl_scan_channel_cfg_umac and * &struct iwl_scan_req_umac_tail */ struct iwl_scan_req_umac { @@ -939,7 +943,7 @@ struct iwl_scan_req_umac { #define IWL_SCAN_REQ_UMAC_SIZE_V1 36 /** - * struct iwl_scan_probe_params_v3 + * struct iwl_scan_probe_params_v3 - scan probe parameters * @preq: scan probe request params * @ssid_num: number of valid SSIDs in direct scan array * @short_ssid_num: number of valid short SSIDs in short ssid array @@ -961,7 +965,7 @@ struct iwl_scan_probe_params_v3 { } __packed; /* SCAN_PROBE_PARAMS_API_S_VER_3 */ /** - * struct iwl_scan_probe_params_v4 + * struct iwl_scan_probe_params_v4 - scan probe parameters * @preq: scan probe request params * @short_ssid_num: number of valid short SSIDs in short ssid array * @bssid_num: number of valid bssid in bssids array @@ -983,7 +987,7 @@ struct iwl_scan_probe_params_v4 { #define SCAN_MAX_NUM_CHANS_V3 67 /** - * struct iwl_scan_channel_params_v4 + * struct iwl_scan_channel_params_v4 - channel params * @flags: channel flags &enum iwl_scan_channel_flags * @count: num of channels in scan request * @num_of_aps_override: override the number of APs the FW uses to calculate @@ -1006,7 +1010,7 @@ struct iwl_scan_channel_params_v4 { SCAN_CHANNEL_PARAMS_API_S_VER_5 */ /** - * struct iwl_scan_channel_params_v7 + * struct iwl_scan_channel_params_v7 - channel params * @flags: channel flags &enum iwl_scan_channel_flags * @count: num of channels in scan request * @n_aps_override: override the number of APs the FW uses to calculate dwell @@ -1024,7 +1028,7 @@ struct iwl_scan_channel_params_v7 { } __packed; /* SCAN_CHANNEL_PARAMS_API_S_VER_6 */ /** - * struct iwl_scan_general_params_v11 + * struct iwl_scan_general_params_v11 - channel params * @flags: &enum iwl_umac_scan_general_flags_v2 * @reserved: reserved for future * @scan_start_mac_or_link_id: report the scan start TSF time according to this @@ -1066,7 +1070,7 @@ struct iwl_scan_general_params_v11 { } __packed; /* SCAN_GENERAL_PARAMS_API_S_VER_12, *_VER_11 and *_VER_10 */ /** - * struct iwl_scan_periodic_parms_v1 + * struct iwl_scan_periodic_parms_v1 - periodicity parameters * @schedule: can scheduling parameter * @delay: initial delay of the periodic scan in seconds * @reserved: reserved for future @@ -1078,7 +1082,7 @@ struct iwl_scan_periodic_parms_v1 { } __packed; /* SCAN_PERIODIC_PARAMS_API_S_VER_1 */ /** - * struct iwl_scan_req_params_v12 + * struct iwl_scan_req_params_v12 - scan request parameters (v12) * @general_params: &struct iwl_scan_general_params_v11 * @channel_params: &struct iwl_scan_channel_params_v4 * @periodic_params: &struct iwl_scan_periodic_parms_v1 @@ -1106,7 +1110,7 @@ struct iwl_scan_req_params_v17 { } __packed; /* SCAN_REQUEST_PARAMS_API_S_VER_17 - 14 */ /** - * struct iwl_scan_req_umac_v12 + * struct iwl_scan_req_umac_v12 - scan request command (v12) * @uid: scan id, &enum iwl_umac_scan_uid_offsets * @ooc_priority: out of channel priority - &enum iwl_scan_priority * @scan_params: scan parameters @@ -1130,7 +1134,7 @@ struct iwl_scan_req_umac_v17 { } __packed; /* SCAN_REQUEST_CMD_UMAC_API_S_VER_17 - 14 */ /** - * struct iwl_umac_scan_abort + * struct iwl_umac_scan_abort - scan abort command * @uid: scan id, &enum iwl_umac_scan_uid_offsets * @flags: reserved */ @@ -1140,7 +1144,7 @@ struct iwl_umac_scan_abort { } __packed; /* SCAN_ABORT_CMD_UMAC_API_S_VER_1 */ /** - * enum iwl_umac_scan_abort_status + * enum iwl_umac_scan_abort_status - scan abort status * * @IWL_UMAC_SCAN_ABORT_STATUS_SUCCESS: scan was successfully aborted * @IWL_UMAC_SCAN_ABORT_STATUS_IN_PROGRESS: scan abort is in progress @@ -1153,7 +1157,7 @@ enum iwl_umac_scan_abort_status { }; /** - * struct iwl_umac_scan_complete + * struct iwl_umac_scan_complete - scan complete notification * @uid: scan id, &enum iwl_umac_scan_uid_offsets * @last_schedule: last scheduling line * @last_iter: last scan iteration number diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h index ecbcd5084cd8d..e6f9abdfa546d 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2012-2014, 2018-2021, 2023 Intel Corporation + * Copyright (C) 2012-2014, 2018-2021, 2023, 2025 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2016-2017 Intel Deutschland GmbH */ @@ -428,7 +428,7 @@ struct iwl_mvm_rm_sta_cmd { } __packed; /* REMOVE_STA_CMD_API_S_VER_2 */ /** - * struct iwl_mvm_mgmt_mcast_key_cmd_v1 + * struct iwl_mvm_mgmt_mcast_key_cmd_v1 - IGTK command * ( MGMT_MCAST_KEY = 0x1f ) * @ctrl_flags: &enum iwl_sta_key_flag * @igtk: IGTK key material @@ -449,7 +449,7 @@ struct iwl_mvm_mgmt_mcast_key_cmd_v1 { } __packed; /* SEC_MGMT_MULTICAST_KEY_CMD_API_S_VER_1 */ /** - * struct iwl_mvm_mgmt_mcast_key_cmd + * struct iwl_mvm_mgmt_mcast_key_cmd - IGTK command * ( MGMT_MCAST_KEY = 0x1f ) * @ctrl_flags: &enum iwl_sta_key_flag * @igtk: IGTK master key diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h index 00713a9918792..8d9a5058d5a54 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/stats.h @@ -26,7 +26,7 @@ struct mvm_statistics_div { } __packed; /* STATISTICS_SLOW_DIV_API_S_VER_2 */ /** - * struct mvm_statistics_rx_non_phy + * struct mvm_statistics_rx_non_phy - non-PHY RX statistics * @bogus_cts: CTS received when not expecting CTS * @bogus_ack: ACK received when not expecting ACK * @non_channel_beacons: beacons with our bss id but not on our serving channel @@ -456,7 +456,7 @@ struct iwl_system_statistics_cmd { } __packed; /* STATISTICS_FW_CMD_API_S_VER_1 */ /** - * enum iwl_fw_statistics_type + * enum iwl_fw_statistics_type - statistics type * * @FW_STATISTICS_OPERATIONAL: operational statistics * @FW_STATISTICS_PHY: phy statistics @@ -478,7 +478,7 @@ enum iwl_fw_statistics_type { #define IWL_STATISTICS_TYPE_MSK 0x7f /** - * struct iwl_statistics_ntfy_hdr + * struct iwl_statistics_ntfy_hdr - statistics notification header * * @type: struct type * @version: version of the struct @@ -491,7 +491,7 @@ struct iwl_statistics_ntfy_hdr { }; /* STATISTICS_NTFY_HDR_API_S_VER_1 */ /** - * struct iwl_stats_ntfy_per_link + * struct iwl_stats_ntfy_per_link - per-link statistics * * @beacon_filter_average_energy: Average energy [-dBm] of the 2 * antennas. @@ -514,7 +514,7 @@ struct iwl_stats_ntfy_per_link { } __packed; /* STATISTICS_NTFY_PER_LINK_API_S_VER_1 */ /** - * struct iwl_stats_ntfy_part1_per_link + * struct iwl_stats_ntfy_part1_per_link - part1 per link statistics * * @rx_time: rx time * @tx_time: tx time @@ -533,7 +533,7 @@ struct iwl_stats_ntfy_part1_per_link { } __packed; /* STATISTICS_FW_NTFY_OPERATIONAL_PART1_PER_LINK_API_S_VER_1 */ /** - * struct iwl_stats_ntfy_per_mac + * struct iwl_stats_ntfy_per_mac - per MAC statistics * * @beacon_filter_average_energy: Average energy [-dBm] of the 2 * antennas. @@ -556,7 +556,8 @@ struct iwl_stats_ntfy_per_mac { } __packed; /* STATISTICS_NTFY_PER_MAC_API_S_VER_1 */ #define IWL_STATS_MAX_BW_INDEX 5 -/** struct iwl_stats_ntfy_per_phy +/** + * struct iwl_stats_ntfy_per_phy - per PHY statistics * @channel_load: channel load * @channel_load_by_us: device contribution to MCLM * @channel_load_not_by_us: other devices' contribution to MCLM @@ -588,7 +589,7 @@ struct iwl_stats_ntfy_per_phy { #define IWL_STATS_UNKNOWN_CHANNEL_LOAD 0xffffffff /** - * struct iwl_stats_ntfy_per_sta + * struct iwl_stats_ntfy_per_sta - per STA statistics * * @average_energy: in fact it is minus the energy.. */ @@ -600,7 +601,7 @@ struct iwl_stats_ntfy_per_sta { #define IWL_STATS_MAX_FW_LINKS (IWL_FW_MAX_LINK_ID + 1) /** - * struct iwl_system_statistics_notif_oper + * struct iwl_system_statistics_notif_oper - statistics notification * * @time_stamp: time when the notification is sent from firmware * @per_link: per link statistics, &struct iwl_stats_ntfy_per_link @@ -615,7 +616,7 @@ struct iwl_system_statistics_notif_oper { } __packed; /* STATISTICS_FW_NTFY_OPERATIONAL_API_S_VER_3 */ /** - * struct iwl_system_statistics_part1_notif_oper + * struct iwl_system_statistics_part1_notif_oper - part1 stats notification * * @time_stamp: time when the notification is sent from firmware * @per_link: per link statistics &struct iwl_stats_ntfy_part1_per_link @@ -628,7 +629,7 @@ struct iwl_system_statistics_part1_notif_oper { } __packed; /* STATISTICS_FW_NTFY_OPERATIONAL_PART1_API_S_VER_4 */ /** - * struct iwl_system_statistics_end_notif + * struct iwl_system_statistics_end_notif - statistics end notification * * @time_stamp: time when the notification is sent from firmware */ @@ -637,7 +638,7 @@ struct iwl_system_statistics_end_notif { } __packed; /* STATISTICS_FW_NTFY_END_API_S_VER_1 */ /** - * struct iwl_statistics_operational_ntfy + * struct iwl_statistics_operational_ntfy - operational stats notification * * @hdr: general statistics header * @flags: bitmap of possible notification structures @@ -662,7 +663,7 @@ struct iwl_statistics_operational_ntfy { } __packed; /* STATISTICS_OPERATIONAL_NTFY_API_S_VER_15 */ /** - * struct iwl_statistics_operational_ntfy_ver_14 + * struct iwl_statistics_operational_ntfy_ver_14 - operational stats notification * * @hdr: general statistics header * @flags: bitmap of possible notification structures @@ -707,7 +708,7 @@ struct iwl_statistics_operational_ntfy_ver_14 { } __packed; /* STATISTICS_OPERATIONAL_NTFY_API_S_VER_14 */ /** - * struct iwl_statistics_phy_ntfy + * struct iwl_statistics_phy_ntfy - PHY statistics notification * * @hdr: general statistics header * RX PHY related statistics @@ -808,7 +809,7 @@ struct iwl_statistics_phy_ntfy { } __packed; /* STATISTICS_PHY_NTFY_API_S_VER_1 */ /** - * struct iwl_statistics_mac_ntfy + * struct iwl_statistics_mac_ntfy - MAC statistics notification * * @hdr: general statistics header * @bcast_filter_passed_per_mac: bcast filter passed per mac @@ -827,7 +828,7 @@ struct iwl_statistics_mac_ntfy { } __packed; /* STATISTICS_MAC_NTFY_API_S_VER_1 */ /** - * struct iwl_statistics_rx_ntfy + * struct iwl_statistics_rx_ntfy - RX statistics notification * * @hdr: general statistics header * @rx_agg_mpdu_cnt: aggregation frame count (number of @@ -867,7 +868,7 @@ struct iwl_statistics_rx_ntfy { } __packed; /* STATISTICS_RX_NTFY_API_S_VER_1 */ /** - * struct iwl_statistics_tx_ntfy + * struct iwl_statistics_tx_ntfy - TX statistics notification * * @hdr: general statistics header * @cts_timeout: timeout when waiting for CTS @@ -976,7 +977,7 @@ struct iwl_statistics_tx_ntfy { } __packed; /* STATISTICS_TX_NTFY_API_S_VER_1 */ /** - * struct iwl_statistics_duration_ntfy + * struct iwl_statistics_duration_ntfy - burst/duration statistics * * @hdr: general statistics header * @cont_burst_chk_cnt: number of times continuation or @@ -995,7 +996,7 @@ struct iwl_statistics_duration_ntfy { } __packed; /* STATISTICS_DURATION_NTFY_API_S_VER_1 */ /** - * struct iwl_statistics_he_ntfy + * struct iwl_statistics_he_ntfy - HE statistics * * @hdr: general statistics header * received HE frames diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h index 26d2013905ed9..31d3336726b42 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h @@ -963,7 +963,7 @@ struct iwl_scd_txq_cfg_cmd { } __packed; /* SCD_QUEUE_CFG_CMD_API_S_VER_1 */ /** - * struct iwl_scd_txq_cfg_rsp + * struct iwl_scd_txq_cfg_rsp - scheduler TXQ configuration response * @token: taken from the command * @sta_id: station id from the command * @tid: tid from the command diff --git a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h index c2a73cc85eff4..525a82030daa4 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/error-dump.h @@ -266,7 +266,7 @@ struct iwl_fw_ini_error_dump_data { } __packed; /** - * struct iwl_fw_ini_dump_entry + * struct iwl_fw_ini_dump_entry - dump entry descriptor * @list: list of dump entries * @size: size of the data * @data: entry data @@ -305,7 +305,7 @@ struct iwl_fw_ini_fifo_hdr { * @dram_base_addr: base address of dram monitor range * @page_num: page number of memory range * @fifo_hdr: fifo header of memory range - * @fw_pkt: FW packet header of memory range + * @fw_pkt_hdr: FW packet header of memory range * @data: the actual memory */ struct iwl_fw_ini_error_dump_range { diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h index b7c1ab7a30061..b9e0b69c66803 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/file.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h @@ -222,7 +222,10 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t; * @IWL_UCODE_TLV_API_STA_TYPE: This ucode supports station type assignement. * @IWL_UCODE_TLV_API_NAN2_VER2: This ucode supports NAN API version 2 * @IWL_UCODE_TLV_API_ADAPTIVE_DWELL: support for adaptive dwell in scanning + * @IWL_UCODE_TLV_API_OCE: support for OCE + * @IWL_UCODE_TLV_API_NEW_BEACON_TEMPLATE: new beacon template * @IWL_UCODE_TLV_API_NEW_RX_STATS: should new RX STATISTICS API be used + * @IWL_UCODE_TLV_API_WOWLAN_KEY_MATERIAL: WoWLAN key material support * @IWL_UCODE_TLV_API_QUOTA_LOW_LATENCY: Quota command includes a field * indicating low latency direction. * @IWL_UCODE_TLV_API_DEPRECATE_TTAK: RX status flag TTAK ok (bit 7) is @@ -245,6 +248,7 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t; * SCAN_OFFLOAD_PROFILES_QUERY_RSP_S. * @IWL_UCODE_TLV_API_MBSSID_HE: This ucode supports v2 of * STA_CONTEXT_DOT11AX_API_S + * @IWL_UCODE_TLV_API_WOWLAN_TCP_SYN_WAKE: WoWLAN TCP-SYN wake support * @IWL_UCODE_TLV_API_FTM_RTT_ACCURACY: version 7 of the range response API * is supported by FW, this indicates the RTT confidence value * @IWL_UCODE_TLV_API_SAR_TABLE_VER: This ucode supports different sar @@ -253,6 +257,7 @@ typedef unsigned int __bitwise iwl_ucode_tlv_api_t; * SCAN_CONFIG_DB_CMD_API_S. * @IWL_UCODE_TLV_API_ADWELL_HB_DEF_N_AP: support for setting adaptive dwell * number of APs in the 5 GHz band + * @IWL_UCODE_TLV_API_SCAN_EXT_CHAN_VER: extended channel config in scan * @IWL_UCODE_TLV_API_BAND_IN_RX_DATA: FW reports band number in RX notification * @IWL_UCODE_TLV_API_NO_HOST_DISABLE_TX: Firmware offloaded the station disable tx * logic. @@ -352,16 +357,24 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * @IWL_UCODE_TLV_CAPA_SOC_LATENCY_SUPPORT: the firmware supports setting * stabilization latency for SoCs. * @IWL_UCODE_TLV_CAPA_STA_PM_NOTIF: firmware will send STA PM notification + * @IWL_UCODE_TLV_CAPA_BINDING_CDB_SUPPORT: binding CDB support + * @IWL_UCODE_TLV_CAPA_CDB_SUPPORT: CDB support + * @IWL_UCODE_TLV_CAPA_D0I3_END_FIRST: D0I3 end command comes first * @IWL_UCODE_TLV_CAPA_TLC_OFFLOAD: firmware implements rate scaling algorithm * @IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA: firmware implements quota related * @IWL_UCODE_TLV_CAPA_COEX_SCHEMA_2: firmware implements Coex Schema 2 - * IWL_UCODE_TLV_CAPA_CHANNEL_SWITCH_CMD: firmware supports CSA command + * @IWL_UCODE_TLV_CAPA_CHANNEL_SWITCH_CMD: firmware supports CSA command * @IWL_UCODE_TLV_CAPA_ULTRA_HB_CHANNELS: firmware supports ultra high band * (6 GHz). * @IWL_UCODE_TLV_CAPA_CS_MODIFY: firmware supports modify action CSA command + * @IWL_UCODE_TLV_CAPA_SET_LTR_GEN2: LTR gen2 support + * @IWL_UCODE_TLV_CAPA_TAS_CFG: TAS configuration support + * @IWL_UCODE_TLV_CAPA_SESSION_PROT_CMD: session protection command + * @IWL_UCODE_TLV_CAPA_SET_PPAG: PPAG support * @IWL_UCODE_TLV_CAPA_EXTENDED_DTS_MEASURE: extended DTS measurement * @IWL_UCODE_TLV_CAPA_SHORT_PM_TIMEOUTS: supports short PM timeouts * @IWL_UCODE_TLV_CAPA_BT_MPLUT_SUPPORT: supports bt-coex Multi-priority LUT + * @IWL_UCODE_TLV_CAPA_MULTI_QUEUE_RX_SUPPORT: MQ RX support * @IWL_UCODE_TLV_CAPA_CSA_AND_TBTT_OFFLOAD: the firmware supports CSA * countdown offloading. Beacon notifications are not sent to the host. * The fw also offloads TBTT alignment. @@ -383,23 +396,46 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * command size (command version 4) that supports toggling ACK TX * power reduction. * @IWL_UCODE_TLV_CAPA_D3_DEBUG: supports debug recording during D3 + * @IWL_UCODE_TLV_CAPA_LED_CMD_SUPPORT: LED command support * @IWL_UCODE_TLV_CAPA_MCC_UPDATE_11AX_SUPPORT: MCC response support 11ax * capability. * @IWL_UCODE_TLV_CAPA_CSI_REPORTING: firmware is capable of being configured * to report the CSI information with (certain) RX frames + * @IWL_UCODE_TLV_CAPA_DBG_SUSPEND_RESUME_CMD_SUPP: suspend/resume command + * @IWL_UCODE_TLV_CAPA_DBG_BUF_ALLOC_CMD_SUPP: support for DBGC + * buffer allocation command * @IWL_UCODE_TLV_CAPA_FTM_CALIBRATED: has FTM calibrated and thus supports both * initiator and responder * @IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_UNII4_US_CA: supports (de)activating UNII-4 * for US/CA/WW from BIOS + * @IWL_UCODE_TLV_CAPA_PSC_CHAN_SUPPORT: supports PSC channels + * @IWL_UCODE_TLV_CAPA_BIGTK_SUPPORT: BIGTK support * @IWL_UCODE_TLV_CAPA_PROTECTED_TWT: Supports protection of TWT action frames * @IWL_UCODE_TLV_CAPA_FW_RESET_HANDSHAKE: Supports the firmware handshake in * reset flow * @IWL_UCODE_TLV_CAPA_PASSIVE_6GHZ_SCAN: Support for passive scan on 6GHz PSC * channels even when these are not enabled. + * @IWL_UCODE_TLV_CAPA_HIDDEN_6GHZ_SCAN: hidden SSID 6 GHz scan support + * @IWL_UCODE_TLV_CAPA_BROADCAST_TWT: broadcast TWT support + * @IWL_UCODE_TLV_CAPA_COEX_HIGH_PRIO: support for BT-coex high + * priority for 802.1X/4-way-HS + * @IWL_UCODE_TLV_CAPA_BAID_ML_SUPPORT: multi-link BAID support + * @IWL_UCODE_TLV_CAPA_SYNCED_TIME: synced time command support + * @IWL_UCODE_TLV_CAPA_TIME_SYNC_BOTH_FTM_TM: time sync support + * @IWL_UCODE_TLV_CAPA_BIGTK_TX_SUPPORT: BIGTK TX support + * @IWL_UCODE_TLV_CAPA_MLD_API_SUPPORT: MLD API support + * @IWL_UCODE_TLV_CAPA_SCAN_DONT_TOGGLE_ANT: fixed antenna scan support + * @IWL_UCODE_TLV_CAPA_PPAG_CHINA_BIOS_SUPPORT: PPAG China BIOS support + * @IWL_UCODE_TLV_CAPA_OFFLOAD_BTM_SUPPORT: BTM protocol offload support + * @IWL_UCODE_TLV_CAPA_STA_EXP_MFP_SUPPORT: STA command MFP support + * @IWL_UCODE_TLV_CAPA_SNIFF_VALIDATE_SUPPORT: sniffer validate bits support + * @IWL_UCODE_TLV_CAPA_CHINA_22_REG_SUPPORT: China 2022 regulator support * @IWL_UCODE_TLV_CAPA_DUMP_COMPLETE_SUPPORT: Support for indicating dump collection * complete to FW. * @IWL_UCODE_TLV_CAPA_SPP_AMSDU_SUPPORT: Support SPP (signaling and payload * protected) A-MSDU. + * @IWL_UCODE_TLV_CAPA_DRAM_FRAG_SUPPORT: support for DBGC fragmented + * DRAM buffers * @IWL_UCODE_TLV_CAPA_SECURE_LTF_SUPPORT: Support secure LTF measurement. * @IWL_UCODE_TLV_CAPA_MONITOR_PASSIVE_CHANS: Support monitor mode on otherwise * passive channels @@ -407,6 +443,8 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t; * for CA from BIOS. * @IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT: supports %TAS_UHB_ALLOWED_CANADA * @IWL_UCODE_TLV_CAPA_EXT_FSEQ_IMAGE_SUPPORT: external FSEQ image support + * @IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT: FW reset handshake is needed + * during assert handling even if the dump isn't split * @IWL_UCODE_TLV_CAPA_FW_ACCEPTS_RAW_DSM_TABLE: Firmware has capability of * handling raw DSM table data. * @@ -487,12 +525,7 @@ enum iwl_ucode_tlv_capa { /* set 3 */ IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_UNII4_US_CA = (__force iwl_ucode_tlv_capa_t)96, - - /* - * @IWL_UCODE_TLV_CAPA_PSC_CHAN_SUPPORT: supports PSC channels - */ IWL_UCODE_TLV_CAPA_PSC_CHAN_SUPPORT = (__force iwl_ucode_tlv_capa_t)98, - IWL_UCODE_TLV_CAPA_BIGTK_SUPPORT = (__force iwl_ucode_tlv_capa_t)100, IWL_UCODE_TLV_CAPA_SPP_AMSDU_SUPPORT = (__force iwl_ucode_tlv_capa_t)103, IWL_UCODE_TLV_CAPA_DRAM_FRAG_SUPPORT = (__force iwl_ucode_tlv_capa_t)104, @@ -514,11 +547,8 @@ enum iwl_ucode_tlv_capa { IWL_UCODE_TLV_CAPA_EXT_FSEQ_IMAGE_SUPPORT = (__force iwl_ucode_tlv_capa_t)125, /* set 4 */ - /** - * @IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT: FW reset handshake is needed - * during assert handling even if the dump isn't split - */ - IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT = (__force iwl_ucode_tlv_capa_t)(4 * 32 + 0), + + IWL_UCODE_TLV_CAPA_RESET_DURING_ASSERT = (__force iwl_ucode_tlv_capa_t)(4 * 32 + 0), IWL_UCODE_TLV_CAPA_FW_ACCEPTS_RAW_DSM_TABLE = (__force iwl_ucode_tlv_capa_t)(4 * 32 + 1), NUM_IWL_UCODE_TLV_CAPA /* @@ -852,6 +882,8 @@ struct iwl_fw_dbg_trigger_low_rssi { * @start_assoc_denied: number of denied association to start recording * @start_assoc_timeout: number of association timeout to start recording * @start_connection_loss: number of connection loss to start recording + * @reserved: reserved + * @reserved2: reserved */ struct iwl_fw_dbg_trigger_mlme { u8 stop_auth_denied; @@ -885,6 +917,7 @@ struct iwl_fw_dbg_trigger_mlme { * @p2p_device: timeout for the queues of a P2P device in ms * @ibss: timeout for the queues of an IBSS in ms * @tdls: timeout for the queues of a TDLS station in ms + * @reserved: reserved */ struct iwl_fw_dbg_trigger_txq_timer { __le32 command_queue; @@ -900,7 +933,7 @@ struct iwl_fw_dbg_trigger_txq_timer { /** * struct iwl_fw_dbg_trigger_time_event - configures a time event trigger - * time_Events: a list of tuples . The driver will issue a + * @time_events: a list of tuples . The driver will issue a * trigger each time a time event notification that relates to time event * id with one of the actions in the bitmap is received and * BIT(notif->status) is set in status_bitmap. @@ -916,19 +949,19 @@ struct iwl_fw_dbg_trigger_time_event { /** * struct iwl_fw_dbg_trigger_ba - configures BlockAck related trigger - * rx_ba_start: tid bitmap to configure on what tid the trigger should occur + * @rx_ba_start: tid bitmap to configure on what tid the trigger should occur * when an Rx BlockAck session is started. - * rx_ba_stop: tid bitmap to configure on what tid the trigger should occur + * @rx_ba_stop: tid bitmap to configure on what tid the trigger should occur * when an Rx BlockAck session is stopped. - * tx_ba_start: tid bitmap to configure on what tid the trigger should occur + * @tx_ba_start: tid bitmap to configure on what tid the trigger should occur * when a Tx BlockAck session is started. - * tx_ba_stop: tid bitmap to configure on what tid the trigger should occur + * @tx_ba_stop: tid bitmap to configure on what tid the trigger should occur * when a Tx BlockAck session is stopped. - * rx_bar: tid bitmap to configure on what tid the trigger should occur + * @rx_bar: tid bitmap to configure on what tid the trigger should occur * when a BAR is received (for a Tx BlockAck session). - * tx_bar: tid bitmap to configure on what tid the trigger should occur + * @tx_bar: tid bitmap to configure on what tid the trigger should occur * when a BAR is send (for an Rx BlocAck session). - * frame_timeout: tid bitmap to configure on what tid the trigger should occur + * @frame_timeout: tid bitmap to configure on what tid the trigger should occur * when a frame times out in the reordering buffer. */ struct iwl_fw_dbg_trigger_ba { @@ -946,6 +979,7 @@ struct iwl_fw_dbg_trigger_ba { * @action_bitmap: the TDLS action to trigger the collection upon * @peer_mode: trigger on specific peer or all * @peer: the TDLS peer to trigger the collection on + * @reserved: reserved */ struct iwl_fw_dbg_trigger_tdls { u8 action_bitmap; @@ -958,6 +992,7 @@ struct iwl_fw_dbg_trigger_tdls { * struct iwl_fw_dbg_trigger_tx_status - configures trigger for tx response * status. * @statuses: the list of statuses to trigger the collection on + * @reserved: reserved */ struct iwl_fw_dbg_trigger_tx_status { struct tx_status { @@ -971,6 +1006,7 @@ struct iwl_fw_dbg_trigger_tx_status { * struct iwl_fw_dbg_conf_tlv - a TLV that describes a debug configuration. * @id: conf id * @usniffer: should the uSniffer image be used + * @reserved: reserved * @num_of_hcmds: how many HCMDs to send are present here * @hcmd: a variable length host command to be sent to apply the configuration. * If there is more than one HCMD to send, they will appear one after the diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h index 5256f20623e90..045a3e0094291 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/img.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h @@ -14,14 +14,13 @@ #include "error-dump.h" /** - * enum iwl_ucode_type - * - * The type of ucode. + * enum iwl_ucode_type - type of ucode * * @IWL_UCODE_REGULAR: Normal runtime ucode * @IWL_UCODE_INIT: Initial ucode * @IWL_UCODE_WOWLAN: Wake on Wireless enabled ucode * @IWL_UCODE_REGULAR_USNIFFER: Normal runtime ucode when using usniffer image + * @IWL_UCODE_TYPE_MAX: (internal value) */ enum iwl_ucode_type { IWL_UCODE_REGULAR, @@ -122,7 +121,7 @@ struct fw_img { #define FW_ADDR_CACHE_CONTROL 0xC0000000UL /** - * struct iwl_fw_paging + * struct iwl_fw_paging - FW paging descriptor * @fw_paging_phys: page phy pointer * @fw_paging_block: pointer to the allocated block * @fw_paging_size: page size @@ -197,6 +196,11 @@ struct iwl_dump_exclude { * @dump_excl_wowlan: image dump exclusion areas for WoWLAN image * @pnvm_data: PNVM data embedded in the .ucode file, if any * @pnvm_size: size of the embedded PNVM data + * @dbg: debug data, see &struct iwl_fw_dbg + * @default_calib: default calibration data + * @phy_config: PHY configuration flags + * @valid_rx_ant: valid RX antenna bitmap + * @valid_tx_ant: valid TX antenna bitmap */ struct iwl_fw { u32 ucode_ver; diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c index e1f28b0532530..d2ad169ae880f 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c +++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c @@ -543,32 +543,14 @@ static size_t iwl_get_lari_config_cmd_size(u8 cmd_ver) switch (cmd_ver) { case 12: - case 11: cmd_size = sizeof(struct iwl_lari_config_change_cmd); break; - case 10: - cmd_size = sizeof(struct iwl_lari_config_change_cmd_v10); - break; - case 9: case 8: - case 7: - cmd_size = sizeof(struct iwl_lari_config_change_cmd_v7); + cmd_size = sizeof(struct iwl_lari_config_change_cmd_v8); break; case 6: cmd_size = sizeof(struct iwl_lari_config_change_cmd_v6); break; - case 5: - cmd_size = sizeof(struct iwl_lari_config_change_cmd_v5); - break; - case 4: - cmd_size = sizeof(struct iwl_lari_config_change_cmd_v4); - break; - case 3: - cmd_size = sizeof(struct iwl_lari_config_change_cmd_v3); - break; - case 2: - cmd_size = sizeof(struct iwl_lari_config_change_cmd_v2); - break; default: cmd_size = sizeof(struct iwl_lari_config_change_cmd_v1); break; @@ -609,11 +591,11 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt, if (!has_raw_dsm_capa) value &= DSM_UNII4_ALLOW_BITMAP; - /* Since version 9, bits 4 and 5 are supported + /* Since version 12, bits 4 and 5 are supported * regardless of this capability, By pass this masking * if firmware has capability of accepting raw DSM table. */ - if (!has_raw_dsm_capa && cmd_ver < 9 && + if (!has_raw_dsm_capa && cmd_ver < 12 && !fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_5G9_FOR_CA)) value &= ~(DSM_VALUE_UNII4_CANADA_OVERRIDE_MSK | @@ -637,7 +619,7 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt, if (!has_raw_dsm_capa && cmd_ver < 12 && !fw_has_capa(&fwrt->fw->ucode_capa, IWL_UCODE_TLV_CAPA_BIOS_OVERRIDE_UNII4_US_CA)) - value &= CHAN_STATE_ACTIVE_BITMAP_CMD_V11; + value &= CHAN_STATE_ACTIVE_BITMAP_CMD_V8; cmd->chan_state_active_bitmap = cpu_to_le32(value); } diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h index 806f9bcdf4f50..57570ff15622e 100644 --- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h +++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h @@ -45,6 +45,8 @@ struct iwl_fwrt_shared_mem_cfg { * struct iwl_fwrt_dump_data - dump data * @trig: trigger the worker was scheduled upon * @fw_pkt: packet received from FW + * @desc: dump descriptor + * @monitor_only: only dump for monitor * * Note that the decision which part of the union is used * is based on iwl_trans_dbg_ini_valid(): the 'trig' part @@ -68,6 +70,7 @@ struct iwl_fwrt_dump_data { * struct iwl_fwrt_wk_data - dump worker data struct * @idx: index of the worker * @wk: worker + * @dump_data: dump data */ struct iwl_fwrt_wk_data { u8 idx; @@ -91,8 +94,8 @@ struct iwl_txf_iter_data { /** * struct iwl_fw_runtime - runtime data for firmware + * @trans: transport pointer * @fw: firmware image - * @cfg: NIC configuration * @dev: device pointer * @ops: user ops * @ops_ctx: user ops context @@ -117,6 +120,23 @@ struct iwl_txf_iter_data { * zero (default initialization) means it hasn't been read yet, * and BIT(0) is set when it has since function 0 also has this * bitmap and is always supported + * @geo_enabled: WGDS table is present + * @geo_num_profiles: number of geo profiles + * @geo_rev: geo profiles table revision + * @ppag_chains: PPAG table data + * @ppag_flags: PPAG flags + * @reduced_power_flags: reduced power flags + * @sanitize_ctx: context for dump sanitizer + * @sanitize_ops: dump sanitizer ops + * @sar_chain_a_profile: SAR chain A profile + * @sar_chain_b_profile: SAR chain B profile + * @sgom_enabled: SGOM enabled + * @sgom_table: SGOM table + * @timestamp: timestamp marker data + * @timestamp.wk: timestamp marking worker + * @timestamp.seq: timestamp marking sequence + * @timestamp.delay: timestamp marking worker delay + * @tpc_enabled: TPC enabled */ struct iwl_fw_runtime { struct iwl_trans *trans; diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h index a607e7ab914ba..076810ee5d341 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h @@ -170,7 +170,6 @@ struct iwl_fw_mon_regs { * for aggregation * @min_txq_size: minimum number of slots required in a TX queue * @gp2_reg_addr: GP2 (timer) register address - * @min_umac_error_event_table: minimum SMEM location of UMAC error table * @mon_dbgi_regs: monitor DBGI registers * @mon_dram_regs: monitor DRAM registers * @mon_smem_regs: monitor SMEM registers @@ -203,7 +202,6 @@ struct iwl_family_base_params { netdev_features_t features; u32 smem_offset; u32 smem_len; - u32 min_umac_error_event_table; u32 d3_debug_data_base_addr; u32 d3_debug_data_length; u32 min_txq_size; @@ -385,7 +383,7 @@ struct iwl_mac_cfg { #define IWL_NUM_RBDS_EHT (512 * 8) /** - * struct iwl_rf_cfg + * struct iwl_rf_cfg - RF/CRF configuration data * @fw_name_pre: Firmware filename prefix. The api version and extension * (.ucode) will be added to filename before loading from disk. The * filename is constructed as -.ucode. @@ -418,6 +416,7 @@ struct iwl_mac_cfg { * @vht_mu_mimo_supported: VHT MU-MIMO support * @nvm_type: see &enum iwl_nvm_type * @uhb_supported: ultra high band channels supported + * @eht_supported: EHT supported * @num_rbds: number of receive buffer descriptors to use * (only used for multi-queue capable devices) * @@ -450,7 +449,8 @@ struct iwl_rf_cfg { host_interrupt_operation_mode:1, lp_xtal_workaround:1, vht_mu_mimo_supported:1, - uhb_supported:1; + uhb_supported:1, + eht_supported:1; u8 valid_tx_ant; u8 valid_rx_ant; u8 non_shared_ant; @@ -686,8 +686,10 @@ extern const char iwl_be211_name[]; extern const char iwl_killer_bn1850w2_name[]; extern const char iwl_killer_bn1850i_name[]; extern const char iwl_bn201_name[]; +extern const char iwl_bn203_name[]; extern const char iwl_be221_name[]; extern const char iwl_be223_name[]; +extern const char iwl_ax221_name[]; #if IS_ENABLED(CONFIG_IWLDVM) extern const struct iwl_rf_cfg iwl5300_agn_cfg; extern const struct iwl_rf_cfg iwl5350_agn_cfg; @@ -743,6 +745,7 @@ extern const struct iwl_rf_cfg iwl_rf_fm; extern const struct iwl_rf_cfg iwl_rf_fm_160mhz; #define iwl_rf_wh iwl_rf_fm #define iwl_rf_wh_160mhz iwl_rf_fm_160mhz +extern const struct iwl_rf_cfg iwl_rf_wh_non_eht; #define iwl_rf_pe iwl_rf_fm #endif /* CONFIG_IWLMLD */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h index 7ed6329fd8ca1..fe4e46a0edbda 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2018-2023 Intel Corporation + * Copyright (C) 2018-2023, 2025 Intel Corporation */ #ifndef __iwl_dbg_tlv_h__ #define __iwl_dbg_tlv_h__ @@ -32,7 +32,7 @@ union iwl_dbg_tlv_tp_data { }; /** - * struct iwl_dbg_tlv_time_point_data + * struct iwl_dbg_tlv_time_point_data - debug time point data * @trig_list: list of triggers * @active_trig_list: list of active triggers * @hcmd_list: list of host commands diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index 607fcea6f4efc..3391f07b01de3 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -177,9 +177,10 @@ static inline char iwl_drv_get_step(int step) return 'a' + step; } -static bool iwl_drv_is_wifi7_supported(struct iwl_trans *trans) +bool iwl_drv_is_wifi7_supported(struct iwl_trans *trans) { - return CSR_HW_RFID_TYPE(trans->info.hw_rf_id) >= IWL_CFG_RF_TYPE_FM; + return trans->mac_cfg->device_family >= IWL_DEVICE_FAMILY_BZ && + CSR_HW_RFID_TYPE(trans->info.hw_rf_id) >= IWL_CFG_RF_TYPE_FM; } const char *iwl_drv_get_fwname_pre(struct iwl_trans *trans, char *buf) @@ -347,8 +348,8 @@ static int iwl_request_firmware(struct iwl_drv *drv, bool first) if (first) drv->fw_index = ucode_api_max; - else if (drv->fw_index == ENCODE_CORE_AS_API(99)) - drv->fw_index = 101; /* last API-scheme number below core 99 */ + else if (drv->fw_index == ENCODE_CORE_AS_API(100)) + drv->fw_index = 102; /* last API-scheme number below core 100 */ else drv->fw_index--; @@ -427,7 +428,6 @@ struct iwl_firmware_pieces { size_t dbg_trigger_tlv_len[FW_DBG_TRIGGER_MAX]; struct iwl_fw_dbg_mem_seg_tlv *dbg_mem_tlv; size_t n_mem_tlv; - u32 major; }; static void alloc_sec_data(struct iwl_firmware_pieces *pieces, @@ -1069,19 +1069,19 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, break; case IWL_UCODE_TLV_FW_VERSION: { const __le32 *ptr = (const void *)tlv_data; - u32 minor; + u32 major, minor; u8 local_comp; if (tlv_len != sizeof(u32) * 3) goto invalid_tlv_len; - pieces->major = le32_to_cpup(ptr++); + major = le32_to_cpup(ptr++); minor = le32_to_cpup(ptr++); local_comp = le32_to_cpup(ptr); snprintf(drv->fw.fw_version, sizeof(drv->fw.fw_version), - "%u.%08x.%u %s", pieces->major, minor, + "%u.%08x.%u %s", major, minor, local_comp, iwl_reduced_fw_name(drv)); break; } @@ -1589,8 +1589,6 @@ static void _iwl_op_mode_stop(struct iwl_drv *drv) } } -#define IWL_MLD_SUPPORTED_FW_VERSION 97 - /* * iwl_req_fw_callback - callback when firmware was loaded * @@ -1859,17 +1857,8 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context) } #if IS_ENABLED(CONFIG_IWLMLD) - if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION && - iwl_drv_is_wifi7_supported(drv->trans)) + if (iwl_drv_is_wifi7_supported(drv->trans)) op = &iwlwifi_opmode_table[MLD_OP_MODE]; -#else - if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION && - iwl_drv_is_wifi7_supported(drv->trans)) { - IWL_ERR(drv, - "IWLMLD needs to be compiled to support this firmware\n"); - mutex_unlock(&iwlwifi_opmode_table_mtx); - goto out_unbind; - } #endif IWL_INFO(drv, "loaded firmware version %s op_mode %s\n", diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h index 595300a14639d..6e60953de2ec4 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.h @@ -62,7 +62,8 @@ struct iwl_rf_cfg; * starts the driver: fetches the firmware. This should be called by bus * specific system flows implementations. For example, the bus specific probe * function should do bus related operations only, and then call to this - * function. It returns the driver object or %NULL if an error occurred. + * function. + * Return: the driver object or %NULL if an error occurred. */ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans); @@ -77,6 +78,12 @@ struct iwl_drv *iwl_drv_start(struct iwl_trans *trans); */ void iwl_drv_stop(struct iwl_drv *drv); +/* + * iwl_drv_is_wifi7_supported - returns if wifi7 is supported + * If yes, iwlmld needs to be used to drive the device. + */ +bool iwl_drv_is_wifi7_supported(struct iwl_trans *trans); + /* * exported symbol management * diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h index 21eabfc3ffc84..0476df7b7f179 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ /* - * Copyright (C) 2005-2014, 2018-2022, 2024 Intel Corporation + * Copyright (C) 2005-2014, 2018-2022, 2024-2025 Intel Corporation */ #ifndef __iwl_modparams_h__ #define __iwl_modparams_h__ @@ -42,7 +42,7 @@ enum iwl_uapsd_disable { }; /** - * struct iwl_mod_params + * struct iwl_mod_params - module parameters for iwlwifi * * Holds the module parameters * diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c index 23465e4c4b399..e021fc57d85d2 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c @@ -2080,7 +2080,7 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans, !!(mac_flags & NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED); nvm->sku_cap_mimo_disabled = !!(mac_flags & NVM_MAC_SKU_FLAGS_MIMO_DISABLED); - if (CSR_HW_RFID_TYPE(trans->info.hw_rf_id) >= IWL_CFG_RF_TYPE_FM) + if (trans->cfg->eht_supported) nvm->sku_cap_11be_enable = true; /* Initialize PHY sku data */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h index cbc92abf9f87a..12f28bb0e859d 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.h @@ -115,11 +115,12 @@ iwl_parse_nvm_data(struct iwl_trans *trans, const struct iwl_rf_cfg *cfg, * iwl_parse_nvm_mcc_info - parse MCC (mobile country code) info coming from FW * * This function parses the regulatory channel data received as a - * MCC_UPDATE_CMD command. It returns a newly allocation regulatory domain, - * to be fed into the regulatory core. In case the geo_info is set handle - * accordingly. An ERR_PTR is returned on error. - * If not given to the regulatory core, the user is responsible for freeing - * the regdomain returned here with kfree. + * MCC_UPDATE_CMD command. + * + * Return: a newly allocation regulatory domain, to be given to the regulatory + * core. In case the geo_info is set handle accordingly. An ERR_PTR is + * returned on error. If not given to the regulatory core, the user is + * responsible for freeing the regdomain returned here with kfree(). * * @trans: the transport * @num_of_ch: the number of channels @@ -140,6 +141,8 @@ iwl_parse_nvm_mcc_info(struct iwl_trans *trans, * This struct holds an NVM section read from the NIC using NVM_ACCESS_CMD, * and saved for later use by the driver. Not all NVM sections are saved * this way, only the needed ones. + * @length: length of the section + * @data: section data */ struct iwl_nvm_section { u16 length; @@ -148,6 +151,10 @@ struct iwl_nvm_section { /** * iwl_read_external_nvm - Reads external NVM from a file into nvm_sections + * @trans: the transport + * @nvm_file_name: the filename to request + * @nvm_sections: sections data to fill + * Return: 0 on success or an error code */ int iwl_read_external_nvm(struct iwl_trans *trans, const char *nvm_file_name, diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h index a146d0e399f22..df6341dfc4a12 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-op-mode.h @@ -185,6 +185,7 @@ void iwl_opmode_deregister(const char *name); /** * struct iwl_op_mode - operational mode * @ops: pointer to its own ops + * @op_mode_specific: per-opmode data * * This holds an implementation of the mac80211 / fw API. */ diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h index a0cc5d7745e8f..a552669db6e2a 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h +++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h @@ -121,7 +121,7 @@ enum CMD_MODE { #define DEF_CMD_PAYLOAD_SIZE 320 /** - * struct iwl_device_cmd + * struct iwl_device_cmd - device command structure * * For allocation of the command and tx queues, this establishes the overall * size of the largest command we send to uCode, except for commands that @@ -516,7 +516,7 @@ enum iwl_trans_state { */ /** - * enum iwl_ini_cfg_state + * enum iwl_ini_cfg_state - debug config state * @IWL_INI_CFG_STATE_NOT_LOADED: no debug cfg was given * @IWL_INI_CFG_STATE_LOADED: debug cfg was found and loaded * @IWL_INI_CFG_STATE_CORRUPTED: debug cfg was found and some of the TLVs @@ -532,7 +532,7 @@ enum iwl_ini_cfg_state { #define IWL_TRANS_NMI_TIMEOUT (HZ / 4) /** - * struct iwl_dram_data + * struct iwl_dram_data - DRAM data descriptor * @physical: page phy pointer * @block: pointer to the allocated block/page * @size: size of the block/page diff --git a/drivers/net/wireless/intel/iwlwifi/mld/constants.h b/drivers/net/wireless/intel/iwlwifi/mld/constants.h index 49accf96f44b6..5d23a618ae3ca 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/constants.h +++ b/drivers/net/wireless/intel/iwlwifi/mld/constants.h @@ -75,5 +75,7 @@ #define IWL_MLD_FTM_RESP_LMR_FEEDBACK_SUPPORT true #define IWL_MLD_FTM_NON_TB_MIN_TIME_BETWEEN_MSR 7 #define IWL_MLD_FTM_NON_TB_MAX_TIME_BETWEEN_MSR 1000 +#define IWL_MLD_STA_EXT_CAPA_SIZE 9 +#define IWL_MLD_EXT_CAPA_NUM_IFTYPES 1 #endif /* __iwl_mld_constants_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c index 1d4282a21f09e..dd85be94433cc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/d3.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c @@ -1794,6 +1794,10 @@ iwl_mld_send_proto_offload(struct iwl_mld *mld, u32 enabled = 0; cmd = kzalloc(hcmd.len[0], GFP_KERNEL); + if (!cmd) { + IWL_DEBUG_WOWLAN(mld, "Failed to allocate proto offload cmd\n"); + return -ENOMEM; + } #if IS_ENABLED(CONFIG_IPV6) struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c index b372173c4a795..19da521a4babc 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c @@ -124,9 +124,8 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, u16 status; switch (version) { - case 6: case 7: - expected_sz = sizeof(struct iwl_alive_ntf_v6); + expected_sz = sizeof(struct iwl_alive_ntf_v7); break; case 8: expected_sz = sizeof(struct iwl_alive_ntf); @@ -168,11 +167,7 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, umac_error_table = le32_to_cpu(umac->dbg_ptrs.error_info_addr) & ~FW_ADDR_CACHE_CONTROL; - if (umac_error_table >= trans->mac_cfg->base->min_umac_error_event_table) - iwl_fw_umac_set_alive_err_table(trans, umac_error_table); - else - IWL_ERR(mld, "Not valid error log pointer 0x%08X\n", - umac_error_table); + iwl_fw_umac_set_alive_err_table(trans, umac_error_table); alive_data->valid = status == IWL_ALIVE_STATUS_OK; @@ -188,9 +183,8 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, le32_to_cpu(umac->umac_major), le32_to_cpu(umac->umac_minor)); - if (version >= 7) - IWL_DEBUG_FW(mld, "FW alive flags 0x%x\n", - le16_to_cpu(palive->flags)); + IWL_DEBUG_FW(mld, "FW alive flags 0x%x\n", + le16_to_cpu(palive->flags)); if (version >= 8) IWL_DEBUG_FW(mld, "platform_id 0x%llx\n", diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c index ed379825a9236..a5ececfc13e44 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c @@ -528,6 +528,19 @@ void iwl_mld_handle_probe_resp_data_notif(struct iwl_mld *mld, mld_link = &iwl_mld_vif_from_mac80211(vif)->deflink; + /* len_low should be 2 + n*13 (where n is the number of descriptors. + * 13 is the size of a NoA descriptor). We can have either one or two + * descriptors. + */ + if (IWL_FW_CHECK(mld, notif->noa_active && + notif->noa_attr.len_low != 2 + + sizeof(struct ieee80211_p2p_noa_desc) && + notif->noa_attr.len_low != 2 + + sizeof(struct ieee80211_p2p_noa_desc) * 2, + "Invalid noa_attr.len_low (%d)\n", + notif->noa_attr.len_low)) + return; + new_data = kzalloc(sizeof(*new_data), GFP_KERNEL); if (!new_data) return; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c index f6f52d297a72c..d89840a1152bd 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/link.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c @@ -465,10 +465,13 @@ int iwl_mld_add_link(struct iwl_mld *mld, int ret; if (!link) { - if (is_deflink) + if (is_deflink) { link = &mld_vif->deflink; - else + } else { link = kzalloc(sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + } } else { WARN_ON(!mld->fw_status.in_hw_restart); } @@ -572,8 +575,12 @@ void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld, /* Not in EMLSR and we can't hear the link. * Try to switch to a better link. EMLSR case is handled below. */ - if (!iwl_mld_emlsr_active(vif)) + if (!iwl_mld_emlsr_active(vif)) { + IWL_DEBUG_EHT(mld, + "missed beacons exceeds threshold. link_id=%u. Try to switch to a better link.\n", + link_id); iwl_mld_int_mlo_scan(mld, vif); + } } /* no more logic if we're not in EMLSR */ @@ -592,7 +599,8 @@ void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld, return; IWL_DEBUG_EHT(mld, - "missed bcn on the other link (link_id=%u): %u\n", + "missed bcn link_id=%u: %u consecutive=%u, other link_id=%u: %u\n", + link_id, missed_bcon, missed_bcon_since_rx, other_link->link_id, scnd_lnk_bcn_lost); /* Exit EMLSR if we lost more than diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c index 5725104a53bf0..55b484c162807 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c @@ -23,6 +23,7 @@ #include "roc.h" #include "mlo.h" #include "stats.h" +#include "iwl-nvm-parse.h" #include "ftm-initiator.h" #include "low_latency.h" #include "fw/api/scan.h" @@ -75,13 +76,12 @@ iwl_mld_iface_combinations[] = { }, }; -static const u8 if_types_ext_capa_sta[] = { - [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING, - [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT, - [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF | - WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB, - [8] = WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB, - [9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT, +static const u8 ext_capa_base[IWL_MLD_STA_EXT_CAPA_SIZE] = { + [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING, + [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT, + [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF | + WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB, + [8] = WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB, }; #define IWL_MLD_EMLSR_CAPA (IEEE80211_EML_CAP_EMLSR_SUPP | \ @@ -94,18 +94,6 @@ static const u8 if_types_ext_capa_sta[] = { IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME) | \ IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT) -static const struct wiphy_iftype_ext_capab iftypes_ext_capa[] = { - { - .iftype = NL80211_IFTYPE_STATION, - .extended_capabilities = if_types_ext_capa_sta, - .extended_capabilities_mask = if_types_ext_capa_sta, - .extended_capabilities_len = sizeof(if_types_ext_capa_sta), - /* relevant only if EHT is supported */ - .eml_capabilities = IWL_MLD_EMLSR_CAPA, - .mld_capa_and_ops = IWL_MLD_CAPA_OPS, - }, -}; - static void iwl_mld_hw_set_addresses(struct iwl_mld *mld) { struct wiphy *wiphy = mld->wiphy; @@ -335,21 +323,37 @@ static void iwl_mac_hw_set_wiphy(struct iwl_mld *mld) if (fw_has_capa(ucode_capa, IWL_UCODE_TLV_CAPA_PROTECTED_TWT)) wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_PROTECTED_TWT); - wiphy->iftype_ext_capab = NULL; - wiphy->num_iftype_ext_capab = 0; - - if (!iwlwifi_mod_params.disable_11ax) { - wiphy->iftype_ext_capab = iftypes_ext_capa; - wiphy->num_iftype_ext_capab = ARRAY_SIZE(iftypes_ext_capa); - - ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); - ieee80211_hw_set(hw, SUPPORTS_ONLY_HE_MULTI_BSSID); - } - if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM) wiphy->flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; else wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT; + + /* We are done for non-HE */ + if (iwlwifi_mod_params.disable_11ax) + return; + + ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID); + ieee80211_hw_set(hw, SUPPORTS_ONLY_HE_MULTI_BSSID); + + wiphy->iftype_ext_capab = mld->ext_capab; + wiphy->num_iftype_ext_capab = ARRAY_SIZE(mld->ext_capab); + + BUILD_BUG_ON(sizeof(mld->sta_ext_capab) < sizeof(ext_capa_base)); + + memcpy(mld->sta_ext_capab, ext_capa_base, sizeof(ext_capa_base)); + + mld->ext_capab[0].iftype = NL80211_IFTYPE_STATION; + mld->ext_capab[0].extended_capabilities = mld->sta_ext_capab; + mld->ext_capab[0].extended_capabilities_mask = mld->sta_ext_capab; + mld->ext_capab[0].extended_capabilities_len = sizeof(mld->sta_ext_capab); + + if (!mld->nvm_data->sku_cap_11be_enable || + iwlwifi_mod_params.disable_11be) + return; + + mld->ext_capab[0].eml_capabilities = IWL_MLD_EMLSR_CAPA; + mld->ext_capab[0].mld_capa_and_ops = IWL_MLD_CAPA_OPS; + } static void iwl_mac_hw_set_misc(struct iwl_mld *mld) @@ -393,11 +397,9 @@ static int iwl_mld_hw_verify_preconditions(struct iwl_mld *mld) TLC_MNG_UPDATE_NOTIF, 0) >= 4) + (iwl_fw_lookup_notif_ver(mld->fw, LEGACY_GROUP, REPLY_RX_MPDU_CMD, 0) >= 6) + - (iwl_fw_lookup_notif_ver(mld->fw, DATA_PATH_GROUP, - RX_NO_DATA_NOTIF, 0) >= 4) + (iwl_fw_lookup_notif_ver(mld->fw, LONG_GROUP, TX_CMD, 0) >= 9); - if (ratecheck != 0 && ratecheck != 5) { + if (ratecheck != 0 && ratecheck != 4) { IWL_ERR(mld, "Firmware has inconsistent rates\n"); return -EINVAL; } @@ -680,6 +682,8 @@ void iwl_mld_mac80211_remove_interface(struct ieee80211_hw *hw, #endif iwl_mld_rm_vif(mld, vif); + + mld->monitor.phy.valid = false; } struct iwl_mld_mc_iter_data { @@ -2591,11 +2595,44 @@ iwl_mld_can_neg_ttlm(struct ieee80211_hw *hw, struct ieee80211_vif *vif, return NEG_TTLM_RES_ACCEPT; } +static int iwl_mld_get_antenna(struct ieee80211_hw *hw, int radio_idx, + u32 *tx_ant, u32 *rx_ant) +{ + struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw); + + *tx_ant = iwl_mld_get_valid_tx_ant(mld); + *rx_ant = iwl_mld_get_valid_rx_ant(mld); + + return 0; +} + +static int iwl_mld_set_antenna(struct ieee80211_hw *hw, int radio_idx, + u32 tx_ant, u32 rx_ant) +{ + struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw); + + if (WARN_ON(!mld->nvm_data)) + return -EBUSY; + + /* mac80211 ensures the device is not started, + * so the firmware cannot be running + */ + + mld->set_tx_ant = tx_ant; + mld->set_rx_ant = rx_ant; + + iwl_reinit_cab(mld->trans, mld->nvm_data, tx_ant, rx_ant, mld->fw); + + return 0; +} + const struct ieee80211_ops iwl_mld_hw_ops = { .tx = iwl_mld_mac80211_tx, .start = iwl_mld_mac80211_start, .stop = iwl_mld_mac80211_stop, .config = iwl_mld_mac80211_config, + .get_antenna = iwl_mld_get_antenna, + .set_antenna = iwl_mld_set_antenna, .add_interface = iwl_mld_mac80211_add_interface, .remove_interface = iwl_mld_mac80211_remove_interface, .conf_tx = iwl_mld_mac80211_conf_tx, diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c index a6962256bdd12..8a4c96385640b 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c @@ -259,6 +259,7 @@ static const struct iwl_hcmd_names iwl_mld_data_path_names[] = { HCMD_NAME(MONITOR_NOTIF), HCMD_NAME(TLC_MNG_UPDATE_NOTIF), HCMD_NAME(BEACON_FILTER_IN_NOTIF), + HCMD_NAME(PHY_AIR_SNIFFER_NOTIF), HCMD_NAME(MU_GROUP_MGMT_NOTIF), }; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h index 94dc9da6360dc..22efe8e10f531 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h +++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h @@ -118,7 +118,11 @@ * @monitor.cur_bssid: current bssid tracked by the sniffer * @monitor.ptp_time: set the Rx mactime using the device's PTP clock time * @monitor.p80: primary channel position relative to he whole bandwidth, in - * steps of 80 MHz + * steps of 80 MHz + * @monitor.phy: PHY data information + * @monitor.phy.data: PHY data (&struct iwl_rx_phy_air_sniffer_ntfy) received + * @monitor.phy.valid: PHY data is valid (was received) + * @monitor.phy.used: PHY data was used by an RX * @fw_id_to_link_sta: maps a fw id of a sta to the corresponding * ieee80211_link_sta. This is not cleaned up on restart since we want to * preserve the fw sta ids during a restart (for SN/PN restoring). @@ -134,6 +138,8 @@ * @fw: a pointer to the fw object * @hw: pointer to the hw object. * @wiphy: a pointer to the wiphy struct, for easier access to it. + * @ext_capab: extended capabilities that will be set to wiphy on registration. + * @sta_ext_capab: extended capabilities for the station interface. * @nvm_data: pointer to the nvm_data that includes all our capabilities * @fwrt: fw runtime data * @debugfs_dir: debugfs directory @@ -180,6 +186,8 @@ * @mcast_filter_cmd: pointer to the multicast filter command. * @mgmt_tx_ant: stores the last TX antenna index; used for setting * TX rate_n_flags for non-STA mgmt frames (toggles on every TX failure). + * @set_tx_ant: stores the last TX antenna bitmask set by user space (if any) + * @set_rx_ant: stores the last RX antenna bitmask set by user space (if any) * @fw_rates_ver_3: FW rates are in version 3 * @low_latency: low-latency manager. * @tzone: thermal zone device's data @@ -205,6 +213,10 @@ struct iwl_mld { u32 ampdu_ref; bool ampdu_toggle; u8 p80; + struct { + struct iwl_rx_phy_air_sniffer_ntfy data; + u8 valid:1, used:1; + } phy; #ifdef CONFIG_IWLWIFI_DEBUGFS __le16 cur_aid; u8 cur_bssid[ETH_ALEN]; @@ -225,6 +237,8 @@ struct iwl_mld { const struct iwl_fw *fw; struct ieee80211_hw *hw; struct wiphy *wiphy; + struct wiphy_iftype_ext_capab ext_capab[IWL_MLD_EXT_CAPA_NUM_IFTYPES]; + u8 sta_ext_capab[IWL_MLD_STA_EXT_CAPA_SIZE]; struct iwl_nvm_data *nvm_data; struct iwl_fw_runtime fwrt; struct dentry *debugfs_dir; @@ -279,6 +293,9 @@ struct iwl_mld { u8 mgmt_tx_ant; + u8 set_tx_ant; + u8 set_rx_ant; + bool fw_rates_ver_3; struct iwl_mld_low_latency low_latency; @@ -374,6 +391,9 @@ static inline u8 iwl_mld_get_valid_tx_ant(const struct iwl_mld *mld) if (mld->nvm_data && mld->nvm_data->valid_tx_ant) tx_ant &= mld->nvm_data->valid_tx_ant; + if (mld->set_tx_ant) + tx_ant &= mld->set_tx_ant; + return tx_ant; } @@ -384,6 +404,9 @@ static inline u8 iwl_mld_get_valid_rx_ant(const struct iwl_mld *mld) if (mld->nvm_data && mld->nvm_data->valid_rx_ant) rx_ant &= mld->nvm_data->valid_rx_ant; + if (mld->set_rx_ant) + rx_ant &= mld->set_rx_ant; + return rx_ant; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c index 241a6271d13d6..c6b151f269216 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c @@ -31,11 +31,9 @@ static void iwl_mld_print_emlsr_blocked(struct iwl_mld *mld, u32 mask) { #define NAME_FMT(x) "%s" #define NAME_PR(x) (mask & IWL_MLD_EMLSR_BLOCKED_##x) ? "[" #x "]" : "", - IWL_DEBUG_INFO(mld, - "EMLSR blocked = " HANDLE_EMLSR_BLOCKED_REASONS(NAME_FMT) - " (0x%x)\n", - HANDLE_EMLSR_BLOCKED_REASONS(NAME_PR) - mask); + IWL_DEBUG_EHT(mld, + "EMLSR blocked = " HANDLE_EMLSR_BLOCKED_REASONS(NAME_FMT) + " (0x%x)\n", HANDLE_EMLSR_BLOCKED_REASONS(NAME_PR) mask); #undef NAME_FMT #undef NAME_PR } @@ -72,11 +70,9 @@ static void iwl_mld_print_emlsr_exit(struct iwl_mld *mld, u32 mask) { #define NAME_FMT(x) "%s" #define NAME_PR(x) (mask & IWL_MLD_EMLSR_EXIT_##x) ? "[" #x "]" : "", - IWL_DEBUG_INFO(mld, - "EMLSR exit = " HANDLE_EMLSR_EXIT_REASONS(NAME_FMT) - " (0x%x)\n", - HANDLE_EMLSR_EXIT_REASONS(NAME_PR) - mask); + IWL_DEBUG_EHT(mld, + "EMLSR exit = " HANDLE_EMLSR_EXIT_REASONS(NAME_FMT) + " (0x%x)\n", HANDLE_EMLSR_EXIT_REASONS(NAME_PR) mask); #undef NAME_FMT #undef NAME_PR } @@ -170,10 +166,10 @@ static void iwl_mld_check_emlsr_prevention(struct iwl_mld *mld, WARN_ON(mld_vif->emlsr.exit_repeat_count > 3); } - IWL_DEBUG_INFO(mld, - "Preventing EMLSR for %ld seconds due to %u exits with the reason = %s (0x%x)\n", - delay / HZ, mld_vif->emlsr.exit_repeat_count, - iwl_mld_get_emlsr_exit_string(reason), reason); + IWL_DEBUG_EHT(mld, + "Preventing EMLSR for %ld seconds due to %u exits with the reason = %s (0x%x)\n", + delay / HZ, mld_vif->emlsr.exit_repeat_count, + iwl_mld_get_emlsr_exit_string(reason), reason); wiphy_delayed_work_queue(mld->wiphy, &mld_vif->emlsr.prevent_done_wk, delay); @@ -217,10 +213,10 @@ static int _iwl_mld_exit_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif, link_to_keep = __ffs(vif->active_links); new_active_links = BIT(link_to_keep); - IWL_DEBUG_INFO(mld, - "Exiting EMLSR. reason = %s (0x%x). Current active links=0x%x, new active links = 0x%x\n", - iwl_mld_get_emlsr_exit_string(exit), exit, - vif->active_links, new_active_links); + IWL_DEBUG_EHT(mld, + "Exiting EMLSR. reason = %s (0x%x). Current active links=0x%x, new active links = 0x%x\n", + iwl_mld_get_emlsr_exit_string(exit), exit, + vif->active_links, new_active_links); if (sync) ret = ieee80211_set_active_links(vif, new_active_links); @@ -262,9 +258,8 @@ static int _iwl_mld_emlsr_block(struct iwl_mld *mld, struct ieee80211_vif *vif, mld_vif->emlsr.blocked_reasons |= reason; - IWL_DEBUG_INFO(mld, - "Blocking EMLSR mode. reason = %s (0x%x)\n", - iwl_mld_get_emlsr_blocked_string(reason), reason); + IWL_DEBUG_EHT(mld, "Blocking EMLSR mode. reason = %s (0x%x)\n", + iwl_mld_get_emlsr_blocked_string(reason), reason); iwl_mld_print_emlsr_blocked(mld, mld_vif->emlsr.blocked_reasons); if (reason == IWL_MLD_EMLSR_BLOCKED_TPT) @@ -335,9 +330,8 @@ void iwl_mld_unblock_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif, mld_vif->emlsr.blocked_reasons &= ~reason; - IWL_DEBUG_INFO(mld, - "Unblocking EMLSR mode. reason = %s (0x%x)\n", - iwl_mld_get_emlsr_blocked_string(reason), reason); + IWL_DEBUG_EHT(mld, "Unblocking EMLSR mode. reason = %s (0x%x)\n", + iwl_mld_get_emlsr_blocked_string(reason), reason); iwl_mld_print_emlsr_blocked(mld, mld_vif->emlsr.blocked_reasons); if (reason == IWL_MLD_EMLSR_BLOCKED_TPT) @@ -348,7 +342,7 @@ void iwl_mld_unblock_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif, if (mld_vif->emlsr.blocked_reasons) return; - IWL_DEBUG_INFO(mld, "EMLSR is unblocked\n"); + IWL_DEBUG_EHT(mld, "EMLSR is unblocked\n"); iwl_mld_int_mlo_scan(mld, vif); } @@ -365,18 +359,17 @@ iwl_mld_vif_iter_emlsr_mode_notif(void *data, u8 *mac, switch (action) { case ESR_RECOMMEND_LEAVE: - IWL_DEBUG_INFO(mld_vif->mld, - "FW recommend leave reason = 0x%x\n", - le32_to_cpu(notif->leave_reason_mask)); + IWL_DEBUG_EHT(mld_vif->mld, + "FW recommend leave reason = 0x%x\n", + le32_to_cpu(notif->leave_reason_mask)); iwl_mld_exit_emlsr(mld_vif->mld, vif, IWL_MLD_EMLSR_EXIT_FW_REQUEST, iwl_mld_get_primary_link(vif)); break; case ESR_FORCE_LEAVE: - IWL_DEBUG_INFO(mld_vif->mld, - "FW force leave reason = 0x%x\n", - le32_to_cpu(notif->leave_reason_mask)); + IWL_DEBUG_EHT(mld_vif->mld, "FW force leave reason = 0x%x\n", + le32_to_cpu(notif->leave_reason_mask)); fallthrough; case ESR_RECOMMEND_ENTER: default: @@ -412,11 +405,12 @@ void iwl_mld_handle_emlsr_trans_fail_notif(struct iwl_mld *mld, struct ieee80211_bss_conf *bss_conf = iwl_mld_fw_id_to_link_conf(mld, fw_link_id); - IWL_DEBUG_INFO(mld, "Failed to %s EMLSR on link %d (FW: %d), reason %d\n", - le32_to_cpu(notif->activation) ? "enter" : "exit", - bss_conf ? bss_conf->link_id : -1, - le32_to_cpu(notif->link_id), - le32_to_cpu(notif->err_code)); + IWL_DEBUG_EHT(mld, + "Failed to %s EMLSR on link %d (FW: %d), reason %d\n", + le32_to_cpu(notif->activation) ? "enter" : "exit", + bss_conf ? bss_conf->link_id : -1, + le32_to_cpu(notif->link_id), + le32_to_cpu(notif->err_code)); if (IWL_FW_CHECK(mld, !bss_conf, "FW reported failure to %sactivate EMLSR on a non-existing link: %d\n", @@ -590,8 +584,8 @@ void iwl_mld_emlsr_check_tpt(struct wiphy *wiphy, struct wiphy_work *wk) spin_unlock_bh(&queue_counter->lock); } - IWL_DEBUG_INFO(mld, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n", - total_tx, total_rx); + IWL_DEBUG_EHT(mld, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n", + total_tx, total_rx); /* If we don't have enough MPDUs - exit EMLSR */ if (total_tx < IWL_MLD_ENTER_EMLSR_TPT_THRESH && @@ -603,10 +597,10 @@ void iwl_mld_emlsr_check_tpt(struct wiphy *wiphy, struct wiphy_work *wk) /* EMLSR is not active */ if (sec_link_id == -1) - return; + goto schedule; - IWL_DEBUG_INFO(mld, "Secondary Link %d: Tx MPDUs: %ld. Rx MPDUs: %ld\n", - sec_link_id, sec_link_tx, sec_link_rx); + IWL_DEBUG_EHT(mld, "Secondary Link %d: Tx MPDUs: %ld. Rx MPDUs: %ld\n", + sec_link_id, sec_link_tx, sec_link_rx); /* Calculate the percentage of the secondary link TX/RX */ sec_link_tx_perc = total_tx ? sec_link_tx * 100 / total_tx : 0; @@ -625,6 +619,7 @@ void iwl_mld_emlsr_check_tpt(struct wiphy *wiphy, struct wiphy_work *wk) return; } +schedule: /* Check again when the next window ends */ wiphy_delayed_work_queue(mld_vif->mld->wiphy, &mld_vif->emlsr.check_tpt_wk, @@ -702,10 +697,8 @@ iwl_mld_emlsr_disallowed_with_link(struct iwl_mld *mld, ret |= IWL_MLD_EMLSR_EXIT_CSA; if (ret) { - IWL_DEBUG_INFO(mld, - "Link %d is not allowed for EMLSR as %s\n", - link->link_id, - primary ? "primary" : "secondary"); + IWL_DEBUG_EHT(mld, "Link %d is not allowed for EMLSR as %s\n", + link->link_id, primary ? "primary" : "secondary"); iwl_mld_print_emlsr_exit(mld, ret); } @@ -869,13 +862,12 @@ iwl_mld_emlsr_pair_state(struct ieee80211_vif *vif, reason_mask |= IWL_MLD_EMLSR_EXIT_CHAN_LOAD; if (reason_mask) { - IWL_DEBUG_INFO(mld, - "Links %d and %d are not a valid pair for EMLSR\n", - a->link_id, b->link_id); - IWL_DEBUG_INFO(mld, - "Links bandwidth are: %d and %d\n", - nl80211_chan_width_to_mhz(a->chandef->width), - nl80211_chan_width_to_mhz(b->chandef->width)); + IWL_DEBUG_EHT(mld, + "Links %d and %d are not a valid pair for EMLSR\n", + a->link_id, b->link_id); + IWL_DEBUG_EHT(mld, "Links bandwidth are: %d and %d\n", + nl80211_chan_width_to_mhz(a->chandef->width), + nl80211_chan_width_to_mhz(b->chandef->width)); iwl_mld_print_emlsr_exit(mld, reason_mask); } @@ -993,8 +985,8 @@ static void _iwl_mld_select_links(struct iwl_mld *mld, } set_active: - IWL_DEBUG_INFO(mld, "Link selection result: 0x%x. Primary = %d\n", - new_active, new_primary); + IWL_DEBUG_EHT(mld, "Link selection result: 0x%x. Primary = %d\n", + new_active, new_primary); mld_vif->emlsr.selected_primary = new_primary; mld_vif->emlsr.selected_links = new_active; diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.c b/drivers/net/wireless/intel/iwlwifi/mld/notif.c index 884973d0b3440..4cf3920b005fe 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/notif.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.c @@ -589,8 +589,8 @@ void iwl_mld_rx(struct iwl_op_mode *op_mode, struct napi_struct *napi, else if (unlikely(cmd_id == WIDE_ID(DATA_PATH_GROUP, RX_QUEUES_NOTIFICATION))) iwl_mld_handle_rx_queues_sync_notif(mld, napi, pkt, 0); - else if (cmd_id == WIDE_ID(DATA_PATH_GROUP, RX_NO_DATA_NOTIF)) - iwl_mld_rx_monitor_no_data(mld, napi, pkt, 0); + else if (cmd_id == WIDE_ID(DATA_PATH_GROUP, PHY_AIR_SNIFFER_NOTIF)) + iwl_mld_handle_phy_air_sniffer_notif(mld, napi, pkt); else iwl_mld_rx_notif(mld, rxb, pkt); } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/roc.c b/drivers/net/wireless/intel/iwlwifi/mld/roc.c index 4136c98030d04..4e37a288471e5 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/roc.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/roc.c @@ -231,7 +231,9 @@ void iwl_mld_handle_roc_notif(struct iwl_mld *mld, struct ieee80211_vif *vif; vif = iwl_mld_find_roc_vif(mld, activity); - if (WARN_ON(!vif)) + if (IWL_FW_CHECK(mld, !vif, + "unexpected ROC notif from FW for activity %d\n", + activity)) return; mld_vif = iwl_mld_vif_from_mac80211(vif); diff --git a/drivers/net/wireless/intel/iwlwifi/mld/rx.c b/drivers/net/wireless/intel/iwlwifi/mld/rx.c index 20d866dd92c2e..6a76e3fcb581c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/rx.c @@ -18,41 +18,32 @@ /* stores relevant PHY data fields extracted from iwl_rx_mpdu_desc */ struct iwl_mld_rx_phy_data { - enum iwl_rx_phy_info_type info_type; - __le32 data0; - __le32 data1; - __le32 data2; - __le32 data3; - __le32 eht_data4; - __le32 data5; - __le16 data4; + struct iwl_rx_phy_air_sniffer_ntfy *ntfy; bool first_subframe; bool with_data; - __le32 rx_vec[4]; u32 rate_n_flags; u32 gp2_on_air_rise; + /* phy_info is only valid when we have a frame, i.e. with_data=true */ u16 phy_info; u8 energy_a, energy_b; }; static void -iwl_mld_fill_phy_data(struct iwl_mld *mld, - struct iwl_rx_mpdu_desc *desc, - struct iwl_mld_rx_phy_data *phy_data) +iwl_mld_fill_phy_data_from_mpdu(struct iwl_mld *mld, + struct iwl_rx_mpdu_desc *desc, + struct iwl_mld_rx_phy_data *phy_data) { + if (unlikely(mld->monitor.phy.valid)) { + mld->monitor.phy.used = true; + phy_data->ntfy = &mld->monitor.phy.data; + } + phy_data->phy_info = le16_to_cpu(desc->phy_info); phy_data->rate_n_flags = iwl_v3_rate_from_v2_v3(desc->v3.rate_n_flags, mld->fw_rates_ver_3); phy_data->gp2_on_air_rise = le32_to_cpu(desc->v3.gp2_on_air_rise); phy_data->energy_a = desc->v3.energy_a; phy_data->energy_b = desc->v3.energy_b; - phy_data->data0 = desc->v3.phy_data0; - phy_data->data1 = desc->v3.phy_data1; - phy_data->data2 = desc->v3.phy_data2; - phy_data->data3 = desc->v3.phy_data3; - phy_data->data4 = desc->phy_data4; - phy_data->eht_data4 = desc->phy_eht_data4; - phy_data->data5 = desc->v3.phy_data5; phy_data->with_data = true; } @@ -217,26 +208,19 @@ static void iwl_mld_fill_signal(struct iwl_mld *mld, int link_id, } static void -iwl_mld_decode_he_phy_ru_alloc(struct iwl_mld_rx_phy_data *phy_data, - struct ieee80211_radiotap_he *he, - struct ieee80211_radiotap_he_mu *he_mu, - struct ieee80211_rx_status *rx_status) +iwl_mld_he_set_ru_alloc(struct ieee80211_rx_status *rx_status, + struct ieee80211_radiotap_he *he, + u8 ru_with_p80) { - /* Unfortunately, we have to leave the mac80211 data - * incorrect for the case that we receive an HE-MU - * transmission and *don't* have the HE phy data (due - * to the bits being used for TSF). This shouldn't - * happen though as management frames where we need - * the TSF/timers are not be transmitted in HE-MU. - */ - u8 ru = le32_get_bits(phy_data->data1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK); - u32 rate_n_flags = phy_data->rate_n_flags; - u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK; + u8 ru = ru_with_p80 >> 1; + u8 p80 = ru_with_p80 & 1; u8 offs = 0; rx_status->bw = RATE_INFO_BW_HE_RU; he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN); + he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN); switch (ru) { case 0 ... 36: @@ -266,227 +250,262 @@ iwl_mld_decode_he_phy_ru_alloc(struct iwl_mld_rx_phy_data *phy_data, rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996; break; } + he->data2 |= le16_encode_bits(offs, IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET); - he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN | - IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN); - if (phy_data->data1 & cpu_to_le32(IWL_RX_PHY_DATA1_HE_RU_ALLOC_SEC80)) - he->data2 |= - cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC); -#define CHECK_BW(bw) \ - BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_ ## bw ## MHZ != \ - RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS); \ - BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_ ## bw ## MHZ != \ - RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS) - CHECK_BW(20); - CHECK_BW(40); - CHECK_BW(80); - CHECK_BW(160); - - if (he_mu) - he_mu->flags2 |= - le16_encode_bits(u32_get_bits(rate_n_flags, - RATE_MCS_CHAN_WIDTH_MSK), - IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW); - else if (he_type == RATE_MCS_HE_TYPE_TRIG) - he->data6 |= - cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) | - le16_encode_bits(u32_get_bits(rate_n_flags, - RATE_MCS_CHAN_WIDTH_MSK), - IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW); + he->data2 |= le16_encode_bits(p80, IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC); } +#define RTAP_ENC_HE(src, src_msk, dst_msk) \ + le16_encode_bits(le32_get_bits(src, src_msk), dst_msk) + static void -iwl_mld_decode_he_mu_ext(struct iwl_mld_rx_phy_data *phy_data, - struct ieee80211_radiotap_he_mu *he_mu) +iwl_mld_decode_he_mu(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_radiotap_he *he, + struct ieee80211_radiotap_he_mu *he_mu, + struct ieee80211_rx_status *rx_status) { - u32 phy_data2 = le32_to_cpu(phy_data->data2); - u32 phy_data3 = le32_to_cpu(phy_data->data3); - u16 phy_data4 = le16_to_cpu(phy_data->data4); u32 rate_n_flags = phy_data->rate_n_flags; - if (u32_get_bits(phy_data4, IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CRC_OK)) { + he_mu->flags1 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.b, + OFDM_RX_FRAME_HE_SIGB_DCM, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM); + he_mu->flags1 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.b, + OFDM_RX_FRAME_HE_SIGB_MCS, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS); + he_mu->flags2 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a1, + OFDM_RX_FRAME_HE_PRMBL_PUNC_TYPE, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW); + he_mu->flags2 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_MU_NUM_OF_SIGB_SYM_OR_USER_NUM, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS); + he_mu->flags2 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.b, + OFDM_RX_FRAME_HE_MU_SIGB_COMP, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP); + + if (phy_data->ntfy->flags & IWL_SNIF_FLAG_VALID_RU && + le32_get_bits(phy_data->ntfy->sigs.he.cmn[2], + OFDM_RX_FRAME_HE_COMMON_CC1_CRC_OK)) { he_mu->flags1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN | IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN); he_mu->flags1 |= - le16_encode_bits(u32_get_bits(phy_data4, - IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CTR_RU), - IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU); - - he_mu->ru_ch1[0] = u32_get_bits(phy_data2, - IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU0); - he_mu->ru_ch1[1] = u32_get_bits(phy_data3, - IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU1); - he_mu->ru_ch1[2] = u32_get_bits(phy_data2, - IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU2); - he_mu->ru_ch1[3] = u32_get_bits(phy_data3, - IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU3); + RTAP_ENC_HE(phy_data->ntfy->sigs.he.cmn[2], + OFDM_RX_FRAME_HE_CENTER_RU_CC1, + IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU); + + he_mu->ru_ch1[0] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[0], + OFDM_RX_FRAME_HE_RU_ALLOC_0_A1); + he_mu->ru_ch1[1] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[1], + OFDM_RX_FRAME_HE_RU_ALLOC_1_C1); + he_mu->ru_ch1[2] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[0], + OFDM_RX_FRAME_HE_RU_ALLOC_0_A2); + he_mu->ru_ch1[3] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[1], + OFDM_RX_FRAME_HE_RU_ALLOC_1_C2); } - if (u32_get_bits(phy_data4, IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CRC_OK) && + if (phy_data->ntfy->flags & IWL_SNIF_FLAG_VALID_RU && + le32_get_bits(phy_data->ntfy->sigs.he.cmn[2], + OFDM_RX_FRAME_HE_COMMON_CC2_CRC_OK) && (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) != RATE_MCS_CHAN_WIDTH_20) { he_mu->flags1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN | IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN); he_mu->flags2 |= - le16_encode_bits(u32_get_bits(phy_data4, - IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CTR_RU), - IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU); - - he_mu->ru_ch2[0] = u32_get_bits(phy_data2, - IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU0); - he_mu->ru_ch2[1] = u32_get_bits(phy_data3, - IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU1); - he_mu->ru_ch2[2] = u32_get_bits(phy_data2, - IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU2); - he_mu->ru_ch2[3] = u32_get_bits(phy_data3, - IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU3); + RTAP_ENC_HE(phy_data->ntfy->sigs.he.cmn[2], + OFDM_RX_FRAME_HE_CENTER_RU_CC2, + IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU); + + he_mu->ru_ch2[0] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[0], + OFDM_RX_FRAME_HE_RU_ALLOC_0_B1); + he_mu->ru_ch2[1] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[1], + OFDM_RX_FRAME_HE_RU_ALLOC_1_D1); + he_mu->ru_ch2[2] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[0], + OFDM_RX_FRAME_HE_RU_ALLOC_0_B2); + he_mu->ru_ch2[3] = le32_get_bits(phy_data->ntfy->sigs.he.cmn[1], + OFDM_RX_FRAME_HE_RU_ALLOC_1_D2); } + +#define CHECK_BW(bw) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_ ## bw ## MHZ != \ + RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS) + CHECK_BW(20); + CHECK_BW(40); + CHECK_BW(80); + CHECK_BW(160); +#undef CHECK_BW + + he_mu->flags2 |= + le16_encode_bits(u32_get_bits(rate_n_flags, RATE_MCS_CHAN_WIDTH_MSK), + IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW); + + iwl_mld_he_set_ru_alloc(rx_status, he, + le32_get_bits(phy_data->ntfy->sigs.he.b, + OFDM_RX_FRAME_HE_SIGB_STA_RU)); +} + +static void +iwl_mld_decode_he_tb_phy_data(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_radiotap_he *he, + struct ieee80211_rx_status *rx_status) +{ + u32 rate_n_flags = phy_data->rate_n_flags; + u32 nsts; + + he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN); + + he->data4 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.a1, + OFDM_RX_HE_TRIG_SPATIAL_REUSE_1, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1); + he->data4 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.a1, + OFDM_RX_HE_TRIG_SPATIAL_REUSE_2, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2); + he->data4 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.a1, + OFDM_RX_HE_TRIG_SPATIAL_REUSE_3, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3); + he->data4 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.a1, + OFDM_RX_HE_TRIG_SPATIAL_REUSE_4, + IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4); + he->data3 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.a1, + OFDM_RX_HE_TRIG_BSS_COLOR, + IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR); + +#define CHECK_BW(bw) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_ ## bw ## MHZ != \ + RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS) + CHECK_BW(20); + CHECK_BW(40); + CHECK_BW(80); + CHECK_BW(160); +#undef CHECK_BW + + he->data6 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) | + le16_encode_bits(u32_get_bits(rate_n_flags, RATE_MCS_CHAN_WIDTH_MSK), + IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW); + + if (!(phy_data->ntfy->flags & IWL_SNIF_FLAG_VALID_TB_RX)) + return; + + he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN); + he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN); + + he->data3 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_CODING_EXTRA_SYM, + IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG); + he->data6 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_DOPPLER, + IEEE80211_RADIOTAP_HE_DATA6_DOPPLER); + he->data5 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_PRE_FEC_PAD_FACTOR, + IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD); + he->data5 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_PE_DISAMBIG, + IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG); + he->data5 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_NUM_OF_LTF_SYM, + IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS); + he->data6 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he_tb.a2, + OFDM_RX_HE_TRIG_TXOP_DURATION, + IEEE80211_RADIOTAP_HE_DATA6_TXOP); + + iwl_mld_he_set_ru_alloc(rx_status, he, + le32_get_bits(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_RU)); + + nsts = le32_get_bits(phy_data->ntfy->sigs.he_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_NSTS) + 1; + rx_status->nss = nsts >> !!(rate_n_flags & RATE_MCS_STBC_MSK); } static void iwl_mld_decode_he_phy_data(struct iwl_mld_rx_phy_data *phy_data, struct ieee80211_radiotap_he *he, struct ieee80211_radiotap_he_mu *he_mu, - struct ieee80211_rx_status *rx_status, - int queue) + struct ieee80211_rx_status *rx_status) { - switch (phy_data->info_type) { - case IWL_RX_PHY_INFO_TYPE_NONE: - case IWL_RX_PHY_INFO_TYPE_CCK: - case IWL_RX_PHY_INFO_TYPE_OFDM_LGCY: - case IWL_RX_PHY_INFO_TYPE_HT: - case IWL_RX_PHY_INFO_TYPE_VHT_SU: - case IWL_RX_PHY_INFO_TYPE_VHT_MU: - case IWL_RX_PHY_INFO_TYPE_EHT_MU: - case IWL_RX_PHY_INFO_TYPE_EHT_TB: - case IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT: - case IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT: - return; - case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT: - he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN | - IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN | - IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN | - IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN); - he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2, - IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE1), - IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1); - he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2, - IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE2), - IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2); - he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2, - IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE3), - IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3); - he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2, - IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE4), - IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4); - fallthrough; - case IWL_RX_PHY_INFO_TYPE_HE_SU: - case IWL_RX_PHY_INFO_TYPE_HE_MU: - case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT: - case IWL_RX_PHY_INFO_TYPE_HE_TB: - /* HE common */ - he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN | - IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN | - IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN); - he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN | - IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN | - IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN | - IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN); - he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_BSS_COLOR_MASK), - IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR); - if (phy_data->info_type != IWL_RX_PHY_INFO_TYPE_HE_TB && - phy_data->info_type != IWL_RX_PHY_INFO_TYPE_HE_TB_EXT) { - he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN); - he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_UPLINK), - IEEE80211_RADIOTAP_HE_DATA3_UL_DL); - } - he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_LDPC_EXT_SYM), - IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG); - he->data5 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_PRE_FEC_PAD_MASK), - IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD); - he->data5 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_PE_DISAMBIG), - IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG); - he->data5 |= le16_encode_bits(le32_get_bits(phy_data->data1, - IWL_RX_PHY_DATA1_HE_LTF_NUM_MASK), - IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS); - he->data6 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_TXOP_DUR_MASK), - IEEE80211_RADIOTAP_HE_DATA6_TXOP); - he->data6 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_DOPPLER), - IEEE80211_RADIOTAP_HE_DATA6_DOPPLER); - break; - } + u32 rate_n_flags = phy_data->rate_n_flags; + u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK; + u32 nsts; - switch (phy_data->info_type) { - case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT: - case IWL_RX_PHY_INFO_TYPE_HE_MU: - case IWL_RX_PHY_INFO_TYPE_HE_SU: - he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN); - he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_SPATIAL_REUSE_MASK), - IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE); - break; - default: - /* nothing here */ - break; - } + switch (he_type) { + case RATE_MCS_HE_TYPE_TRIG: + iwl_mld_decode_he_tb_phy_data(phy_data, he, rx_status); + /* that's it, below is only for SU/MU */ + return; + case RATE_MCS_HE_TYPE_MU: + iwl_mld_decode_he_mu(phy_data, he, he_mu, rx_status); - switch (phy_data->info_type) { - case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT: - he_mu->flags1 |= - le16_encode_bits(le16_get_bits(phy_data->data4, - IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_DCM), - IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM); - he_mu->flags1 |= - le16_encode_bits(le16_get_bits(phy_data->data4, - IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_MCS_MASK), - IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS); - he_mu->flags2 |= - le16_encode_bits(le16_get_bits(phy_data->data4, - IWL_RX_PHY_DATA4_HE_MU_EXT_PREAMBLE_PUNC_TYPE_MASK), - IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW); - iwl_mld_decode_he_mu_ext(phy_data, he_mu); - fallthrough; - case IWL_RX_PHY_INFO_TYPE_HE_MU: - he_mu->flags2 |= - le16_encode_bits(le32_get_bits(phy_data->data1, - IWL_RX_PHY_DATA1_HE_MU_SIBG_SYM_OR_USER_NUM_MASK), - IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS); - he_mu->flags2 |= - le16_encode_bits(le32_get_bits(phy_data->data1, - IWL_RX_PHY_DATA1_HE_MU_SIGB_COMPRESSION), - IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP); - fallthrough; - case IWL_RX_PHY_INFO_TYPE_HE_TB: - case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT: - iwl_mld_decode_he_phy_ru_alloc(phy_data, he, he_mu, rx_status); + nsts = le32_get_bits(phy_data->ntfy->sigs.he.b, + OFDM_RX_FRAME_HE_SIGB_NSTS) + 1; break; - case IWL_RX_PHY_INFO_TYPE_HE_SU: + case RATE_MCS_HE_TYPE_SU: + case RATE_MCS_HE_TYPE_EXT_SU: he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN); - he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_HE_BEAM_CHNG), - IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE); - break; - default: - /* nothing */ + he->data3 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a1, + OFDM_RX_FRAME_HE_BEAM_CHANGE, + IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE); + + nsts = le32_get_bits(phy_data->ntfy->sigs.he.a1, + OFDM_RX_FRAME_HE_NSTS) + 1; break; } + + rx_status->nss = nsts >> !!(rate_n_flags & RATE_MCS_STBC_MSK); + + he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN); + he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN | + IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN); + + he->data3 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_CODING_EXTRA_SYM, + IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG); + he->data5 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_PRE_FEC_PAD_FACTOR, + IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD); + he->data5 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_PE_DISAMBIG, + IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG); + he->data5 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_MU_NUM_OF_LTF_SYM, + IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS); + he->data6 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_TXOP_DURATION, + IEEE80211_RADIOTAP_HE_DATA6_TXOP); + he->data6 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a2, + OFDM_RX_FRAME_HE_DOPPLER, + IEEE80211_RADIOTAP_HE_DATA6_DOPPLER); + + he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN | + IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN); + + he->data3 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a1, + OFDM_RX_FRAME_HE_BSS_COLOR, + IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR); + he->data3 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a1, + OFDM_RX_FRAME_HE_UL_FLAG, + IEEE80211_RADIOTAP_HE_DATA3_UL_DL); + he->data4 |= RTAP_ENC_HE(phy_data->ntfy->sigs.he.a1, + OFDM_RX_FRAME_HE_SPATIAL_REUSE, + IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE); } -static void iwl_mld_rx_he(struct iwl_mld *mld, struct sk_buff *skb, - struct iwl_mld_rx_phy_data *phy_data, - int queue) +static void iwl_mld_rx_he(struct sk_buff *skb, + struct iwl_mld_rx_phy_data *phy_data) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); struct ieee80211_radiotap_he *he = NULL; @@ -510,48 +529,28 @@ static void iwl_mld_rx_he(struct iwl_mld *mld, struct sk_buff *skb, .flags2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN | IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN), }; - u16 phy_info = phy_data->phy_info; he = skb_put_data(skb, &known, sizeof(known)); rx_status->flag |= RX_FLAG_RADIOTAP_HE; - if (phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_MU || - phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_MU_EXT) { - he_mu = skb_put_data(skb, &mu_known, sizeof(mu_known)); - rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU; - } - - /* report the AMPDU-EOF bit on single frames */ - if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) { - rx_status->flag |= RX_FLAG_AMPDU_DETAILS; - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; - if (phy_data->data0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF)) - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; - } - - if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) - iwl_mld_decode_he_phy_data(phy_data, he, he_mu, rx_status, - queue); - - /* update aggregation data for monitor sake on default queue */ - if (!queue && (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) && - (phy_info & IWL_RX_MPDU_PHY_AMPDU) && phy_data->first_subframe) { - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; - if (phy_data->data0 & cpu_to_le32(IWL_RX_PHY_DATA0_EHT_DELIM_EOF)) - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; - } - - if (he_type == RATE_MCS_HE_TYPE_EXT_SU && - rate_n_flags & RATE_MCS_HE_106T_MSK) { - rx_status->bw = RATE_INFO_BW_HE_RU; - rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106; - } - - /* actually data is filled in mac80211 */ - if (he_type == RATE_MCS_HE_TYPE_SU || - he_type == RATE_MCS_HE_TYPE_EXT_SU) + switch (he_type) { + case RATE_MCS_HE_TYPE_EXT_SU: + /* + * Except for this special case we won't have + * HE RU allocation info outside of monitor mode + * since we don't get the PHY notif. + */ + if (rate_n_flags & RATE_MCS_HE_106T_MSK) { + rx_status->bw = RATE_INFO_BW_HE_RU; + rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106; + } + fallthrough; + case RATE_MCS_HE_TYPE_SU: + /* actual data is filled in mac80211 */ he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN); + break; + } #define CHECK_TYPE(F) \ BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_ ## F != \ @@ -567,8 +566,7 @@ static void iwl_mld_rx_he(struct iwl_mld *mld, struct sk_buff *skb, if (rate_n_flags & RATE_MCS_BF_MSK) he->data5 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA5_TXBF); - switch ((rate_n_flags & RATE_MCS_HE_GI_LTF_MSK) >> - RATE_MCS_HE_GI_LTF_POS) { + switch (u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK)) { case 0: if (he_type == RATE_MCS_HE_TYPE_TRIG) rx_status->he_gi = NL80211_RATE_INFO_HE_GI_1_6; @@ -609,37 +607,52 @@ static void iwl_mld_rx_he(struct iwl_mld *mld, struct sk_buff *skb, he->data5 |= le16_encode_bits(ltf, IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE); + + if (likely(!phy_data->ntfy)) + return; + + if (he_type == RATE_MCS_HE_TYPE_MU) { + he_mu = skb_put_data(skb, &mu_known, sizeof(mu_known)); + rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU; + } + + iwl_mld_decode_he_phy_data(phy_data, he, he_mu, rx_status); } static void iwl_mld_decode_lsig(struct sk_buff *skb, struct iwl_mld_rx_phy_data *phy_data) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); + u32 format = phy_data->rate_n_flags & RATE_MCS_MOD_TYPE_MSK; struct ieee80211_radiotap_lsig *lsig; + u32 lsig_len, rate; - switch (phy_data->info_type) { - case IWL_RX_PHY_INFO_TYPE_HT: - case IWL_RX_PHY_INFO_TYPE_VHT_SU: - case IWL_RX_PHY_INFO_TYPE_VHT_MU: - case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT: - case IWL_RX_PHY_INFO_TYPE_HE_SU: - case IWL_RX_PHY_INFO_TYPE_HE_MU: - case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT: - case IWL_RX_PHY_INFO_TYPE_HE_TB: - case IWL_RX_PHY_INFO_TYPE_EHT_MU: - case IWL_RX_PHY_INFO_TYPE_EHT_TB: - case IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT: - case IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT: - lsig = skb_put(skb, sizeof(*lsig)); - lsig->data1 = cpu_to_le16(IEEE80211_RADIOTAP_LSIG_DATA1_LENGTH_KNOWN); - lsig->data2 = le16_encode_bits(le32_get_bits(phy_data->data1, - IWL_RX_PHY_DATA1_LSIG_LEN_MASK), - IEEE80211_RADIOTAP_LSIG_DATA2_LENGTH); - rx_status->flag |= RX_FLAG_RADIOTAP_LSIG; - break; - default: - break; - } + if (likely(!phy_data->ntfy)) + return; + + /* + * Technically legacy CCK/OFDM frames don't have an L-SIG + * since that's the compat format for HT (non-greenfield) + * and up. However, it's meant to be compatible with the + * LENGTH and RATE fields in Clause 17 and 18 OFDM frames + * so include the field for any non-CCK frame. For CCK it + * cannot work, since the LENGTH field for them is 16-bit + * and the radiotap field only has 12 bits. + */ + if (format == RATE_MCS_MOD_TYPE_CCK) + return; + + lsig_len = le32_get_bits(phy_data->ntfy->legacy_sig.ofdm, + OFDM_RX_LEGACY_LENGTH); + rate = le32_get_bits(phy_data->ntfy->legacy_sig.ofdm, OFDM_RX_RATE); + + lsig = skb_put(skb, sizeof(*lsig)); + lsig->data1 = cpu_to_le16(IEEE80211_RADIOTAP_LSIG_DATA1_LENGTH_KNOWN) | + cpu_to_le16(IEEE80211_RADIOTAP_LSIG_DATA1_RATE_KNOWN); + lsig->data2 = le16_encode_bits(lsig_len, + IEEE80211_RADIOTAP_LSIG_DATA2_LENGTH) | + le16_encode_bits(rate, IEEE80211_RADIOTAP_LSIG_DATA2_RATE); + rx_status->flag |= RX_FLAG_RADIOTAP_LSIG; } /* Put a TLV on the skb and return data pointer @@ -667,209 +680,144 @@ iwl_mld_radiotap_put_tlv(struct sk_buff *skb, u16 type, u16 len) (_usig)->value |= LE32_DEC_ENC(in_value, dec_bits, _enc_bits); \ } while (0) -#define __IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) \ - eht->data[(rt_data)] |= \ - (cpu_to_le32 \ - (IEEE80211_RADIOTAP_EHT_DATA ## rt_data ## _RU_ALLOC_CC_ ## rt_ru ## _KNOWN) | \ - LE32_DEC_ENC(data ## fw_data, \ - IWL_RX_PHY_DATA ## fw_data ## _EHT_MU_EXT_RU_ALLOC_ ## fw_ru, \ - IEEE80211_RADIOTAP_EHT_DATA ## rt_data ## _RU_ALLOC_CC_ ## rt_ru)) +static void iwl_mld_decode_eht_usig_tb(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_radiotap_eht_usig *usig) +{ + __le32 usig_a1 = phy_data->ntfy->sigs.eht_tb.usig_a1; + __le32 usig_a2 = phy_data->ntfy->sigs.eht_tb.usig_a2_eht; + + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1, + OFDM_RX_FRAME_EHT_USIG1_DISREGARD, + IEEE80211_RADIOTAP_EHT_USIG1_TB_B20_B25_DISREGARD); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_PPDU_TYPE, + IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B2, + IEEE80211_RADIOTAP_EHT_USIG2_TB_B2_VALIDATE); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_TRIG_SPATIAL_REUSE_1, + IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_TRIG_SPATIAL_REUSE_2, + IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_TRIG_USIG2_DISREGARD, + IEEE80211_RADIOTAP_EHT_USIG2_TB_B11_B15_DISREGARD); +} -#define _IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) \ - __IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) +static void iwl_mld_decode_eht_usig_non_tb(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_radiotap_eht_usig *usig) +{ + __le32 usig_a1 = phy_data->ntfy->sigs.eht.usig_a1; + __le32 usig_a2 = phy_data->ntfy->sigs.eht.usig_a2_eht; + + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1, + OFDM_RX_FRAME_EHT_USIG1_DISREGARD, + IEEE80211_RADIOTAP_EHT_USIG1_MU_B20_B24_DISREGARD); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1, + OFDM_RX_FRAME_EHT_USIG1_VALIDATE, + IEEE80211_RADIOTAP_EHT_USIG1_MU_B25_VALIDATE); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_PPDU_TYPE, + IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B2, + IEEE80211_RADIOTAP_EHT_USIG2_MU_B2_VALIDATE); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_PUNC_CHANNEL, + IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B8, + IEEE80211_RADIOTAP_EHT_USIG2_MU_B8_VALIDATE); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_SIG_MCS, + IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS); + IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, + OFDM_RX_FRAME_EHT_SIG_SYM_NUM, + IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS); +} -#define IEEE80211_RADIOTAP_RU_DATA_1_1_1 1 -#define IEEE80211_RADIOTAP_RU_DATA_2_1_1 2 -#define IEEE80211_RADIOTAP_RU_DATA_1_1_2 2 -#define IEEE80211_RADIOTAP_RU_DATA_2_1_2 2 -#define IEEE80211_RADIOTAP_RU_DATA_1_2_1 3 -#define IEEE80211_RADIOTAP_RU_DATA_2_2_1 3 -#define IEEE80211_RADIOTAP_RU_DATA_1_2_2 3 -#define IEEE80211_RADIOTAP_RU_DATA_2_2_2 4 +static void iwl_mld_decode_eht_usig(struct iwl_mld_rx_phy_data *phy_data, + struct sk_buff *skb) +{ + u32 he_type = phy_data->rate_n_flags & RATE_MCS_HE_TYPE_MSK; + __le32 usig_a1 = phy_data->ntfy->sigs.eht.usig_a1; + __le32 usig_a2 = phy_data->ntfy->sigs.eht.usig_a2_eht; + struct ieee80211_radiotap_eht_usig *usig; + u32 bw; -#define IWL_RX_RU_DATA_A1 2 -#define IWL_RX_RU_DATA_A2 2 -#define IWL_RX_RU_DATA_B1 2 -#define IWL_RX_RU_DATA_B2 4 -#define IWL_RX_RU_DATA_C1 3 -#define IWL_RX_RU_DATA_C2 3 -#define IWL_RX_RU_DATA_D1 4 -#define IWL_RX_RU_DATA_D2 4 + usig = iwl_mld_radiotap_put_tlv(skb, IEEE80211_RADIOTAP_EHT_USIG, + sizeof(*usig)); -#define IWL_MLD_ENC_EHT_RU(rt_ru, fw_ru) \ - _IWL_MLD_ENC_EHT_RU(IEEE80211_RADIOTAP_RU_DATA_ ## rt_ru, \ - rt_ru, \ - IWL_RX_RU_DATA_ ## fw_ru, \ - fw_ru) + BUILD_BUG_ON(offsetof(union iwl_sigs, eht.usig_a1) != + offsetof(union iwl_sigs, eht_tb.usig_a1)); + BUILD_BUG_ON(offsetof(union iwl_sigs, eht.usig_a2_eht) != + offsetof(union iwl_sigs, eht_tb.usig_a2_eht)); -static void iwl_mld_decode_eht_ext_mu(struct iwl_mld *mld, - struct iwl_mld_rx_phy_data *phy_data, - struct ieee80211_rx_status *rx_status, - struct ieee80211_radiotap_eht *eht, - struct ieee80211_radiotap_eht_usig *usig) -{ - if (phy_data->with_data) { - __le32 data1 = phy_data->data1; - __le32 data2 = phy_data->data2; - __le32 data3 = phy_data->data3; - __le32 data4 = phy_data->eht_data4; - __le32 data5 = phy_data->data5; - u32 phy_bw = phy_data->rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK; - - IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5, - IWL_RX_PHY_DATA5_EHT_TYPE_AND_COMP, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5, - IWL_RX_PHY_DATA5_EHT_MU_PUNC_CH_CODE, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, data4, - IWL_RX_PHY_DATA4_EHT_MU_EXT_SIGB_MCS, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS); - IWL_MLD_ENC_USIG_VALUE_MASK - (usig, data1, IWL_RX_PHY_DATA1_EHT_MU_NUM_SIG_SYM_USIGA2, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS); + usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL_KNOWN | + IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR_KNOWN | + IEEE80211_RADIOTAP_EHT_USIG_COMMON_VALIDATE_BITS_CHECKED | + IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_KNOWN | + IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP_KNOWN); - eht->user_info[0] |= - cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID_KNOWN) | - LE32_DEC_ENC(data5, IWL_RX_PHY_DATA5_EHT_MU_STA_ID_USR, - IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID); +#define CHECK_BW(bw) \ + BUILD_BUG_ON(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_ ## bw ## MHZ != \ + RATE_MCS_CHAN_WIDTH_ ## bw ## _VAL) + CHECK_BW(20); + CHECK_BW(40); + CHECK_BW(80); + CHECK_BW(160); +#undef CHECK_BW + BUILD_BUG_ON(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_320MHZ_1 != + RATE_MCS_CHAN_WIDTH_320_VAL); + bw = u32_get_bits(phy_data->rate_n_flags, RATE_MCS_CHAN_WIDTH_MSK); + /* specific handling for 320MHz-1/320MHz-2 */ + if (bw == RATE_MCS_CHAN_WIDTH_320_VAL) + bw += le32_get_bits(usig_a1, OFDM_RX_FRAME_EHT_BW320_SLOT); + usig->common |= le32_encode_bits(bw, + IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW); - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_NR_NON_OFDMA_USERS_M); - eht->data[7] |= LE32_DEC_ENC - (data5, IWL_RX_PHY_DATA5_EHT_MU_NUM_USR_NON_OFDMA, - IEEE80211_RADIOTAP_EHT_DATA7_NUM_OF_NON_OFDMA_USERS); + usig->common |= LE32_DEC_ENC(usig_a1, OFDM_RX_FRAME_ENHANCED_WIFI_UL_FLAG, + IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL); + usig->common |= LE32_DEC_ENC(usig_a1, OFDM_RX_FRAME_ENHANCED_WIFI_BSS_COLOR, + IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR); - /* - * Hardware labels the content channels/RU allocation values - * as follows: - * Content Channel 1 Content Channel 2 - * 20 MHz: A1 - * 40 MHz: A1 B1 - * 80 MHz: A1 C1 B1 D1 - * 160 MHz: A1 C1 A2 C2 B1 D1 B2 D2 - * 320 MHz: A1 C1 A2 C2 A3 C3 A4 C4 B1 D1 B2 D2 B3 D3 B4 D4 - * - * However firmware can only give us A1-D2, so the higher - * frequencies are missing. - */ + if (le32_get_bits(usig_a1, OFDM_RX_FRAME_EHT_USIG1_VALIDATE) && + le32_get_bits(usig_a2, OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B2) && + le32_get_bits(usig_a2, OFDM_RX_FRAME_EHT_USIG2_VALIDATE_B8)) + usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_VALIDATE_BITS_OK); - switch (phy_bw) { - case RATE_MCS_CHAN_WIDTH_320: - /* additional values are missing in RX metadata */ - fallthrough; - case RATE_MCS_CHAN_WIDTH_160: - /* content channel 1 */ - IWL_MLD_ENC_EHT_RU(1_2_1, A2); - IWL_MLD_ENC_EHT_RU(1_2_2, C2); - /* content channel 2 */ - IWL_MLD_ENC_EHT_RU(2_2_1, B2); - IWL_MLD_ENC_EHT_RU(2_2_2, D2); - fallthrough; - case RATE_MCS_CHAN_WIDTH_80: - /* content channel 1 */ - IWL_MLD_ENC_EHT_RU(1_1_2, C1); - /* content channel 2 */ - IWL_MLD_ENC_EHT_RU(2_1_2, D1); - fallthrough; - case RATE_MCS_CHAN_WIDTH_40: - /* content channel 2 */ - IWL_MLD_ENC_EHT_RU(2_1_1, B1); - fallthrough; - case RATE_MCS_CHAN_WIDTH_20: - IWL_MLD_ENC_EHT_RU(1_1_1, A1); - break; - } - } else { - __le32 usig_a1 = phy_data->rx_vec[0]; - __le32 usig_a2 = phy_data->rx_vec[1]; - - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1, - IWL_RX_USIG_A1_DISREGARD, - IEEE80211_RADIOTAP_EHT_USIG1_MU_B20_B24_DISREGARD); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1, - IWL_RX_USIG_A1_VALIDATE, - IEEE80211_RADIOTAP_EHT_USIG1_MU_B25_VALIDATE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_PPDU_TYPE, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_USIG2_VALIDATE_B2, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B2_VALIDATE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_PUNC_CHANNEL, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_USIG2_VALIDATE_B8, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B8_VALIDATE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_SIG_MCS, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS); - IWL_MLD_ENC_USIG_VALUE_MASK - (usig, usig_a2, IWL_RX_USIG_A2_EHT_SIG_SYM_NUM, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_CRC_OK, - IEEE80211_RADIOTAP_EHT_USIG2_MU_B16_B19_CRC); - } -} + usig->common |= LE32_DEC_ENC(usig_a1, + OFDM_RX_FRAME_ENHANCED_WIFI_TXOP_DURATION, + IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP); -static void iwl_mld_decode_eht_ext_tb(struct iwl_mld *mld, - struct iwl_mld_rx_phy_data *phy_data, - struct ieee80211_rx_status *rx_status, - struct ieee80211_radiotap_eht *eht, - struct ieee80211_radiotap_eht_usig *usig) -{ - if (phy_data->with_data) { - __le32 data5 = phy_data->data5; - - IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5, - IWL_RX_PHY_DATA5_EHT_TYPE_AND_COMP, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5, - IWL_RX_PHY_DATA5_EHT_TB_SPATIAL_REUSE1, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1); - - IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5, - IWL_RX_PHY_DATA5_EHT_TB_SPATIAL_REUSE2, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2); - } else { - __le32 usig_a1 = phy_data->rx_vec[0]; - __le32 usig_a2 = phy_data->rx_vec[1]; - - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1, - IWL_RX_USIG_A1_DISREGARD, - IEEE80211_RADIOTAP_EHT_USIG1_TB_B20_B25_DISREGARD); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_PPDU_TYPE, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_USIG2_VALIDATE_B2, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B2_VALIDATE); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_TRIG_SPATIAL_REUSE_1, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_TRIG_SPATIAL_REUSE_2, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_TRIG_USIG2_DISREGARD, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B11_B15_DISREGARD); - IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2, - IWL_RX_USIG_A2_EHT_CRC_OK, - IEEE80211_RADIOTAP_EHT_USIG2_TB_B16_B19_CRC); - } + if (!le32_get_bits(usig_a2, OFDM_RX_USIG_CRC_OK)) + usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BAD_USIG_CRC); + + usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER_KNOWN); + usig->common |= LE32_DEC_ENC(usig_a1, + OFDM_RX_FRAME_ENHANCED_WIFI_VER_ID, + IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER); + + if (he_type == RATE_MCS_HE_TYPE_TRIG) + iwl_mld_decode_eht_usig_tb(phy_data, usig); + else + iwl_mld_decode_eht_usig_non_tb(phy_data, usig); } -static void iwl_mld_decode_eht_ru(struct iwl_mld *mld, - struct ieee80211_rx_status *rx_status, - struct ieee80211_radiotap_eht *eht) +static void +iwl_mld_eht_set_ru_alloc(struct ieee80211_rx_status *rx_status, + u32 ru_with_p80) { - u32 ru = le32_get_bits(eht->data[8], - IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B7_B1); enum nl80211_eht_ru_alloc nl_ru; + u32 ru = ru_with_p80 >> 1; - /* Using D1.5 Table 9-53a - Encoding of PS160 and RU Allocation subfields - * in an EHT variant User Info field + /* + * HW always uses trigger frame format: + * + * Draft PIEEE802.11be D7.0 Table 9-46l - Encoding of the PS160 and + * RU Allocation subfields in an EHT variant User Info field */ switch (ru) { @@ -929,135 +877,228 @@ static void iwl_mld_decode_eht_ru(struct iwl_mld *mld, rx_status->eht.ru = nl_ru; } -static void iwl_mld_decode_eht_phy_data(struct iwl_mld *mld, - struct iwl_mld_rx_phy_data *phy_data, - struct ieee80211_rx_status *rx_status, - struct ieee80211_radiotap_eht *eht, - struct ieee80211_radiotap_eht_usig *usig) - +static void iwl_mld_decode_eht_tb(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_rx_status *rx_status, + struct ieee80211_radiotap_eht *eht) { - __le32 data0 = phy_data->data0; - __le32 data1 = phy_data->data1; - __le32 usig_a1 = phy_data->rx_vec[0]; - u8 info_type = phy_data->info_type; - - /* Not in EHT range */ - if (info_type < IWL_RX_PHY_INFO_TYPE_EHT_MU || - info_type > IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT) + if (!(phy_data->ntfy->flags & IWL_SNIF_FLAG_VALID_TB_RX)) return; - usig->common |= cpu_to_le32 - (IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL_KNOWN | - IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR_KNOWN); - if (phy_data->with_data) { - usig->common |= LE32_DEC_ENC(data0, - IWL_RX_PHY_DATA0_EHT_UPLINK, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL); - usig->common |= LE32_DEC_ENC(data0, - IWL_RX_PHY_DATA0_EHT_BSS_COLOR_MASK, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR); - } else { - usig->common |= LE32_DEC_ENC(usig_a1, - IWL_RX_USIG_A1_UL_FLAG, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL); - usig->common |= LE32_DEC_ENC(usig_a1, - IWL_RX_USIG_A1_BSS_COLOR, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR); - } - - usig->common |= - cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_VALIDATE_BITS_CHECKED); - usig->common |= - LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_VALIDATE, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_VALIDATE_BITS_OK); - - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_SPATIAL_REUSE); - eht->data[0] |= LE32_DEC_ENC(data0, - IWL_RX_PHY_DATA0_ETH_SPATIAL_REUSE_MASK, - IEEE80211_RADIOTAP_EHT_DATA0_SPATIAL_REUSE); + eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_RU_ALLOC_TB_FMT | + IEEE80211_RADIOTAP_EHT_KNOWN_LDPC_EXTRA_SYM_OM | + IEEE80211_RADIOTAP_EHT_KNOWN_PRE_PADD_FACOR_OM | + IEEE80211_RADIOTAP_EHT_KNOWN_PE_DISAMBIGUITY_OM | + IEEE80211_RADIOTAP_EHT_KNOWN_EHT_LTF | + IEEE80211_RADIOTAP_EHT_KNOWN_PRIMARY_80); - /* All RU allocating size/index is in TB format */ - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_RU_ALLOC_TB_FMT); - eht->data[8] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PS160, + eht->data[8] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx0, + OFDM_UCODE_TRIG_BASE_PS160, IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_PS_160); - eht->data[8] |= LE32_DEC_ENC(data1, IWL_RX_PHY_DATA1_EHT_RU_ALLOC_B0, - IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B0); - eht->data[8] |= LE32_DEC_ENC(data1, IWL_RX_PHY_DATA1_EHT_RU_ALLOC_B1_B7, + eht->data[8] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_RU, + IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B0 | IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B7_B1); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_CODING_EXTRA_SYM, + IEEE80211_RADIOTAP_EHT_DATA0_LDPC_EXTRA_SYM_OM); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_PRE_FEC_PAD_FACTOR, + IEEE80211_RADIOTAP_EHT_DATA0_PRE_PADD_FACOR_OM); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_PE_DISAMBIG, + IEEE80211_RADIOTAP_EHT_DATA0_PE_DISAMBIGUITY_OM); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_NUM_OF_LTF_SYM, + IEEE80211_RADIOTAP_EHT_DATA0_EHT_LTF); + eht->data[1] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht_tb.tb_rx0, + OFDM_UCODE_TRIG_BASE_RX_RU_P80, + IEEE80211_RADIOTAP_EHT_DATA1_PRIMARY_80); - iwl_mld_decode_eht_ru(mld, rx_status, eht); - - /* We only get here in case of IWL_RX_MPDU_PHY_TSF_OVERLOAD is set - * which is on only in case of monitor mode so no need to check monitor - * mode - */ - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_PRIMARY_80); - eht->data[1] |= - le32_encode_bits(mld->monitor.p80, - IEEE80211_RADIOTAP_EHT_DATA1_PRIMARY_80); - - usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP_KNOWN); - if (phy_data->with_data) - usig->common |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_TXOP_DUR_MASK, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP); - else - usig->common |= LE32_DEC_ENC(usig_a1, IWL_RX_USIG_A1_TXOP_DURATION, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP); + iwl_mld_eht_set_ru_alloc(rx_status, + le32_get_bits(phy_data->ntfy->sigs.eht_tb.tb_rx1, + OFDM_UCODE_TRIG_BASE_RX_RU)); +} - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_LDPC_EXTRA_SYM_OM); - eht->data[0] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_LDPC_EXT_SYM, - IEEE80211_RADIOTAP_EHT_DATA0_LDPC_EXTRA_SYM_OM); +static void iwl_mld_eht_decode_user_ru(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_radiotap_eht *eht) +{ + u32 phy_bw = phy_data->rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK; - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_PRE_PADD_FACOR_OM); - eht->data[0] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PRE_FEC_PAD_MASK, - IEEE80211_RADIOTAP_EHT_DATA0_PRE_PADD_FACOR_OM); + if (!(phy_data->ntfy->flags & IWL_SNIF_FLAG_VALID_RU)) + return; - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_PE_DISAMBIGUITY_OM); - eht->data[0] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PE_DISAMBIG, - IEEE80211_RADIOTAP_EHT_DATA0_PE_DISAMBIGUITY_OM); +#define __IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) \ + eht->data[(rt_data)] |= \ + (cpu_to_le32(IEEE80211_RADIOTAP_EHT_DATA ## rt_data ## _RU_ALLOC_CC_ ## rt_ru ## _KNOWN) | \ + LE32_DEC_ENC(phy_data->ntfy->sigs.eht.cmn[fw_data], \ + OFDM_RX_FRAME_EHT_RU_ALLOC_ ## fw_data ## _ ## fw_ru, \ + IEEE80211_RADIOTAP_EHT_DATA ## rt_data ## _RU_ALLOC_CC_ ## rt_ru)) - /* TODO: what about IWL_RX_PHY_DATA0_EHT_BW320_SLOT */ +#define _IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) \ + __IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) - if (!le32_get_bits(data0, IWL_RX_PHY_DATA0_EHT_SIGA_CRC_OK)) - usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BAD_USIG_CRC); +#define IEEE80211_RADIOTAP_RU_DATA_1_1_1 1 +#define IEEE80211_RADIOTAP_RU_DATA_2_1_1 2 +#define IEEE80211_RADIOTAP_RU_DATA_1_1_2 2 +#define IEEE80211_RADIOTAP_RU_DATA_2_1_2 2 +#define IEEE80211_RADIOTAP_RU_DATA_1_2_1 3 +#define IEEE80211_RADIOTAP_RU_DATA_2_2_1 3 +#define IEEE80211_RADIOTAP_RU_DATA_1_2_2 3 +#define IEEE80211_RADIOTAP_RU_DATA_2_2_2 4 +#define IEEE80211_RADIOTAP_RU_DATA_1_2_3 4 +#define IEEE80211_RADIOTAP_RU_DATA_2_2_3 4 +#define IEEE80211_RADIOTAP_RU_DATA_1_2_4 5 +#define IEEE80211_RADIOTAP_RU_DATA_2_2_4 5 +#define IEEE80211_RADIOTAP_RU_DATA_1_2_5 5 +#define IEEE80211_RADIOTAP_RU_DATA_2_2_5 6 +#define IEEE80211_RADIOTAP_RU_DATA_1_2_6 6 +#define IEEE80211_RADIOTAP_RU_DATA_2_2_6 6 + +#define IWL_RX_RU_DATA_A1 0 +#define IWL_RX_RU_DATA_A2 0 +#define IWL_RX_RU_DATA_A3 0 +#define IWL_RX_RU_DATA_A4 4 +#define IWL_RX_RU_DATA_B1 1 +#define IWL_RX_RU_DATA_B2 1 +#define IWL_RX_RU_DATA_B3 1 +#define IWL_RX_RU_DATA_B4 4 +#define IWL_RX_RU_DATA_C1 2 +#define IWL_RX_RU_DATA_C2 2 +#define IWL_RX_RU_DATA_C3 2 +#define IWL_RX_RU_DATA_C4 5 +#define IWL_RX_RU_DATA_D1 3 +#define IWL_RX_RU_DATA_D2 3 +#define IWL_RX_RU_DATA_D3 3 +#define IWL_RX_RU_DATA_D4 5 - usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER_KNOWN); - usig->common |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PHY_VER, - IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER); +#define IWL_MLD_ENC_EHT_RU(rt_ru, fw_ru) \ + _IWL_MLD_ENC_EHT_RU(IEEE80211_RADIOTAP_RU_DATA_ ## rt_ru, \ + rt_ru, \ + IWL_RX_RU_DATA_ ## fw_ru, \ + fw_ru) /* - * TODO: what about TB - IWL_RX_PHY_DATA1_EHT_TB_PILOT_TYPE, - * IWL_RX_PHY_DATA1_EHT_TB_LOW_SS + * Hardware labels the content channels/RU allocation values + * as follows: + * + * Content Channel 1 Content Channel 2 + * 20 MHz: A1 + * 40 MHz: A1 B1 + * 80 MHz: A1 C1 B1 D1 + * 160 MHz: A1 C1 A2 C2 B1 D1 B2 D2 + * 320 MHz: A1 C1 A2 C2 A3 C3 A4 C4 B1 D1 B2 D2 B3 D3 B4 D4 */ - eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_EHT_LTF); - eht->data[0] |= LE32_DEC_ENC(data1, IWL_RX_PHY_DATA1_EHT_SIG_LTF_NUM, + switch (phy_bw) { + case RATE_MCS_CHAN_WIDTH_320: + /* content channel 1 */ + IWL_MLD_ENC_EHT_RU(1_2_3, A3); + IWL_MLD_ENC_EHT_RU(1_2_4, C3); + IWL_MLD_ENC_EHT_RU(1_2_5, A4); + IWL_MLD_ENC_EHT_RU(1_2_6, C4); + /* content channel 2 */ + IWL_MLD_ENC_EHT_RU(2_2_3, B3); + IWL_MLD_ENC_EHT_RU(2_2_4, D3); + IWL_MLD_ENC_EHT_RU(2_2_5, B4); + IWL_MLD_ENC_EHT_RU(2_2_6, D4); + fallthrough; + case RATE_MCS_CHAN_WIDTH_160: + /* content channel 1 */ + IWL_MLD_ENC_EHT_RU(1_2_1, A2); + IWL_MLD_ENC_EHT_RU(1_2_2, C2); + /* content channel 2 */ + IWL_MLD_ENC_EHT_RU(2_2_1, B2); + IWL_MLD_ENC_EHT_RU(2_2_2, D2); + fallthrough; + case RATE_MCS_CHAN_WIDTH_80: + /* content channel 1 */ + IWL_MLD_ENC_EHT_RU(1_1_2, C1); + /* content channel 2 */ + IWL_MLD_ENC_EHT_RU(2_1_2, D1); + fallthrough; + case RATE_MCS_CHAN_WIDTH_40: + /* content channel 2 */ + IWL_MLD_ENC_EHT_RU(2_1_1, B1); + fallthrough; + case RATE_MCS_CHAN_WIDTH_20: + /* content channel 1 */ + IWL_MLD_ENC_EHT_RU(1_1_1, A1); + break; + } +} + +static void iwl_mld_decode_eht_non_tb(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_rx_status *rx_status, + struct ieee80211_radiotap_eht *eht) +{ + eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_SPATIAL_REUSE | + /* All RU allocating size/index is in TB format */ + IEEE80211_RADIOTAP_EHT_KNOWN_RU_ALLOC_TB_FMT | + IEEE80211_RADIOTAP_EHT_KNOWN_LDPC_EXTRA_SYM_OM | + IEEE80211_RADIOTAP_EHT_KNOWN_PRE_PADD_FACOR_OM | + IEEE80211_RADIOTAP_EHT_KNOWN_PE_DISAMBIGUITY_OM | + IEEE80211_RADIOTAP_EHT_KNOWN_EHT_LTF | + IEEE80211_RADIOTAP_EHT_KNOWN_PRIMARY_80 | + IEEE80211_RADIOTAP_EHT_KNOWN_NR_NON_OFDMA_USERS_M); + + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_SPATIAL_REUSE, + IEEE80211_RADIOTAP_EHT_DATA0_SPATIAL_REUSE); + eht->data[8] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b2, + OFDM_RX_FRAME_EHT_STA_RU_PS160, + IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_PS_160); + eht->data[8] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b2, + OFDM_RX_FRAME_EHT_STA_RU, + IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B0 | + IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B7_B1); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_CODING_EXTRA_SYM, + IEEE80211_RADIOTAP_EHT_DATA0_LDPC_EXTRA_SYM_OM); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_PRE_FEC_PAD_FACTOR, + IEEE80211_RADIOTAP_EHT_DATA0_PRE_PADD_FACOR_OM); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_PE_DISAMBIG, + IEEE80211_RADIOTAP_EHT_DATA0_PE_DISAMBIGUITY_OM); + eht->data[0] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_NUM_OF_LTF_SYM, IEEE80211_RADIOTAP_EHT_DATA0_EHT_LTF); + eht->data[1] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b2, + OFDM_RX_FRAME_EHT_STA_RU_P80, + IEEE80211_RADIOTAP_EHT_DATA1_PRIMARY_80); + eht->data[7] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_NUM_OF_USERS, + IEEE80211_RADIOTAP_EHT_DATA7_NUM_OF_NON_OFDMA_USERS); + + iwl_mld_eht_decode_user_ru(phy_data, eht); + + iwl_mld_eht_set_ru_alloc(rx_status, + le32_get_bits(phy_data->ntfy->sigs.eht.b2, + OFDM_RX_FRAME_EHT_STA_RU)); +} - if (info_type == IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT || - info_type == IWL_RX_PHY_INFO_TYPE_EHT_TB) - iwl_mld_decode_eht_ext_tb(mld, phy_data, rx_status, eht, usig); +static void iwl_mld_decode_eht_phy_data(struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_rx_status *rx_status, + struct ieee80211_radiotap_eht *eht) +{ + u32 he_type = phy_data->rate_n_flags & RATE_MCS_HE_TYPE_MSK; - if (info_type == IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT || - info_type == IWL_RX_PHY_INFO_TYPE_EHT_MU) - iwl_mld_decode_eht_ext_mu(mld, phy_data, rx_status, eht, usig); + if (he_type == RATE_MCS_HE_TYPE_TRIG) + iwl_mld_decode_eht_tb(phy_data, rx_status, eht); + else + iwl_mld_decode_eht_non_tb(phy_data, rx_status, eht); } static void iwl_mld_rx_eht(struct iwl_mld *mld, struct sk_buff *skb, - struct iwl_mld_rx_phy_data *phy_data, - int queue) + struct iwl_mld_rx_phy_data *phy_data) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); struct ieee80211_radiotap_eht *eht; - struct ieee80211_radiotap_eht_usig *usig; size_t eht_len = sizeof(*eht); - u32 rate_n_flags = phy_data->rate_n_flags; u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK; /* EHT and HE have the same values for LTF */ u8 ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN; - u16 phy_info = phy_data->phy_info; - u32 bw; /* u32 for 1 user_info */ if (phy_data->with_data) @@ -1065,50 +1106,7 @@ static void iwl_mld_rx_eht(struct iwl_mld *mld, struct sk_buff *skb, eht = iwl_mld_radiotap_put_tlv(skb, IEEE80211_RADIOTAP_EHT, eht_len); - usig = iwl_mld_radiotap_put_tlv(skb, IEEE80211_RADIOTAP_EHT_USIG, - sizeof(*usig)); rx_status->flag |= RX_FLAG_RADIOTAP_TLV_AT_END; - usig->common |= - cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_KNOWN); - - /* specific handling for 320MHz */ - bw = u32_get_bits(rate_n_flags, RATE_MCS_CHAN_WIDTH_MSK); - if (bw == RATE_MCS_CHAN_WIDTH_320_VAL) - bw += le32_get_bits(phy_data->data0, - IWL_RX_PHY_DATA0_EHT_BW320_SLOT); - - usig->common |= cpu_to_le32 - (FIELD_PREP(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW, bw)); - - /* report the AMPDU-EOF bit on single frames */ - if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) { - rx_status->flag |= RX_FLAG_AMPDU_DETAILS; - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; - if (phy_data->data0 & - cpu_to_le32(IWL_RX_PHY_DATA0_EHT_DELIM_EOF)) - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; - } - - /* update aggregation data for monitor sake on default queue */ - if (!queue && (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) && - (phy_info & IWL_RX_MPDU_PHY_AMPDU) && phy_data->first_subframe) { - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; - if (phy_data->data0 & - cpu_to_le32(IWL_RX_PHY_DATA0_EHT_DELIM_EOF)) - rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; - } - - if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) - iwl_mld_decode_eht_phy_data(mld, phy_data, rx_status, eht, usig); - -#define CHECK_TYPE(F) \ - BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_ ## F != \ - (RATE_MCS_HE_TYPE_ ## F >> RATE_MCS_HE_TYPE_POS)) - - CHECK_TYPE(SU); - CHECK_TYPE(EXT_SU); - CHECK_TYPE(MU); - CHECK_TYPE(TRIG); switch (u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK)) { case 0: @@ -1144,20 +1142,18 @@ static void iwl_mld_rx_eht(struct iwl_mld *mld, struct sk_buff *skb, if (ltf != IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN) { eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_GI); - eht->data[0] |= cpu_to_le32 - (FIELD_PREP(IEEE80211_RADIOTAP_EHT_DATA0_LTF, - ltf) | - FIELD_PREP(IEEE80211_RADIOTAP_EHT_DATA0_GI, - rx_status->eht.gi)); + eht->data[0] |= le32_encode_bits(ltf, + IEEE80211_RADIOTAP_EHT_DATA0_LTF) | + le32_encode_bits(rx_status->eht.gi, + IEEE80211_RADIOTAP_EHT_DATA0_GI); } if (!phy_data->with_data) { eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_NSS_S | IEEE80211_RADIOTAP_EHT_KNOWN_BEAMFORMED_S); - eht->data[7] |= - le32_encode_bits(le32_get_bits(phy_data->rx_vec[2], - RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK), - IEEE80211_RADIOTAP_EHT_DATA7_NSS_S); + eht->data[7] |= LE32_DEC_ENC(phy_data->ntfy->sigs.eht.b1, + OFDM_RX_FRAME_EHT_NSTS, + IEEE80211_RADIOTAP_EHT_DATA7_NSS_S); if (rate_n_flags & RATE_MCS_BF_MSK) eht->data[7] |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_DATA7_BEAMFORMED_S); @@ -1177,14 +1173,28 @@ static void iwl_mld_rx_eht(struct iwl_mld *mld, struct sk_buff *skb, eht->user_info[0] |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_CODING); - eht->user_info[0] |= cpu_to_le32 - (FIELD_PREP(IEEE80211_RADIOTAP_EHT_USER_INFO_MCS, - u32_get_bits(rate_n_flags, - RATE_VHT_MCS_RATE_CODE_MSK)) | - FIELD_PREP(IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O, - u32_get_bits(rate_n_flags, - RATE_MCS_NSS_MSK))); + eht->user_info[0] |= + le32_encode_bits(u32_get_bits(rate_n_flags, + RATE_VHT_MCS_RATE_CODE_MSK), + IEEE80211_RADIOTAP_EHT_USER_INFO_MCS) | + le32_encode_bits(u32_get_bits(rate_n_flags, + RATE_MCS_NSS_MSK), + IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O); } + + if (likely(!phy_data->ntfy)) + return; + + if (phy_data->with_data) { + eht->user_info[0] |= + cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID_KNOWN) | + LE32_DEC_ENC(phy_data->ntfy->sigs.eht.user_id, + OFDM_RX_FRAME_EHT_USER_FIELD_ID, + IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID); + } + + iwl_mld_decode_eht_usig(phy_data, skb); + iwl_mld_decode_eht_phy_data(phy_data, rx_status, eht); } #ifdef CONFIG_IWLWIFI_DEBUGFS @@ -1207,8 +1217,9 @@ static void iwl_mld_add_rtap_sniffer_config(struct iwl_mld *mld, radiotap->oui[0] = 0xf6; radiotap->oui[1] = 0x54; radiotap->oui[2] = 0x25; - /* radiotap sniffer config sub-namespace */ + /* Intel OUI default radiotap subtype */ radiotap->oui_subtype = 1; + /* Sniffer config element type */ radiotap->vendor_type = 0; /* fill the data now */ @@ -1219,34 +1230,58 @@ static void iwl_mld_add_rtap_sniffer_config(struct iwl_mld *mld, } #endif -/* Note: hdr can be NULL */ -static void iwl_mld_rx_fill_status(struct iwl_mld *mld, int link_id, - struct ieee80211_hdr *hdr, - struct sk_buff *skb, - struct iwl_mld_rx_phy_data *phy_data, - int queue) +static void iwl_mld_add_rtap_sniffer_phy_data(struct iwl_mld *mld, + struct sk_buff *skb, + struct iwl_rx_phy_air_sniffer_ntfy *ntfy) { struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); - u32 format = phy_data->rate_n_flags & RATE_MCS_MOD_TYPE_MSK; - u32 rate_n_flags = phy_data->rate_n_flags; - u8 stbc = u32_get_bits(rate_n_flags, RATE_MCS_STBC_MSK); - bool is_sgi = rate_n_flags & RATE_MCS_SGI_MSK; + struct ieee80211_radiotap_vendor_content *radiotap; + const u16 vendor_data_len = sizeof(*ntfy); - phy_data->info_type = IWL_RX_PHY_INFO_TYPE_NONE; + radiotap = + iwl_mld_radiotap_put_tlv(skb, + IEEE80211_RADIOTAP_VENDOR_NAMESPACE, + sizeof(*radiotap) + vendor_data_len); - if (phy_data->phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) - phy_data->info_type = - le32_get_bits(phy_data->data1, - IWL_RX_PHY_DATA1_INFO_TYPE_MASK); + /* Intel OUI */ + radiotap->oui[0] = 0xf6; + radiotap->oui[1] = 0x54; + radiotap->oui[2] = 0x25; + /* Intel OUI default radiotap subtype */ + radiotap->oui_subtype = 1; + /* PHY data element type */ + radiotap->vendor_type = cpu_to_le16(1); - /* set the preamble flag if appropriate */ - if (format == RATE_MCS_MOD_TYPE_CCK && - phy_data->phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE) - rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE; + /* fill the data now */ + memcpy(radiotap->data, ntfy, vendor_data_len); - iwl_mld_fill_signal(mld, link_id, hdr, rx_status, phy_data); + rx_status->flag |= RX_FLAG_RADIOTAP_TLV_AT_END; +} + +static void +iwl_mld_set_rx_nonlegacy_rate_info(u32 rate_n_flags, + struct ieee80211_rx_status *rx_status) +{ + u8 stbc = u32_get_bits(rate_n_flags, RATE_MCS_STBC_MSK); + + /* NSS may be overridden by PHY ntfy with full value */ + rx_status->nss = u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1; + rx_status->rate_idx = rate_n_flags & RATE_MCS_CODE_MSK; + rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT; + if (rate_n_flags & RATE_MCS_LDPC_MSK) + rx_status->enc_flags |= RX_ENC_FLAG_LDPC; +} + +static void iwl_mld_set_rx_rate(struct iwl_mld *mld, + struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_rx_status *rx_status) +{ + u32 rate_n_flags = phy_data->rate_n_flags; + u8 stbc = u32_get_bits(rate_n_flags, RATE_MCS_STBC_MSK); + u32 format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK; + bool is_sgi = rate_n_flags & RATE_MCS_SGI_MSK; - /* This may be overridden by iwl_mld_rx_he() to HE_RU */ + /* bandwidth may be overridden to RU by PHY ntfy */ switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) { case RATE_MCS_CHAN_WIDTH_20: break; @@ -1264,17 +1299,93 @@ static void iwl_mld_rx_fill_status(struct iwl_mld *mld, int link_id, break; } - /* must be before L-SIG data */ - if (format == RATE_MCS_MOD_TYPE_HE) - iwl_mld_rx_he(mld, skb, phy_data, queue); + switch (format) { + case RATE_MCS_MOD_TYPE_CCK: + if (phy_data->phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE) + rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE; + fallthrough; + case RATE_MCS_MOD_TYPE_LEGACY_OFDM: { + int rate = + iwl_mld_legacy_hw_idx_to_mac80211_idx(rate_n_flags, + rx_status->band); - iwl_mld_decode_lsig(skb, phy_data); + /* override BW - it could be DUP and indicate the wrong BW */ + rx_status->bw = RATE_INFO_BW_20; + + /* valid rate */ + if (rate >= 0 && rate <= 0xFF) { + rx_status->rate_idx = rate; + break; + } + + /* invalid rate */ + rx_status->rate_idx = 0; + + /* + * In monitor mode we can see CCK frames on 5 or 6 GHz, usually + * just the (possibly malformed) PHY header by accident, since + * the decoder doesn't seem to turn off CCK. We cannot correctly + * encode the rate to mac80211 (and therefore not in radiotap) + * since we give the per-band index which doesn't cover those + * rates. + */ + if (!mld->monitor.on && net_ratelimit()) + IWL_ERR(mld, "invalid rate_n_flags=0x%x, band=%d\n", + rate_n_flags, rx_status->band); + break; + } + case RATE_MCS_MOD_TYPE_HT: + rx_status->encoding = RX_ENC_HT; + rx_status->rate_idx = RATE_HT_MCS_INDEX(rate_n_flags); + rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT; + break; + case RATE_MCS_MOD_TYPE_VHT: + rx_status->encoding = RX_ENC_VHT; + iwl_mld_set_rx_nonlegacy_rate_info(rate_n_flags, rx_status); + break; + case RATE_MCS_MOD_TYPE_HE: + rx_status->encoding = RX_ENC_HE; + rx_status->he_dcm = + !!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK); + iwl_mld_set_rx_nonlegacy_rate_info(rate_n_flags, rx_status); + break; + case RATE_MCS_MOD_TYPE_EHT: + rx_status->encoding = RX_ENC_EHT; + iwl_mld_set_rx_nonlegacy_rate_info(rate_n_flags, rx_status); + break; + default: + WARN_ON_ONCE(1); + } + + if (format != RATE_MCS_MOD_TYPE_CCK && is_sgi) + rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI; +} + +/* Note: hdr can be NULL */ +static void iwl_mld_rx_fill_status(struct iwl_mld *mld, int link_id, + struct ieee80211_hdr *hdr, + struct sk_buff *skb, + struct iwl_mld_rx_phy_data *phy_data) +{ + struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb); + u32 rate_n_flags = phy_data->rate_n_flags; + u32 format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK; + + iwl_mld_fill_signal(mld, link_id, hdr, rx_status, phy_data); rx_status->device_timestamp = phy_data->gp2_on_air_rise; - /* using TLV format and must be after all fixed len fields */ + iwl_mld_set_rx_rate(mld, phy_data, rx_status); + + /* must be before L-SIG data (radiotap field order) */ + if (format == RATE_MCS_MOD_TYPE_HE) + iwl_mld_rx_he(skb, phy_data); + + iwl_mld_decode_lsig(skb, phy_data); + + /* TLVs - must be after radiotap fixed fields */ if (format == RATE_MCS_MOD_TYPE_EHT) - iwl_mld_rx_eht(mld, skb, phy_data, queue); + iwl_mld_rx_eht(mld, skb, phy_data); #ifdef CONFIG_IWLWIFI_DEBUGFS if (unlikely(mld->monitor.on)) { @@ -1282,9 +1393,9 @@ static void iwl_mld_rx_fill_status(struct iwl_mld *mld, int link_id, if (mld->monitor.ptp_time) { u64 adj_time = - iwl_mld_ptp_get_adj_time(mld, - phy_data->gp2_on_air_rise * - NSEC_PER_USEC); + iwl_mld_ptp_get_adj_time(mld, + phy_data->gp2_on_air_rise * + NSEC_PER_USEC); rx_status->mactime = div64_u64(adj_time, NSEC_PER_USEC); rx_status->flag |= RX_FLAG_MACTIME_IS_RTAP_TS64; @@ -1293,56 +1404,8 @@ static void iwl_mld_rx_fill_status(struct iwl_mld *mld, int link_id, } #endif - if (format != RATE_MCS_MOD_TYPE_CCK && is_sgi) - rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI; - - if (rate_n_flags & RATE_MCS_LDPC_MSK) - rx_status->enc_flags |= RX_ENC_FLAG_LDPC; - - switch (format) { - case RATE_MCS_MOD_TYPE_HT: - rx_status->encoding = RX_ENC_HT; - rx_status->rate_idx = RATE_HT_MCS_INDEX(rate_n_flags); - rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT; - break; - case RATE_MCS_MOD_TYPE_VHT: - case RATE_MCS_MOD_TYPE_HE: - case RATE_MCS_MOD_TYPE_EHT: - if (format == RATE_MCS_MOD_TYPE_VHT) { - rx_status->encoding = RX_ENC_VHT; - } else if (format == RATE_MCS_MOD_TYPE_HE) { - rx_status->encoding = RX_ENC_HE; - rx_status->he_dcm = - !!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK); - } else if (format == RATE_MCS_MOD_TYPE_EHT) { - rx_status->encoding = RX_ENC_EHT; - } - - rx_status->nss = u32_get_bits(rate_n_flags, - RATE_MCS_NSS_MSK) + 1; - rx_status->rate_idx = rate_n_flags & RATE_MCS_CODE_MSK; - rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT; - break; - default: { - int rate = - iwl_mld_legacy_hw_idx_to_mac80211_idx(rate_n_flags, - rx_status->band); - - /* valid rate */ - if (rate >= 0 && rate <= 0xFF) { - rx_status->rate_idx = rate; - break; - } - - /* invalid rate */ - rx_status->rate_idx = 0; - - if (net_ratelimit()) - IWL_ERR(mld, "invalid rate_n_flags=0x%x, band=%d\n", - rate_n_flags, rx_status->band); - break; - } - } + if (phy_data->ntfy) + iwl_mld_add_rtap_sniffer_phy_data(mld, skb, phy_data->ntfy); } /* iwl_mld_create_skb adds the rxb to a new skb */ @@ -1763,13 +1826,36 @@ static int iwl_mld_rx_crypto(struct iwl_mld *mld, return 0; } -static void iwl_mld_rx_update_ampdu_ref(struct iwl_mld *mld, - struct iwl_mld_rx_phy_data *phy_data, - struct ieee80211_rx_status *rx_status) +static void iwl_mld_rx_update_ampdu_data(struct iwl_mld *mld, + struct iwl_mld_rx_phy_data *phy_data, + struct ieee80211_rx_status *rx_status) { + u32 format = phy_data->rate_n_flags & RATE_MCS_MOD_TYPE_MSK; bool toggle_bit = phy_data->phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE; + switch (format) { + case RATE_MCS_MOD_TYPE_CCK: + case RATE_MCS_MOD_TYPE_LEGACY_OFDM: + /* no aggregation possible */ + return; + case RATE_MCS_MOD_TYPE_HT: + case RATE_MCS_MOD_TYPE_VHT: + /* single frames are not A-MPDU format */ + if (!(phy_data->phy_info & IWL_RX_MPDU_PHY_AMPDU)) + return; + break; + default: + /* HE/EHT/UHR have A-MPDU format for single frames */ + if (!(phy_data->phy_info & IWL_RX_MPDU_PHY_AMPDU)) { + rx_status->flag |= RX_FLAG_AMPDU_DETAILS; + rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; + if (phy_data->phy_info & IWL_RX_MPDU_PHY_EOF_INDICATION) + rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; + return; + } + } + rx_status->flag |= RX_FLAG_AMPDU_DETAILS; /* Toggle is switched whenever new aggregation starts. Make * sure ampdu_reference is never 0 so we can later use it to @@ -1781,6 +1867,11 @@ static void iwl_mld_rx_update_ampdu_ref(struct iwl_mld *mld, mld->monitor.ampdu_ref++; mld->monitor.ampdu_toggle = toggle_bit; phy_data->first_subframe = true; + + /* report EOF bit on the first subframe */ + rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN; + if (phy_data->phy_info & IWL_RX_MPDU_PHY_EOF_INDICATION) + rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT; } rx_status->ampdu_reference = mld->monitor.ampdu_ref; } @@ -1810,6 +1901,7 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi, u32 mpdu_len; enum iwl_mld_reorder_result reorder_res; struct ieee80211_rx_status *rx_status; + unsigned int alloc_size = 128; if (unlikely(mld->fw_status.in_hw_restart)) return; @@ -1824,10 +1916,17 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi, "FW lied about packet len (%d)\n", pkt_len)) return; + iwl_mld_fill_phy_data_from_mpdu(mld, mpdu_desc, &phy_data); + /* Don't use dev_alloc_skb(), we'll have enough headroom once * ieee80211_hdr pulled. + * + * For monitor mode we need more space to include the full PHY + * notification data. */ - skb = alloc_skb(128, GFP_ATOMIC); + if (unlikely(mld->monitor.on) && phy_data.ntfy) + alloc_size += sizeof(struct iwl_rx_phy_air_sniffer_ntfy); + skb = alloc_skb(alloc_size, GFP_ATOMIC); if (!skb) { IWL_ERR(mld, "alloc_skb failed\n"); return; @@ -1835,8 +1934,6 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi, hdr = (void *)(pkt->data + mpdu_desc_size); - iwl_mld_fill_phy_data(mld, mpdu_desc, &phy_data); - if (mpdu_desc->mac_flags2 & IWL_RX_MPDU_MFLG2_PAD) { /* If the device inserted padding it means that (it thought) * the 802.11 header wasn't a multiple of 4 bytes long. In @@ -1861,9 +1958,8 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi, if (drop) goto drop; - /* update aggregation data for monitor sake on default queue */ - if (!queue && (phy_data.phy_info & IWL_RX_MPDU_PHY_AMPDU)) - iwl_mld_rx_update_ampdu_ref(mld, &phy_data, rx_status); + if (unlikely(mld->monitor.on)) + iwl_mld_rx_update_ampdu_data(mld, &phy_data, rx_status); /* Keep packets with CRC errors (and with overrun) for monitor mode * (otherwise the firmware discards them) but mark them as bad. @@ -1897,7 +1993,7 @@ void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi, link_id = u8_get_bits(mpdu_desc->mac_phy_band, IWL_RX_MPDU_MAC_PHY_BAND_LINK_MASK); - iwl_mld_rx_fill_status(mld, link_id, hdr, skb, &phy_data, queue); + iwl_mld_rx_fill_status(mld, link_id, hdr, skb, &phy_data); if (iwl_mld_rx_crypto(mld, sta, hdr, rx_status, mpdu_desc, queue, le32_to_cpu(pkt->len_n_flags), &crypto_len)) @@ -2031,87 +2127,65 @@ void iwl_mld_handle_rx_queues_sync_notif(struct iwl_mld *mld, wake_up(&mld->rxq_sync.waitq); } -void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi, - struct iwl_rx_packet *pkt, int queue) +static void iwl_mld_no_data_rx(struct iwl_mld *mld, + struct napi_struct *napi, + struct iwl_rx_phy_air_sniffer_ntfy *ntfy) { - struct iwl_rx_no_data_ver_3 *desc; - struct iwl_mld_rx_phy_data phy_data; struct ieee80211_rx_status *rx_status; + struct iwl_mld_rx_phy_data phy_data = { + .ntfy = ntfy, + .phy_info = 0, /* short preamble set below */ + .rate_n_flags = le32_to_cpu(ntfy->rate), + .gp2_on_air_rise = le32_to_cpu(ntfy->on_air_rise_time), + .energy_a = ntfy->rssi_a, + .energy_b = ntfy->rssi_b, + }; + u32 format = phy_data.rate_n_flags & RATE_MCS_MOD_TYPE_MSK; struct sk_buff *skb; - u32 format, rssi; - u8 channel; - - if (unlikely(mld->fw_status.in_hw_restart)) - return; - - if (IWL_FW_CHECK(mld, iwl_rx_packet_payload_len(pkt) < sizeof(*desc), - "Bad RX_NO_DATA_NOTIF size (%d)\n", - iwl_rx_packet_payload_len(pkt))) - return; - - desc = (void *)pkt->data; - - rssi = le32_to_cpu(desc->rssi); - channel = u32_get_bits(rssi, RX_NO_DATA_CHANNEL_MSK); - - phy_data.energy_a = u32_get_bits(rssi, RX_NO_DATA_CHAIN_A_MSK); - phy_data.energy_b = u32_get_bits(rssi, RX_NO_DATA_CHAIN_B_MSK); - phy_data.data0 = desc->phy_info[0]; - phy_data.data1 = desc->phy_info[1]; - phy_data.phy_info = IWL_RX_MPDU_PHY_TSF_OVERLOAD; - phy_data.gp2_on_air_rise = le32_to_cpu(desc->on_air_rise_time); - phy_data.rate_n_flags = iwl_v3_rate_from_v2_v3(desc->rate, - mld->fw_rates_ver_3); - phy_data.with_data = false; - - BUILD_BUG_ON(sizeof(phy_data.rx_vec) != sizeof(desc->rx_vec)); - memcpy(phy_data.rx_vec, desc->rx_vec, sizeof(phy_data.rx_vec)); - format = phy_data.rate_n_flags & RATE_MCS_MOD_TYPE_MSK; - - /* Don't use dev_alloc_skb(), we'll have enough headroom once - * ieee80211_hdr pulled. - */ - skb = alloc_skb(128, GFP_ATOMIC); - if (!skb) { - IWL_ERR(mld, "alloc_skb failed\n"); + skb = alloc_skb(128 + sizeof(struct iwl_rx_phy_air_sniffer_ntfy), + GFP_ATOMIC); + if (!skb) return; - } rx_status = IEEE80211_SKB_RXCB(skb); /* 0-length PSDU */ rx_status->flag |= RX_FLAG_NO_PSDU; - /* mark as failed PLCP on any errors to skip checks in mac80211 */ - if (le32_get_bits(desc->info, RX_NO_DATA_INFO_ERR_MSK) != - RX_NO_DATA_INFO_ERR_NONE) - rx_status->flag |= RX_FLAG_FAILED_PLCP_CRC; - - switch (le32_get_bits(desc->info, RX_NO_DATA_INFO_TYPE_MSK)) { - case RX_NO_DATA_INFO_TYPE_NDP: + switch (ntfy->status) { + case IWL_SNIF_STAT_PLCP_RX_OK: + /* we only get here with sounding PPDUs */ rx_status->zero_length_psdu_type = IEEE80211_RADIOTAP_ZERO_LEN_PSDU_SOUNDING; break; - case RX_NO_DATA_INFO_TYPE_MU_UNMATCHED: - case RX_NO_DATA_INFO_TYPE_TB_UNMATCHED: + case IWL_SNIF_STAT_AID_NOT_FOR_US: rx_status->zero_length_psdu_type = IEEE80211_RADIOTAP_ZERO_LEN_PSDU_NOT_CAPTURED; break; + case IWL_SNIF_STAT_PLCP_RX_LSIG_ERR: + case IWL_SNIF_STAT_PLCP_RX_SIGA_ERR: + case IWL_SNIF_STAT_PLCP_RX_SIGB_ERR: + case IWL_SNIF_STAT_UNKNOWN_ERROR: default: + rx_status->flag |= RX_FLAG_FAILED_PLCP_CRC; + fallthrough; + case IWL_SNIF_STAT_UNEXPECTED_TB: + case IWL_SNIF_STAT_UNSUPPORTED_RATE: rx_status->zero_length_psdu_type = IEEE80211_RADIOTAP_ZERO_LEN_PSDU_VENDOR; - break; + /* we could include the real reason in a vendor TLV */ } - rx_status->band = channel > 14 ? NL80211_BAND_5GHZ : - NL80211_BAND_2GHZ; + if (format == RATE_MCS_MOD_TYPE_CCK && + ntfy->legacy_sig.cck & cpu_to_le32(CCK_CRFR_SHORT_PREAMBLE)) + phy_data.phy_info |= IWL_RX_MPDU_PHY_SHORT_PREAMBLE; - rx_status->freq = ieee80211_channel_to_frequency(channel, - rx_status->band); + iwl_mld_fill_rx_status_band_freq(IEEE80211_SKB_RXCB(skb), + ntfy->band, ntfy->channel); /* link ID is ignored for NULL header */ - iwl_mld_rx_fill_status(mld, -1, NULL, skb, &phy_data, queue); + iwl_mld_rx_fill_status(mld, -1, NULL, skb, &phy_data); /* No more radiotap info should be added after this point. * Mark it as mac header for upper layers to know where @@ -2119,29 +2193,72 @@ void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi, */ skb_set_mac_header(skb, skb->len); - /* Override the nss from the rx_vec since the rate_n_flags has - * only 1 bit for the nss which gives a max of 2 ss but there - * may be up to 8 spatial streams. - */ - switch (format) { + /* pass the packet to mac80211 */ + rcu_read_lock(); + ieee80211_rx_napi(mld->hw, NULL, skb, napi); + rcu_read_unlock(); +} + +void iwl_mld_handle_phy_air_sniffer_notif(struct iwl_mld *mld, + struct napi_struct *napi, + struct iwl_rx_packet *pkt) +{ + struct iwl_rx_phy_air_sniffer_ntfy *ntfy = (void *)pkt->data; + bool is_ndp = false; + u32 he_type; + + if (IWL_FW_CHECK(mld, iwl_rx_packet_payload_len(pkt) < sizeof(*ntfy), + "invalid air sniffer notification size\n")) + return; + + /* check if there's an old one to release as errored */ + if (mld->monitor.phy.valid && !mld->monitor.phy.used) { + /* didn't capture data, so override status */ + mld->monitor.phy.data.status = IWL_SNIF_STAT_AID_NOT_FOR_US; + iwl_mld_no_data_rx(mld, napi, &mld->monitor.phy.data); + } + + /* old data is no longer valid now */ + mld->monitor.phy.valid = false; + + he_type = le32_to_cpu(ntfy->rate) & RATE_MCS_HE_TYPE_MSK; + + switch (le32_to_cpu(ntfy->rate) & RATE_MCS_MOD_TYPE_MSK) { + case RATE_MCS_MOD_TYPE_HT: + is_ndp = !le32_get_bits(ntfy->sigs.ht.a1, + OFDM_RX_FRAME_HT_LENGTH); + break; case RATE_MCS_MOD_TYPE_VHT: - rx_status->nss = - le32_get_bits(desc->rx_vec[0], - RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK) + 1; + is_ndp = le32_get_bits(ntfy->sigs.vht.a0, + OFDM_RX_FRAME_VHT_NUM_OF_DATA_SYM_VALID) && + !le32_get_bits(ntfy->sigs.vht.a0, + OFDM_RX_FRAME_VHT_NUM_OF_DATA_SYM); break; case RATE_MCS_MOD_TYPE_HE: - rx_status->nss = - le32_get_bits(desc->rx_vec[0], - RX_NO_DATA_RX_VEC0_HE_NSTS_MSK) + 1; + if (he_type == RATE_MCS_HE_TYPE_TRIG) + break; + is_ndp = le32_get_bits(ntfy->sigs.he.a3, + OFDM_RX_FRAME_HE_NUM_OF_DATA_SYM_VALID) && + !le32_get_bits(ntfy->sigs.he.a3, + OFDM_RX_FRAME_HE_NUM_OF_DATA_SYM); break; case RATE_MCS_MOD_TYPE_EHT: - rx_status->nss = - le32_get_bits(desc->rx_vec[2], - RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK) + 1; + if (he_type == RATE_MCS_HE_TYPE_TRIG) + break; + is_ndp = le32_get_bits(ntfy->sigs.eht.sig2, + OFDM_RX_FRAME_EHT_NUM_OF_DATA_SYM_VALID) && + !le32_get_bits(ntfy->sigs.eht.sig2, + OFDM_RX_FRAME_EHT_NUM_OF_DATA_SYM); + break; } - /* pass the packet to mac80211 */ - rcu_read_lock(); - ieee80211_rx_napi(mld->hw, NULL, skb, napi); - rcu_read_unlock(); + if (ntfy->status != IWL_SNIF_STAT_PLCP_RX_OK || is_ndp) { + iwl_mld_no_data_rx(mld, napi, ntfy); + return; + } + + /* hang on to it for the RX_MPDU data packet(s) */ + mld->monitor.phy.data = *ntfy; + mld->monitor.phy.valid = true; + mld->monitor.phy.used = false; } diff --git a/drivers/net/wireless/intel/iwlwifi/mld/rx.h b/drivers/net/wireless/intel/iwlwifi/mld/rx.h index 2beabd7e70b15..09dddbd40f553 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/rx.h +++ b/drivers/net/wireless/intel/iwlwifi/mld/rx.h @@ -66,7 +66,8 @@ void iwl_mld_pass_packet_to_mac80211(struct iwl_mld *mld, struct sk_buff *skb, int queue, struct ieee80211_sta *sta); -void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi, - struct iwl_rx_packet *pkt, int queue); +void iwl_mld_handle_phy_air_sniffer_notif(struct iwl_mld *mld, + struct napi_struct *napi, + struct iwl_rx_packet *pkt); #endif /* __iwl_mld_agg_h__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.c b/drivers/net/wireless/intel/iwlwifi/mld/sta.c index 5cdbfa29a2027..61ecc33116cf0 100644 --- a/drivers/net/wireless/intel/iwlwifi/mld/sta.c +++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.c @@ -890,7 +890,7 @@ static void iwl_mld_count_mpdu(struct ieee80211_link_sta *link_sta, int queue, sizeof(queue_counter->per_link)); queue_counter->window_start_time = jiffies; - IWL_DEBUG_INFO(mld, "MPDU counters are cleared\n"); + IWL_DEBUG_EHT(mld, "MPDU counters are cleared\n"); } link_counter = &queue_counter->per_link[mld_link->fw_id]; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c index 865f973f677db..edae13755ee61 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c @@ -115,7 +115,7 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, if (version >= 6) { - struct iwl_alive_ntf_v6 *palive; + struct iwl_alive_ntf_v7 *palive; if (pkt_len < sizeof(*palive)) return false; @@ -214,17 +214,8 @@ static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait, ~FW_ADDR_CACHE_CONTROL; if (umac_error_table) { - if (umac_error_table >= - mvm->trans->mac_cfg->base->min_umac_error_event_table) { - iwl_fw_umac_set_alive_err_table(mvm->trans, - umac_error_table); - } else { - IWL_ERR(mvm, - "Not valid error log pointer 0x%08X for %s uCode\n", - umac_error_table, - (mvm->fwrt.cur_fw_img == IWL_UCODE_INIT) ? - "Init" : "RT"); - } + iwl_fw_umac_set_alive_err_table(mvm->trans, + umac_error_table); } alive_data->valid = status == IWL_ALIVE_STATUS_OK; diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c index b1dca76b7141e..380b6f8a53fde 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c @@ -102,9 +102,6 @@ static int iwl_mvm_mld_mac_add_interface(struct ieee80211_hw *hw, mvm->csme_vif = vif; } - if (vif->p2p || iwl_fw_lookup_cmd_ver(mvm->fw, PHY_CONTEXT_CMD, 1) < 5) - vif->driver_flags |= IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW; - return 0; out_free_bf: diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h index b515028adc8f5..301d590fe0bd6 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h @@ -2894,4 +2894,9 @@ iwl_mvm_send_ap_tx_power_constraint_cmd(struct iwl_mvm *mvm, void iwl_mvm_smps_workaround(struct iwl_mvm *mvm, struct ieee80211_vif *vif, bool update); + +/* rate_n_flags conversion */ +u32 iwl_mvm_v3_rate_from_fw(__le32 rate, u8 rate_ver); +__le32 iwl_mvm_v3_rate_to_fw(u32 rate, u8 rate_ver); + #endif /* __IWL_MVM_H__ */ diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c index 5e7e2926be0ce..4f4111055ddd2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/phy-ctxt.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause /* - * Copyright (C) 2012-2014, 2018-2024 Intel Corporation + * Copyright (C) 2012-2014, 2018-2025 Intel Corporation * Copyright (C) 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2017 Intel Deutschland GmbH */ @@ -202,17 +202,13 @@ int iwl_mvm_phy_send_rlc(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt, static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt, const struct cfg80211_chan_def *chandef, - const struct cfg80211_chan_def *ap, u8 chains_static, u8 chains_dynamic, u32 action) { int ret; int ver = iwl_fw_lookup_cmd_ver(mvm->fw, PHY_CONTEXT_CMD, 1); - if (ver < 5 || !ap || !ap->chan) - ap = NULL; - - if (ver >= 3 && ver <= 6) { + if (ver >= 3 && ver <= 4) { struct iwl_phy_context_cmd cmd = {}; /* Set the command header fields */ @@ -223,14 +219,6 @@ static int iwl_mvm_phy_ctxt_apply(struct iwl_mvm *mvm, chains_static, chains_dynamic); - if (ap) { - cmd.sbb_bandwidth = iwl_mvm_get_channel_width(ap); - cmd.sbb_ctrl_channel_loc = iwl_mvm_get_ctrl_pos(ap); - } - - if (ver == 6) - cmd.puncture_mask = cpu_to_le16(chandef->punctured); - ret = iwl_mvm_send_cmd_pdu(mvm, PHY_CONTEXT_CMD, 0, sizeof(cmd), &cmd); } else if (ver < 3) { @@ -284,7 +272,7 @@ int iwl_mvm_phy_ctxt_add(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt, ctxt->width = chandef->width; ctxt->center_freq1 = chandef->center_freq1; - ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, ap, + ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, chains_static, chains_dynamic, FW_CTXT_ACTION_ADD); @@ -342,7 +330,7 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt, int ret; /* ... remove it here ...*/ - ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, NULL, + ret = iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, chains_static, chains_dynamic, FW_CTXT_ACTION_REMOVE); if (ret) @@ -356,7 +344,7 @@ int iwl_mvm_phy_ctxt_changed(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt, ctxt->width = chandef->width; ctxt->center_freq1 = chandef->center_freq1; - return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, ap, + return iwl_mvm_phy_ctxt_apply(mvm, ctxt, chandef, chains_static, chains_dynamic, action); } @@ -376,7 +364,7 @@ void iwl_mvm_phy_ctxt_unref(struct iwl_mvm *mvm, struct iwl_mvm_phy_ctxt *ctxt) cfg80211_chandef_create(&chandef, ctxt->channel, NL80211_CHAN_NO_HT); - iwl_mvm_phy_ctxt_apply(mvm, ctxt, &chandef, NULL, 1, 1, + iwl_mvm_phy_ctxt_apply(mvm, ctxt, &chandef, 1, 1, FW_CTXT_ACTION_REMOVE); } diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c index 5802ed80a9ca9..d1619a229d8f2 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c @@ -4178,167 +4178,3 @@ int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, else return rs_drv_tx_protection(mvm, mvmsta, enable); } - -static u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags) -{ - int rate = rate_n_flags & RATE_LEGACY_RATE_MSK_V1; - int idx; - bool ofdm = !(rate_n_flags & RATE_MCS_CCK_MSK_V1); - int offset = ofdm ? IWL_FIRST_OFDM_RATE : 0; - int last = ofdm ? IWL_RATE_COUNT_LEGACY : IWL_FIRST_OFDM_RATE; - - for (idx = offset; idx < last; idx++) - if (iwl_fw_rate_idx_to_plcp(idx) == rate) - return idx - offset; - return IWL_RATE_INVALID; -} - -u32 iwl_mvm_v3_rate_from_fw(__le32 rate, u8 rate_ver) -{ - u32 rate_v3 = 0, rate_v1; - u32 dup = 0; - - if (rate_ver > 1) - return iwl_v3_rate_from_v2_v3(rate, rate_ver >= 3); - - rate_v1 = le32_to_cpu(rate); - if (rate_v1 == 0) - return rate_v1; - /* convert rate */ - if (rate_v1 & RATE_MCS_HT_MSK_V1) { - u32 nss; - - rate_v3 |= RATE_MCS_MOD_TYPE_HT; - rate_v3 |= - rate_v1 & RATE_HT_MCS_RATE_CODE_MSK_V1; - nss = u32_get_bits(rate_v1, RATE_HT_MCS_MIMO2_MSK); - rate_v3 |= u32_encode_bits(nss, RATE_MCS_NSS_MSK); - } else if (rate_v1 & RATE_MCS_VHT_MSK_V1 || - rate_v1 & RATE_MCS_HE_MSK_V1) { - u32 nss = u32_get_bits(rate_v1, RATE_VHT_MCS_NSS_MSK); - - rate_v3 |= rate_v1 & RATE_VHT_MCS_RATE_CODE_MSK; - - rate_v3 |= u32_encode_bits(nss, RATE_MCS_NSS_MSK); - - if (rate_v1 & RATE_MCS_HE_MSK_V1) { - u32 he_type_bits = rate_v1 & RATE_MCS_HE_TYPE_MSK_V1; - u32 he_type = he_type_bits >> RATE_MCS_HE_TYPE_POS_V1; - u32 he_106t = (rate_v1 & RATE_MCS_HE_106T_MSK_V1) >> - RATE_MCS_HE_106T_POS_V1; - u32 he_gi_ltf = (rate_v1 & RATE_MCS_HE_GI_LTF_MSK_V1) >> - RATE_MCS_HE_GI_LTF_POS; - - if ((he_type_bits == RATE_MCS_HE_TYPE_SU || - he_type_bits == RATE_MCS_HE_TYPE_EXT_SU) && - he_gi_ltf == RATE_MCS_HE_SU_4_LTF) - /* the new rate have an additional bit to - * represent the value 4 rather then using SGI - * bit for this purpose - as it was done in the - * old rate - */ - he_gi_ltf += (rate_v1 & RATE_MCS_SGI_MSK_V1) >> - RATE_MCS_SGI_POS_V1; - - rate_v3 |= he_gi_ltf << RATE_MCS_HE_GI_LTF_POS; - rate_v3 |= he_type << RATE_MCS_HE_TYPE_POS; - rate_v3 |= he_106t << RATE_MCS_HE_106T_POS; - rate_v3 |= rate_v1 & RATE_HE_DUAL_CARRIER_MODE_MSK; - rate_v3 |= RATE_MCS_MOD_TYPE_HE; - } else { - rate_v3 |= RATE_MCS_MOD_TYPE_VHT; - } - /* if legacy format */ - } else { - u32 legacy_rate = iwl_legacy_rate_to_fw_idx(rate_v1); - - if (WARN_ON_ONCE(legacy_rate == IWL_RATE_INVALID)) - legacy_rate = (rate_v1 & RATE_MCS_CCK_MSK_V1) ? - IWL_FIRST_CCK_RATE : IWL_FIRST_OFDM_RATE; - - rate_v3 |= legacy_rate; - if (!(rate_v1 & RATE_MCS_CCK_MSK_V1)) - rate_v3 |= RATE_MCS_MOD_TYPE_LEGACY_OFDM; - } - - /* convert flags */ - if (rate_v1 & RATE_MCS_LDPC_MSK_V1) - rate_v3 |= RATE_MCS_LDPC_MSK; - rate_v3 |= (rate_v1 & RATE_MCS_CHAN_WIDTH_MSK_V1) | - (rate_v1 & RATE_MCS_ANT_AB_MSK) | - (rate_v1 & RATE_MCS_STBC_MSK) | - (rate_v1 & RATE_MCS_BF_MSK); - - dup = (rate_v1 & RATE_MCS_DUP_MSK_V1) >> RATE_MCS_DUP_POS_V1; - if (dup) { - rate_v3 |= RATE_MCS_DUP_MSK; - rate_v3 |= dup << RATE_MCS_CHAN_WIDTH_POS; - } - - if ((!(rate_v1 & RATE_MCS_HE_MSK_V1)) && - (rate_v1 & RATE_MCS_SGI_MSK_V1)) - rate_v3 |= RATE_MCS_SGI_MSK; - - return rate_v3; -} - -__le32 iwl_mvm_v3_rate_to_fw(u32 rate, u8 rate_ver) -{ - u32 result = 0; - int rate_idx; - - if (rate_ver > 1) - return iwl_v3_rate_to_v2_v3(rate, rate_ver > 2); - - switch (rate & RATE_MCS_MOD_TYPE_MSK) { - case RATE_MCS_MOD_TYPE_CCK: - result = RATE_MCS_CCK_MSK_V1; - fallthrough; - case RATE_MCS_MOD_TYPE_LEGACY_OFDM: - rate_idx = u32_get_bits(rate, RATE_LEGACY_RATE_MSK); - if (!(result & RATE_MCS_CCK_MSK_V1)) - rate_idx += IWL_FIRST_OFDM_RATE; - result |= u32_encode_bits(iwl_fw_rate_idx_to_plcp(rate_idx), - RATE_LEGACY_RATE_MSK_V1); - break; - case RATE_MCS_MOD_TYPE_HT: - result = RATE_MCS_HT_MSK_V1; - result |= u32_encode_bits(u32_get_bits(rate, - RATE_HT_MCS_CODE_MSK), - RATE_HT_MCS_RATE_CODE_MSK_V1); - result |= u32_encode_bits(u32_get_bits(rate, - RATE_MCS_NSS_MSK), - RATE_HT_MCS_MIMO2_MSK); - break; - case RATE_MCS_MOD_TYPE_VHT: - result = RATE_MCS_VHT_MSK_V1; - result |= u32_encode_bits(u32_get_bits(rate, - RATE_VHT_MCS_NSS_MSK), - RATE_MCS_CODE_MSK); - result |= u32_encode_bits(u32_get_bits(rate, RATE_MCS_NSS_MSK), - RATE_VHT_MCS_NSS_MSK); - break; - case RATE_MCS_MOD_TYPE_HE: /* not generated */ - default: - WARN_ONCE(1, "bad modulation type %d\n", - u32_get_bits(rate, RATE_MCS_MOD_TYPE_MSK)); - return 0; - } - - if (rate & RATE_MCS_LDPC_MSK) - result |= RATE_MCS_LDPC_MSK_V1; - WARN_ON_ONCE(u32_get_bits(rate, RATE_MCS_CHAN_WIDTH_MSK) > - RATE_MCS_CHAN_WIDTH_160_VAL); - result |= (rate & RATE_MCS_CHAN_WIDTH_MSK_V1) | - (rate & RATE_MCS_ANT_AB_MSK) | - (rate & RATE_MCS_STBC_MSK) | - (rate & RATE_MCS_BF_MSK); - - /* not handling DUP since we don't use it */ - WARN_ON_ONCE(rate & RATE_MCS_DUP_MSK); - - if (rate & RATE_MCS_SGI_MSK) - result |= RATE_MCS_SGI_MSK_V1; - - return cpu_to_le32(result); -} diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h index dfb062b7c5c21..34c957bef6f8a 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h @@ -425,9 +425,6 @@ void iwl_mvm_rate_control_unregister(void); struct iwl_mvm_sta; -u32 iwl_mvm_v3_rate_from_fw(__le32 rate, u8 rate_ver); -__le32 iwl_mvm_v3_rate_to_fw(u32 rate, u8 rate_ver); - int iwl_mvm_tx_protection(struct iwl_mvm *mvm, struct iwl_mvm_sta *mvmsta, bool enable); diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c index 8c1bb3a7ffcaa..d0c0faae01221 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/rx.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/rx.c @@ -519,6 +519,8 @@ void iwl_mvm_rx_rx_mpdu(struct iwl_mvm *mvm, struct napi_struct *napi, return; } rx_status->rate_idx = rate; + /* override BW - it could be DUP and indicate the wrong BW */ + rx_status->bw = RATE_INFO_BW_20; } #ifdef CONFIG_IWLWIFI_DEBUGFS diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c index fa995e235d9b4..1a6c1f8706e1c 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c @@ -1243,3 +1243,167 @@ bool iwl_mvm_vif_is_active(struct iwl_mvm_vif *mvmvif) return false; } + +static u32 iwl_legacy_rate_to_fw_idx(u32 rate_n_flags) +{ + int rate = rate_n_flags & RATE_LEGACY_RATE_MSK_V1; + int idx; + bool ofdm = !(rate_n_flags & RATE_MCS_CCK_MSK_V1); + int offset = ofdm ? IWL_FIRST_OFDM_RATE : 0; + int last = ofdm ? IWL_RATE_COUNT_LEGACY : IWL_FIRST_OFDM_RATE; + + for (idx = offset; idx < last; idx++) + if (iwl_fw_rate_idx_to_plcp(idx) == rate) + return idx - offset; + return IWL_RATE_INVALID; +} + +u32 iwl_mvm_v3_rate_from_fw(__le32 rate, u8 rate_ver) +{ + u32 rate_v3 = 0, rate_v1; + u32 dup = 0; + + if (rate_ver > 1) + return iwl_v3_rate_from_v2_v3(rate, rate_ver >= 3); + + rate_v1 = le32_to_cpu(rate); + if (rate_v1 == 0) + return rate_v1; + /* convert rate */ + if (rate_v1 & RATE_MCS_HT_MSK_V1) { + u32 nss; + + rate_v3 |= RATE_MCS_MOD_TYPE_HT; + rate_v3 |= + rate_v1 & RATE_HT_MCS_RATE_CODE_MSK_V1; + nss = u32_get_bits(rate_v1, RATE_HT_MCS_MIMO2_MSK); + rate_v3 |= u32_encode_bits(nss, RATE_MCS_NSS_MSK); + } else if (rate_v1 & RATE_MCS_VHT_MSK_V1 || + rate_v1 & RATE_MCS_HE_MSK_V1) { + u32 nss = u32_get_bits(rate_v1, RATE_VHT_MCS_NSS_MSK); + + rate_v3 |= rate_v1 & RATE_VHT_MCS_RATE_CODE_MSK; + + rate_v3 |= u32_encode_bits(nss, RATE_MCS_NSS_MSK); + + if (rate_v1 & RATE_MCS_HE_MSK_V1) { + u32 he_type_bits = rate_v1 & RATE_MCS_HE_TYPE_MSK_V1; + u32 he_type = he_type_bits >> RATE_MCS_HE_TYPE_POS_V1; + u32 he_106t = (rate_v1 & RATE_MCS_HE_106T_MSK_V1) >> + RATE_MCS_HE_106T_POS_V1; + u32 he_gi_ltf = (rate_v1 & RATE_MCS_HE_GI_LTF_MSK_V1) >> + RATE_MCS_HE_GI_LTF_POS; + + if ((he_type_bits == RATE_MCS_HE_TYPE_SU || + he_type_bits == RATE_MCS_HE_TYPE_EXT_SU) && + he_gi_ltf == RATE_MCS_HE_SU_4_LTF) + /* the new rate have an additional bit to + * represent the value 4 rather then using SGI + * bit for this purpose - as it was done in the + * old rate + */ + he_gi_ltf += (rate_v1 & RATE_MCS_SGI_MSK_V1) >> + RATE_MCS_SGI_POS_V1; + + rate_v3 |= he_gi_ltf << RATE_MCS_HE_GI_LTF_POS; + rate_v3 |= he_type << RATE_MCS_HE_TYPE_POS; + rate_v3 |= he_106t << RATE_MCS_HE_106T_POS; + rate_v3 |= rate_v1 & RATE_HE_DUAL_CARRIER_MODE_MSK; + rate_v3 |= RATE_MCS_MOD_TYPE_HE; + } else { + rate_v3 |= RATE_MCS_MOD_TYPE_VHT; + } + /* if legacy format */ + } else { + u32 legacy_rate = iwl_legacy_rate_to_fw_idx(rate_v1); + + if (WARN_ON_ONCE(legacy_rate == IWL_RATE_INVALID)) + legacy_rate = (rate_v1 & RATE_MCS_CCK_MSK_V1) ? + IWL_FIRST_CCK_RATE : IWL_FIRST_OFDM_RATE; + + rate_v3 |= legacy_rate; + if (!(rate_v1 & RATE_MCS_CCK_MSK_V1)) + rate_v3 |= RATE_MCS_MOD_TYPE_LEGACY_OFDM; + } + + /* convert flags */ + if (rate_v1 & RATE_MCS_LDPC_MSK_V1) + rate_v3 |= RATE_MCS_LDPC_MSK; + rate_v3 |= (rate_v1 & RATE_MCS_CHAN_WIDTH_MSK_V1) | + (rate_v1 & RATE_MCS_ANT_AB_MSK) | + (rate_v1 & RATE_MCS_STBC_MSK) | + (rate_v1 & RATE_MCS_BF_MSK); + + dup = (rate_v1 & RATE_MCS_DUP_MSK_V1) >> RATE_MCS_DUP_POS_V1; + if (dup) { + rate_v3 |= RATE_MCS_DUP_MSK; + rate_v3 |= dup << RATE_MCS_CHAN_WIDTH_POS; + } + + if ((!(rate_v1 & RATE_MCS_HE_MSK_V1)) && + (rate_v1 & RATE_MCS_SGI_MSK_V1)) + rate_v3 |= RATE_MCS_SGI_MSK; + + return rate_v3; +} + +__le32 iwl_mvm_v3_rate_to_fw(u32 rate, u8 rate_ver) +{ + u32 result = 0; + int rate_idx; + + if (rate_ver > 1) + return iwl_v3_rate_to_v2_v3(rate, rate_ver > 2); + + switch (rate & RATE_MCS_MOD_TYPE_MSK) { + case RATE_MCS_MOD_TYPE_CCK: + result = RATE_MCS_CCK_MSK_V1; + fallthrough; + case RATE_MCS_MOD_TYPE_LEGACY_OFDM: + rate_idx = u32_get_bits(rate, RATE_LEGACY_RATE_MSK); + if (!(result & RATE_MCS_CCK_MSK_V1)) + rate_idx += IWL_FIRST_OFDM_RATE; + result |= u32_encode_bits(iwl_fw_rate_idx_to_plcp(rate_idx), + RATE_LEGACY_RATE_MSK_V1); + break; + case RATE_MCS_MOD_TYPE_HT: + result = RATE_MCS_HT_MSK_V1; + result |= u32_encode_bits(u32_get_bits(rate, + RATE_HT_MCS_CODE_MSK), + RATE_HT_MCS_RATE_CODE_MSK_V1); + result |= u32_encode_bits(u32_get_bits(rate, + RATE_MCS_NSS_MSK), + RATE_HT_MCS_MIMO2_MSK); + break; + case RATE_MCS_MOD_TYPE_VHT: + result = RATE_MCS_VHT_MSK_V1; + result |= u32_encode_bits(u32_get_bits(rate, + RATE_VHT_MCS_NSS_MSK), + RATE_MCS_CODE_MSK); + result |= u32_encode_bits(u32_get_bits(rate, RATE_MCS_NSS_MSK), + RATE_VHT_MCS_NSS_MSK); + break; + case RATE_MCS_MOD_TYPE_HE: /* not generated */ + default: + WARN_ONCE(1, "bad modulation type %d\n", + u32_get_bits(rate, RATE_MCS_MOD_TYPE_MSK)); + return 0; + } + + if (rate & RATE_MCS_LDPC_MSK) + result |= RATE_MCS_LDPC_MSK_V1; + WARN_ON_ONCE(u32_get_bits(rate, RATE_MCS_CHAN_WIDTH_MSK) > + RATE_MCS_CHAN_WIDTH_160_VAL); + result |= (rate & RATE_MCS_CHAN_WIDTH_MSK_V1) | + (rate & RATE_MCS_ANT_AB_MSK) | + (rate & RATE_MCS_STBC_MSK) | + (rate & RATE_MCS_BF_MSK); + + /* not handling DUP since we don't use it */ + WARN_ON_ONCE(rate & RATE_MCS_DUP_MSK); + + if (rate & RATE_MCS_SGI_MSK) + result |= RATE_MCS_SGI_MSK_V1; + + return cpu_to_le32(result); +} diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c index b21a4d8eb1051..dc99e7ac47261 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c @@ -1061,12 +1061,18 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = { /* WH RF */ IWL_DEV_INFO(iwl_rf_wh, iwl_be211_name, RF_TYPE(WH)), + IWL_DEV_INFO(iwl_rf_wh_non_eht, iwl_ax221_name, RF_TYPE(WH), + SUBDEV(0x0514)), + IWL_DEV_INFO(iwl_rf_wh_non_eht, iwl_ax221_name, RF_TYPE(WH), + SUBDEV(0x4514)), IWL_DEV_INFO(iwl_rf_wh_160mhz, iwl_be213_name, RF_TYPE(WH), BW_LIMITED), /* PE RF */ IWL_DEV_INFO(iwl_rf_pe, iwl_bn201_name, RF_TYPE(PE)), - IWL_DEV_INFO(iwl_rf_pe, iwl_be223_name, RF_TYPE(PE), SUBDEV(0x0524)), - IWL_DEV_INFO(iwl_rf_pe, iwl_be221_name, RF_TYPE(PE), SUBDEV(0x0324)), + IWL_DEV_INFO(iwl_rf_pe, iwl_be223_name, RF_TYPE(PE), + SUBDEV_MASKED(0x0524, 0xFFF)), + IWL_DEV_INFO(iwl_rf_pe, iwl_bn203_name, RF_TYPE(PE), + SUBDEV_MASKED(0x0324, 0xFFF)), /* Killer */ IWL_DEV_INFO(iwl_rf_wh, iwl_killer_be1775s_name, SUBDEV(0x1776)), diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans.c index 59307b5df4417..164d060ec617c 100644 --- a/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/gen1_2/trans.c @@ -4218,6 +4218,15 @@ int iwl_pci_gen1_2_probe(struct pci_dev *pdev, pdev->device, pdev->subsystem_device, info.hw_rev, info.hw_rf_id); +#if !IS_ENABLED(CONFIG_IWLMLD) + if (iwl_drv_is_wifi7_supported(iwl_trans)) { + IWL_ERR(iwl_trans, + "IWLMLD needs to be compiled to support this device\n"); + ret = -EOPNOTSUPP; + goto out_free_trans; + } +#endif + dev_info = iwl_pci_find_dev_info(pdev->device, pdev->subsystem_device, CSR_HW_RFID_TYPE(info.hw_rf_id), CSR_HW_RFID_IS_CDB(info.hw_rf_id), diff --git a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c index c31bbd4e7a4ae..6bf2ad18b0091 100644 --- a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c +++ b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c @@ -265,6 +265,34 @@ static void devinfo_api_range(struct kunit *test) } } +static void devinfo_pci_ids_config(struct kunit *test) +{ + for (int i = 0; iwl_hw_card_ids[i].vendor; i++) { + const struct pci_device_id *s = &iwl_hw_card_ids[i]; + const struct iwl_dev_info *di; + + if (s->device == PCI_ANY_ID || s->subdevice == PCI_ANY_ID) + continue; + +#if IS_ENABLED(CONFIG_IWLMVM) || IS_ENABLED(CONFIG_IWLMLD) + /* + * The check below only works for old (pre-CNVI) devices. Most + * new have subdevice==ANY, so are already skipped, but for some + * Bz platform(s) we list all the RF PCI IDs. Skip those too. + */ + if (s->driver_data == (kernel_ulong_t)&iwl_bz_mac_cfg) + continue; +#endif + + di = iwl_pci_find_dev_info(s->device, s->subdevice, + 0, 0, 0, 0, true); + + KUNIT_EXPECT_PTR_NE_MSG(test, di, NULL, + "PCI ID %04x:%04x not found\n", + s->device, s->subdevice); + } +} + static struct kunit_case devinfo_test_cases[] = { KUNIT_CASE(devinfo_table_order), KUNIT_CASE(devinfo_discrete_match), @@ -276,6 +304,7 @@ static struct kunit_case devinfo_test_cases[] = { KUNIT_CASE(devinfo_pci_ids), KUNIT_CASE(devinfo_no_mac_cfg_dups), KUNIT_CASE(devinfo_api_range), + KUNIT_CASE(devinfo_pci_ids_config), {} }; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c index b264ed0af9234..65d0f805459ce 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include "rt2x00.h" @@ -10962,6 +10963,36 @@ int rt2800_read_eeprom_efuse(struct rt2x00_dev *rt2x00dev) } EXPORT_SYMBOL_GPL(rt2800_read_eeprom_efuse); +int rt2800_read_eeprom_nvmem(struct rt2x00_dev *rt2x00dev) +{ + struct device_node *np = rt2x00dev->dev->of_node; + unsigned int len = rt2x00dev->ops->eeprom_size; + struct nvmem_cell *cell; + const void *data; + size_t retlen; + + cell = of_nvmem_cell_get(np, "eeprom"); + if (IS_ERR(cell)) + return PTR_ERR(cell); + + data = nvmem_cell_read(cell, &retlen); + nvmem_cell_put(cell); + + if (IS_ERR(data)) + return PTR_ERR(data); + + if (retlen != len) { + dev_err(rt2x00dev->dev, "invalid eeprom size, required: 0x%04x\n", len); + kfree(data); + return -EINVAL; + } + + memcpy(rt2x00dev->eeprom, data, len); + kfree(data); + return 0; +} +EXPORT_SYMBOL_GPL(rt2800_read_eeprom_nvmem); + static u8 rt2800_get_txmixer_gain_24g(struct rt2x00_dev *rt2x00dev) { u16 word; @@ -11011,7 +11042,9 @@ static int rt2800_validate_eeprom(struct rt2x00_dev *rt2x00dev) * Start validation of the data that has been read. */ mac = rt2800_eeprom_addr(rt2x00dev, EEPROM_MAC_ADDR_0); - rt2x00lib_set_mac_address(rt2x00dev, mac); + retval = rt2x00lib_set_mac_address(rt2x00dev, mac); + if (retval) + return retval; word = rt2800_eeprom_read(rt2x00dev, EEPROM_NIC_CONF0); if (word == 0xffff) { diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h index 620a3d9872cec..a3c3a751f57e3 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2800lib.h @@ -248,6 +248,8 @@ void rt2800_disable_radio(struct rt2x00_dev *rt2x00dev); int rt2800_efuse_detect(struct rt2x00_dev *rt2x00dev); int rt2800_read_eeprom_efuse(struct rt2x00_dev *rt2x00dev); +int rt2800_read_eeprom_nvmem(struct rt2x00_dev *rt2x00dev); + int rt2800_probe_hw(struct rt2x00_dev *rt2x00dev); void rt2800_get_key_seq(struct ieee80211_hw *hw, diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c index 14c45aba836f2..4fa14bb573add 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800pci.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800pci.c @@ -278,6 +278,9 @@ static int rt2800pci_read_eeprom(struct rt2x00_dev *rt2x00dev) { int retval; + if (!rt2800_read_eeprom_nvmem(rt2x00dev)) + return 0; + if (rt2800pci_efuse_detect(rt2x00dev)) retval = rt2800pci_read_eeprom_efuse(rt2x00dev); else diff --git a/drivers/net/wireless/ralink/rt2x00/rt2800soc.c b/drivers/net/wireless/ralink/rt2x00/rt2800soc.c index 8f510a84e7f16..5c29201b34c8b 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2800soc.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2800soc.c @@ -92,8 +92,12 @@ static int rt2800soc_set_device_state(struct rt2x00_dev *rt2x00dev, static int rt2800soc_read_eeprom(struct rt2x00_dev *rt2x00dev) { - void __iomem *base_addr = ioremap(0x1F040000, EEPROM_SIZE); + void __iomem *base_addr; + if (!rt2800_read_eeprom_nvmem(rt2x00dev)) + return 0; + + base_addr = ioremap(0x1F040000, EEPROM_SIZE); if (!base_addr) return -ENOMEM; diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00.h b/drivers/net/wireless/ralink/rt2x00/rt2x00.h index 09b9d1f9f793f..665887e9b118b 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00.h +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00.h @@ -1427,7 +1427,7 @@ static inline void rt2x00debug_dump_frame(struct rt2x00_dev *rt2x00dev, */ u32 rt2x00lib_get_bssidx(struct rt2x00_dev *rt2x00dev, struct ieee80211_vif *vif); -void rt2x00lib_set_mac_address(struct rt2x00_dev *rt2x00dev, u8 *eeprom_mac_addr); +int rt2x00lib_set_mac_address(struct rt2x00_dev *rt2x00dev, u8 *eeprom_mac_addr); /* * Interrupt context handlers. diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c index f8a6f9c968a1e..778a478ab53a9 100644 --- a/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/ralink/rt2x00/rt2x00dev.c @@ -988,14 +988,20 @@ static void rt2x00lib_rate(struct ieee80211_rate *entry, entry->flags |= IEEE80211_RATE_SHORT_PREAMBLE; } -void rt2x00lib_set_mac_address(struct rt2x00_dev *rt2x00dev, u8 *eeprom_mac_addr) +int rt2x00lib_set_mac_address(struct rt2x00_dev *rt2x00dev, u8 *eeprom_mac_addr) { - of_get_mac_address(rt2x00dev->dev->of_node, eeprom_mac_addr); + int ret; + + ret = of_get_mac_address(rt2x00dev->dev->of_node, eeprom_mac_addr); + if (ret == -EPROBE_DEFER) + return ret; if (!is_valid_ether_addr(eeprom_mac_addr)) { eth_random_addr(eeprom_mac_addr); rt2x00_eeprom_dbg(rt2x00dev, "MAC: %pM\n", eeprom_mac_addr); } + + return 0; } EXPORT_SYMBOL_GPL(rt2x00lib_set_mac_address); diff --git a/drivers/net/wireless/st/cw1200/bh.c b/drivers/net/wireless/st/cw1200/bh.c index 3b4ded2ac801c..37232ee220375 100644 --- a/drivers/net/wireless/st/cw1200/bh.c +++ b/drivers/net/wireless/st/cw1200/bh.c @@ -317,10 +317,12 @@ static int cw1200_bh_rx_helper(struct cw1200_common *priv, if (wsm_id & 0x0400) { int rc = wsm_release_tx_buffer(priv, 1); - if (WARN_ON(rc < 0)) + if (WARN_ON(rc < 0)) { + dev_kfree_skb(skb_rx); return rc; - else if (rc > 0) + } else if (rc > 0) { *tx = 1; + } } /* cw1200_wsm_rx takes care on SKB livetime */ diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c index 80fbf740fe6d7..ac756318e8ea5 100644 --- a/drivers/net/wireless/ti/wl18xx/debugfs.c +++ b/drivers/net/wireless/ti/wl18xx/debugfs.c @@ -272,7 +272,6 @@ static ssize_t radar_detection_write(struct file *file, if (ret < 0) count = ret; - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -312,7 +311,6 @@ static ssize_t dynamic_fw_traces_write(struct file *file, if (ret < 0) count = ret; - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -374,7 +372,6 @@ static ssize_t radar_debug_mode_write(struct file *file, wl->radar_debug_mode, 0); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c index fa3a3f71dd156..9d73ba933a16c 100644 --- a/drivers/net/wireless/ti/wlcore/cmd.c +++ b/drivers/net/wireless/ti/wlcore/cmd.c @@ -213,7 +213,6 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl, } while (!event); out: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); free_vector: kfree(events_vector); diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c index eb3d3f0e0b4df..bbfd2725215b4 100644 --- a/drivers/net/wireless/ti/wlcore/debugfs.c +++ b/drivers/net/wireless/ti/wlcore/debugfs.c @@ -63,7 +63,6 @@ void wl1271_debugfs_update_stats(struct wl1271 *wl) wl->stats.fw_stats_update = jiffies; } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -113,7 +112,6 @@ static void chip_op_handler(struct wl1271 *wl, unsigned long value, chip_op = arg; chip_op(wl); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); } @@ -287,7 +285,6 @@ static ssize_t dynamic_ps_timeout_write(struct file *file, wl1271_ps_set_mode(wl, wlvif, STATION_AUTO_PS_MODE); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -357,7 +354,6 @@ static ssize_t forced_ps_write(struct file *file, wl1271_ps_set_mode(wl, wlvif, ps_mode); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -830,7 +826,6 @@ static ssize_t rx_streaming_interval_write(struct file *file, wl1271_recalc_rx_streaming(wl, wlvif); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -886,7 +881,6 @@ static ssize_t rx_streaming_always_write(struct file *file, wl1271_recalc_rx_streaming(wl, wlvif); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -934,7 +928,6 @@ static ssize_t beacon_filtering_write(struct file *file, ret = wl1271_acx_beacon_filter_opt(wl, wlvif, !!value); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -1015,7 +1008,6 @@ static ssize_t sleep_auth_write(struct file *file, goto out_sleep; out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -1090,7 +1082,6 @@ static ssize_t dev_mem_read(struct file *file, goto part_err; part_err: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); skip_read: @@ -1172,7 +1163,6 @@ static ssize_t dev_mem_write(struct file *file, const char __user *user_buf, goto part_err; part_err: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); skip_write: @@ -1247,7 +1237,6 @@ static ssize_t fw_logger_write(struct file *file, ret = wl12xx_cmd_config_fwlog(wl); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c index 6116a8522d960..12f0167d7380e 100644 --- a/drivers/net/wireless/ti/wlcore/main.c +++ b/drivers/net/wireless/ti/wlcore/main.c @@ -154,7 +154,6 @@ static void wl1271_rx_streaming_enable_work(struct work_struct *work) jiffies + msecs_to_jiffies(wl->conf.rx_streaming.duration)); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -181,7 +180,6 @@ static void wl1271_rx_streaming_disable_work(struct work_struct *work) goto out_sleep; out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -234,7 +232,6 @@ static void wlcore_rc_update_work(struct work_struct *work) } out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -711,7 +708,6 @@ static int wlcore_irq_locked(struct wl1271 *wl) } err_ret: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -1047,7 +1043,6 @@ static void wl1271_recovery_work(struct work_struct *work) } wlcore_op_stop_locked(wl); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); ieee80211_restart_hw(wl->hw); @@ -1943,7 +1938,6 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw) goto out_sleep; out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -2131,7 +2125,6 @@ static void wlcore_channel_switch_work(struct work_struct *work) wl12xx_cmd_stop_channel_switch(wl, wlvif); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -2201,7 +2194,6 @@ static void wlcore_pending_auth_complete_work(struct work_struct *work) /* cancel the ROC if active */ wlcore_update_inconn_sta(wl, wlvif, NULL, false); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -2694,7 +2686,6 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw, else wl->sta_count++; out: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out_unlock: mutex_unlock(&wl->mutex); @@ -2774,7 +2765,6 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl, } } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); } deinit: @@ -3200,7 +3190,6 @@ static int wl1271_op_config(struct ieee80211_hw *hw, int radio_idx, u32 changed) } out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -3315,7 +3304,6 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw, */ out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -3531,7 +3519,6 @@ static int wlcore_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, ret = wlcore_hw_set_key(wl, cmd, vif, sta, key_conf); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out_wake_queues: @@ -3695,7 +3682,6 @@ static void wl1271_op_set_default_key_idx(struct ieee80211_hw *hw, } out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out_unlock: @@ -3724,7 +3710,6 @@ void wlcore_regdomain_config(struct wl1271 *wl) goto out; } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -3772,7 +3757,6 @@ static int wl1271_op_hw_scan(struct ieee80211_hw *hw, ret = wlcore_scan(hw->priv, vif, ssid, len, req); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -3823,7 +3807,6 @@ static void wl1271_op_cancel_hw_scan(struct ieee80211_hw *hw, ieee80211_scan_completed(wl->hw, &info); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -3860,7 +3843,6 @@ static int wl1271_op_sched_scan_start(struct ieee80211_hw *hw, wl->sched_vif = wlvif; out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -3887,7 +3869,6 @@ static int wl1271_op_sched_scan_stop(struct ieee80211_hw *hw, wl->ops->sched_scan_stop(wl, wlvif); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -3916,7 +3897,6 @@ static int wl1271_op_set_frag_threshold(struct ieee80211_hw *hw, if (ret < 0) wl1271_warning("wl1271_op_set_frag_threshold failed: %d", ret); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -3948,7 +3928,6 @@ static int wl1271_op_set_rts_threshold(struct ieee80211_hw *hw, int radio_idx, if (ret < 0) wl1271_warning("set rts threshold failed: %d", ret); } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -4714,7 +4693,6 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw, else wl1271_bss_info_changed_sta(wl, vif, bss_conf, changed); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -4779,7 +4757,6 @@ static void wlcore_op_change_chanctx(struct ieee80211_hw *hw, } } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -4828,7 +4805,6 @@ static int wlcore_op_assign_vif_chanctx(struct ieee80211_hw *hw, wlvif->radar_enabled = true; } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -4871,7 +4847,6 @@ static void wlcore_op_unassign_vif_chanctx(struct ieee80211_hw *hw, wlvif->radar_enabled = false; } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -4941,7 +4916,6 @@ wlcore_op_switch_vif_chanctx(struct ieee80211_hw *hw, goto out_sleep; } out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -4995,7 +4969,6 @@ static int wl1271_op_conf_tx(struct ieee80211_hw *hw, 0, 0); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -5029,7 +5002,6 @@ static u64 wl1271_op_get_tsf(struct ieee80211_hw *hw, goto out_sleep; out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -5342,7 +5314,6 @@ static int wl12xx_op_sta_state(struct ieee80211_hw *hw, ret = wl12xx_update_sta_state(wl, wlvif, sta, old_state, new_state); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -5467,7 +5438,6 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw, ret = -EINVAL; } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -5511,7 +5481,6 @@ static int wl12xx_set_bitrate_mask(struct ieee80211_hw *hw, wl1271_tx_min_rate_get(wl, wlvif->basic_rate_set); ret = wl1271_acx_sta_rate_policies(wl, wlvif); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); } out: @@ -5566,7 +5535,6 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw, } out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: @@ -5645,7 +5613,6 @@ static void wlcore_op_channel_switch_beacon(struct ieee80211_hw *hw, set_bit(WLVIF_FLAG_CS_PROGRESS, &wlvif->flags); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -5699,7 +5666,6 @@ static int wlcore_op_remain_on_channel(struct ieee80211_hw *hw, ieee80211_queue_delayed_work(hw, &wl->roc_complete_work, msecs_to_jiffies(duration)); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -5748,7 +5714,6 @@ static int wlcore_roc_completed(struct wl1271 *wl) ret = __wlcore_roc_completed(wl); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -5839,7 +5804,6 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw, sinfo->signal = rssi_dbm; out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: diff --git a/drivers/net/wireless/ti/wlcore/scan.c b/drivers/net/wireless/ti/wlcore/scan.c index b414305acc322..f6dc54c1dbade 100644 --- a/drivers/net/wireless/ti/wlcore/scan.c +++ b/drivers/net/wireless/ti/wlcore/scan.c @@ -69,7 +69,6 @@ void wl1271_scan_complete_work(struct work_struct *work) wlcore_cmd_regdomain_config_locked(wl); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); ieee80211_scan_completed(wl->hw, &info); diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c index 65ca5dc569a04..5ab6c16836756 100644 --- a/drivers/net/wireless/ti/wlcore/sysfs.c +++ b/drivers/net/wireless/ti/wlcore/sysfs.c @@ -58,7 +58,6 @@ static ssize_t bt_coex_state_store(struct device *dev, goto out; wl1271_acx_sg_enable(wl, wl->sg_enabled); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c index fc8ea58bc1659..7c0cb1b7fef0b 100644 --- a/drivers/net/wireless/ti/wlcore/testmode.c +++ b/drivers/net/wireless/ti/wlcore/testmode.c @@ -127,7 +127,6 @@ static int wl1271_tm_cmd_test(struct wl1271 *wl, struct nlattr *tb[]) } out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -192,7 +191,6 @@ static int wl1271_tm_cmd_interrogate(struct wl1271 *wl, struct nlattr *tb[]) out_free: kfree(cmd); out_sleep: - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c index 464587d16ab20..f76087be2f758 100644 --- a/drivers/net/wireless/ti/wlcore/tx.c +++ b/drivers/net/wireless/ti/wlcore/tx.c @@ -863,7 +863,6 @@ void wl1271_tx_work(struct work_struct *work) goto out; } - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c index e4269e2b00981..5bb9eb300f979 100644 --- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c +++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c @@ -60,7 +60,6 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy, ret = wlcore_smart_config_start(wl, nla_get_u32(tb[WLCORE_VENDOR_ATTR_GROUP_ID])); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -92,7 +91,6 @@ wlcore_vendor_cmd_smart_config_stop(struct wiphy *wiphy, ret = wlcore_smart_config_stop(wl); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); @@ -140,7 +138,6 @@ wlcore_vendor_cmd_smart_config_set_group_key(struct wiphy *wiphy, nla_len(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]), nla_data(tb[WLCORE_VENDOR_ATTR_GROUP_KEY])); - pm_runtime_mark_last_busy(wl->dev); pm_runtime_put_autosuspend(wl->dev); out: mutex_unlock(&wl->mutex); diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c index 5903d82e1ab1e..551f5eb4e7477 100644 --- a/drivers/net/wireless/virtual/mac80211_hwsim.c +++ b/drivers/net/wireless/virtual/mac80211_hwsim.c @@ -5799,6 +5799,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, ieee80211_hw_set(hw, NO_AUTO_VIF); wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); + wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_PUNCT); for (i = 0; i < ARRAY_SIZE(data->link_data); i++) { hrtimer_setup(&data->link_data[i].beacon_timer, mac80211_hwsim_beacon, diff --git a/drivers/net/wwan/qcom_bam_dmux.c b/drivers/net/wwan/qcom_bam_dmux.c index 64dab8b57611c..6a5b22589af48 100644 --- a/drivers/net/wwan/qcom_bam_dmux.c +++ b/drivers/net/wwan/qcom_bam_dmux.c @@ -162,7 +162,6 @@ static void bam_dmux_tx_done(struct bam_dmux_skb_dma *skb_dma) struct bam_dmux *dmux = skb_dma->dmux; unsigned long flags; - pm_runtime_mark_last_busy(dmux->dev); pm_runtime_put_autosuspend(dmux->dev); if (skb_dma->addr) @@ -397,7 +396,6 @@ static void bam_dmux_tx_wakeup_work(struct work_struct *work) dma_async_issue_pending(dmux->tx); out: - pm_runtime_mark_last_busy(dmux->dev); pm_runtime_put_autosuspend(dmux->dev); } diff --git a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c index 97163e1e5783e..689c920ca8981 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_cldma.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_cldma.c @@ -250,7 +250,6 @@ static void t7xx_cldma_rx_done(struct work_struct *work) t7xx_cldma_clear_ip_busy(&md_ctrl->hw_info); t7xx_cldma_hw_irq_en_txrx(&md_ctrl->hw_info, queue->index, MTK_RX); t7xx_cldma_hw_irq_en_eq(&md_ctrl->hw_info, queue->index, MTK_RX); - pm_runtime_mark_last_busy(md_ctrl->dev); pm_runtime_put_autosuspend(md_ctrl->dev); } @@ -362,7 +361,6 @@ static void t7xx_cldma_tx_done(struct work_struct *work) } spin_unlock_irqrestore(&md_ctrl->cldma_lock, flags); - pm_runtime_mark_last_busy(md_ctrl->dev); pm_runtime_put_autosuspend(md_ctrl->dev); } @@ -987,7 +985,6 @@ int t7xx_cldma_send_skb(struct cldma_ctrl *md_ctrl, int qno, struct sk_buff *skb allow_sleep: t7xx_pci_enable_sleep(md_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(md_ctrl->dev); pm_runtime_put_autosuspend(md_ctrl->dev); return ret; } diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c index 2310493203d3c..b76bea6ab2d76 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c @@ -877,7 +877,6 @@ int t7xx_dpmaif_napi_rx_poll(struct napi_struct *napi, const int budget) t7xx_dpmaif_clr_ip_busy_sts(&rxq->dpmaif_ctrl->hw_info); t7xx_dpmaif_dlq_unmask_rx_done(&rxq->dpmaif_ctrl->hw_info, rxq->index); t7xx_pci_enable_sleep(rxq->dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(rxq->dpmaif_ctrl->dev); pm_runtime_put_autosuspend(rxq->dpmaif_ctrl->dev); atomic_set(&rxq->rx_processing, 0); } else { @@ -1078,7 +1077,6 @@ static void t7xx_dpmaif_bat_release_work(struct work_struct *work) } t7xx_pci_enable_sleep(dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(dpmaif_ctrl->dev); pm_runtime_put_autosuspend(dpmaif_ctrl->dev); } diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_tx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_tx.c index 8dab025a088a2..236d632cf591b 100644 --- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_tx.c +++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_tx.c @@ -185,7 +185,6 @@ static void t7xx_dpmaif_tx_done(struct work_struct *work) } t7xx_pci_enable_sleep(dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(dpmaif_ctrl->dev); pm_runtime_put_autosuspend(dpmaif_ctrl->dev); } @@ -468,7 +467,6 @@ static int t7xx_dpmaif_tx_hw_push_thread(void *arg) t7xx_pci_disable_sleep(dpmaif_ctrl->t7xx_dev); t7xx_do_tx_hw_push(dpmaif_ctrl); t7xx_pci_enable_sleep(dpmaif_ctrl->t7xx_dev); - pm_runtime_mark_last_busy(dpmaif_ctrl->dev); pm_runtime_put_autosuspend(dpmaif_ctrl->dev); } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index a11a0e9494005..7c2220366623e 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2696,8 +2696,9 @@ static int __init netif_init(void) pr_info("Initialising Xen virtual ethernet driver\n"); - /* Allow as many queues as there are CPUs inut max. 8 if user has not - * specified a value. + /* Allow the number of queues to match the number of CPUs, but not exceed + * the maximum limit. If the user has not specified a value, the default + * maximum limit is 8. */ if (xennet_max_queues == 0) xennet_max_queues = min_t(unsigned int, MAX_QUEUES_DEFAULT, diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 9a96df1a511c0..6795b8286c354 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -1834,7 +1834,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, sk_set_memalloc(queue->sock->sk); if (nctrl->opts->mask & NVMF_OPT_HOST_TRADDR) { - ret = kernel_bind(queue->sock, (struct sockaddr *)&ctrl->src_addr, + ret = kernel_bind(queue->sock, (struct sockaddr_unsized *)&ctrl->src_addr, sizeof(ctrl->src_addr)); if (ret) { dev_err(nctrl->device, @@ -1872,7 +1872,7 @@ static int nvme_tcp_alloc_queue(struct nvme_ctrl *nctrl, int qid, dev_dbg(nctrl->device, "connecting queue %d\n", nvme_tcp_queue_id(queue)); - ret = kernel_connect(queue->sock, (struct sockaddr *)&ctrl->addr, + ret = kernel_connect(queue->sock, (struct sockaddr_unsized *)&ctrl->addr, sizeof(ctrl->addr), 0); if (ret) { dev_err(nctrl->device, diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c index 470bf37e5a637..d543da09ef8e2 100644 --- a/drivers/nvme/target/tcp.c +++ b/drivers/nvme/target/tcp.c @@ -2055,7 +2055,7 @@ static int nvmet_tcp_add_port(struct nvmet_port *nport) if (so_priority > 0) sock_set_priority(port->sock->sk, so_priority); - ret = kernel_bind(port->sock, (struct sockaddr *)&port->addr, + ret = kernel_bind(port->sock, (struct sockaddr_unsized *)&port->addr, sizeof(port->addr)); if (ret) { pr_err("failed to bind port socket %d\n", ret); diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c index cc64f93709a4f..ca4f97be75389 100644 --- a/drivers/pci/tph.c +++ b/drivers/pci/tph.c @@ -155,7 +155,16 @@ static u8 get_st_modes(struct pci_dev *pdev) return reg; } -static u32 get_st_table_loc(struct pci_dev *pdev) +/** + * pcie_tph_get_st_table_loc - Return the device's ST table location + * @pdev: PCI device to query + * + * Return: + * PCI_TPH_LOC_NONE - Not present + * PCI_TPH_LOC_CAP - Located in the TPH Requester Extended Capability + * PCI_TPH_LOC_MSIX - Located in the MSI-X Table + */ +u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev) { u32 reg; @@ -163,6 +172,7 @@ static u32 get_st_table_loc(struct pci_dev *pdev) return FIELD_GET(PCI_TPH_CAP_LOC_MASK, reg); } +EXPORT_SYMBOL(pcie_tph_get_st_table_loc); /* * Return the size of ST table. If ST table is not in TPH Requester Extended @@ -174,7 +184,7 @@ u16 pcie_tph_get_st_table_size(struct pci_dev *pdev) u32 loc; /* Check ST table location first */ - loc = get_st_table_loc(pdev); + loc = pcie_tph_get_st_table_loc(pdev); /* Convert loc to match with PCI_TPH_LOC_* defined in pci_regs.h */ loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc); @@ -299,7 +309,7 @@ int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag) */ set_ctrl_reg_req_en(pdev, PCI_TPH_REQ_DISABLE); - loc = get_st_table_loc(pdev); + loc = pcie_tph_get_st_table_loc(pdev); /* Convert loc to match with PCI_TPH_LOC_* */ loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc); diff --git a/drivers/ptp/ptp_clock.c b/drivers/ptp/ptp_clock.c index ef020599b7711..b0e167c0b3ebd 100644 --- a/drivers/ptp/ptp_clock.c +++ b/drivers/ptp/ptp_clock.c @@ -322,7 +322,9 @@ struct ptp_clock *ptp_clock_register(struct ptp_clock_info *info, char debugfsname[16]; size_t size; - if (info->n_alarm > PTP_MAX_ALARMS) + if (WARN_ON_ONCE(info->n_alarm > PTP_MAX_ALARMS || + (!info->gettimex64 && !info->gettime64) || + !info->settime64)) return ERR_PTR(-EINVAL); /* Initialize a clock structure. */ diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c index a5c3632529862..eeebe4d149f71 100644 --- a/drivers/ptp/ptp_ocp.c +++ b/drivers/ptp/ptp_ocp.c @@ -3430,6 +3430,12 @@ ptp_ocp_tty_show(struct device *dev, struct device_attribute *attr, char *buf) struct dev_ext_attribute *ea = to_ext_attr(attr); struct ptp_ocp *bp = dev_get_drvdata(dev); + /* + * NOTE: This output does not include a trailing newline for backward + * compatibility. Existing userspace software uses this value directly + * as a device path (e.g., "/dev/ttyS4"), and adding a newline would + * break those applications. Do not add a newline to this output. + */ return sysfs_emit(buf, "ttyS%d", bp->port[(uintptr_t)ea->var].line); } diff --git a/drivers/s390/net/ctcm_fsms.c b/drivers/s390/net/ctcm_fsms.c index 9678c6a2cda72..1a48258b63b28 100644 --- a/drivers/s390/net/ctcm_fsms.c +++ b/drivers/s390/net/ctcm_fsms.c @@ -882,6 +882,13 @@ static void ctcm_chx_rxiniterr(fsm_instance *fi, int event, void *arg) fsm_newstate(fi, CTC_STATE_RXERR); fsm_event(priv->fsm, DEV_EVENT_RXDOWN, dev); } + } else if (event == CTC_EVENT_UC_RCRESET) { + CTCM_DBF_TEXT_(TRACE, CTC_DBF_NOTICE, + "%s(%s): %s in %s", CTCM_FUNTAIL, ch->id, + ctc_ch_event_names[event], fsm_getstate_str(fi)); + + dev_info(&dev->dev, + "Init handshake not received, peer not ready yet\n"); } else { CTCM_DBF_TEXT_(ERROR, CTC_DBF_ERROR, "%s(%s): %s in %s", CTCM_FUNTAIL, ch->id, @@ -967,6 +974,13 @@ static void ctcm_chx_txiniterr(fsm_instance *fi, int event, void *arg) fsm_newstate(fi, CTC_STATE_TXERR); fsm_event(priv->fsm, DEV_EVENT_TXDOWN, dev); } + } else if (event == CTC_EVENT_UC_RCRESET) { + CTCM_DBF_TEXT_(TRACE, CTC_DBF_NOTICE, + "%s(%s): %s in %s", CTCM_FUNTAIL, ch->id, + ctc_ch_event_names[event], fsm_getstate_str(fi)); + + dev_info(&dev->dev, + "Init handshake not sent, peer not ready yet\n"); } else { CTCM_DBF_TEXT_(ERROR, CTC_DBF_ERROR, "%s(%s): %s in %s", CTCM_FUNTAIL, ch->id, diff --git a/drivers/s390/net/ctcm_mpc.c b/drivers/s390/net/ctcm_mpc.c index 0aeafa772fb1e..407b7c5166585 100644 --- a/drivers/s390/net/ctcm_mpc.c +++ b/drivers/s390/net/ctcm_mpc.c @@ -701,7 +701,6 @@ static void mpc_rcvd_sweep_req(struct mpcg_info *mpcginfo) grp->sweep_req_pend_num--; ctcmpc_send_sweep_resp(ch); - kfree(mpcginfo); return; } diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index edc0bcd46923c..10b53bba373c9 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -761,7 +761,7 @@ static void qeth_issue_ipa_msg(struct qeth_ipa_cmd *cmd, int rc, if (rc) QETH_DBF_MESSAGE(2, "IPA: %s(%#x) for device %x returned %#x \"%s\"\n", ipa_name, com, CARD_DEVID(card), rc, - qeth_get_ipa_msg(rc)); + qeth_get_ipa_msg(com, rc)); else QETH_DBF_MESSAGE(5, "IPA: %s(%#x) for device %x succeeded\n", ipa_name, com, CARD_DEVID(card)); diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c index d9266f7d81879..1add124e033b6 100644 --- a/drivers/s390/net/qeth_core_mpc.c +++ b/drivers/s390/net/qeth_core_mpc.c @@ -139,82 +139,237 @@ struct ipa_rc_msg { const char *msg; }; -static const struct ipa_rc_msg qeth_ipa_rc_msg[] = { +static const struct ipa_rc_msg qeth_ipa_rc_def_msg[] = { {IPA_RC_SUCCESS, "success"}, {IPA_RC_NOTSUPP, "Command not supported"}, - {IPA_RC_IP_TABLE_FULL, "Add Addr IP Table Full - ipv6"}, - {IPA_RC_UNKNOWN_ERROR, "IPA command failed - reason unknown"}, {IPA_RC_UNSUPPORTED_COMMAND, "Command not supported"}, - {IPA_RC_VNICC_OOSEQ, "Command issued out of sequence"}, - {IPA_RC_INVALID_FORMAT, "invalid format or length"}, {IPA_RC_DUP_IPV6_REMOTE, "ipv6 address already registered remote"}, - {IPA_RC_SBP_IQD_NOT_CONFIGURED, "Not configured for bridgeport"}, {IPA_RC_DUP_IPV6_HOME, "ipv6 address already registered"}, {IPA_RC_UNREGISTERED_ADDR, "Address not registered"}, - {IPA_RC_NO_ID_AVAILABLE, "No identifiers available"}, {IPA_RC_ID_NOT_FOUND, "Identifier not found"}, - {IPA_RC_SBP_IQD_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, - {IPA_RC_SBP_IQD_CURRENT_SECOND, "Bridgeport is currently secondary"}, - {IPA_RC_SBP_IQD_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, - {IPA_RC_INVALID_IP_VERSION, "IP version incorrect"}, - {IPA_RC_SBP_IQD_CURRENT_PRIMARY, "Bridgeport is currently primary"}, {IPA_RC_LAN_FRAME_MISMATCH, "LAN and frame mismatch"}, - {IPA_RC_SBP_IQD_NO_QDIO_QUEUES, "QDIO queues not established"}, {IPA_RC_L2_UNSUPPORTED_CMD, "Unsupported layer 2 command"}, - {IPA_RC_L2_DUP_MAC, "Duplicate MAC address"}, {IPA_RC_L2_ADDR_TABLE_FULL, "Layer2 address table full"}, - {IPA_RC_L2_DUP_LAYER3_MAC, "Duplicate with layer 3 MAC"}, - {IPA_RC_L2_GMAC_NOT_FOUND, "GMAC not found"}, - {IPA_RC_L2_MAC_NOT_AUTH_BY_HYP, "L2 mac not authorized by hypervisor"}, {IPA_RC_L2_MAC_NOT_AUTH_BY_ADP, "L2 mac not authorized by adapter"}, - {IPA_RC_L2_MAC_NOT_FOUND, "L2 mac address not found"}, - {IPA_RC_L2_INVALID_VLAN_ID, "L2 invalid vlan id"}, - {IPA_RC_L2_DUP_VLAN_ID, "L2 duplicate vlan id"}, - {IPA_RC_L2_VLAN_ID_NOT_FOUND, "L2 vlan id not found"}, - {IPA_RC_VNICC_VNICBP, "VNIC is BridgePort"}, - {IPA_RC_SBP_OSA_NOT_CONFIGURED, "Not configured for bridgeport"}, - {IPA_RC_SBP_OSA_OS_MISMATCH, "OS mismatch"}, - {IPA_RC_SBP_OSA_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, - {IPA_RC_SBP_OSA_CURRENT_SECOND, "Bridgeport is currently secondary"}, - {IPA_RC_SBP_OSA_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, - {IPA_RC_SBP_OSA_NOT_AUTHD_BY_ZMAN, "Not authorized by zManager"}, - {IPA_RC_SBP_OSA_CURRENT_PRIMARY, "Bridgeport is currently primary"}, - {IPA_RC_SBP_OSA_NO_QDIO_QUEUES, "QDIO queues not established"}, {IPA_RC_DATA_MISMATCH, "Data field mismatch (v4/v6 mixed)"}, {IPA_RC_INVALID_MTU_SIZE, "Invalid MTU size"}, {IPA_RC_INVALID_LANTYPE, "Invalid LAN type"}, {IPA_RC_INVALID_LANNUM, "Invalid LAN num"}, - {IPA_RC_DUPLICATE_IP_ADDRESS, "Address already registered"}, - {IPA_RC_IP_ADDR_TABLE_FULL, "IP address table full"}, {IPA_RC_LAN_PORT_STATE_ERROR, "LAN port state error"}, {IPA_RC_SETIP_NO_STARTLAN, "Setip no startlan received"}, {IPA_RC_SETIP_ALREADY_RECEIVED, "Setip already received"}, - {IPA_RC_IP_ADDR_ALREADY_USED, "IP address already in use on LAN"}, - {IPA_RC_MC_ADDR_NOT_FOUND, "Multicast address not found"}, {IPA_RC_SETIP_INVALID_VERSION, "SETIP invalid IP version"}, {IPA_RC_UNSUPPORTED_SUBCMD, "Unsupported assist subcommand"}, {IPA_RC_ARP_ASSIST_NO_ENABLE, "Only partial success, no enable"}, - {IPA_RC_PRIMARY_ALREADY_DEFINED, "Primary already defined"}, - {IPA_RC_SECOND_ALREADY_DEFINED, "Secondary already defined"}, - {IPA_RC_INVALID_SETRTG_INDICATOR, "Invalid SETRTG indicator"}, - {IPA_RC_MC_ADDR_ALREADY_DEFINED, "Multicast address already defined"}, - {IPA_RC_LAN_OFFLINE, "STRTLAN_LAN_DISABLED - LAN offline"}, - {IPA_RC_VEPA_TO_VEB_TRANSITION, "Adj. switch disabled port mode RR"}, {IPA_RC_INVALID_IP_VERSION2, "Invalid IP version"}, /* default for qeth_get_ipa_msg(): */ {IPA_RC_FFFF, "Unknown Error"} }; -const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc) +static const struct ipa_rc_msg qeth_ipa_rc_adp_parms_msg[] = { + {IPA_RC_IP_TABLE_FULL, "Add Addr IP Table Full - ipv6"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_diag_ass_msg[] = { + {IPA_RC_INVALID_FORMAT, "invalid format or length"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_addr_msg[] = { + {IPA_RC_UNKNOWN_ERROR, "IPA command failed - reason unknown"}, + {IPA_RC_NO_ID_AVAILABLE, "No identifiers available"}, + {IPA_RC_INVALID_IP_VERSION, "IP version incorrect"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_vnicc_msg[] = { + {IPA_RC_VNICC_OOSEQ, "Command issued out of sequence"}, + {IPA_RC_VNICC_VNICBP, "VNIC is BridgePort"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_sbp_iqd_msg[] = { + {IPA_RC_SBP_IQD_NOT_CONFIGURED, "Not configured for bridgeport"}, + {IPA_RC_SBP_IQD_OS_MISMATCH, "OS mismatch"}, + {IPA_RC_SBP_IQD_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, + {IPA_RC_SBP_IQD_CURRENT_SECOND, "Bridgeport is currently secondary"}, + {IPA_RC_SBP_IQD_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, + {IPA_RC_SBP_IQD_NOT_AUTHD_BY_ZMAN, "Not authorized by zManager"}, + {IPA_RC_SBP_IQD_CURRENT_PRIMARY, "Bridgeport is currently primary"}, + {IPA_RC_SBP_IQD_NO_QDIO_QUEUES, "QDIO queues not established"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_sbp_osa_msg[] = { + {IPA_RC_SBP_OSA_NOT_CONFIGURED, "Not configured for bridgeport"}, + {IPA_RC_SBP_OSA_OS_MISMATCH, "OS mismatch"}, + {IPA_RC_SBP_OSA_ANO_DEV_PRIMARY, "Primary bridgeport exists already"}, + {IPA_RC_SBP_OSA_CURRENT_SECOND, "Bridgeport is currently secondary"}, + {IPA_RC_SBP_OSA_LIMIT_SECOND, "Limit of secondary bridgeports reached"}, + {IPA_RC_SBP_OSA_NOT_AUTHD_BY_ZMAN, "Not authorized by zManager"}, + {IPA_RC_SBP_OSA_CURRENT_PRIMARY, "Bridgeport is currently primary"}, + {IPA_RC_SBP_OSA_NO_QDIO_QUEUES, "QDIO queues not established"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_mac_msg[] = { + {IPA_RC_L2_DUP_MAC, "Duplicate MAC address"}, + {IPA_RC_L2_DUP_LAYER3_MAC, "Duplicate with layer 3 MAC"}, + {IPA_RC_L2_GMAC_NOT_FOUND, "GMAC not found"}, + {IPA_RC_L2_MAC_NOT_AUTH_BY_HYP, "L2 mac not authorized by hypervisor"}, + {IPA_RC_L2_MAC_NOT_FOUND, "L2 mac address not found"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_ip_msg[] = { + {IPA_RC_DUPLICATE_IP_ADDRESS, "Address already registered"}, + {IPA_RC_IP_ADDR_TABLE_FULL, "IP address table full"}, + {IPA_RC_IP_ADDR_ALREADY_USED, "IP address already in use on LAN"}, + {IPA_RC_MC_ADDR_NOT_FOUND, "Multicast address not found"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_lan_msg[] = { + {IPA_RC_LAN_OFFLINE, "STRTLAN_LAN_DISABLED - LAN offline"}, + {IPA_RC_VEPA_TO_VEB_TRANSITION, "Adj. switch disabled port mode RR"}, +}; + +static const struct ipa_rc_msg qeth_ipa_rc_vlan_msg[] = { + {IPA_RC_L2_INVALID_VLAN_ID, "L2 invalid vlan id"}, + {IPA_RC_L2_DUP_VLAN_ID, "L2 duplicate vlan id"}, + {IPA_RC_L2_VLAN_ID_NOT_FOUND, "L2 vlan id not found"} +}; + +static const struct ipa_rc_msg qeth_ipa_rc_rtg_msg[] = { + {IPA_RC_PRIMARY_ALREADY_DEFINED, "Primary already defined"}, + {IPA_RC_SECOND_ALREADY_DEFINED, "Secondary already defined"}, + {IPA_RC_INVALID_SETRTG_INDICATOR, "Invalid SETRTG indicator"}, + {IPA_RC_MC_ADDR_ALREADY_DEFINED, "Multicast address already defined"} +}; + +struct ipa_cmd_rc_map { + enum qeth_ipa_cmds cmd; + const struct ipa_rc_msg *msg_arr; + const size_t arr_len; +}; + +static const struct ipa_cmd_rc_map qeth_ipa_cmd_rc_map[] = { + { + .cmd = IPA_CMD_SETADAPTERPARMS, + .msg_arr = qeth_ipa_rc_adp_parms_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_adp_parms_msg) + }, + { + .cmd = IPA_CMD_SET_DIAG_ASS, + .msg_arr = qeth_ipa_rc_diag_ass_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_diag_ass_msg) + }, + { + .cmd = IPA_CMD_CREATE_ADDR, + .msg_arr = qeth_ipa_rc_addr_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_addr_msg) + }, + { + .cmd = IPA_CMD_DESTROY_ADDR, + .msg_arr = qeth_ipa_rc_addr_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_addr_msg) + }, + { + .cmd = IPA_CMD_VNICC, + .msg_arr = qeth_ipa_rc_vnicc_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_vnicc_msg) + }, + { + .cmd = IPA_CMD_SETBRIDGEPORT_IQD, + .msg_arr = qeth_ipa_rc_sbp_iqd_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_sbp_iqd_msg) + }, + { + .cmd = IPA_CMD_SETBRIDGEPORT_OSA, + .msg_arr = qeth_ipa_rc_sbp_osa_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_sbp_osa_msg) + }, + { + .cmd = IPA_CMD_SETVMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_DELVMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_SETGMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_DELGMAC, + .msg_arr = qeth_ipa_rc_mac_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_mac_msg) + }, + { + .cmd = IPA_CMD_SETIP, + .msg_arr = qeth_ipa_rc_ip_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_ip_msg) + }, + { + .cmd = IPA_CMD_SETIPM, + .msg_arr = qeth_ipa_rc_ip_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_ip_msg) + }, + { + .cmd = IPA_CMD_DELIPM, + .msg_arr = qeth_ipa_rc_ip_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_ip_msg) + }, + { + .cmd = IPA_CMD_STARTLAN, + .msg_arr = qeth_ipa_rc_lan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_lan_msg) + }, + { + .cmd = IPA_CMD_STOPLAN, + .msg_arr = qeth_ipa_rc_lan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_lan_msg) + }, + { + .cmd = IPA_CMD_SETVLAN, + .msg_arr = qeth_ipa_rc_vlan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_vlan_msg) + }, + { + .cmd = IPA_CMD_DELVLAN, + .msg_arr = qeth_ipa_rc_vlan_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_vlan_msg) + }, + { + .cmd = IPA_CMD_SETRTG, + .msg_arr = qeth_ipa_rc_rtg_msg, + .arr_len = ARRAY_SIZE(qeth_ipa_rc_rtg_msg) + } +}; + +const char *qeth_get_ipa_msg(enum qeth_ipa_cmds cmd, + enum qeth_ipa_return_codes rc) { int x; + const struct ipa_rc_msg *msg_arr = NULL; + size_t arr_len = 0; - for (x = 0; x < ARRAY_SIZE(qeth_ipa_rc_msg) - 1; x++) - if (qeth_ipa_rc_msg[x].rc == rc) - return qeth_ipa_rc_msg[x].msg; - return qeth_ipa_rc_msg[x].msg; -} + for (x = 0; x < ARRAY_SIZE(qeth_ipa_cmd_rc_map); x++) { + if (qeth_ipa_cmd_rc_map[x].cmd == cmd) { + msg_arr = qeth_ipa_cmd_rc_map[x].msg_arr; + arr_len = qeth_ipa_cmd_rc_map[x].arr_len; + break; + } + } + for (x = 0; x < arr_len; x++) { + if (msg_arr[x].rc == rc) + return msg_arr[x].msg; + } + + for (x = 0; x < ARRAY_SIZE(qeth_ipa_rc_def_msg) - 1; x++) { + if (qeth_ipa_rc_def_msg[x].rc == rc) + return qeth_ipa_rc_def_msg[x].msg; + } + return qeth_ipa_rc_def_msg[x].msg; +} struct ipa_cmd_names { enum qeth_ipa_cmds cmd; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index 6257f00786b36..252fc84e6eca1 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -159,13 +159,17 @@ enum qeth_ipa_return_codes { IPA_RC_SUCCESS = 0x0000, IPA_RC_NOTSUPP = 0x0001, IPA_RC_IP_TABLE_FULL = 0x0002, + IPA_RC_INVALID_SUBCMD = 0x0002, IPA_RC_UNKNOWN_ERROR = 0x0003, + IPA_RC_HARDWARE_AUTH_ERROR = 0x0003, IPA_RC_UNSUPPORTED_COMMAND = 0x0004, IPA_RC_TRACE_ALREADY_ACTIVE = 0x0005, + IPA_RC_VNICC_OOSEQ = 0x0005, IPA_RC_INVALID_FORMAT = 0x0006, IPA_RC_DUP_IPV6_REMOTE = 0x0008, IPA_RC_SBP_IQD_NOT_CONFIGURED = 0x000C, IPA_RC_DUP_IPV6_HOME = 0x0010, + IPA_RC_SBP_IQD_OS_MISMATCH = 0x0010, IPA_RC_UNREGISTERED_ADDR = 0x0011, IPA_RC_NO_ID_AVAILABLE = 0x0012, IPA_RC_ID_NOT_FOUND = 0x0013, @@ -173,6 +177,7 @@ enum qeth_ipa_return_codes { IPA_RC_SBP_IQD_CURRENT_SECOND = 0x0018, IPA_RC_SBP_IQD_LIMIT_SECOND = 0x001C, IPA_RC_INVALID_IP_VERSION = 0x0020, + IPA_RC_SBP_IQD_NOT_AUTHD_BY_ZMAN = 0x0020, IPA_RC_SBP_IQD_CURRENT_PRIMARY = 0x0024, IPA_RC_LAN_FRAME_MISMATCH = 0x0040, IPA_RC_SBP_IQD_NO_QDIO_QUEUES = 0x00EB, @@ -220,16 +225,6 @@ enum qeth_ipa_return_codes { IPA_RC_INVALID_IP_VERSION2 = 0xf001, IPA_RC_FFFF = 0xffff }; -/* for VNIC Characteristics */ -#define IPA_RC_VNICC_OOSEQ 0x0005 - -/* for SET_DIAGNOSTIC_ASSIST */ -#define IPA_RC_INVALID_SUBCMD IPA_RC_IP_TABLE_FULL -#define IPA_RC_HARDWARE_AUTH_ERROR IPA_RC_UNKNOWN_ERROR - -/* for SETBRIDGEPORT (double occupancies) */ -#define IPA_RC_SBP_IQD_OS_MISMATCH IPA_RC_DUP_IPV6_HOME -#define IPA_RC_SBP_IQD_NOT_AUTHD_BY_ZMAN IPA_RC_INVALID_IP_VERSION /* IPA function flags; each flag marks availability of respective function */ enum qeth_ipa_funcs { @@ -862,8 +857,9 @@ enum qeth_ipa_arp_return_codes { QETH_IPA_ARP_RC_Q_NO_DATA = 0x0008, }; -extern const char *qeth_get_ipa_msg(enum qeth_ipa_return_codes rc); -extern const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); +const char *qeth_get_ipa_msg(enum qeth_ipa_cmds cmd, + enum qeth_ipa_return_codes rc); +const char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd); /* Helper functions */ #define IS_IPA_REPLY(cmd) ((cmd)->hdr.initiator == IPA_CMD_INITIATOR_HOST) diff --git a/drivers/s390/net/smsgiucv_app.c b/drivers/s390/net/smsgiucv_app.c index 4bd4d6bfc1262..768108c90b325 100644 --- a/drivers/s390/net/smsgiucv_app.c +++ b/drivers/s390/net/smsgiucv_app.c @@ -88,9 +88,10 @@ static struct smsg_app_event *smsg_app_event_alloc(const char *from, ev->envp[3] = NULL; /* setting up environment: sender, prefix name, and message text */ - snprintf(ev->envp[0], ENV_SENDER_LEN, ENV_SENDER_STR "%s", from); - snprintf(ev->envp[1], ENV_PREFIX_LEN, ENV_PREFIX_STR "%s", SMSG_PREFIX); - snprintf(ev->envp[2], ENV_TEXT_LEN(msg), ENV_TEXT_STR "%s", msg); + scnprintf(ev->envp[0], ENV_SENDER_LEN, ENV_SENDER_STR "%s", from); + scnprintf(ev->envp[1], ENV_PREFIX_LEN, ENV_PREFIX_STR "%s", + SMSG_PREFIX); + scnprintf(ev->envp[2], ENV_TEXT_LEN(msg), ENV_TEXT_STR "%s", msg); return ev; } diff --git a/drivers/slimbus/qcom-ngd-ctrl.c b/drivers/slimbus/qcom-ngd-ctrl.c index 4fb66986cc22e..fdb94dc4a7307 100644 --- a/drivers/slimbus/qcom-ngd-ctrl.c +++ b/drivers/slimbus/qcom-ngd-ctrl.c @@ -463,7 +463,7 @@ static int qcom_slim_qmi_init(struct qcom_slim_ngd_ctrl *ctrl, } rc = kernel_connect(handle->sock, - (struct sockaddr *)&ctrl->qmi.svc_info, + (struct sockaddr_unsized *)&ctrl->qmi.svc_info, sizeof(ctrl->qmi.svc_info), 0); if (rc < 0) { dev_err(ctrl->dev, "Remote Service connect failed: %d\n", rc); diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c index c2ac9a99ebbb2..53aca059dc16d 100644 --- a/drivers/target/iscsi/iscsi_target_login.c +++ b/drivers/target/iscsi/iscsi_target_login.c @@ -822,7 +822,7 @@ int iscsit_setup_np( sock_set_reuseaddr(sock->sk); ip_sock_set_freebind(sock->sk); - ret = kernel_bind(sock, (struct sockaddr *)&np->np_sockaddr, len); + ret = kernel_bind(sock, (struct sockaddr_unsized *)&np->np_sockaddr, len); if (ret < 0) { pr_err("kernel_bind() failed: %d\n", ret); goto fail; diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile index eefcfe90d6b8b..2b4a204dde331 100644 --- a/drivers/virtio/Makefile +++ b/drivers/virtio/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o +obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o virtio_admin_commands.o obj-$(CONFIG_VIRTIO_ANCHOR) += virtio_anchor.o obj-$(CONFIG_VIRTIO_PCI_LIB) += virtio_pci_modern_dev.o obj-$(CONFIG_VIRTIO_PCI_LIB_LEGACY) += virtio_pci_legacy_dev.o diff --git a/drivers/virtio/virtio_admin_commands.c b/drivers/virtio/virtio_admin_commands.c new file mode 100644 index 0000000000000..2b80548ba3bcf --- /dev/null +++ b/drivers/virtio/virtio_admin_commands.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +int virtio_admin_cap_id_list_query(struct virtio_device *vdev, + struct virtio_admin_cmd_query_cap_id_result *data) +{ + struct virtio_admin_cmd cmd = {}; + struct scatterlist result_sg; + + if (!vdev->config->admin_cmd_exec) + return -EOPNOTSUPP; + + sg_init_one(&result_sg, data, sizeof(*data)); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); + cmd.result_sg = &result_sg; + + return vdev->config->admin_cmd_exec(vdev, &cmd); +} +EXPORT_SYMBOL_GPL(virtio_admin_cap_id_list_query); + +int virtio_admin_cap_get(struct virtio_device *vdev, + u16 id, + void *caps, + size_t cap_size) +{ + struct virtio_admin_cmd_cap_get_data *data; + struct virtio_admin_cmd cmd = {}; + struct scatterlist result_sg; + struct scatterlist data_sg; + int err; + + if (!vdev->config->admin_cmd_exec) + return -EOPNOTSUPP; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->id = cpu_to_le16(id); + sg_init_one(&data_sg, data, sizeof(*data)); + sg_init_one(&result_sg, caps, cap_size); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); + cmd.data_sg = &data_sg; + cmd.result_sg = &result_sg; + + err = vdev->config->admin_cmd_exec(vdev, &cmd); + kfree(data); + + return err; +} +EXPORT_SYMBOL_GPL(virtio_admin_cap_get); + +int virtio_admin_cap_set(struct virtio_device *vdev, + u16 id, + const void *caps, + size_t cap_size) +{ + struct virtio_admin_cmd_cap_set_data *data; + struct virtio_admin_cmd cmd = {}; + struct scatterlist data_sg; + size_t data_size; + int err; + + if (!vdev->config->admin_cmd_exec) + return -EOPNOTSUPP; + + data_size = sizeof(*data) + cap_size; + data = kzalloc(data_size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->id = cpu_to_le16(id); + memcpy(data->cap_specific_data, caps, cap_size); + sg_init_one(&data_sg, data, data_size); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); + cmd.data_sg = &data_sg; + cmd.result_sg = NULL; + + err = vdev->config->admin_cmd_exec(vdev, &cmd); + kfree(data); + + return err; +} +EXPORT_SYMBOL_GPL(virtio_admin_cap_set); + +int virtio_admin_obj_create(struct virtio_device *vdev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id, + const void *obj_specific_data, + size_t obj_specific_data_size) +{ + size_t data_size = sizeof(struct virtio_admin_cmd_resource_obj_create_data); + struct virtio_admin_cmd_resource_obj_create_data *obj_create_data; + struct virtio_admin_cmd cmd = {}; + struct scatterlist data_sg; + void *data; + int err; + + if (!vdev->config->admin_cmd_exec) + return -EOPNOTSUPP; + + data_size += obj_specific_data_size; + data = kzalloc(data_size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + obj_create_data = data; + obj_create_data->hdr.type = cpu_to_le16(obj_type); + obj_create_data->hdr.id = cpu_to_le32(obj_id); + memcpy(obj_create_data->resource_obj_specific_data, obj_specific_data, + obj_specific_data_size); + sg_init_one(&data_sg, data, data_size); + + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE); + cmd.group_type = cpu_to_le16(group_type); + cmd.group_member_id = cpu_to_le64(group_member_id); + cmd.data_sg = &data_sg; + + err = vdev->config->admin_cmd_exec(vdev, &cmd); + kfree(data); + + return err; +} +EXPORT_SYMBOL_GPL(virtio_admin_obj_create); + +int virtio_admin_obj_destroy(struct virtio_device *vdev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id) +{ + struct virtio_admin_cmd_resource_obj_cmd_hdr *data; + struct virtio_admin_cmd cmd = {}; + struct scatterlist data_sg; + int err; + + if (!vdev->config->admin_cmd_exec) + return -EOPNOTSUPP; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->type = cpu_to_le16(obj_type); + data->id = cpu_to_le32(obj_id); + sg_init_one(&data_sg, data, sizeof(*data)); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY); + cmd.group_type = cpu_to_le16(group_type); + cmd.group_member_id = cpu_to_le64(group_member_id); + cmd.data_sg = &data_sg; + + err = vdev->config->admin_cmd_exec(vdev, &cmd); + kfree(data); + + return err; +} +EXPORT_SYMBOL_GPL(virtio_admin_obj_destroy); diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 8cd01de27bafe..fc26e035e7a66 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -48,7 +48,6 @@ struct virtio_pci_admin_vq { /* Protects virtqueue access. */ spinlock_t lock; u64 supported_cmds; - u64 supported_caps; u8 max_dev_parts_objects; struct ida dev_parts_ida; /* Name of the admin queue: avq.$vq_index. */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index dd0e65f71d413..acc3f958f96a8 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -304,7 +304,6 @@ virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev) static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev) { - struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev); struct virtio_admin_cmd_query_cap_id_result *data; struct virtio_admin_cmd cmd = {}; struct scatterlist result_sg; @@ -323,12 +322,7 @@ static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev) if (ret) goto end; - /* Max number of caps fits into a single u64 */ - BUILD_BUG_ON(sizeof(data->supported_caps) > sizeof(u64)); - - vp_dev->admin_vq.supported_caps = le64_to_cpu(data->supported_caps[0]); - - if (!(vp_dev->admin_vq.supported_caps & (1 << VIRTIO_DEV_PARTS_CAP))) + if (!(le64_to_cpu(data->supported_caps[0]) & (1 << VIRTIO_DEV_PARTS_CAP))) goto end; virtio_pci_admin_cmd_dev_parts_objects_enable(virtio_dev); @@ -1242,6 +1236,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, + .admin_cmd_exec = vp_modern_admin_cmd_exec, }; static const struct virtio_config_ops virtio_pci_config_ops = { @@ -1262,6 +1257,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .get_shm_region = vp_get_shm_region, .disable_vq_and_reset = vp_modern_disable_vq_and_reset, .enable_vq_after_reset = vp_modern_enable_vq_after_reset, + .admin_cmd_exec = vp_modern_admin_cmd_exec, }; /* the PCI probing function */ diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index fd7ed65e0197d..c5b6f6fa11eb7 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -409,7 +409,7 @@ static int pvcalls_back_connect(struct xenbus_device *dev, ret = sock_create(AF_INET, SOCK_STREAM, 0, &sock); if (ret < 0) goto out; - ret = inet_stream_connect(sock, sa, req->u.connect.len, 0); + ret = inet_stream_connect(sock, (struct sockaddr_unsized *)sa, req->u.connect.len, 0); if (ret < 0) { sock_release(sock); goto out; @@ -650,7 +650,7 @@ static int pvcalls_back_bind(struct xenbus_device *dev, if (ret < 0) goto out; - ret = inet_bind(map->sock, (struct sockaddr *)&req->u.bind.addr, + ret = inet_bind(map->sock, (struct sockaddr_unsized *)&req->u.bind.addr, req->u.bind.len); if (ret < 0) goto out; diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index c1cadf8fb346a..bf0e4ea0aafdf 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -82,16 +82,16 @@ int afs_open_socket(struct afs_net *net) if (ret < 0) pr_err("Couldn't create RxGK CM key: %d\n", ret); - ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx)); + ret = kernel_bind(socket, (struct sockaddr_unsized *) &srx, sizeof(srx)); if (ret == -EADDRINUSE) { srx.transport.sin6.sin6_port = 0; - ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx)); + ret = kernel_bind(socket, (struct sockaddr_unsized *) &srx, sizeof(srx)); } if (ret < 0) goto error_2; srx.srx_service = YFS_CM_SERVICE; - ret = kernel_bind(socket, (struct sockaddr *) &srx, sizeof(srx)); + ret = kernel_bind(socket, (struct sockaddr_unsized *) &srx, sizeof(srx)); if (ret < 0) goto error_2; diff --git a/fs/coredump.c b/fs/coredump.c index 5c1c381ee3806..14837d9e2abbe 100644 --- a/fs/coredump.c +++ b/fs/coredump.c @@ -708,7 +708,7 @@ static bool coredump_sock_connect(struct core_name *cn, struct coredump_params * */ pidfs_coredump(cprm); - retval = kernel_connect(socket, (struct sockaddr *)(&addr), addr_len, + retval = kernel_connect(socket, (struct sockaddr_unsized *)(&addr), addr_len, O_NONBLOCK | SOCK_COREDUMP); if (retval) { diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index 9a0b6c2b6b01e..b3958008ba3f7 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -1126,7 +1126,7 @@ static void writequeue_entry_complete(struct writequeue_entry *e, int completed) static int sctp_bind_addrs(struct socket *sock, __be16 port) { struct sockaddr_storage localaddr; - struct sockaddr *addr = (struct sockaddr *)&localaddr; + struct sockaddr_unsized *addr = (struct sockaddr_unsized *)&localaddr; int i, addr_len, result = 0; for (i = 0; i < dlm_local_count; i++) { @@ -1599,7 +1599,7 @@ static int dlm_connect(struct connection *con) log_print_ratelimited("connecting to %d", con->nodeid); make_sockaddr(&addr, dlm_config.ci_tcp_port, &addr_len); - result = kernel_connect(sock, (struct sockaddr *)&addr, addr_len, 0); + result = kernel_connect(sock, (struct sockaddr_unsized *)&addr, addr_len, 0); switch (result) { case -EINPROGRESS: /* not an error */ @@ -1813,7 +1813,7 @@ static int dlm_tcp_bind(struct socket *sock) memcpy(&src_addr, &dlm_local_addr[0], sizeof(src_addr)); make_sockaddr(&src_addr, 0, &addr_len); - result = kernel_bind(sock, (struct sockaddr *)&src_addr, + result = kernel_bind(sock, (struct sockaddr_unsized *)&src_addr, addr_len); if (result < 0) { /* This *may* not indicate a critical error */ @@ -1852,7 +1852,7 @@ static int dlm_tcp_listen_bind(struct socket *sock) /* Bind to our port */ make_sockaddr(&dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len); - return kernel_bind(sock, (struct sockaddr *)&dlm_local_addr[0], + return kernel_bind(sock, (struct sockaddr_unsized *)&dlm_local_addr[0], addr_len); } diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig index 01873c2a34ad2..5bad43e85ee1a 100644 --- a/fs/ext4/Kconfig +++ b/fs/ext4/Kconfig @@ -77,7 +77,6 @@ config EXT4_DEBUG config EXT4_KUNIT_TESTS tristate "KUnit tests for ext4" if !KUNIT_ALL_TESTS depends on EXT4_FS && KUNIT - default KUNIT_ALL_TESTS help This builds the ext4 KUnit tests. diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig index 25fae1c83725b..79c8502ba9115 100644 --- a/fs/fat/Kconfig +++ b/fs/fat/Kconfig @@ -121,7 +121,6 @@ config FAT_DEFAULT_UTF8 config FAT_KUNIT_TEST tristate "Unit Tests for FAT filesystems" if !KUNIT_ALL_TESTS depends on KUNIT && FAT_FS - default KUNIT_ALL_TESTS help This builds the FAT KUnit tests diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index b05d4e9d13b28..79b281e32f4ce 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -1615,7 +1615,7 @@ static void o2net_start_connect(struct work_struct *work) myaddr.sin_addr.s_addr = mynode->nd_ipv4_address; myaddr.sin_port = htons(0); /* any port */ - ret = sock->ops->bind(sock, (struct sockaddr *)&myaddr, + ret = sock->ops->bind(sock, (struct sockaddr_unsized *)&myaddr, sizeof(myaddr)); if (ret) { mlog(ML_ERROR, "bind failed with %d at address %pI4\n", @@ -1638,7 +1638,7 @@ static void o2net_start_connect(struct work_struct *work) remoteaddr.sin_port = node->nd_ipv4_port; ret = sc->sc_sock->ops->connect(sc->sc_sock, - (struct sockaddr *)&remoteaddr, + (struct sockaddr_unsized *)&remoteaddr, sizeof(remoteaddr), O_NONBLOCK); if (ret == -EINPROGRESS) @@ -2002,7 +2002,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port) INIT_WORK(&o2net_listen_work, o2net_accept_many); sock->sk->sk_reuse = SK_CAN_REUSE; - ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin)); + ret = sock->ops->bind(sock, (struct sockaddr_unsized *)&sin, sizeof(sin)); if (ret < 0) { printk(KERN_ERR "o2net: Error %d while binding socket at " "%pI4:%u\n", ret, &addr, ntohs(port)); diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 55cb4b0cbd48f..176301191f295 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -3104,7 +3104,7 @@ bind_socket(struct TCP_Server_Info *server) struct socket *socket = server->ssocket; rc = kernel_bind(socket, - (struct sockaddr *) &server->srcaddr, + (struct sockaddr_unsized *) &server->srcaddr, sizeof(server->srcaddr)); if (rc < 0) { struct sockaddr_in *saddr4; @@ -3403,7 +3403,7 @@ generic_ip_connect(struct TCP_Server_Info *server) socket->sk->sk_sndbuf, socket->sk->sk_rcvbuf, socket->sk->sk_rcvtimeo); - rc = kernel_connect(socket, saddr, slen, + rc = kernel_connect(socket, (struct sockaddr_unsized *)saddr, slen, server->noblockcnt ? O_NONBLOCK : 0); /* * When mounting SMB root file systems, we do not want to block in diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c index d2e391c29464e..6e03e93321b82 100644 --- a/fs/smb/server/transport_tcp.c +++ b/fs/smb/server/transport_tcp.c @@ -522,10 +522,10 @@ static int create_socket(struct interface *iface) } if (ipv4) - ret = kernel_bind(ksmbd_socket, (struct sockaddr *)&sin, + ret = kernel_bind(ksmbd_socket, (struct sockaddr_unsized *)&sin, sizeof(sin)); else - ret = kernel_bind(ksmbd_socket, (struct sockaddr *)&sin6, + ret = kernel_bind(ksmbd_socket, (struct sockaddr_unsized *)&sin6, sizeof(sin6)); if (ret) { pr_err("Failed to bind socket: %d\n", ret); diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index 5be1881abbb66..11bdab5522fd5 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -1253,6 +1253,17 @@ enum virtchnl_proto_hdr_type { VIRTCHNL_PROTO_HDR_ESP, VIRTCHNL_PROTO_HDR_AH, VIRTCHNL_PROTO_HDR_PFCP, + VIRTCHNL_PROTO_HDR_GTPC, + VIRTCHNL_PROTO_HDR_ECPRI, + VIRTCHNL_PROTO_HDR_L2TPV2, + VIRTCHNL_PROTO_HDR_PPP, + /* IPv4 and IPv6 Fragment header types are only associated to + * VIRTCHNL_PROTO_HDR_IPV4 and VIRTCHNL_PROTO_HDR_IPV6 respectively, + * cannot be used independently. + */ + VIRTCHNL_PROTO_HDR_IPV4_FRAG, + VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG, + VIRTCHNL_PROTO_HDR_GRE, }; /* Protocol header field within a protocol header. */ @@ -1275,6 +1286,7 @@ enum virtchnl_proto_hdr_field { VIRTCHNL_PROTO_HDR_IPV4_DSCP, VIRTCHNL_PROTO_HDR_IPV4_TTL, VIRTCHNL_PROTO_HDR_IPV4_PROT, + VIRTCHNL_PROTO_HDR_IPV4_CHKSUM, /* IPV6 */ VIRTCHNL_PROTO_HDR_IPV6_SRC = PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV6), @@ -1282,18 +1294,34 @@ enum virtchnl_proto_hdr_field { VIRTCHNL_PROTO_HDR_IPV6_TC, VIRTCHNL_PROTO_HDR_IPV6_HOP_LIMIT, VIRTCHNL_PROTO_HDR_IPV6_PROT, + /* IPV6 Prefix */ + VIRTCHNL_PROTO_HDR_IPV6_PREFIX32_SRC, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX32_DST, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX40_SRC, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX40_DST, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX48_SRC, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX48_DST, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX56_SRC, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX56_DST, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX96_SRC, + VIRTCHNL_PROTO_HDR_IPV6_PREFIX96_DST, /* TCP */ VIRTCHNL_PROTO_HDR_TCP_SRC_PORT = PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_TCP), VIRTCHNL_PROTO_HDR_TCP_DST_PORT, + VIRTCHNL_PROTO_HDR_TCP_CHKSUM, /* UDP */ VIRTCHNL_PROTO_HDR_UDP_SRC_PORT = PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_UDP), VIRTCHNL_PROTO_HDR_UDP_DST_PORT, + VIRTCHNL_PROTO_HDR_UDP_CHKSUM, /* SCTP */ VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT = PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_SCTP), VIRTCHNL_PROTO_HDR_SCTP_DST_PORT, + VIRTCHNL_PROTO_HDR_SCTP_CHKSUM, /* GTPU_IP */ VIRTCHNL_PROTO_HDR_GTPU_IP_TEID = PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_IP), @@ -1317,6 +1345,28 @@ enum virtchnl_proto_hdr_field { VIRTCHNL_PROTO_HDR_PFCP_S_FIELD = PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_PFCP), VIRTCHNL_PROTO_HDR_PFCP_SEID, + /* GTPC */ + VIRTCHNL_PROTO_HDR_GTPC_TEID = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPC), + /* ECPRI */ + VIRTCHNL_PROTO_HDR_ECPRI_MSG_TYPE = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_ECPRI), + VIRTCHNL_PROTO_HDR_ECPRI_PC_RTC_ID, + /* IPv4 Dummy Fragment */ + VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV4_FRAG), + /* IPv6 Extension Fragment */ + VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG), + /* GTPU_DWN/UP */ + VIRTCHNL_PROTO_HDR_GTPU_DWN_QFI = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN), + VIRTCHNL_PROTO_HDR_GTPU_UP_QFI = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP), + /* L2TPv2 */ + VIRTCHNL_PROTO_HDR_L2TPV2_SESS_ID = + PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_L2TPV2), + VIRTCHNL_PROTO_HDR_L2TPV2_LEN_SESS_ID, }; struct virtchnl_proto_hdr { diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index aedf573bdb426..d1eb5c7729cb8 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -120,7 +120,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, enum cgroup_bpf_attach_type atype); int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, @@ -238,8 +238,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ - atype, NULL, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, \ + (struct sockaddr_unsized *)uaddr, uaddrlen, \ + atype, NULL, NULL); \ __ret; \ }) @@ -248,8 +249,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ - atype, t_ctx, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, \ + (struct sockaddr_unsized *)uaddr, uaddrlen, \ + atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ @@ -266,8 +268,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ - atype, NULL, &__flags); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, \ + (struct sockaddr_unsized *)uaddr, uaddrlen, \ + atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index a2229a61ccde8..bd7410b5d8a67 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -127,10 +127,13 @@ struct can_priv *safe_candev_priv(struct net_device *dev); int open_candev(struct net_device *dev); void close_candev(struct net_device *dev); void can_set_default_mtu(struct net_device *dev); -int can_change_mtu(struct net_device *dev, int new_mtu); int __must_check can_set_static_ctrlmode(struct net_device *dev, u32 static_mode); -int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd); +int can_hwtstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg); +int can_hwtstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *cfg, + struct netlink_ext_ack *extack); int can_ethtool_op_get_ts_info_hwts(struct net_device *dev, struct kernel_ethtool_ts_info *info); diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 25be745bf41f1..562f520b23c27 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -163,6 +163,7 @@ struct dpll_pin_properties { u32 freq_supported_num; struct dpll_pin_frequency *freq_supported; struct dpll_pin_phase_adjust_range phase_range; + u32 phase_gran; }; #if IS_ENABLED(CONFIG_DPLL) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 5c9162193d269..a57be6e45d3b4 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -216,13 +216,46 @@ static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx) void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); struct link_mode_info { - int speed; - u8 lanes; - u8 duplex; + int speed; + u8 lanes; + u8 min_pairs; + u8 pairs; + u8 duplex; + u16 mediums; }; extern const struct link_mode_info link_mode_params[]; +extern const char ethtool_link_medium_names[][ETH_GSTRING_LEN]; + +#define ETHTOOL_MEDIUM_FIBER_BITS (BIT(ETHTOOL_LINK_MEDIUM_BASES) | \ + BIT(ETHTOOL_LINK_MEDIUM_BASEL) | \ + BIT(ETHTOOL_LINK_MEDIUM_BASEF)) + +static inline const char *phy_mediums(enum ethtool_link_medium medium) +{ + if (medium >= __ETHTOOL_LINK_MEDIUM_LAST) + return "unknown"; + + return ethtool_link_medium_names[medium]; +} + +static inline enum ethtool_link_medium ethtool_str_to_medium(const char *str) +{ + int i; + + for (i = 0; i < __ETHTOOL_LINK_MEDIUM_LAST; i++) + if (!strcmp(phy_mediums(i), str)) + return i; + + return ETHTOOL_LINK_MEDIUM_NONE; +} + +static inline int ethtool_linkmode_n_pairs(unsigned int mode) +{ + return link_mode_params[mode].pairs; +} + /* declare a link mode bitmap */ #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) diff --git a/include/linux/filter.h b/include/linux/filter.h index 973233b82dc1f..03e7516c61872 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1535,7 +1535,7 @@ static inline int bpf_tell_extensions(void) struct bpf_sock_addr_kern { struct sock *sk; - struct sockaddr *uaddr; + struct sockaddr_unsized *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time @@ -1801,6 +1801,8 @@ int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); +int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, + const void *from, u32 len, u64 flags); void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, @@ -1837,6 +1839,13 @@ static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, voi { } +static inline int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, + const void *from, u32 len, + u64 flags) +{ + return -EOPNOTSUPP; +} + static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) { return ERR_PTR(-EOPNOTSUPP); diff --git a/include/linux/icmp.h b/include/linux/icmp.h index 0af4d210ee315..043ec5d9c8821 100644 --- a/include/linux/icmp.h +++ b/include/linux/icmp.h @@ -40,4 +40,36 @@ void ip_icmp_error_rfc4884(const struct sk_buff *skb, struct sock_ee_data_rfc4884 *out, int thlen, int off); +/* RFC 4884 */ +#define ICMP_EXT_ORIG_DGRAM_MIN_LEN 128 +#define ICMP_EXT_VERSION_2 2 + +/* ICMP Extension Object Classes */ +#define ICMP_EXT_OBJ_CLASS_IIO 2 /* RFC 5837 */ + +/* Interface Information Object - RFC 5837 */ +enum { + ICMP_EXT_CTYPE_IIO_ROLE_IIF, +}; + +#define ICMP_EXT_CTYPE_IIO_ROLE(ROLE) ((ROLE) << 6) +#define ICMP_EXT_CTYPE_IIO_MTU BIT(0) +#define ICMP_EXT_CTYPE_IIO_NAME BIT(1) +#define ICMP_EXT_CTYPE_IIO_IPADDR BIT(2) +#define ICMP_EXT_CTYPE_IIO_IFINDEX BIT(3) + +struct icmp_ext_iio_name_subobj { + u8 len; + char name[IFNAMSIZ]; +}; + +enum { + /* RFC 5837 - Incoming IP Interface Role */ + ICMP_ERR_EXT_IIO_IIF, + /* Add new constants above. Used by "icmp_errors_extension_mask" + * sysctl. + */ + ICMP_ERR_EXT_COUNT, +}; + #endif /* _LINUX_ICMP_H */ diff --git a/include/linux/ieee80211-eht.h b/include/linux/ieee80211-eht.h new file mode 100644 index 0000000000000..f9782e46c5e52 --- /dev/null +++ b/include/linux/ieee80211-eht.h @@ -0,0 +1,1182 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 EHT definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_EHT_H +#define LINUX_IEEE80211_EHT_H + +#include +#include +/* need HE definitions for the inlines here */ +#include + +#define IEEE80211_TTLM_MAX_CNT 2 +#define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 +#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 +#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 +#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 +#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 + +#define IEEE80211_TTLM_DIRECTION_DOWN 0 +#define IEEE80211_TTLM_DIRECTION_UP 1 +#define IEEE80211_TTLM_DIRECTION_BOTH 2 + +/** + * struct ieee80211_ttlm_elem - TID-To-Link Mapping element + * + * Defined in section 9.4.2.314 in P802.11be_D4 + * + * @control: the first part of control field + * @optional: the second part of control field + */ +struct ieee80211_ttlm_elem { + u8 control; + u8 optional[]; +} __packed; + +#define IEEE80211_EHT_MCS_NSS_RX 0x0f +#define IEEE80211_EHT_MCS_NSS_TX 0xf0 + +/** + * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max + * supported NSS for per MCS. + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 7. + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 8 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + * @rx_tx_max_nss: array of the previous fields for easier loop access + */ +struct ieee80211_eht_mcs_nss_supp_20mhz_only { + union { + struct { + u8 rx_tx_mcs7_max_nss; + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; + }; + u8 rx_tx_max_nss[4]; + }; +}; + +/** + * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except + * 20MHz only stations). + * + * For each field below, bits 0 - 3 indicate the maximal number of spatial + * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams + * for Tx. + * + * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 0 - 9. + * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 10 - 11. + * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams + * supported for reception and the maximum number of spatial streams + * supported for transmission for MCS 12 - 13. + * @rx_tx_max_nss: array of the previous fields for easier loop access + */ +struct ieee80211_eht_mcs_nss_supp_bw { + union { + struct { + u8 rx_tx_mcs9_max_nss; + u8 rx_tx_mcs11_max_nss; + u8 rx_tx_mcs13_max_nss; + }; + u8 rx_tx_max_nss[3]; + }; +}; + +/** + * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data + * + * This structure is the "EHT Capabilities element" fixed fields as + * described in P802.11be_D2.0 section 9.4.2.313. + * + * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* + * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* + */ +struct ieee80211_eht_cap_elem_fixed { + u8 mac_cap_info[2]; + u8 phy_cap_info[9]; +} __packed; + +/** + * struct ieee80211_eht_cap_elem - EHT capabilities element + * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed + * @optional: optional parts + */ +struct ieee80211_eht_cap_elem { + struct ieee80211_eht_cap_elem_fixed fixed; + + /* + * Followed by: + * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. + * EHT PPE Thresholds field: variable length. + */ + u8 optional[]; +} __packed; + +#define IEEE80211_EHT_OPER_INFO_PRESENT 0x01 +#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x02 +#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION 0x04 +#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT 0x08 +#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK 0x30 +#define IEEE80211_EHT_OPER_MCS15_DISABLE 0x40 + +/** + * struct ieee80211_eht_operation - eht operation element + * + * This structure is the "EHT Operation Element" fields as + * described in P802.11be_D2.0 section 9.4.2.311 + * + * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_* + * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in + * EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and + * receive. + * @optional: optional parts + */ +struct ieee80211_eht_operation { + u8 params; + struct ieee80211_eht_mcs_nss_supp_20mhz_only basic_mcs_nss; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_eht_operation_info - eht operation information + * + * @control: EHT operation information control. + * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz + * EHT BSS. + * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS. + * @optional: optional parts + */ +struct ieee80211_eht_operation_info { + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 optional[]; +} __packed; + +/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ +#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 +#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 +#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 +#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 +#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK 0xc0 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895 0 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991 1 +#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 + +#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 +#define IEEE80211_EHT_MAC_CAP1_EHT_TRS 0x02 +#define IEEE80211_EHT_MAC_CAP1_TXOP_RET 0x04 +#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS 0x08 +#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK 0x30 +#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS 0x40 + +/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ +#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 +#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 +#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 +#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 + +/* EHT beamformee number of spatial streams <= 80MHz is split */ +#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 + +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c +#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 + +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 + +/* EHT number of sounding dimensions for 320MHz is split */ +#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 +#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 +#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 +#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 +#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 +#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 +#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 + +#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 +#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 +#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 + +#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 +#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 +#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 +#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 +#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 + +/* Maximum number of supported EHT LTF is split */ +#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 +#define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 +#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 + +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x30 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 +#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 + +#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 +#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 +#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 +#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 + +#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 +#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 + +/* + * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311 + */ +#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 +#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 + +/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ +static inline u8 +ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, + const struct ieee80211_eht_cap_elem_fixed *eht_cap, + bool from_ap) +{ + u8 count = 0; + + /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) + return 3; + + /* on 2.4 GHz, these three bits are reserved, so should be 0 */ + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) + count += 3; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 3; + + if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) + count += 3; + + if (count) + return count; + + return from_ap ? 3 : 4; +} + +/* 802.11be EHT PPE Thresholds */ +#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 +#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf +#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 +#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 +#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 + +/* + * Calculate 802.11be EHT capabilities IE EHT field size + */ +static inline u8 +ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u32 n; + + if (!(phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) + return 0; + + n = hweight16(ppe_thres_hdr & + IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); + + /* + * Each pair is 6 bits, and we need to add the 9 "header" bits to the + * total size. + */ + n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + + IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; + return DIV_ROUND_UP(n, 8); +} + +static inline bool +ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, + bool from_ap) +{ + const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; + u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); + + if (len < needed || !he_capa) + return false; + + needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, + (const void *)data, + from_ap); + if (len < needed) + return false; + + if (elem->phy_cap_info[5] & + IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { + u16 ppe_thres_hdr; + + if (len < needed + sizeof(ppe_thres_hdr)) + return false; + + ppe_thres_hdr = get_unaligned_le16(data + needed); + needed += ieee80211_eht_ppe_size(ppe_thres_hdr, + elem->phy_cap_info); + } + + return len >= needed; +} + +static inline bool +ieee80211_eht_oper_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_eht_operation *elem = (const void *)data; + u8 needed = sizeof(*elem); + + if (len < needed) + return false; + + if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) { + needed += 3; + + if (elem->params & + IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) + needed += 2; + } + + return len >= needed; +} + +/* must validate ieee80211_eht_oper_size_ok() first */ +static inline u16 +ieee80211_eht_oper_dis_subchan_bitmap(const struct ieee80211_eht_operation *eht_oper) +{ + const struct ieee80211_eht_operation_info *info = + (const void *)eht_oper->optional; + + if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) + return 0; + + if (!(eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) + return 0; + + return get_unaligned_le16(info->optional); +} + +#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) + +struct ieee80211_bandwidth_indication { + u8 params; + struct ieee80211_eht_operation_info info; +} __packed; + +static inline bool +ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_bandwidth_indication *bwi = (const void *)data; + + if (len < sizeof(*bwi)) + return false; + + if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && + len < sizeof(*bwi) + 2) + return false; + + return true; +} + +/* Protected EHT action codes */ +enum ieee80211_protected_eht_actioncode { + WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, + WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, + WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4, + WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5, + WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6, + WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8, + WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11, + WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12, +}; + +/* multi-link device */ +#define IEEE80211_MLD_MAX_NUM_LINKS 15 + +#define IEEE80211_ML_CONTROL_TYPE 0x0007 +#define IEEE80211_ML_CONTROL_TYPE_BASIC 0 +#define IEEE80211_ML_CONTROL_TYPE_PREQ 1 +#define IEEE80211_ML_CONTROL_TYPE_RECONF 2 +#define IEEE80211_ML_CONTROL_TYPE_TDLS 3 +#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 +#define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 + +struct ieee80211_multi_link_elem { + __le16 control; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 +#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 +#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 +#define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 +#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 +#define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 +#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP 0x0400 + +#define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff +#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 +#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 + +/* + * Described in P802.11be_D3.0 + * dot11MSDTimerDuration should default to 5484 (i.e. 171.375) + * dot11MSDOFDMEDthreshold defaults to -72 (i.e. 0) + * dot11MSDTXOPMAX defaults to 1 + */ +#define IEEE80211_MED_SYNC_DELAY_DEFAULT 0x10ac + +#define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 +#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 +#define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 +#define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 +#define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 +#define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 +#define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 +#define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 +#define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 +#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 + +#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f +#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_NO_SUPP 0 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME 1 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_RESERVED 2 +#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 +#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 +#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 +#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT 0x2000 +#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT 0x4000 + +struct ieee80211_mle_basic_common_info { + u8 len; + u8 mld_mac_addr[ETH_ALEN]; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 + +struct ieee80211_mle_preq_common_info { + u8 len; + u8 variable[]; +} __packed; + +#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 +#define IEEE80211_MLC_RECONF_PRES_EML_CAPA 0x0020 +#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP 0x0040 +#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP 0x0080 + +/* no fixed fields in RECONF */ + +struct ieee80211_mle_tdls_common_info { + u8 len; + u8 ap_mld_mac_addr[ETH_ALEN]; +} __packed; + +#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 + +/* no fixed fields in PRIO_ACCESS */ + +/** + * ieee80211_mle_common_size - check multi-link element common size + * @data: multi-link element, must already be checked for size using + * ieee80211_mle_size_ok() + * Return: the size of the multi-link element's "common" subfield + */ +static inline u8 ieee80211_mle_common_size(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + case IEEE80211_ML_CONTROL_TYPE_PREQ: + case IEEE80211_ML_CONTROL_TYPE_TDLS: + case IEEE80211_ML_CONTROL_TYPE_RECONF: + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + /* + * The length is the first octet pointed by mle->variable so no + * need to add anything + */ + break; + default: + WARN_ON(1); + return 0; + } + + return sizeof(*mle) + mle->variable[0]; +} + +/** + * ieee80211_mle_get_link_id - returns the link ID + * @data: the basic multi link element + * Return: the link ID, or -1 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline int ieee80211_mle_get_link_id(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_LINK_ID)) + return -1; + + return *common; +} + +/** + * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count + * @data: pointer to the basic multi link element + * Return: the BSS Parameter Change Count field value, or -1 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline int +ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)) + return -1; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + + return *common; +} + +/** + * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay + * @data: pointer to the multi-link element + * Return: the medium synchronization delay field value from the multi-link + * element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT) + * if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) + return IEEE80211_MED_SYNC_DELAY_DEFAULT; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_eml_cap - returns the EML capability + * @data: pointer to the multi-link element + * Return: the EML capability field value from the multi-link element, + * or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* common points now at the beginning of ieee80211_mle_basic_common_info */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. + * @data: pointer to the multi-link element + * Return: the MLD capabilities and operations field value from the multi-link + * element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + + return get_unaligned_le16(common); +} + +/* Defined in Figure 9-1074t in P802.11be_D7.0 */ +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE 0x0001 +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_RECO_MAX_LINKS_MASK 0x001e +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE 0x0020 +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK 0x0040 +#define IEEE80211_EHT_ML_EXT_MLD_CAPA_BTM_MLD_RECO_MULTI_AP 0x0080 + +/** + * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities + * and operations. + * @data: pointer to the multi-link element + * Return: the extended MLD capabilities and operations field value from + * the multi-link element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + + return get_unaligned_le16(common); +} + +/** + * ieee80211_mle_get_mld_id - returns the MLD ID + * @data: pointer to the multi-link element + * Return: The MLD ID in the given multi-link element, or 0 if not present + * + * The element is assumed to be of the correct type (BASIC) and big enough, + * this must be checked using ieee80211_mle_type_ok(). + */ +static inline u8 ieee80211_mle_get_mld_id(const u8 *data) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control = le16_to_cpu(mle->control); + const u8 *common = mle->variable; + + /* + * common points now at the beginning of + * ieee80211_mle_basic_common_info + */ + common += sizeof(struct ieee80211_mle_basic_common_info); + + if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_ID)) + return 0; + + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + + return *common; +} + +/** + * ieee80211_mle_size_ok - validate multi-link element size + * @data: pointer to the element data + * @len: length of the containing element + * Return: whether or not the multi-link element size is OK + */ +static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u8 fixed = sizeof(*mle); + u8 common = 0; + bool check_common_len = false; + u16 control; + + if (!data || len < fixed) + return false; + + control = le16_to_cpu(mle->control); + + switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { + case IEEE80211_ML_CONTROL_TYPE_BASIC: + common += sizeof(struct ieee80211_mle_basic_common_info); + check_common_len = true; + if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) + common += 1; + if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP) + common += 2; + break; + case IEEE80211_ML_CONTROL_TYPE_PREQ: + common += sizeof(struct ieee80211_mle_preq_common_info); + if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) + common += 1; + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_RECONF: + if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) + common += ETH_ALEN; + if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP) + common += 2; + if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP) + common += 2; + break; + case IEEE80211_ML_CONTROL_TYPE_TDLS: + common += sizeof(struct ieee80211_mle_tdls_common_info); + check_common_len = true; + break; + case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: + common = ETH_ALEN + 1; + break; + default: + /* we don't know this type */ + return true; + } + + if (len < fixed + common) + return false; + + if (!check_common_len) + return true; + + /* if present, common length is the first octet there */ + return mle->variable[0] >= common; +} + +/** + * ieee80211_mle_type_ok - validate multi-link element type and size + * @data: pointer to the element data + * @type: expected type of the element + * @len: length of the containing element + * Return: whether or not the multi-link element type matches and size is OK + */ +static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) +{ + const struct ieee80211_multi_link_elem *mle = (const void *)data; + u16 control; + + if (!ieee80211_mle_size_ok(data, len)) + return false; + + control = le16_to_cpu(mle->control); + + if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) == type) + return true; + + return false; +} + +enum ieee80211_mle_subelems { + IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, + IEEE80211_MLE_SUBELEM_FRAGMENT = 254, +}; + +#define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f +#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 +#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 +#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 +#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 +#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 +#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 +#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 +#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 + +struct ieee80211_mle_per_sta_profile { + __le16 control; + u8 sta_info_len; + u8 variable[]; +} __packed; + +/** + * ieee80211_mle_basic_sta_prof_size_ok - validate basic multi-link element sta + * profile size + * @data: pointer to the sub element data + * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise + */ +static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, + size_t len) +{ + const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; + u16 control; + u8 fixed = sizeof(*prof); + u8 info_len = 1; + + if (len < fixed) + return false; + + control = le16_to_cpu(prof->control); + + if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) + info_len += 6; + if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) + info_len += 8; + if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && + control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { + if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) + info_len += 2; + else + info_len += 1; + } + if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT) + info_len += 1; + + return prof->sta_info_len >= info_len && + fixed + prof->sta_info_len - 1 <= len; +} + +/** + * ieee80211_mle_basic_sta_prof_bss_param_ch_cnt - get per-STA profile BSS + * parameter change count + * @prof: the per-STA profile, having been checked with + * ieee80211_mle_basic_sta_prof_size_ok() for the correct length + * + * Return: The BSS parameter change count value if present, 0 otherwise. + */ +static inline u8 +ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta_profile *prof) +{ + u16 control = le16_to_cpu(prof->control); + const u8 *pos = prof->variable; + + if (!(control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)) + return 0; + + if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) + pos += 6; + if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) + pos += 2; + if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) + pos += 8; + if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) + pos += 2; + if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && + control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { + if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) + pos += 2; + else + pos += 1; + } + + return *pos; +} + +#define IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID 0x000f +#define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 +#define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 +#define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE 0x0780 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM 0 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK 2 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK 3 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS 4 +#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 + +/** + * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link + * element sta profile size. + * @data: pointer to the sub element data + * @len: length of the containing sub element + * Return: %true if the STA profile is large enough, %false otherwise + */ +static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, + size_t len) +{ + const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; + u16 control; + u8 fixed = sizeof(*prof); + u8 info_len = 1; + + if (len < fixed) + return false; + + control = le16_to_cpu(prof->control); + + if (control & IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT) + info_len += ETH_ALEN; + if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT) + info_len += 2; + if (control & IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT) + info_len += 2; + + return prof->sta_info_len >= info_len && + fixed + prof->sta_info_len - 1 <= len; +} + +#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID 0x000f +#define IEEE80211_EPCS_ENA_RESP_BODY_LEN 3 + +static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_ttlm_elem *t2l = (const void *)data; + u8 control, fixed = sizeof(*t2l), elem_len = 0; + + if (len < fixed) + return false; + + control = t2l->control; + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) + elem_len += 2; + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) + elem_len += 3; + + if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { + u8 bm_size; + + elem_len += 1; + if (len < fixed + elem_len) + return false; + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + bm_size = 1; + else + bm_size = 2; + + elem_len += hweight8(t2l->optional[0]) * bm_size; + } + + return len >= fixed + elem_len; +} + +/** + * ieee80211_emlsr_pad_delay_in_us - Fetch the EMLSR Padding delay + * in microseconds + * @eml_cap: EML capabilities field value from common info field of + * the Multi-link element + * Return: the EMLSR Padding delay (in microseconds) encoded in the + * EML Capabilities field + */ + +static inline u32 ieee80211_emlsr_pad_delay_in_us(u16 eml_cap) +{ + /* IEEE Std 802.11be-2024 Table 9-417i—Encoding of the EMLSR + * Padding Delay subfield. + */ + u32 pad_delay = u16_get_bits(eml_cap, + IEEE80211_EML_CAP_EMLSR_PADDING_DELAY); + + if (!pad_delay || + pad_delay > IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US) + return 0; + + return 32 * (1 << (pad_delay - 1)); +} + +/** + * ieee80211_emlsr_trans_delay_in_us - Fetch the EMLSR Transition + * delay in microseconds + * @eml_cap: EML capabilities field value from common info field of + * the Multi-link element + * Return: the EMLSR Transition delay (in microseconds) encoded in the + * EML Capabilities field + */ + +static inline u32 ieee80211_emlsr_trans_delay_in_us(u16 eml_cap) +{ + /* IEEE Std 802.11be-2024 Table 9-417j—Encoding of the EMLSR + * Transition Delay subfield. + */ + u32 trans_delay = + u16_get_bits(eml_cap, + IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY); + + /* invalid values also just use 0 */ + if (!trans_delay || + trans_delay > IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US) + return 0; + + return 16 * (1 << (trans_delay - 1)); +} + +/** + * ieee80211_eml_trans_timeout_in_us - Fetch the EMLSR Transition + * timeout value in microseconds + * @eml_cap: EML capabilities field value from common info field of + * the Multi-link element + * Return: the EMLSR Transition timeout (in microseconds) encoded in + * the EML Capabilities field + */ + +static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) +{ + /* IEEE Std 802.11be-2024 Table 9-417m—Encoding of the + * Transition Timeout subfield. + */ + u8 timeout = u16_get_bits(eml_cap, + IEEE80211_EML_CAP_TRANSITION_TIMEOUT); + + /* invalid values also just use 0 */ + if (!timeout || timeout > IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU) + return 0; + + return 128 * (1 << (timeout - 1)); +} + +#define for_each_mle_subelement(_elem, _data, _len) \ + if (ieee80211_mle_size_ok(_data, _len)) \ + for_each_element(_elem, \ + _data + ieee80211_mle_common_size(_data),\ + _len - ieee80211_mle_common_size(_data)) + +#endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/ieee80211-he.h b/include/linux/ieee80211-he.h new file mode 100644 index 0000000000000..904d50db5bb80 --- /dev/null +++ b/include/linux/ieee80211-he.h @@ -0,0 +1,824 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 HE definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_HE_H +#define LINUX_IEEE80211_HE_H + +#include +#include + +#define IEEE80211_TWT_CONTROL_NDP BIT(0) +#define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) +#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) +#define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) +#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) + +#define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) +#define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) +#define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) +#define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) +#define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) +#define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) +#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) +#define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) + +enum ieee80211_twt_setup_cmd { + TWT_SETUP_CMD_REQUEST, + TWT_SETUP_CMD_SUGGEST, + TWT_SETUP_CMD_DEMAND, + TWT_SETUP_CMD_GROUPING, + TWT_SETUP_CMD_ACCEPT, + TWT_SETUP_CMD_ALTERNATE, + TWT_SETUP_CMD_DICTATE, + TWT_SETUP_CMD_REJECT, +}; + +struct ieee80211_twt_params { + __le16 req_type; + __le64 twt; + u8 min_twt_dur; + __le16 mantissa; + u8 channel; +} __packed; + +struct ieee80211_twt_setup { + u8 dialog_token; + u8 element_id; + u8 length; + u8 control; + u8 params[]; +} __packed; + +/** + * struct ieee80211_he_cap_elem - HE capabilities element + * @mac_cap_info: HE MAC Capabilities Information + * @phy_cap_info: HE PHY Capabilities Information + * + * This structure represents the fixed fields of the payload of the + * "HE capabilities element" as described in IEEE Std 802.11ax-2021 + * sections 9.4.2.248.2 and 9.4.2.248.3. + */ +struct ieee80211_he_cap_elem { + u8 mac_cap_info[6]; + u8 phy_cap_info[11]; +} __packed; + +#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 + +/** + * enum ieee80211_he_mcs_support - HE MCS support definitions + * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported + * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the rx_mcs_* + * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_he_mcs_support { + IEEE80211_HE_MCS_SUPPORT_0_7 = 0, + IEEE80211_HE_MCS_SUPPORT_0_9 = 1, + IEEE80211_HE_MCS_SUPPORT_0_11 = 2, + IEEE80211_HE_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field + * + * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field + * described in P802.11ax_D2.0 section 9.4.2.237.4 + * + * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * widths less than 80MHz. + * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel + * width 160MHz. + * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for + * channel width 80p80MHz. + */ +struct ieee80211_he_mcs_nss_supp { + __le16 rx_mcs_80; + __le16 tx_mcs_80; + __le16 rx_mcs_160; + __le16 tx_mcs_160; + __le16 rx_mcs_80p80; + __le16 tx_mcs_80p80; +} __packed; + +/** + * struct ieee80211_he_operation - HE Operation element + * @he_oper_params: HE Operation Parameters + BSS Color Information + * @he_mcs_nss_set: Basic HE-MCS And NSS Set + * @optional: Optional fields VHT Operation Information, Max Co-Hosted + * BSSID Indicator, and 6 GHz Operation Information + * + * This structure represents the payload of the "HE Operation + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. + */ +struct ieee80211_he_operation { + __le32 he_oper_params; + __le16 he_mcs_nss_set; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_he_spr - Spatial Reuse Parameter Set element + * @he_sr_control: SR Control + * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD + * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color + * Bitmap, and SRG Partial BSSID Bitmap + * + * This structure represents the payload of the "Spatial Reuse + * Parameter Set element" as described in IEEE Std 802.11ax-2021 + * section 9.4.2.252. + */ +struct ieee80211_he_spr { + u8 he_sr_control; + u8 optional[]; +} __packed; + +/** + * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field + * @aifsn: ACI/AIFSN + * @ecw_min_max: ECWmin/ECWmax + * @mu_edca_timer: MU EDCA Timer + * + * This structure represents the "MU AC Parameter Record" as described + * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. + */ +struct ieee80211_he_mu_edca_param_ac_rec { + u8 aifsn; + u8 ecw_min_max; + u8 mu_edca_timer; +} __packed; + +/** + * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element + * @mu_qos_info: QoS Info + * @ac_be: MU AC_BE Parameter Record + * @ac_bk: MU AC_BK Parameter Record + * @ac_vi: MU AC_VI Parameter Record + * @ac_vo: MU AC_VO Parameter Record + * + * This structure represents the payload of the "MU EDCA Parameter Set + * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. + */ +struct ieee80211_mu_edca_param_set { + u8 mu_qos_info; + struct ieee80211_he_mu_edca_param_ac_rec ac_be; + struct ieee80211_he_mu_edca_param_ac_rec ac_bk; + struct ieee80211_he_mu_edca_param_ac_rec ac_vi; + struct ieee80211_he_mu_edca_param_ac_rec ac_vo; +} __packed; + +/* 802.11ax HE MAC capabilities */ +#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 +#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 +#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 +#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 +#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 + +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 +#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 +#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 +#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 + +/* Link adaptation is split between byte HE_MAC_CAP1 and + * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE + * in which case the following values apply: + * 0 = No feedback. + * 1 = reserved. + * 2 = Unsolicited feedback. + * 3 = both + */ +#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 + +#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 +#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 +#define IEEE80211_HE_MAC_CAP2_TRS 0x04 +#define IEEE80211_HE_MAC_CAP2_BSR 0x08 +#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 +#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 +#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 +#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 + +#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 +#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 + +/* The maximum length of an A-MDPU is defined by the combination of the Maximum + * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the + * same field in the HE capabilities. + */ +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0 0x00 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1 0x08 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2 0x10 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3 0x18 +#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 +#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 +#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 +#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 + +#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 +#define IEEE80211_HE_MAC_CAP4_QTP 0x02 +#define IEEE80211_HE_MAC_CAP4_BQR 0x04 +#define IEEE80211_HE_MAC_CAP4_PSR_RESP 0x08 +#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 +#define IEEE80211_HE_MAC_CAP4_OPS 0x20 +#define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU 0x40 +/* Multi TID agg TX is split between byte #4 and #5 + * The value is a combination of B39,B40,B41 + */ +#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 + +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 +#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 +#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION 0x04 +#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 +#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 +#define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS 0x20 +#define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 +#define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 + +#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 +#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 +#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR 13 + +/* 802.11ax HE PHY capabilities */ +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e + +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 +#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe + +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 +#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f +#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 +#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 +#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 +/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ +#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 + +#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 +#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 +#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 +#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 +#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 + +/* Note that the meaning of UL MU below is different between an AP and a non-AP + * sta, where in the AP case it indicates support for Rx and in the non-AP sta + * case it indicates support for Tx. + */ +#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 +#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 + +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 +#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 +#define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU 0x40 +#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 + +#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 +#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 + +/* Minimal allowed value of Max STS under 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c + +/* Minimal allowed value of Max STS above 80MHz is 3 */ +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 +#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 + +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 +#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 + +#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 +#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 + +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 +#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 +#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB 0x04 +#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB 0x08 +#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 +#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 +#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 + +#define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR 0x01 +#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP 0x02 +#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 +#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 +#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 +#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 + +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 +#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 +#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 +#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 +#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242 0x00 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484 0x40 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996 0x80 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996 0xc0 +#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 +#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 +#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 +#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 +#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 + +#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 + +/* 802.11ax HE TX/RX MCS NSS Support */ +#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) +#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 +#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 + +/* TX/RX HE MCS Support field Highest MCS subfield encoding */ +enum ieee80211_he_highest_mcs_supported_subfield_enc { + HIGHEST_MCS_SUPPORTED_MCS7 = 0, + HIGHEST_MCS_SUPPORTED_MCS8, + HIGHEST_MCS_SUPPORTED_MCS9, + HIGHEST_MCS_SUPPORTED_MCS10, + HIGHEST_MCS_SUPPORTED_MCS11, +}; + +/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ +static inline u8 +ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) +{ + u8 count = 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) + count += 4; + + if (he_cap->phy_cap_info[0] & + IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) + count += 4; + + return count; +} + +/* 802.11ax HE PPE Thresholds */ +#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) +#define IEEE80211_PPE_THRES_NSS_POS (0) +#define IEEE80211_PPE_THRES_NSS_MASK (7) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ + (BIT(5) | BIT(6)) +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 +#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) +#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) +#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) + +/* + * Calculate 802.11ax HE capabilities IE PPE field size + * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* + */ +static inline u8 +ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) +{ + u8 n; + + if ((phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) + return 0; + + n = hweight8(ppe_thres_hdr & + IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); + n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> + IEEE80211_PPE_THRES_NSS_POS)); + + /* + * Each pair is 6 bits, and we need to add the 7 "header" bits to the + * total size. + */ + n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; + n = DIV_ROUND_UP(n, 8); + + return n; +} + +static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; + u8 needed = sizeof(*he_cap_ie_elem); + + if (len < needed) + return false; + + needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); + if (len < needed) + return false; + + if (he_cap_ie_elem->phy_cap_info[6] & + IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { + if (len < needed + 1) + return false; + needed += ieee80211_he_ppe_size(data[needed], + he_cap_ie_elem->phy_cap_info); + } + + return len >= needed; +} + +/* HE Operation defines */ +#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 +#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 +#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 +#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 +#define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 +#define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 +#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 +#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 +#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 + +#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 +#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 +#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD 4 +#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 8 + +/** + * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field + * @primary: primary channel + * @control: control flags + * @ccfs0: channel center frequency segment 0 + * @ccfs1: channel center frequency segment 1 + * @minrate: minimum rate (in 1 Mbps units) + */ +struct ieee80211_he_6ghz_oper { + u8 primary; +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 +#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 +#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 +#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x78 + u8 control; + u8 ccfs0; + u8 ccfs1; + u8 minrate; +} __packed; + +/** + * enum ieee80211_reg_conn_bits - represents Regulatory connectivity field bits. + * + * This enumeration defines bit flags used to represent regulatory connectivity + * field bits. + * + * @IEEE80211_REG_CONN_LPI_VALID: Indicates whether the LPI bit is valid. + * @IEEE80211_REG_CONN_LPI_VALUE: Represents the value of the LPI bit. + * @IEEE80211_REG_CONN_SP_VALID: Indicates whether the SP bit is valid. + * @IEEE80211_REG_CONN_SP_VALUE: Represents the value of the SP bit. + */ +enum ieee80211_reg_conn_bits { + IEEE80211_REG_CONN_LPI_VALID = BIT(0), + IEEE80211_REG_CONN_LPI_VALUE = BIT(1), + IEEE80211_REG_CONN_SP_VALID = BIT(2), + IEEE80211_REG_CONN_SP_VALUE = BIT(3), +}; + +/* transmit power interpretation type of transmit power envelope element */ +enum ieee80211_tx_power_intrpt_type { + IEEE80211_TPE_LOCAL_EIRP, + IEEE80211_TPE_LOCAL_EIRP_PSD, + IEEE80211_TPE_REG_CLIENT_EIRP, + IEEE80211_TPE_REG_CLIENT_EIRP_PSD, +}; + +/* category type of transmit power envelope element */ +enum ieee80211_tx_power_category_6ghz { + IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0, + IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1, +}; + +/* + * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP, + * setting to 63.5 dBm means no constraint. + */ +#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT 127 + +/* + * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD, + * setting to 127 indicates no PSD limit for the 20 MHz channel. + */ +#define IEEE80211_TPE_PSD_NO_LIMIT 127 + +/** + * struct ieee80211_tx_pwr_env - Transmit Power Envelope + * @info: Transmit Power Information field + * @variable: Maximum Transmit Power field + * + * This structure represents the payload of the "Transmit Power + * Envelope element" as described in IEEE Std 802.11ax-2021 section + * 9.4.2.161 + */ +struct ieee80211_tx_pwr_env { + u8 info; + u8 variable[]; +} __packed; + +#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 +#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 +#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 + +#define IEEE80211_TX_PWR_ENV_EXT_COUNT 0xF + +static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len) +{ + const struct ieee80211_tx_pwr_env *env = (const void *)data; + u8 count, interpret, category; + u8 needed = sizeof(*env); + u8 N; /* also called N in the spec */ + + if (len < needed) + return false; + + count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); + interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); + category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); + + switch (category) { + case IEEE80211_TPE_CAT_6GHZ_DEFAULT: + case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE: + break; + default: + return false; + } + + switch (interpret) { + case IEEE80211_TPE_LOCAL_EIRP: + case IEEE80211_TPE_REG_CLIENT_EIRP: + if (count > 3) + return false; + + /* count == 0 encodes 1 value for 20 MHz, etc. */ + needed += count + 1; + + if (len < needed) + return false; + + /* there can be extension fields not accounted for in 'count' */ + + return true; + case IEEE80211_TPE_LOCAL_EIRP_PSD: + case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: + if (count > 4) + return false; + + N = count ? 1 << (count - 1) : 1; + needed += N; + + if (len < needed) + return false; + + if (len > needed) { + u8 K = u8_get_bits(env->variable[N], + IEEE80211_TX_PWR_ENV_EXT_COUNT); + + needed += 1 + K; + if (len < needed) + return false; + } + + return true; + } + + return false; +} + +/* + * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size + * @he_oper_ie: byte data of the He Operations IE, stating from the byte + * after the ext ID byte. It is assumed that he_oper_ie has at least + * sizeof(struct ieee80211_he_operation) bytes, the caller must have + * validated this. + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_oper_size(const u8 *he_oper_ie) +{ + const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; + u8 oper_len = sizeof(struct ieee80211_he_operation); + u32 he_oper_params; + + /* Make sure the input is not NULL */ + if (!he_oper_ie) + return 0; + + /* Calc required length */ + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + oper_len += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) + oper_len++; + if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) + oper_len += sizeof(struct ieee80211_he_6ghz_oper); + + /* Add the first byte (extension ID) to the total length */ + oper_len++; + + return oper_len; +} + +/** + * ieee80211_he_6ghz_oper - obtain 6 GHz operation field + * @he_oper: HE operation element (must be pre-validated for size) + * but may be %NULL + * + * Return: a pointer to the 6 GHz operation field, or %NULL + */ +static inline const struct ieee80211_he_6ghz_oper * +ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) +{ + const u8 *ret; + u32 he_oper_params; + + if (!he_oper) + return NULL; + + ret = (const void *)&he_oper->optional; + + he_oper_params = le32_to_cpu(he_oper->he_oper_params); + + if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) + return NULL; + if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) + ret += 3; + if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) + ret++; + + return (const void *)ret; +} + +/* HE Spatial Reuse defines */ +#define IEEE80211_HE_SPR_PSR_DISALLOWED BIT(0) +#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED BIT(1) +#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT BIT(2) +#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT BIT(3) +#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED BIT(4) + +/* + * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size + * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte + * after the ext ID byte. It is assumed that he_spr_ie has at least + * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated + * this + * @return the actual size of the IE data (not including header), or 0 on error + */ +static inline u8 +ieee80211_he_spr_size(const u8 *he_spr_ie) +{ + const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; + u8 spr_len = sizeof(struct ieee80211_he_spr); + u8 he_spr_params; + + /* Make sure the input is not NULL */ + if (!he_spr_ie) + return 0; + + /* Calc required length */ + he_spr_params = he_spr->he_sr_control; + if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) + spr_len++; + if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) + spr_len += 18; + + /* Add the first byte (extension ID) to the total length */ + spr_len++; + + return spr_len; +} + +struct ieee80211_he_6ghz_capa { + /* uses IEEE80211_HE_6GHZ_CAP_* below */ + __le16 capa; +} __packed; + +/* HE 6 GHz band capabilities */ +/* uses enum ieee80211_min_mpdu_spacing values */ +#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 +/* uses enum ieee80211_vht_max_ampdu_length_exp values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 +/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ +#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 +/* WLAN_HT_CAP_SM_PS_* values */ +#define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 +#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 +#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 +#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 + +#endif /* LINUX_IEEE80211_HE_H */ diff --git a/include/linux/ieee80211-ht.h b/include/linux/ieee80211-ht.h new file mode 100644 index 0000000000000..21bbf470540f6 --- /dev/null +++ b/include/linux/ieee80211-ht.h @@ -0,0 +1,292 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 HT definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_HT_H +#define LINUX_IEEE80211_HT_H + +#include +#include + +/* Maximal size of an A-MSDU that can be transported in a HT BA session */ +#define IEEE80211_MAX_MPDU_LEN_HT_BA 4095 + +/* Maximal size of an A-MSDU */ +#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 +#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 + +#define IEEE80211_HT_CTL_LEN 4 + +enum ieee80211_ht_chanwidth_values { + IEEE80211_HT_CHANWIDTH_20MHZ = 0, + IEEE80211_HT_CHANWIDTH_ANY = 1, +}; + +/** + * struct ieee80211_bar - Block Ack Request frame format + * @frame_control: Frame Control + * @duration: Duration + * @ra: RA + * @ta: TA + * @control: BAR Control + * @start_seq_num: Starting Sequence Number (see Figure 9-37) + * + * This structure represents the "BlockAckReq frame format" + * as described in IEEE Std 802.11-2020 section 9.3.1.7. +*/ +struct ieee80211_bar { + __le16 frame_control; + __le16 duration; + __u8 ra[ETH_ALEN]; + __u8 ta[ETH_ALEN]; + __le16 control; + __le16 start_seq_num; +} __packed; + +/* 802.11 BAR control masks */ +#define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL 0x0000 +#define IEEE80211_BAR_CTRL_MULTI_TID 0x0002 +#define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA 0x0004 +#define IEEE80211_BAR_CTRL_TID_INFO_MASK 0xf000 +#define IEEE80211_BAR_CTRL_TID_INFO_SHIFT 12 + +#define IEEE80211_HT_MCS_MASK_LEN 10 + +/** + * struct ieee80211_mcs_info - Supported MCS Set field + * @rx_mask: RX mask + * @rx_highest: highest supported RX rate. If set represents + * the highest supported RX data rate in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. + * @tx_params: TX parameters + * @reserved: Reserved bits + * + * This structure represents the "Supported MCS Set field" as + * described in IEEE Std 802.11-2020 section 9.4.2.55.4. + */ +struct ieee80211_mcs_info { + u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; + __le16 rx_highest; + u8 tx_params; + u8 reserved[3]; +} __packed; + +/* 802.11n HT capability MSC set */ +#define IEEE80211_HT_MCS_RX_HIGHEST_MASK 0x3ff +#define IEEE80211_HT_MCS_TX_DEFINED 0x01 +#define IEEE80211_HT_MCS_TX_RX_DIFF 0x02 +/* value 0 == 1 stream etc */ +#define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK 0x0C +#define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT 2 +#define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 +#define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 + +#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) + +/* + * 802.11n D5.0 20.3.5 / 20.6 says: + * - indices 0 to 7 and 32 are single spatial stream + * - 8 to 31 are multiple spatial streams using equal modulation + * [8..15 for two streams, 16..23 for three and 24..31 for four] + * - remainder are multiple spatial streams using unequal modulation + */ +#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33 +#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \ + (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) + +/** + * struct ieee80211_ht_cap - HT capabilities element + * @cap_info: HT Capability Information + * @ampdu_params_info: A-MPDU Parameters + * @mcs: Supported MCS Set + * @extended_ht_cap_info: HT Extended Capabilities + * @tx_BF_cap_info: Transmit Beamforming Capabilities + * @antenna_selection_info: ASEL Capability + * + * This structure represents the payload of the "HT Capabilities + * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. + */ +struct ieee80211_ht_cap { + __le16 cap_info; + u8 ampdu_params_info; + + /* 16 bytes MCS information */ + struct ieee80211_mcs_info mcs; + + __le16 extended_ht_cap_info; + __le32 tx_BF_cap_info; + u8 antenna_selection_info; +} __packed; + +/* 802.11n HT capabilities masks (for cap_info) */ +#define IEEE80211_HT_CAP_LDPC_CODING 0x0001 +#define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 +#define IEEE80211_HT_CAP_SM_PS 0x000C +#define IEEE80211_HT_CAP_SM_PS_SHIFT 2 +#define IEEE80211_HT_CAP_GRN_FLD 0x0010 +#define IEEE80211_HT_CAP_SGI_20 0x0020 +#define IEEE80211_HT_CAP_SGI_40 0x0040 +#define IEEE80211_HT_CAP_TX_STBC 0x0080 +#define IEEE80211_HT_CAP_RX_STBC 0x0300 +#define IEEE80211_HT_CAP_RX_STBC_SHIFT 8 +#define IEEE80211_HT_CAP_DELAY_BA 0x0400 +#define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 +#define IEEE80211_HT_CAP_DSSSCCK40 0x1000 +#define IEEE80211_HT_CAP_RESERVED 0x2000 +#define IEEE80211_HT_CAP_40MHZ_INTOLERANT 0x4000 +#define IEEE80211_HT_CAP_LSIG_TXOP_PROT 0x8000 + +/* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */ +#define IEEE80211_HT_EXT_CAP_PCO 0x0001 +#define IEEE80211_HT_EXT_CAP_PCO_TIME 0x0006 +#define IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT 1 +#define IEEE80211_HT_EXT_CAP_MCS_FB 0x0300 +#define IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT 8 +#define IEEE80211_HT_EXT_CAP_HTC_SUP 0x0400 +#define IEEE80211_HT_EXT_CAP_RD_RESPONDER 0x0800 + +/* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ +#define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 +#define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C +#define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 + +/* + * Maximum length of AMPDU that the STA can receive in high-throughput (HT). + * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) + */ +enum ieee80211_max_ampdu_length_exp { + IEEE80211_HT_MAX_AMPDU_8K = 0, + IEEE80211_HT_MAX_AMPDU_16K = 1, + IEEE80211_HT_MAX_AMPDU_32K = 2, + IEEE80211_HT_MAX_AMPDU_64K = 3 +}; + +#define IEEE80211_HT_MAX_AMPDU_FACTOR 13 + +/* Minimum MPDU start spacing */ +enum ieee80211_min_mpdu_spacing { + IEEE80211_HT_MPDU_DENSITY_NONE = 0, /* No restriction */ + IEEE80211_HT_MPDU_DENSITY_0_25 = 1, /* 1/4 usec */ + IEEE80211_HT_MPDU_DENSITY_0_5 = 2, /* 1/2 usec */ + IEEE80211_HT_MPDU_DENSITY_1 = 3, /* 1 usec */ + IEEE80211_HT_MPDU_DENSITY_2 = 4, /* 2 usec */ + IEEE80211_HT_MPDU_DENSITY_4 = 5, /* 4 usec */ + IEEE80211_HT_MPDU_DENSITY_8 = 6, /* 8 usec */ + IEEE80211_HT_MPDU_DENSITY_16 = 7 /* 16 usec */ +}; + +/** + * struct ieee80211_ht_operation - HT operation IE + * @primary_chan: Primary Channel + * @ht_param: HT Operation Information parameters + * @operation_mode: HT Operation Information operation mode + * @stbc_param: HT Operation Information STBC params + * @basic_set: Basic HT-MCS Set + * + * This structure represents the payload of the "HT Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. + */ +struct ieee80211_ht_operation { + u8 primary_chan; + u8 ht_param; + __le16 operation_mode; + __le16 stbc_param; + u8 basic_set[16]; +} __packed; + +/* for ht_param */ +#define IEEE80211_HT_PARAM_CHA_SEC_OFFSET 0x03 +#define IEEE80211_HT_PARAM_CHA_SEC_NONE 0x00 +#define IEEE80211_HT_PARAM_CHA_SEC_ABOVE 0x01 +#define IEEE80211_HT_PARAM_CHA_SEC_BELOW 0x03 +#define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY 0x04 +#define IEEE80211_HT_PARAM_RIFS_MODE 0x08 + +/* for operation_mode */ +#define IEEE80211_HT_OP_MODE_PROTECTION 0x0003 +#define IEEE80211_HT_OP_MODE_PROTECTION_NONE 0 +#define IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER 1 +#define IEEE80211_HT_OP_MODE_PROTECTION_20MHZ 2 +#define IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED 3 +#define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT 0x0004 +#define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT 0x0010 +#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT 5 +#define IEEE80211_HT_OP_MODE_CCFS2_MASK 0x1fe0 + +/* for stbc_param */ +#define IEEE80211_HT_STBC_PARAM_DUAL_BEACON 0x0040 +#define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT 0x0080 +#define IEEE80211_HT_STBC_PARAM_STBC_BEACON 0x0100 +#define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT 0x0200 +#define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE 0x0400 +#define IEEE80211_HT_STBC_PARAM_PCO_PHASE 0x0800 + + +/* block-ack parameters */ +#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 +#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 +#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C +#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 +#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000 +#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 + +/* + * A-MPDU buffer sizes + * According to HT size varies from 8 to 64 frames + * HE adds the ability to have up to 256 frames. + * EHT adds the ability to have up to 1K frames. + */ +#define IEEE80211_MIN_AMPDU_BUF 0x8 +#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 +#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 +#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 + + +/* Spatial Multiplexing Power Save Modes (for capability) */ +#define WLAN_HT_CAP_SM_PS_STATIC 0 +#define WLAN_HT_CAP_SM_PS_DYNAMIC 1 +#define WLAN_HT_CAP_SM_PS_INVALID 2 +#define WLAN_HT_CAP_SM_PS_DISABLED 3 + +/* for SM power control field lower two bits */ +#define WLAN_HT_SMPS_CONTROL_DISABLED 0 +#define WLAN_HT_SMPS_CONTROL_STATIC 1 +#define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 + +/* HT action codes */ +enum ieee80211_ht_actioncode { + WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, + WLAN_HT_ACTION_SMPS = 1, + WLAN_HT_ACTION_PSMP = 2, + WLAN_HT_ACTION_PCO_PHASE = 3, + WLAN_HT_ACTION_CSI = 4, + WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, + WLAN_HT_ACTION_COMPRESSED_BF = 6, + WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, +}; + +/* BACK action code */ +enum ieee80211_back_actioncode { + WLAN_ACTION_ADDBA_REQ = 0, + WLAN_ACTION_ADDBA_RESP = 1, + WLAN_ACTION_DELBA = 2, +}; + +/* BACK (block-ack) parties */ +enum ieee80211_back_parties { + WLAN_BACK_RECIPIENT = 0, + WLAN_BACK_INITIATOR = 1, +}; + +#endif /* LINUX_IEEE80211_HT_H */ diff --git a/include/linux/ieee80211-mesh.h b/include/linux/ieee80211-mesh.h new file mode 100644 index 0000000000000..4b829bcb38b61 --- /dev/null +++ b/include/linux/ieee80211-mesh.h @@ -0,0 +1,230 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 mesh definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_MESH_H +#define LINUX_IEEE80211_MESH_H + +#include +#include + +#define IEEE80211_MAX_MESH_ID_LEN 32 + +struct ieee80211s_hdr { + u8 flags; + u8 ttl; + __le32 seqnum; + u8 eaddr1[ETH_ALEN]; + u8 eaddr2[ETH_ALEN]; +} __packed __aligned(2); + +/* Mesh flags */ +#define MESH_FLAGS_AE_A4 0x1 +#define MESH_FLAGS_AE_A5_A6 0x2 +#define MESH_FLAGS_AE 0x3 +#define MESH_FLAGS_PS_DEEP 0x4 + +/** + * enum ieee80211_preq_flags - mesh PREQ element flags + * + * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield + */ +enum ieee80211_preq_flags { + IEEE80211_PREQ_PROACTIVE_PREP_FLAG = 1<<2, +}; + +/** + * enum ieee80211_preq_target_flags - mesh PREQ element per target flags + * + * @IEEE80211_PREQ_TO_FLAG: target only subfield + * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield + */ +enum ieee80211_preq_target_flags { + IEEE80211_PREQ_TO_FLAG = 1<<0, + IEEE80211_PREQ_USN_FLAG = 1<<2, +}; + +/** + * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE + * @mesh_ttl: Time To Live + * @mesh_flags: Flags + * @mesh_reason: Reason Code + * @mesh_pre_value: Precedence Value + * + * This structure represents the payload of the "Mesh Channel Switch + * Parameters element" as described in IEEE Std 802.11-2020 section + * 9.4.2.102. + */ +struct ieee80211_mesh_chansw_params_ie { + u8 mesh_ttl; + u8 mesh_flags; + __le16 mesh_reason; + __le16 mesh_pre_value; +} __packed; + +/** + * struct ieee80211_meshconf_ie - Mesh Configuration element + * @meshconf_psel: Active Path Selection Protocol Identifier + * @meshconf_pmetric: Active Path Selection Metric Identifier + * @meshconf_congest: Congestion Control Mode Identifier + * @meshconf_synch: Synchronization Method Identifier + * @meshconf_auth: Authentication Protocol Identifier + * @meshconf_form: Mesh Formation Info + * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) + * + * This structure represents the payload of the "Mesh Configuration + * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. + */ +struct ieee80211_meshconf_ie { + u8 meshconf_psel; + u8 meshconf_pmetric; + u8 meshconf_congest; + u8 meshconf_synch; + u8 meshconf_auth; + u8 meshconf_form; + u8 meshconf_cap; +} __packed; + +/** + * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags + * + * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish + * additional mesh peerings with other mesh STAs + * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs + * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure + * is ongoing + * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has + * neighbors in deep sleep mode + * + * Enumerates the "Mesh Capability" as described in IEEE Std + * 802.11-2020 section 9.4.2.97.7. + */ +enum mesh_config_capab_flags { + IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, + IEEE80211_MESHCONF_CAPAB_FORWARDING = 0x08, + IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING = 0x20, + IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL = 0x40, +}; + +#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 + +/* + * mesh channel switch parameters element's flag indicator + * + */ +#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0) +#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1) +#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) + +/** + * struct ieee80211_rann_ie - RANN (root announcement) element + * @rann_flags: Flags + * @rann_hopcount: Hop Count + * @rann_ttl: Element TTL + * @rann_addr: Root Mesh STA Address + * @rann_seq: HWMP Sequence Number + * @rann_interval: Interval + * @rann_metric: Metric + * + * This structure represents the payload of the "RANN element" as + * described in IEEE Std 802.11-2020 section 9.4.2.111. + */ +struct ieee80211_rann_ie { + u8 rann_flags; + u8 rann_hopcount; + u8 rann_ttl; + u8 rann_addr[ETH_ALEN]; + __le32 rann_seq; + __le32 rann_interval; + __le32 rann_metric; +} __packed; + +enum ieee80211_rann_flags { + RANN_FLAG_IS_GATE = 1 << 0, +}; + +/* Mesh action codes */ +enum ieee80211_mesh_actioncode { + WLAN_MESH_ACTION_LINK_METRIC_REPORT, + WLAN_MESH_ACTION_HWMP_PATH_SELECTION, + WLAN_MESH_ACTION_GATE_ANNOUNCEMENT, + WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION, + WLAN_MESH_ACTION_MCCA_SETUP_REQUEST, + WLAN_MESH_ACTION_MCCA_SETUP_REPLY, + WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST, + WLAN_MESH_ACTION_MCCA_ADVERTISEMENT, + WLAN_MESH_ACTION_MCCA_TEARDOWN, + WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST, + WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE, +}; + +/** + * enum ieee80211_mesh_sync_method - mesh synchronization method identifier + * + * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method + * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method + * that will be specified in a vendor specific information element + */ +enum ieee80211_mesh_sync_method { + IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, + IEEE80211_SYNC_METHOD_VENDOR = 255, +}; + +/** + * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier + * + * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol + * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will + * be specified in a vendor specific information element + */ +enum ieee80211_mesh_path_protocol { + IEEE80211_PATH_PROTOCOL_HWMP = 1, + IEEE80211_PATH_PROTOCOL_VENDOR = 255, +}; + +/** + * enum ieee80211_mesh_path_metric - mesh path selection metric identifier + * + * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric + * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be + * specified in a vendor specific information element + */ +enum ieee80211_mesh_path_metric { + IEEE80211_PATH_METRIC_AIRTIME = 1, + IEEE80211_PATH_METRIC_VENDOR = 255, +}; + +/** + * enum ieee80211_root_mode_identifier - root mesh STA mode identifier + * + * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode + * + * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default) + * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than + * this value + * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports + * the proactive PREQ with proactive PREP subfield set to 0 + * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA + * supports the proactive PREQ with proactive PREP subfield set to 1 + * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports + * the proactive RANN + */ +enum ieee80211_root_mode_identifier { + IEEE80211_ROOTMODE_NO_ROOT = 0, + IEEE80211_ROOTMODE_ROOT = 1, + IEEE80211_PROACTIVE_PREQ_NO_PREP = 2, + IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3, + IEEE80211_PROACTIVE_RANN = 4, +}; + +#endif /* LINUX_IEEE80211_MESH_H */ diff --git a/include/linux/ieee80211-nan.h b/include/linux/ieee80211-nan.h new file mode 100644 index 0000000000000..d07959bf8a90a --- /dev/null +++ b/include/linux/ieee80211-nan.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * WFA NAN definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_NAN_H +#define LINUX_IEEE80211_NAN_H + +/* NAN operation mode, as defined in Wi-Fi Aware (TM) specification Table 81 */ +#define NAN_OP_MODE_PHY_MODE_VHT 0x01 +#define NAN_OP_MODE_PHY_MODE_HE 0x10 +#define NAN_OP_MODE_PHY_MODE_MASK 0x11 +#define NAN_OP_MODE_80P80MHZ 0x02 +#define NAN_OP_MODE_160MHZ 0x04 +#define NAN_OP_MODE_PNDL_SUPPRTED 0x08 + +/* NAN Device capabilities, as defined in Wi-Fi Aware (TM) specification + * Table 79 + */ +#define NAN_DEV_CAPA_DFS_OWNER 0x01 +#define NAN_DEV_CAPA_EXT_KEY_ID_SUPPORTED 0x02 +#define NAN_DEV_CAPA_SIM_NDP_RX_SUPPORTED 0x04 +#define NAN_DEV_CAPA_NDPE_SUPPORTED 0x08 +#define NAN_DEV_CAPA_S3_SUPPORTED 0x10 + +#endif /* LINUX_IEEE80211_NAN_H */ diff --git a/include/linux/ieee80211-p2p.h b/include/linux/ieee80211-p2p.h new file mode 100644 index 0000000000000..180891c11f087 --- /dev/null +++ b/include/linux/ieee80211-p2p.h @@ -0,0 +1,71 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * WFA P2P definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_P2P_H +#define LINUX_IEEE80211_P2P_H + +#include +/* + * Peer-to-Peer IE attribute related definitions. + */ +/* + * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute. + */ +enum ieee80211_p2p_attr_id { + IEEE80211_P2P_ATTR_STATUS = 0, + IEEE80211_P2P_ATTR_MINOR_REASON, + IEEE80211_P2P_ATTR_CAPABILITY, + IEEE80211_P2P_ATTR_DEVICE_ID, + IEEE80211_P2P_ATTR_GO_INTENT, + IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT, + IEEE80211_P2P_ATTR_LISTEN_CHANNEL, + IEEE80211_P2P_ATTR_GROUP_BSSID, + IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING, + IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR, + IEEE80211_P2P_ATTR_MANAGABILITY, + IEEE80211_P2P_ATTR_CHANNEL_LIST, + IEEE80211_P2P_ATTR_ABSENCE_NOTICE, + IEEE80211_P2P_ATTR_DEVICE_INFO, + IEEE80211_P2P_ATTR_GROUP_INFO, + IEEE80211_P2P_ATTR_GROUP_ID, + IEEE80211_P2P_ATTR_INTERFACE, + IEEE80211_P2P_ATTR_OPER_CHANNEL, + IEEE80211_P2P_ATTR_INVITE_FLAGS, + /* 19 - 220: Reserved */ + IEEE80211_P2P_ATTR_VENDOR_SPECIFIC = 221, + + IEEE80211_P2P_ATTR_MAX +}; + +/* Notice of Absence attribute - described in P2P spec 4.1.14 */ +/* Typical max value used here */ +#define IEEE80211_P2P_NOA_DESC_MAX 4 + +struct ieee80211_p2p_noa_desc { + u8 count; + __le32 duration; + __le32 interval; + __le32 start_time; +} __packed; + +struct ieee80211_p2p_noa_attr { + u8 index; + u8 oppps_ctwindow; + struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX]; +} __packed; + +#define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) +#define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F + +#endif /* LINUX_IEEE80211_P2P_H */ diff --git a/include/linux/ieee80211-s1g.h b/include/linux/ieee80211-s1g.h new file mode 100644 index 0000000000000..5b9ed2dcc00e0 --- /dev/null +++ b/include/linux/ieee80211-s1g.h @@ -0,0 +1,575 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 S1G definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_S1G_H +#define LINUX_IEEE80211_S1G_H + +#include +#include + +/* bits unique to S1G beacon frame control */ +#define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 +#define IEEE80211_S1G_BCN_CSSID 0x200 +#define IEEE80211_S1G_BCN_ANO 0x400 + +/* see 802.11ah-2016 9.9 NDP CMAC frames */ +#define IEEE80211_S1G_1MHZ_NDP_BITS 25 +#define IEEE80211_S1G_1MHZ_NDP_BYTES 4 +#define IEEE80211_S1G_2MHZ_NDP_BITS 37 +#define IEEE80211_S1G_2MHZ_NDP_BYTES 5 + +/** + * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && + * IEEE80211_STYPE_S1G_BEACON + * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame is an S1G beacon + */ +static inline bool ieee80211_is_s1g_beacon(__le16 fc) +{ + return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | + IEEE80211_FCTL_STYPE)) == + cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON); +} + +/** + * ieee80211_s1g_has_next_tbtt - check if IEEE80211_S1G_BCN_NEXT_TBTT + * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame contains the variable-length + * next TBTT field + */ +static inline bool ieee80211_s1g_has_next_tbtt(__le16 fc) +{ + return ieee80211_is_s1g_beacon(fc) && + (fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT)); +} + +/** + * ieee80211_s1g_has_ano - check if IEEE80211_S1G_BCN_ANO + * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame contains the variable-length + * ANO field + */ +static inline bool ieee80211_s1g_has_ano(__le16 fc) +{ + return ieee80211_is_s1g_beacon(fc) && + (fc & cpu_to_le16(IEEE80211_S1G_BCN_ANO)); +} + +/** + * ieee80211_s1g_has_cssid - check if IEEE80211_S1G_BCN_CSSID + * @fc: frame control bytes in little-endian byteorder + * Return: whether or not the frame contains the variable-length + * compressed SSID field + */ +static inline bool ieee80211_s1g_has_cssid(__le16 fc) +{ + return ieee80211_is_s1g_beacon(fc) && + (fc & cpu_to_le16(IEEE80211_S1G_BCN_CSSID)); +} + +/** + * enum ieee80211_s1g_chanwidth - S1G channel widths + * These are defined in IEEE802.11-2016ah Table 10-20 + * as BSS Channel Width + * + * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel + * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel + */ +enum ieee80211_s1g_chanwidth { + IEEE80211_S1G_CHANWIDTH_1MHZ = 0, + IEEE80211_S1G_CHANWIDTH_2MHZ = 1, + IEEE80211_S1G_CHANWIDTH_4MHZ = 3, + IEEE80211_S1G_CHANWIDTH_8MHZ = 7, + IEEE80211_S1G_CHANWIDTH_16MHZ = 15, +}; + +/** + * enum ieee80211_s1g_pri_chanwidth - S1G primary channel widths + * described in IEEE80211-2024 Table 10-39. + * + * @IEEE80211_S1G_PRI_CHANWIDTH_2MHZ: 2MHz primary channel + * @IEEE80211_S1G_PRI_CHANWIDTH_1MHZ: 1MHz primary channel + */ +enum ieee80211_s1g_pri_chanwidth { + IEEE80211_S1G_PRI_CHANWIDTH_2MHZ = 0, + IEEE80211_S1G_PRI_CHANWIDTH_1MHZ = 1, +}; + +/** + * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element + * @compat_info: Compatibility Information + * @beacon_int: Beacon Interval + * @tsf_completion: TSF Completion + * + * This structure represents the payload of the "S1G Beacon + * Compatibility element" as described in IEEE Std 802.11-2020 section + * 9.4.2.196. + */ +struct ieee80211_s1g_bcn_compat_ie { + __le16 compat_info; + __le16 beacon_int; + __le32 tsf_completion; +} __packed; + +/** + * struct ieee80211_s1g_oper_ie - S1G Operation element + * @ch_width: S1G Operation Information Channel Width + * @oper_class: S1G Operation Information Operating Class + * @primary_ch: S1G Operation Information Primary Channel Number + * @oper_ch: S1G Operation Information Channel Center Frequency + * @basic_mcs_nss: Basic S1G-MCS and NSS Set + * + * This structure represents the payload of the "S1G Operation + * element" as described in IEEE Std 802.11-2020 section 9.4.2.212. + */ +struct ieee80211_s1g_oper_ie { + u8 ch_width; + u8 oper_class; + u8 primary_ch; + u8 oper_ch; + __le16 basic_mcs_nss; +} __packed; + +/** + * struct ieee80211_aid_response_ie - AID Response element + * @aid: AID/Group AID + * @switch_count: AID Switch Count + * @response_int: AID Response Interval + * + * This structure represents the payload of the "AID Response element" + * as described in IEEE Std 802.11-2020 section 9.4.2.194. + */ +struct ieee80211_aid_response_ie { + __le16 aid; + u8 switch_count; + __le16 response_int; +} __packed; + +struct ieee80211_s1g_cap { + u8 capab_info[10]; + u8 supp_mcs_nss[5]; +} __packed; + +/** + * ieee80211_s1g_optional_len - determine length of optional S1G beacon fields + * @fc: frame control bytes in little-endian byteorder + * Return: total length in bytes of the optional fixed-length fields + * + * S1G beacons may contain up to three optional fixed-length fields that + * precede the variable-length elements. Whether these fields are present + * is indicated by flags in the frame control field. + * + * From IEEE 802.11-2024 section 9.3.4.3: + * - Next TBTT field may be 0 or 3 bytes + * - Short SSID field may be 0 or 4 bytes + * - Access Network Options (ANO) field may be 0 or 1 byte + */ +static inline size_t +ieee80211_s1g_optional_len(__le16 fc) +{ + size_t len = 0; + + if (ieee80211_s1g_has_next_tbtt(fc)) + len += 3; + + if (ieee80211_s1g_has_cssid(fc)) + len += 4; + + if (ieee80211_s1g_has_ano(fc)) + len += 1; + + return len; +} + +/* S1G Capabilities Information field */ +#define IEEE80211_S1G_CAPABILITY_LEN 15 + +#define S1G_CAP0_S1G_LONG BIT(0) +#define S1G_CAP0_SGI_1MHZ BIT(1) +#define S1G_CAP0_SGI_2MHZ BIT(2) +#define S1G_CAP0_SGI_4MHZ BIT(3) +#define S1G_CAP0_SGI_8MHZ BIT(4) +#define S1G_CAP0_SGI_16MHZ BIT(5) +#define S1G_CAP0_SUPP_CH_WIDTH GENMASK(7, 6) + +#define S1G_SUPP_CH_WIDTH_2 0 +#define S1G_SUPP_CH_WIDTH_4 1 +#define S1G_SUPP_CH_WIDTH_8 2 +#define S1G_SUPP_CH_WIDTH_16 3 +#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \ + cap[0])) << 1) + +#define S1G_CAP1_RX_LDPC BIT(0) +#define S1G_CAP1_TX_STBC BIT(1) +#define S1G_CAP1_RX_STBC BIT(2) +#define S1G_CAP1_SU_BFER BIT(3) +#define S1G_CAP1_SU_BFEE BIT(4) +#define S1G_CAP1_BFEE_STS GENMASK(7, 5) + +#define S1G_CAP2_SOUNDING_DIMENSIONS GENMASK(2, 0) +#define S1G_CAP2_MU_BFER BIT(3) +#define S1G_CAP2_MU_BFEE BIT(4) +#define S1G_CAP2_PLUS_HTC_VHT BIT(5) +#define S1G_CAP2_TRAVELING_PILOT GENMASK(7, 6) + +#define S1G_CAP3_RD_RESPONDER BIT(0) +#define S1G_CAP3_HT_DELAYED_BA BIT(1) +#define S1G_CAP3_MAX_MPDU_LEN BIT(2) +#define S1G_CAP3_MAX_AMPDU_LEN_EXP GENMASK(4, 3) +#define S1G_CAP3_MIN_MPDU_START GENMASK(7, 5) + +#define S1G_CAP4_UPLINK_SYNC BIT(0) +#define S1G_CAP4_DYNAMIC_AID BIT(1) +#define S1G_CAP4_BAT BIT(2) +#define S1G_CAP4_TIME_ADE BIT(3) +#define S1G_CAP4_NON_TIM BIT(4) +#define S1G_CAP4_GROUP_AID BIT(5) +#define S1G_CAP4_STA_TYPE GENMASK(7, 6) + +#define S1G_CAP5_CENT_AUTH_CONTROL BIT(0) +#define S1G_CAP5_DIST_AUTH_CONTROL BIT(1) +#define S1G_CAP5_AMSDU BIT(2) +#define S1G_CAP5_AMPDU BIT(3) +#define S1G_CAP5_ASYMMETRIC_BA BIT(4) +#define S1G_CAP5_FLOW_CONTROL BIT(5) +#define S1G_CAP5_SECTORIZED_BEAM GENMASK(7, 6) + +#define S1G_CAP6_OBSS_MITIGATION BIT(0) +#define S1G_CAP6_FRAGMENT_BA BIT(1) +#define S1G_CAP6_NDP_PS_POLL BIT(2) +#define S1G_CAP6_RAW_OPERATION BIT(3) +#define S1G_CAP6_PAGE_SLICING BIT(4) +#define S1G_CAP6_TXOP_SHARING_IMP_ACK BIT(5) +#define S1G_CAP6_VHT_LINK_ADAPT GENMASK(7, 6) + +#define S1G_CAP7_TACK_AS_PS_POLL BIT(0) +#define S1G_CAP7_DUP_1MHZ BIT(1) +#define S1G_CAP7_MCS_NEGOTIATION BIT(2) +#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) +#define S1G_CAP7_NDP_BFING_REPORT_POLL BIT(4) +#define S1G_CAP7_UNSOLICITED_DYN_AID BIT(5) +#define S1G_CAP7_SECTOR_TRAINING_OPERATION BIT(6) +#define S1G_CAP7_TEMP_PS_MODE_SWITCH BIT(7) + +#define S1G_CAP8_TWT_GROUPING BIT(0) +#define S1G_CAP8_BDT BIT(1) +#define S1G_CAP8_COLOR GENMASK(4, 2) +#define S1G_CAP8_TWT_REQUEST BIT(5) +#define S1G_CAP8_TWT_RESPOND BIT(6) +#define S1G_CAP8_PV1_FRAME BIT(7) + +#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) + +#define S1G_OPER_CH_WIDTH_PRIMARY BIT(0) +#define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) +#define S1G_OPER_CH_PRIMARY_LOCATION BIT(5) + +#define S1G_2M_PRIMARY_LOCATION_LOWER 0 +#define S1G_2M_PRIMARY_LOCATION_UPPER 1 + +#define LISTEN_INT_USF GENMASK(15, 14) +#define LISTEN_INT_UI GENMASK(13, 0) + +#define IEEE80211_MAX_USF FIELD_MAX(LISTEN_INT_USF) +#define IEEE80211_MAX_UI FIELD_MAX(LISTEN_INT_UI) + +/* S1G encoding types */ +#define IEEE80211_S1G_TIM_ENC_MODE_BLOCK 0 +#define IEEE80211_S1G_TIM_ENC_MODE_SINGLE 1 +#define IEEE80211_S1G_TIM_ENC_MODE_OLB 2 + +enum ieee80211_s1g_actioncode { + WLAN_S1G_AID_SWITCH_REQUEST, + WLAN_S1G_AID_SWITCH_RESPONSE, + WLAN_S1G_SYNC_CONTROL, + WLAN_S1G_STA_INFO_ANNOUNCE, + WLAN_S1G_EDCA_PARAM_SET, + WLAN_S1G_EL_OPERATION, + WLAN_S1G_TWT_SETUP, + WLAN_S1G_TWT_TEARDOWN, + WLAN_S1G_SECT_GROUP_ID_LIST, + WLAN_S1G_SECT_ID_FEEDBACK, + WLAN_S1G_TWT_INFORMATION = 11, +}; + +/** + * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon + * @fc: frame control bytes in little-endian byteorder + * @variable: pointer to the beacon frame elements + * @variable_len: length of the frame elements + * Return: whether or not the frame is an S1G short beacon. As per + * IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall + * always be present as the first element in beacon frames generated at a + * TBTT (Target Beacon Transmission Time), so any frame not containing + * this element must have been generated at a TSBTT (Target Short Beacon + * Transmission Time) that is not a TBTT. Additionally, short beacons are + * prohibited from containing the S1G beacon compatibility element as per + * IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with + * either no elements or the first element is not the beacon compatibility + * element, we have a short beacon. + */ +static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable, + size_t variable_len) +{ + if (!ieee80211_is_s1g_beacon(fc)) + return false; + + /* + * If the frame does not contain at least 1 element (this is perfectly + * valid in a short beacon) and is an S1G beacon, we have a short + * beacon. + */ + if (variable_len < 2) + return true; + + return variable[0] != WLAN_EID_S1G_BCN_COMPAT; +} + +struct s1g_tim_aid { + u16 aid; + u8 target_blk; /* Target block index */ + u8 target_subblk; /* Target subblock index */ + u8 target_subblk_bit; /* Target subblock bit */ +}; + +struct s1g_tim_enc_block { + u8 enc_mode; + bool inverse; + const u8 *ptr; + u8 len; + + /* + * For an OLB encoded block that spans multiple blocks, this + * is the offset into the span described by that encoded block. + */ + u8 olb_blk_offset; +}; + +/* + * Helper routines to quickly extract the length of an encoded block. Validation + * is also performed to ensure the length extracted lies within the TIM. + */ + +static inline int ieee80211_s1g_len_bitmap(const u8 *ptr, const u8 *end) +{ + u8 blkmap; + u8 n_subblks; + + if (ptr >= end) + return -EINVAL; + + blkmap = *ptr; + n_subblks = hweight8(blkmap); + + if (ptr + 1 + n_subblks > end) + return -EINVAL; + + return 1 + n_subblks; +} + +static inline int ieee80211_s1g_len_single(const u8 *ptr, const u8 *end) +{ + return (ptr + 1 > end) ? -EINVAL : 1; +} + +static inline int ieee80211_s1g_len_olb(const u8 *ptr, const u8 *end) +{ + if (ptr >= end) + return -EINVAL; + + return (ptr + 1 + *ptr > end) ? -EINVAL : 1 + *ptr; +} + +/* + * Enumerate all encoded blocks until we find the encoded block that describes + * our target AID. OLB is a special case as a single encoded block can describe + * multiple blocks as a single encoded block. + */ +static inline int ieee80211_s1g_find_target_block(struct s1g_tim_enc_block *enc, + const struct s1g_tim_aid *aid, + const u8 *ptr, const u8 *end) +{ + /* need at least block-control octet */ + while (ptr + 1 <= end) { + u8 ctrl = *ptr++; + u8 mode = ctrl & 0x03; + bool contains, inverse = ctrl & BIT(2); + u8 span, blk_off = ctrl >> 3; + int len; + + switch (mode) { + case IEEE80211_S1G_TIM_ENC_MODE_BLOCK: + len = ieee80211_s1g_len_bitmap(ptr, end); + contains = blk_off == aid->target_blk; + break; + case IEEE80211_S1G_TIM_ENC_MODE_SINGLE: + len = ieee80211_s1g_len_single(ptr, end); + contains = blk_off == aid->target_blk; + break; + case IEEE80211_S1G_TIM_ENC_MODE_OLB: + len = ieee80211_s1g_len_olb(ptr, end); + /* + * An OLB encoded block can describe more then one + * block, meaning an encoded OLB block can span more + * then a single block. + */ + if (len > 0) { + /* Minus one for the length octet */ + span = DIV_ROUND_UP(len - 1, 8); + /* + * Check if our target block lies within the + * block span described by this encoded block. + */ + contains = (aid->target_blk >= blk_off) && + (aid->target_blk < blk_off + span); + } + break; + default: + return -EOPNOTSUPP; + } + + if (len < 0) + return len; + + if (contains) { + enc->enc_mode = mode; + enc->inverse = inverse; + enc->ptr = ptr; + enc->len = (u8)len; + enc->olb_blk_offset = blk_off; + return 0; + } + + ptr += len; + } + + return -ENOENT; +} + +static inline bool ieee80211_s1g_parse_bitmap(struct s1g_tim_enc_block *enc, + struct s1g_tim_aid *aid) +{ + const u8 *ptr = enc->ptr; + u8 blkmap = *ptr++; + + /* + * If our block bitmap does not contain a set bit that corresponds + * to our AID, it could mean a variety of things depending on if + * the encoding mode is inverted or not. + * + * 1. If inverted, it means the entire subblock is present and hence + * our AID has been set. + * 2. If not inverted, it means our subblock is not present and hence + * it is all zero meaning our AID is not set. + */ + if (!(blkmap & BIT(aid->target_subblk))) + return enc->inverse; + + /* + * Increment ptr by the number of set subblocks that appear before our + * target subblock. If our target subblock is 0, do nothing as ptr + * already points to our target subblock. + */ + if (aid->target_subblk) + ptr += hweight8(blkmap & GENMASK(aid->target_subblk - 1, 0)); + + return !!(*ptr & BIT(aid->target_subblk_bit)) ^ enc->inverse; +} + +static inline bool ieee80211_s1g_parse_single(struct s1g_tim_enc_block *enc, + struct s1g_tim_aid *aid) +{ + /* + * Single AID mode describes, as the name suggests, a single AID + * within the block described by the encoded block. The octet + * contains the 6 LSBs of the AID described in the block. The other + * 2 bits are reserved. When inversed, every single AID described + * by the current block have buffered traffic except for the AID + * described in the single AID octet. + */ + return ((*enc->ptr & 0x3f) == (aid->aid & 0x3f)) ^ enc->inverse; +} + +static inline bool ieee80211_s1g_parse_olb(struct s1g_tim_enc_block *enc, + struct s1g_tim_aid *aid) +{ + const u8 *ptr = enc->ptr; + u8 blk_len = *ptr++; + /* + * Given an OLB encoded block that describes multiple blocks, + * calculate the offset into the span. Then calculate the + * subblock location normally. + */ + u16 span_offset = aid->target_blk - enc->olb_blk_offset; + u16 subblk_idx = span_offset * 8 + aid->target_subblk; + + if (subblk_idx >= blk_len) + return enc->inverse; + + return !!(ptr[subblk_idx] & BIT(aid->target_subblk_bit)) ^ enc->inverse; +} + +/* + * An S1G PVB has 3 non optional encoding types, each that can be inverted. + * An S1G PVB is constructed with zero or more encoded block subfields. Each + * encoded block represents a single "block" of AIDs (64), and each encoded + * block can contain one of the 3 encoding types alongside a single bit for + * whether the bits should be inverted. + * + * As the standard makes no guarantee about the ordering of encoded blocks, + * we must parse every encoded block in the worst case scenario given an + * AID that lies within the last block. + */ +static inline bool ieee80211_s1g_check_tim(const struct ieee80211_tim_ie *tim, + u8 tim_len, u16 aid) +{ + int err; + struct s1g_tim_aid target_aid; + struct s1g_tim_enc_block enc_blk; + + if (tim_len < 3) + return false; + + target_aid.aid = aid; + target_aid.target_blk = (aid >> 6) & 0x1f; + target_aid.target_subblk = (aid >> 3) & 0x7; + target_aid.target_subblk_bit = aid & 0x7; + + /* + * Find our AIDs target encoded block and fill &enc_blk with the + * encoded blocks information. If no entry is found or an error + * occurs return false. + */ + err = ieee80211_s1g_find_target_block(&enc_blk, &target_aid, + tim->virtual_map, + (const u8 *)tim + tim_len + 2); + if (err) + return false; + + switch (enc_blk.enc_mode) { + case IEEE80211_S1G_TIM_ENC_MODE_BLOCK: + return ieee80211_s1g_parse_bitmap(&enc_blk, &target_aid); + case IEEE80211_S1G_TIM_ENC_MODE_SINGLE: + return ieee80211_s1g_parse_single(&enc_blk, &target_aid); + case IEEE80211_S1G_TIM_ENC_MODE_OLB: + return ieee80211_s1g_parse_olb(&enc_blk, &target_aid); + default: + return false; + } +} + +#endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/ieee80211-vht.h b/include/linux/ieee80211-vht.h new file mode 100644 index 0000000000000..898dfb561fef2 --- /dev/null +++ b/include/linux/ieee80211-vht.h @@ -0,0 +1,236 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * IEEE 802.11 VHT definitions + * + * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen + * + * Copyright (c) 2002-2003, Jouni Malinen + * Copyright (c) 2005, Devicescape Software, Inc. + * Copyright (c) 2006, Michael Wu + * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH + * Copyright (c) 2016 - 2017 Intel Deutschland GmbH + * Copyright (c) 2018 - 2025 Intel Corporation + */ + +#ifndef LINUX_IEEE80211_VHT_H +#define LINUX_IEEE80211_VHT_H + +#include +#include + +#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 +#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 +#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 + +/** + * enum ieee80211_vht_opmode_bits - VHT operating mode field bits + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width + * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width + * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag + * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask + * (the NSS value is the value of this field + 1) + * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift + * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU + * using a beamforming steering matrix + */ +enum ieee80211_vht_opmode_bits { + IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, + IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, + IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, + IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, + IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, + IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, +}; + +/* + * Maximum length of AMPDU that the STA can receive in VHT. + * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) + */ +enum ieee80211_vht_max_ampdu_length_exp { + IEEE80211_VHT_MAX_AMPDU_8K = 0, + IEEE80211_VHT_MAX_AMPDU_16K = 1, + IEEE80211_VHT_MAX_AMPDU_32K = 2, + IEEE80211_VHT_MAX_AMPDU_64K = 3, + IEEE80211_VHT_MAX_AMPDU_128K = 4, + IEEE80211_VHT_MAX_AMPDU_256K = 5, + IEEE80211_VHT_MAX_AMPDU_512K = 6, + IEEE80211_VHT_MAX_AMPDU_1024K = 7 +}; + +/** + * struct ieee80211_vht_mcs_info - VHT MCS information + * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams + * @rx_highest: Indicates highest long GI VHT PPDU data rate + * STA can receive. Rate expressed in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest RX data rate supported. + * The top 3 bits of this field indicate the Maximum NSTS,total + * (a beamformee capability.) + * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams + * @tx_highest: Indicates highest long GI VHT PPDU data rate + * STA can transmit. Rate expressed in units of 1 Mbps. + * If this field is 0 this value should not be used to + * consider the highest TX data rate supported. + * The top 2 bits of this field are reserved, the + * 3rd bit from the top indiciates VHT Extended NSS BW + * Capability. + */ +struct ieee80211_vht_mcs_info { + __le16 rx_mcs_map; + __le16 rx_highest; + __le16 tx_mcs_map; + __le16 tx_highest; +} __packed; + +/* for rx_highest */ +#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 +#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) + +/* for tx_highest */ +#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) + +/** + * enum ieee80211_vht_mcs_support - VHT MCS support definitions + * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the + * number of streams + * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported + * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported + * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported + * + * These definitions are used in each 2-bit subfield of the @rx_mcs_map + * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are + * both split into 8 subfields by number of streams. These values indicate + * which MCSes are supported for the number of streams the value appears + * for. + */ +enum ieee80211_vht_mcs_support { + IEEE80211_VHT_MCS_SUPPORT_0_7 = 0, + IEEE80211_VHT_MCS_SUPPORT_0_8 = 1, + IEEE80211_VHT_MCS_SUPPORT_0_9 = 2, + IEEE80211_VHT_MCS_NOT_SUPPORTED = 3, +}; + +/** + * struct ieee80211_vht_cap - VHT capabilities + * + * This structure is the "VHT capabilities element" as + * described in 802.11ac D3.0 8.4.2.160 + * @vht_cap_info: VHT capability info + * @supp_mcs: VHT MCS supported rates + */ +struct ieee80211_vht_cap { + __le32 vht_cap_info; + struct ieee80211_vht_mcs_info supp_mcs; +} __packed; + +/** + * enum ieee80211_vht_chanwidth - VHT channel width + * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to + * determine the channel width (20 or 40 MHz) + * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth + * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth + * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth + */ +enum ieee80211_vht_chanwidth { + IEEE80211_VHT_CHANWIDTH_USE_HT = 0, + IEEE80211_VHT_CHANWIDTH_80MHZ = 1, + IEEE80211_VHT_CHANWIDTH_160MHZ = 2, + IEEE80211_VHT_CHANWIDTH_80P80MHZ = 3, +}; + +/** + * struct ieee80211_vht_operation - VHT operation IE + * + * This structure is the "VHT operation element" as + * described in 802.11ac D3.0 8.4.2.161 + * @chan_width: Operating channel width + * @center_freq_seg0_idx: center freq segment 0 index + * @center_freq_seg1_idx: center freq segment 1 index + * @basic_mcs_set: VHT Basic MCS rate set + */ +struct ieee80211_vht_operation { + u8 chan_width; + u8 center_freq_seg0_idx; + u8 center_freq_seg1_idx; + __le16 basic_mcs_set; +} __packed; + +/* 802.11ac VHT Capabilities */ +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 +#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 +#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C +#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 +#define IEEE80211_VHT_CAP_RXLDPC 0x00000010 +#define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 +#define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 +#define IEEE80211_VHT_CAP_TXSTBC 0x00000080 +#define IEEE80211_VHT_CAP_RXSTBC_1 0x00000100 +#define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 +#define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 +#define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 +#define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 +#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 +#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 +#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 +#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 +#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK \ + (7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT) +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT 16 +#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK \ + (7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT) +#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 +#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 +#define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 +#define IEEE80211_VHT_CAP_HTC_VHT 0x00400000 +#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT 23 +#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK \ + (7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT) +#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB 0x08000000 +#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 +#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 +#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 +#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 + +/** + * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS + * @cap: VHT capabilities of the peer + * @bw: bandwidth to use + * @mcs: MCS index to use + * @ext_nss_bw_capable: indicates whether or not the local transmitter + * (rate scaling algorithm) can deal with the new logic + * (dot11VHTExtendedNSSBWCapable) + * @max_vht_nss: current maximum NSS as advertised by the STA in + * operating mode notification, can be 0 in which case the + * capability data will be used to derive this (from MCS support) + * Return: The maximum NSS that can be used for the given bandwidth/MCS + * combination + * + * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can + * vary for a given BW/MCS. This function parses the data. + * + * Note: This function is exported by cfg80211. + */ +int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, + enum ieee80211_vht_chanwidth bw, + int mcs, bool ext_nss_bw_capable, + unsigned int max_vht_nss); + +/* VHT action codes */ +enum ieee80211_vht_actioncode { + WLAN_VHT_ACTION_COMPRESSED_BF = 0, + WLAN_VHT_ACTION_GROUPID_MGMT = 1, + WLAN_VHT_ACTION_OPMODE_NOTIF = 2, +}; + +#endif /* LINUX_IEEE80211_VHT_H */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index ddff9102f6332..6d4bc80caf96c 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -43,6 +43,7 @@ #define IEEE80211_FCTL_VERS 0x0003 #define IEEE80211_FCTL_FTYPE 0x000c #define IEEE80211_FCTL_STYPE 0x00f0 +#define IEEE80211_FCTL_TYPE (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE) #define IEEE80211_FCTL_TODS 0x0100 #define IEEE80211_FCTL_FROMDS 0x0200 #define IEEE80211_FCTL_MOREFRAGS 0x0400 @@ -109,17 +110,6 @@ #define IEEE80211_STYPE_DMG_BEACON 0x0000 #define IEEE80211_STYPE_S1G_BEACON 0x0010 -/* bits unique to S1G beacon */ -#define IEEE80211_S1G_BCN_NEXT_TBTT 0x100 -#define IEEE80211_S1G_BCN_CSSID 0x200 -#define IEEE80211_S1G_BCN_ANO 0x400 - -/* see 802.11ah-2016 9.9 NDP CMAC frames */ -#define IEEE80211_S1G_1MHZ_NDP_BITS 25 -#define IEEE80211_S1G_1MHZ_NDP_BYTES 4 -#define IEEE80211_S1G_2MHZ_NDP_BITS 37 -#define IEEE80211_S1G_2MHZ_NDP_BYTES 5 - #define IEEE80211_NDP_FTYPE_CTS 0 #define IEEE80211_NDP_FTYPE_CF_END 0 #define IEEE80211_NDP_FTYPE_PS_POLL 1 @@ -221,11 +211,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_MAX_TIM_LEN 251 #define IEEE80211_MAX_MESH_PEERINGS 63 -/* S1G encoding types */ -#define IEEE80211_S1G_TIM_ENC_MODE_BLOCK 0 -#define IEEE80211_S1G_TIM_ENC_MODE_SINGLE 1 -#define IEEE80211_S1G_TIM_ENC_MODE_OLB 2 - /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section 6.2.1.1.2. @@ -239,21 +224,8 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */ #define IEEE80211_MAX_FRAME_LEN 2352 -/* Maximal size of an A-MSDU that can be transported in a HT BA session */ -#define IEEE80211_MAX_MPDU_LEN_HT_BA 4095 - -/* Maximal size of an A-MSDU */ -#define IEEE80211_MAX_MPDU_LEN_HT_3839 3839 -#define IEEE80211_MAX_MPDU_LEN_HT_7935 7935 - -#define IEEE80211_MAX_MPDU_LEN_VHT_3895 3895 -#define IEEE80211_MAX_MPDU_LEN_VHT_7991 7991 -#define IEEE80211_MAX_MPDU_LEN_VHT_11454 11454 - #define IEEE80211_MAX_SSID_LEN 32 -#define IEEE80211_MAX_MESH_ID_LEN 32 - #define IEEE80211_FIRST_TSPEC_TSID 8 #define IEEE80211_NUM_TIDS 16 @@ -304,8 +276,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK 0x03 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT 5 -#define IEEE80211_HT_CTL_LEN 4 - /* trigger type within common_info of trigger frame */ #define IEEE80211_TRIGGER_TYPE_MASK 0xf #define IEEE80211_TRIGGER_TYPE_BASIC 0x0 @@ -619,55 +589,6 @@ static inline bool ieee80211_is_beacon(__le16 fc) cpu_to_le16(IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON); } -/** - * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT && - * IEEE80211_STYPE_S1G_BEACON - * @fc: frame control bytes in little-endian byteorder - * Return: whether or not the frame is an S1G beacon - */ -static inline bool ieee80211_is_s1g_beacon(__le16 fc) -{ - return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | - IEEE80211_FCTL_STYPE)) == - cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON); -} - -/** - * ieee80211_s1g_has_next_tbtt - check if IEEE80211_S1G_BCN_NEXT_TBTT - * @fc: frame control bytes in little-endian byteorder - * Return: whether or not the frame contains the variable-length - * next TBTT field - */ -static inline bool ieee80211_s1g_has_next_tbtt(__le16 fc) -{ - return ieee80211_is_s1g_beacon(fc) && - (fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT)); -} - -/** - * ieee80211_s1g_has_ano - check if IEEE80211_S1G_BCN_ANO - * @fc: frame control bytes in little-endian byteorder - * Return: whether or not the frame contains the variable-length - * ANO field - */ -static inline bool ieee80211_s1g_has_ano(__le16 fc) -{ - return ieee80211_is_s1g_beacon(fc) && - (fc & cpu_to_le16(IEEE80211_S1G_BCN_ANO)); -} - -/** - * ieee80211_s1g_has_cssid - check if IEEE80211_S1G_BCN_CSSID - * @fc: frame control bytes in little-endian byteorder - * Return: whether or not the frame contains the variable-length - * compressed SSID field - */ -static inline bool ieee80211_s1g_has_cssid(__le16 fc) -{ - return ieee80211_is_s1g_beacon(fc) && - (fc & cpu_to_le16(IEEE80211_S1G_BCN_CSSID)); -} - /** * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM * @fc: frame control bytes in little-endian byteorder @@ -881,40 +802,6 @@ static inline u16 ieee80211_get_sn(struct ieee80211_hdr *hdr) return le16_get_bits(hdr->seq_ctrl, IEEE80211_SCTL_SEQ); } -struct ieee80211s_hdr { - u8 flags; - u8 ttl; - __le32 seqnum; - u8 eaddr1[ETH_ALEN]; - u8 eaddr2[ETH_ALEN]; -} __packed __aligned(2); - -/* Mesh flags */ -#define MESH_FLAGS_AE_A4 0x1 -#define MESH_FLAGS_AE_A5_A6 0x2 -#define MESH_FLAGS_AE 0x3 -#define MESH_FLAGS_PS_DEEP 0x4 - -/** - * enum ieee80211_preq_flags - mesh PREQ element flags - * - * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield - */ -enum ieee80211_preq_flags { - IEEE80211_PREQ_PROACTIVE_PREP_FLAG = 1<<2, -}; - -/** - * enum ieee80211_preq_target_flags - mesh PREQ element per target flags - * - * @IEEE80211_PREQ_TO_FLAG: target only subfield - * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield - */ -enum ieee80211_preq_target_flags { - IEEE80211_PREQ_TO_FLAG = 1<<0, - IEEE80211_PREQ_USN_FLAG = 1<<2, -}; - /** * struct ieee80211_quiet_ie - Quiet element * @count: Quiet Count @@ -993,24 +880,6 @@ struct ieee80211_sec_chan_offs_ie { u8 sec_chan_offs; } __packed; -/** - * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE - * @mesh_ttl: Time To Live - * @mesh_flags: Flags - * @mesh_reason: Reason Code - * @mesh_pre_value: Precedence Value - * - * This structure represents the payload of the "Mesh Channel Switch - * Parameters element" as described in IEEE Std 802.11-2020 section - * 9.4.2.102. - */ -struct ieee80211_mesh_chansw_params_ie { - u8 mesh_ttl; - u8 mesh_flags; - __le16 mesh_reason; - __le16 mesh_pre_value; -} __packed; - /** * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE * @new_channel_width: New Channel Width @@ -1051,149 +920,6 @@ struct ieee80211_tim_ie { }; } __packed; -/** - * struct ieee80211_meshconf_ie - Mesh Configuration element - * @meshconf_psel: Active Path Selection Protocol Identifier - * @meshconf_pmetric: Active Path Selection Metric Identifier - * @meshconf_congest: Congestion Control Mode Identifier - * @meshconf_synch: Synchronization Method Identifier - * @meshconf_auth: Authentication Protocol Identifier - * @meshconf_form: Mesh Formation Info - * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags) - * - * This structure represents the payload of the "Mesh Configuration - * element" as described in IEEE Std 802.11-2020 section 9.4.2.97. - */ -struct ieee80211_meshconf_ie { - u8 meshconf_psel; - u8 meshconf_pmetric; - u8 meshconf_congest; - u8 meshconf_synch; - u8 meshconf_auth; - u8 meshconf_form; - u8 meshconf_cap; -} __packed; - -/** - * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags - * - * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish - * additional mesh peerings with other mesh STAs - * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs - * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure - * is ongoing - * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has - * neighbors in deep sleep mode - * - * Enumerates the "Mesh Capability" as described in IEEE Std - * 802.11-2020 section 9.4.2.97.7. - */ -enum mesh_config_capab_flags { - IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS = 0x01, - IEEE80211_MESHCONF_CAPAB_FORWARDING = 0x08, - IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING = 0x20, - IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL = 0x40, -}; - -#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1 - -/* - * mesh channel switch parameters element's flag indicator - * - */ -#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0) -#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1) -#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2) - -/** - * struct ieee80211_rann_ie - RANN (root announcement) element - * @rann_flags: Flags - * @rann_hopcount: Hop Count - * @rann_ttl: Element TTL - * @rann_addr: Root Mesh STA Address - * @rann_seq: HWMP Sequence Number - * @rann_interval: Interval - * @rann_metric: Metric - * - * This structure represents the payload of the "RANN element" as - * described in IEEE Std 802.11-2020 section 9.4.2.111. - */ -struct ieee80211_rann_ie { - u8 rann_flags; - u8 rann_hopcount; - u8 rann_ttl; - u8 rann_addr[ETH_ALEN]; - __le32 rann_seq; - __le32 rann_interval; - __le32 rann_metric; -} __packed; - -enum ieee80211_rann_flags { - RANN_FLAG_IS_GATE = 1 << 0, -}; - -enum ieee80211_ht_chanwidth_values { - IEEE80211_HT_CHANWIDTH_20MHZ = 0, - IEEE80211_HT_CHANWIDTH_ANY = 1, -}; - -/** - * enum ieee80211_vht_opmode_bits - VHT operating mode field bits - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width - * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width - * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag - * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask - * (the NSS value is the value of this field + 1) - * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift - * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU - * using a beamforming steering matrix - */ -enum ieee80211_vht_opmode_bits { - IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK = 0x03, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ = 0, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ = 1, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ = 2, - IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ = 3, - IEEE80211_OPMODE_NOTIF_BW_160_80P80 = 0x04, - IEEE80211_OPMODE_NOTIF_RX_NSS_MASK = 0x70, - IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT = 4, - IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF = 0x80, -}; - -/** - * enum ieee80211_s1g_chanwidth - S1G channel widths - * These are defined in IEEE802.11-2016ah Table 10-20 - * as BSS Channel Width - * - * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel - * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel - * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel - * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel - * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel - */ -enum ieee80211_s1g_chanwidth { - IEEE80211_S1G_CHANWIDTH_1MHZ = 0, - IEEE80211_S1G_CHANWIDTH_2MHZ = 1, - IEEE80211_S1G_CHANWIDTH_4MHZ = 3, - IEEE80211_S1G_CHANWIDTH_8MHZ = 7, - IEEE80211_S1G_CHANWIDTH_16MHZ = 15, -}; - -/** - * enum ieee80211_s1g_pri_chanwidth - S1G primary channel widths - * described in IEEE80211-2024 Table 10-39. - * - * @IEEE80211_S1G_PRI_CHANWIDTH_2MHZ: 2MHz primary channel - * @IEEE80211_S1G_PRI_CHANWIDTH_1MHZ: 1MHz primary channel - */ -enum ieee80211_s1g_pri_chanwidth { - IEEE80211_S1G_PRI_CHANWIDTH_2MHZ = 0, - IEEE80211_S1G_PRI_CHANWIDTH_1MHZ = 1, -}; - #define WLAN_SA_QUERY_TR_ID_LEN 2 #define WLAN_MEMBERSHIP_LEN 8 #define WLAN_USER_POSITION_LEN 16 @@ -1221,61 +947,6 @@ struct ieee80211_addba_ext_ie { u8 data; } __packed; -/** - * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element - * @compat_info: Compatibility Information - * @beacon_int: Beacon Interval - * @tsf_completion: TSF Completion - * - * This structure represents the payload of the "S1G Beacon - * Compatibility element" as described in IEEE Std 802.11-2020 section - * 9.4.2.196. - */ -struct ieee80211_s1g_bcn_compat_ie { - __le16 compat_info; - __le16 beacon_int; - __le32 tsf_completion; -} __packed; - -/** - * struct ieee80211_s1g_oper_ie - S1G Operation element - * @ch_width: S1G Operation Information Channel Width - * @oper_class: S1G Operation Information Operating Class - * @primary_ch: S1G Operation Information Primary Channel Number - * @oper_ch: S1G Operation Information Channel Center Frequency - * @basic_mcs_nss: Basic S1G-MCS and NSS Set - * - * This structure represents the payload of the "S1G Operation - * element" as described in IEEE Std 802.11-2020 section 9.4.2.212. - */ -struct ieee80211_s1g_oper_ie { - u8 ch_width; - u8 oper_class; - u8 primary_ch; - u8 oper_ch; - __le16 basic_mcs_nss; -} __packed; - -/** - * struct ieee80211_aid_response_ie - AID Response element - * @aid: AID/Group AID - * @switch_count: AID Switch Count - * @response_int: AID Response Interval - * - * This structure represents the payload of the "AID Response element" - * as described in IEEE Std 802.11-2020 section 9.4.2.194. - */ -struct ieee80211_aid_response_ie { - __le16 aid; - u8 switch_count; - __le16 response_int; -} __packed; - -struct ieee80211_s1g_cap { - u8 capab_info[10]; - u8 supp_mcs_nss[5]; -} __packed; - struct ieee80211_ext { __le16 frame_control; __le16 duration; @@ -1289,103 +960,6 @@ struct ieee80211_ext { } u; } __packed __aligned(2); -/** - * ieee80211_s1g_optional_len - determine length of optional S1G beacon fields - * @fc: frame control bytes in little-endian byteorder - * Return: total length in bytes of the optional fixed-length fields - * - * S1G beacons may contain up to three optional fixed-length fields that - * precede the variable-length elements. Whether these fields are present - * is indicated by flags in the frame control field. - * - * From IEEE 802.11-2024 section 9.3.4.3: - * - Next TBTT field may be 0 or 3 bytes - * - Short SSID field may be 0 or 4 bytes - * - Access Network Options (ANO) field may be 0 or 1 byte - */ -static inline size_t -ieee80211_s1g_optional_len(__le16 fc) -{ - size_t len = 0; - - if (ieee80211_s1g_has_next_tbtt(fc)) - len += 3; - - if (ieee80211_s1g_has_cssid(fc)) - len += 4; - - if (ieee80211_s1g_has_ano(fc)) - len += 1; - - return len; -} - -#define IEEE80211_TWT_CONTROL_NDP BIT(0) -#define IEEE80211_TWT_CONTROL_RESP_MODE BIT(1) -#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST BIT(3) -#define IEEE80211_TWT_CONTROL_RX_DISABLED BIT(4) -#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT BIT(5) - -#define IEEE80211_TWT_REQTYPE_REQUEST BIT(0) -#define IEEE80211_TWT_REQTYPE_SETUP_CMD GENMASK(3, 1) -#define IEEE80211_TWT_REQTYPE_TRIGGER BIT(4) -#define IEEE80211_TWT_REQTYPE_IMPLICIT BIT(5) -#define IEEE80211_TWT_REQTYPE_FLOWTYPE BIT(6) -#define IEEE80211_TWT_REQTYPE_FLOWID GENMASK(9, 7) -#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP GENMASK(14, 10) -#define IEEE80211_TWT_REQTYPE_PROTECTION BIT(15) - -enum ieee80211_twt_setup_cmd { - TWT_SETUP_CMD_REQUEST, - TWT_SETUP_CMD_SUGGEST, - TWT_SETUP_CMD_DEMAND, - TWT_SETUP_CMD_GROUPING, - TWT_SETUP_CMD_ACCEPT, - TWT_SETUP_CMD_ALTERNATE, - TWT_SETUP_CMD_DICTATE, - TWT_SETUP_CMD_REJECT, -}; - -struct ieee80211_twt_params { - __le16 req_type; - __le64 twt; - u8 min_twt_dur; - __le16 mantissa; - u8 channel; -} __packed; - -struct ieee80211_twt_setup { - u8 dialog_token; - u8 element_id; - u8 length; - u8 control; - u8 params[]; -} __packed; - -#define IEEE80211_TTLM_MAX_CNT 2 -#define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 -#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 -#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 -#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 -#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 - -#define IEEE80211_TTLM_DIRECTION_DOWN 0 -#define IEEE80211_TTLM_DIRECTION_UP 1 -#define IEEE80211_TTLM_DIRECTION_BOTH 2 - -/** - * struct ieee80211_ttlm_elem - TID-To-Link Mapping element - * - * Defined in section 9.4.2.314 in P802.11be_D4 - * - * @control: the first part of control field - * @optional: the second part of control field - */ -struct ieee80211_ttlm_elem { - u8 control; - u8 optional[]; -} __packed; - /** * struct ieee80211_bss_load_elem - BSS Load elemen * @@ -1760,1775 +1334,91 @@ struct ieee80211_tdls_data { } u; } __packed; -/* - * Peer-to-Peer IE attribute related definitions. - */ -/* - * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute. - */ -enum ieee80211_p2p_attr_id { - IEEE80211_P2P_ATTR_STATUS = 0, - IEEE80211_P2P_ATTR_MINOR_REASON, - IEEE80211_P2P_ATTR_CAPABILITY, - IEEE80211_P2P_ATTR_DEVICE_ID, - IEEE80211_P2P_ATTR_GO_INTENT, - IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT, - IEEE80211_P2P_ATTR_LISTEN_CHANNEL, - IEEE80211_P2P_ATTR_GROUP_BSSID, - IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING, - IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR, - IEEE80211_P2P_ATTR_MANAGABILITY, - IEEE80211_P2P_ATTR_CHANNEL_LIST, - IEEE80211_P2P_ATTR_ABSENCE_NOTICE, - IEEE80211_P2P_ATTR_DEVICE_INFO, - IEEE80211_P2P_ATTR_GROUP_INFO, - IEEE80211_P2P_ATTR_GROUP_ID, - IEEE80211_P2P_ATTR_INTERFACE, - IEEE80211_P2P_ATTR_OPER_CHANNEL, - IEEE80211_P2P_ATTR_INVITE_FLAGS, - /* 19 - 220: Reserved */ - IEEE80211_P2P_ATTR_VENDOR_SPECIFIC = 221, - - IEEE80211_P2P_ATTR_MAX -}; - -/* Notice of Absence attribute - described in P2P spec 4.1.14 */ -/* Typical max value used here */ -#define IEEE80211_P2P_NOA_DESC_MAX 4 - -struct ieee80211_p2p_noa_desc { - u8 count; - __le32 duration; - __le32 interval; - __le32 start_time; -} __packed; - -struct ieee80211_p2p_noa_attr { - u8 index; - u8 oppps_ctwindow; - struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX]; -} __packed; - -#define IEEE80211_P2P_OPPPS_ENABLE_BIT BIT(7) -#define IEEE80211_P2P_OPPPS_CTWINDOW_MASK 0x7F - -/** - * struct ieee80211_bar - Block Ack Request frame format - * @frame_control: Frame Control - * @duration: Duration - * @ra: RA - * @ta: TA - * @control: BAR Control - * @start_seq_num: Starting Sequence Number (see Figure 9-37) - * - * This structure represents the "BlockAckReq frame format" - * as described in IEEE Std 802.11-2020 section 9.3.1.7. -*/ -struct ieee80211_bar { - __le16 frame_control; - __le16 duration; - __u8 ra[ETH_ALEN]; - __u8 ta[ETH_ALEN]; - __le16 control; - __le16 start_seq_num; -} __packed; +/* Authentication algorithms */ +#define WLAN_AUTH_OPEN 0 +#define WLAN_AUTH_SHARED_KEY 1 +#define WLAN_AUTH_FT 2 +#define WLAN_AUTH_SAE 3 +#define WLAN_AUTH_FILS_SK 4 +#define WLAN_AUTH_FILS_SK_PFS 5 +#define WLAN_AUTH_FILS_PK 6 +#define WLAN_AUTH_LEAP 128 -/* 802.11 BAR control masks */ -#define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL 0x0000 -#define IEEE80211_BAR_CTRL_MULTI_TID 0x0002 -#define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA 0x0004 -#define IEEE80211_BAR_CTRL_TID_INFO_MASK 0xf000 -#define IEEE80211_BAR_CTRL_TID_INFO_SHIFT 12 +#define WLAN_AUTH_CHALLENGE_LEN 128 -#define IEEE80211_HT_MCS_MASK_LEN 10 +#define WLAN_CAPABILITY_ESS (1<<0) +#define WLAN_CAPABILITY_IBSS (1<<1) -/** - * struct ieee80211_mcs_info - Supported MCS Set field - * @rx_mask: RX mask - * @rx_highest: highest supported RX rate. If set represents - * the highest supported RX data rate in units of 1 Mbps. - * If this field is 0 this value should not be used to - * consider the highest RX data rate supported. - * @tx_params: TX parameters - * @reserved: Reserved bits - * - * This structure represents the "Supported MCS Set field" as - * described in IEEE Std 802.11-2020 section 9.4.2.55.4. +/* + * A mesh STA sets the ESS and IBSS capability bits to zero. + * however, this holds true for p2p probe responses (in the p2p_find + * phase) as well. */ -struct ieee80211_mcs_info { - u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN]; - __le16 rx_highest; - u8 tx_params; - u8 reserved[3]; -} __packed; +#define WLAN_CAPABILITY_IS_STA_BSS(cap) \ + (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS))) -/* 802.11n HT capability MSC set */ -#define IEEE80211_HT_MCS_RX_HIGHEST_MASK 0x3ff -#define IEEE80211_HT_MCS_TX_DEFINED 0x01 -#define IEEE80211_HT_MCS_TX_RX_DIFF 0x02 -/* value 0 == 1 stream etc */ -#define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK 0x0C -#define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT 2 -#define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 -#define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 +#define WLAN_CAPABILITY_CF_POLLABLE (1<<2) +#define WLAN_CAPABILITY_CF_POLL_REQUEST (1<<3) +#define WLAN_CAPABILITY_PRIVACY (1<<4) +#define WLAN_CAPABILITY_SHORT_PREAMBLE (1<<5) +#define WLAN_CAPABILITY_PBCC (1<<6) +#define WLAN_CAPABILITY_CHANNEL_AGILITY (1<<7) -#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) +/* 802.11h */ +#define WLAN_CAPABILITY_SPECTRUM_MGMT (1<<8) +#define WLAN_CAPABILITY_QOS (1<<9) +#define WLAN_CAPABILITY_SHORT_SLOT_TIME (1<<10) +#define WLAN_CAPABILITY_APSD (1<<11) +#define WLAN_CAPABILITY_RADIO_MEASURE (1<<12) +#define WLAN_CAPABILITY_DSSS_OFDM (1<<13) +#define WLAN_CAPABILITY_DEL_BACK (1<<14) +#define WLAN_CAPABILITY_IMM_BACK (1<<15) -/* - * 802.11n D5.0 20.3.5 / 20.6 says: - * - indices 0 to 7 and 32 are single spatial stream - * - 8 to 31 are multiple spatial streams using equal modulation - * [8..15 for two streams, 16..23 for three and 24..31 for four] - * - remainder are multiple spatial streams using unequal modulation - */ -#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33 -#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \ - (IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8) +/* DMG (60gHz) 802.11ad */ +/* type - bits 0..1 */ +#define WLAN_CAPABILITY_DMG_TYPE_MASK (3<<0) +#define WLAN_CAPABILITY_DMG_TYPE_IBSS (1<<0) /* Tx by: STA */ +#define WLAN_CAPABILITY_DMG_TYPE_PBSS (2<<0) /* Tx by: PCP */ +#define WLAN_CAPABILITY_DMG_TYPE_AP (3<<0) /* Tx by: AP */ -/** - * struct ieee80211_ht_cap - HT capabilities element - * @cap_info: HT Capability Information - * @ampdu_params_info: A-MPDU Parameters - * @mcs: Supported MCS Set - * @extended_ht_cap_info: HT Extended Capabilities - * @tx_BF_cap_info: Transmit Beamforming Capabilities - * @antenna_selection_info: ASEL Capability - * - * This structure represents the payload of the "HT Capabilities - * element" as described in IEEE Std 802.11-2020 section 9.4.2.55. - */ -struct ieee80211_ht_cap { - __le16 cap_info; - u8 ampdu_params_info; +#define WLAN_CAPABILITY_DMG_CBAP_ONLY (1<<2) +#define WLAN_CAPABILITY_DMG_CBAP_SOURCE (1<<3) +#define WLAN_CAPABILITY_DMG_PRIVACY (1<<4) +#define WLAN_CAPABILITY_DMG_ECPAC (1<<5) - /* 16 bytes MCS information */ - struct ieee80211_mcs_info mcs; +#define WLAN_CAPABILITY_DMG_SPECTRUM_MGMT (1<<8) +#define WLAN_CAPABILITY_DMG_RADIO_MEASURE (1<<12) - __le16 extended_ht_cap_info; - __le32 tx_BF_cap_info; - u8 antenna_selection_info; -} __packed; +/* measurement */ +#define IEEE80211_SPCT_MSR_RPRT_MODE_LATE (1<<0) +#define IEEE80211_SPCT_MSR_RPRT_MODE_INCAPABLE (1<<1) +#define IEEE80211_SPCT_MSR_RPRT_MODE_REFUSED (1<<2) -/* 802.11n HT capabilities masks (for cap_info) */ -#define IEEE80211_HT_CAP_LDPC_CODING 0x0001 -#define IEEE80211_HT_CAP_SUP_WIDTH_20_40 0x0002 -#define IEEE80211_HT_CAP_SM_PS 0x000C -#define IEEE80211_HT_CAP_SM_PS_SHIFT 2 -#define IEEE80211_HT_CAP_GRN_FLD 0x0010 -#define IEEE80211_HT_CAP_SGI_20 0x0020 -#define IEEE80211_HT_CAP_SGI_40 0x0040 -#define IEEE80211_HT_CAP_TX_STBC 0x0080 -#define IEEE80211_HT_CAP_RX_STBC 0x0300 -#define IEEE80211_HT_CAP_RX_STBC_SHIFT 8 -#define IEEE80211_HT_CAP_DELAY_BA 0x0400 -#define IEEE80211_HT_CAP_MAX_AMSDU 0x0800 -#define IEEE80211_HT_CAP_DSSSCCK40 0x1000 -#define IEEE80211_HT_CAP_RESERVED 0x2000 -#define IEEE80211_HT_CAP_40MHZ_INTOLERANT 0x4000 -#define IEEE80211_HT_CAP_LSIG_TXOP_PROT 0x8000 - -/* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */ -#define IEEE80211_HT_EXT_CAP_PCO 0x0001 -#define IEEE80211_HT_EXT_CAP_PCO_TIME 0x0006 -#define IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT 1 -#define IEEE80211_HT_EXT_CAP_MCS_FB 0x0300 -#define IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT 8 -#define IEEE80211_HT_EXT_CAP_HTC_SUP 0x0400 -#define IEEE80211_HT_EXT_CAP_RD_RESPONDER 0x0800 - -/* 802.11n HT capability AMPDU settings (for ampdu_params_info) */ -#define IEEE80211_HT_AMPDU_PARM_FACTOR 0x03 -#define IEEE80211_HT_AMPDU_PARM_DENSITY 0x1C -#define IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT 2 +#define IEEE80211_SPCT_MSR_RPRT_TYPE_BASIC 0 +#define IEEE80211_SPCT_MSR_RPRT_TYPE_CCA 1 +#define IEEE80211_SPCT_MSR_RPRT_TYPE_RPI 2 +#define IEEE80211_SPCT_MSR_RPRT_TYPE_LCI 8 +#define IEEE80211_SPCT_MSR_RPRT_TYPE_CIVIC 11 -/* - * Maximum length of AMPDU that the STA can receive in high-throughput (HT). - * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) - */ -enum ieee80211_max_ampdu_length_exp { - IEEE80211_HT_MAX_AMPDU_8K = 0, - IEEE80211_HT_MAX_AMPDU_16K = 1, - IEEE80211_HT_MAX_AMPDU_32K = 2, - IEEE80211_HT_MAX_AMPDU_64K = 3 -}; +/* 802.11g ERP information element */ +#define WLAN_ERP_NON_ERP_PRESENT (1<<0) +#define WLAN_ERP_USE_PROTECTION (1<<1) +#define WLAN_ERP_BARKER_PREAMBLE (1<<2) -/* - * Maximum length of AMPDU that the STA can receive in VHT. - * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets) - */ -enum ieee80211_vht_max_ampdu_length_exp { - IEEE80211_VHT_MAX_AMPDU_8K = 0, - IEEE80211_VHT_MAX_AMPDU_16K = 1, - IEEE80211_VHT_MAX_AMPDU_32K = 2, - IEEE80211_VHT_MAX_AMPDU_64K = 3, - IEEE80211_VHT_MAX_AMPDU_128K = 4, - IEEE80211_VHT_MAX_AMPDU_256K = 5, - IEEE80211_VHT_MAX_AMPDU_512K = 6, - IEEE80211_VHT_MAX_AMPDU_1024K = 7 +/* WLAN_ERP_BARKER_PREAMBLE values */ +enum { + WLAN_ERP_PREAMBLE_SHORT = 0, + WLAN_ERP_PREAMBLE_LONG = 1, }; -#define IEEE80211_HT_MAX_AMPDU_FACTOR 13 - -/* Minimum MPDU start spacing */ -enum ieee80211_min_mpdu_spacing { - IEEE80211_HT_MPDU_DENSITY_NONE = 0, /* No restriction */ - IEEE80211_HT_MPDU_DENSITY_0_25 = 1, /* 1/4 usec */ - IEEE80211_HT_MPDU_DENSITY_0_5 = 2, /* 1/2 usec */ - IEEE80211_HT_MPDU_DENSITY_1 = 3, /* 1 usec */ - IEEE80211_HT_MPDU_DENSITY_2 = 4, /* 2 usec */ - IEEE80211_HT_MPDU_DENSITY_4 = 5, /* 4 usec */ - IEEE80211_HT_MPDU_DENSITY_8 = 6, /* 8 usec */ - IEEE80211_HT_MPDU_DENSITY_16 = 7 /* 16 usec */ -}; - -/** - * struct ieee80211_ht_operation - HT operation IE - * @primary_chan: Primary Channel - * @ht_param: HT Operation Information parameters - * @operation_mode: HT Operation Information operation mode - * @stbc_param: HT Operation Information STBC params - * @basic_set: Basic HT-MCS Set - * - * This structure represents the payload of the "HT Operation - * element" as described in IEEE Std 802.11-2020 section 9.4.2.56. - */ -struct ieee80211_ht_operation { - u8 primary_chan; - u8 ht_param; - __le16 operation_mode; - __le16 stbc_param; - u8 basic_set[16]; -} __packed; - -/* for ht_param */ -#define IEEE80211_HT_PARAM_CHA_SEC_OFFSET 0x03 -#define IEEE80211_HT_PARAM_CHA_SEC_NONE 0x00 -#define IEEE80211_HT_PARAM_CHA_SEC_ABOVE 0x01 -#define IEEE80211_HT_PARAM_CHA_SEC_BELOW 0x03 -#define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY 0x04 -#define IEEE80211_HT_PARAM_RIFS_MODE 0x08 - -/* for operation_mode */ -#define IEEE80211_HT_OP_MODE_PROTECTION 0x0003 -#define IEEE80211_HT_OP_MODE_PROTECTION_NONE 0 -#define IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER 1 -#define IEEE80211_HT_OP_MODE_PROTECTION_20MHZ 2 -#define IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED 3 -#define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT 0x0004 -#define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT 0x0010 -#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT 5 -#define IEEE80211_HT_OP_MODE_CCFS2_MASK 0x1fe0 - -/* for stbc_param */ -#define IEEE80211_HT_STBC_PARAM_DUAL_BEACON 0x0040 -#define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT 0x0080 -#define IEEE80211_HT_STBC_PARAM_STBC_BEACON 0x0100 -#define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT 0x0200 -#define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE 0x0400 -#define IEEE80211_HT_STBC_PARAM_PCO_PHASE 0x0800 - - -/* block-ack parameters */ -#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001 -#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002 -#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C -#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0 -#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000 -#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800 - -/* - * A-MPDU buffer sizes - * According to HT size varies from 8 to 64 frames - * HE adds the ability to have up to 256 frames. - * EHT adds the ability to have up to 1K frames. - */ -#define IEEE80211_MIN_AMPDU_BUF 0x8 -#define IEEE80211_MAX_AMPDU_BUF_HT 0x40 -#define IEEE80211_MAX_AMPDU_BUF_HE 0x100 -#define IEEE80211_MAX_AMPDU_BUF_EHT 0x400 - - -/* Spatial Multiplexing Power Save Modes (for capability) */ -#define WLAN_HT_CAP_SM_PS_STATIC 0 -#define WLAN_HT_CAP_SM_PS_DYNAMIC 1 -#define WLAN_HT_CAP_SM_PS_INVALID 2 -#define WLAN_HT_CAP_SM_PS_DISABLED 3 - -/* for SM power control field lower two bits */ -#define WLAN_HT_SMPS_CONTROL_DISABLED 0 -#define WLAN_HT_SMPS_CONTROL_STATIC 1 -#define WLAN_HT_SMPS_CONTROL_DYNAMIC 3 - -/** - * struct ieee80211_vht_mcs_info - VHT MCS information - * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams - * @rx_highest: Indicates highest long GI VHT PPDU data rate - * STA can receive. Rate expressed in units of 1 Mbps. - * If this field is 0 this value should not be used to - * consider the highest RX data rate supported. - * The top 3 bits of this field indicate the Maximum NSTS,total - * (a beamformee capability.) - * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams - * @tx_highest: Indicates highest long GI VHT PPDU data rate - * STA can transmit. Rate expressed in units of 1 Mbps. - * If this field is 0 this value should not be used to - * consider the highest TX data rate supported. - * The top 2 bits of this field are reserved, the - * 3rd bit from the top indiciates VHT Extended NSS BW - * Capability. - */ -struct ieee80211_vht_mcs_info { - __le16 rx_mcs_map; - __le16 rx_highest; - __le16 tx_mcs_map; - __le16 tx_highest; -} __packed; - -/* for rx_highest */ -#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT 13 -#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK (7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT) - -/* for tx_highest */ -#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE (1 << 13) - -/** - * enum ieee80211_vht_mcs_support - VHT MCS support definitions - * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the - * number of streams - * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported - * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported - * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported - * - * These definitions are used in each 2-bit subfield of the @rx_mcs_map - * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are - * both split into 8 subfields by number of streams. These values indicate - * which MCSes are supported for the number of streams the value appears - * for. - */ -enum ieee80211_vht_mcs_support { - IEEE80211_VHT_MCS_SUPPORT_0_7 = 0, - IEEE80211_VHT_MCS_SUPPORT_0_8 = 1, - IEEE80211_VHT_MCS_SUPPORT_0_9 = 2, - IEEE80211_VHT_MCS_NOT_SUPPORTED = 3, -}; - -/** - * struct ieee80211_vht_cap - VHT capabilities - * - * This structure is the "VHT capabilities element" as - * described in 802.11ac D3.0 8.4.2.160 - * @vht_cap_info: VHT capability info - * @supp_mcs: VHT MCS supported rates - */ -struct ieee80211_vht_cap { - __le32 vht_cap_info; - struct ieee80211_vht_mcs_info supp_mcs; -} __packed; - -/** - * enum ieee80211_vht_chanwidth - VHT channel width - * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to - * determine the channel width (20 or 40 MHz) - * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth - * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth - * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth - */ -enum ieee80211_vht_chanwidth { - IEEE80211_VHT_CHANWIDTH_USE_HT = 0, - IEEE80211_VHT_CHANWIDTH_80MHZ = 1, - IEEE80211_VHT_CHANWIDTH_160MHZ = 2, - IEEE80211_VHT_CHANWIDTH_80P80MHZ = 3, -}; - -/** - * struct ieee80211_vht_operation - VHT operation IE - * - * This structure is the "VHT operation element" as - * described in 802.11ac D3.0 8.4.2.161 - * @chan_width: Operating channel width - * @center_freq_seg0_idx: center freq segment 0 index - * @center_freq_seg1_idx: center freq segment 1 index - * @basic_mcs_set: VHT Basic MCS rate set - */ -struct ieee80211_vht_operation { - u8 chan_width; - u8 center_freq_seg0_idx; - u8 center_freq_seg1_idx; - __le16 basic_mcs_set; -} __packed; - -/** - * struct ieee80211_he_cap_elem - HE capabilities element - * @mac_cap_info: HE MAC Capabilities Information - * @phy_cap_info: HE PHY Capabilities Information - * - * This structure represents the fixed fields of the payload of the - * "HE capabilities element" as described in IEEE Std 802.11ax-2021 - * sections 9.4.2.248.2 and 9.4.2.248.3. - */ -struct ieee80211_he_cap_elem { - u8 mac_cap_info[6]; - u8 phy_cap_info[11]; -} __packed; - -#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN 5 - -/** - * enum ieee80211_he_mcs_support - HE MCS support definitions - * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the - * number of streams - * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported - * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported - * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported - * - * These definitions are used in each 2-bit subfield of the rx_mcs_* - * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are - * both split into 8 subfields by number of streams. These values indicate - * which MCSes are supported for the number of streams the value appears - * for. - */ -enum ieee80211_he_mcs_support { - IEEE80211_HE_MCS_SUPPORT_0_7 = 0, - IEEE80211_HE_MCS_SUPPORT_0_9 = 1, - IEEE80211_HE_MCS_SUPPORT_0_11 = 2, - IEEE80211_HE_MCS_NOT_SUPPORTED = 3, -}; - -/** - * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field - * - * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field - * described in P802.11ax_D2.0 section 9.4.2.237.4 - * - * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel - * widths less than 80MHz. - * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel - * widths less than 80MHz. - * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel - * width 160MHz. - * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel - * width 160MHz. - * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for - * channel width 80p80MHz. - * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for - * channel width 80p80MHz. - */ -struct ieee80211_he_mcs_nss_supp { - __le16 rx_mcs_80; - __le16 tx_mcs_80; - __le16 rx_mcs_160; - __le16 tx_mcs_160; - __le16 rx_mcs_80p80; - __le16 tx_mcs_80p80; -} __packed; - -/** - * struct ieee80211_he_operation - HE Operation element - * @he_oper_params: HE Operation Parameters + BSS Color Information - * @he_mcs_nss_set: Basic HE-MCS And NSS Set - * @optional: Optional fields VHT Operation Information, Max Co-Hosted - * BSSID Indicator, and 6 GHz Operation Information - * - * This structure represents the payload of the "HE Operation - * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249. - */ -struct ieee80211_he_operation { - __le32 he_oper_params; - __le16 he_mcs_nss_set; - u8 optional[]; -} __packed; - -/** - * struct ieee80211_he_spr - Spatial Reuse Parameter Set element - * @he_sr_control: SR Control - * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD - * Min Offset, SRG OBSS PD Max Offset, SRG BSS Color - * Bitmap, and SRG Partial BSSID Bitmap - * - * This structure represents the payload of the "Spatial Reuse - * Parameter Set element" as described in IEEE Std 802.11ax-2021 - * section 9.4.2.252. - */ -struct ieee80211_he_spr { - u8 he_sr_control; - u8 optional[]; -} __packed; - -/** - * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field - * @aifsn: ACI/AIFSN - * @ecw_min_max: ECWmin/ECWmax - * @mu_edca_timer: MU EDCA Timer - * - * This structure represents the "MU AC Parameter Record" as described - * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p. - */ -struct ieee80211_he_mu_edca_param_ac_rec { - u8 aifsn; - u8 ecw_min_max; - u8 mu_edca_timer; -} __packed; - -/** - * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element - * @mu_qos_info: QoS Info - * @ac_be: MU AC_BE Parameter Record - * @ac_bk: MU AC_BK Parameter Record - * @ac_vi: MU AC_VI Parameter Record - * @ac_vo: MU AC_VO Parameter Record - * - * This structure represents the payload of the "MU EDCA Parameter Set - * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251. - */ -struct ieee80211_mu_edca_param_set { - u8 mu_qos_info; - struct ieee80211_he_mu_edca_param_ac_rec ac_be; - struct ieee80211_he_mu_edca_param_ac_rec ac_bk; - struct ieee80211_he_mu_edca_param_ac_rec ac_vi; - struct ieee80211_he_mu_edca_param_ac_rec ac_vo; -} __packed; - -#define IEEE80211_EHT_MCS_NSS_RX 0x0f -#define IEEE80211_EHT_MCS_NSS_TX 0xf0 - -/** - * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max - * supported NSS for per MCS. - * - * For each field below, bits 0 - 3 indicate the maximal number of spatial - * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams - * for Tx. - * - * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 0 - 7. - * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 8 - 9. - * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 10 - 11. - * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 12 - 13. - * @rx_tx_max_nss: array of the previous fields for easier loop access - */ -struct ieee80211_eht_mcs_nss_supp_20mhz_only { - union { - struct { - u8 rx_tx_mcs7_max_nss; - u8 rx_tx_mcs9_max_nss; - u8 rx_tx_mcs11_max_nss; - u8 rx_tx_mcs13_max_nss; - }; - u8 rx_tx_max_nss[4]; - }; -}; - -/** - * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except - * 20MHz only stations). - * - * For each field below, bits 0 - 3 indicate the maximal number of spatial - * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams - * for Tx. - * - * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 0 - 9. - * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 10 - 11. - * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams - * supported for reception and the maximum number of spatial streams - * supported for transmission for MCS 12 - 13. - * @rx_tx_max_nss: array of the previous fields for easier loop access - */ -struct ieee80211_eht_mcs_nss_supp_bw { - union { - struct { - u8 rx_tx_mcs9_max_nss; - u8 rx_tx_mcs11_max_nss; - u8 rx_tx_mcs13_max_nss; - }; - u8 rx_tx_max_nss[3]; - }; -}; - -/** - * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data - * - * This structure is the "EHT Capabilities element" fixed fields as - * described in P802.11be_D2.0 section 9.4.2.313. - * - * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP* - * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP* - */ -struct ieee80211_eht_cap_elem_fixed { - u8 mac_cap_info[2]; - u8 phy_cap_info[9]; -} __packed; - -/** - * struct ieee80211_eht_cap_elem - EHT capabilities element - * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed - * @optional: optional parts - */ -struct ieee80211_eht_cap_elem { - struct ieee80211_eht_cap_elem_fixed fixed; - - /* - * Followed by: - * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets. - * EHT PPE Thresholds field: variable length. - */ - u8 optional[]; -} __packed; - -#define IEEE80211_EHT_OPER_INFO_PRESENT 0x01 -#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT 0x02 -#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION 0x04 -#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT 0x08 -#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK 0x30 -#define IEEE80211_EHT_OPER_MCS15_DISABLE 0x40 - -/** - * struct ieee80211_eht_operation - eht operation element - * - * This structure is the "EHT Operation Element" fields as - * described in P802.11be_D2.0 section 9.4.2.311 - * - * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_* - * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in - * EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and - * receive. - * @optional: optional parts - */ -struct ieee80211_eht_operation { - u8 params; - struct ieee80211_eht_mcs_nss_supp_20mhz_only basic_mcs_nss; - u8 optional[]; -} __packed; - -/** - * struct ieee80211_eht_operation_info - eht operation information - * - * @control: EHT operation information control. - * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz - * EHT BSS. - * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS. - * @optional: optional parts - */ -struct ieee80211_eht_operation_info { - u8 control; - u8 ccfs0; - u8 ccfs1; - u8 optional[]; -} __packed; - -/* 802.11ac VHT Capabilities */ -#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895 0x00000000 -#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991 0x00000001 -#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454 0x00000002 -#define IEEE80211_VHT_CAP_MAX_MPDU_MASK 0x00000003 -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ 0x00000004 -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ 0x00000008 -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK 0x0000000C -#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT 2 -#define IEEE80211_VHT_CAP_RXLDPC 0x00000010 -#define IEEE80211_VHT_CAP_SHORT_GI_80 0x00000020 -#define IEEE80211_VHT_CAP_SHORT_GI_160 0x00000040 -#define IEEE80211_VHT_CAP_TXSTBC 0x00000080 -#define IEEE80211_VHT_CAP_RXSTBC_1 0x00000100 -#define IEEE80211_VHT_CAP_RXSTBC_2 0x00000200 -#define IEEE80211_VHT_CAP_RXSTBC_3 0x00000300 -#define IEEE80211_VHT_CAP_RXSTBC_4 0x00000400 -#define IEEE80211_VHT_CAP_RXSTBC_MASK 0x00000700 -#define IEEE80211_VHT_CAP_RXSTBC_SHIFT 8 -#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE 0x00000800 -#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE 0x00001000 -#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT 13 -#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK \ - (7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT) -#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT 16 -#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK \ - (7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT) -#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE 0x00080000 -#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE 0x00100000 -#define IEEE80211_VHT_CAP_VHT_TXOP_PS 0x00200000 -#define IEEE80211_VHT_CAP_HTC_VHT 0x00400000 -#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT 23 -#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK \ - (7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT) -#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB 0x08000000 -#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB 0x0c000000 -#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN 0x10000000 -#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN 0x20000000 -#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT 30 -#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK 0xc0000000 - -/** - * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS - * @cap: VHT capabilities of the peer - * @bw: bandwidth to use - * @mcs: MCS index to use - * @ext_nss_bw_capable: indicates whether or not the local transmitter - * (rate scaling algorithm) can deal with the new logic - * (dot11VHTExtendedNSSBWCapable) - * @max_vht_nss: current maximum NSS as advertised by the STA in - * operating mode notification, can be 0 in which case the - * capability data will be used to derive this (from MCS support) - * Return: The maximum NSS that can be used for the given bandwidth/MCS - * combination - * - * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can - * vary for a given BW/MCS. This function parses the data. - * - * Note: This function is exported by cfg80211. - */ -int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap, - enum ieee80211_vht_chanwidth bw, - int mcs, bool ext_nss_bw_capable, - unsigned int max_vht_nss); - -/* 802.11ax HE MAC capabilities */ -#define IEEE80211_HE_MAC_CAP0_HTC_HE 0x01 -#define IEEE80211_HE_MAC_CAP0_TWT_REQ 0x02 -#define IEEE80211_HE_MAC_CAP0_TWT_RES 0x04 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP 0x00 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1 0x08 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2 0x10 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3 0x18 -#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK 0x18 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1 0x00 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2 0x20 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4 0x40 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8 0x60 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16 0x80 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32 0xa0 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64 0xc0 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED 0xe0 -#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK 0xe0 - -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED 0x00 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128 0x01 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256 0x02 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512 0x03 -#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK 0x03 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US 0x00 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US 0x04 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US 0x08 -#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK 0x0c -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1 0x00 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2 0x10 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3 0x20 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4 0x30 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5 0x40 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6 0x50 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7 0x60 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8 0x70 -#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK 0x70 - -/* Link adaptation is split between byte HE_MAC_CAP1 and - * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE - * in which case the following values apply: - * 0 = No feedback. - * 1 = reserved. - * 2 = Unsolicited feedback. - * 3 = both - */ -#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION 0x80 - -#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION 0x01 -#define IEEE80211_HE_MAC_CAP2_ALL_ACK 0x02 -#define IEEE80211_HE_MAC_CAP2_TRS 0x04 -#define IEEE80211_HE_MAC_CAP2_BSR 0x08 -#define IEEE80211_HE_MAC_CAP2_BCAST_TWT 0x10 -#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP 0x20 -#define IEEE80211_HE_MAC_CAP2_MU_CASCADING 0x40 -#define IEEE80211_HE_MAC_CAP2_ACK_EN 0x80 - -#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL 0x02 -#define IEEE80211_HE_MAC_CAP3_OFDMA_RA 0x04 - -/* The maximum length of an A-MDPU is defined by the combination of the Maximum - * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the - * same field in the HE capabilities. - */ -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0 0x00 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1 0x08 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2 0x10 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3 0x18 -#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK 0x18 -#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG 0x20 -#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED 0x40 -#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS 0x80 - -#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG 0x01 -#define IEEE80211_HE_MAC_CAP4_QTP 0x02 -#define IEEE80211_HE_MAC_CAP4_BQR 0x04 -#define IEEE80211_HE_MAC_CAP4_PSR_RESP 0x08 -#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP 0x10 -#define IEEE80211_HE_MAC_CAP4_OPS 0x20 -#define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU 0x40 -/* Multi TID agg TX is split between byte #4 and #5 - * The value is a combination of B39,B40,B41 - */ -#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39 0x80 - -#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40 0x01 -#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41 0x02 -#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION 0x04 -#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU 0x08 -#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX 0x10 -#define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS 0x20 -#define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING 0x40 -#define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX 0x80 - -#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR 20 -#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR 16 -#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR 13 - -/* 802.11ax HE PHY capabilities */ -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G 0x02 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G 0x04 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G 0x08 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G 0x10 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL 0x1e - -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G 0x20 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G 0x40 -#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK 0xfe - -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ 0x01 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ 0x02 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ 0x04 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ 0x08 -#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK 0x0f -#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A 0x10 -#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD 0x20 -#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US 0x40 -/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */ -#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS 0x80 - -#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS 0x01 -#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US 0x02 -#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ 0x04 -#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ 0x08 -#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX 0x10 -#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX 0x20 - -/* Note that the meaning of UL MU below is different between an AP and a non-AP - * sta, where in the AP case it indicates support for Rx and in the non-AP sta - * case it indicates support for Tx. - */ -#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO 0x40 -#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO 0x80 - -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK 0x01 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK 0x02 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM 0x03 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK 0x03 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2 0x04 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK 0x08 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK 0x10 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM 0x18 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK 0x18 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1 0x00 -#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2 0x20 -#define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU 0x40 -#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER 0x80 - -#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE 0x01 -#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER 0x02 - -/* Minimal allowed value of Max STS under 80MHz is 3 */ -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4 0x0c -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5 0x10 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6 0x14 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7 0x18 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8 0x1c -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK 0x1c - -/* Minimal allowed value of Max STS above 80MHz is 3 */ -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4 0x60 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5 0x80 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6 0xa0 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7 0xc0 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 0xe0 -#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK 0xe0 - -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1 0x00 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 0x01 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3 0x02 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4 0x03 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5 0x04 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6 0x05 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7 0x06 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8 0x07 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK 0x07 - -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1 0x00 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2 0x08 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3 0x10 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4 0x18 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5 0x20 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6 0x28 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7 0x30 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8 0x38 -#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK 0x38 - -#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK 0x40 -#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK 0x80 - -#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU 0x01 -#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU 0x02 -#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB 0x04 -#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB 0x08 -#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB 0x10 -#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE 0x20 -#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO 0x40 -#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT 0x80 - -#define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR 0x01 -#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP 0x02 -#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI 0x04 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_1 0x08 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_2 0x10 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_3 0x18 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_4 0x20 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_5 0x28 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_6 0x30 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_7 0x38 -#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK 0x38 -#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ 0x40 -#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ 0x80 - -#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI 0x01 -#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G 0x02 -#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU 0x04 -#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU 0x08 -#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI 0x10 -#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF 0x20 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242 0x00 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484 0x40 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996 0x80 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996 0xc0 -#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK 0xc0 - -#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM 0x01 -#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK 0x02 -#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU 0x04 -#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 -#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 -#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 -#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 - -#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 - -/* 802.11ax HE TX/RX MCS NSS Support */ -#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS (3) -#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS (6) -#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS (11) -#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK 0x07c0 -#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK 0xf800 - -/* TX/RX HE MCS Support field Highest MCS subfield encoding */ -enum ieee80211_he_highest_mcs_supported_subfield_enc { - HIGHEST_MCS_SUPPORTED_MCS7 = 0, - HIGHEST_MCS_SUPPORTED_MCS8, - HIGHEST_MCS_SUPPORTED_MCS9, - HIGHEST_MCS_SUPPORTED_MCS10, - HIGHEST_MCS_SUPPORTED_MCS11, -}; - -/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */ -static inline u8 -ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap) -{ - u8 count = 4; - - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) - count += 4; - - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G) - count += 4; - - return count; -} - -/* 802.11ax HE PPE Thresholds */ -#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS (1) -#define IEEE80211_PPE_THRES_NSS_POS (0) -#define IEEE80211_PPE_THRES_NSS_MASK (7) -#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU \ - (BIT(5) | BIT(6)) -#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK 0x78 -#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS (3) -#define IEEE80211_PPE_THRES_INFO_PPET_SIZE (3) -#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE (7) - -/* - * Calculate 802.11ax HE capabilities IE PPE field size - * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8* - */ -static inline u8 -ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info) -{ - u8 n; - - if ((phy_cap_info[6] & - IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0) - return 0; - - n = hweight8(ppe_thres_hdr & - IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK); - n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >> - IEEE80211_PPE_THRES_NSS_POS)); - - /* - * Each pair is 6 bits, and we need to add the 7 "header" bits to the - * total size. - */ - n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7; - n = DIV_ROUND_UP(n, 8); - - return n; -} - -static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len) -{ - const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data; - u8 needed = sizeof(*he_cap_ie_elem); - - if (len < needed) - return false; - - needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem); - if (len < needed) - return false; - - if (he_cap_ie_elem->phy_cap_info[6] & - IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) { - if (len < needed + 1) - return false; - needed += ieee80211_he_ppe_size(data[needed], - he_cap_ie_elem->phy_cap_info); - } - - return len >= needed; -} - -/* HE Operation defines */ -#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK 0x00000007 -#define IEEE80211_HE_OPERATION_TWT_REQUIRED 0x00000008 -#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK 0x00003ff0 -#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET 4 -#define IEEE80211_HE_OPERATION_VHT_OPER_INFO 0x00004000 -#define IEEE80211_HE_OPERATION_CO_HOSTED_BSS 0x00008000 -#define IEEE80211_HE_OPERATION_ER_SU_DISABLE 0x00010000 -#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO 0x00020000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK 0x3f000000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET 24 -#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR 0x40000000 -#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED 0x80000000 - -#define IEEE80211_6GHZ_CTRL_REG_LPI_AP 0 -#define IEEE80211_6GHZ_CTRL_REG_SP_AP 1 -#define IEEE80211_6GHZ_CTRL_REG_VLP_AP 2 -#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP 3 -#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD 4 -#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP 8 - -/** - * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field - * @primary: primary channel - * @control: control flags - * @ccfs0: channel center frequency segment 0 - * @ccfs1: channel center frequency segment 1 - * @minrate: minimum rate (in 1 Mbps units) - */ -struct ieee80211_he_6ghz_oper { - u8 primary; -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH 0x3 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ 0 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ 1 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ 2 -#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ 3 -#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON 0x4 -#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO 0x78 - u8 control; - u8 ccfs0; - u8 ccfs1; - u8 minrate; -} __packed; - -/** - * enum ieee80211_reg_conn_bits - represents Regulatory connectivity field bits. - * - * This enumeration defines bit flags used to represent regulatory connectivity - * field bits. - * - * @IEEE80211_REG_CONN_LPI_VALID: Indicates whether the LPI bit is valid. - * @IEEE80211_REG_CONN_LPI_VALUE: Represents the value of the LPI bit. - * @IEEE80211_REG_CONN_SP_VALID: Indicates whether the SP bit is valid. - * @IEEE80211_REG_CONN_SP_VALUE: Represents the value of the SP bit. - */ -enum ieee80211_reg_conn_bits { - IEEE80211_REG_CONN_LPI_VALID = BIT(0), - IEEE80211_REG_CONN_LPI_VALUE = BIT(1), - IEEE80211_REG_CONN_SP_VALID = BIT(2), - IEEE80211_REG_CONN_SP_VALUE = BIT(3), -}; - -/* transmit power interpretation type of transmit power envelope element */ -enum ieee80211_tx_power_intrpt_type { - IEEE80211_TPE_LOCAL_EIRP, - IEEE80211_TPE_LOCAL_EIRP_PSD, - IEEE80211_TPE_REG_CLIENT_EIRP, - IEEE80211_TPE_REG_CLIENT_EIRP_PSD, -}; - -/* category type of transmit power envelope element */ -enum ieee80211_tx_power_category_6ghz { - IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0, - IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1, -}; - -/* - * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP, - * setting to 63.5 dBm means no constraint. - */ -#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT 127 - -/* - * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD, - * setting to 127 indicates no PSD limit for the 20 MHz channel. - */ -#define IEEE80211_TPE_PSD_NO_LIMIT 127 - -/** - * struct ieee80211_tx_pwr_env - Transmit Power Envelope - * @info: Transmit Power Information field - * @variable: Maximum Transmit Power field - * - * This structure represents the payload of the "Transmit Power - * Envelope element" as described in IEEE Std 802.11ax-2021 section - * 9.4.2.161 - */ -struct ieee80211_tx_pwr_env { - u8 info; - u8 variable[]; -} __packed; - -#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7 -#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38 -#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0 - -#define IEEE80211_TX_PWR_ENV_EXT_COUNT 0xF - -static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len) -{ - const struct ieee80211_tx_pwr_env *env = (const void *)data; - u8 count, interpret, category; - u8 needed = sizeof(*env); - u8 N; /* also called N in the spec */ - - if (len < needed) - return false; - - count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT); - interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET); - category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY); - - switch (category) { - case IEEE80211_TPE_CAT_6GHZ_DEFAULT: - case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE: - break; - default: - return false; - } - - switch (interpret) { - case IEEE80211_TPE_LOCAL_EIRP: - case IEEE80211_TPE_REG_CLIENT_EIRP: - if (count > 3) - return false; - - /* count == 0 encodes 1 value for 20 MHz, etc. */ - needed += count + 1; - - if (len < needed) - return false; - - /* there can be extension fields not accounted for in 'count' */ - - return true; - case IEEE80211_TPE_LOCAL_EIRP_PSD: - case IEEE80211_TPE_REG_CLIENT_EIRP_PSD: - if (count > 4) - return false; - - N = count ? 1 << (count - 1) : 1; - needed += N; - - if (len < needed) - return false; - - if (len > needed) { - u8 K = u8_get_bits(env->variable[N], - IEEE80211_TX_PWR_ENV_EXT_COUNT); - - needed += 1 + K; - if (len < needed) - return false; - } - - return true; - } - - return false; -} - -/* - * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size - * @he_oper_ie: byte data of the He Operations IE, stating from the byte - * after the ext ID byte. It is assumed that he_oper_ie has at least - * sizeof(struct ieee80211_he_operation) bytes, the caller must have - * validated this. - * @return the actual size of the IE data (not including header), or 0 on error - */ -static inline u8 -ieee80211_he_oper_size(const u8 *he_oper_ie) -{ - const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie; - u8 oper_len = sizeof(struct ieee80211_he_operation); - u32 he_oper_params; - - /* Make sure the input is not NULL */ - if (!he_oper_ie) - return 0; - - /* Calc required length */ - he_oper_params = le32_to_cpu(he_oper->he_oper_params); - if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) - oper_len += 3; - if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) - oper_len++; - if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO) - oper_len += sizeof(struct ieee80211_he_6ghz_oper); - - /* Add the first byte (extension ID) to the total length */ - oper_len++; - - return oper_len; -} - -/** - * ieee80211_he_6ghz_oper - obtain 6 GHz operation field - * @he_oper: HE operation element (must be pre-validated for size) - * but may be %NULL - * - * Return: a pointer to the 6 GHz operation field, or %NULL - */ -static inline const struct ieee80211_he_6ghz_oper * -ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper) -{ - const u8 *ret; - u32 he_oper_params; - - if (!he_oper) - return NULL; - - ret = (const void *)&he_oper->optional; - - he_oper_params = le32_to_cpu(he_oper->he_oper_params); - - if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)) - return NULL; - if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO) - ret += 3; - if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS) - ret++; - - return (const void *)ret; -} - -/* HE Spatial Reuse defines */ -#define IEEE80211_HE_SPR_PSR_DISALLOWED BIT(0) -#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED BIT(1) -#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT BIT(2) -#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT BIT(3) -#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED BIT(4) - -/* - * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size - * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte - * after the ext ID byte. It is assumed that he_spr_ie has at least - * sizeof(struct ieee80211_he_spr) bytes, the caller must have validated - * this - * @return the actual size of the IE data (not including header), or 0 on error - */ -static inline u8 -ieee80211_he_spr_size(const u8 *he_spr_ie) -{ - const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie; - u8 spr_len = sizeof(struct ieee80211_he_spr); - u8 he_spr_params; - - /* Make sure the input is not NULL */ - if (!he_spr_ie) - return 0; - - /* Calc required length */ - he_spr_params = he_spr->he_sr_control; - if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT) - spr_len++; - if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT) - spr_len += 18; - - /* Add the first byte (extension ID) to the total length */ - spr_len++; - - return spr_len; -} - -/* S1G Capabilities Information field */ -#define IEEE80211_S1G_CAPABILITY_LEN 15 - -#define S1G_CAP0_S1G_LONG BIT(0) -#define S1G_CAP0_SGI_1MHZ BIT(1) -#define S1G_CAP0_SGI_2MHZ BIT(2) -#define S1G_CAP0_SGI_4MHZ BIT(3) -#define S1G_CAP0_SGI_8MHZ BIT(4) -#define S1G_CAP0_SGI_16MHZ BIT(5) -#define S1G_CAP0_SUPP_CH_WIDTH GENMASK(7, 6) - -#define S1G_SUPP_CH_WIDTH_2 0 -#define S1G_SUPP_CH_WIDTH_4 1 -#define S1G_SUPP_CH_WIDTH_8 2 -#define S1G_SUPP_CH_WIDTH_16 3 -#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \ - cap[0])) << 1) - -#define S1G_CAP1_RX_LDPC BIT(0) -#define S1G_CAP1_TX_STBC BIT(1) -#define S1G_CAP1_RX_STBC BIT(2) -#define S1G_CAP1_SU_BFER BIT(3) -#define S1G_CAP1_SU_BFEE BIT(4) -#define S1G_CAP1_BFEE_STS GENMASK(7, 5) - -#define S1G_CAP2_SOUNDING_DIMENSIONS GENMASK(2, 0) -#define S1G_CAP2_MU_BFER BIT(3) -#define S1G_CAP2_MU_BFEE BIT(4) -#define S1G_CAP2_PLUS_HTC_VHT BIT(5) -#define S1G_CAP2_TRAVELING_PILOT GENMASK(7, 6) - -#define S1G_CAP3_RD_RESPONDER BIT(0) -#define S1G_CAP3_HT_DELAYED_BA BIT(1) -#define S1G_CAP3_MAX_MPDU_LEN BIT(2) -#define S1G_CAP3_MAX_AMPDU_LEN_EXP GENMASK(4, 3) -#define S1G_CAP3_MIN_MPDU_START GENMASK(7, 5) - -#define S1G_CAP4_UPLINK_SYNC BIT(0) -#define S1G_CAP4_DYNAMIC_AID BIT(1) -#define S1G_CAP4_BAT BIT(2) -#define S1G_CAP4_TIME_ADE BIT(3) -#define S1G_CAP4_NON_TIM BIT(4) -#define S1G_CAP4_GROUP_AID BIT(5) -#define S1G_CAP4_STA_TYPE GENMASK(7, 6) - -#define S1G_CAP5_CENT_AUTH_CONTROL BIT(0) -#define S1G_CAP5_DIST_AUTH_CONTROL BIT(1) -#define S1G_CAP5_AMSDU BIT(2) -#define S1G_CAP5_AMPDU BIT(3) -#define S1G_CAP5_ASYMMETRIC_BA BIT(4) -#define S1G_CAP5_FLOW_CONTROL BIT(5) -#define S1G_CAP5_SECTORIZED_BEAM GENMASK(7, 6) - -#define S1G_CAP6_OBSS_MITIGATION BIT(0) -#define S1G_CAP6_FRAGMENT_BA BIT(1) -#define S1G_CAP6_NDP_PS_POLL BIT(2) -#define S1G_CAP6_RAW_OPERATION BIT(3) -#define S1G_CAP6_PAGE_SLICING BIT(4) -#define S1G_CAP6_TXOP_SHARING_IMP_ACK BIT(5) -#define S1G_CAP6_VHT_LINK_ADAPT GENMASK(7, 6) - -#define S1G_CAP7_TACK_AS_PS_POLL BIT(0) -#define S1G_CAP7_DUP_1MHZ BIT(1) -#define S1G_CAP7_MCS_NEGOTIATION BIT(2) -#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE BIT(3) -#define S1G_CAP7_NDP_BFING_REPORT_POLL BIT(4) -#define S1G_CAP7_UNSOLICITED_DYN_AID BIT(5) -#define S1G_CAP7_SECTOR_TRAINING_OPERATION BIT(6) -#define S1G_CAP7_TEMP_PS_MODE_SWITCH BIT(7) - -#define S1G_CAP8_TWT_GROUPING BIT(0) -#define S1G_CAP8_BDT BIT(1) -#define S1G_CAP8_COLOR GENMASK(4, 2) -#define S1G_CAP8_TWT_REQUEST BIT(5) -#define S1G_CAP8_TWT_RESPOND BIT(6) -#define S1G_CAP8_PV1_FRAME BIT(7) - -#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0) - -#define S1G_OPER_CH_WIDTH_PRIMARY BIT(0) -#define S1G_OPER_CH_WIDTH_OPER GENMASK(4, 1) -#define S1G_OPER_CH_PRIMARY_LOCATION BIT(5) - -#define S1G_2M_PRIMARY_LOCATION_LOWER 0 -#define S1G_2M_PRIMARY_LOCATION_UPPER 1 - -/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */ -#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS 0x01 -#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL 0x02 -#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 0x04 -#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 0x08 -#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT 0x10 -#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC 0x20 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK 0xc0 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895 0 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991 1 -#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454 2 - -#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK 0x01 -#define IEEE80211_EHT_MAC_CAP1_EHT_TRS 0x02 -#define IEEE80211_EHT_MAC_CAP1_TXOP_RET 0x04 -#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS 0x08 -#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK 0x30 -#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS 0x40 - -/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */ -#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ 0x02 -#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ 0x04 -#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI 0x08 -#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO 0x10 -#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER 0x20 -#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE 0x40 - -/* EHT beamformee number of spatial streams <= 80MHz is split */ -#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK 0x80 -#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK 0x03 - -#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK 0x1c -#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK 0xe0 - -#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK 0x07 -#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK 0x38 - -/* EHT number of sounding dimensions for 320MHz is split */ -#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK 0xc0 -#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK 0x01 -#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK 0x02 -#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK 0x04 -#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK 0x08 -#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK 0x10 -#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK 0x20 -#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK 0x40 -#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK 0x80 - -#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO 0x01 -#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP 0x02 -#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP 0x04 -#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI 0x08 -#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK 0xf0 - -#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK 0x01 -#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP 0x02 -#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP 0x04 -#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT 0x08 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK 0x30 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US 0 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US 1 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US 2 -#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US 3 - -/* Maximum number of supported EHT LTF is split */ -#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK 0xc0 -#define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF 0x40 -#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK 0x07 - -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ 0x08 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ 0x30 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ 0x40 -#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK 0x78 -#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP 0x80 - -#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW 0x01 -#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ 0x02 -#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ 0x04 -#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ 0x08 -#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ 0x10 -#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ 0x20 -#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ 0x40 -#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT 0x80 - -#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA 0x01 -#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA 0x02 - -/* - * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311 - */ -#define IEEE80211_EHT_OPER_CHAN_WIDTH 0x7 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ 0 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ 1 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ 2 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ 3 -#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ 4 - -/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */ -static inline u8 -ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap, - const struct ieee80211_eht_cap_elem_fixed *eht_cap, - bool from_ap) -{ - u8 count = 0; - - /* on 2.4 GHz, if it supports 40 MHz, the result is 3 */ - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G) - return 3; - - /* on 2.4 GHz, these three bits are reserved, so should be 0 */ - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G) - count += 3; - - if (he_cap->phy_cap_info[0] & - IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G) - count += 3; - - if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ) - count += 3; - - if (count) - return count; - - return from_ap ? 3 : 4; -} - -/* 802.11be EHT PPE Thresholds */ -#define IEEE80211_EHT_PPE_THRES_NSS_POS 0 -#define IEEE80211_EHT_PPE_THRES_NSS_MASK 0xf -#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK 0x1f0 -#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE 3 -#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE 9 - -/* - * Calculate 802.11be EHT capabilities IE EHT field size - */ -static inline u8 -ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info) -{ - u32 n; - - if (!(phy_cap_info[5] & - IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT)) - return 0; - - n = hweight16(ppe_thres_hdr & - IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK); - n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK); - - /* - * Each pair is 6 bits, and we need to add the 9 "header" bits to the - * total size. - */ - n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 + - IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE; - return DIV_ROUND_UP(n, 8); -} - -static inline bool -ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len, - bool from_ap) -{ - const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data; - u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed); - - if (len < needed || !he_capa) - return false; - - needed += ieee80211_eht_mcs_nss_size((const void *)he_capa, - (const void *)data, - from_ap); - if (len < needed) - return false; - - if (elem->phy_cap_info[5] & - IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) { - u16 ppe_thres_hdr; - - if (len < needed + sizeof(ppe_thres_hdr)) - return false; - - ppe_thres_hdr = get_unaligned_le16(data + needed); - needed += ieee80211_eht_ppe_size(ppe_thres_hdr, - elem->phy_cap_info); - } - - return len >= needed; -} - -static inline bool -ieee80211_eht_oper_size_ok(const u8 *data, u8 len) -{ - const struct ieee80211_eht_operation *elem = (const void *)data; - u8 needed = sizeof(*elem); - - if (len < needed) - return false; - - if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) { - needed += 3; - - if (elem->params & - IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT) - needed += 2; - } - - return len >= needed; -} - -/* must validate ieee80211_eht_oper_size_ok() first */ -static inline u16 -ieee80211_eht_oper_dis_subchan_bitmap(const struct ieee80211_eht_operation *eht_oper) -{ - const struct ieee80211_eht_operation_info *info = - (const void *)eht_oper->optional; - - if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT)) - return 0; - - if (!(eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)) - return 0; - - return get_unaligned_le16(info->optional); -} - -#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) - -struct ieee80211_bandwidth_indication { - u8 params; - struct ieee80211_eht_operation_info info; -} __packed; - -static inline bool -ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) -{ - const struct ieee80211_bandwidth_indication *bwi = (const void *)data; - - if (len < sizeof(*bwi)) - return false; - - if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && - len < sizeof(*bwi) + 2) - return false; - - return true; -} - -#define LISTEN_INT_USF GENMASK(15, 14) -#define LISTEN_INT_UI GENMASK(13, 0) - -#define IEEE80211_MAX_USF FIELD_MAX(LISTEN_INT_USF) -#define IEEE80211_MAX_UI FIELD_MAX(LISTEN_INT_UI) - -/* Authentication algorithms */ -#define WLAN_AUTH_OPEN 0 -#define WLAN_AUTH_SHARED_KEY 1 -#define WLAN_AUTH_FT 2 -#define WLAN_AUTH_SAE 3 -#define WLAN_AUTH_FILS_SK 4 -#define WLAN_AUTH_FILS_SK_PFS 5 -#define WLAN_AUTH_FILS_PK 6 -#define WLAN_AUTH_LEAP 128 - -#define WLAN_AUTH_CHALLENGE_LEN 128 - -#define WLAN_CAPABILITY_ESS (1<<0) -#define WLAN_CAPABILITY_IBSS (1<<1) - -/* - * A mesh STA sets the ESS and IBSS capability bits to zero. - * however, this holds true for p2p probe responses (in the p2p_find - * phase) as well. - */ -#define WLAN_CAPABILITY_IS_STA_BSS(cap) \ - (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS))) - -#define WLAN_CAPABILITY_CF_POLLABLE (1<<2) -#define WLAN_CAPABILITY_CF_POLL_REQUEST (1<<3) -#define WLAN_CAPABILITY_PRIVACY (1<<4) -#define WLAN_CAPABILITY_SHORT_PREAMBLE (1<<5) -#define WLAN_CAPABILITY_PBCC (1<<6) -#define WLAN_CAPABILITY_CHANNEL_AGILITY (1<<7) - -/* 802.11h */ -#define WLAN_CAPABILITY_SPECTRUM_MGMT (1<<8) -#define WLAN_CAPABILITY_QOS (1<<9) -#define WLAN_CAPABILITY_SHORT_SLOT_TIME (1<<10) -#define WLAN_CAPABILITY_APSD (1<<11) -#define WLAN_CAPABILITY_RADIO_MEASURE (1<<12) -#define WLAN_CAPABILITY_DSSS_OFDM (1<<13) -#define WLAN_CAPABILITY_DEL_BACK (1<<14) -#define WLAN_CAPABILITY_IMM_BACK (1<<15) - -/* DMG (60gHz) 802.11ad */ -/* type - bits 0..1 */ -#define WLAN_CAPABILITY_DMG_TYPE_MASK (3<<0) -#define WLAN_CAPABILITY_DMG_TYPE_IBSS (1<<0) /* Tx by: STA */ -#define WLAN_CAPABILITY_DMG_TYPE_PBSS (2<<0) /* Tx by: PCP */ -#define WLAN_CAPABILITY_DMG_TYPE_AP (3<<0) /* Tx by: AP */ - -#define WLAN_CAPABILITY_DMG_CBAP_ONLY (1<<2) -#define WLAN_CAPABILITY_DMG_CBAP_SOURCE (1<<3) -#define WLAN_CAPABILITY_DMG_PRIVACY (1<<4) -#define WLAN_CAPABILITY_DMG_ECPAC (1<<5) - -#define WLAN_CAPABILITY_DMG_SPECTRUM_MGMT (1<<8) -#define WLAN_CAPABILITY_DMG_RADIO_MEASURE (1<<12) - -/* measurement */ -#define IEEE80211_SPCT_MSR_RPRT_MODE_LATE (1<<0) -#define IEEE80211_SPCT_MSR_RPRT_MODE_INCAPABLE (1<<1) -#define IEEE80211_SPCT_MSR_RPRT_MODE_REFUSED (1<<2) - -#define IEEE80211_SPCT_MSR_RPRT_TYPE_BASIC 0 -#define IEEE80211_SPCT_MSR_RPRT_TYPE_CCA 1 -#define IEEE80211_SPCT_MSR_RPRT_TYPE_RPI 2 -#define IEEE80211_SPCT_MSR_RPRT_TYPE_LCI 8 -#define IEEE80211_SPCT_MSR_RPRT_TYPE_CIVIC 11 - -/* 802.11g ERP information element */ -#define WLAN_ERP_NON_ERP_PRESENT (1<<0) -#define WLAN_ERP_USE_PROTECTION (1<<1) -#define WLAN_ERP_BARKER_PREAMBLE (1<<2) - -/* WLAN_ERP_BARKER_PREAMBLE values */ -enum { - WLAN_ERP_PREAMBLE_SHORT = 0, - WLAN_ERP_PREAMBLE_LONG = 1, -}; - -/* Band ID, 802.11ad #8.4.1.45 */ -enum { - IEEE80211_BANDID_TV_WS = 0, /* TV white spaces */ - IEEE80211_BANDID_SUB1 = 1, /* Sub-1 GHz (excluding TV white spaces) */ - IEEE80211_BANDID_2G = 2, /* 2.4 GHz */ - IEEE80211_BANDID_3G = 3, /* 3.6 GHz */ - IEEE80211_BANDID_5G = 4, /* 4.9 and 5 GHz */ - IEEE80211_BANDID_60G = 5, /* 60 GHz */ +/* Band ID, 802.11ad #8.4.1.45 */ +enum { + IEEE80211_BANDID_TV_WS = 0, /* TV white spaces */ + IEEE80211_BANDID_SUB1 = 1, /* Sub-1 GHz (excluding TV white spaces) */ + IEEE80211_BANDID_2G = 2, /* 2.4 GHz */ + IEEE80211_BANDID_3G = 3, /* 3.6 GHz */ + IEEE80211_BANDID_5G = 4, /* 4.9 and 5 GHz */ + IEEE80211_BANDID_60G = 5, /* 60 GHz */ }; /* Status codes */ @@ -3942,25 +1832,6 @@ enum ieee80211_spectrum_mgmt_actioncode { WLAN_ACTION_SPCT_CHL_SWITCH = 4, }; -/* HT action codes */ -enum ieee80211_ht_actioncode { - WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0, - WLAN_HT_ACTION_SMPS = 1, - WLAN_HT_ACTION_PSMP = 2, - WLAN_HT_ACTION_PCO_PHASE = 3, - WLAN_HT_ACTION_CSI = 4, - WLAN_HT_ACTION_NONCOMPRESSED_BF = 5, - WLAN_HT_ACTION_COMPRESSED_BF = 6, - WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7, -}; - -/* VHT action codes */ -enum ieee80211_vht_actioncode { - WLAN_VHT_ACTION_COMPRESSED_BF = 0, - WLAN_VHT_ACTION_GROUPID_MGMT = 1, - WLAN_VHT_ACTION_OPMODE_NOTIF = 2, -}; - /* Self Protected Action codes */ enum ieee80211_self_protected_actioncode { WLAN_SP_RESERVED = 0, @@ -3971,44 +1842,12 @@ enum ieee80211_self_protected_actioncode { WLAN_SP_MGK_ACK = 5, }; -/* Mesh action codes */ -enum ieee80211_mesh_actioncode { - WLAN_MESH_ACTION_LINK_METRIC_REPORT, - WLAN_MESH_ACTION_HWMP_PATH_SELECTION, - WLAN_MESH_ACTION_GATE_ANNOUNCEMENT, - WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION, - WLAN_MESH_ACTION_MCCA_SETUP_REQUEST, - WLAN_MESH_ACTION_MCCA_SETUP_REPLY, - WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST, - WLAN_MESH_ACTION_MCCA_ADVERTISEMENT, - WLAN_MESH_ACTION_MCCA_TEARDOWN, - WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST, - WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE, -}; - /* Unprotected WNM action codes */ enum ieee80211_unprotected_wnm_actioncode { WLAN_UNPROTECTED_WNM_ACTION_TIM = 0, WLAN_UNPROTECTED_WNM_ACTION_TIMING_MEASUREMENT_RESPONSE = 1, }; -/* Protected EHT action codes */ -enum ieee80211_protected_eht_actioncode { - WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0, - WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1, - WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2, - WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3, - WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4, - WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5, - WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6, - WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7, - WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8, - WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9, - WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10, - WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11, - WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12, -}; - /* Security key length */ enum ieee80211_key_len { WLAN_KEY_LEN_WEP40 = 5, @@ -4025,20 +1864,6 @@ enum ieee80211_key_len { WLAN_KEY_LEN_BIP_GMAC_256 = 32, }; -enum ieee80211_s1g_actioncode { - WLAN_S1G_AID_SWITCH_REQUEST, - WLAN_S1G_AID_SWITCH_RESPONSE, - WLAN_S1G_SYNC_CONTROL, - WLAN_S1G_STA_INFO_ANNOUNCE, - WLAN_S1G_EDCA_PARAM_SET, - WLAN_S1G_EL_OPERATION, - WLAN_S1G_TWT_SETUP, - WLAN_S1G_TWT_TEARDOWN, - WLAN_S1G_SECT_GROUP_ID_LIST, - WLAN_S1G_SECT_ID_FEEDBACK, - WLAN_S1G_TWT_INFORMATION = 11, -}; - /* Radio measurement action codes as defined in IEEE 802.11-2024 - Table 9-470 */ enum ieee80211_radio_measurement_actioncode { WLAN_RM_ACTION_RADIO_MEASUREMENT_REQUEST = 0, @@ -4198,65 +2023,6 @@ enum ieee80211_tdls_actioncode { /* BSS Coex IE information field bits */ #define WLAN_BSS_COEX_INFORMATION_REQUEST BIT(0) -/** - * enum ieee80211_mesh_sync_method - mesh synchronization method identifier - * - * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method - * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method - * that will be specified in a vendor specific information element - */ -enum ieee80211_mesh_sync_method { - IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1, - IEEE80211_SYNC_METHOD_VENDOR = 255, -}; - -/** - * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier - * - * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol - * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will - * be specified in a vendor specific information element - */ -enum ieee80211_mesh_path_protocol { - IEEE80211_PATH_PROTOCOL_HWMP = 1, - IEEE80211_PATH_PROTOCOL_VENDOR = 255, -}; - -/** - * enum ieee80211_mesh_path_metric - mesh path selection metric identifier - * - * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric - * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be - * specified in a vendor specific information element - */ -enum ieee80211_mesh_path_metric { - IEEE80211_PATH_METRIC_AIRTIME = 1, - IEEE80211_PATH_METRIC_VENDOR = 255, -}; - -/** - * enum ieee80211_root_mode_identifier - root mesh STA mode identifier - * - * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode - * - * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default) - * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than - * this value - * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports - * the proactive PREQ with proactive PREP subfield set to 0 - * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA - * supports the proactive PREQ with proactive PREP subfield set to 1 - * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports - * the proactive RANN - */ -enum ieee80211_root_mode_identifier { - IEEE80211_ROOTMODE_NO_ROOT = 0, - IEEE80211_ROOTMODE_ROOT = 1, - IEEE80211_PROACTIVE_PREQ_NO_PREP = 2, - IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3, - IEEE80211_PROACTIVE_RANN = 4, -}; - /* * IEEE 802.11-2007 7.3.2.9 Country information element * @@ -4364,19 +2130,6 @@ struct ieee80211_bss_max_idle_period_ie { u8 idle_options; } __packed; -/* BACK action code */ -enum ieee80211_back_actioncode { - WLAN_ACTION_ADDBA_REQ = 0, - WLAN_ACTION_ADDBA_RESP = 1, - WLAN_ACTION_DELBA = 2, -}; - -/* BACK (block-ack) parties */ -enum ieee80211_back_parties { - WLAN_BACK_RECIPIENT = 0, - WLAN_BACK_INITIATOR = 1, -}; - /* SA Query action */ enum ieee80211_sa_query_action { WLAN_ACTION_SA_QUERY_REQUEST = 0, @@ -4510,24 +2263,6 @@ struct ieee80211_tspec_ie { __le16 medium_time; } __packed; -struct ieee80211_he_6ghz_capa { - /* uses IEEE80211_HE_6GHZ_CAP_* below */ - __le16 capa; -} __packed; - -/* HE 6 GHz band capabilities */ -/* uses enum ieee80211_min_mpdu_spacing values */ -#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START 0x0007 -/* uses enum ieee80211_vht_max_ampdu_length_exp values */ -#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP 0x0038 -/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */ -#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN 0x00c0 -/* WLAN_HT_CAP_SM_PS_* values */ -#define IEEE80211_HE_6GHZ_CAP_SM_PS 0x0600 -#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER 0x0800 -#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS 0x1000 -#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS 0x2000 - /** * ieee80211_get_qos_ctl - get pointer to qos control bytes * @hdr: the frame @@ -4779,276 +2514,28 @@ static inline unsigned long ieee80211_tu_to_usec(unsigned long tu) return 1024 * tu; } -static inline bool __ieee80211_check_tim(const struct ieee80211_tim_ie *tim, - u8 tim_len, u16 aid) -{ - u8 mask; - u8 index, indexn1, indexn2; - - if (unlikely(!tim || tim_len < sizeof(*tim))) - return false; - - aid &= 0x3fff; - index = aid / 8; - mask = 1 << (aid & 7); - - indexn1 = tim->bitmap_ctrl & 0xfe; - indexn2 = tim_len + indexn1 - 4; - - if (index < indexn1 || index > indexn2) - return false; - - index -= indexn1; - - return !!(tim->virtual_map[index] & mask); -} - -struct s1g_tim_aid { - u16 aid; - u8 target_blk; /* Target block index */ - u8 target_subblk; /* Target subblock index */ - u8 target_subblk_bit; /* Target subblock bit */ -}; - -struct s1g_tim_enc_block { - u8 enc_mode; - bool inverse; - const u8 *ptr; - u8 len; - - /* - * For an OLB encoded block that spans multiple blocks, this - * is the offset into the span described by that encoded block. - */ - u8 olb_blk_offset; -}; - -/* - * Helper routines to quickly extract the length of an encoded block. Validation - * is also performed to ensure the length extracted lies within the TIM. - */ - -static inline int ieee80211_s1g_len_bitmap(const u8 *ptr, const u8 *end) -{ - u8 blkmap; - u8 n_subblks; - - if (ptr >= end) - return -EINVAL; - - blkmap = *ptr; - n_subblks = hweight8(blkmap); - - if (ptr + 1 + n_subblks > end) - return -EINVAL; - - return 1 + n_subblks; -} - -static inline int ieee80211_s1g_len_single(const u8 *ptr, const u8 *end) -{ - return (ptr + 1 > end) ? -EINVAL : 1; -} - -static inline int ieee80211_s1g_len_olb(const u8 *ptr, const u8 *end) -{ - if (ptr >= end) - return -EINVAL; - - return (ptr + 1 + *ptr > end) ? -EINVAL : 1 + *ptr; -} - -/* - * Enumerate all encoded blocks until we find the encoded block that describes - * our target AID. OLB is a special case as a single encoded block can describe - * multiple blocks as a single encoded block. - */ -static inline int ieee80211_s1g_find_target_block(struct s1g_tim_enc_block *enc, - const struct s1g_tim_aid *aid, - const u8 *ptr, const u8 *end) -{ - /* need at least block-control octet */ - while (ptr + 1 <= end) { - u8 ctrl = *ptr++; - u8 mode = ctrl & 0x03; - bool contains, inverse = ctrl & BIT(2); - u8 span, blk_off = ctrl >> 3; - int len; - - switch (mode) { - case IEEE80211_S1G_TIM_ENC_MODE_BLOCK: - len = ieee80211_s1g_len_bitmap(ptr, end); - contains = blk_off == aid->target_blk; - break; - case IEEE80211_S1G_TIM_ENC_MODE_SINGLE: - len = ieee80211_s1g_len_single(ptr, end); - contains = blk_off == aid->target_blk; - break; - case IEEE80211_S1G_TIM_ENC_MODE_OLB: - len = ieee80211_s1g_len_olb(ptr, end); - /* - * An OLB encoded block can describe more then one - * block, meaning an encoded OLB block can span more - * then a single block. - */ - if (len > 0) { - /* Minus one for the length octet */ - span = DIV_ROUND_UP(len - 1, 8); - /* - * Check if our target block lies within the - * block span described by this encoded block. - */ - contains = (aid->target_blk >= blk_off) && - (aid->target_blk < blk_off + span); - } - break; - default: - return -EOPNOTSUPP; - } - - if (len < 0) - return len; - - if (contains) { - enc->enc_mode = mode; - enc->inverse = inverse; - enc->ptr = ptr; - enc->len = (u8)len; - enc->olb_blk_offset = blk_off; - return 0; - } - - ptr += len; - } - - return -ENOENT; -} - -static inline bool ieee80211_s1g_parse_bitmap(struct s1g_tim_enc_block *enc, - struct s1g_tim_aid *aid) -{ - const u8 *ptr = enc->ptr; - u8 blkmap = *ptr++; - - /* - * If our block bitmap does not contain a set bit that corresponds - * to our AID, it could mean a variety of things depending on if - * the encoding mode is inverted or not. - * - * 1. If inverted, it means the entire subblock is present and hence - * our AID has been set. - * 2. If not inverted, it means our subblock is not present and hence - * it is all zero meaning our AID is not set. - */ - if (!(blkmap & BIT(aid->target_subblk))) - return enc->inverse; - - /* - * Increment ptr by the number of set subblocks that appear before our - * target subblock. If our target subblock is 0, do nothing as ptr - * already points to our target subblock. - */ - if (aid->target_subblk) - ptr += hweight8(blkmap & GENMASK(aid->target_subblk - 1, 0)); - - return !!(*ptr & BIT(aid->target_subblk_bit)) ^ enc->inverse; -} - -static inline bool ieee80211_s1g_parse_single(struct s1g_tim_enc_block *enc, - struct s1g_tim_aid *aid) -{ - /* - * Single AID mode describes, as the name suggests, a single AID - * within the block described by the encoded block. The octet - * contains the 6 LSBs of the AID described in the block. The other - * 2 bits are reserved. When inversed, every single AID described - * by the current block have buffered traffic except for the AID - * described in the single AID octet. - */ - return ((*enc->ptr & 0x3f) == (aid->aid & 0x3f)) ^ enc->inverse; -} - -static inline bool ieee80211_s1g_parse_olb(struct s1g_tim_enc_block *enc, - struct s1g_tim_aid *aid) -{ - const u8 *ptr = enc->ptr; - u8 blk_len = *ptr++; - /* - * Given an OLB encoded block that describes multiple blocks, - * calculate the offset into the span. Then calculate the - * subblock location normally. - */ - u16 span_offset = aid->target_blk - enc->olb_blk_offset; - u16 subblk_idx = span_offset * 8 + aid->target_subblk; - - if (subblk_idx >= blk_len) - return enc->inverse; - - return !!(ptr[subblk_idx] & BIT(aid->target_subblk_bit)) ^ enc->inverse; -} - -/* - * An S1G PVB has 3 non optional encoding types, each that can be inverted. - * An S1G PVB is constructed with zero or more encoded block subfields. Each - * encoded block represents a single "block" of AIDs (64), and each encoded - * block can contain one of the 3 encoding types alongside a single bit for - * whether the bits should be inverted. - * - * As the standard makes no guarantee about the ordering of encoded blocks, - * we must parse every encoded block in the worst case scenario given an - * AID that lies within the last block. - */ -static inline bool ieee80211_s1g_check_tim(const struct ieee80211_tim_ie *tim, - u8 tim_len, u16 aid) +static inline bool __ieee80211_check_tim(const struct ieee80211_tim_ie *tim, + u8 tim_len, u16 aid) { - int err; - struct s1g_tim_aid target_aid; - struct s1g_tim_enc_block enc_blk; + u8 mask; + u8 index, indexn1, indexn2; - if (tim_len < 3) + if (unlikely(!tim || tim_len < sizeof(*tim))) return false; - target_aid.aid = aid; - target_aid.target_blk = (aid >> 6) & 0x1f; - target_aid.target_subblk = (aid >> 3) & 0x7; - target_aid.target_subblk_bit = aid & 0x7; + aid &= 0x3fff; + index = aid / 8; + mask = 1 << (aid & 7); - /* - * Find our AIDs target encoded block and fill &enc_blk with the - * encoded blocks information. If no entry is found or an error - * occurs return false. - */ - err = ieee80211_s1g_find_target_block(&enc_blk, &target_aid, - tim->virtual_map, - (const u8 *)tim + tim_len + 2); - if (err) - return false; + indexn1 = tim->bitmap_ctrl & 0xfe; + indexn2 = tim_len + indexn1 - 4; - switch (enc_blk.enc_mode) { - case IEEE80211_S1G_TIM_ENC_MODE_BLOCK: - return ieee80211_s1g_parse_bitmap(&enc_blk, &target_aid); - case IEEE80211_S1G_TIM_ENC_MODE_SINGLE: - return ieee80211_s1g_parse_single(&enc_blk, &target_aid); - case IEEE80211_S1G_TIM_ENC_MODE_OLB: - return ieee80211_s1g_parse_olb(&enc_blk, &target_aid); - default: + if (index < indexn1 || index > indexn2) return false; - } -} -/** - * ieee80211_check_tim - check if AID bit is set in TIM - * @tim: the TIM IE - * @tim_len: length of the TIM IE - * @aid: the AID to look for - * @s1g: whether the TIM is from an S1G PPDU - * Return: whether or not traffic is indicated in the TIM for the given AID - */ -static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, - u8 tim_len, u16 aid, bool s1g) -{ - return s1g ? ieee80211_s1g_check_tim(tim, tim_len, aid) : - __ieee80211_check_tim(tim, tim_len, aid); + index -= indexn1; + + return !!(tim->virtual_map[index] & mask); } /** @@ -5184,39 +2671,6 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb) return false; } -/** - * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon - * @fc: frame control bytes in little-endian byteorder - * @variable: pointer to the beacon frame elements - * @variable_len: length of the frame elements - * Return: whether or not the frame is an S1G short beacon. As per - * IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall - * always be present as the first element in beacon frames generated at a - * TBTT (Target Beacon Transmission Time), so any frame not containing - * this element must have been generated at a TSBTT (Target Short Beacon - * Transmission Time) that is not a TBTT. Additionally, short beacons are - * prohibited from containing the S1G beacon compatibility element as per - * IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with - * either no elements or the first element is not the beacon compatibility - * element, we have a short beacon. - */ -static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable, - size_t variable_len) -{ - if (!ieee80211_is_s1g_beacon(fc)) - return false; - - /* - * If the frame does not contain at least 1 element (this is perfectly - * valid in a short beacon) and is an S1G beacon, we have a short - * beacon. - */ - if (variable_len < 2) - return true; - - return variable[0] != WLAN_EID_S1G_BCN_COMPAT; -} - struct element { u8 id; u8 datalen; @@ -5350,752 +2804,28 @@ struct ieee80211_tbtt_info_ge_11 { struct ieee80211_rnr_mld_params mld_params; } __packed; -/* multi-link device */ -#define IEEE80211_MLD_MAX_NUM_LINKS 15 - -#define IEEE80211_ML_CONTROL_TYPE 0x0007 -#define IEEE80211_ML_CONTROL_TYPE_BASIC 0 -#define IEEE80211_ML_CONTROL_TYPE_PREQ 1 -#define IEEE80211_ML_CONTROL_TYPE_RECONF 2 -#define IEEE80211_ML_CONTROL_TYPE_TDLS 3 -#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS 4 -#define IEEE80211_ML_CONTROL_PRESENCE_MASK 0xfff0 - -struct ieee80211_multi_link_elem { - __le16 control; - u8 variable[]; -} __packed; - -#define IEEE80211_MLC_BASIC_PRES_LINK_ID 0x0010 -#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT 0x0020 -#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY 0x0040 -#define IEEE80211_MLC_BASIC_PRES_EML_CAPA 0x0080 -#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP 0x0100 -#define IEEE80211_MLC_BASIC_PRES_MLD_ID 0x0200 -#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP 0x0400 - -#define IEEE80211_MED_SYNC_DELAY_DURATION 0x00ff -#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH 0x0f00 -#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS 0xf000 - -/* - * Described in P802.11be_D3.0 - * dot11MSDTimerDuration should default to 5484 (i.e. 171.375) - * dot11MSDOFDMEDthreshold defaults to -72 (i.e. 0) - * dot11MSDTXOPMAX defaults to 1 - */ -#define IEEE80211_MED_SYNC_DELAY_DEFAULT 0x10ac - -#define IEEE80211_EML_CAP_EMLSR_SUPP 0x0001 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY 0x000e -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US 0 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US 1 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US 2 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US 3 -#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US 4 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY 0x0070 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US 0 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US 1 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US 2 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US 3 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US 4 -#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US 5 -#define IEEE80211_EML_CAP_EMLMR_SUPPORT 0x0080 -#define IEEE80211_EML_CAP_EMLMR_DELAY 0x0700 -#define IEEE80211_EML_CAP_EMLMR_DELAY_0US 0 -#define IEEE80211_EML_CAP_EMLMR_DELAY_32US 1 -#define IEEE80211_EML_CAP_EMLMR_DELAY_64US 2 -#define IEEE80211_EML_CAP_EMLMR_DELAY_128US 3 -#define IEEE80211_EML_CAP_EMLMR_DELAY_256US 4 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT 0x7800 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0 0 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US 1 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US 2 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US 3 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU 4 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU 5 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU 6 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU 7 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU 8 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU 9 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU 10 -#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU 11 - -#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS 0x000f -#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT 0x0010 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP 0x0060 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_NO_SUPP 0 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME 1 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_RESERVED 2 -#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF 3 -#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND 0x0f80 -#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT 0x1000 -#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT 0x2000 -#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT 0x4000 - -struct ieee80211_mle_basic_common_info { - u8 len; - u8 mld_mac_addr[ETH_ALEN]; - u8 variable[]; -} __packed; - -#define IEEE80211_MLC_PREQ_PRES_MLD_ID 0x0010 - -struct ieee80211_mle_preq_common_info { - u8 len; - u8 variable[]; -} __packed; - -#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR 0x0010 -#define IEEE80211_MLC_RECONF_PRES_EML_CAPA 0x0020 -#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP 0x0040 -#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP 0x0080 - -/* no fixed fields in RECONF */ - -struct ieee80211_mle_tdls_common_info { - u8 len; - u8 ap_mld_mac_addr[ETH_ALEN]; -} __packed; - -#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR 0x0010 - -/* no fixed fields in PRIO_ACCESS */ - -/** - * ieee80211_mle_common_size - check multi-link element common size - * @data: multi-link element, must already be checked for size using - * ieee80211_mle_size_ok() - * Return: the size of the multi-link element's "common" subfield - */ -static inline u8 ieee80211_mle_common_size(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - - switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { - case IEEE80211_ML_CONTROL_TYPE_BASIC: - case IEEE80211_ML_CONTROL_TYPE_PREQ: - case IEEE80211_ML_CONTROL_TYPE_TDLS: - case IEEE80211_ML_CONTROL_TYPE_RECONF: - case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - /* - * The length is the first octet pointed by mle->variable so no - * need to add anything - */ - break; - default: - WARN_ON(1); - return 0; - } - - return sizeof(*mle) + mle->variable[0]; -} - -/** - * ieee80211_mle_get_link_id - returns the link ID - * @data: the basic multi link element - * Return: the link ID, or -1 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline int ieee80211_mle_get_link_id(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_LINK_ID)) - return -1; - - return *common; -} - -/** - * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count - * @data: pointer to the basic multi link element - * Return: the BSS Parameter Change Count field value, or -1 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline int -ieee80211_mle_get_bss_param_ch_cnt(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)) - return -1; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - - return *common; -} - -/** - * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay - * @data: pointer to the multi-link element - * Return: the medium synchronization delay field value from the multi-link - * element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT) - * if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)) - return IEEE80211_MED_SYNC_DELAY_DEFAULT; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - - return get_unaligned_le16(common); -} - -/** - * ieee80211_mle_get_eml_cap - returns the EML capability - * @data: pointer to the multi-link element - * Return: the EML capability field value from the multi-link element, - * or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_eml_cap(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* common points now at the beginning of ieee80211_mle_basic_common_info */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - - return get_unaligned_le16(common); -} - -/** - * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations. - * @data: pointer to the multi-link element - * Return: the MLD capabilities and operations field value from the multi-link - * element, or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* - * common points now at the beginning of - * ieee80211_mle_basic_common_info - */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - - return get_unaligned_le16(common); -} - -/* Defined in Figure 9-1074t in P802.11be_D7.0 */ -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE 0x0001 -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_RECO_MAX_LINKS_MASK 0x001e -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE 0x0020 -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK 0x0040 -#define IEEE80211_EHT_ML_EXT_MLD_CAPA_BTM_MLD_RECO_MULTI_AP 0x0080 - -/** - * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities - * and operations. - * @data: pointer to the multi-link element - * Return: the extended MLD capabilities and operations field value from - * the multi-link element, or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* - * common points now at the beginning of - * ieee80211_mle_basic_common_info - */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) - common += 1; - - return get_unaligned_le16(common); -} - -/** - * ieee80211_mle_get_mld_id - returns the MLD ID - * @data: pointer to the multi-link element - * Return: The MLD ID in the given multi-link element, or 0 if not present - * - * The element is assumed to be of the correct type (BASIC) and big enough, - * this must be checked using ieee80211_mle_type_ok(). - */ -static inline u8 ieee80211_mle_get_mld_id(const u8 *data) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control = le16_to_cpu(mle->control); - const u8 *common = mle->variable; - - /* - * common points now at the beginning of - * ieee80211_mle_basic_common_info - */ - common += sizeof(struct ieee80211_mle_basic_common_info); - - if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_ID)) - return 0; - - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) - common += 2; - - return *common; -} - -/** - * ieee80211_mle_size_ok - validate multi-link element size - * @data: pointer to the element data - * @len: length of the containing element - * Return: whether or not the multi-link element size is OK - */ -static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u8 fixed = sizeof(*mle); - u8 common = 0; - bool check_common_len = false; - u16 control; - - if (!data || len < fixed) - return false; - - control = le16_to_cpu(mle->control); - - switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) { - case IEEE80211_ML_CONTROL_TYPE_BASIC: - common += sizeof(struct ieee80211_mle_basic_common_info); - check_common_len = true; - if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP) - common += 2; - if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID) - common += 1; - if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP) - common += 2; - break; - case IEEE80211_ML_CONTROL_TYPE_PREQ: - common += sizeof(struct ieee80211_mle_preq_common_info); - if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID) - common += 1; - check_common_len = true; - break; - case IEEE80211_ML_CONTROL_TYPE_RECONF: - if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR) - common += ETH_ALEN; - if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA) - common += 2; - if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP) - common += 2; - if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP) - common += 2; - break; - case IEEE80211_ML_CONTROL_TYPE_TDLS: - common += sizeof(struct ieee80211_mle_tdls_common_info); - check_common_len = true; - break; - case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS: - common = ETH_ALEN + 1; - break; - default: - /* we don't know this type */ - return true; - } - - if (len < fixed + common) - return false; - - if (!check_common_len) - return true; - - /* if present, common length is the first octet there */ - return mle->variable[0] >= common; -} - -/** - * ieee80211_mle_type_ok - validate multi-link element type and size - * @data: pointer to the element data - * @type: expected type of the element - * @len: length of the containing element - * Return: whether or not the multi-link element type matches and size is OK - */ -static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len) -{ - const struct ieee80211_multi_link_elem *mle = (const void *)data; - u16 control; - - if (!ieee80211_mle_size_ok(data, len)) - return false; - - control = le16_to_cpu(mle->control); - - if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) == type) - return true; - - return false; -} - -enum ieee80211_mle_subelems { - IEEE80211_MLE_SUBELEM_PER_STA_PROFILE = 0, - IEEE80211_MLE_SUBELEM_FRAGMENT = 254, -}; - -#define IEEE80211_MLE_STA_CONTROL_LINK_ID 0x000f -#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE 0x0010 -#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 -#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT 0x0040 -#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT 0x0080 -#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT 0x0100 -#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT 0x0200 -#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE 0x0400 -#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT 0x0800 - -struct ieee80211_mle_per_sta_profile { - __le16 control; - u8 sta_info_len; - u8 variable[]; -} __packed; - -/** - * ieee80211_mle_basic_sta_prof_size_ok - validate basic multi-link element sta - * profile size - * @data: pointer to the sub element data - * @len: length of the containing sub element - * Return: %true if the STA profile is large enough, %false otherwise - */ -static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data, - size_t len) -{ - const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; - u16 control; - u8 fixed = sizeof(*prof); - u8 info_len = 1; - - if (len < fixed) - return false; - - control = le16_to_cpu(prof->control); - - if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) - info_len += 6; - if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) - info_len += 2; - if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) - info_len += 8; - if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) - info_len += 2; - if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && - control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { - if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) - info_len += 2; - else - info_len += 1; - } - if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT) - info_len += 1; - - return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len - 1 <= len; -} - -/** - * ieee80211_mle_basic_sta_prof_bss_param_ch_cnt - get per-STA profile BSS - * parameter change count - * @prof: the per-STA profile, having been checked with - * ieee80211_mle_basic_sta_prof_size_ok() for the correct length - * - * Return: The BSS parameter change count value if present, 0 otherwise. - */ -static inline u8 -ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta_profile *prof) -{ - u16 control = le16_to_cpu(prof->control); - const u8 *pos = prof->variable; - - if (!(control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)) - return 0; - - if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT) - pos += 6; - if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT) - pos += 2; - if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT) - pos += 8; - if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT) - pos += 2; - if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE && - control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) { - if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) - pos += 2; - else - pos += 1; - } - - return *pos; -} - -#define IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID 0x000f -#define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE 0x0010 -#define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT 0x0020 -#define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT 0x0040 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE 0x0780 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM 0 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK 2 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK 3 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS 4 -#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT 0x0800 - -/** - * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link - * element sta profile size. - * @data: pointer to the sub element data - * @len: length of the containing sub element - * Return: %true if the STA profile is large enough, %false otherwise - */ -static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, - size_t len) -{ - const struct ieee80211_mle_per_sta_profile *prof = (const void *)data; - u16 control; - u8 fixed = sizeof(*prof); - u8 info_len = 1; - - if (len < fixed) - return false; - - control = le16_to_cpu(prof->control); - - if (control & IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT) - info_len += ETH_ALEN; - if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT) - info_len += 2; - if (control & IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT) - info_len += 2; - - return prof->sta_info_len >= info_len && - fixed + prof->sta_info_len - 1 <= len; -} - -#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID 0x000f -#define IEEE80211_EPCS_ENA_RESP_BODY_LEN 3 - -static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) -{ - const struct ieee80211_ttlm_elem *t2l = (const void *)data; - u8 control, fixed = sizeof(*t2l), elem_len = 0; - - if (len < fixed) - return false; - - control = t2l->control; - - if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) - elem_len += 2; - if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) - elem_len += 3; - - if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { - u8 bm_size; - - elem_len += 1; - if (len < fixed + elem_len) - return false; - - if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) - bm_size = 1; - else - bm_size = 2; - - elem_len += hweight8(t2l->optional[0]) * bm_size; - } - - return len >= fixed + elem_len; -} - -/** - * ieee80211_emlsr_pad_delay_in_us - Fetch the EMLSR Padding delay - * in microseconds - * @eml_cap: EML capabilities field value from common info field of - * the Multi-link element - * Return: the EMLSR Padding delay (in microseconds) encoded in the - * EML Capabilities field - */ - -static inline u32 ieee80211_emlsr_pad_delay_in_us(u16 eml_cap) -{ - /* IEEE Std 802.11be-2024 Table 9-417i—Encoding of the EMLSR - * Padding Delay subfield. - */ - u32 pad_delay = u16_get_bits(eml_cap, - IEEE80211_EML_CAP_EMLSR_PADDING_DELAY); - - if (!pad_delay || - pad_delay > IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US) - return 0; - - return 32 * (1 << (pad_delay - 1)); -} - -/** - * ieee80211_emlsr_trans_delay_in_us - Fetch the EMLSR Transition - * delay in microseconds - * @eml_cap: EML capabilities field value from common info field of - * the Multi-link element - * Return: the EMLSR Transition delay (in microseconds) encoded in the - * EML Capabilities field - */ - -static inline u32 ieee80211_emlsr_trans_delay_in_us(u16 eml_cap) -{ - /* IEEE Std 802.11be-2024 Table 9-417j—Encoding of the EMLSR - * Transition Delay subfield. - */ - u32 trans_delay = - u16_get_bits(eml_cap, - IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY); - - /* invalid values also just use 0 */ - if (!trans_delay || - trans_delay > IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US) - return 0; - - return 16 * (1 << (trans_delay - 1)); -} +#include "ieee80211-ht.h" +#include "ieee80211-vht.h" +#include "ieee80211-he.h" +#include "ieee80211-eht.h" +#include "ieee80211-mesh.h" +#include "ieee80211-s1g.h" +#include "ieee80211-p2p.h" +#include "ieee80211-nan.h" /** - * ieee80211_eml_trans_timeout_in_us - Fetch the EMLSR Transition - * timeout value in microseconds - * @eml_cap: EML capabilities field value from common info field of - * the Multi-link element - * Return: the EMLSR Transition timeout (in microseconds) encoded in - * the EML Capabilities field + * ieee80211_check_tim - check if AID bit is set in TIM + * @tim: the TIM IE + * @tim_len: length of the TIM IE + * @aid: the AID to look for + * @s1g: whether the TIM is from an S1G PPDU + * Return: whether or not traffic is indicated in the TIM for the given AID */ - -static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap) +static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, + u8 tim_len, u16 aid, bool s1g) { - /* IEEE Std 802.11be-2024 Table 9-417m—Encoding of the - * Transition Timeout subfield. - */ - u8 timeout = u16_get_bits(eml_cap, - IEEE80211_EML_CAP_TRANSITION_TIMEOUT); - - /* invalid values also just use 0 */ - if (!timeout || timeout > IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU) - return 0; - - return 128 * (1 << (timeout - 1)); + return s1g ? ieee80211_s1g_check_tim(tim, tim_len, aid) : + __ieee80211_check_tim(tim, tim_len, aid); } -#define for_each_mle_subelement(_elem, _data, _len) \ - if (ieee80211_mle_size_ok(_data, _len)) \ - for_each_element(_elem, \ - _data + ieee80211_mle_common_size(_data),\ - _len - ieee80211_mle_common_size(_data)) - -/* NAN operation mode, as defined in Wi-Fi Aware (TM) specification Table 81 */ -#define NAN_OP_MODE_PHY_MODE_VHT 0x01 -#define NAN_OP_MODE_PHY_MODE_HE 0x10 -#define NAN_OP_MODE_PHY_MODE_MASK 0x11 -#define NAN_OP_MODE_80P80MHZ 0x02 -#define NAN_OP_MODE_160MHZ 0x04 -#define NAN_OP_MODE_PNDL_SUPPRTED 0x08 - -/* NAN Device capabilities, as defined in Wi-Fi Aware (TM) specification - * Table 79 - */ -#define NAN_DEV_CAPA_DFS_OWNER 0x01 -#define NAN_DEV_CAPA_EXT_KEY_ID_SUPPORTED 0x02 -#define NAN_DEV_CAPA_SIM_NDP_RX_SUPPORTED 0x04 -#define NAN_DEV_CAPA_NDPE_SUPPORTED 0x08 -#define NAN_DEV_CAPA_S3_SUPPORTED 0x10 - #endif /* LINUX_IEEE80211_H */ diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 15e01935d3fad..f7f34eb15e068 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -355,16 +355,17 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci, unsigned int mac_len) { + const u8 meta_len = mac_len > ETH_TLEN ? skb_metadata_len(skb) : 0; struct vlan_ethhdr *veth; - if (skb_cow_head(skb, VLAN_HLEN) < 0) + if (skb_cow_head(skb, meta_len + VLAN_HLEN) < 0) return -ENOMEM; skb_push(skb, VLAN_HLEN); /* Move the mac header sans proto to the beginning of the new header. */ if (likely(mac_len > ETH_TLEN)) - memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN); + skb_postpush_data_move(skb, VLAN_HLEN, mac_len - ETH_TLEN); if (skb_mac_header_was_set(skb)) skb->mac_header -= VLAN_HLEN; @@ -731,18 +732,16 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb, * * Expects the skb to contain a VLAN tag in the payload, and to have skb->data * pointing at the MAC header. - * - * Returns: a new pointer to skb->data, or NULL on failure to pull. */ -static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) +static inline void vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci) { struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN); *vlan_tci = ntohs(vhdr->h_vlan_TCI); - memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN); vlan_set_encap_proto(skb, vhdr); - return __skb_pull(skb, VLAN_HLEN); + __skb_pull(skb, VLAN_HLEN); + skb_postpull_data_move(skb, VLAN_HLEN, 2 * ETH_ALEN); } /** diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 43b7bb8287388..7294e4e89b797 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -271,7 +271,6 @@ struct ipv6_pinfo { struct ipv6_mc_socklist __rcu *ipv6_mc_list; struct ipv6_ac_socklist *ipv6_ac_list; - struct ipv6_fl_socklist __rcu *ipv6_fl_list; }; /* We currently use available bits from inet_sk(sk)->inet_flags, diff --git a/include/linux/mdio.h b/include/linux/mdio.h index c640ba44dd6ee..42d6d47e445b7 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -689,16 +689,7 @@ struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr); * init/exit. Each module may only use this macro once, and calling it * replaces module_init() and module_exit(). */ -#define mdio_module_driver(_mdio_driver) \ -static int __init mdio_module_init(void) \ -{ \ - return mdio_driver_register(&_mdio_driver); \ -} \ -module_init(mdio_module_init); \ -static void __exit mdio_module_exit(void) \ -{ \ - mdio_driver_unregister(&_mdio_driver); \ -} \ -module_exit(mdio_module_exit) +#define mdio_module_driver(_mdio_driver) \ + module_driver(_mdio_driver, mdio_driver_register, mdio_driver_unregister) #endif /* __LINUX_MDIO_H__ */ diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 5405ca1038f9e..046396269ccf6 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1379,4 +1379,7 @@ static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev) { return devlink_net(priv_to_devlink(dev)); } + +#define MLX5_SW_IMAGE_GUID_MAX_BYTES 9 + #endif /* MLX5_DRIVER_H */ diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 6ac76a0c38277..9cadb1d5e6df0 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -71,6 +71,7 @@ enum { MLX5_FLOW_TABLE_UNMANAGED = BIT(3), MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4), MLX5_FLOW_TABLE_UPLINK_VPORT = BIT(5), + MLX5_FLOW_TABLE_OTHER_ESWITCH = BIT(6), }; #define LEFTOVERS_RULE_NUM 2 @@ -116,6 +117,7 @@ enum mlx5_flow_namespace_type { }; enum { + FDB_DROP_ROOT, FDB_BYPASS_PATH, FDB_CRYPTO_INGRESS, FDB_TC_OFFLOAD, @@ -127,6 +129,24 @@ enum { FDB_PER_VPORT, }; +enum fs_flow_table_type { + FS_FT_NIC_RX = 0x0, + FS_FT_NIC_TX = 0x1, + FS_FT_ESW_EGRESS_ACL = 0x2, + FS_FT_ESW_INGRESS_ACL = 0x3, + FS_FT_FDB = 0X4, + FS_FT_SNIFFER_RX = 0X5, + FS_FT_SNIFFER_TX = 0X6, + FS_FT_RDMA_RX = 0X7, + FS_FT_RDMA_TX = 0X8, + FS_FT_PORT_SEL = 0X9, + FS_FT_FDB_RX = 0xa, + FS_FT_FDB_TX = 0xb, + FS_FT_RDMA_TRANSPORT_RX = 0xd, + FS_FT_RDMA_TRANSPORT_TX = 0xe, + FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX, +}; + struct mlx5_pkt_reformat; struct mlx5_modify_hdr; struct mlx5_flow_definer; @@ -208,6 +228,7 @@ struct mlx5_flow_table_attr { u32 flags; u16 uid; u16 vport; + u16 esw_owner_vhca_id; struct mlx5_flow_table *next_ft; struct { @@ -353,4 +374,8 @@ u32 mlx5_flow_table_id(struct mlx5_flow_table *ft); struct mlx5_flow_root_namespace * mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type); + +int mlx5_fs_set_root_dev(struct mlx5_core_dev *dev, + struct mlx5_core_dev *new_dev, + enum fs_flow_table_type table_type); #endif diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1b0b36aa2a767..e9dcd4bf355da 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -5251,13 +5251,15 @@ struct mlx5_ifc_set_fte_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8809,13 +8811,15 @@ struct mlx5_ifc_destroy_flow_table_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8840,13 +8844,15 @@ struct mlx5_ifc_destroy_flow_group_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -8985,13 +8991,15 @@ struct mlx5_ifc_delete_fte_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -9535,13 +9543,15 @@ struct mlx5_ifc_create_flow_table_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x20]; @@ -9580,7 +9590,8 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x20]; @@ -9588,7 +9599,7 @@ struct mlx5_ifc_create_flow_group_in_bits { u8 table_type[0x8]; u8 reserved_at_88[0x4]; u8 group_type[0x4]; - u8 reserved_at_90[0x10]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; @@ -11878,10 +11889,12 @@ struct mlx5_ifc_set_flow_table_root_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; - u8 reserved_at_60[0x20]; + u8 reserved_at_60[0x10]; + u8 eswitch_owner_vhca_id[0x10]; u8 table_type[0x8]; u8 reserved_at_88[0x7]; @@ -11921,14 +11934,16 @@ struct mlx5_ifc_modify_flow_table_in_bits { u8 op_mod[0x10]; u8 other_vport[0x1]; - u8 reserved_at_41[0xf]; + u8 other_eswitch[0x1]; + u8 reserved_at_42[0xe]; u8 vport_number[0x10]; u8 reserved_at_60[0x10]; u8 modify_field_select[0x10]; u8 table_type[0x8]; - u8 reserved_at_88[0x18]; + u8 reserved_at_88[0x8]; + u8 eswitch_owner_vhca_id[0x10]; u8 reserved_at_a0[0x8]; u8 table_id[0x18]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index 58770b86f7939..1df9d9a57bbc3 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -112,6 +112,7 @@ enum mlx5e_ext_link_mode { MLX5E_400GAUI_2_400GBASE_CR2_KR2 = 17, MLX5E_800GAUI_8_800GBASE_CR8_KR8 = 19, MLX5E_800GAUI_4_800GBASE_CR4_KR4 = 20, + MLX5E_1600TAUI_8_1600TBASE_CR8_KR8 = 23, MLX5E_EXT_LINK_MODES_NUMBER, }; diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h index c87b9507cfa18..f876bfc0669c8 100644 --- a/include/linux/mlx5/vport.h +++ b/include/linux/mlx5/vport.h @@ -73,7 +73,8 @@ int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu); int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev, u64 *system_image_guid); int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group); -int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid); +int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, + u16 vport, bool other_vport, u64 *node_guid); int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev, u16 vport, u64 node_guid); int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev, diff --git a/include/linux/net.h b/include/linux/net.h index ec09620f40f70..f58b38ab37f8a 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -148,7 +148,6 @@ typedef struct { struct vm_area_struct; struct page; -struct sockaddr; struct msghdr; struct module; struct sk_buff; @@ -163,10 +162,10 @@ struct proto_ops { struct module *owner; int (*release) (struct socket *sock); int (*bind) (struct socket *sock, - struct sockaddr *myaddr, + struct sockaddr_unsized *myaddr, int sockaddr_len); int (*connect) (struct socket *sock, - struct sockaddr *vaddr, + struct sockaddr_unsized *vaddr, int sockaddr_len, int flags); int (*socketpair)(struct socket *sock1, struct socket *sock2); @@ -345,10 +344,10 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t len, int flags); -int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen); +int kernel_bind(struct socket *sock, struct sockaddr_unsized *addr, int addrlen); int kernel_listen(struct socket *sock, int backlog); int kernel_accept(struct socket *sock, struct socket **newsock, int flags); -int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, +int kernel_connect(struct socket *sock, struct sockaddr_unsized *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 7a01c518e5730..93e4da7046a10 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -255,6 +255,24 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) +/* virtual device features */ +#define MASTER_UPPER_DEV_VLAN_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \ + NETIF_F_GSO_ENCAP_ALL | \ + NETIF_F_HIGHDMA | NETIF_F_LRO) + +#define MASTER_UPPER_DEV_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \ + NETIF_F_GSO_PARTIAL) + +#define MASTER_UPPER_DEV_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_GSO_SOFTWARE) + +#define MASTER_UPPER_DEV_XFRM_FEATURES (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \ + NETIF_F_GSO_ESP) + +#define MASTER_UPPER_DEV_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP) + static inline netdev_features_t netdev_base_features(netdev_features_t features) { features &= ~NETIF_F_ONE_FOR_ALL; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d1a687444b275..e808071dbb7d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -377,6 +377,8 @@ struct napi_config { * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { + /* This field should be first or softnet_data.backlog needs tweaks. */ + unsigned long state; /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct @@ -385,7 +387,6 @@ struct napi_struct { */ struct list_head poll_list; - unsigned long state; int weight; u32 defer_hard_irqs_count; int (*poll)(struct napi_struct *, int); @@ -422,11 +423,12 @@ enum { NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ - NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ + NAPI_STATE_IN_BUSY_POLL, /* Do not rearm NAPI interrupt */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ NAPI_STATE_HAS_NOTIFIER, /* Napi has an IRQ notifier */ + NAPI_STATE_THREADED_BUSY_POLL, /* The threaded NAPI poller will busy poll */ }; enum { @@ -441,6 +443,7 @@ enum { NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), NAPIF_STATE_HAS_NOTIFIER = BIT(NAPI_STATE_HAS_NOTIFIER), + NAPIF_STATE_THREADED_BUSY_POLL = BIT(NAPI_STATE_THREADED_BUSY_POLL), }; enum gro_result { @@ -3529,9 +3532,17 @@ struct softnet_data { call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; + + /* We force a cacheline alignment from here, to hold together + * input_queue_tail, input_pkt_queue and backlog.state. + * We add holes so that backlog.state is the last field + * of this cache line. + */ + long pad[3] ____cacheline_aligned_in_smp; unsigned int input_queue_tail; #endif struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; struct numa_drop_counters drop_counters; @@ -5304,6 +5315,7 @@ static inline netdev_features_t netdev_add_tso_features(netdev_features_t featur int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); +void netdev_compute_master_upper_features(struct net_device *dev, bool update_header); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); diff --git a/include/linux/netdevice_xmit.h b/include/linux/netdevice_xmit.h index 813a19122ebbb..cc232508e695e 100644 --- a/include/linux/netdevice_xmit.h +++ b/include/linux/netdevice_xmit.h @@ -2,6 +2,12 @@ #ifndef _LINUX_NETDEVICE_XMIT_H #define _LINUX_NETDEVICE_XMIT_H +#if IS_ENABLED(CONFIG_NET_ACT_MIRRED) +#define MIRRED_NEST_LIMIT 4 +#endif + +struct net_device; + struct netdev_xmit { u16 recursion; u8 more; @@ -9,7 +15,8 @@ struct netdev_xmit { u8 skip_txqueue; #endif #if IS_ENABLED(CONFIG_NET_ACT_MIRRED) - u8 sched_mirred_nest; + u8 sched_mirred_nest; + struct net_device *sched_mirred_dev[MIRRED_NEST_LIMIT]; #endif #if IS_ENABLED(CONFIG_NF_DUP_NETDEV) u8 nf_dup_skb_recursion; diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h index 9e4e331b16033..ba28140ce6707 100644 --- a/include/linux/pci-tph.h +++ b/include/linux/pci-tph.h @@ -29,6 +29,7 @@ int pcie_tph_get_cpu_st(struct pci_dev *dev, void pcie_disable_tph(struct pci_dev *pdev); int pcie_enable_tph(struct pci_dev *pdev, int mode); u16 pcie_tph_get_st_table_size(struct pci_dev *pdev); +u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev); #else static inline int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag) diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h index e40f554ff717a..36073f7b6bb40 100644 --- a/include/linux/pcs/pcs-xpcs.h +++ b/include/linux/pcs/pcs-xpcs.h @@ -38,7 +38,9 @@ enum dw_xpcs_pma_id { DW_XPCS_PMA_GEN4_6G_ID, DW_XPCS_PMA_GEN5_10G_ID, DW_XPCS_PMA_GEN5_12G_ID, - WX_TXGBE_XPCS_PMA_10G_ID = 0x0018fc80, + WX_TXGBE_XPCS_PMA_10G_ID = 0xfc806000, + /* Meta Platforms OUI 88:25:08, model 0, revision 0 */ + MP_FBNIC_XPCS_PMA_100G_ID = 0x46904000, }; struct dw_xpcs_info { diff --git a/include/linux/phy.h b/include/linux/phy.h index 3c7634482356e..8c8f25c7a1ac4 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -327,6 +327,7 @@ static inline long rgmii_clock(int speed) struct device; struct kernel_hwtstamp_config; struct phylink; +struct phy_port; struct sfp_bus; struct sfp_upstream_ops; struct sk_buff; @@ -621,6 +622,9 @@ struct macsec_ops; * @master_slave_state: Current master/slave configuration * @mii_ts: Pointer to time stamper callbacks * @psec: Pointer to Power Sourcing Equipment control struct + * @ports: List of PHY ports structures + * @n_ports: Number of ports currently attached to the PHY + * @max_n_ports: Max number of ports this PHY can expose * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine * @link_down_events: Number of times link was lost @@ -666,6 +670,8 @@ struct phy_device { /* The most recently read link state */ unsigned link:1; unsigned autoneg_complete:1; + bool pause:1; + bool asym_pause:1; /* Interrupts are enabled */ unsigned interrupts:1; @@ -690,8 +696,6 @@ struct phy_device { int speed; int duplex; int port; - int pause; - int asym_pause; u8 master_slave_get; u8 master_slave_set; u8 master_slave_state; @@ -758,6 +762,10 @@ struct phy_device { struct mii_timestamper *mii_ts; struct pse_control *psec; + struct list_head ports; + int n_ports; + int max_n_ports; + u8 mdix; u8 mdix_ctrl; @@ -780,6 +788,9 @@ struct phy_device { #define to_phy_device(__dev) container_of_const(to_mdio_device(__dev), struct phy_device, mdio) +#define phy_for_each_port(phydev, port) \ + list_for_each_entry(port, &(phydev)->ports, head) + /** * struct phy_tdr_config - Configuration of a TDR raw test * @@ -903,6 +914,165 @@ struct phy_led { #define to_phy_led(d) container_of(d, struct phy_led, led_cdev) +/* + * PHY_MSE_CAP_* - Bitmask flags for Mean Square Error (MSE) capabilities + * + * These flags describe which MSE metrics and selectors are implemented + * by the PHY for the current link mode. They are used in + * struct phy_mse_capability.supported_caps. + * + * Standardization: + * The OPEN Alliance (OA) defines the presence of MSE/SQI/pMSE but not their + * numeric scaling, update intervals, or aggregation windows. See: + * OA 100BASE-T1 TC1 v1.0, sections 6.1.1-6.1.3 + * OA 1000BASE-T1 TC12 v2.2, sections 6.1.1-6.1.2 + * + * Description of flags: + * + * PHY_MSE_CAP_CHANNEL_A + * Per-pair diagnostics for Channel A are supported. Mapping to the + * physical wire pair may depend on MDI/MDI-X polarity. + * + * PHY_MSE_CAP_CHANNEL_B, _C, _D + * Same as above for channels B-D. + * + * PHY_MSE_CAP_WORST_CHANNEL + * The PHY or driver can identify and report the single worst-performing + * channel without querying each one individually. + * + * PHY_MSE_CAP_LINK + * The PHY provides only a link-wide aggregate measurement or cannot map + * results to a specific pair (for example 100BASE-TX with unknown + * MDI/MDI-X). + * + * PHY_MSE_CAP_AVG + * Average MSE (mean DCQ metric) is supported. For 100/1000BASE-T1 the OA + * recommends 2^16 symbols, scaled 0..511, but the exact scaling is + * vendor-specific. + * + * PHY_MSE_CAP_PEAK + * Peak MSE (current peak within the measurement window) is supported. + * Defined as pMSE for 100BASE-T1; vendor-specific for others. + * + * PHY_MSE_CAP_WORST_PEAK + * Latched worst-case peak MSE since the last read (read-to-clear if + * implemented). Optional in OA 100BASE-T1 TC1 6.1.3. + */ +#define PHY_MSE_CAP_CHANNEL_A BIT(0) +#define PHY_MSE_CAP_CHANNEL_B BIT(1) +#define PHY_MSE_CAP_CHANNEL_C BIT(2) +#define PHY_MSE_CAP_CHANNEL_D BIT(3) +#define PHY_MSE_CAP_WORST_CHANNEL BIT(4) +#define PHY_MSE_CAP_LINK BIT(5) +#define PHY_MSE_CAP_AVG BIT(6) +#define PHY_MSE_CAP_PEAK BIT(7) +#define PHY_MSE_CAP_WORST_PEAK BIT(8) + +/* + * enum phy_mse_channel - Identifiers for selecting MSE measurement channels + * + * PHY_MSE_CHANNEL_A - PHY_MSE_CHANNEL_D + * Select per-pair measurement for the corresponding channel. + * + * PHY_MSE_CHANNEL_WORST + * Select the single worst-performing channel reported by hardware. + * + * PHY_MSE_CHANNEL_LINK + * Select link-wide aggregate data (used when per-pair results are + * unavailable). + */ +enum phy_mse_channel { + PHY_MSE_CHANNEL_A, + PHY_MSE_CHANNEL_B, + PHY_MSE_CHANNEL_C, + PHY_MSE_CHANNEL_D, + PHY_MSE_CHANNEL_WORST, + PHY_MSE_CHANNEL_LINK, +}; + +/** + * struct phy_mse_capability - Capabilities of Mean Square Error (MSE) + * measurement interface + * + * Standardization notes: + * + * - Presence of MSE/SQI/pMSE is defined by OPEN Alliance specs, but numeric + * scaling, refresh/update rate and aggregation windows are not fixed and + * are vendor-/product-specific. (OA 100BASE-T1 TC1 v1.0 6.1.*; + * OA 1000BASE-T1 TC12 v2.2 6.1.*) + * + * - Typical recommendations: 2^16 symbols and 0..511 scaling for MSE; pMSE only + * defined for 100BASE-T1 (sliding window example), others are vendor + * extensions. Drivers must report actual scale/limits here. + * + * Describes the MSE measurement capabilities for the current link mode. These + * properties are dynamic and may change when link settings are modified. + * Callers should re-query this capability after any link state change to + * ensure they have the most up-to-date information. + * + * Callers should only request measurements for channels and types that are + * indicated as supported by the @supported_caps bitmask. If @supported_caps + * is 0, the device provides no MSE diagnostics, and driver operations should + * typically return -EOPNOTSUPP. + * + * Snapshot values for average and peak MSE can be normalized to a 0..1 ratio + * by dividing the raw snapshot by the corresponding @max_average_mse or + * @max_peak_mse value. + * + * @max_average_mse: The maximum value for an average MSE snapshot. This + * defines the scale for the measurement. If the PHY_MSE_CAP_AVG capability is + * supported, this value MUST be greater than 0. (vendor-specific units). + * @max_peak_mse: The maximum value for a peak MSE snapshot. If either + * PHY_MSE_CAP_PEAK or PHY_MSE_CAP_WORST_PEAK is supported, this value MUST + * be greater than 0. (vendor-specific units). + * @refresh_rate_ps: The typical interval, in picoseconds, between hardware + * updates of the MSE values. This is an estimate, and callers should not + * assume synchronous sampling. (vendor-specific units). + * @num_symbols: The number of symbols aggregated per hardware sample to + * calculate the MSE. (vendor-specific units). + * @supported_caps: A bitmask of PHY_MSE_CAP_* values indicating which + * measurement types (e.g., average, peak) and channels + * (e.g., per-pair or link-wide) are supported. + */ +struct phy_mse_capability { + u64 max_average_mse; + u64 max_peak_mse; + u64 refresh_rate_ps; + u64 num_symbols; + u32 supported_caps; +}; + +/** + * struct phy_mse_snapshot - A snapshot of Mean Square Error (MSE) diagnostics + * + * Holds a set of MSE diagnostic values that were all captured from a single + * measurement window. + * + * Values are raw, device-scaled and not normalized. Use struct + * phy_mse_capability to interpret the scale and sampling window. + * + * @average_mse: The average MSE value over the measurement window. + * OPEN Alliance references MSE as a DCQ metric; recommends 2^16 symbols and + * 0..511 scaling. Exact scale and refresh are vendor-specific. + * (100BASE-T1 TC1 v1.0 6.1.1; 1000BASE-T1 TC12 v2.2 6.1.1). + * + * @peak_mse: The peak MSE value observed within the measurement window. + * For 100BASE-T1, "pMSE" is optional and may be implemented via a sliding + * 128-symbol window with periodic capture; not standardized for 1000BASE-T1. + * (100BASE-T1 TC1 v1.0 6.1.3, Table "DCQ.peakMSE"). + * + * @worst_peak_mse: A latched high-water mark of the peak MSE since last read + * (read-to-clear if implemented). OPEN Alliance shows a latched "worst case + * peak MSE" for 100BASE-T1 pMSE; availability/semantics outside that are + * vendor-specific. (100BASE-T1 TC1 v1.0 6.1.3, DCQ.peakMSE high byte; + * 1000BASE-T1 TC12 v2.2 treats DCQ details as vendor-specific.) + */ +struct phy_mse_snapshot { + u64 average_mse; + u64 peak_mse; + u64 worst_peak_mse; +}; + /** * struct phy_driver - Driver structure for a particular PHY type * @@ -1184,6 +1354,53 @@ struct phy_driver { /** @get_sqi_max: Get the maximum signal quality indication */ int (*get_sqi_max)(struct phy_device *dev); + /** + * @get_mse_capability: Get capabilities and scale of MSE measurement + * @dev: PHY device + * @cap: Output (filled on success) + * + * Fill @cap with the PHY's MSE capability for the current + * link mode: scale limits (max_average_mse, max_peak_mse), update + * interval (refresh_rate_ps), sample length (num_symbols) and the + * capability bitmask (supported_caps). + * + * Implementations may defer capability report until hardware has + * converged; in that case they should return -EAGAIN and allow the + * caller to retry later. + * + * Return: 0 on success. On failure, returns a negative errno code, such + * as -EOPNOTSUPP if MSE measurement is not supported by the PHY or in + * the current link mode, or -EAGAIN if the capability information is + * not yet available. + */ + int (*get_mse_capability)(struct phy_device *dev, + struct phy_mse_capability *cap); + + /** + * @get_mse_snapshot: Retrieve a snapshot of MSE diagnostic values + * @dev: PHY device + * @channel: Channel identifier (PHY_MSE_CHANNEL_*) + * @snapshot: Output (filled on success) + * + * Fill @snapshot with a correlated set of MSE values from the most + * recent measurement window. + * + * Callers must validate @channel against supported_caps returned by + * get_mse_capability(). Drivers must not coerce @channel; if the + * requested selector is not implemented by the device or current link + * mode, the operation must fail. + * + * worst_peak_mse is latched and must be treated as read-to-clear. + * + * Return: 0 on success. On failure, returns a negative errno code, such + * as -EOPNOTSUPP if MSE measurement is not supported by the PHY or in + * the current link mode, or -EAGAIN if measurements are not yet + * available. + */ + int (*get_mse_snapshot)(struct phy_device *dev, + enum phy_mse_channel channel, + struct phy_mse_snapshot *snapshot); + /* PLCA RS interface */ /** @get_plca_cfg: Return the current PLCA configuration */ int (*get_plca_cfg)(struct phy_device *dev, @@ -1274,6 +1491,49 @@ struct phy_driver { * Returns the time in jiffies until the next update event. */ unsigned int (*get_next_update_time)(struct phy_device *dev); + + /** + * @attach_mii_port: Attach the given MII port to the PHY device + * @dev: PHY device to notify + * @port: The port being added + * + * Called when an MII port that needs to be driven by the PHY is found. + * + * The port that is being passed may or may not be initialized. If it is + * already initialized, it is by the generic port representation from + * devicetree, which superseeds any strapping or vendor-specific + * properties. + * + * If the port isn't initialized, the port->mediums and port->lanes + * fields must be set, possibly according to strapping information. + * + * The PHY driver must set the port->interfaces field to indicate the + * possible MII modes that this PHY can output on the port. + * + * Returns 0, or an error code. + */ + int (*attach_mii_port)(struct phy_device *dev, struct phy_port *port); + + /** + * @attach_mdi_port: Attach the given MII port to the PHY device + * @dev: PHY device to notify + * @port: The port being added + * + * Called when a port that needs to be driven by the PHY is found. The + * number of time this will be called depends on phydev->max_n_ports, + * which the driver can change in .probe(). + * + * The port that is being passed may or may not be initialized. If it is + * already initialized, it is by the generic port representation from + * devicetree, which superseeds any strapping or vendor-specific + * properties. + * + * If the port isn't initialized, the port->mediums and port->lanes + * fields must be set, possibly according to strapping information. + * + * Returns 0, or an error code. + */ + int (*attach_mdi_port)(struct phy_device *dev, struct phy_port *port); }; #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) @@ -1379,6 +1639,27 @@ static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode linkmode_clear_bit(link_mode, phydev->advertising_eee); } +/** + * phy_can_wakeup() - indicate whether PHY has driver model wakeup capabilities + * @phydev: The phy_device struct + * + * Returns: true/false depending on the PHY driver's device_set_wakeup_capable() + * setting. + */ +static inline bool phy_can_wakeup(struct phy_device *phydev) +{ + return device_can_wakeup(&phydev->mdio.dev); +} + +/** + * phy_may_wakeup() - indicate whether PHY has wakeup enabled + * @phydev: The phy_device struct + * + * Returns: true/false depending on the PHY driver's device_set_wakeup_enabled() + * setting if using the driver model, otherwise the legacy determination. + */ +bool phy_may_wakeup(struct phy_device *phydev); + void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); @@ -1813,6 +2094,9 @@ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) return phydev->is_pseudo_fixed_link; } +phy_interface_t phy_fix_phy_mode_for_mac_delays(phy_interface_t interface, + bool mac_txid, bool mac_rxid); + int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); @@ -1840,15 +2124,9 @@ int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable, int speed); -int phy_sfp_connect_phy(void *upstream, struct phy_device *phy); -void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy); -void phy_sfp_attach(void *upstream, struct sfp_bus *bus); -void phy_sfp_detach(void *upstream, struct sfp_bus *bus); -int phy_sfp_probe(struct phy_device *phydev, - const struct sfp_upstream_ops *ops); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); -struct phy_device *phy_find_first(struct mii_bus *bus); +struct phy_device *phy_find_next(struct mii_bus *bus, struct phy_device *pos); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, @@ -1875,6 +2153,15 @@ bool phy_check_valid(int speed, int duplex, unsigned long *features); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); +static inline struct phy_device *phy_find_first(struct mii_bus *bus) +{ + return phy_find_next(bus, NULL); +} + +#define mdiobus_for_each_phy(_bus, _phydev) \ + for (_phydev = phy_find_first(_bus); _phydev; \ + _phydev = phy_find_next(_bus, _phydev)) + #if IS_ENABLED(CONFIG_PHYLIB) int phy_start_cable_test(struct phy_device *phydev, struct netlink_ext_ack *extack); @@ -2015,6 +2302,9 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_keee *data); int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); +int genphy_c45_oatc14_cable_test_start(struct phy_device *phydev); +int genphy_c45_oatc14_cable_test_get_status(struct phy_device *phydev, + bool *finished); /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); @@ -2039,6 +2329,7 @@ void phy_trigger_machine(struct phy_device *phydev); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); + void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, @@ -2129,6 +2420,8 @@ int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); +struct phy_port *phy_get_sfp_port(struct phy_device *phydev); + extern const struct bus_type mdio_bus_type; extern const struct class mdio_bus_class; diff --git a/include/linux/phy_fixed.h b/include/linux/phy_fixed.h index d17ff750c7082..436bff20f324f 100644 --- a/include/linux/phy_fixed.h +++ b/include/linux/phy_fixed.h @@ -5,11 +5,11 @@ #include struct fixed_phy_status { - int link; int speed; int duplex; - int pause; - int asym_pause; + bool link:1; + bool pause:1; + bool asym_pause:1; }; struct device_node; @@ -17,16 +17,15 @@ struct net_device; #if IS_ENABLED(CONFIG_FIXED_PHY) extern int fixed_phy_change_carrier(struct net_device *dev, bool new_carrier); -void fixed_phy_add(const struct fixed_phy_status *status); struct phy_device *fixed_phy_register(const struct fixed_phy_status *status, struct device_node *np); +struct phy_device *fixed_phy_register_100fd(void); extern void fixed_phy_unregister(struct phy_device *phydev); extern int fixed_phy_set_link_update(struct phy_device *phydev, int (*link_update)(struct net_device *, struct fixed_phy_status *)); #else -static inline void fixed_phy_add(const struct fixed_phy_status *status) {} static inline struct phy_device * fixed_phy_register(const struct fixed_phy_status *status, struct device_node *np) @@ -34,6 +33,11 @@ fixed_phy_register(const struct fixed_phy_status *status, return ERR_PTR(-ENODEV); } +static inline struct phy_device *fixed_phy_register_100fd(void) +{ + return ERR_PTR(-ENODEV); +} + static inline void fixed_phy_unregister(struct phy_device *phydev) { } diff --git a/include/linux/phy_port.h b/include/linux/phy_port.h new file mode 100644 index 0000000000000..0ef0f5ce47092 --- /dev/null +++ b/include/linux/phy_port.h @@ -0,0 +1,99 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef __PHY_PORT_H +#define __PHY_PORT_H + +#include +#include +#include + +struct phy_port; + +/** + * enum phy_port_parent - The device this port is attached to + * + * @PHY_PORT_PHY: Indicates that the port is driven by a PHY device + */ +enum phy_port_parent { + PHY_PORT_PHY, +}; + +struct phy_port_ops { + /* Sometimes, the link state can be retrieved from physical, + * out-of-band channels such as the LOS signal on SFP. These + * callbacks allows notifying the port about state changes + */ + void (*link_up)(struct phy_port *port); + void (*link_down)(struct phy_port *port); + + /* If the port acts as a Media Independent Interface (Serdes port), + * configures the port with the relevant state and mode. When enable is + * not set, interface should be ignored + */ + int (*configure_mii)(struct phy_port *port, bool enable, phy_interface_t interface); +}; + +/** + * struct phy_port - A representation of a network device physical interface + * + * @head: Used by the port's parent to list ports + * @parent_type: The type of device this port is directly connected to + * @phy: If the parent is PHY_PORT_PHYDEV, the PHY controlling that port + * @ops: Callback ops implemented by the port controller + * @pairs: The number of pairs this port has, 0 if not applicable + * @mediums: Bitmask of the physical mediums this port provides access to + * @supported: The link modes this port can expose, if this port is MDI (not MII) + * @interfaces: The MII interfaces this port supports, if this port is MII + * @not_described: Indicates to the parent driver if this port isn't described, + * so it's up to the parent to filter its capabilities. + * @active: Indicates if the port is currently part of the active link. + * @is_mii: Indicates if this port is MII (Media Independent Interface), + * or MDI (Media Dependent Interface). + * @is_sfp: Indicates if this port drives an SFP cage. + */ +struct phy_port { + struct list_head head; + enum phy_port_parent parent_type; + union { + struct phy_device *phy; + }; + + const struct phy_port_ops *ops; + + int pairs; + unsigned long mediums; + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); + DECLARE_PHY_INTERFACE_MASK(interfaces); + + unsigned int not_described:1; + unsigned int active:1; + unsigned int is_mii:1; + unsigned int is_sfp:1; +}; + +struct phy_port *phy_port_alloc(void); +void phy_port_destroy(struct phy_port *port); + +static inline struct phy_device *port_phydev(struct phy_port *port) +{ + return port->phy; +} + +struct phy_port *phy_of_parse_port(struct device_node *dn); + +static inline bool phy_port_is_copper(struct phy_port *port) +{ + return port->mediums == BIT(ETHTOOL_LINK_MEDIUM_BASET); +} + +static inline bool phy_port_is_fiber(struct phy_port *port) +{ + return !!(port->mediums & ETHTOOL_MEDIUM_FIBER_BITS); +} + +void phy_port_update_supported(struct phy_port *port); +int phy_port_restrict_mediums(struct phy_port *port, unsigned long mediums); + +int phy_port_get_type(struct phy_port *port); + +#endif diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 9af0411761d75..38363e566ac3d 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -156,6 +156,9 @@ enum phylink_op_type { * @lpi_capabilities: MAC speeds which can support LPI signalling * @lpi_timer_default: Default EEE LPI timer setting. * @eee_enabled_default: If set, EEE will be enabled by phylink at creation time + * @wol_phy_legacy: Use Wake-on-Lan with PHY even if phy_can_wakeup() is false + * @wol_phy_speed_ctrl: Use phy speed control on suspend/resume + * @wol_mac_support: Bitmask of MAC supported %WAKE_* options */ struct phylink_config { struct device *dev; @@ -173,6 +176,11 @@ struct phylink_config { unsigned long lpi_capabilities; u32 lpi_timer_default; bool eee_enabled_default; + + /* Wake-on-Lan support */ + bool wol_phy_legacy; + bool wol_phy_speed_ctrl; + u32 wol_mac_support; }; void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); @@ -188,6 +196,7 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); * @mac_link_up: allow the link to come up. * @mac_disable_tx_lpi: disable LPI. * @mac_enable_tx_lpi: enable and configure LPI. + * @mac_wol_set: configure Wake-on-Lan settings at the MAC. * * The individual methods are described more fully below. */ @@ -211,6 +220,9 @@ struct phylink_mac_ops { void (*mac_disable_tx_lpi)(struct phylink_config *config); int (*mac_enable_tx_lpi)(struct phylink_config *config, u32 timer, bool tx_clk_stop); + + int (*mac_wol_set)(struct phylink_config *config, u32 wolopts, + const u8 *sopass); }; #if 0 /* For kernel-doc purposes only. */ @@ -440,6 +452,22 @@ void mac_disable_tx_lpi(struct phylink_config *config); */ int mac_enable_tx_lpi(struct phylink_config *config, u32 timer, bool tx_clk_stop); + +/** + * mac_wol_set() - configure the Wake-on-Lan parameters + * @config: a pointer to a &struct phylink_config. + * @wolopts: Bitmask of %WAKE_* flags for enabled Wake-On-Lan modes. + * @sopass: SecureOn(tm) password; meaningful only for %WAKE_MAGICSECURE + * + * Enable the specified Wake-on-Lan options at the MAC. Options that the + * PHY can handle will have been removed from @wolopts. + * + * The presence of this method enables phylink-managed WoL support. + * + * Returns: 0 on success. + */ +int (*mac_wol_set)(struct phylink_config *config, u32 wolopts, + const u8 *sopass); #endif struct phylink_pcs_ops; diff --git a/include/linux/platform_data/bcmgenet.h b/include/linux/platform_data/bcmgenet.h deleted file mode 100644 index d8f8738629d20..0000000000000 --- a/include/linux/platform_data/bcmgenet.h +++ /dev/null @@ -1,19 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __LINUX_PLATFORM_DATA_BCMGENET_H__ -#define __LINUX_PLATFORM_DATA_BCMGENET_H__ - -#include -#include -#include - -struct bcmgenet_platform_data { - bool mdio_enabled; - phy_interface_t phy_interface; - int phy_address; - int phy_speed; - int phy_duplex; - u8 mac_address[ETH_ALEN]; - int genet_version; -}; - -#endif diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index 89186c499dd47..c26cb83ca0711 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -52,6 +52,13 @@ static inline void hlist_nulls_del_init_rcu(struct hlist_nulls_node *n) #define hlist_nulls_next_rcu(node) \ (*((struct hlist_nulls_node __rcu __force **)&(node)->next)) +/** + * hlist_nulls_pprev_rcu - returns the dereferenced pprev of @node. + * @node: element of the list. + */ +#define hlist_nulls_pprev_rcu(node) \ + (*((struct hlist_nulls_node __rcu __force **)(node)->pprev)) + /** * hlist_nulls_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. @@ -152,6 +159,58 @@ static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); } +/** + * hlist_nulls_replace_rcu - replace an old entry by a new one + * @old: the element to be replaced + * @new: the new element to insert + * + * Description: + * Replace the old entry with the new one in a RCU-protected hlist_nulls, while + * permitting racing traversals. + * + * The caller must take whatever precautions are necessary (such as holding + * appropriate locks) to avoid racing with another list-mutation primitive, such + * as hlist_nulls_add_head_rcu() or hlist_nulls_del_rcu(), running on this same + * list. However, it is perfectly legal to run concurrently with the _rcu + * list-traversal primitives, such as hlist_nulls_for_each_entry_rcu(). + */ +static inline void hlist_nulls_replace_rcu(struct hlist_nulls_node *old, + struct hlist_nulls_node *new) +{ + struct hlist_nulls_node *next = old->next; + + WRITE_ONCE(new->next, next); + WRITE_ONCE(new->pprev, old->pprev); + rcu_assign_pointer(hlist_nulls_pprev_rcu(new), new); + if (!is_a_nulls(next)) + WRITE_ONCE(next->pprev, &new->next); +} + +/** + * hlist_nulls_replace_init_rcu - replace an old entry by a new one and + * initialize the old + * @old: the element to be replaced + * @new: the new element to insert + * + * Description: + * Replace the old entry with the new one in a RCU-protected hlist_nulls, while + * permitting racing traversals, and reinitialize the old entry. + * + * Note: @old must be hashed. + * + * The caller must take whatever precautions are necessary (such as holding + * appropriate locks) to avoid racing with another list-mutation primitive, such + * as hlist_nulls_add_head_rcu() or hlist_nulls_del_rcu(), running on this same + * list. However, it is perfectly legal to run concurrently with the _rcu + * list-traversal primitives, such as hlist_nulls_for_each_entry_rcu(). + */ +static inline void hlist_nulls_replace_init_rcu(struct hlist_nulls_node *old, + struct hlist_nulls_node *new) +{ + hlist_nulls_replace_rcu(old, new); + WRITE_ONCE(old->pprev, NULL); +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a7cc3d1f4fd11..e09455cee8e3a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -671,7 +671,13 @@ enum { /* This indicates the skb is from an untrusted source. */ SKB_GSO_DODGY = 1 << 1, - /* This indicates the tcp segment has CWR set. */ + /* For Tx, this indicates the first TCP segment has CWR set, and any + * subsequent segment in the same skb has CWR cleared. This is not + * used on Rx except for virtio_net. However, because the connection + * to which the segment belongs is not tracked to use RFC3168 or + * Accurate ECN, and using RFC3168 ECN offload may corrupt AccECN + * signal of AccECN segments. Therefore, this cannot be used on Rx. + */ SKB_GSO_TCP_ECN = 1 << 2, __SKB_GSO_TCP_FIXEDID = 1 << 3, @@ -706,6 +712,12 @@ enum { SKB_GSO_FRAGLIST = 1 << 18, + /* For TX, this indicates the TCP segment uses the CWR flag as part of + * AccECN signal, and the CWR flag is not modified in the skb. This is + * not used on Rx except for virtio_net. For RX, any CWR flagged segment + * must use SKB_GSO_TCP_ACCECN to ensure CWR flag is not cleared by any + * RFC3168 ECN offload, and thus keeping AccECN signal of TCP segments. + */ SKB_GSO_TCP_ACCECN = 1 << 19, /* These indirectly map onto the same netdev feature. @@ -4564,6 +4576,81 @@ static inline void skb_metadata_clear(struct sk_buff *skb) skb_metadata_set(skb, 0); } +/** + * skb_data_move - Move packet data and metadata after skb_push() or skb_pull(). + * @skb: packet to operate on + * @len: number of bytes pushed or pulled from &sk_buff->data + * @n: number of bytes to memmove() from pre-push/pull &sk_buff->data + * + * Moves @n bytes of packet data, can be zero, and all bytes of skb metadata. + * + * Assumes metadata is located immediately before &sk_buff->data prior to the + * push/pull, and that sufficient headroom exists to hold it after an + * skb_push(). Otherwise, metadata is cleared and a one-time warning is issued. + * + * Prefer skb_postpull_data_move() or skb_postpush_data_move() to calling this + * helper directly. + */ +static inline void skb_data_move(struct sk_buff *skb, const int len, + const unsigned int n) +{ + const u8 meta_len = skb_metadata_len(skb); + u8 *meta, *meta_end; + + if (!len || (!n && !meta_len)) + return; + + if (!meta_len) + goto no_metadata; + + meta_end = skb_metadata_end(skb); + meta = meta_end - meta_len; + + if (WARN_ON_ONCE(meta_end + len != skb->data || + meta_len > skb_headroom(skb))) { + skb_metadata_clear(skb); + goto no_metadata; + } + + memmove(meta + len, meta, meta_len + n); + return; + +no_metadata: + memmove(skb->data, skb->data - len, n); +} + +/** + * skb_postpull_data_move - Move packet data and metadata after skb_pull(). + * @skb: packet to operate on + * @len: number of bytes pulled from &sk_buff->data + * @n: number of bytes to memmove() from pre-pull &sk_buff->data + * + * See skb_data_move() for details. + */ +static inline void skb_postpull_data_move(struct sk_buff *skb, + const unsigned int len, + const unsigned int n) +{ + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_data_move(skb, len, n); +} + +/** + * skb_postpush_data_move - Move packet data and metadata after skb_push(). + * @skb: packet to operate on + * @len: number of bytes pushed onto &sk_buff->data + * @n: number of bytes to memmove() from pre-push &sk_buff->data + * + * See skb_data_move() for details. + */ +static inline void skb_postpush_data_move(struct sk_buff *skb, + const unsigned int len, + const unsigned int n) +{ + DEBUG_NET_WARN_ON_ONCE(len > INT_MAX); + skb_data_move(skb, -len, n); +} + struct sk_buff *skb_clone_sk(struct sk_buff *skb); #ifdef CONFIG_NETWORK_PHY_TIMESTAMPING diff --git a/include/linux/socket.h b/include/linux/socket.h index 3b262487ec060..944027f9765e7 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -32,12 +32,27 @@ typedef __kernel_sa_family_t sa_family_t; * 1003.1g requires sa_family_t and that sa_data is char. */ +/* Deprecated for in-kernel use. Use struct sockaddr_unsized instead. */ struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - union { - char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ - DECLARE_FLEX_ARRAY(char, sa_data); - }; + char sa_data[14]; /* 14 bytes of protocol address */ +}; + +/** + * struct sockaddr_unsized - Unspecified size sockaddr for callbacks + * @sa_family: Address family (AF_UNIX, AF_INET, AF_INET6, etc.) + * @sa_data: Flexible array for address data + * + * This structure is designed for callback interfaces where the + * total size is known via the sockaddr_len parameter. Unlike struct + * sockaddr which has a fixed 14-byte sa_data limit or struct + * sockaddr_storage which has a fixed 128-byte sa_data limit, this + * structure can accommodate addresses of any size, but must be used + * carefully. + */ +struct sockaddr_unsized { + __kernel_sa_family_t sa_family; /* address family, AF_xxx */ + char sa_data[]; /* flexible address data */ }; struct linger { diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index fa1318bac06c4..4f70a6551e68c 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -171,7 +171,13 @@ struct dwmac4_addrs { u32 mtl_low_cred_offset; }; -#define STMMAC_FLAG_HAS_INTEGRATED_PCS BIT(0) +enum dwmac_core_type { + DWMAC_CORE_MAC100, + DWMAC_CORE_GMAC, + DWMAC_CORE_GMAC4, + DWMAC_CORE_XGMAC, +}; + #define STMMAC_FLAG_SPH_DISABLE BIT(1) #define STMMAC_FLAG_USE_PHY_WOL BIT(2) #define STMMAC_FLAG_HAS_SUN8I BIT(3) @@ -186,7 +192,10 @@ struct dwmac4_addrs { #define STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP BIT(12) #define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY BIT(13) +struct mac_device_info; + struct plat_stmmacenet_data { + enum dwmac_core_type core_type; int bus_id; int phy_addr; /* MAC ----- optional PCS ----- SerDes ----- optional PHY ----- Media @@ -220,7 +229,6 @@ struct plat_stmmacenet_data { struct stmmac_dma_cfg *dma_cfg; struct stmmac_safety_feature_cfg *safety_feat_cfg; int clk_csr; - int has_gmac; int enh_desc; int tx_coe; int rx_coe; @@ -244,6 +252,7 @@ struct plat_stmmacenet_data { struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES]; void (*get_interfaces)(struct stmmac_priv *priv, void *bsp_priv, unsigned long *interfaces); + int (*set_phy_intf_sel)(void *priv, u8 phy_intf_sel); int (*set_clk_tx_rate)(void *priv, struct clk *clk_tx_i, phy_interface_t interface, int speed); void (*fix_mac_speed)(void *priv, int speed, unsigned int mode); @@ -259,7 +268,7 @@ struct plat_stmmacenet_data { void (*exit)(struct platform_device *pdev, void *priv); int (*suspend)(struct device *dev, void *priv); int (*resume)(struct device *dev, void *priv); - struct mac_device_info *(*setup)(void *priv); + int (*mac_setup)(void *priv, struct mac_device_info *mac); int (*clks_config)(void *priv, bool enabled); int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); @@ -283,10 +292,8 @@ struct plat_stmmacenet_data { struct reset_control *stmmac_rst; struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; - int has_gmac4; int rss_en; int mac_port_sel_speed; - int has_xgmac; u8 vlan_fail_q; struct pci_dev *pdev; int int_snapshot_num; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 20b8c6e21fef3..32b031d092949 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -294,7 +294,8 @@ struct tcp_sock { u8 nonagle : 4,/* Disable Nagle algorithm? */ rate_app_limited:1; /* rate_{delivered,interval_us} limited? */ u8 received_ce_pending:4, /* Not yet transmit cnt of received_ce */ - unused2:4; + accecn_opt_sent:1,/* Sent AccECN option in previous ACK */ + unused2:3; u8 accecn_minlen:2,/* Minimum length of AccECN option sent */ est_ecnfield:2,/* ECN field for AccECN delivered estimates */ accecn_opt_demand:2,/* Demand AccECN option for n next ACKs */ @@ -345,6 +346,7 @@ struct tcp_sock { u32 rate_interval_us; /* saved rate sample: time elapsed */ u32 rcv_rtt_last_tsecr; u32 delivered_ecn_bytes[3]; + u16 pkts_acked_ewma;/* Pkts acked EWMA for AccECN cep heuristic */ u64 first_tx_mstamp; /* start of window send phase */ u64 delivered_mstamp; /* time we reached "delivered" */ u64 bytes_acked; /* RFC4898 tcpEStatsAppHCThruOctetsAcked diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index a2d54122823da..2945923a8a958 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -14,6 +14,7 @@ #include #include #include +#include /* interface from usbnet core to each USB networking link we handle */ struct usbnet { @@ -59,6 +60,7 @@ struct usbnet { struct mutex interrupt_mutex; struct usb_anchor deferred; struct work_struct bh_work; + spinlock_t bql_spinlock; struct work_struct kevent; unsigned long flags; diff --git a/include/linux/virtio_admin.h b/include/linux/virtio_admin.h new file mode 100644 index 0000000000000..db0f42346ca9b --- /dev/null +++ b/include/linux/virtio_admin.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Header file for virtio admin operations + */ +#include +#include + +#ifndef _LINUX_VIRTIO_ADMIN_H +#define _LINUX_VIRTIO_ADMIN_H + +struct virtio_device; + +/** + * VIRTIO_CAP_IN_LIST - Check if a capability is supported in the capability list + * @cap_list: Pointer to capability list structure containing supported_caps array + * @cap: Capability ID to check + * + * The cap_list contains a supported_caps array of little-endian 64-bit integers + * where each bit represents a capability. Bit 0 of the first element represents + * capability ID 0, bit 1 represents capability ID 1, and so on. + * + * Return: 1 if capability is supported, 0 otherwise + */ +#define VIRTIO_CAP_IN_LIST(cap_list, cap) \ + (!!(1 & (le64_to_cpu(cap_list->supported_caps[cap / 64]) >> cap % 64))) + +/** + * virtio_admin_cap_id_list_query - Query the list of available capability IDs + * @vdev: The virtio device to query + * @data: Pointer to result structure (must be heap allocated) + * + * This function queries the virtio device for the list of available capability + * IDs that can be used with virtio_admin_cap_get() and virtio_admin_cap_set(). + * The result is stored in the provided data structure. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or capability queries, or a negative error code on other failures. + */ +int virtio_admin_cap_id_list_query(struct virtio_device *vdev, + struct virtio_admin_cmd_query_cap_id_result *data); + +/** + * virtio_admin_cap_get - Get capability data for a specific capability ID + * @vdev: The virtio device + * @id: Capability ID to retrieve + * @caps: Pointer to capability data structure (must be heap allocated) + * @cap_size: Size of the capability data structure + * + * This function retrieves a specific capability from the virtio device. + * The capability data is stored in the provided buffer. The caller must + * ensure the buffer is large enough to hold the capability data. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or capability retrieval, or a negative error code on other failures. + */ +int virtio_admin_cap_get(struct virtio_device *vdev, + u16 id, + void *caps, + size_t cap_size); + +/** + * virtio_admin_cap_set - Set capability data for a specific capability ID + * @vdev: The virtio device + * @id: Capability ID to set + * @caps: Pointer to capability data structure (must be heap allocated) + * @cap_size: Size of the capability data structure + * + * This function sets a specific capability on the virtio device. + * The capability data is read from the provided buffer and applied + * to the device. The device may validate the capability data before + * applying it. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or capability setting, or a negative error code on other failures. + */ +int virtio_admin_cap_set(struct virtio_device *vdev, + u16 id, + const void *caps, + size_t cap_size); + +/** + * virtio_admin_obj_create - Create an object on a virtio device + * @vdev: the virtio device + * @obj_type: type of object to create + * @obj_id: ID for the new object + * @group_type: administrative group type for the operation + * @group_member_id: member identifier within the administrative group + * @obj_specific_data: object-specific data for creation + * @obj_specific_data_size: size of the object-specific data in bytes + * + * Creates a new object on the virtio device with the specified type and ID. + * The object may require object-specific data for proper initialization. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or object creation, or a negative error code on other failures. + */ +int virtio_admin_obj_create(struct virtio_device *vdev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id, + const void *obj_specific_data, + size_t obj_specific_data_size); + +/** + * virtio_admin_obj_destroy - Destroy an object on a virtio device + * @vdev: the virtio device + * @obj_type: type of object to destroy + * @obj_id: ID of the object to destroy + * @group_type: administrative group type for the operation + * @group_member_id: member identifier within the administrative group + * + * Destroys an existing object on the virtio device with the specified type + * and ID. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or object destruction, or a negative error code on other failures. + */ +int virtio_admin_obj_destroy(struct virtio_device *vdev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id); + +#endif /* _LINUX_VIRTIO_ADMIN_H */ diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h index 16001e9f9b391..19606609254e9 100644 --- a/include/linux/virtio_config.h +++ b/include/linux/virtio_config.h @@ -108,6 +108,10 @@ struct virtqueue_info { * Returns 0 on success or error status * If disable_vq_and_reset is set, then enable_vq_after_reset must also be * set. + * @admin_cmd_exec: Execute an admin VQ command. + * vdev: the virtio_device + * cmd: the command to execute + * Returns 0 on success or error status */ struct virtio_config_ops { void (*get)(struct virtio_device *vdev, unsigned offset, @@ -137,6 +141,8 @@ struct virtio_config_ops { struct virtio_shm_region *region, u8 id); int (*disable_vq_and_reset)(struct virtqueue *vq); int (*enable_vq_after_reset)(struct virtqueue *vq); + int (*admin_cmd_exec)(struct virtio_device *vdev, + struct virtio_admin_cmd *cmd); }; /** diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 9e5e95988b9e5..78e8b877fb257 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -347,6 +347,11 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) return rcu_dereference_rtnl(dev->ip6_ptr); } +static inline struct inet6_dev *in6_dev_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->ip6_ptr); +} + static inline struct inet6_dev *__in6_dev_get_rtnl_net(const struct net_device *dev) { return rtnl_net_dereference(dev_net(dev), dev->ip6_ptr); diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 820e299f06b5e..625cb2c783613 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -685,7 +685,7 @@ ieee80211_get_he_6ghz_capa(const struct ieee80211_supported_band *sband, } /** - * ieee80211_get_eht_iftype_cap - return ETH capabilities for an sband's iftype + * ieee80211_get_eht_iftype_cap - return EHT capabilities for an sband's iftype * @sband: the sband to search for the iftype on * @iftype: enum nl80211_iftype * @@ -786,8 +786,7 @@ struct vif_params { * @key: key material * @key_len: length of key material * @cipher: cipher suite selector - * @seq: sequence counter (IV/PN) for TKIP and CCMP keys, only used - * with the get_key() callback, must be in little endian, + * @seq: sequence counter (IV/PN), must be in little endian, * length given by @seq_len. * @seq_len: length of @seq. * @vlan_id: vlan_id for VLAN group key (if nonzero) @@ -1015,6 +1014,7 @@ const struct cfg80211_chan_def * cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1, const struct cfg80211_chan_def *chandef2); + /** * nl80211_chan_width_to_mhz - get the channel width in MHz * @chan_width: the channel width from &enum nl80211_chan_width @@ -5683,9 +5683,13 @@ struct wiphy_iftype_akm_suites { * * @rts_threshold: RTS threshold (dot11RTSThreshold); * -1 (default) = RTS/CTS disabled + * @radio_debugfsdir: Pointer to debugfs directory containing the radio- + * specific parameters. + * NULL (default) = Debugfs directory not created */ struct wiphy_radio_cfg { u32 rts_threshold; + struct dentry *radio_debugfsdir; }; /** @@ -6960,6 +6964,19 @@ static inline bool cfg80211_channel_is_psc(struct ieee80211_channel *chan) return ieee80211_frequency_to_channel(chan->center_freq) % 16 == 5; } +/** + * ieee80211_radio_freq_range_valid - Check if the radio supports the + * specified frequency range + * + * @radio: wiphy radio + * @freq: the frequency (in KHz) to be queried + * @width: the bandwidth (in KHz) to be queried + * + * Return: whether or not the given frequency range is valid for the given radio + */ +bool ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, + u32 freq, u32 width); + /** * cfg80211_radio_chandef_valid - Check if the radio supports the chandef * @@ -10117,6 +10134,35 @@ static inline int cfg80211_color_change_notify(struct net_device *dev, 0, 0, link_id); } +/** + * cfg80211_6ghz_power_type - determine AP regulatory power type + * @control: control flags + * @client_flags: &enum ieee80211_channel_flags for station mode to enable + * SP to LPI fallback, zero otherwise. + * + * Return: regulatory power type from &enum ieee80211_ap_reg_power + */ +static inline enum ieee80211_ap_reg_power +cfg80211_6ghz_power_type(u8 control, u32 client_flags) +{ + switch (u8_get_bits(control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { + case IEEE80211_6GHZ_CTRL_REG_LPI_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: + return IEEE80211_REG_LPI_AP; + case IEEE80211_6GHZ_CTRL_REG_SP_AP: + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD: + return IEEE80211_REG_SP_AP; + case IEEE80211_6GHZ_CTRL_REG_VLP_AP: + return IEEE80211_REG_VLP_AP; + case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: + if (client_flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) + return IEEE80211_REG_LPI_AP; + return IEEE80211_REG_SP_AP; + default: + return IEEE80211_REG_UNSET_AP; + } +} + /** * cfg80211_links_removed - Notify about removed STA MLD setup links. * @dev: network device. diff --git a/include/net/devlink.h b/include/net/devlink.h index 9e824f61e40f6..d01046ef0577c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -532,6 +532,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_CLOCK_ID, DEVLINK_PARAM_GENERIC_ID_TOTAL_VFS, DEVLINK_PARAM_GENERIC_ID_NUM_DOORBELLS, + DEVLINK_PARAM_GENERIC_ID_MAX_MAC_PER_VF, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -602,6 +603,9 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_NUM_DOORBELLS_NAME "num_doorbells" #define DEVLINK_PARAM_GENERIC_NUM_DOORBELLS_TYPE DEVLINK_PARAM_TYPE_U32 +#define DEVLINK_PARAM_GENERIC_MAX_MAC_PER_VF_NAME "max_mac_per_vf" +#define DEVLINK_PARAM_GENERIC_MAX_MAC_PER_VF_TYPE DEVLINK_PARAM_TYPE_U32 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/include/net/dsa.h b/include/net/dsa.h index d73ea08800660..97d5f401cfcf9 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -55,6 +55,8 @@ struct tc_action; #define DSA_TAG_PROTO_LAN937X_VALUE 27 #define DSA_TAG_PROTO_VSC73XX_8021Q_VALUE 28 #define DSA_TAG_PROTO_BRCM_LEGACY_FCS_VALUE 29 +#define DSA_TAG_PROTO_YT921X_VALUE 30 +#define DSA_TAG_PROTO_MXL_GSW1XX_VALUE 31 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -87,6 +89,8 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_RZN1_A5PSW = DSA_TAG_PROTO_RZN1_A5PSW_VALUE, DSA_TAG_PROTO_LAN937X = DSA_TAG_PROTO_LAN937X_VALUE, DSA_TAG_PROTO_VSC73XX_8021Q = DSA_TAG_PROTO_VSC73XX_8021Q_VALUE, + DSA_TAG_PROTO_YT921X = DSA_TAG_PROTO_YT921X_VALUE, + DSA_TAG_PROTO_MXL_GSW1XX = DSA_TAG_PROTO_MXL_GSW1XX_VALUE, }; struct dsa_switch; @@ -1310,11 +1314,6 @@ static inline int dsa_devlink_port_to_port(struct devlink_port *port) return port->index; } -struct dsa_switch_driver { - struct list_head list; - const struct dsa_switch_ops *ops; -}; - bool dsa_fdb_present_in_other_db(struct dsa_switch *ds, int port, const unsigned char *addr, u16 vid, struct dsa_db db); diff --git a/include/net/gro.h b/include/net/gro.h index e3affb2e2ca8b..b65f631c521d7 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -593,4 +593,31 @@ static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int * struct packet_offload *gro_find_receive_by_type(__be16 type); struct packet_offload *gro_find_complete_by_type(__be16 type); +static inline struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) +{ + unsigned int thlen, hlen, off; + struct tcphdr *th; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*th); + th = skb_gro_header(skb, hlen, off); + if (unlikely(!th)) + return NULL; + + thlen = th->doff * 4; + if (unlikely(thlen < sizeof(*th))) + return NULL; + + hlen = off + thlen; + if (!skb_gro_may_pull(skb, hlen)) { + th = skb_gro_header_slow(skb, hlen, off); + if (unlikely(!th)) + return NULL; + } + + skb_gro_pull(skb, thlen); + + return th; +} + #endif /* _NET_GRO_H */ diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h index 813e163ce27cc..c60867e7e43c9 100644 --- a/include/net/ieee80211_radiotap.h +++ b/include/net/ieee80211_radiotap.h @@ -1,6 +1,6 @@ /* * Copyright (c) 2017 Intel Deutschland GmbH - * Copyright (c) 2018-2019, 2021-2022 Intel Corporation + * Copyright (c) 2018-2019, 2021-2022, 2025 Intel Corporation * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -202,6 +202,24 @@ enum ieee80211_radiotap_vht_coding { IEEE80211_RADIOTAP_CODING_LDPC_USER3 = 0x08, }; +enum ieee80211_radiotap_vht_bandwidth { + /* Note: more values are defined but can't really be used */ + IEEE80211_RADIOTAP_VHT_BW_20 = 0, + IEEE80211_RADIOTAP_VHT_BW_40 = 1, + IEEE80211_RADIOTAP_VHT_BW_80 = 4, + IEEE80211_RADIOTAP_VHT_BW_160 = 11, +}; + +struct ieee80211_radiotap_vht { + __le16 known; + u8 flags; + u8 bandwidth; + u8 mcs_nss[4]; + u8 coding; + u8 group_id; + __le16 partial_aid; +} __packed; + /* for IEEE80211_RADIOTAP_TIMESTAMP */ enum ieee80211_radiotap_timestamp_unit_spos { IEEE80211_RADIOTAP_TIMESTAMP_UNIT_MASK = 0x000F, diff --git a/include/net/inet_common.h b/include/net/inet_common.h index c17a6585d0b0b..5dd2bf24449ef 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -19,15 +19,14 @@ struct msghdr; struct net; struct page; struct sock; -struct sockaddr; struct socket; int inet_release(struct socket *sock); -int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, +int inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags); -int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, +int __inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags, int is_sendmsg); -int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, +int inet_dgram_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags); int inet_accept(struct socket *sock, struct socket *newsock, struct proto_accept_arg *arg); @@ -42,8 +41,8 @@ int inet_shutdown(struct socket *sock, int how); int inet_listen(struct socket *sock, int backlog); int __inet_listen_sk(struct sock *sk, int backlog); void inet_sock_destruct(struct sock *sk); -int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); -int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len); +int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); /* Don't allocate port at this moment, defer to connect. */ #define BIND_FORCE_ADDRESS_NO_PORT (1 << 0) /* Grab and release socket lock. */ @@ -52,7 +51,7 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); #define BIND_FROM_BPF (1 << 2) /* Skip CAP_NET_BIND_SERVICE check. */ #define BIND_NO_CAP_NET_BIND_SERVICE (1 << 3) -int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, +int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags); int inet_getname(struct socket *sock, struct sockaddr *uaddr, int peer); diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b4b8866476075..fd40af2221b99 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -267,8 +267,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); -bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, - unsigned long timeout); +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, bool own_req); @@ -291,14 +290,6 @@ static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk) bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req); void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req); -static inline unsigned long -reqsk_timeout(struct request_sock *req, unsigned long max_timeout) -{ - u64 timeout = (u64)req->timeout << req->num_timeout; - - return (unsigned long)min_t(u64, timeout, max_timeout); -} - void inet_csk_destroy_sock(struct sock *sk); void inet_csk_prepare_for_destroy_sock(struct sock *sk); void inet_csk_prepare_forced_close(struct sock *sk); diff --git a/include/net/inet_ecn.h b/include/net/inet_ecn.h index ea32393464a29..827b87a95dab3 100644 --- a/include/net/inet_ecn.h +++ b/include/net/inet_ecn.h @@ -51,11 +51,25 @@ static inline __u8 INET_ECN_encapsulate(__u8 outer, __u8 inner) return outer; } +/* Apply either ECT(0) or ECT(1) */ +static inline void __INET_ECN_xmit(struct sock *sk, bool use_ect_1) +{ + __u8 ect = use_ect_1 ? INET_ECN_ECT_1 : INET_ECN_ECT_0; + + /* Mask the complete byte in case the connection alternates between + * ECT(0) and ECT(1). + */ + inet_sk(sk)->tos &= ~INET_ECN_MASK; + inet_sk(sk)->tos |= ect; + if (inet6_sk(sk)) { + inet6_sk(sk)->tclass &= ~INET_ECN_MASK; + inet6_sk(sk)->tclass |= ect; + } +} + static inline void INET_ECN_xmit(struct sock *sk) { - inet_sk(sk)->tos |= INET_ECN_ECT_0; - if (inet6_sk(sk) != NULL) - inet6_sk(sk)->tclass |= INET_ECN_ECT_0; + __INET_ECN_xmit(sk, false); } static inline void INET_ECN_dontxmit(struct sock *sk) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 1086256549faa..ac1c75975908a 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -214,6 +214,7 @@ struct inet_sock { struct sock sk; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *pinet6; + struct ipv6_fl_socklist __rcu *ipv6_fl_list; #endif /* Socket demultiplex comparisons on incoming packets. */ #define inet_daddr sk.__sk_common.skc_daddr @@ -354,14 +355,6 @@ static inline struct sock *skb_to_full_sk(const struct sk_buff *skb) #define inet_sk(ptr) container_of_const(ptr, struct inet_sock, sk) -static inline void __inet_sk_copy_descendant(struct sock *sk_to, - const struct sock *sk_from, - const int ancestor_size) -{ - memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1, - sk_from->sk_prot->obj_size - ancestor_size); -} - int inet_sk_rebuild_header(struct sock *sk); /** diff --git a/include/net/ip.h b/include/net/ip.h index 380afb691c419..69d5cef460040 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -261,8 +261,8 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet, } /* datagram.c */ -int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); -int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int __ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); +int ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); void ip4_datagram_release_cb(struct sock *sk); diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 2ccdf85f34f16..74fbf1ad8065a 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -1188,10 +1188,10 @@ int do_ipv6_getsockopt(struct sock *sk, int level, int optname, int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); -int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, +int __ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); -int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); -int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, +int ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); +int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); @@ -1208,8 +1208,8 @@ void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); -int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int inet6_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len); +int inet6_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); diff --git a/include/net/ipv6_stubs.h b/include/net/ipv6_stubs.h index 8a3465c8c2c5c..d3013e721b144 100644 --- a/include/net/ipv6_stubs.h +++ b/include/net/ipv6_stubs.h @@ -80,7 +80,7 @@ extern const struct ipv6_stub *ipv6_stub __read_mostly; /* A stub used by bpf helpers. Similarly ugly as ipv6_stub */ struct ipv6_bpf_stub { - int (*inet6_bind)(struct sock *sk, struct sockaddr *uaddr, int addr_len, + int (*inet6_bind)(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags); struct sock *(*udp6_lib_lookup)(const struct net *net, const struct in6_addr *saddr, __be16 sport, diff --git a/include/net/mac80211.h b/include/net/mac80211.h index a55085cf4ec49..c2e49542626c8 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1529,6 +1529,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) * known the frame shouldn't be reported. * @RX_FLAG_8023: the frame has an 802.3 header (decap offload performed by * hardware or driver) + * @RX_FLAG_RADIOTAP_VHT: VHT radiotap data is present */ enum mac80211_rx_flags { RX_FLAG_MMIC_ERROR = BIT(0), @@ -1564,6 +1565,7 @@ enum mac80211_rx_flags { RX_FLAG_RADIOTAP_LSIG = BIT(28), RX_FLAG_NO_PSDU = BIT(29), RX_FLAG_8023 = BIT(30), + RX_FLAG_RADIOTAP_VHT = BIT(31), }; /** @@ -7221,7 +7223,7 @@ ieee80211_get_he_6ghz_capa_vif(const struct ieee80211_supported_band *sband, } /** - * ieee80211_get_eht_iftype_cap_vif - return ETH capabilities for sband/vif + * ieee80211_get_eht_iftype_cap_vif - return EHT capabilities for sband/vif * @sband: the sband to search for the iftype on * @vif: the vif to get the iftype from * diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h index 57df78cfbf82c..2e4f2f3175e55 100644 --- a/include/net/mana/gdma.h +++ b/include/net/mana/gdma.h @@ -590,6 +590,10 @@ enum { /* Driver can self reset on FPGA Reconfig EQE notification */ #define GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE BIT(17) +#define GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE BIT(6) + +/* Driver can send HWC periodically to query stats */ +#define GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY BIT(21) #define GDMA_DRV_CAP_FLAGS1 \ (GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \ @@ -599,7 +603,9 @@ enum { GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP | \ GDMA_DRV_CAP_FLAG_1_DYNAMIC_IRQ_ALLOC_SUPPORT | \ GDMA_DRV_CAP_FLAG_1_SELF_RESET_ON_EQE | \ - GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE) + GDMA_DRV_CAP_FLAG_1_HANDLE_RECONFIG_EQE | \ + GDMA_DRV_CAP_FLAG_1_HW_VPORT_LINK_AWARE | \ + GDMA_DRV_CAP_FLAG_1_PERIODIC_STATS_QUERY) #define GDMA_DRV_CAP_FLAGS2 0 diff --git a/include/net/mana/hw_channel.h b/include/net/mana/hw_channel.h index 83cf93338eb38..16feb39616c1b 100644 --- a/include/net/mana/hw_channel.h +++ b/include/net/mana/hw_channel.h @@ -24,6 +24,8 @@ #define HWC_INIT_DATA_PF_DEST_CQ_ID 11 #define HWC_DATA_CFG_HWC_TIMEOUT 1 +#define HWC_DATA_HW_LINK_CONNECT 2 +#define HWC_DATA_HW_LINK_DISCONNECT 3 #define HW_CHANNEL_WAIT_RESOURCE_TIMEOUT_MS 30000 diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h index 0921485565c05..d37f4cea0ac3e 100644 --- a/include/net/mana/mana.h +++ b/include/net/mana/mana.h @@ -375,6 +375,13 @@ struct mana_tx_qp { struct mana_ethtool_stats { u64 stop_queue; u64 wake_queue; + u64 tx_cqe_err; + u64 tx_cqe_unknown_type; + u64 rx_coalesced_err; + u64 rx_cqe_unknown_type; +}; + +struct mana_ethtool_hc_stats { u64 hc_rx_discards_no_wqe; u64 hc_rx_err_vport_disabled; u64 hc_rx_bytes; @@ -402,10 +409,6 @@ struct mana_ethtool_stats { u64 hc_tx_mcast_pkts; u64 hc_tx_mcast_bytes; u64 hc_tx_err_gdma; - u64 tx_cqe_err; - u64 tx_cqe_unknown_type; - u64 rx_coalesced_err; - u64 rx_cqe_unknown_type; }; struct mana_ethtool_phy_stats { @@ -473,10 +476,19 @@ struct mana_context { u16 num_ports; u8 bm_hostmode; + struct mana_ethtool_hc_stats hc_stats; struct mana_eq *eqs; struct dentry *mana_eqs_debugfs; + /* Workqueue for querying hardware stats */ + struct delayed_work gf_stats_work; + bool hwc_timeout_occurred; + struct net_device *ports[MAX_PORTS_IN_MANA_DEV]; + + /* Link state change work */ + struct work_struct link_change_work; + u32 link_event; }; struct mana_port_context { @@ -573,7 +585,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq, struct bpf_prog *mana_xdp_get(struct mana_port_context *apc); void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog); int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf); -void mana_query_gf_stats(struct mana_port_context *apc); +int mana_query_gf_stats(struct mana_context *ac); int mana_query_link_cfg(struct mana_port_context *apc); int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed, int enable_clamping); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 4a30bd458c5a9..2dfee6d4258af 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -92,15 +92,17 @@ struct neigh_parms { static inline void neigh_var_set(struct neigh_parms *p, int index, int val) { set_bit(index, p->data_state); - p->data[index] = val; + WRITE_ONCE(p->data[index], val); } -#define NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) +#define __NEIGH_VAR(p, attr) ((p)->data[NEIGH_VAR_ ## attr]) +#define NEIGH_VAR(p, attr) READ_ONCE(__NEIGH_VAR(p, attr)) +#define NEIGH_VAR_PTR(p, attr) (&(__NEIGH_VAR(p, attr))) /* In ndo_neigh_setup, NEIGH_VAR_INIT should be used. * In other cases, NEIGH_VAR_SET should be used. */ -#define NEIGH_VAR_INIT(p, attr, val) (NEIGH_VAR(p, attr) = val) +#define NEIGH_VAR_INIT(p, attr, val) (__NEIGH_VAR(p, attr) = val) #define NEIGH_VAR_SET(p, attr, val) neigh_var_set(p, NEIGH_VAR_ ## attr, val) static inline void neigh_parms_data_state_setall(struct neigh_parms *p) @@ -236,7 +238,7 @@ struct neigh_table { atomic_t gc_entries; struct list_head gc_list; struct list_head managed_list; - rwlock_t lock; + spinlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; struct neigh_hash_table __rcu *nht; @@ -378,6 +380,13 @@ struct net *neigh_parms_net(const struct neigh_parms *parms) unsigned long neigh_rand_reach_time(unsigned long base); +static inline void neigh_set_reach_time(struct neigh_parms *p) +{ + unsigned long base = NEIGH_VAR(p, BASE_REACHABLE_TIME); + + WRITE_ONCE(p->reachable_time, neigh_rand_reach_time(base)); +} + void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, struct sk_buff *skb); struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h index 6929f8daf1ed0..cd5020835a6d3 100644 --- a/include/net/netfilter/nf_conntrack_l4proto.h +++ b/include/net/netfilter/nf_conntrack_l4proto.h @@ -30,7 +30,7 @@ struct nf_conntrack_l4proto { /* called by gc worker if table is full */ bool (*can_early_drop)(const struct nf_conn *ct); - /* convert protoinfo to nfnetink attributes */ + /* convert protoinfo to nfnetlink attributes */ int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla, struct nf_conn *ct, bool destroy); diff --git a/include/net/netmem.h b/include/net/netmem.h index f7dacc9e75fd1..9e10f4ac50c3d 100644 --- a/include/net/netmem.h +++ b/include/net/netmem.h @@ -68,10 +68,6 @@ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers); enum net_iov_type { NET_IOV_DMABUF, NET_IOV_IOURING, - - /* Force size to unsigned long to make the NET_IOV_ASSERTS below pass. - */ - NET_IOV_MAX = ULONG_MAX }; /* A memory descriptor representing abstract networking I/O vectors, @@ -247,6 +243,23 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem) return page_to_pfn(netmem_to_page(netmem)); } +/* XXX: How to extract netmem_desc from page must be changed, once + * netmem_desc no longer overlays on page and will be allocated through + * slab. + */ +#define __pp_page_to_nmdesc(p) (_Generic((p), \ + const struct page * : (const struct netmem_desc *)(p), \ + struct page * : (struct netmem_desc *)(p))) + +/* CAUTION: Check if the page is a pp page before calling this helper or + * know it's a pp page. + */ +#define pp_page_to_nmdesc(p) \ +({ \ + DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p)); \ + __pp_page_to_nmdesc(p); \ +}) + /** * __netmem_to_nmdesc - unsafely get pointer to the &netmem_desc backing * @netmem @@ -265,42 +278,25 @@ static inline struct netmem_desc *__netmem_to_nmdesc(netmem_ref netmem) return (__force struct netmem_desc *)netmem; } -/* __netmem_clear_lsb - convert netmem_ref to struct net_iov * for access to - * common fields. - * @netmem: netmem reference to extract as net_iov. +/* netmem_to_nmdesc - convert netmem_ref to struct netmem_desc * for + * access to common fields. + * @netmem: netmem reference to get netmem_desc. * - * All the sub types of netmem_ref (page, net_iov) have the same pp, pp_magic, - * dma_addr, and pp_ref_count fields at the same offsets. Thus, we can access - * these fields without a type check to make sure that the underlying mem is - * net_iov or page. + * All the sub types of netmem_ref (netmem_desc, net_iov) have the same + * pp, pp_magic, dma_addr, and pp_ref_count fields via netmem_desc. * - * The resulting value of this function can only be used to access the fields - * that are NET_IOV_ASSERT_OFFSET'd. Accessing any other fields will result in - * undefined behavior. - * - * Return: the netmem_ref cast to net_iov* regardless of its underlying type. + * Return: the pointer to struct netmem_desc * regardless of its + * underlying type. */ -static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem) +static inline struct netmem_desc *netmem_to_nmdesc(netmem_ref netmem) { - return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV); -} + void *p = (void *)((__force unsigned long)netmem & ~NET_IOV); -/* XXX: How to extract netmem_desc from page must be changed, once - * netmem_desc no longer overlays on page and will be allocated through - * slab. - */ -#define __pp_page_to_nmdesc(p) (_Generic((p), \ - const struct page * : (const struct netmem_desc *)(p), \ - struct page * : (struct netmem_desc *)(p))) + if (netmem_is_net_iov(netmem)) + return &((struct net_iov *)p)->desc; -/* CAUTION: Check if the page is a pp page before calling this helper or - * know it's a pp page. - */ -#define pp_page_to_nmdesc(p) \ -({ \ - DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p)); \ - __pp_page_to_nmdesc(p); \ -}) + return __pp_page_to_nmdesc((struct page *)p); +} /** * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem @@ -320,12 +316,12 @@ static inline struct page_pool *__netmem_get_pp(netmem_ref netmem) static inline struct page_pool *netmem_get_pp(netmem_ref netmem) { - return __netmem_clear_lsb(netmem)->pp; + return netmem_to_nmdesc(netmem)->pp; } static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem) { - return &__netmem_clear_lsb(netmem)->pp_ref_count; + return &netmem_to_nmdesc(netmem)->pp_ref_count; } static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid) @@ -390,7 +386,7 @@ static inline bool netmem_is_pfmemalloc(netmem_ref netmem) static inline unsigned long netmem_get_dma_addr(netmem_ref netmem) { - return __netmem_clear_lsb(netmem)->dma_addr; + return netmem_to_nmdesc(netmem)->dma_addr; } void get_netmem(netmem_ref netmem); diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 9b36f0ff0c200..9ef3d70e5e9c0 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -13,9 +13,11 @@ struct netns_core { struct ctl_table_header *sysctl_hdr; int sysctl_somaxconn; + int sysctl_txq_reselection; int sysctl_optmem_max; u8 sysctl_txrehash; u8 sysctl_tstamp_allow_data; + u8 sysctl_bypass_prot_mem; #ifdef CONFIG_PROC_FS struct prot_inuse __percpu *prot_inuse; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 34eb3aecb3f21..de9d36acc8e22 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -135,6 +135,7 @@ struct netns_ipv4 { u8 sysctl_icmp_echo_ignore_broadcasts; u8 sysctl_icmp_ignore_bogus_error_responses; u8 sysctl_icmp_errors_use_inbound_ifaddr; + u8 sysctl_icmp_errors_extension_mask; int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_msgs_per_sec; @@ -220,6 +221,7 @@ struct netns_ipv4 { int sysctl_tcp_pacing_ss_ratio; int sysctl_tcp_pacing_ca_ratio; unsigned int sysctl_tcp_child_ehash_entries; + int sysctl_tcp_comp_sack_rtt_percent; unsigned long sysctl_tcp_comp_sack_delay_ns; unsigned long sysctl_tcp_comp_sack_slack_ns; int sysctl_max_syn_backlog; diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 47dc70d8100a4..08d2ecc96e2b4 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -56,6 +56,7 @@ struct netns_sysctl_ipv6 { u8 skip_notify_on_dev_down; u8 fib_notify_on_flag_change; u8 icmpv6_error_anycast_as_unicast; + u8 icmpv6_errors_extension_mask; }; struct netns_ipv6 { diff --git a/include/net/netns/mpls.h b/include/net/netns/mpls.h index 19ad2574b267c..6682e51513efa 100644 --- a/include/net/netns/mpls.h +++ b/include/net/netns/mpls.h @@ -16,6 +16,7 @@ struct netns_mpls { int default_ttl; size_t platform_labels; struct mpls_route __rcu * __rcu *platform_label; + struct mutex platform_mutex; struct ctl_table_header *ctl; }; diff --git a/include/net/netns/smc.h b/include/net/netns/smc.h index fc752a50f91b4..ed24c9f638eea 100644 --- a/include/net/netns/smc.h +++ b/include/net/netns/smc.h @@ -17,6 +17,9 @@ struct netns_smc { #ifdef CONFIG_SYSCTL struct ctl_table_header *smc_hdr; #endif +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) + struct smc_hs_ctrl __rcu *hs_ctrl; +#endif /* CONFIG_SMC_HS_CTRL_BPF */ unsigned int sysctl_autocorking_size; unsigned int sysctl_smcr_buf_type; int sysctl_smcr_testlink_time; @@ -24,5 +27,7 @@ struct netns_smc { int sysctl_rmem; int sysctl_max_links_per_lgr; int sysctl_max_conns_per_lgr; + unsigned int sysctl_smcr_max_send_wr; + unsigned int sysctl_smcr_max_recv_wr; }; #endif diff --git a/include/net/nl802154.h b/include/net/nl802154.h index a994dea745966..442822746e924 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -191,14 +191,12 @@ enum nl802154_iftype { * @NL802154_CAP_ATTR_CHANNELS: a nested attribute for nl802154_channel_attr * @NL802154_CAP_ATTR_TX_POWERS: a nested attribute for * nl802154_wpan_phy_tx_power - * @NL802154_CAP_ATTR_MIN_CCA_ED_LEVEL: minimum value for cca_ed_level - * @NL802154_CAP_ATTR_MAX_CCA_ED_LEVEL: maximum value for cca_ed_level * @NL802154_CAP_ATTR_CCA_MODES: nl802154_cca_modes flags * @NL802154_CAP_ATTR_CCA_OPTS: nl802154_cca_opts flags * @NL802154_CAP_ATTR_MIN_MINBE: minimum of minbe value * @NL802154_CAP_ATTR_MAX_MINBE: maximum of minbe value * @NL802154_CAP_ATTR_MIN_MAXBE: minimum of maxbe value - * @NL802154_CAP_ATTR_MAX_MINBE: maximum of maxbe value + * @NL802154_CAP_ATTR_MAX_MAXBE: maximum of maxbe value * @NL802154_CAP_ATTR_MIN_CSMA_BACKOFFS: minimum of csma backoff value * @NL802154_CAP_ATTR_MAX_CSMA_BACKOFFS: maximum of csma backoffs value * @NL802154_CAP_ATTR_MIN_FRAME_RETRIES: minimum of frame retries value @@ -364,6 +362,7 @@ enum nl802154_cca_opts { NL802154_CCA_OPT_ENERGY_CARRIER_AND, NL802154_CCA_OPT_ENERGY_CARRIER_OR, + /* private: */ /* keep last */ __NL802154_CCA_OPT_ATTR_AFTER_LAST, NL802154_CCA_OPT_ATTR_MAX = __NL802154_CCA_OPT_ATTR_AFTER_LAST - 1 diff --git a/include/net/ping.h b/include/net/ping.h index 9634b8800814d..05bfd594a64c0 100644 --- a/include/net/ping.h +++ b/include/net/ping.h @@ -58,7 +58,7 @@ void ping_unhash(struct sock *sk); int ping_init_sock(struct sock *sk); void ping_close(struct sock *sk, long timeout); -int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); void ping_err(struct sk_buff *skb, int offset, u32 info); int ping_getfrag(void *from, char *to, int offset, int fraglen, int odd, struct sk_buff *); diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 8a75c73fc5558..4678db45832a1 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -25,11 +25,6 @@ struct qdisc_walker { const struct Qdisc * : (const void *)&q->privdata, \ struct Qdisc * : (void *)&q->privdata) -static inline struct Qdisc *qdisc_from_priv(void *priv) -{ - return container_of(priv, struct Qdisc, privdata); -} - /* Timer resolution MUST BE < 10% of min_schedulable_packet_size/bandwidth @@ -48,7 +43,6 @@ static inline struct Qdisc *qdisc_from_priv(void *priv) */ typedef u64 psched_time_t; -typedef long psched_tdiff_t; /* Avoid doing 64 bit divide */ #define PSCHED_SHIFT 6 diff --git a/include/net/proto_memory.h b/include/net/proto_memory.h index 8e91a8fa31b52..ad6d703ce6fe1 100644 --- a/include/net/proto_memory.h +++ b/include/net/proto_memory.h @@ -35,6 +35,9 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) mem_cgroup_sk_under_memory_pressure(sk)) return true; + if (sk->sk_bypass_prot_mem) + return false; + return !!READ_ONCE(*sk->sk_prot->memory_pressure); } diff --git a/include/net/psp/types.h b/include/net/psp/types.h index 31cee64b7c86a..25a9096d4e7da 100644 --- a/include/net/psp/types.h +++ b/include/net/psp/types.h @@ -59,6 +59,10 @@ struct psp_dev_config { * device key * @stale_assocs: associations which use a rotated out key * + * @stats: statistics maintained by the core + * @stats.rotations: See stats attr key-rotations + * @stats.stales: See stats attr stale-events + * * @rcu: RCU head for freeing the structure */ struct psp_dev { @@ -81,6 +85,11 @@ struct psp_dev { struct list_head prev_assocs; struct list_head stale_assocs; + struct { + unsigned long rotations; + unsigned long stales; + } stats; + struct rcu_head rcu; }; @@ -141,6 +150,22 @@ struct psp_assoc { u8 drv_data[] __aligned(8); }; +struct psp_dev_stats { + union { + struct { + u64 rx_packets; + u64 rx_bytes; + u64 rx_auth_fail; + u64 rx_error; + u64 rx_bad; + u64 tx_packets; + u64 tx_bytes; + u64 tx_error; + }; + DECLARE_FLEX_ARRAY(u64, required); + }; +}; + /** * struct psp_dev_ops - netdev driver facing PSP callbacks */ @@ -179,6 +204,13 @@ struct psp_dev_ops { * Remove an association from the device. */ void (*tx_key_del)(struct psp_dev *psd, struct psp_assoc *pas); + + /** + * @get_stats: get statistics from the device + * Stats required by the spec must be maintained and filled in. + * Stats must be filled in member-by-member, never memset the struct. + */ + void (*get_stats)(struct psp_dev *psd, struct psp_dev_stats *stats); }; #endif /* __NET_PSP_H */ diff --git a/include/net/request_sock.h b/include/net/request_sock.h index cd4d4cf71d0d2..9b9e04f6bb893 100644 --- a/include/net/request_sock.h +++ b/include/net/request_sock.h @@ -36,7 +36,6 @@ struct request_sock_ops { struct sk_buff *skb, enum sk_rst_reason reason); void (*destructor)(struct request_sock *req); - void (*syn_ack_timeout)(const struct request_sock *req); }; struct saved_syn { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 738cd5b13c62f..94966692ccdf5 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -41,13 +41,6 @@ enum qdisc_state_t { __QDISC_STATE_DRAINING, }; -enum qdisc_state2_t { - /* Only for !TCQ_F_NOLOCK qdisc. Never access it directly. - * Use qdisc_run_begin/end() or qdisc_is_running() instead. - */ - __QDISC_STATE2_RUNNING, -}; - #define QDISC_STATE_MISSED BIT(__QDISC_STATE_MISSED) #define QDISC_STATE_DRAINING BIT(__QDISC_STATE_DRAINING) @@ -117,13 +110,14 @@ struct Qdisc { struct qdisc_skb_head q; struct gnet_stats_basic_sync bstats; struct gnet_stats_queue qstats; - int owner; + bool running; /* must be written under qdisc spinlock */ unsigned long state; - unsigned long state2; /* must be written under qdisc spinlock */ struct Qdisc *next_sched; struct sk_buff_head skb_bad_txq; - spinlock_t busylock ____cacheline_aligned_in_smp; + atomic_long_t defer_count ____cacheline_aligned_in_smp; + struct llist_head defer_list; + spinlock_t seqlock; struct rcu_head rcu; @@ -168,7 +162,7 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_NOLOCK) return spin_is_locked(&qdisc->seqlock); - return test_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); + return READ_ONCE(qdisc->running); } static inline bool nolock_qdisc_is_empty(const struct Qdisc *qdisc) @@ -211,7 +205,10 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc) */ return spin_trylock(&qdisc->seqlock); } - return !__test_and_set_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); + if (READ_ONCE(qdisc->running)) + return false; + WRITE_ONCE(qdisc->running, true); + return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) @@ -229,7 +226,7 @@ static inline void qdisc_run_end(struct Qdisc *qdisc) &qdisc->state))) __netif_schedule(qdisc); } else { - __clear_bit(__QDISC_STATE2_RUNNING, &qdisc->state2); + WRITE_ONCE(qdisc->running, false); } } diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index 3d5879e08e78a..6f2cd562b1de6 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -72,7 +72,6 @@ struct sctp_shared_key *sctp_auth_get_shkey( int sctp_auth_asoc_copy_shkeys(const struct sctp_endpoint *ep, struct sctp_association *asoc, gfp_t gfp); -int sctp_auth_init_hmacs(struct sctp_endpoint *ep, gfp_t gfp); const struct sctp_hmac *sctp_auth_get_hmac(__u16 hmac_id); const struct sctp_hmac * sctp_auth_asoc_get_hmac(const struct sctp_association *asoc); diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index e96d1bd087f62..58242b37b47a1 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -85,7 +85,7 @@ void sctp_udp_sock_stop(struct net *net); /* * sctp/socket.c */ -int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, +int sctp_inet_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags); int sctp_backlog_rcv(struct sock *sk, struct sk_buff *skb); int sctp_inet_listen(struct socket *sock, int backlog); @@ -94,8 +94,7 @@ void sctp_data_ready(struct sock *sk); __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait); void sctp_sock_rfree(struct sk_buff *skb); -void sctp_copy_sock(struct sock *newsk, struct sock *sk, - struct sctp_association *asoc); + extern struct percpu_counter sctp_sockets_allocated; int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int *); diff --git a/include/net/sctp/stream_sched.h b/include/net/sctp/stream_sched.h index 8034bf5febbe8..77806ef1cb70c 100644 --- a/include/net/sctp/stream_sched.h +++ b/include/net/sctp/stream_sched.h @@ -52,10 +52,10 @@ void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch); void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch); int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp); -struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream); +const struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream); void sctp_sched_ops_register(enum sctp_sched_type sched, - struct sctp_sched_ops *sched_ops); + const struct sctp_sched_ops *sched_ops); void sctp_sched_ops_prio_init(void); void sctp_sched_ops_rr_init(void); void sctp_sched_ops_fc_init(void); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 2ae390219efdd..affee44bd38e3 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -228,10 +228,6 @@ struct sctp_sock { atomic_t pd_mode; - /* Fields after this point will be skipped on copies, like on accept - * and peeloff operations - */ - /* Receive to here while partial delivery is in effect. */ struct sk_buff_head pd_lobby; @@ -497,9 +493,6 @@ struct sctp_pf { int (*bind_verify) (struct sctp_sock *, union sctp_addr *); int (*send_verify) (struct sctp_sock *, union sctp_addr *); int (*supported_addrs)(const struct sctp_sock *, __be16 *); - struct sock *(*create_accept_sk) (struct sock *sk, - struct sctp_association *asoc, - bool kern); int (*addr_to_user)(struct sctp_sock *sk, union sctp_addr *addr); void (*to_sk_saddr)(union sctp_addr *, struct sock *sk); void (*to_sk_daddr)(union sctp_addr *, struct sock *sk); @@ -1076,7 +1069,7 @@ struct sctp_outq { struct list_head out_chunk_list; /* Stream scheduler being used */ - struct sctp_sched_ops *sched; + const struct sctp_sched_ops *sched; unsigned int out_qlen; /* Total length of queued data chunks. */ diff --git a/include/net/selftests.h b/include/net/selftests.h index e65e8d230d33c..c36e07406ad4c 100644 --- a/include/net/selftests.h +++ b/include/net/selftests.h @@ -3,9 +3,48 @@ #define _NET_SELFTESTS #include +#include + +struct net_packet_attrs { + const unsigned char *src; + const unsigned char *dst; + u32 ip_src; + u32 ip_dst; + bool tcp; + u16 sport; + u16 dport; + int timeout; + int size; + int max_size; + u8 id; + u16 queue_mapping; + bool bad_csum; +}; + +struct net_test_priv { + struct net_packet_attrs *packet; + struct packet_type pt; + struct completion comp; + int double_vlan; + int vlan_id; + int ok; +}; + +struct netsfhdr { + __be32 version; + __be64 magic; + u8 id; +} __packed; + +#define NET_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ + sizeof(struct netsfhdr)) +#define NET_TEST_PKT_MAGIC 0xdeadcafecafedeadULL +#define NET_LB_TIMEOUT msecs_to_jiffies(200) #if IS_ENABLED(CONFIG_NET_SELFTESTS) +struct sk_buff *net_test_get_skb(struct net_device *ndev, u8 id, + struct net_packet_attrs *attr); void net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf); int net_selftest_get_count(void); @@ -13,6 +52,12 @@ void net_selftest_get_strings(u8 *data); #else +static inline struct sk_buff *net_test_get_skb(struct net_device *ndev, u8 id, + struct net_packet_attrs *attr) +{ + return NULL; +} + static inline void net_selftest(struct net_device *ndev, struct ethtool_test *etest, u64 *buf) { diff --git a/include/net/smc.h b/include/net/smc.h index 08bee529ed8d4..bfdc4c41f0198 100644 --- a/include/net/smc.h +++ b/include/net/smc.h @@ -17,6 +17,8 @@ #include #include +struct tcp_sock; +struct inet_request_sock; struct sock; #define SMC_MAX_PNETID_LEN 16 /* Max. length of PNET id */ @@ -50,4 +52,55 @@ struct smcd_dev { u8 going_away : 1; }; +#define SMC_HS_CTRL_NAME_MAX 16 + +enum { + /* ops can be inherit from init_net */ + SMC_HS_CTRL_FLAG_INHERITABLE = 0x1, + + SMC_HS_CTRL_ALL_FLAGS = SMC_HS_CTRL_FLAG_INHERITABLE, +}; + +struct smc_hs_ctrl { + /* private */ + + struct list_head list; + struct module *owner; + + /* public */ + + /* unique name */ + char name[SMC_HS_CTRL_NAME_MAX]; + int flags; + + /* Invoked before computing SMC option for SYN packets. + * We can control whether to set SMC options by returning various value. + * Return 0 to disable SMC, or return any other value to enable it. + */ + int (*syn_option)(struct tcp_sock *tp); + + /* Invoked before Set up SMC options for SYN-ACK packets + * We can control whether to respond SMC options by returning various + * value. Return 0 to disable SMC, or return any other value to enable + * it. + */ + int (*synack_option)(const struct tcp_sock *tp, + struct inet_request_sock *ireq); +}; + +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) +#define smc_call_hsbpf(init_val, tp, func, ...) ({ \ + typeof(init_val) __ret = (init_val); \ + struct smc_hs_ctrl *ctrl; \ + rcu_read_lock(); \ + ctrl = rcu_dereference(sock_net((struct sock *)(tp))->smc.hs_ctrl); \ + if (ctrl && ctrl->func) \ + __ret = ctrl->func(tp, ##__VA_ARGS__); \ + rcu_read_unlock(); \ + __ret; \ +}) +#else +#define smc_call_hsbpf(init_val, tp, ...) ({ (void)(tp); (init_val); }) +#endif /* CONFIG_SMC_HS_CTRL_BPF */ + #endif /* _SMC_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 60bcb13f045c3..a5f36ea9d46f0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -118,6 +118,7 @@ typedef __u64 __bitwise __addrpair; * @skc_reuseport: %SO_REUSEPORT setting * @skc_ipv6only: socket is IPV6 only * @skc_net_refcnt: socket is using net ref counting + * @skc_bypass_prot_mem: bypass the per-protocol memory accounting for skb * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol @@ -174,6 +175,7 @@ struct sock_common { unsigned char skc_reuseport:1; unsigned char skc_ipv6only:1; unsigned char skc_net_refcnt:1; + unsigned char skc_bypass_prot_mem:1; int skc_bound_dev_if; union { struct hlist_node skc_bind_node; @@ -313,6 +315,7 @@ struct sk_filter; * @sk_bind_phc: SO_TIMESTAMPING bind PHC index of PTP virtual clock * for timestamping * @sk_tskey: counter to disambiguate concurrent tstamp requests + * @sk_tx_queue_mapping_jiffies: time in jiffies of last @sk_tx_queue_mapping refresh. * @sk_zckey: counter to order MSG_ZEROCOPY notifications * @sk_socket: Identd and reporting IO signals * @sk_user_data: RPC layer private data. Write-protected by @sk_callback_lock. @@ -380,6 +383,7 @@ struct sock { #define sk_reuseport __sk_common.skc_reuseport #define sk_ipv6only __sk_common.skc_ipv6only #define sk_net_refcnt __sk_common.skc_net_refcnt +#define sk_bypass_prot_mem __sk_common.skc_bypass_prot_mem #define sk_bound_dev_if __sk_common.skc_bound_dev_if #define sk_bind_node __sk_common.skc_bind_node #define sk_prot __sk_common.skc_prot @@ -485,6 +489,7 @@ struct sock { unsigned long sk_pacing_rate; /* bytes per second */ atomic_t sk_zckey; atomic_t sk_tskey; + unsigned long sk_tx_queue_mapping_jiffies; __cacheline_group_end(sock_write_tx); __cacheline_group_begin(sock_read_tx); @@ -828,11 +833,9 @@ static inline bool sk_del_node_init(struct sock *sk) { bool rc = __sk_del_node_init(sk); - if (rc) { - /* paranoid for a while -acme */ - WARN_ON(refcount_read(&sk->sk_refcnt) == 1); + if (rc) __sock_put(sk); - } + return rc; } #define sk_del_node_init_rcu(sk) sk_del_node_init(sk) @@ -850,14 +853,25 @@ static inline bool sk_nulls_del_node_init_rcu(struct sock *sk) { bool rc = __sk_nulls_del_node_init_rcu(sk); - if (rc) { - /* paranoid for a while -acme */ - WARN_ON(refcount_read(&sk->sk_refcnt) == 1); + if (rc) __sock_put(sk); - } + return rc; } +static inline bool sk_nulls_replace_node_init_rcu(struct sock *old, + struct sock *new) +{ + if (sk_hashed(old)) { + hlist_nulls_replace_init_rcu(&old->sk_nulls_node, + &new->sk_nulls_node); + __sock_put(old); + return true; + } + + return false; +} + static inline void __sk_add_node(struct sock *sk, struct hlist_head *list) { hlist_add_head(&sk->sk_node, list); @@ -1260,10 +1274,10 @@ struct proto { void (*close)(struct sock *sk, long timeout); int (*pre_connect)(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, int addr_len); int (*connect)(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, int addr_len); int (*disconnect)(struct sock *sk, int flags); @@ -1292,9 +1306,9 @@ struct proto { size_t len, int flags, int *addr_len); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, - struct sockaddr *addr, int addr_len); + struct sockaddr_unsized *addr, int addr_len); int (*bind_add)(struct sock *sk, - struct sockaddr *addr, int addr_len); + struct sockaddr_unsized *addr, int addr_len); int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); @@ -1808,7 +1822,12 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, void sk_free(struct sock *sk); void sk_net_refcnt_upgrade(struct sock *sk); void sk_destruct(struct sock *sk); -struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority); +struct sock *sk_clone(const struct sock *sk, const gfp_t priority, bool lock); + +static inline struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) +{ + return sk_clone(sk, priority, true); +} struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); @@ -1901,8 +1920,8 @@ int sock_cmsg_send(struct sock *sk, struct msghdr *msg, * Functions to fill in entries in struct proto_ops when a protocol * does not implement a particular function. */ -int sock_no_bind(struct socket *, struct sockaddr *, int); -int sock_no_connect(struct socket *, struct sockaddr *, int, int); +int sock_no_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len); +int sock_no_connect(struct socket *sock, struct sockaddr_unsized *saddr, int len, int flags); int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, struct proto_accept_arg *); int sock_no_getname(struct socket *, struct sockaddr *, int); @@ -1992,7 +2011,15 @@ static inline void sk_tx_queue_set(struct sock *sk, int tx_queue) /* Paired with READ_ONCE() in sk_tx_queue_get() and * other WRITE_ONCE() because socket lock might be not held. */ - WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); + if (READ_ONCE(sk->sk_tx_queue_mapping) != tx_queue) { + WRITE_ONCE(sk->sk_tx_queue_mapping, tx_queue); + WRITE_ONCE(sk->sk_tx_queue_mapping_jiffies, jiffies); + return; + } + + /* Refresh sk_tx_queue_mapping_jiffies if too old. */ + if (time_is_before_jiffies(READ_ONCE(sk->sk_tx_queue_mapping_jiffies) + HZ)) + WRITE_ONCE(sk->sk_tx_queue_mapping_jiffies, jiffies); } #define NO_QUEUE_MAPPING USHRT_MAX @@ -2005,19 +2032,7 @@ static inline void sk_tx_queue_clear(struct sock *sk) WRITE_ONCE(sk->sk_tx_queue_mapping, NO_QUEUE_MAPPING); } -static inline int sk_tx_queue_get(const struct sock *sk) -{ - if (sk) { - /* Paired with WRITE_ONCE() in sk_tx_queue_clear() - * and sk_tx_queue_set(). - */ - int val = READ_ONCE(sk->sk_tx_queue_mapping); - - if (val != NO_QUEUE_MAPPING) - return val; - } - return -1; -} +int sk_tx_queue_get(const struct sock *sk); static inline void __sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb, @@ -2303,6 +2318,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro return 0; } +#define SK_WMEM_ALLOC_BIAS 1 /** * sk_wmem_alloc_get - returns write allocations * @sk: socket @@ -2311,7 +2327,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro */ static inline int sk_wmem_alloc_get(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) - 1; + return refcount_read(&sk->sk_wmem_alloc) - SK_WMEM_ALLOC_BIAS; } /** @@ -2596,12 +2612,16 @@ static inline struct page_frag *sk_page_frag(struct sock *sk) bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag); +static inline bool __sock_writeable(const struct sock *sk, int wmem_alloc) +{ + return wmem_alloc < (READ_ONCE(sk->sk_sndbuf) >> 1); +} /* * Default write policy as shown to user space via poll/select/SIGIO */ static inline bool sock_writeable(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); + return __sock_writeable(sk, refcount_read(&sk->sk_wmem_alloc)); } static inline gfp_t gfp_any(void) @@ -3085,7 +3105,7 @@ void sock_set_reuseaddr(struct sock *sk); void sock_set_reuseport(struct sock *sk); void sock_set_sndtimeo(struct sock *sk, s64 secs); -int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +int sock_bind_add(struct sock *sk, struct sockaddr_unsized *addr, int addr_len); int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, diff --git a/include/net/tcp.h b/include/net/tcp.h index ab20f549b8f91..607a4cb4984c3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -303,6 +303,9 @@ static inline bool tcp_under_memory_pressure(const struct sock *sk) mem_cgroup_sk_under_memory_pressure(sk)) return true; + if (sk->sk_bypass_prot_mem) + return false; + return READ_ONCE(tcp_memory_pressure); } /* @@ -461,6 +464,8 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child, void tcp_enter_loss(struct sock *sk); void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag); void tcp_clear_retrans(struct tcp_sock *tp); +void tcp_update_pacing_rate(struct sock *sk); +void tcp_set_rto(struct sock *sk); void tcp_update_metrics(struct sock *sk); void tcp_init_metrics(struct sock *sk); void tcp_metrics_init(void); @@ -530,12 +535,13 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req_unhash, bool *own_req); int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb); -int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int tcp_connect(struct sock *sk); enum tcp_synack_type { TCP_SYNACK_NORMAL, TCP_SYNACK_FASTOPEN, TCP_SYNACK_COOKIE, + TCP_SYNACK_RETRANS, }; struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, struct request_sock *req, @@ -836,6 +842,14 @@ static inline u32 __tcp_set_rto(const struct tcp_sock *tp) return usecs_to_jiffies((tp->srtt_us >> 3) + tp->rttvar_us); } +static inline unsigned long tcp_reqsk_timeout(struct request_sock *req) +{ + u64 timeout = (u64)req->timeout << req->num_timeout; + + return (unsigned long)min_t(u64, timeout, + tcp_rto_max(req->rsk_listener)); +} + u32 tcp_delack_max(const struct sock *sk); /* Compute the actual rto_min value */ @@ -1190,7 +1204,15 @@ enum tcp_ca_ack_event_flags { #define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ #define TCP_CONG_NEEDS_ECN BIT(1) -#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) +/* Require successfully negotiated AccECN capability */ +#define TCP_CONG_NEEDS_ACCECN BIT(2) +/* Use ECT(1) instead of ECT(0) while the CA is uninitialized */ +#define TCP_CONG_ECT_1_NEGOTIATION BIT(3) +/* Cannot fallback to RFC3168 during AccECN negotiation */ +#define TCP_CONG_NO_FALLBACK_RFC3168 BIT(4) +#define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN | \ + TCP_CONG_NEEDS_ACCECN | TCP_CONG_ECT_1_NEGOTIATION | \ + TCP_CONG_NO_FALLBACK_RFC3168) union tcp_cc_info; @@ -1322,6 +1344,27 @@ static inline bool tcp_ca_needs_ecn(const struct sock *sk) return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ECN; } +static inline bool tcp_ca_needs_accecn(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NEEDS_ACCECN; +} + +static inline bool tcp_ca_ect_1_negotiation(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_ECT_1_NEGOTIATION; +} + +static inline bool tcp_ca_no_fallback_rfc3168(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + + return icsk->icsk_ca_ops->flags & TCP_CONG_NO_FALLBACK_RFC3168; +} + static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) { const struct inet_connection_sock *icsk = inet_csk(sk); @@ -1896,13 +1939,6 @@ struct tcp6_pseudohdr { __be32 protocol; /* including padding */ }; -union tcp_md5sum_block { - struct tcp4_pseudohdr ip4; -#if IS_ENABLED(CONFIG_IPV6) - struct tcp6_pseudohdr ip6; -#endif -}; - /* * struct tcp_sigpool - per-CPU pool of ahash_requests * @scratch: per-CPU temporary area, that can be used between @@ -1937,8 +1973,8 @@ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c); void tcp_sigpool_end(struct tcp_sigpool *c); size_t tcp_sigpool_algo(unsigned int id, char *buf, size_t buf_len); /* - functions */ -int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, - const struct sock *sk, const struct sk_buff *skb); +void tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb); int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, int l3index, u8 flags, const u8 *newkey, u8 newkeylen); @@ -1997,13 +2033,10 @@ static inline void tcp_md5_destruct_sock(struct sock *sk) } #endif -int tcp_md5_alloc_sigpool(void); -void tcp_md5_release_sigpool(void); -void tcp_md5_add_sigpool(void); -extern int tcp_md5_sigpool_id; - -int tcp_md5_hash_key(struct tcp_sigpool *hp, - const struct tcp_md5sig_key *key); +struct md5_ctx; +void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb, + unsigned int header_len); +void tcp_md5_hash_key(struct md5_ctx *ctx, const struct tcp_md5sig_key *key); /* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, @@ -2310,7 +2343,6 @@ void tcp_v4_destroy_sock(struct sock *sk); struct sk_buff *tcp_gso_segment(struct sk_buff *skb, netdev_features_t features); -struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb); struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th); struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th); @@ -2353,7 +2385,7 @@ struct tcp_sock_af_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*md5_lookup) (const struct sock *sk, const struct sock *addr_sk); - int (*calc_md5_hash)(char *location, + void (*calc_md5_hash)(char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); @@ -2381,7 +2413,7 @@ struct tcp_request_sock_ops { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *(*req_md5_lookup)(const struct sock *sk, const struct sock *addr_sk); - int (*calc_md5_hash) (char *location, + void (*calc_md5_hash) (char *location, const struct tcp_md5sig_key *md5, const struct sock *sk, const struct sk_buff *skb); diff --git a/include/net/tcp_ecn.h b/include/net/tcp_ecn.h index f13e5cd2b1ac3..c15891711f77b 100644 --- a/include/net/tcp_ecn.h +++ b/include/net/tcp_ecn.h @@ -29,8 +29,15 @@ enum tcp_accecn_option { TCP_ACCECN_OPTION_DISABLED = 0, TCP_ACCECN_OPTION_MINIMUM = 1, TCP_ACCECN_OPTION_FULL = 2, + TCP_ACCECN_OPTION_PERSIST = 3, }; +/* Apply either ECT(0) or ECT(1) based on TCP_CONG_ECT_1_NEGOTIATION flag */ +static inline void INET_ECN_xmit_ect_1_negotiation(struct sock *sk) +{ + __INET_ECN_xmit(sk, tcp_ca_ect_1_negotiation(sk)); +} + static inline void tcp_ecn_queue_cwr(struct tcp_sock *tp) { /* Do not set CWR if in AccECN mode! */ @@ -169,7 +176,9 @@ static inline void tcp_accecn_third_ack(struct sock *sk, switch (ace) { case 0x0: /* Invalid value */ - tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV); + if (!TCP_SKB_CB(skb)->sacked) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_ACE_FAIL_RECV | + TCP_ACCECN_OPT_FAIL_RECV); break; case 0x7: case 0x5: @@ -398,6 +407,7 @@ static inline void tcp_accecn_init_counters(struct tcp_sock *tp) tp->received_ce_pending = 0; __tcp_accecn_init_bytes_counters(tp->received_ecn_bytes); __tcp_accecn_init_bytes_counters(tp->delivered_ecn_bytes); + tp->accecn_opt_sent = 0; tp->accecn_minlen = 0; tp->accecn_opt_demand = 0; tp->est_ecnfield = 0; @@ -467,6 +477,26 @@ static inline u8 tcp_accecn_option_init(const struct sk_buff *skb, return TCP_ACCECN_OPT_COUNTER_SEEN; } +static inline void tcp_ecn_rcv_synack_accecn(struct sock *sk, + const struct sk_buff *skb, u8 dsf) +{ + struct tcp_sock *tp = tcp_sk(sk); + + tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); + tp->syn_ect_rcv = dsf & INET_ECN_MASK; + /* Demand Accurate ECN option in response to the SYN on the SYN/ACK + * and the TCP server will try to send one more packet with an AccECN + * Option at a later point during the connection. + */ + if (tp->rx_opt.accecn && + tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { + u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); + + tcp_accecn_saw_opt_fail_recv(tp, saw_opt); + tp->accecn_opt_demand = 2; + } +} + /* See Table 2 of the AccECN draft */ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb, const struct tcphdr *th, u8 ip_dsfield) @@ -489,32 +519,32 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); break; case 0x1: - case 0x5: /* +========+========+============+=============+ * | A | B | SYN/ACK | Feedback | * | | | B->A | Mode of A | * | | | AE CWR ECE | | * +========+========+============+=============+ - * | AccECN | Nonce | 1 0 1 | (Reserved) | * | AccECN | ECN | 0 0 1 | Classic ECN | * | Nonce | AccECN | 0 0 1 | Classic ECN | * | ECN | AccECN | 0 0 1 | Classic ECN | * +========+========+============+=============+ */ - if (tcp_ecn_mode_pending(tp)) - /* Downgrade from AccECN, or requested initially */ + if (tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); + else tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); break; - default: - tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); - tp->syn_ect_rcv = ip_dsfield & INET_ECN_MASK; - if (tp->rx_opt.accecn && - tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { - u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); - - tcp_accecn_saw_opt_fail_recv(tp, saw_opt); - tp->accecn_opt_demand = 2; + case 0x5: + if (tcp_ecn_mode_pending(tp)) { + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); + if (INET_ECN_is_ce(ip_dsfield)) { + tp->received_ce++; + tp->received_ce_pending++; + } } + break; + default: + tcp_ecn_rcv_synack_accecn(sk, skb, ip_dsfield); if (INET_ECN_is_ce(ip_dsfield) && tcp_accecn_validate_syn_feedback(sk, ace, tp->syn_ect_snt)) { @@ -525,9 +555,11 @@ static inline void tcp_ecn_rcv_synack(struct sock *sk, const struct sk_buff *skb } } -static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, +static inline void tcp_ecn_rcv_syn(struct sock *sk, const struct tcphdr *th, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + if (tcp_ecn_mode_pending(tp)) { if (!tcp_accecn_syn_requested(th)) { /* Downgrade to classic ECN feedback */ @@ -539,7 +571,8 @@ static inline void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th, tcp_ecn_mode_set(tp, TCP_ECN_MODE_ACCECN); } } - if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr)) + if (tcp_ecn_mode_rfc3168(tp) && + (!th->ece || !th->cwr || tcp_ca_no_fallback_rfc3168(sk))) tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } @@ -561,7 +594,7 @@ static inline void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE; else if (tcp_ca_needs_ecn(sk) || tcp_bpf_ca_needs_ecn(sk)) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); if (tp->ecn_flags & TCP_ECN_MODE_ACCECN) { TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ACE; @@ -579,7 +612,8 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) bool use_ecn, use_accecn; u8 tcp_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn); - use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN; + use_accecn = tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ACCECN || + tcp_ca_needs_accecn(sk); use_ecn = tcp_ecn == TCP_ECN_IN_ECN_OUT_ECN || tcp_ecn == TCP_ECN_IN_ACCECN_OUT_ECN || tcp_ca_needs_ecn(sk) || bpf_needs_ecn || use_accecn; @@ -595,7 +629,7 @@ static inline void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) if (use_ecn) { if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR; if (use_accecn) { @@ -619,12 +653,20 @@ static inline void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) } static inline void -tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th) -{ - if (tcp_rsk(req)->accecn_ok) - tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv); - else if (inet_rsk(req)->ecn_ok) - th->ece = 1; +tcp_ecn_make_synack(const struct request_sock *req, struct tcphdr *th, + enum tcp_synack_type synack_type) +{ + // num_retrans will be incresaed after tcp_ecn_make_synack() + if (!req->num_retrans) { + if (tcp_rsk(req)->accecn_ok) + tcp_accecn_echo_syn_ect(th, tcp_rsk(req)->syn_ect_rcv); + else if (inet_rsk(req)->ecn_ok) + th->ece = 1; + } else if (tcp_rsk(req)->accecn_ok) { + th->ae = 0; + th->cwr = 0; + th->ece = 0; + } } static inline bool tcp_accecn_option_beacon_check(const struct sock *sk) diff --git a/include/net/tls.h b/include/net/tls.h index c7bcdb3afad75..ebd2550280ae2 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -53,6 +53,8 @@ struct tls_rec; /* Maximum data size carried in a TLS record */ #define TLS_MAX_PAYLOAD_SIZE ((size_t)1 << 14) +/* Minimum record size limit as per RFC8449 */ +#define TLS_MIN_RECORD_SIZE_LIM ((size_t)1 << 6) #define TLS_HEADER_SIZE 5 #define TLS_NONCE_OFFSET TLS_HEADER_SIZE @@ -226,6 +228,7 @@ struct tls_context { u8 rx_conf:3; u8 zerocopy_sendfile:1; u8 rx_no_pad:1; + u16 tx_max_payload_len; int (*push_pending_record)(struct sock *sk, int flags); void (*sk_write_space)(struct sock *sk); diff --git a/include/net/udp.h b/include/net/udp.h index cffedb3e40f24..a061d1b22ddc2 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -424,7 +424,7 @@ void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); int udp_ioctl(struct sock *sk, int cmd, int *karg); int udp_init_sock(struct sock *sk); -int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); +int udp_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len); int __udp_disconnect(struct sock *sk, int flags); int udp_disconnect(struct sock *sk, int flags); __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait); diff --git a/include/net/vsock_addr.h b/include/net/vsock_addr.h index cf8cc140d68db..c3f4cc206198f 100644 --- a/include/net/vsock_addr.h +++ b/include/net/vsock_addr.h @@ -16,7 +16,7 @@ bool vsock_addr_bound(const struct sockaddr_vm *addr); void vsock_addr_unbind(struct sockaddr_vm *addr); bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, const struct sockaddr_vm *other); -int vsock_addr_cast(const struct sockaddr *addr, size_t len, +int vsock_addr_cast(const struct sockaddr_unsized *addr, size_t len, struct sockaddr_vm **out_addr); #endif diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ce587a2256618..23e8861e8b25e 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -125,6 +125,7 @@ struct xsk_tx_metadata_ops { int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp); void __xsk_map_flush(struct list_head *flush_list); +INDIRECT_CALLABLE_DECLARE(void xsk_destruct_skb(struct sk_buff *)); /** * xsk_tx_metadata_to_compl - Save enough relevant metadata information @@ -218,6 +219,12 @@ static inline void __xsk_map_flush(struct list_head *flush_list) { } +#ifdef CONFIG_MITIGATION_RETPOLINE +static inline void xsk_destruct_skb(struct sk_buff *skb) +{ +} +#endif + static inline void xsk_tx_metadata_to_compl(struct xsk_tx_metadata *meta, struct xsk_tx_metadata_compl *compl) { diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 4f2d3268a6769..242e34f771cca 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -12,6 +12,10 @@ #define XDP_UMEM_MIN_CHUNK_SHIFT 11 #define XDP_UMEM_MIN_CHUNK_SIZE (1 << XDP_UMEM_MIN_CHUNK_SHIFT) +#define NETDEV_XDP_ACT_XSK (NETDEV_XDP_ACT_BASIC | \ + NETDEV_XDP_ACT_REDIRECT | \ + NETDEV_XDP_ACT_XSK_ZEROCOPY) + struct xsk_cb_desc { void *src; u8 off; diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h index cac56e6b0869b..92a2358c6ce34 100644 --- a/include/net/xsk_buff_pool.h +++ b/include/net/xsk_buff_pool.h @@ -85,11 +85,16 @@ struct xsk_buff_pool { bool unaligned; bool tx_sw_csum; void *addrs; - /* Mutual exclusion of the completion ring in the SKB mode. Two cases to protect: - * NAPI TX thread and sendmsg error paths in the SKB destructor callback and when - * sockets share a single cq when the same netdev and queue id is shared. + /* Mutual exclusion of the completion ring in the SKB mode. + * Protect: NAPI TX thread and sendmsg error paths in the SKB + * destructor callback. */ - spinlock_t cq_lock; + spinlock_t cq_prod_lock; + /* Mutual exclusion of the completion ring in the SKB mode. + * Protect: when sockets share a single cq when the same netdev + * and queue id is shared. + */ + spinlock_t cq_cached_prod_lock; struct xdp_buff_xsk *free_heads[]; }; diff --git a/include/trace/events/net.h b/include/trace/events/net.h index d55162c12f90a..fdd9ad474ce3a 100644 --- a/include/trace/events/net.h +++ b/include/trace/events/net.h @@ -35,6 +35,7 @@ TRACE_EVENT(net_dev_start_xmit, __field( u16, gso_size ) __field( u16, gso_segs ) __field( u16, gso_type ) + __field( u64, net_cookie ) ), TP_fast_assign( @@ -57,16 +58,18 @@ TRACE_EVENT(net_dev_start_xmit, __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_segs = skb_shinfo(skb)->gso_segs; __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->net_cookie = dev_net(dev)->net_cookie; ), - TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x", + TP_printk("dev=%s queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d len=%u data_len=%u network_offset=%d transport_offset_valid=%d transport_offset=%d tx_flags=%d gso_size=%d gso_segs=%d gso_type=%#x net_cookie=%llu", __get_str(name), __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->len, __entry->data_len, __entry->network_offset, __entry->transport_offset_valid, __entry->transport_offset, __entry->tx_flags, - __entry->gso_size, __entry->gso_segs, __entry->gso_type) + __entry->gso_size, __entry->gso_segs, + __entry->gso_type, __entry->net_cookie) ); TRACE_EVENT(net_dev_xmit, @@ -83,17 +86,21 @@ TRACE_EVENT(net_dev_xmit, __field( unsigned int, len ) __field( int, rc ) __string( name, dev->name ) + __field( u64, net_cookie ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb_len; __entry->rc = rc; + __entry->net_cookie = dev_net(dev)->net_cookie; __assign_str(name); ), - TP_printk("dev=%s skbaddr=%p len=%u rc=%d", - __get_str(name), __entry->skbaddr, __entry->len, __entry->rc) + TP_printk("dev=%s skbaddr=%p len=%u rc=%d net_cookie=%llu", + __get_str(name), __entry->skbaddr, + __entry->len, __entry->rc, + __entry->net_cookie) ); TRACE_EVENT(net_dev_xmit_timeout, @@ -107,16 +114,19 @@ TRACE_EVENT(net_dev_xmit_timeout, __string( name, dev->name ) __string( driver, netdev_drivername(dev)) __field( int, queue_index ) + __field( u64, net_cookie ) ), TP_fast_assign( __assign_str(name); __assign_str(driver); __entry->queue_index = queue_index; + __entry->net_cookie = dev_net(dev)->net_cookie; ), - TP_printk("dev=%s driver=%s queue=%d", - __get_str(name), __get_str(driver), __entry->queue_index) + TP_printk("dev=%s driver=%s queue=%d net_cookie=%llu", + __get_str(name), __get_str(driver), + __entry->queue_index, __entry->net_cookie) ); DECLARE_EVENT_CLASS(net_dev_template, @@ -129,16 +139,20 @@ DECLARE_EVENT_CLASS(net_dev_template, __field( void *, skbaddr ) __field( unsigned int, len ) __string( name, skb->dev->name ) + __field( u64, net_cookie ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = skb->len; + __entry->net_cookie = dev_net(skb->dev)->net_cookie; __assign_str(name); ), - TP_printk("dev=%s skbaddr=%p len=%u", - __get_str(name), __entry->skbaddr, __entry->len) + TP_printk("dev=%s skbaddr=%p len=%u net_cookie=%llu", + __get_str(name), __entry->skbaddr, + __entry->len, + __entry->net_cookie) ) DEFINE_EVENT(net_dev_template, net_dev_queue, @@ -188,6 +202,7 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, __field( unsigned char, nr_frags ) __field( u16, gso_size ) __field( u16, gso_type ) + __field( u64, net_cookie ) ), TP_fast_assign( @@ -214,16 +229,18 @@ DECLARE_EVENT_CLASS(net_dev_rx_verbose_template, __entry->nr_frags = skb_shinfo(skb)->nr_frags; __entry->gso_size = skb_shinfo(skb)->gso_size; __entry->gso_type = skb_shinfo(skb)->gso_type; + __entry->net_cookie = dev_net(skb->dev)->net_cookie; ), - TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x", + TP_printk("dev=%s napi_id=%#x queue_mapping=%u skbaddr=%p vlan_tagged=%d vlan_proto=0x%04x vlan_tci=0x%04x protocol=0x%04x ip_summed=%d hash=0x%08x l4_hash=%d len=%u data_len=%u truesize=%u mac_header_valid=%d mac_header=%d nr_frags=%d gso_size=%d gso_type=%#x net_cookie=%llu", __get_str(name), __entry->napi_id, __entry->queue_mapping, __entry->skbaddr, __entry->vlan_tagged, __entry->vlan_proto, __entry->vlan_tci, __entry->protocol, __entry->ip_summed, __entry->hash, __entry->l4_hash, __entry->len, __entry->data_len, __entry->truesize, __entry->mac_header_valid, __entry->mac_header, - __entry->nr_frags, __entry->gso_size, __entry->gso_type) + __entry->nr_frags, __entry->gso_size, + __entry->gso_type, __entry->net_cookie) ); DEFINE_EVENT(net_dev_rx_verbose_template, napi_gro_frags_entry, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f5713f59ac10a..f8d8513eda27b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -7205,6 +7205,8 @@ enum { TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ + SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ + }; enum { diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index bcad11a787a55..157f11d3fb72f 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -181,6 +181,7 @@ enum devlink_sb_threshold_type { enum devlink_eswitch_mode { DEVLINK_ESWITCH_MODE_LEGACY, DEVLINK_ESWITCH_MODE_SWITCHDEV, + DEVLINK_ESWITCH_MODE_SWITCHDEV_INACTIVE, }; enum devlink_eswitch_inline_mode { diff --git a/include/uapi/linux/dpll.h b/include/uapi/linux/dpll.h index ab1725a954d74..69d35570ac4f1 100644 --- a/include/uapi/linux/dpll.h +++ b/include/uapi/linux/dpll.h @@ -251,6 +251,7 @@ enum dpll_a_pin { DPLL_A_PIN_ESYNC_FREQUENCY_SUPPORTED, DPLL_A_PIN_ESYNC_PULSE, DPLL_A_PIN_REFERENCE_SYNC, + DPLL_A_PIN_PHASE_ADJUST_GRAN, __DPLL_A_PIN_MAX, DPLL_A_PIN_MAX = (__DPLL_A_PIN_MAX - 1) diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 8bd5ea5469d98..6ed235053aedf 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -2587,4 +2587,24 @@ enum phy_upstream { PHY_UPSTREAM_PHY, }; +enum ethtool_link_medium { + ETHTOOL_LINK_MEDIUM_BASET = 0, + ETHTOOL_LINK_MEDIUM_BASEK, + ETHTOOL_LINK_MEDIUM_BASES, + ETHTOOL_LINK_MEDIUM_BASEC, + ETHTOOL_LINK_MEDIUM_BASEL, + ETHTOOL_LINK_MEDIUM_BASED, + ETHTOOL_LINK_MEDIUM_BASEE, + ETHTOOL_LINK_MEDIUM_BASEF, + ETHTOOL_LINK_MEDIUM_BASEV, + ETHTOOL_LINK_MEDIUM_BASEMLD, + ETHTOOL_LINK_MEDIUM_NONE, + + __ETHTOOL_LINK_MEDIUM_LAST, +}; + +#define ETHTOOL_MEDIUM_FIBER_BITS (BIT(ETHTOOL_LINK_MEDIUM_BASES) | \ + BIT(ETHTOOL_LINK_MEDIUM_BASEL) | \ + BIT(ETHTOOL_LINK_MEDIUM_BASEF)) + #endif /* _UAPI_LINUX_ETHTOOL_H */ diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h index 0e8ac0d974e20..b71b175df46df 100644 --- a/include/uapi/linux/ethtool_netlink_generated.h +++ b/include/uapi/linux/ethtool_netlink_generated.h @@ -803,6 +803,39 @@ enum { ETHTOOL_A_PSE_NTF_MAX = (__ETHTOOL_A_PSE_NTF_CNT - 1) }; +enum { + ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE = 1, + ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE, + ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS, + ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS, + + __ETHTOOL_A_MSE_CAPABILITIES_CNT, + ETHTOOL_A_MSE_CAPABILITIES_MAX = (__ETHTOOL_A_MSE_CAPABILITIES_CNT - 1) +}; + +enum { + ETHTOOL_A_MSE_SNAPSHOT_AVERAGE_MSE = 1, + ETHTOOL_A_MSE_SNAPSHOT_PEAK_MSE, + ETHTOOL_A_MSE_SNAPSHOT_WORST_PEAK_MSE, + + __ETHTOOL_A_MSE_SNAPSHOT_CNT, + ETHTOOL_A_MSE_SNAPSHOT_MAX = (__ETHTOOL_A_MSE_SNAPSHOT_CNT - 1) +}; + +enum { + ETHTOOL_A_MSE_HEADER = 1, + ETHTOOL_A_MSE_CAPABILITIES, + ETHTOOL_A_MSE_CHANNEL_A, + ETHTOOL_A_MSE_CHANNEL_B, + ETHTOOL_A_MSE_CHANNEL_C, + ETHTOOL_A_MSE_CHANNEL_D, + ETHTOOL_A_MSE_WORST_CHANNEL, + ETHTOOL_A_MSE_LINK, + + __ETHTOOL_A_MSE_CNT, + ETHTOOL_A_MSE_MAX = (__ETHTOOL_A_MSE_CNT - 1) +}; + enum { ETHTOOL_MSG_USER_NONE = 0, ETHTOOL_MSG_STRSET_GET = 1, @@ -855,6 +888,7 @@ enum { ETHTOOL_MSG_RSS_SET, ETHTOOL_MSG_RSS_CREATE_ACT, ETHTOOL_MSG_RSS_DELETE_ACT, + ETHTOOL_MSG_MSE_GET, __ETHTOOL_MSG_USER_CNT, ETHTOOL_MSG_USER_MAX = (__ETHTOOL_MSG_USER_CNT - 1) @@ -915,6 +949,7 @@ enum { ETHTOOL_MSG_RSS_CREATE_ACT_REPLY, ETHTOOL_MSG_RSS_CREATE_NTF, ETHTOOL_MSG_RSS_DELETE_NTF, + ETHTOOL_MSG_MSE_GET_REPLY, __ETHTOOL_MSG_KERNEL_CNT, ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1) diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 69e0457eb2000..df9d44a115403 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -92,6 +92,9 @@ #define ETH_P_ETHERCAT 0x88A4 /* EtherCAT */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ +#define ETH_P_MXLGSW 0x88C3 /* Infineon Technologies Corporate Research ST + * Used by MaxLinear GSW DSA + */ #define ETH_P_PREAUTH 0x88C7 /* 802.11 Preauthentication */ #define ETH_P_TIPC 0x88CA /* TIPC */ #define ETH_P_LLDP 0x88CC /* Link Layer Discovery Protocol */ @@ -114,6 +117,7 @@ #define ETH_P_QINQ1 0x9100 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ2 0x9200 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_QINQ3 0x9300 /* deprecated QinQ VLAN [ NOT AN OFFICIALLY REGISTERED ID ] */ +#define ETH_P_YT921X 0x9988 /* Motorcomm YT921x DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_EDSA 0xDADA /* Ethertype DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_DSA_8021Q 0xDADB /* Fake VLAN Header for DSA [ NOT AN OFFICIALLY REGISTERED ID ] */ #define ETH_P_DSA_A5PSW 0xE001 /* A5PSW Tag Value [ NOT AN OFFICIALLY REGISTERED ID ] */ diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index 6975f182b22c6..7b6b51a4ff29b 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -116,10 +116,27 @@ #define MDIO_CTRL1_SPEED10G (MDIO_CTRL1_SPEEDSELEXT | 0x00) /* 10PASS-TS/2BASE-TL */ #define MDIO_CTRL1_SPEED10P2B (MDIO_CTRL1_SPEEDSELEXT | 0x04) +/* Note: the MDIO_CTRL1_SPEED_XXX values for everything past 10PASS-TS/2BASE-TL + * do not match between the PCS and PMA values. Any additions past this point + * should be PMA or PCS specific. The following 2 defines are workarounds for + * values added before this was caught. They should be considered deprecated. + */ +#define MDIO_CTRL1_SPEED2_5G MDIO_PMA_CTRL1_SPEED2_5G +#define MDIO_CTRL1_SPEED5G MDIO_PMA_CTRL1_SPEED5G +/* 100 Gb/s */ +#define MDIO_PMA_CTRL1_SPEED100G (MDIO_CTRL1_SPEEDSELEXT | 0x0c) +#define MDIO_PCS_CTRL1_SPEED100G (MDIO_CTRL1_SPEEDSELEXT | 0x10) +/* 25 Gb/s */ +#define MDIO_PMA_CTRL1_SPEED25G (MDIO_CTRL1_SPEEDSELEXT | 0x10) +#define MDIO_PCS_CTRL1_SPEED25G (MDIO_CTRL1_SPEEDSELEXT | 0x14) +/* 50 Gb/s */ +#define MDIO_PMA_CTRL1_SPEED50G (MDIO_CTRL1_SPEEDSELEXT | 0x14) +#define MDIO_PCS_CTRL1_SPEED50G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 2.5 Gb/s */ -#define MDIO_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) +#define MDIO_PMA_CTRL1_SPEED2_5G (MDIO_CTRL1_SPEEDSELEXT | 0x18) /* 5 Gb/s */ -#define MDIO_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) +#define MDIO_PMA_CTRL1_SPEED5G (MDIO_CTRL1_SPEEDSELEXT | 0x1c) + /* Status register 1. */ #define MDIO_STAT1_LPOWERABLE 0x0002 /* Low-power ability */ @@ -133,6 +150,11 @@ #define MDIO_AN_STAT1_PAGE 0x0040 /* Page received */ #define MDIO_AN_STAT1_XNP 0x0080 /* Extended next page status */ +/* Device Identifier 2 */ +#define MDIO_DEVID2_OUI 0xfc00 /* OUI Portion of PHY ID */ +#define MDIO_DEVID2_MODEL_NUM 0x03f0 /* Manufacturer's Model Number */ +#define MDIO_DEVID2_REV_NUM 0x000f /* Revision Number */ + /* Speed register. */ #define MDIO_SPEED_10G 0x0001 /* 10G capable */ #define MDIO_PMA_SPEED_2B 0x0002 /* 2BASE-TL capable */ diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 87cfab874e241..04eea6d1d0a9b 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -70,7 +70,8 @@ struct mptcp_info { __u64 mptcpi_bytes_acked; __u8 mptcpi_subflows_total; __u8 mptcpi_endp_laminar_max; - __u8 reserved[2]; + __u8 mptcpi_endp_fullmesh_max; + __u8 reserved; __u32 mptcpi_last_data_sent; __u32 mptcpi_last_data_recv; __u32 mptcpi_last_ack_recv; diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 48eb49aa03d41..048c8de1a130d 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -80,6 +80,7 @@ enum netdev_qstats_scope { enum netdev_napi_threaded { NETDEV_NAPI_THREADED_DISABLED, NETDEV_NAPI_THREADED_ENABLED, + NETDEV_NAPI_THREADED_BUSY_POLL, }; enum { diff --git a/include/uapi/linux/psp.h b/include/uapi/linux/psp.h index 607c42c39ba55..d8449c043ba11 100644 --- a/include/uapi/linux/psp.h +++ b/include/uapi/linux/psp.h @@ -45,6 +45,23 @@ enum { PSP_A_KEYS_MAX = (__PSP_A_KEYS_MAX - 1) }; +enum { + PSP_A_STATS_DEV_ID = 1, + PSP_A_STATS_KEY_ROTATIONS, + PSP_A_STATS_STALE_EVENTS, + PSP_A_STATS_RX_PACKETS, + PSP_A_STATS_RX_BYTES, + PSP_A_STATS_RX_AUTH_FAIL, + PSP_A_STATS_RX_ERROR, + PSP_A_STATS_RX_BAD, + PSP_A_STATS_TX_PACKETS, + PSP_A_STATS_TX_BYTES, + PSP_A_STATS_TX_ERROR, + + __PSP_A_STATS_MAX, + PSP_A_STATS_MAX = (__PSP_A_STATS_MAX - 1) +}; + enum { PSP_CMD_DEV_GET = 1, PSP_CMD_DEV_ADD_NTF, @@ -55,6 +72,7 @@ enum { PSP_CMD_KEY_ROTATE_NTF, PSP_CMD_RX_ASSOC, PSP_CMD_TX_ASSOC, + PSP_CMD_GET_STATS, __PSP_CMD_MAX, PSP_CMD_MAX = (__PSP_CMD_MAX - 1) diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index b66a800389cc0..b8b9c42f848c8 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -41,6 +41,7 @@ #define TLS_RX 2 /* Set receive parameters */ #define TLS_TX_ZEROCOPY_RO 3 /* TX zerocopy (only sendfile now) */ #define TLS_RX_EXPECT_NO_PAD 4 /* Attempt opportunistic zero-copy */ +#define TLS_TX_MAX_PAYLOAD_LEN 5 /* Maximum plaintext size */ /* Supported versions */ #define TLS_VERSION_MINOR(ver) ((ver) & 0xFF) @@ -194,6 +195,7 @@ enum { TLS_INFO_RXCONF, TLS_INFO_ZC_RO_TX, TLS_INFO_RX_NO_PAD, + TLS_INFO_TX_MAX_PAYLOAD_LEN, __TLS_INFO_MAX, }; #define TLS_INFO_MAX (__TLS_INFO_MAX - 1) diff --git a/include/uapi/linux/virtio_net_ff.h b/include/uapi/linux/virtio_net_ff.h new file mode 100644 index 0000000000000..c98aa4942beeb --- /dev/null +++ b/include/uapi/linux/virtio_net_ff.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note + * + * Header file for virtio_net flow filters + */ +#ifndef _LINUX_VIRTIO_NET_FF_H +#define _LINUX_VIRTIO_NET_FF_H + +#include +#include + +#define VIRTIO_NET_FF_RESOURCE_CAP 0x800 +#define VIRTIO_NET_FF_SELECTOR_CAP 0x801 +#define VIRTIO_NET_FF_ACTION_CAP 0x802 + +#define VIRTIO_NET_RESOURCE_OBJ_FF_GROUP 0x0200 +#define VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER 0x0201 +#define VIRTIO_NET_RESOURCE_OBJ_FF_RULE 0x0202 + +/** + * struct virtio_net_ff_cap_data - Flow filter resource capability limits + * @groups_limit: maximum number of flow filter groups supported by the device + * @classifiers_limit: maximum number of classifiers supported by the device + * @rules_limit: maximum number of rules supported device-wide across all groups + * @rules_per_group_limit: maximum number of rules allowed in a single group + * @last_rule_priority: priority value associated with the lowest-priority rule + * @selectors_per_classifier_limit: maximum selectors allowed in one classifier + * + * The limits are reported by the device and describe resource capacities for + * flow filters. Multi-byte fields are little-endian. + */ +struct virtio_net_ff_cap_data { + __le32 groups_limit; + __le32 classifiers_limit; + __le32 rules_limit; + __le32 rules_per_group_limit; + __u8 last_rule_priority; + __u8 selectors_per_classifier_limit; +}; + +/** + * struct virtio_net_ff_selector - Selector mask descriptor + * @type: selector type, one of VIRTIO_NET_FF_MASK_TYPE_* constants + * @flags: selector flags, see VIRTIO_NET_FF_MASK_F_* constants + * @reserved: must be set to 0 by the driver and ignored by the device + * @length: size in bytes of @mask + * @reserved1: must be set to 0 by the driver and ignored by the device + * @mask: variable-length mask payload for @type, length given by @length + * + * A selector describes a header mask that a classifier can apply. The format + * of @mask depends on @type. + */ +struct virtio_net_ff_selector { + __u8 type; + __u8 flags; + __u8 reserved[2]; + __u8 length; + __u8 reserved1[3]; + __u8 mask[]; +}; + +#define VIRTIO_NET_FF_MASK_TYPE_ETH 1 +#define VIRTIO_NET_FF_MASK_TYPE_IPV4 2 +#define VIRTIO_NET_FF_MASK_TYPE_IPV6 3 +#define VIRTIO_NET_FF_MASK_TYPE_TCP 4 +#define VIRTIO_NET_FF_MASK_TYPE_UDP 5 +#define VIRTIO_NET_FF_MASK_TYPE_MAX VIRTIO_NET_FF_MASK_TYPE_UDP + +/** + * struct virtio_net_ff_cap_mask_data - Supported selector mask formats + * @count: number of entries in @selectors + * @reserved: must be set to 0 by the driver and ignored by the device + * @selectors: array of supported selector descriptors + */ +struct virtio_net_ff_cap_mask_data { + __u8 count; + __u8 reserved[7]; + __u8 selectors[]; +}; +#define VIRTIO_NET_FF_MASK_F_PARTIAL_MASK (1 << 0) + +#define VIRTIO_NET_FF_ACTION_DROP 1 +#define VIRTIO_NET_FF_ACTION_RX_VQ 2 +#define VIRTIO_NET_FF_ACTION_MAX VIRTIO_NET_FF_ACTION_RX_VQ +/** + * struct virtio_net_ff_actions - Supported flow actions + * @count: number of supported actions in @actions + * @reserved: must be set to 0 by the driver and ignored by the device + * @actions: array of action identifiers (VIRTIO_NET_FF_ACTION_*) + */ +struct virtio_net_ff_actions { + __u8 count; + __u8 reserved[7]; + __u8 actions[]; +}; + +/** + * struct virtio_net_resource_obj_ff_group - Flow filter group object + * @group_priority: priority of the group used to order evaluation + * + * This structure is the payload for the VIRTIO_NET_RESOURCE_OBJ_FF_GROUP + * administrative object. Devices use @group_priority to order flow filter + * groups. Multi-byte fields are little-endian. + */ +struct virtio_net_resource_obj_ff_group { + __le16 group_priority; +}; + +/** + * struct virtio_net_resource_obj_ff_classifier - Flow filter classifier object + * @count: number of selector entries in @selectors + * @reserved: must be set to 0 by the driver and ignored by the device + * @selectors: array of selector descriptors that define match masks + * + * Payload for the VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER administrative object. + * Each selector describes a header mask used to match packets + * (see struct virtio_net_ff_selector). Selectors appear in the order they are + * to be applied. + */ +struct virtio_net_resource_obj_ff_classifier { + __u8 count; + __u8 reserved[7]; + __u8 selectors[]; +}; + +/** + * struct virtio_net_resource_obj_ff_rule - Flow filter rule object + * @group_id: identifier of the target flow filter group + * @classifier_id: identifier of the classifier referenced by this rule + * @rule_priority: relative priority of this rule within the group + * @key_length: number of bytes in @keys + * @action: action to perform, one of VIRTIO_NET_FF_ACTION_* + * @reserved: must be set to 0 by the driver and ignored by the device + * @vq_index: RX virtqueue index for VIRTIO_NET_FF_ACTION_RX_VQ, 0 otherwise + * @reserved1: must be set to 0 by the driver and ignored by the device + * @keys: concatenated key bytes matching the classifier's selectors order + * + * Payload for the VIRTIO_NET_RESOURCE_OBJ_FF_RULE administrative object. + * @group_id and @classifier_id refer to previously created objects of types + * VIRTIO_NET_RESOURCE_OBJ_FF_GROUP and VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER + * respectively. The key bytes are compared against packet headers using the + * masks provided by the classifier's selectors. Multi-byte fields are + * little-endian. + */ +struct virtio_net_resource_obj_ff_rule { + __le32 group_id; + __le32 classifier_id; + __u8 rule_priority; + __u8 key_length; /* length of key in bytes */ + __u8 action; + __u8 reserved; + __le16 vq_index; + __u8 reserved1[2]; + __u8 keys[]; +}; + +#endif diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index c691ac210ce2e..0d5ca0cff629a 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -315,15 +315,18 @@ struct virtio_admin_cmd_notify_info_result { #define VIRTIO_DEV_PARTS_CAP 0x0000 +/* Update this value to largest implemented cap number. */ +#define VIRTIO_ADMIN_MAX_CAP 0x0fff + struct virtio_dev_parts_cap { __u8 get_parts_resource_objects_limit; __u8 set_parts_resource_objects_limit; }; -#define MAX_CAP_ID __KERNEL_DIV_ROUND_UP(VIRTIO_DEV_PARTS_CAP + 1, 64) +#define VIRTIO_ADMIN_CAP_ID_ARRAY_SIZE __KERNEL_DIV_ROUND_UP(VIRTIO_ADMIN_MAX_CAP, 64) struct virtio_admin_cmd_query_cap_id_result { - __le64 supported_caps[MAX_CAP_ID]; + __le64 supported_caps[VIRTIO_ADMIN_CAP_ID_ARRAY_SIZE]; }; struct virtio_admin_cmd_cap_get_data { diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index a41e6730edcf3..278490683d288 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -1162,6 +1162,7 @@ bool bpf_struct_ops_get(const void *kdata) map = __bpf_map_inc_not_zero(&st_map->map, false); return !IS_ERR(map); } +EXPORT_SYMBOL_GPL(bpf_struct_ops_get); void bpf_struct_ops_put(const void *kdata) { @@ -1173,6 +1174,7 @@ void bpf_struct_ops_put(const void *kdata) bpf_map_put(&st_map->map); } +EXPORT_SYMBOL_GPL(bpf_struct_ops_put); u32 bpf_struct_ops_id(const void *kdata) { diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 248f517d66d04..69988af44b378 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1665,7 +1665,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk); * returned value != 1 during execution. In all other cases, 0 is returned. */ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, - struct sockaddr *uaddr, + struct sockaddr_unsized *uaddr, int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, @@ -1676,7 +1676,7 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, .uaddr = uaddr, .t_ctx = t_ctx, }; - struct sockaddr_storage unspec; + struct sockaddr_storage storage; struct cgroup *cgrp; int ret; @@ -1688,8 +1688,8 @@ int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, return 0; if (!ctx.uaddr) { - memset(&unspec, 0, sizeof(unspec)); - ctx.uaddr = (struct sockaddr *)&unspec; + memset(&storage, 0, sizeof(storage)); + ctx.uaddr = (struct sockaddr_unsized *)&storage; ctx.uaddrlen = 0; } else { ctx.uaddrlen = *uaddrlen; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 07bfa72f96493..db72b96f9c8c8 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1893,10 +1893,8 @@ int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u64 offset, void *src, return -EINVAL; return __bpf_xdp_store_bytes(dst->data, dst->offset + offset, src, len); case BPF_DYNPTR_TYPE_SKB_META: - if (flags) - return -EINVAL; - memmove(bpf_skb_meta_pointer(dst->data, dst->offset + offset), src, len); - return 0; + return __bpf_skb_meta_store_bytes(dst->data, dst->offset + offset, src, + len, flags); default: WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type); return -EFAULT; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a2a441185f810..c3387cd8e9ca5 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1234,6 +1234,7 @@ int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size) return src - orig_src; } +EXPORT_SYMBOL_GPL(bpf_obj_name_cpy); int map_check_no_btf(const struct bpf_map *map, const struct btf *btf, diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index e81327d2cd639..84fcc67875fdc 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -58,7 +58,7 @@ CONFIG_DEBUG_NET=y CONFIG_PAGE_EXTENSION=y CONFIG_PAGE_OWNER=y CONFIG_DEBUG_KMEMLEAK=y -CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=y +CONFIG_DEBUG_KMEMLEAK_AUTO_SCAN=n CONFIG_DEBUG_OBJECTS=y CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT=1 CONFIG_DEBUG_OBJECTS_FREE=y diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 1b4254d19a73e..c49dee35fc520 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -144,7 +144,6 @@ config IRQ_KUNIT_TEST bool "KUnit tests for IRQ management APIs" if !KUNIT_ALL_TESTS depends on KUNIT=y depends on SPARSE_IRQ - default KUNIT_ALL_TESTS select IRQ_DOMAIN imply SMP help diff --git a/lib/crypto/tests/Kconfig b/lib/crypto/tests/Kconfig index 578af717e13a7..18573597e2fcc 100644 --- a/lib/crypto/tests/Kconfig +++ b/lib/crypto/tests/Kconfig @@ -3,7 +3,6 @@ config CRYPTO_LIB_BLAKE2S_KUNIT_TEST tristate "KUnit tests for BLAKE2s" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE # No need to select CRYPTO_LIB_BLAKE2S here, as that option doesn't # exist; the BLAKE2s code is always built-in for the /dev/random driver. @@ -13,7 +12,6 @@ config CRYPTO_LIB_BLAKE2S_KUNIT_TEST config CRYPTO_LIB_CURVE25519_KUNIT_TEST tristate "KUnit tests for Curve25519" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE select CRYPTO_LIB_CURVE25519 help @@ -22,7 +20,6 @@ config CRYPTO_LIB_CURVE25519_KUNIT_TEST config CRYPTO_LIB_MD5_KUNIT_TEST tristate "KUnit tests for MD5" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE select CRYPTO_LIB_MD5 help @@ -32,7 +29,6 @@ config CRYPTO_LIB_MD5_KUNIT_TEST config CRYPTO_LIB_POLY1305_KUNIT_TEST tristate "KUnit tests for Poly1305" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE select CRYPTO_LIB_POLY1305 help @@ -41,7 +37,6 @@ config CRYPTO_LIB_POLY1305_KUNIT_TEST config CRYPTO_LIB_SHA1_KUNIT_TEST tristate "KUnit tests for SHA-1" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE select CRYPTO_LIB_SHA1 help @@ -53,7 +48,6 @@ config CRYPTO_LIB_SHA1_KUNIT_TEST config CRYPTO_LIB_SHA256_KUNIT_TEST tristate "KUnit tests for SHA-224 and SHA-256" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE select CRYPTO_LIB_SHA256 help @@ -65,7 +59,6 @@ config CRYPTO_LIB_SHA256_KUNIT_TEST config CRYPTO_LIB_SHA512_KUNIT_TEST tristate "KUnit tests for SHA-384 and SHA-512" if !KUNIT_ALL_TESTS depends on KUNIT - default KUNIT_ALL_TESTS || CRYPTO_SELFTESTS select CRYPTO_LIB_BENCHMARK_VISIBLE select CRYPTO_LIB_SHA512 help diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index a516745f732f7..49d674f5e73a8 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -966,7 +966,7 @@ static int p9_bind_privport(struct socket *sock) ((struct sockaddr_in *)&stor)->sin_port = htons((ushort)port); else ((struct sockaddr_in6 *)&stor)->sin6_port = htons((ushort)port); - err = kernel_bind(sock, (struct sockaddr *)&stor, sizeof(stor)); + err = kernel_bind(sock, (struct sockaddr_unsized *)&stor, sizeof(stor)); if (err != -EADDRINUSE) break; } @@ -1018,7 +1018,7 @@ p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args) } err = READ_ONCE(csocket->ops)->connect(csocket, - (struct sockaddr *)&stor, + (struct sockaddr_unsized *)&stor, sizeof(stor), 0); if (err < 0) { pr_err("%s (%d): problem connecting socket to %s\n", @@ -1058,8 +1058,8 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args) return err; } - err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr *)&sun_server, - sizeof(struct sockaddr_un) - 1, 0); + err = READ_ONCE(csocket->ops)->connect(csocket, (struct sockaddr_unsized *)&sun_server, + sizeof(struct sockaddr_un) - 1, 0); if (err < 0) { pr_err("%s (%d): problem connecting socket: %s: %d\n", __func__, task_pid_nr(current), addr, err); diff --git a/net/Kconfig b/net/Kconfig index 1d3f757d4b07e..62266eaf0e95a 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -400,15 +400,15 @@ config NET_PKTGEN module will be called pktgen. config NET_DROP_MONITOR - tristate "Network packet drop alerting service" + tristate "Legacy network packet drop alerting service" depends on INET && TRACEPOINTS help This feature provides an alerting service to userspace in the event that packets are discarded in the network stack. Alerts are broadcast via netlink socket to any listening user space - process. If you don't need network drop alerts, or if you are ok - just checking the various proc files and other utilities for - drop statistics, say N here. + process. This feature is NOT related to "perf" based drop monitoring. + Say N here unless you need to support older userspace tools like + "dropwatch". endmenu # Network testing diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 30242fe103419..2a01fff46c9da 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1149,7 +1149,7 @@ static int atalk_autobind(struct sock *sk) } /* Set the address 'our end' of the connection */ -static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int atalk_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_at *addr = (struct sockaddr_at *)uaddr; struct sock *sk = sock->sk; @@ -1204,7 +1204,7 @@ static int atalk_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } /* Set the address we talk to */ -static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, +static int atalk_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; diff --git a/net/atm/clip.c b/net/atm/clip.c index f7a5565e794ef..8f152e5fa6594 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -168,10 +168,10 @@ static int neigh_check_cb(struct neighbour *n) static void idle_timer_check(struct timer_list *unused) { - write_lock(&arp_tbl.lock); + spin_lock(&arp_tbl.lock); __neigh_for_each_release(&arp_tbl, neigh_check_cb); mod_timer(&idle_timer, jiffies + CLIP_CHECK_INTERVAL * HZ); - write_unlock(&arp_tbl.lock); + spin_unlock(&arp_tbl.lock); } static int clip_arp_rcv(struct sk_buff *skb) diff --git a/net/atm/common.c b/net/atm/common.c index 881c7f259dbd4..cecc71a8bee11 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -157,7 +157,7 @@ int vcc_create(struct net *net, struct socket *sock, int protocol, int family, i memset(&vcc->local, 0, sizeof(struct sockaddr_atmsvc)); memset(&vcc->remote, 0, sizeof(struct sockaddr_atmsvc)); vcc->qos.txtp.max_sdu = 1 << 16; /* for meta VCs */ - refcount_set(&sk->sk_wmem_alloc, 1); + refcount_set(&sk->sk_wmem_alloc, SK_WMEM_ALLOC_BIAS); atomic_set(&sk->sk_rmem_alloc, 0); vcc->push = NULL; vcc->pop = NULL; diff --git a/net/atm/pvc.c b/net/atm/pvc.c index 66d9a9bd58967..8f5e76f5dd9e8 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -24,7 +24,7 @@ static int pvc_shutdown(struct socket *sock, int how) return 0; } -static int pvc_bind(struct socket *sock, struct sockaddr *sockaddr, +static int pvc_bind(struct socket *sock, struct sockaddr_unsized *sockaddr, int sockaddr_len) { struct sock *sk = sock->sk; @@ -56,7 +56,7 @@ static int pvc_bind(struct socket *sock, struct sockaddr *sockaddr, return error; } -static int pvc_connect(struct socket *sock, struct sockaddr *sockaddr, +static int pvc_connect(struct socket *sock, struct sockaddr_unsized *sockaddr, int sockaddr_len, int flags) { return pvc_bind(sock, sockaddr, sockaddr_len); diff --git a/net/atm/svc.c b/net/atm/svc.c index f8137ae693b08..005964250ecd2 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -97,7 +97,7 @@ static int svc_release(struct socket *sock) return 0; } -static int svc_bind(struct socket *sock, struct sockaddr *sockaddr, +static int svc_bind(struct socket *sock, struct sockaddr_unsized *sockaddr, int sockaddr_len) { DEFINE_WAIT(wait); @@ -153,7 +153,7 @@ static int svc_bind(struct socket *sock, struct sockaddr *sockaddr, return error; } -static int svc_connect(struct socket *sock, struct sockaddr *sockaddr, +static int svc_connect(struct socket *sock, struct sockaddr_unsized *sockaddr, int sockaddr_len, int flags) { DEFINE_WAIT(wait); diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 6ef8b2a57a9bf..7ebbff2f00201 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1094,7 +1094,7 @@ static int ax25_release(struct socket *sock) * that we've implemented support for SO_BINDTODEVICE. It is however small * and trivially backward compatible. */ -static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int ax25_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; struct full_sockaddr_ax25 *addr = (struct full_sockaddr_ax25 *)uaddr; @@ -1175,7 +1175,7 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) * FIXME: nonblock behaviour looks like it may have a bug. */ static int __must_check ax25_connect(struct socket *sock, - struct sockaddr *uaddr, int addr_len, int flags) + struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; ax25_cb *ax25 = sk_to_ax25(sk), *ax25t; diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index c299e2bc87eda..58c408b7a7d9c 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -35,6 +35,7 @@ config BATMAN_ADV_BLA bool "Bridge Loop Avoidance" depends on BATMAN_ADV && INET select CRC16 + select NET_CRC32C default y help This option enables BLA (Bridge Loop Avoidance), a mechanism diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index b992ba12aa247..3dc791c15bf72 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -1585,45 +1584,11 @@ int batadv_bla_init(struct batadv_priv *bat_priv) return 0; } -/** - * batadv_skb_crc32() - calculate CRC32 of the whole packet and skip bytes in - * the header - * @skb: skb pointing to fragmented socket buffers - * @payload_ptr: Pointer to position inside the head buffer of the skb - * marking the start of the data to be CRC'ed - * - * payload_ptr must always point to an address in the skb head buffer and not to - * a fragment. - * - * Return: big endian crc32c of the checksummed data - */ -static __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr) -{ - unsigned int to = skb->len; - unsigned int consumed = 0; - struct skb_seq_state st; - unsigned int from; - unsigned int len; - const u8 *data; - u32 crc = 0; - - from = (unsigned int)(payload_ptr - skb->data); - - skb_prepare_seq_read(skb, from, to, &st); - while ((len = skb_seq_read(consumed, &data, &st)) != 0) { - crc = crc32c(crc, data, len); - consumed += len; - } - - return htonl(crc); -} - /** * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup. * @bat_priv: the bat priv with all the mesh interface information * @skb: contains the multicast packet to be checked - * @payload_ptr: pointer to position inside the head buffer of the skb - * marking the start of the data to be CRC'ed + * @payload_offset: offset in the skb, marking the start of the data to be CRC'ed * @orig: originator mac address, NULL if unknown * * Check if it is on our broadcast list. Another gateway might have sent the @@ -1638,16 +1603,18 @@ static __be32 batadv_skb_crc32(struct sk_buff *skb, u8 *payload_ptr) * Return: true if a packet is in the duplicate list, false otherwise. */ static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, - struct sk_buff *skb, u8 *payload_ptr, + struct sk_buff *skb, int payload_offset, const u8 *orig) { struct batadv_bcast_duplist_entry *entry; bool ret = false; + int payload_len; int i, curr; - __be32 crc; + u32 crc; /* calculate the crc ... */ - crc = batadv_skb_crc32(skb, payload_ptr); + payload_len = skb->len - payload_offset; + crc = skb_crc32c(skb, payload_offset, payload_len, 0); spin_lock_bh(&bat_priv->bla.bcast_duplist_lock); @@ -1727,7 +1694,7 @@ static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv, static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb) { - return batadv_bla_check_duplist(bat_priv, skb, (u8 *)skb->data, NULL); + return batadv_bla_check_duplist(bat_priv, skb, 0, NULL); } /** @@ -1745,12 +1712,10 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv, struct sk_buff *skb) { struct batadv_bcast_packet *bcast_packet; - u8 *payload_ptr; bcast_packet = (struct batadv_bcast_packet *)skb->data; - payload_ptr = (u8 *)(bcast_packet + 1); - return batadv_bla_check_duplist(bat_priv, skb, payload_ptr, + return batadv_bla_check_duplist(bat_priv, skb, sizeof(*bcast_packet), bcast_packet->orig); } diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 2be1ac17acaa4..af230b017bc17 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2025.4" +#define BATADV_SOURCE_VERSION "2025.5" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index ae1d7a8dc480f..8fc5fe0e9b053 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -734,7 +734,7 @@ struct batadv_bcast_duplist_entry { u8 orig[ETH_ALEN]; /** @crc: crc32 checksum of broadcast payload */ - __be32 crc; + u32 crc; /** @entrytime: time when the broadcast packet was received */ unsigned long entrytime; diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index fc866759910d9..ba9f48771e11d 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1185,7 +1185,7 @@ static int hci_sock_compat_ioctl(struct socket *sock, unsigned int cmd, } #endif -static int hci_sock_bind(struct socket *sock, struct sockaddr *addr, +static int hci_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_hci haddr; diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 3d98cb6291da6..243505b897331 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -944,7 +944,7 @@ static int iso_sock_create(struct net *net, struct socket *sock, int protocol, return 0; } -static int iso_sock_bind_bc(struct socket *sock, struct sockaddr *addr, +static int iso_sock_bind_bc(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; @@ -1022,7 +1022,7 @@ static int iso_sock_bind_pa_sk(struct sock *sk, struct sockaddr_iso *sa, return err; } -static int iso_sock_bind(struct socket *sock, struct sockaddr *addr, +static int iso_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; @@ -1080,7 +1080,7 @@ static int iso_sock_bind(struct socket *sock, struct sockaddr *addr, return err; } -static int iso_sock_connect(struct socket *sock, struct sockaddr *addr, +static int iso_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { struct sockaddr_iso *sa = (struct sockaddr_iso *)addr; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 814fb8610ac43..9ee189c815d49 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -80,7 +80,7 @@ static int l2cap_validate_le_psm(u16 psm) return 0; } -static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) +static int l2cap_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int alen) { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; @@ -178,7 +178,7 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) return err; } -static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, +static int l2cap_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { struct sock *sk = sock->sk; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 96250807b32b4..57b1dca8141f0 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -781,7 +781,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, addr.l2_psm = 0; addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; - *err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr)); + *err = kernel_bind(sock, (struct sockaddr_unsized *)&addr, sizeof(addr)); if (*err < 0) goto failed; @@ -808,7 +808,7 @@ static struct rfcomm_session *rfcomm_session_create(bdaddr_t *src, addr.l2_psm = cpu_to_le16(L2CAP_PSM_RFCOMM); addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; - *err = kernel_connect(sock, (struct sockaddr *) &addr, sizeof(addr), O_NONBLOCK); + *err = kernel_connect(sock, (struct sockaddr_unsized *)&addr, sizeof(addr), O_NONBLOCK); if (*err == 0 || *err == -EINPROGRESS) return s; @@ -2068,7 +2068,7 @@ static int rfcomm_add_listener(bdaddr_t *ba) addr.l2_psm = cpu_to_le16(L2CAP_PSM_RFCOMM); addr.l2_cid = 0; addr.l2_bdaddr_type = BDADDR_BREDR; - err = kernel_bind(sock, (struct sockaddr *) &addr, sizeof(addr)); + err = kernel_bind(sock, (struct sockaddr_unsized *)&addr, sizeof(addr)); if (err < 0) { BT_ERR("Bind failed %d", err); goto failed; diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 913402806fa0d..be6639cd6f590 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -324,7 +324,7 @@ static int rfcomm_sock_create(struct net *net, struct socket *sock, return 0; } -static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +static int rfcomm_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_rc sa; struct sock *sk = sock->sk; @@ -371,7 +371,8 @@ static int rfcomm_sock_bind(struct socket *sock, struct sockaddr *addr, int addr return err; } -static int rfcomm_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) +static int rfcomm_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, + int alen, int flags) { struct sockaddr_rc *sa = (struct sockaddr_rc *) addr; struct sock *sk = sock->sk; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index ab0cf442d57b9..7afe65e7ff371 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -605,7 +605,7 @@ static int sco_sock_create(struct net *net, struct socket *sock, int protocol, return 0; } -static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, +static int sco_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; @@ -639,7 +639,7 @@ static int sco_sock_bind(struct socket *sock, struct sockaddr *addr, return err; } -static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) +static int sco_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index ca3a637d7cca7..4c67a32745f6b 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -526,20 +526,6 @@ void br_mtu_auto_adjust(struct net_bridge *br) br_opt_toggle(br, BROPT_MTU_SET_BY_USER, false); } -static void br_set_gso_limits(struct net_bridge *br) -{ - unsigned int tso_max_size = TSO_MAX_SIZE; - const struct net_bridge_port *p; - u16 tso_max_segs = TSO_MAX_SEGS; - - list_for_each_entry(p, &br->port_list, list) { - tso_max_size = min(tso_max_size, p->dev->tso_max_size); - tso_max_segs = min(tso_max_segs, p->dev->tso_max_segs); - } - netif_set_tso_max_size(br->dev, tso_max_size); - netif_set_tso_max_segs(br->dev, tso_max_segs); -} - /* * Recomputes features using slave's features */ @@ -653,8 +639,6 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, netdev_err(dev, "failed to sync bridge static fdb addresses to this port\n"); } - netdev_update_features(br->dev); - br_hr = br->dev->needed_headroom; dev_hr = netdev_get_fwd_headroom(dev); if (br_hr < dev_hr) @@ -695,7 +679,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev, call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); br_mtu_auto_adjust(br); - br_set_gso_limits(br); + + netdev_compute_master_upper_features(br->dev, false); kobject_uevent(&p->kobj, KOBJ_ADD); @@ -741,7 +726,6 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) del_nbp(p); br_mtu_auto_adjust(br); - br_set_gso_limits(br); spin_lock_bh(&br->lock); changed_addr = br_stp_recalculate_bridge_id(br); @@ -750,7 +734,7 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) if (changed_addr) call_netdevice_notifiers(NETDEV_CHANGEADDR, br->dev); - netdev_update_features(br->dev); + netdev_compute_master_upper_features(br->dev, false); return 0; } diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 22d12e5459668..d55a4ab87837f 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -4649,6 +4649,14 @@ static void br_multicast_start_querier(struct net_bridge_mcast *brmctx, rcu_read_unlock(); } +static void br_multicast_del_grps(struct net_bridge *br) +{ + struct net_bridge_port *port; + + list_for_each_entry(port, &br->port_list, list) + __br_multicast_disable_port_ctx(&port->multicast_ctx); +} + int br_multicast_toggle(struct net_bridge *br, unsigned long val, struct netlink_ext_ack *extack) { @@ -4669,6 +4677,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val, br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { change_snoopers = true; + br_multicast_del_grps(br); goto unlock; } diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 4e2d53b272210..0264730938f4b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -467,7 +467,7 @@ static int br_fill_ifinfo(struct sk_buff *skb, else br = netdev_priv(dev); - br_debug(br, "br_fill_info event %d port %s master %s\n", + br_debug(br, "br_fill_ifinfo event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 039dfbd367c97..af218742af5ac 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -734,7 +734,7 @@ static int setsockopt(struct socket *sock, int lvl, int opt, sockptr_t ov, * o sock->state: holds the SS_* socket state and is updated by connect and * disconnect. */ -static int caif_connect(struct socket *sock, struct sockaddr *uaddr, +static int caif_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; diff --git a/net/can/bcm.c b/net/can/bcm.c index 5e690a2377e48..7eba8ae01a5b1 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1657,7 +1657,7 @@ static int bcm_release(struct socket *sock) return 0; } -static int bcm_connect(struct socket *sock, struct sockaddr *uaddr, int len, +static int bcm_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int len, int flags) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; diff --git a/net/can/isotp.c b/net/can/isotp.c index 74ee1e52249b2..ce588b85665a0 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1246,7 +1246,7 @@ static int isotp_release(struct socket *sock) return 0; } -static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len) +static int isotp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 88e7160d42489..6272326dd614a 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -440,7 +440,7 @@ static int j1939_sk_sanity_check(struct sockaddr_can *addr, int len) return 0; } -static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) +static int j1939_sk_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct j1939_sock *jsk = j1939_sk(sock->sk); @@ -535,7 +535,7 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) return ret; } -static int j1939_sk_connect(struct socket *sock, struct sockaddr *uaddr, +static int j1939_sk_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int len, int flags) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; diff --git a/net/can/raw.c b/net/can/raw.c index a53853f5e9afc..f36a83d3447cf 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -449,7 +449,7 @@ static int raw_release(struct socket *sock) return 0; } -static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) +static int raw_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int len) { struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index f8181acaf8704..70b25f4ecba67 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -460,7 +460,7 @@ int ceph_tcp_connect(struct ceph_connection *con) set_sock_callbacks(sock, con); con_sock_state_connecting(con); - ret = kernel_connect(sock, (struct sockaddr *)&ss, sizeof(ss), + ret = kernel_connect(sock, (struct sockaddr_unsized *)&ss, sizeof(ss), O_NONBLOCK); if (ret == -EINPROGRESS) { dout("connect %s EINPROGRESS sk_state = %u\n", diff --git a/net/core/dev.c b/net/core/dev.c index 2acfa44927daa..69515edd17bc6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1163,6 +1163,7 @@ void netdev_copy_name(struct net_device *dev, char *name) strscpy(name, dev->name, IFNAMSIZ); } while (read_seqretry(&netdev_rename_lock, seq)); } +EXPORT_IPV6_MOD_GPL(netdev_copy_name); /** * netdev_get_name - get a netdevice name, knowing its ifindex. @@ -2462,9 +2463,9 @@ int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb) return __dev_forward_skb2(dev, skb, false) ?: netif_rx_internal(skb); } -static inline int deliver_skb(struct sk_buff *skb, - struct packet_type *pt_prev, - struct net_device *orig_dev) +static int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) { if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) return -ENOMEM; @@ -2483,7 +2484,7 @@ static inline void deliver_ptype_list_skb(struct sk_buff *skb, list_for_each_entry_rcu(ptype, ptype_list, list) { if (ptype->type != type) continue; - if (pt_prev) + if (unlikely(pt_prev)) deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } @@ -2544,7 +2545,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if (skb_loop_sk(ptype, skb)) continue; - if (pt_prev) { + if (unlikely(pt_prev)) { deliver_skb(skb2, pt_prev, skb->dev); pt_prev = ptype; continue; @@ -3373,6 +3374,13 @@ static void __netif_reschedule(struct Qdisc *q) void __netif_schedule(struct Qdisc *q) { + /* If q->defer_list is not empty, at least one thread is + * in __dev_xmit_skb() before llist_del_all(&q->defer_list). + * This thread will attempt to run the queue. + */ + if (!llist_empty(&q->defer_list)) + return; + if (!test_and_set_bit(__QDISC_STATE_SCHED, &q->state)) __netif_reschedule(q); } @@ -4125,9 +4133,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq) { + struct sk_buff *next, *to_free = NULL; spinlock_t *root_lock = qdisc_lock(q); - struct sk_buff *to_free = NULL; - bool contended; + struct llist_node *ll_list, *first_n; + unsigned long defer_count = 0; int rc; qdisc_calculate_pkt_len(skb, q); @@ -4167,67 +4176,81 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } - if (unlikely(READ_ONCE(q->owner) == smp_processor_id())) { - kfree_skb_reason(skb, SKB_DROP_REASON_TC_RECLASSIFY_LOOP); - return NET_XMIT_DROP; - } - /* - * Heuristic to force contended enqueues to serialize on a - * separate lock before trying to get qdisc main lock. - * This permits qdisc->running owner to get the lock more - * often and dequeue packets faster. - * On PREEMPT_RT it is possible to preempt the qdisc owner during xmit - * and then other tasks will only enqueue packets. The packets will be - * sent after the qdisc owner is scheduled again. To prevent this - * scenario the task always serialize on the lock. + /* Open code llist_add(&skb->ll_node, &q->defer_list) + queue limit. + * In the try_cmpxchg() loop, we want to increment q->defer_count + * at most once to limit the number of skbs in defer_list. + * We perform the defer_count increment only if the list is not empty, + * because some arches have slow atomic_long_inc_return(). */ - contended = qdisc_is_running(q) || IS_ENABLED(CONFIG_PREEMPT_RT); - if (unlikely(contended)) - spin_lock(&q->busylock); + first_n = READ_ONCE(q->defer_list.first); + do { + if (first_n && !defer_count) { + defer_count = atomic_long_inc_return(&q->defer_count); + if (unlikely(defer_count > q->limit)) { + kfree_skb_reason(skb, SKB_DROP_REASON_QDISC_DROP); + return NET_XMIT_DROP; + } + } + skb->ll_node.next = first_n; + } while (!try_cmpxchg(&q->defer_list.first, &first_n, &skb->ll_node)); + + /* If defer_list was not empty, we know the cpu which queued + * the first skb will process the whole list for us. + */ + if (first_n) + return NET_XMIT_SUCCESS; spin_lock(root_lock); + + ll_list = llist_del_all(&q->defer_list); + /* There is a small race because we clear defer_count not atomically + * with the prior llist_del_all(). This means defer_list could grow + * over q->limit. + */ + atomic_long_set(&q->defer_count, 0); + + ll_list = llist_reverse_order(ll_list); + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { - __qdisc_drop(skb, &to_free); + llist_for_each_entry_safe(skb, next, ll_list, ll_node) + __qdisc_drop(skb, &to_free); rc = NET_XMIT_DROP; - } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && - qdisc_run_begin(q)) { + goto unlock; + } + if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && + !llist_next(ll_list) && qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - * xmit the skb directly. */ + DEBUG_NET_WARN_ON_ONCE(skb != llist_entry(ll_list, + struct sk_buff, + ll_node)); qdisc_bstats_update(q, skb); - - if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) { - if (unlikely(contended)) { - spin_unlock(&q->busylock); - contended = false; - } + if (sch_direct_xmit(skb, q, dev, txq, root_lock, true)) __qdisc_run(q); - } - qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { - WRITE_ONCE(q->owner, smp_processor_id()); - rc = dev_qdisc_enqueue(skb, q, &to_free, txq); - WRITE_ONCE(q->owner, -1); - if (qdisc_run_begin(q)) { - if (unlikely(contended)) { - spin_unlock(&q->busylock); - contended = false; - } - __qdisc_run(q); - qdisc_run_end(q); + int count = 0; + + llist_for_each_entry_safe(skb, next, ll_list, ll_node) { + prefetch(next); + skb_mark_not_on_list(skb); + rc = dev_qdisc_enqueue(skb, q, &to_free, txq); + count++; } + qdisc_run(q); + if (count != 1) + rc = NET_XMIT_SUCCESS; } +unlock: spin_unlock(root_lock); if (unlikely(to_free)) kfree_skb_list_reason(to_free, tcf_get_drop_reason(to_free)); - if (unlikely(contended)) - spin_unlock(&q->busylock); return rc; } @@ -4398,7 +4421,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, return skb; bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx); - if (*pt_prev) { + if (unlikely(*pt_prev)) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } @@ -4591,6 +4614,32 @@ u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, } EXPORT_SYMBOL(dev_pick_tx_zero); +int sk_tx_queue_get(const struct sock *sk) +{ + int resel, val; + + if (!sk) + return -1; + /* Paired with WRITE_ONCE() in sk_tx_queue_clear() + * and sk_tx_queue_set(). + */ + val = READ_ONCE(sk->sk_tx_queue_mapping); + + if (val == NO_QUEUE_MAPPING) + return -1; + + if (!sk_fullsock(sk)) + return val; + + resel = READ_ONCE(sock_net(sk)->core.sysctl_txq_reselection); + if (resel && time_is_before_jiffies( + READ_ONCE(sk->sk_tx_queue_mapping_jiffies) + resel)) + return -1; + + return val; +} +EXPORT_SYMBOL(sk_tx_queue_get); + u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev) { @@ -4606,8 +4655,7 @@ u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, if (new_index < 0) new_index = skb_tx_hash(dev, sb_dev, skb); - if (queue_index != new_index && sk && - sk_fullsock(sk) && + if (sk && sk_fullsock(sk) && rcu_access_pointer(sk->sk_dst_cache)) sk_tx_queue_set(sk, new_index); @@ -5202,14 +5250,15 @@ void kick_defer_list_purge(unsigned int cpu) int netdev_flow_limit_table_len __read_mostly = (1 << 12); #endif -static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen) +static bool skb_flow_limit(struct sk_buff *skb, unsigned int qlen, + int max_backlog) { #ifdef CONFIG_NET_FLOW_LIMIT - struct sd_flow_limit *fl; - struct softnet_data *sd; unsigned int old_flow, new_flow; + const struct softnet_data *sd; + struct sd_flow_limit *fl; - if (qlen < (READ_ONCE(net_hotdata.max_backlog) >> 1)) + if (likely(qlen < (max_backlog >> 1))) return false; sd = this_cpu_ptr(&softnet_data); @@ -5254,19 +5303,19 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, u32 tail; reason = SKB_DROP_REASON_DEV_READY; - if (!netif_running(skb->dev)) + if (unlikely(!netif_running(skb->dev))) goto bad_dev; - reason = SKB_DROP_REASON_CPU_BACKLOG; sd = &per_cpu(softnet_data, cpu); qlen = skb_queue_len_lockless(&sd->input_pkt_queue); max_backlog = READ_ONCE(net_hotdata.max_backlog); - if (unlikely(qlen > max_backlog)) + if (unlikely(qlen > max_backlog) || + skb_flow_limit(skb, qlen, max_backlog)) goto cpu_backlog_drop; backlog_lock_irq_save(sd, &flags); qlen = skb_queue_len(&sd->input_pkt_queue); - if (qlen <= max_backlog && !skb_flow_limit(skb, qlen)) { + if (likely(qlen <= max_backlog)) { if (!qlen) { /* Schedule NAPI for backlog device. We can use * non atomic operation as we own the queue lock. @@ -5287,6 +5336,7 @@ static int enqueue_to_backlog(struct sk_buff *skb, int cpu, backlog_unlock_irq_restore(sd, &flags); cpu_backlog_drop: + reason = SKB_DROP_REASON_CPU_BACKLOG; numa_drop_add(&sd->drop_counters, 1); bad_dev: dev_core_stats_rx_dropped_inc(skb->dev); @@ -5833,7 +5883,7 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, if (nf_hook_ingress_active(skb)) { int ingress_retval; - if (*pt_prev) { + if (unlikely(*pt_prev)) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; } @@ -5910,13 +5960,13 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, list_for_each_entry_rcu(ptype, &dev_net_rcu(skb->dev)->ptype_all, list) { - if (pt_prev) + if (unlikely(pt_prev)) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } list_for_each_entry_rcu(ptype, &skb->dev->ptype_all, list) { - if (pt_prev) + if (unlikely(pt_prev)) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; } @@ -5947,7 +5997,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, } if (skb_vlan_tag_present(skb)) { - if (pt_prev) { + if (unlikely(pt_prev)) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } @@ -5959,7 +6009,7 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, rx_handler = rcu_dereference(skb->dev->rx_handler); if (rx_handler) { - if (pt_prev) { + if (unlikely(pt_prev)) { ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = NULL; } @@ -6732,6 +6782,7 @@ static void skb_defer_free_flush(void) free_list = llist_del_all(&sdn->defer_list); llist_for_each_entry_safe(skb, next, free_list, ll_node) { + prefetch(next); napi_consume_skb(skb, 1); } } @@ -7039,7 +7090,8 @@ static void napi_stop_kthread(struct napi_struct *napi) */ if ((val & NAPIF_STATE_SCHED_THREADED) || !(val & NAPIF_STATE_SCHED)) { - new = val & (~NAPIF_STATE_THREADED); + new = val & (~(NAPIF_STATE_THREADED | + NAPIF_STATE_THREADED_BUSY_POLL)); } else { msleep(20); continue; @@ -7063,6 +7115,16 @@ static void napi_stop_kthread(struct napi_struct *napi) napi->thread = NULL; } +static void napi_set_threaded_state(struct napi_struct *napi, + enum netdev_napi_threaded threaded_mode) +{ + bool threaded = threaded_mode != NETDEV_NAPI_THREADED_DISABLED; + bool busy_poll = threaded_mode == NETDEV_NAPI_THREADED_BUSY_POLL; + + assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); + assign_bit(NAPI_STATE_THREADED_BUSY_POLL, &napi->state, busy_poll); +} + int napi_set_threaded(struct napi_struct *napi, enum netdev_napi_threaded threaded) { @@ -7089,7 +7151,7 @@ int napi_set_threaded(struct napi_struct *napi, } else { /* Make sure kthread is created before THREADED bit is set. */ smp_mb__before_atomic(); - assign_bit(NAPI_STATE_THREADED, &napi->state, threaded); + napi_set_threaded_state(napi, threaded); } return 0; @@ -7481,7 +7543,9 @@ void napi_disable_locked(struct napi_struct *n) } new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; - new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); + new &= ~(NAPIF_STATE_THREADED | + NAPIF_STATE_THREADED_BUSY_POLL | + NAPIF_STATE_PREFER_BUSY_POLL); } while (!try_cmpxchg(&n->state, &val, new)); hrtimer_cancel(&n->timer); @@ -7693,7 +7757,7 @@ static int napi_thread_wait(struct napi_struct *napi) return -1; } -static void napi_threaded_poll_loop(struct napi_struct *napi) +static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll) { struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx; struct softnet_data *sd; @@ -7722,22 +7786,47 @@ static void napi_threaded_poll_loop(struct napi_struct *napi) } skb_defer_free_flush(); bpf_net_ctx_clear(bpf_net_ctx); + + /* When busy poll is enabled, the old packets are not flushed in + * napi_complete_done. So flush them here. + */ + if (busy_poll) + gro_flush_normal(&napi->gro, HZ >= 1000); local_bh_enable(); + /* Call cond_resched here to avoid watchdog warnings. */ + if (repoll || busy_poll) { + rcu_softirq_qs_periodic(last_qs); + cond_resched(); + } + if (!repoll) break; - - rcu_softirq_qs_periodic(last_qs); - cond_resched(); } } static int napi_threaded_poll(void *data) { struct napi_struct *napi = data; + bool want_busy_poll; + bool in_busy_poll; + unsigned long val; + + while (!napi_thread_wait(napi)) { + val = READ_ONCE(napi->state); + + want_busy_poll = val & NAPIF_STATE_THREADED_BUSY_POLL; + in_busy_poll = val & NAPIF_STATE_IN_BUSY_POLL; - while (!napi_thread_wait(napi)) - napi_threaded_poll_loop(napi); + if (unlikely(val & NAPIF_STATE_DISABLE)) + want_busy_poll = false; + + if (want_busy_poll != in_busy_poll) + assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state, + want_busy_poll); + + napi_threaded_poll_loop(napi, want_busy_poll); + } return 0; } @@ -9885,7 +9974,7 @@ DECLARE_RWSEM(dev_addr_sem); /* "sa" is a true struct sockaddr with limited "sa_data" member. */ int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data_min); + size_t size = sizeof(sa->sa_data); struct net_device *dev; int ret = 0; @@ -12646,6 +12735,94 @@ netdev_features_t netdev_increment_features(netdev_features_t all, } EXPORT_SYMBOL(netdev_increment_features); +/** + * netdev_compute_master_upper_features - compute feature from lowers + * @dev: the upper device + * @update_header: whether to update upper device's header_len/headroom/tailroom + * + * Recompute the upper device's feature based on all lower devices. + */ +void netdev_compute_master_upper_features(struct net_device *dev, bool update_header) +{ + unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; + netdev_features_t gso_partial_features = MASTER_UPPER_DEV_GSO_PARTIAL_FEATURES; + netdev_features_t xfrm_features = MASTER_UPPER_DEV_XFRM_FEATURES; + netdev_features_t mpls_features = MASTER_UPPER_DEV_MPLS_FEATURES; + netdev_features_t vlan_features = MASTER_UPPER_DEV_VLAN_FEATURES; + netdev_features_t enc_features = MASTER_UPPER_DEV_ENC_FEATURES; + unsigned short max_header_len = ETH_HLEN; + unsigned int tso_max_size = TSO_MAX_SIZE; + unsigned short max_headroom = 0; + unsigned short max_tailroom = 0; + u16 tso_max_segs = TSO_MAX_SEGS; + struct net_device *lower_dev; + struct list_head *iter; + + mpls_features = netdev_base_features(mpls_features); + vlan_features = netdev_base_features(vlan_features); + enc_features = netdev_base_features(enc_features); + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + gso_partial_features = netdev_increment_features(gso_partial_features, + lower_dev->gso_partial_features, + MASTER_UPPER_DEV_GSO_PARTIAL_FEATURES); + + vlan_features = netdev_increment_features(vlan_features, + lower_dev->vlan_features, + MASTER_UPPER_DEV_VLAN_FEATURES); + + enc_features = netdev_increment_features(enc_features, + lower_dev->hw_enc_features, + MASTER_UPPER_DEV_ENC_FEATURES); + + if (IS_ENABLED(CONFIG_XFRM_OFFLOAD)) + xfrm_features = netdev_increment_features(xfrm_features, + lower_dev->hw_enc_features, + MASTER_UPPER_DEV_XFRM_FEATURES); + + mpls_features = netdev_increment_features(mpls_features, + lower_dev->mpls_features, + MASTER_UPPER_DEV_MPLS_FEATURES); + + dst_release_flag &= lower_dev->priv_flags; + + if (update_header) { + max_header_len = max(max_header_len, lower_dev->hard_header_len); + max_headroom = max(max_headroom, lower_dev->needed_headroom); + max_tailroom = max(max_tailroom, lower_dev->needed_tailroom); + } + + tso_max_size = min(tso_max_size, lower_dev->tso_max_size); + tso_max_segs = min(tso_max_segs, lower_dev->tso_max_segs); + } + + dev->gso_partial_features = gso_partial_features; + dev->vlan_features = vlan_features; + dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; + if (IS_ENABLED(CONFIG_XFRM_OFFLOAD)) + dev->hw_enc_features |= xfrm_features; + dev->mpls_features = mpls_features; + + dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + if ((dev->priv_flags & IFF_XMIT_DST_RELEASE_PERM) && + dst_release_flag == (IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM)) + dev->priv_flags |= IFF_XMIT_DST_RELEASE; + + if (update_header) { + dev->hard_header_len = max_header_len; + dev->needed_headroom = max_headroom; + dev->needed_tailroom = max_tailroom; + } + + netif_set_tso_max_segs(dev, tso_max_segs); + netif_set_tso_max_size(dev, tso_max_size); + + netdev_change_features(dev); +} +EXPORT_SYMBOL(netdev_compute_master_upper_features); + static struct hlist_head * __net_init netdev_create_hash(void) { int i; @@ -12959,7 +13136,7 @@ static void run_backlog_napi(unsigned int cpu) { struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu); - napi_threaded_poll_loop(&sd->backlog); + napi_threaded_poll_loop(&sd->backlog, false); } static void backlog_napi_setup(unsigned int cpu) diff --git a/net/core/dev.h b/net/core/dev.h index 900880e8b5b4b..4d872a79bafbc 100644 --- a/net/core/dev.h +++ b/net/core/dev.h @@ -317,6 +317,9 @@ static inline void napi_set_irq_suspend_timeout(struct napi_struct *n, static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n) { + if (test_bit(NAPI_STATE_THREADED_BUSY_POLL, &n->state)) + return NETDEV_NAPI_THREADED_BUSY_POLL; + if (test_bit(NAPI_STATE_THREADED, &n->state)) return NETDEV_NAPI_THREADED_ENABLED; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index ad54b12d4b4c8..0720ccc14df90 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -443,6 +443,9 @@ static int generic_hwtstamp_ioctl_lower(struct net_device *dev, int cmd, struct ifreq ifrr; int err; + if (!kernel_cfg->ifr) + return -EINVAL; + strscpy_pad(ifrr.ifr_name, dev->name, IFNAMSIZ); ifrr.ifr_ifru = kernel_cfg->ifr->ifr_ifru; @@ -596,7 +599,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data, if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data_min), + min(sizeof(ifr->ifr_hwaddr.sa_data), (size_t)dev->addr_len)); netdev_lock_ops(dev); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); diff --git a/net/core/devmem.h b/net/core/devmem.h index 101150d761af2..0b43a648cd2ef 100644 --- a/net/core/devmem.h +++ b/net/core/devmem.h @@ -94,7 +94,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding); int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx, struct net_devmem_dmabuf_binding *binding, struct netlink_ext_ack *extack); -void net_devmem_bind_tx_release(struct sock *sk); static inline struct dmabuf_genpool_chunk_owner * net_devmem_iov_to_chunk_owner(const struct net_iov *niov) diff --git a/net/core/filter.c b/net/core/filter.c index df6ce85e48dcd..616e0520a0bb8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -3260,11 +3260,11 @@ static void bpf_skb_change_protocol(struct sk_buff *skb, u16 proto) static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { - /* Caller already did skb_cow() with len as headroom, + /* Caller already did skb_cow() with meta_len+len as headroom, * so no need to do it here. */ skb_push(skb, len); - memmove(skb->data, skb->data + len, off); + skb_postpush_data_move(skb, len, off); memset(skb->data + off, 0, len); /* No skb_postpush_rcsum(skb, skb->data + off, len) @@ -3288,7 +3288,7 @@ static int bpf_skb_generic_pop(struct sk_buff *skb, u32 off, u32 len) old_data = skb->data; __skb_pull(skb, len); skb_postpull_rcsum(skb, old_data + off, len); - memmove(skb->data, old_data, off); + skb_postpull_data_move(skb, len, off); return 0; } @@ -3333,10 +3333,11 @@ static int bpf_skb_net_hdr_pop(struct sk_buff *skb, u32 off, u32 len) static int bpf_skb_proto_4_to_6(struct sk_buff *skb) { const u32 len_diff = sizeof(struct ipv6hdr) - sizeof(struct iphdr); + const u8 meta_len = skb_metadata_len(skb); u32 off = skb_mac_header_len(skb); int ret; - ret = skb_cow(skb, len_diff); + ret = skb_cow(skb, meta_len + len_diff); if (unlikely(ret < 0)) return ret; @@ -3496,6 +3497,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT; bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK; u16 mac_len = 0, inner_net = 0, inner_trans = 0; + const u8 meta_len = skb_metadata_len(skb); unsigned int gso_type = SKB_GSO_DODGY; int ret; @@ -3506,7 +3508,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, return -ENOTSUPP; } - ret = skb_cow_head(skb, len_diff); + ret = skb_cow_head(skb, meta_len + len_diff); if (unlikely(ret < 0)) return ret; @@ -3880,6 +3882,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = { static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, u64 flags) { + const u8 meta_len = skb_metadata_len(skb); u32 max_len = BPF_SKB_MAX_LEN; u32 new_len = skb->len + head_room; int ret; @@ -3889,7 +3892,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, new_len < skb->len)) return -EINVAL; - ret = skb_cow(skb, head_room); + ret = skb_cow(skb, meta_len + head_room); if (likely(!ret)) { /* Idea for this helper is that we currently only * allow to expand on mac header. This means that @@ -3901,6 +3904,7 @@ static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, * for redirection into L2 device. */ __skb_push(skb, head_room); + skb_postpush_data_move(skb, head_room, 0); memset(skb->data, 0, head_room); skb_reset_mac_header(skb); skb_reset_mac_len(skb); @@ -5741,6 +5745,77 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +static int sk_bpf_set_get_bypass_prot_mem(struct sock *sk, + char *optval, int optlen, + bool getopt) +{ + int val; + + if (optlen != sizeof(int)) + return -EINVAL; + + if (!sk_has_account(sk)) + return -EOPNOTSUPP; + + if (getopt) { + *(int *)optval = sk->sk_bypass_prot_mem; + return 0; + } + + val = *(int *)optval; + if (val < 0 || val > 1) + return -EINVAL; + + sk->sk_bypass_prot_mem = val; + return 0; +} + +BPF_CALL_5(bpf_sock_create_setsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + if (level == SOL_SOCKET && optname == SK_BPF_BYPASS_PROT_MEM) + return sk_bpf_set_get_bypass_prot_mem(sk, optval, optlen, false); + + return __bpf_setsockopt(sk, level, optname, optval, optlen); +} + +static const struct bpf_func_proto bpf_sock_create_setsockopt_proto = { + .func = bpf_sock_create_setsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM | MEM_RDONLY, + .arg5_type = ARG_CONST_SIZE, +}; + +BPF_CALL_5(bpf_sock_create_getsockopt, struct sock *, sk, int, level, + int, optname, char *, optval, int, optlen) +{ + if (level == SOL_SOCKET && optname == SK_BPF_BYPASS_PROT_MEM) { + int err = sk_bpf_set_get_bypass_prot_mem(sk, optval, optlen, true); + + if (err) + memset(optval, 0, optlen); + + return err; + } + + return __bpf_getsockopt(sk, level, optname, optval, optlen); +} + +static const struct bpf_func_proto bpf_sock_create_getsockopt_proto = { + .func = bpf_sock_create_getsockopt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_UNINIT_MEM, + .arg5_type = ARG_CONST_SIZE, +}; + BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { @@ -5915,7 +5990,7 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, return err; if (((struct sockaddr_in *)addr)->sin_port == htons(0)) flags |= BIND_FORCE_ADDRESS_NO_PORT; - return __inet_bind(sk, addr, addr_len, flags); + return __inet_bind(sk, (struct sockaddr_unsized *)addr, addr_len, flags); #if IS_ENABLED(CONFIG_IPV6) } else if (addr->sa_family == AF_INET6) { if (addr_len < SIN6_LEN_RFC2133) @@ -5925,7 +6000,8 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr, /* ipv6_bpf_stub cannot be NULL, since it's called from * bpf_cgroup_inet6_connect hook and ipv6 is already loaded */ - return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags); + return ipv6_bpf_stub->inet6_bind(sk, (struct sockaddr_unsized *)addr, + addr_len, flags); #endif /* CONFIG_IPV6 */ } #endif /* CONFIG_INET */ @@ -8073,6 +8149,20 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_get_cg_sock_proto; case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; + case BPF_FUNC_setsockopt: + switch (prog->expected_attach_type) { + case BPF_CGROUP_INET_SOCK_CREATE: + return &bpf_sock_create_setsockopt_proto; + default: + return NULL; + } + case BPF_FUNC_getsockopt: + switch (prog->expected_attach_type) { + case BPF_CGROUP_INET_SOCK_CREATE: + return &bpf_sock_create_getsockopt_proto; + default: + return NULL; + } default: return bpf_base_func_proto(func_id, prog); } @@ -12026,6 +12116,18 @@ void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset) return skb_metadata_end(skb) - skb_metadata_len(skb) + offset; } +int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset, + const void *from, u32 len, u64 flags) +{ + if (unlikely(flags)) + return -EINVAL; + if (unlikely(bpf_try_make_writable(skb, 0))) + return -EFAULT; + + memmove(bpf_skb_meta_pointer(skb, offset), from, len); + return 0; +} + __bpf_kfunc_start_defs(); __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, struct bpf_dynptr *ptr__uninit) @@ -12053,9 +12155,6 @@ __bpf_kfunc int bpf_dynptr_from_skb(struct __sk_buff *s, u64 flags, * XDP context with bpf_xdp_adjust_meta(). Serves as an alternative to * &__sk_buff->data_meta. * - * If passed @skb_ is a clone which shares the data with the original, the - * dynptr will be read-only. This limitation may be lifted in the future. - * * Return: * * %0 - dynptr ready to use * * %-EINVAL - invalid flags, dynptr set to null @@ -12073,9 +12172,6 @@ __bpf_kfunc int bpf_dynptr_from_skb_meta(struct __sk_buff *skb_, u64 flags, bpf_dynptr_init(ptr, skb, BPF_DYNPTR_TYPE_SKB_META, 0, skb_metadata_len(skb)); - if (skb_cloned(skb)) - bpf_dynptr_set_rdonly(ptr); - return 0; } diff --git a/net/core/hotdata.c b/net/core/hotdata.c index 95d0a4df10069..dddd5c287cf08 100644 --- a/net/core/hotdata.c +++ b/net/core/hotdata.c @@ -20,7 +20,7 @@ struct net_hotdata net_hotdata __cacheline_aligned = { .dev_tx_weight = 64, .dev_rx_weight = 64, .sysctl_max_skb_frags = MAX_SKB_FRAGS, - .sysctl_skb_defer_max = 64, + .sysctl_skb_defer_max = 128, .sysctl_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE }; EXPORT_SYMBOL(net_hotdata); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index bddfa389effa7..96a3b1a93252a 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -81,7 +81,7 @@ static struct hlist_head *neigh_get_dev_table(struct net_device *dev, int family } /* - Neighbour hash table buckets are protected with rwlock tbl->lock. + Neighbour hash table buckets are protected with tbl->lock. - All the scans/updates to hash buckets MUST be made under this lock. - NOTHING clever should be made under this lock: no callbacks @@ -149,7 +149,7 @@ static void neigh_update_gc_list(struct neighbour *n) { bool on_gc_list, exempt_from_gc; - write_lock_bh(&n->tbl->lock); + spin_lock_bh(&n->tbl->lock); write_lock(&n->lock); if (n->dead) goto out; @@ -172,14 +172,14 @@ static void neigh_update_gc_list(struct neighbour *n) } out: write_unlock(&n->lock); - write_unlock_bh(&n->tbl->lock); + spin_unlock_bh(&n->tbl->lock); } static void neigh_update_managed_list(struct neighbour *n) { bool on_managed_list, add_to_managed; - write_lock_bh(&n->tbl->lock); + spin_lock_bh(&n->tbl->lock); write_lock(&n->lock); if (n->dead) goto out; @@ -193,7 +193,7 @@ static void neigh_update_managed_list(struct neighbour *n) list_add_tail(&n->managed_list, &n->tbl->managed_list); out: write_unlock(&n->lock); - write_unlock_bh(&n->tbl->lock); + spin_unlock_bh(&n->tbl->lock); } static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, @@ -263,7 +263,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); list_for_each_entry_safe(n, tmp, &tbl->gc_list, gc_list) { if (refcount_read(&n->refcnt) == 1) { @@ -292,7 +292,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) WRITE_ONCE(tbl->last_flush, jiffies); unlock: - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); return shrunk; } @@ -454,23 +454,23 @@ static void neigh_flush_table(struct neigh_table *tbl) void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev) { - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); neigh_flush_dev(tbl, dev, false); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); } EXPORT_SYMBOL(neigh_changeaddr); static int __neigh_ifdown(struct neigh_table *tbl, struct net_device *dev, bool skip_perm) { - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); if (likely(dev)) { neigh_flush_dev(tbl, dev, skip_perm); } else { DEBUG_NET_WARN_ON_ONCE(skip_perm); neigh_flush_table(tbl); } - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); pneigh_ifdown(tbl, dev, skip_perm); pneigh_queue_purge(&tbl->proxy_queue, dev ? dev_net(dev) : NULL, @@ -687,7 +687,7 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, n->confirmed = jiffies - (NEIGH_VAR(n->parms, BASE_REACHABLE_TIME) << 1); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); @@ -722,13 +722,13 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, hlist_add_head_rcu(&n->dev_list, neigh_get_dev_table(dev, tbl->family)); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); neigh_dbg(2, "neigh %p is created\n", n); rc = n; out: return rc; out_tbl_unlock: - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); out_neigh_release: if (!exempt_from_gc) atomic_dec(&tbl->gc_entries); @@ -982,7 +982,7 @@ static void neigh_periodic_work(struct work_struct *work) NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); @@ -995,8 +995,7 @@ static void neigh_periodic_work(struct work_struct *work) WRITE_ONCE(tbl->last_rand, jiffies); list_for_each_entry(p, &tbl->parms_list, list) - p->reachable_time = - neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + neigh_set_reach_time(p); } if (atomic_read(&tbl->entries) < READ_ONCE(tbl->gc_thresh1)) @@ -1037,9 +1036,9 @@ static void neigh_periodic_work(struct work_struct *work) * It's fine to release lock here, even if hash table * grows while we are preempted. */ - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); cond_resched(); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); } @@ -1050,7 +1049,7 @@ static void neigh_periodic_work(struct work_struct *work) */ queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME) >> 1); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) @@ -1642,12 +1641,12 @@ static void neigh_managed_work(struct work_struct *work) managed_work.work); struct neighbour *neigh; - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); list_for_each_entry(neigh, &tbl->managed_list, managed_list) neigh_event_send_probe(neigh, NULL, false); queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, NEIGH_VAR(&tbl->parms, INTERVAL_PROBE_TIME_MS)); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); } static void neigh_proxy_process(struct timer_list *t) @@ -1749,8 +1748,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, if (p) { p->tbl = tbl; refcount_set(&p->refcnt, 1); - p->reachable_time = - neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + neigh_set_reach_time(p); p->qlen = 0; netdev_hold(dev, &p->dev_tracker, GFP_KERNEL); p->dev = dev; @@ -1763,9 +1761,9 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, return NULL; } - write_lock_bh(&tbl->lock); - list_add(&p->list, &tbl->parms.list); - write_unlock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); + list_add_rcu(&p->list, &tbl->parms.list); + spin_unlock_bh(&tbl->lock); neigh_parms_data_state_cleanall(p); } @@ -1785,10 +1783,12 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms) { if (!parms || parms == &tbl->parms) return; - write_lock_bh(&tbl->lock); - list_del(&parms->list); + + spin_lock_bh(&tbl->lock); + list_del_rcu(&parms->list); parms->dead = 1; - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); + netdev_put(parms->dev, &parms->dev_tracker); call_rcu(&parms->rcu_head, neigh_rcu_free_parms); } @@ -1810,8 +1810,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); - tbl->parms.reachable_time = - neigh_rand_reach_time(NEIGH_VAR(&tbl->parms, BASE_REACHABLE_TIME)); + neigh_set_reach_time(&tbl->parms); tbl->parms.qlen = 0; tbl->stats = alloc_percpu(struct neigh_statistics); @@ -1838,7 +1837,7 @@ void neigh_table_init(int index, struct neigh_table *tbl) else WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); - rwlock_init(&tbl->lock); + spin_lock_init(&tbl->lock); mutex_init(&tbl->phash_lock); INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); @@ -1981,10 +1980,10 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, err = __neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN, NETLINK_CB(skb).portid, extack); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); out: return err; @@ -2179,7 +2178,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) return -ENOBUFS; if ((parms->dev && - nla_put_u32(skb, NDTPA_IFINDEX, parms->dev->ifindex)) || + nla_put_u32(skb, NDTPA_IFINDEX, READ_ONCE(parms->dev->ifindex))) || nla_put_u32(skb, NDTPA_REFCNT, refcount_read(&parms->refcnt)) || nla_put_u32(skb, NDTPA_QUEUE_LENBYTES, NEIGH_VAR(parms, QUEUE_LEN_BYTES)) || @@ -2194,7 +2193,7 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) NEIGH_VAR(parms, MCAST_PROBES)) || nla_put_u32(skb, NDTPA_MCAST_REPROBES, NEIGH_VAR(parms, MCAST_REPROBES)) || - nla_put_msecs(skb, NDTPA_REACHABLE_TIME, parms->reachable_time, + nla_put_msecs(skb, NDTPA_REACHABLE_TIME, READ_ONCE(parms->reachable_time), NDTPA_PAD) || nla_put_msecs(skb, NDTPA_BASE_REACHABLE_TIME, NEIGH_VAR(parms, BASE_REACHABLE_TIME), NDTPA_PAD) || @@ -2231,8 +2230,6 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, return -EMSGSIZE; ndtmsg = nlmsg_data(nlh); - - read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; @@ -2258,11 +2255,9 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_proxy_qlen = READ_ONCE(tbl->proxy_queue.qlen), }; - rcu_read_lock(); nht = rcu_dereference(tbl->nht); ndc.ndtc_hash_rnd = nht->hash_rnd[0]; ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); - rcu_read_unlock(); if (nla_put(skb, NDTA_CONFIG, sizeof(ndc), &ndc)) goto nla_put_failure; @@ -2300,12 +2295,10 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, if (neightbl_fill_parms(skb, &tbl->parms) < 0) goto nla_put_failure; - read_unlock_bh(&tbl->lock); nlmsg_end(skb, nlh); return 0; nla_put_failure: - read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); return -EMSGSIZE; } @@ -2324,8 +2317,6 @@ static int neightbl_fill_param_info(struct sk_buff *skb, return -EMSGSIZE; ndtmsg = nlmsg_data(nlh); - - read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; @@ -2334,11 +2325,9 @@ static int neightbl_fill_param_info(struct sk_buff *skb, neightbl_fill_parms(skb, parms) < 0) goto errout; - read_unlock_bh(&tbl->lock); nlmsg_end(skb, nlh); return 0; errout: - read_unlock_bh(&tbl->lock); nlmsg_cancel(skb, nlh); return -EMSGSIZE; } @@ -2375,9 +2364,9 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct nlattr *tb[NDTA_MAX + 1]; struct neigh_table *tbl; struct ndtmsg *ndtmsg; - struct nlattr *tb[NDTA_MAX+1]; bool found = false; int err, tidx; @@ -2393,26 +2382,33 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, ndtmsg = nlmsg_data(nlh); + rcu_read_lock(); + for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { - tbl = rcu_dereference_rtnl(neigh_tables[tidx]); + tbl = rcu_dereference(neigh_tables[tidx]); if (!tbl) continue; + if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; + if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) { found = true; break; } } - if (!found) - return -ENOENT; + if (!found) { + rcu_read_unlock(); + err = -ENOENT; + goto errout; + } /* * We acquire tbl->lock to be nice to the periodic timers and * make sure they always see a consistent set of values. */ - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); if (tb[NDTA_PARMS]) { struct nlattr *tbp[NDTPA_MAX+1]; @@ -2475,8 +2471,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, * only be effective after the next time neigh_periodic_work * decides to recompute it (can be multiple minutes) */ - p->reachable_time = - neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + neigh_set_reach_time(p); break; case NDTPA_GC_STALETIME: NEIGH_VAR_SET(p, GC_STALETIME, @@ -2532,7 +2527,8 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, err = 0; errout_tbl_lock: - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); + rcu_read_unlock(); errout: return err; } @@ -2579,10 +2575,12 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) family = ((struct rtgenmsg *)nlmsg_data(nlh))->rtgen_family; + rcu_read_lock(); + for (tidx = 0; tidx < NEIGH_NR_TABLES; tidx++) { struct neigh_parms *p; - tbl = rcu_dereference_rtnl(neigh_tables[tidx]); + tbl = rcu_dereference(neigh_tables[tidx]); if (!tbl) continue; @@ -2596,7 +2594,7 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) nidx = 0; p = list_next_entry(&tbl->parms, list); - list_for_each_entry_from(p, &tbl->parms_list, list) { + list_for_each_entry_from_rcu(p, &tbl->parms_list, list) { if (!net_eq(neigh_parms_net(p), net)) continue; @@ -2616,6 +2614,8 @@ static int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) neigh_skip = 0; } out: + rcu_read_unlock(); + cb->args[0] = tidx; cb->args[1] = nidx; @@ -3127,14 +3127,14 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void rcu_read_lock(); nht = rcu_dereference(tbl->nht); - read_lock_bh(&tbl->lock); /* avoid resizes */ + spin_lock_bh(&tbl->lock); /* avoid resizes */ for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; neigh_for_each_in_bucket(n, &nht->hash_heads[chain]) cb(n, cookie); } - read_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); rcu_read_unlock(); } EXPORT_SYMBOL(neigh_for_each); @@ -3404,7 +3404,7 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl rcu_read_lock(); state->nht = rcu_dereference(tbl->nht); - read_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } @@ -3444,7 +3444,7 @@ void neigh_seq_stop(struct seq_file *seq, void *v) struct neigh_seq_state *state = seq->private; struct neigh_table *tbl = state->tbl; - read_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); rcu_read_unlock(); } EXPORT_SYMBOL(neigh_seq_stop); @@ -3721,8 +3721,7 @@ static int neigh_proc_base_reachable_time(const struct ctl_table *ctl, int write * only be effective after the next time neigh_periodic_work * decides to recompute it */ - p->reachable_time = - neigh_rand_reach_time(NEIGH_VAR(p, BASE_REACHABLE_TIME)); + neigh_set_reach_time(p); } return ret; } @@ -3918,8 +3917,10 @@ static const struct rtnl_msg_handler neigh_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_DELNEIGH, .doit = neigh_delete}, {.msgtype = RTM_GETNEIGH, .doit = neigh_get, .dumpit = neigh_dump_info, .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, - {.msgtype = RTM_GETNEIGHTBL, .dumpit = neightbl_dump_info}, - {.msgtype = RTM_SETNEIGHTBL, .doit = neightbl_set}, + {.msgtype = RTM_GETNEIGHTBL, .dumpit = neightbl_dump_info, + .flags = RTNL_FLAG_DUMP_UNLOCKED}, + {.msgtype = RTM_SETNEIGHTBL, .doit = neightbl_set, + .flags = RTNL_FLAG_DOIT_UNLOCKED}, }; static int __init neigh_init(void) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b0e0f22d7b213..adcfef55a66f1 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -395,6 +395,7 @@ static __net_init void preinit_net_sysctl(struct net *net) net->core.sysctl_optmem_max = 128 * 1024; net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; net->core.sysctl_tstamp_allow_data = 1; + net->core.sysctl_txq_reselection = msecs_to_jiffies(1000); } /* init code that must occur even if setup_net() is not called. */ diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c index e9a2a6f26cb7d..ff20435c45d25 100644 --- a/net/core/netdev-genl-gen.c +++ b/net/core/netdev-genl-gen.c @@ -97,7 +97,7 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED [NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range), [NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, }, [NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, }, - [NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 1), + [NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 2), }; /* NETDEV_CMD_BIND_TX - do */ diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h index cd95394399b40..23175cb2bd866 100644 --- a/net/core/netmem_priv.h +++ b/net/core/netmem_priv.h @@ -5,19 +5,19 @@ static inline unsigned long netmem_get_pp_magic(netmem_ref netmem) { - return __netmem_clear_lsb(netmem)->pp_magic & ~PP_DMA_INDEX_MASK; + return netmem_to_nmdesc(netmem)->pp_magic & ~PP_DMA_INDEX_MASK; } static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic) { - __netmem_clear_lsb(netmem)->pp_magic |= pp_magic; + netmem_to_nmdesc(netmem)->pp_magic |= pp_magic; } static inline void netmem_clear_pp_magic(netmem_ref netmem) { - WARN_ON_ONCE(__netmem_clear_lsb(netmem)->pp_magic & PP_DMA_INDEX_MASK); + WARN_ON_ONCE(netmem_to_nmdesc(netmem)->pp_magic & PP_DMA_INDEX_MASK); - __netmem_clear_lsb(netmem)->pp_magic = 0; + netmem_to_nmdesc(netmem)->pp_magic = 0; } static inline bool netmem_is_pp(netmem_ref netmem) @@ -27,13 +27,13 @@ static inline bool netmem_is_pp(netmem_ref netmem) static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool) { - __netmem_clear_lsb(netmem)->pp = pool; + netmem_to_nmdesc(netmem)->pp = pool; } static inline void netmem_set_dma_addr(netmem_ref netmem, unsigned long dma_addr) { - __netmem_clear_lsb(netmem)->dma_addr = dma_addr; + netmem_to_nmdesc(netmem)->dma_addr = dma_addr; } static inline unsigned long netmem_get_dma_index(netmem_ref netmem) @@ -43,7 +43,7 @@ static inline unsigned long netmem_get_dma_index(netmem_ref netmem) if (WARN_ON_ONCE(netmem_is_net_iov(netmem))) return 0; - magic = __netmem_clear_lsb(netmem)->pp_magic; + magic = netmem_to_nmdesc(netmem)->pp_magic; return (magic & PP_DMA_INDEX_MASK) >> PP_DMA_INDEX_SHIFT; } @@ -57,6 +57,6 @@ static inline void netmem_set_dma_index(netmem_ref netmem, return; magic = netmem_get_pp_magic(netmem) | (id << PP_DMA_INDEX_SHIFT); - __netmem_clear_lsb(netmem)->pp_magic = magic; + netmem_to_nmdesc(netmem)->pp_magic = magic; } #endif diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 576d5ec3bb364..b1ed55141d8a7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1270,13 +1270,13 @@ static size_t rtnl_dpll_pin_size(const struct net_device *dev) static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { - return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + size_t size; + + size = NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(IFALIASZ) /* IFLA_IFALIAS */ + nla_total_size(IFNAMSIZ) /* IFLA_QDISC */ + nla_total_size_64bit(sizeof(struct rtnl_link_ifmap)) - + nla_total_size(sizeof(struct rtnl_link_stats)) - + nla_total_size_64bit(sizeof(struct rtnl_link_stats64)) + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_BROADCAST */ + nla_total_size(4) /* IFLA_TXQLEN */ @@ -1329,6 +1329,12 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(2) /* IFLA_HEADROOM */ + nla_total_size(2) /* IFLA_TAILROOM */ + 0; + + if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS)) + size += nla_total_size(sizeof(struct rtnl_link_stats)) + + nla_total_size_64bit(sizeof(struct rtnl_link_stats64)); + + return size; } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -2123,7 +2129,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, if (rtnl_phys_switch_id_fill(skb, dev)) goto nla_put_failure; - if (rtnl_fill_stats(skb, dev)) + if (!(ext_filter_mask & RTEXT_FILTER_SKIP_STATS) && + rtnl_fill_stats(skb, dev)) goto nla_put_failure; if (rtnl_fill_vf(skb, dev, ext_filter_mask)) diff --git a/net/core/selftests.c b/net/core/selftests.c index 3d79133a91a61..8b81feb82c4ae 100644 --- a/net/core/selftests.c +++ b/net/core/selftests.c @@ -14,46 +14,10 @@ #include #include -struct net_packet_attrs { - const unsigned char *src; - const unsigned char *dst; - u32 ip_src; - u32 ip_dst; - bool tcp; - u16 sport; - u16 dport; - int timeout; - int size; - int max_size; - u8 id; - u16 queue_mapping; - bool bad_csum; -}; - -struct net_test_priv { - struct net_packet_attrs *packet; - struct packet_type pt; - struct completion comp; - int double_vlan; - int vlan_id; - int ok; -}; - -struct netsfhdr { - __be32 version; - __be64 magic; - u8 id; -} __packed; - static u8 net_test_next_id; -#define NET_TEST_PKT_SIZE (sizeof(struct ethhdr) + sizeof(struct iphdr) + \ - sizeof(struct netsfhdr)) -#define NET_TEST_PKT_MAGIC 0xdeadcafecafedeadULL -#define NET_LB_TIMEOUT msecs_to_jiffies(200) - -static struct sk_buff *net_test_get_skb(struct net_device *ndev, - struct net_packet_attrs *attr) +struct sk_buff *net_test_get_skb(struct net_device *ndev, u8 id, + struct net_packet_attrs *attr) { struct sk_buff *skb = NULL; struct udphdr *uhdr = NULL; @@ -142,8 +106,8 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev, shdr = skb_put(skb, sizeof(*shdr)); shdr->version = 0; shdr->magic = cpu_to_be64(NET_TEST_PKT_MAGIC); - attr->id = net_test_next_id; - shdr->id = net_test_next_id++; + attr->id = id; + shdr->id = id; if (attr->size) { void *payload = skb_put(skb, attr->size); @@ -190,6 +154,7 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev, return skb; } +EXPORT_SYMBOL_GPL(net_test_get_skb); static int net_test_loopback_validate(struct sk_buff *skb, struct net_device *ndev, @@ -286,12 +251,13 @@ static int __net_test_loopback(struct net_device *ndev, tpriv->packet = attr; dev_add_pack(&tpriv->pt); - skb = net_test_get_skb(ndev, attr); + skb = net_test_get_skb(ndev, net_test_next_id, attr); if (!skb) { ret = -ENOMEM; goto cleanup; } + net_test_next_id++; ret = dev_direct_xmit(skb, attr->queue_mapping); if (ret < 0) { goto cleanup; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6be01454f262a..bda7e2196060f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -81,6 +81,7 @@ #include #include #include +#include #include #include @@ -274,17 +275,23 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) } EXPORT_SYMBOL(__netdev_alloc_frag_align); -static struct sk_buff *napi_skb_cache_get(void) +/* Cache kmem_cache_size(net_hotdata.skbuff_cache) to help the compiler + * remove dead code (and skbuff_cache_size) when CONFIG_KASAN is unset. + */ +static u32 skbuff_cache_size __read_mostly; + +static struct sk_buff *napi_skb_cache_get(bool alloc) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); struct sk_buff *skb; local_lock_nested_bh(&napi_alloc_cache.bh_lock); if (unlikely(!nc->skb_count)) { - nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, - GFP_ATOMIC | __GFP_NOWARN, - NAPI_SKB_CACHE_BULK, - nc->skb_cache); + if (alloc) + nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + GFP_ATOMIC | __GFP_NOWARN, + NAPI_SKB_CACHE_BULK, + nc->skb_cache); if (unlikely(!nc->skb_count)) { local_unlock_nested_bh(&napi_alloc_cache.bh_lock); return NULL; @@ -293,7 +300,7 @@ static struct sk_buff *napi_skb_cache_get(void) skb = nc->skb_cache[--nc->skb_count]; local_unlock_nested_bh(&napi_alloc_cache.bh_lock); - kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache)); + kasan_mempool_unpoison_object(skb, skbuff_cache_size); return skb; } @@ -345,11 +352,9 @@ u32 napi_skb_cache_get_bulk(void **skbs, u32 n) get: for (u32 base = nc->skb_count - n, i = 0; i < n; i++) { - u32 cache_size = kmem_cache_size(net_hotdata.skbuff_cache); - skbs[i] = nc->skb_cache[base + i]; - kasan_mempool_unpoison_object(skbs[i], cache_size); + kasan_mempool_unpoison_object(skbs[i], skbuff_cache_size); memset(skbs[i], 0, offsetof(struct sk_buff, tail)); } @@ -526,7 +531,7 @@ static struct sk_buff *__napi_build_skb(void *data, unsigned int frag_size) { struct sk_buff *skb; - skb = napi_skb_cache_get(); + skb = napi_skb_cache_get(true); if (unlikely(!skb)) return NULL; @@ -641,25 +646,36 @@ static void *kmalloc_reserve(unsigned int *size, gfp_t flags, int node, struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, int flags, int node) { + struct sk_buff *skb = NULL; struct kmem_cache *cache; - struct sk_buff *skb; bool pfmemalloc; u8 *data; - cache = (flags & SKB_ALLOC_FCLONE) - ? net_hotdata.skbuff_fclone_cache : net_hotdata.skbuff_cache; - if (sk_memalloc_socks() && (flags & SKB_ALLOC_RX)) gfp_mask |= __GFP_MEMALLOC; - /* Get the HEAD */ - if ((flags & (SKB_ALLOC_FCLONE | SKB_ALLOC_NAPI)) == SKB_ALLOC_NAPI && - likely(node == NUMA_NO_NODE || node == numa_mem_id())) - skb = napi_skb_cache_get(); - else + if (flags & SKB_ALLOC_FCLONE) { + cache = net_hotdata.skbuff_fclone_cache; + goto fallback; + } + cache = net_hotdata.skbuff_cache; + if (unlikely(node != NUMA_NO_NODE && node != numa_mem_id())) + goto fallback; + + if (flags & SKB_ALLOC_NAPI) { + skb = napi_skb_cache_get(true); + } else if (!in_hardirq() && !irqs_disabled()) { + local_bh_disable(); + skb = napi_skb_cache_get(false); + local_bh_enable(); + } + + if (!skb) { +fallback: skb = kmem_cache_alloc_node(cache, gfp_mask & ~GFP_DMA, node); - if (unlikely(!skb)) - return NULL; + if (unlikely(!skb)) + return NULL; + } prefetchw(skb); /* We do our best to align skb_shared_info on a separate cache @@ -1136,12 +1152,22 @@ void skb_release_head_state(struct sk_buff *skb) skb_dst_drop(skb); if (skb->destructor) { DEBUG_NET_WARN_ON_ONCE(in_hardirq()); - skb->destructor(skb); - } -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - nf_conntrack_put(skb_nfct(skb)); +#ifdef CONFIG_INET + INDIRECT_CALL_4(skb->destructor, + tcp_wfree, __sock_wfree, sock_wfree, + xsk_destruct_skb, + skb); +#else + INDIRECT_CALL_2(skb->destructor, + sock_wfree, xsk_destruct_skb, + skb); + #endif - skb_ext_put(skb); + skb->destructor = NULL; + skb->sk = NULL; + } + nf_reset_ct(skb); + skb_ext_reset(skb); } /* Free everything but the sk_buff shell. */ @@ -1428,7 +1454,7 @@ static void napi_skb_cache_put(struct sk_buff *skb) if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) { for (i = NAPI_SKB_CACHE_HALF; i < NAPI_SKB_CACHE_SIZE; i++) kasan_mempool_unpoison_object(nc->skb_cache[i], - kmem_cache_size(net_hotdata.skbuff_cache)); + skbuff_cache_size); kmem_cache_free_bulk(net_hotdata.skbuff_cache, NAPI_SKB_CACHE_HALF, nc->skb_cache + NAPI_SKB_CACHE_HALF); @@ -1465,6 +1491,11 @@ void napi_consume_skb(struct sk_buff *skb, int budget) DEBUG_NET_WARN_ON_ONCE(!in_softirq()); + if (skb->alloc_cpu != smp_processor_id() && !skb_shared(skb)) { + skb_release_head_state(skb); + return skb_attempt_defer_free(skb); + } + if (!skb_unref(skb)) return; @@ -2218,6 +2249,10 @@ EXPORT_SYMBOL(__pskb_copy_fclone); * * All the pointers pointing into skb header may change and must be * reloaded after call to this function. + * + * Note: If you skb_push() the start of the buffer after reallocating the + * header, call skb_postpush_data_move() first to move the metadata out of + * the way before writing to &sk_buff->data. */ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, @@ -2289,8 +2324,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb->nohdr = 0; atomic_set(&skb_shinfo(skb)->dataref, 1); - skb_metadata_clear(skb); - /* It is not generally safe to change skb->truesize. * For the moment, we really care of rx path, or * when skb is orphaned (not attached to a socket). @@ -5116,6 +5149,8 @@ void __init skb_init(void) offsetof(struct sk_buff, cb), sizeof_field(struct sk_buff, cb), NULL); + skbuff_cache_size = kmem_cache_size(net_hotdata.skbuff_cache); + net_hotdata.skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), 0, diff --git a/net/core/sock.c b/net/core/sock.c index dc03d4b5909a2..3b74fc71f51c1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -155,7 +155,7 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); -static void sock_def_write_space_wfree(struct sock *sk); +static void sock_def_write_space_wfree(struct sock *sk, int wmem_alloc); static void sock_def_write_space(struct sock *sk); /** @@ -1046,9 +1046,13 @@ static int sock_reserve_memory(struct sock *sk, int bytes) if (!charged) return -ENOMEM; + if (sk->sk_bypass_prot_mem) + goto success; + /* pre-charge to forward_alloc */ sk_memory_allocated_add(sk, pages); allocated = sk_memory_allocated(sk); + /* If the system goes into memory pressure with this * precharge, give up and return error. */ @@ -1057,6 +1061,8 @@ static int sock_reserve_memory(struct sock *sk, int bytes) mem_cgroup_sk_uncharge(sk, pages); return -ENOMEM; } + +success: sk_forward_alloc_add(sk, pages << PAGE_SHIFT); WRITE_ONCE(sk->sk_reserved_mem, @@ -2300,8 +2306,13 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, * why we need sk_prot_creator -acme */ sk->sk_prot = sk->sk_prot_creator = prot; + + if (READ_ONCE(net->core.sysctl_bypass_prot_mem)) + sk->sk_bypass_prot_mem = 1; + sk->sk_kern_sock = kern; sock_lock_init(sk); + sk->sk_net_refcnt = kern ? 0 : 1; if (likely(sk->sk_net_refcnt)) { get_net_track(net, &sk->ns_tracker, priority); @@ -2313,7 +2324,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, } sock_net_set(sk, net); - refcount_set(&sk->sk_wmem_alloc, 1); + refcount_set(&sk->sk_wmem_alloc, SK_WMEM_ALLOC_BIAS); mem_cgroup_sk_alloc(sk); cgroup_sk_alloc(&sk->sk_cgrp_data); @@ -2451,13 +2462,16 @@ static void sk_init_common(struct sock *sk) } /** - * sk_clone_lock - clone a socket, and lock its clone - * @sk: the socket to clone - * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * sk_clone - clone a socket + * @sk: the socket to clone + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * @lock: if true, lock the cloned sk * - * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + * If @lock is true, the clone is locked by bh_lock_sock(), and + * caller must unlock socket even in error path by bh_unlock_sock(). */ -struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) +struct sock *sk_clone(const struct sock *sk, const gfp_t priority, + bool lock) { struct proto *prot = READ_ONCE(sk->sk_prot); struct sk_filter *filter; @@ -2486,16 +2500,19 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) __netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker, false, priority); } + sk_node_init(&newsk->sk_node); sock_lock_init(newsk); - bh_lock_sock(newsk); + + if (lock) + bh_lock_sock(newsk); + newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; newsk->sk_backlog.len = 0; atomic_set(&newsk->sk_rmem_alloc, 0); - /* sk_wmem_alloc set to one (see sk_free() and sock_wfree()) */ - refcount_set(&newsk->sk_wmem_alloc, 1); + refcount_set(&newsk->sk_wmem_alloc, SK_WMEM_ALLOC_BIAS); atomic_set(&newsk->sk_omem_alloc, 0); sk_init_common(newsk); @@ -2580,12 +2597,13 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) * destructor and make plain sk_free() */ newsk->sk_destruct = NULL; - bh_unlock_sock(newsk); + if (lock) + bh_unlock_sock(newsk); sk_free(newsk); newsk = NULL; goto out; } -EXPORT_SYMBOL_GPL(sk_clone_lock); +EXPORT_SYMBOL_GPL(sk_clone); static u32 sk_dst_gso_max_size(struct sock *sk, const struct net_device *dev) { @@ -2649,16 +2667,18 @@ EXPORT_SYMBOL_GPL(sk_setup_caps); */ void sock_wfree(struct sk_buff *skb) { - struct sock *sk = skb->sk; unsigned int len = skb->truesize; + struct sock *sk = skb->sk; bool free; + int old; if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) { if (sock_flag(sk, SOCK_RCU_FREE) && sk->sk_write_space == sock_def_write_space) { rcu_read_lock(); - free = refcount_sub_and_test(len, &sk->sk_wmem_alloc); - sock_def_write_space_wfree(sk); + free = __refcount_sub_and_test(len, &sk->sk_wmem_alloc, + &old); + sock_def_write_space_wfree(sk, old - len); rcu_read_unlock(); if (unlikely(free)) __sk_free(sk); @@ -2695,6 +2715,8 @@ void __sock_wfree(struct sk_buff *skb) void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) { + int old_wmem; + skb_orphan(skb); #ifdef CONFIG_INET if (unlikely(!sk_fullsock(sk))) @@ -2708,7 +2730,15 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk) * is enough to guarantee sk_free() won't free this sock until * all in-flight packets are completed */ - refcount_add(skb->truesize, &sk->sk_wmem_alloc); + __refcount_add(skb->truesize, &sk->sk_wmem_alloc, &old_wmem); + + /* (old_wmem == SK_WMEM_ALLOC_BIAS) if no other TX packet for this socket + * is in a host queue (qdisc, NIC queue). + * Set skb->ooo_okay so that netdev_pick_tx() can choose a TX queue + * based on XPS for better performance. + * Otherwise clear ooo_okay to not risk Out Of Order delivery. + */ + skb->ooo_okay = (old_wmem == SK_WMEM_ALLOC_BIAS); } EXPORT_SYMBOL(skb_set_owner_w); @@ -3136,8 +3166,11 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag) if (likely(skb_page_frag_refill(32U, pfrag, sk->sk_allocation))) return true; - sk_enter_memory_pressure(sk); + if (!sk->sk_bypass_prot_mem) + sk_enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return false; } EXPORT_SYMBOL(sk_page_frag_refill); @@ -3254,10 +3287,12 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) { bool memcg_enabled = false, charged = false; struct proto *prot = sk->sk_prot; - long allocated; + long allocated = 0; - sk_memory_allocated_add(sk, amt); - allocated = sk_memory_allocated(sk); + if (!sk->sk_bypass_prot_mem) { + sk_memory_allocated_add(sk, amt); + allocated = sk_memory_allocated(sk); + } if (mem_cgroup_sk_enabled(sk)) { memcg_enabled = true; @@ -3266,6 +3301,9 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) goto suppress_allocation; } + if (!allocated) + return 1; + /* Under limit. */ if (allocated <= sk_prot_mem_limits(sk, 0)) { sk_leave_memory_pressure(sk); @@ -3344,7 +3382,8 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind) trace_sock_exceed_buf_limit(sk, prot, allocated, kind); - sk_memory_allocated_sub(sk, amt); + if (allocated) + sk_memory_allocated_sub(sk, amt); if (charged) mem_cgroup_sk_uncharge(sk, amt); @@ -3383,11 +3422,14 @@ EXPORT_SYMBOL(__sk_mem_schedule); */ void __sk_mem_reduce_allocated(struct sock *sk, int amount) { - sk_memory_allocated_sub(sk, amount); - if (mem_cgroup_sk_enabled(sk)) mem_cgroup_sk_uncharge(sk, amount); + if (sk->sk_bypass_prot_mem) + return; + + sk_memory_allocated_sub(sk, amount); + if (sk_under_global_memory_pressure(sk) && (sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0))) sk_leave_memory_pressure(sk); @@ -3420,13 +3462,13 @@ EXPORT_SYMBOL_GPL(sk_set_peek_off); * function, some default processing is provided. */ -int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) +int sock_no_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len) { return -EOPNOTSUPP; } EXPORT_SYMBOL(sock_no_bind); -int sock_no_connect(struct socket *sock, struct sockaddr *saddr, +int sock_no_connect(struct socket *sock, struct sockaddr_unsized *saddr, int len, int flags) { return -EOPNOTSUPP; @@ -3580,12 +3622,12 @@ static void sock_def_write_space(struct sock *sk) * for SOCK_RCU_FREE sockets under RCU read section and after putting * ->sk_wmem_alloc. */ -static void sock_def_write_space_wfree(struct sock *sk) +static void sock_def_write_space_wfree(struct sock *sk, int wmem_alloc) { /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if (sock_writeable(sk)) { + if (__sock_writeable(sk, wmem_alloc)) { struct socket_wq *wq = rcu_dereference(sk->sk_wq); /* rely on refcount_sub from sock_wfree() */ @@ -4353,7 +4395,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) EXPORT_SYMBOL(sk_busy_loop_end); #endif /* CONFIG_NET_RX_BUSY_POLL */ -int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) +int sock_bind_add(struct sock *sk, struct sockaddr_unsized *addr, int addr_len) { if (!sk->sk_prot->bind_add) return -EOPNOTSUPP; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 8cf04b57ade1e..8d4decb2606fa 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -667,6 +667,13 @@ static struct ctl_table netns_core_table[] = { .extra2 = SYSCTL_ONE, .proc_handler = proc_dou8vec_minmax, }, + { + .procname = "txq_reselection_ms", + .data = &init_net.core.sysctl_txq_reselection, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_ms_jiffies, + }, { .procname = "tstamp_allow_data", .data = &init_net.core.sysctl_tstamp_allow_data, @@ -676,6 +683,15 @@ static struct ctl_table netns_core_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, + { + .procname = "bypass_prot_mem", + .data = &init_net.core.sysctl_bypass_prot_mem, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE + }, /* sysctl_core_net_init() will set the values after this * to readonly in network namespaces */ diff --git a/net/devlink/dev.c b/net/devlink/dev.c index 02602704bdeaa..012211455f97f 100644 --- a/net/devlink/dev.c +++ b/net/devlink/dev.c @@ -701,6 +701,30 @@ int devlink_nl_eswitch_get_doit(struct sk_buff *skb, struct genl_info *info) return genlmsg_reply(msg, info); } +static void devlink_eswitch_notify(struct devlink *devlink) +{ + struct sk_buff *msg; + int err; + + WARN_ON(!devl_is_registered(devlink)); + + if (!devlink_nl_notify_need(devlink)) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_eswitch_fill(msg, devlink, DEVLINK_CMD_ESWITCH_SET, + 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + devlink_nl_notify_send(devlink, msg); +} + int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -742,6 +766,7 @@ int devlink_nl_eswitch_set_doit(struct sk_buff *skb, struct genl_info *info) return err; } + devlink_eswitch_notify(devlink); return 0; } diff --git a/net/devlink/netlink_gen.c b/net/devlink/netlink_gen.c index 9fd00977d59e3..5ad435aee29de 100644 --- a/net/devlink/netlink_gen.c +++ b/net/devlink/netlink_gen.c @@ -229,7 +229,7 @@ static const struct nla_policy devlink_eswitch_get_nl_policy[DEVLINK_ATTR_DEV_NA static const struct nla_policy devlink_eswitch_set_nl_policy[DEVLINK_ATTR_ESWITCH_ENCAP_MODE + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING, }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING, }, - [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 1), + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_MAX(NLA_U16, 2), [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = NLA_POLICY_MAX(NLA_U8, 3), [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = NLA_POLICY_MAX(NLA_U8, 1), }; diff --git a/net/devlink/param.c b/net/devlink/param.c index 70e69523412cb..6b233b13b69ae 100644 --- a/net/devlink/param.c +++ b/net/devlink/param.c @@ -112,6 +112,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_NUM_DOORBELLS_NAME, .type = DEVLINK_PARAM_GENERIC_NUM_DOORBELLS_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_MAX_MAC_PER_VF, + .name = DEVLINK_PARAM_GENERIC_MAX_MAC_PER_VF_NAME, + .type = DEVLINK_PARAM_GENERIC_MAX_MAC_PER_VF_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) diff --git a/net/devlink/region.c b/net/devlink/region.c index 63fb297f6d678..d6e5805cf3a09 100644 --- a/net/devlink/region.c +++ b/net/devlink/region.c @@ -50,7 +50,7 @@ devlink_port_region_get_by_name(struct devlink_port *port, struct devlink_region *region; list_for_each_entry(region, &port->region_list, list) - if (!strcmp(region->ops->name, region_name)) + if (!strcmp(region->port_ops->name, region_name)) return region; return NULL; diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index 869cbe57162f9..f86b30742122f 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -104,6 +104,14 @@ config NET_DSA_TAG_MTK Say Y or M if you want to enable support for tagging frames for Mediatek switches. +config NET_DSA_TAG_MXL_GSW1XX + tristate "Tag driver for MaxLinear GSW1xx switches" + help + The GSW1xx family of switches supports an 8-byte special tag which + can be used on the CPU port of the switch. + Say Y or M if you want to enable support for tagging frames for + MaxLinear GSW1xx switches. + config NET_DSA_TAG_KSZ tristate "Tag driver for Microchip 8795/937x/9477/9893 families of switches" help @@ -190,4 +198,10 @@ config NET_DSA_TAG_XRS700X Say Y or M if you want to enable support for tagging frames for Arrow SpeedChips XRS700x switches that use a single byte tag trailer. +config NET_DSA_TAG_YT921X + tristate "Tag driver for Motorcomm YT921x switches" + help + Say Y or M if you want to enable support for tagging frames for + Motorcomm YT921x switches. + endif diff --git a/net/dsa/Makefile b/net/dsa/Makefile index 555c07cfeb712..42d173f5a7013 100644 --- a/net/dsa/Makefile +++ b/net/dsa/Makefile @@ -28,6 +28,7 @@ obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o obj-$(CONFIG_NET_DSA_TAG_MTK) += tag_mtk.o +obj-$(CONFIG_NET_DSA_TAG_MXL_GSW1XX) += tag_mxl-gsw1xx.o obj-$(CONFIG_NET_DSA_TAG_NONE) += tag_none.o obj-$(CONFIG_NET_DSA_TAG_OCELOT) += tag_ocelot.o obj-$(CONFIG_NET_DSA_TAG_OCELOT_8021Q) += tag_ocelot_8021q.o @@ -39,6 +40,7 @@ obj-$(CONFIG_NET_DSA_TAG_SJA1105) += tag_sja1105.o obj-$(CONFIG_NET_DSA_TAG_TRAILER) += tag_trailer.o obj-$(CONFIG_NET_DSA_TAG_VSC73XX_8021Q) += tag_vsc73xx_8021q.o obj-$(CONFIG_NET_DSA_TAG_XRS700X) += tag_xrs700x.o +obj-$(CONFIG_NET_DSA_TAG_YT921X) += tag_yt921x.o # for tracing framework to find trace.h CFLAGS_trace.o := -I$(src) diff --git a/net/dsa/tag_mxl-gsw1xx.c b/net/dsa/tag_mxl-gsw1xx.c new file mode 100644 index 0000000000000..701a079955f2e --- /dev/null +++ b/net/dsa/tag_mxl-gsw1xx.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * DSA driver Special Tag support for MaxLinear GSW1xx switch chips + * + * Copyright (C) 2025 Daniel Golle + * Copyright (C) 2023 - 2024 MaxLinear Inc. + */ + +#include +#include +#include +#include + +#include "tag.h" + +/* To define the outgoing port and to discover the incoming port a special + * tag is used by the GSW1xx. + * + * Dest MAC Src MAC special TAG EtherType + * ...| 1 2 3 4 5 6 | 1 2 3 4 5 6 | 1 2 3 4 5 6 7 8 | 1 2 |... + * |<--------------->| + */ + +#define GSW1XX_TAG_NAME "gsw1xx" + +/* special tag header length (RX and TX) */ +#define GSW1XX_HEADER_LEN 8 + +/* Word 0 = Ethertype -> 0x88C3 */ + +/* Word 1 */ +#define GSW1XX_TX_PORT_MAP GENMASK(7, 0) +#define GSW1XX_TX_PORT_MAP_EN BIT(15) +#define GSW1XX_TX_CLASS_EN BIT(14) +#define GSW1XX_TX_TIME_STAMP_EN BIT(13) +#define GSW1XX_TX_LRN_DIS BIT(12) +#define GSW1XX_TX_CLASS GENMASK(11, 8) + +/* special tag in RX path header */ +/* Word 2 */ +#define GSW1XX_RX_PORT_MAP GENMASK(15, 8) + +static struct sk_buff *gsw1xx_tag_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct dsa_port *dp = dsa_user_to_port(dev); + __be16 *gsw1xx_tag; + + /* provide additional space 'GSW1XX_HEADER_LEN' bytes */ + skb_push(skb, GSW1XX_HEADER_LEN); + + /* add space between MAC address and Ethertype */ + dsa_alloc_etype_header(skb, GSW1XX_HEADER_LEN); + + /* special tag ingress */ + gsw1xx_tag = dsa_etype_header_pos_tx(skb); + gsw1xx_tag[0] = htons(ETH_P_MXLGSW); + gsw1xx_tag[1] = htons(GSW1XX_TX_PORT_MAP_EN | GSW1XX_TX_LRN_DIS | + FIELD_PREP(GSW1XX_TX_PORT_MAP, BIT(dp->index))); + + gsw1xx_tag[2] = 0; + gsw1xx_tag[3] = 0; + + return skb; +} + +static struct sk_buff *gsw1xx_tag_rcv(struct sk_buff *skb, + struct net_device *dev) +{ + int port; + __be16 *gsw1xx_tag; + + if (unlikely(!pskb_may_pull(skb, GSW1XX_HEADER_LEN))) { + dev_warn_ratelimited(&dev->dev, "Dropping packet, cannot pull SKB\n"); + return NULL; + } + + gsw1xx_tag = dsa_etype_header_pos_rx(skb); + + if (unlikely(ntohs(gsw1xx_tag[0]) != ETH_P_MXLGSW)) { + dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid special tag\n"); + dev_warn_ratelimited(&dev->dev, "Tag: %8ph\n", gsw1xx_tag); + return NULL; + } + + /* Get source port information */ + port = FIELD_GET(GSW1XX_RX_PORT_MAP, ntohs(gsw1xx_tag[1])); + skb->dev = dsa_conduit_find_user(dev, 0, port); + if (!skb->dev) { + dev_warn_ratelimited(&dev->dev, "Dropping packet due to invalid source port\n"); + dev_warn_ratelimited(&dev->dev, "Tag: %8ph\n", gsw1xx_tag); + return NULL; + } + + /* remove the GSW1xx special tag between MAC addresses and the current + * ethertype field. + */ + skb_pull_rcsum(skb, GSW1XX_HEADER_LEN); + dsa_strip_etype_header(skb, GSW1XX_HEADER_LEN); + + return skb; +} + +static const struct dsa_device_ops gsw1xx_netdev_ops = { + .name = GSW1XX_TAG_NAME, + .proto = DSA_TAG_PROTO_MXL_GSW1XX, + .xmit = gsw1xx_tag_xmit, + .rcv = gsw1xx_tag_rcv, + .needed_headroom = GSW1XX_HEADER_LEN, +}; + +MODULE_DESCRIPTION("DSA tag driver for MaxLinear GSW1xx 8 byte protocol"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_MXL_GSW1XX, GSW1XX_TAG_NAME); + +module_dsa_tag_driver(gsw1xx_netdev_ops); diff --git a/net/dsa/tag_yt921x.c b/net/dsa/tag_yt921x.c new file mode 100644 index 0000000000000..995da44f0a2a1 --- /dev/null +++ b/net/dsa/tag_yt921x.c @@ -0,0 +1,141 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Motorcomm YT921x Switch Extended CPU Port Tagging + * + * Copyright (c) 2025 David Yang + * + * +----+----+-------+-----+----+--------- + * | DA | SA | TagET | Tag | ET | Payload ... + * +----+----+-------+-----+----+--------- + * 6 6 2 6 2 N + * + * Tag Ethertype: CPU_TAG_TPID_TPID (default: ETH_P_YT921X = 0x9988) + * * Hardcoded for the moment, but still configurable. Discuss it if there + * are conflicts somewhere and/or you want to change it for some reason. + * Tag: + * 2: VLAN Tag + * 2: Rx Port + * 15b: Rx Port Valid + * 14b-11b: Rx Port + * 10b-0b: Cmd? + * 2: Tx Port(s) + * 15b: Tx Port(s) Valid + * 10b-0b: Tx Port(s) Mask + */ + +#include + +#include "tag.h" + +#define YT921X_TAG_NAME "yt921x" + +#define YT921X_TAG_LEN 8 + +#define YT921X_TAG_PORT_EN BIT(15) +#define YT921X_TAG_RX_PORT_M GENMASK(14, 11) +#define YT921X_TAG_RX_CMD_M GENMASK(10, 0) +#define YT921X_TAG_RX_CMD(x) FIELD_PREP(YT921X_TAG_RX_CMD_M, (x)) +#define YT921X_TAG_RX_CMD_FORWARDED 0x80 +#define YT921X_TAG_RX_CMD_UNK_UCAST 0xb2 +#define YT921X_TAG_RX_CMD_UNK_MCAST 0xb4 +#define YT921X_TAG_TX_PORTS_M GENMASK(10, 0) +#define YT921X_TAG_TX_PORTn(port) BIT(port) + +static struct sk_buff * +yt921x_tag_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + struct dsa_port *dp = dsa_user_to_port(netdev); + unsigned int port = dp->index; + __be16 *tag; + u16 tx; + + skb_push(skb, YT921X_TAG_LEN); + dsa_alloc_etype_header(skb, YT921X_TAG_LEN); + + tag = dsa_etype_header_pos_tx(skb); + + tag[0] = htons(ETH_P_YT921X); + /* VLAN tag unrelated when TX */ + tag[1] = 0; + tag[2] = 0; + tx = YT921X_TAG_PORT_EN | YT921X_TAG_TX_PORTn(port); + tag[3] = htons(tx); + + return skb; +} + +static struct sk_buff * +yt921x_tag_rcv(struct sk_buff *skb, struct net_device *netdev) +{ + unsigned int port; + __be16 *tag; + u16 cmd; + u16 rx; + + if (unlikely(!pskb_may_pull(skb, YT921X_TAG_LEN))) + return NULL; + + tag = dsa_etype_header_pos_rx(skb); + + if (unlikely(tag[0] != htons(ETH_P_YT921X))) { + dev_warn_ratelimited(&netdev->dev, + "Unexpected EtherType 0x%04x\n", + ntohs(tag[0])); + return NULL; + } + + /* Locate which port this is coming from */ + rx = ntohs(tag[2]); + if (unlikely((rx & YT921X_TAG_PORT_EN) == 0)) { + dev_warn_ratelimited(&netdev->dev, + "Unexpected rx tag 0x%04x\n", rx); + return NULL; + } + + port = FIELD_GET(YT921X_TAG_RX_PORT_M, rx); + skb->dev = dsa_conduit_find_user(netdev, 0, port); + if (unlikely(!skb->dev)) { + dev_warn_ratelimited(&netdev->dev, + "Couldn't decode source port %u\n", port); + return NULL; + } + + cmd = FIELD_GET(YT921X_TAG_RX_CMD_M, rx); + switch (cmd) { + case YT921X_TAG_RX_CMD_FORWARDED: + /* Already forwarded by hardware */ + dsa_default_offload_fwd_mark(skb); + break; + case YT921X_TAG_RX_CMD_UNK_UCAST: + case YT921X_TAG_RX_CMD_UNK_MCAST: + /* NOTE: hardware doesn't distinguish between TRAP (copy to CPU + * only) and COPY (forward and copy to CPU). In order to perform + * a soft switch, NEVER use COPY action in the switch driver. + */ + break; + default: + dev_warn_ratelimited(&netdev->dev, + "Unexpected rx cmd 0x%02x\n", cmd); + break; + } + + /* Remove YT921x tag and update checksum */ + skb_pull_rcsum(skb, YT921X_TAG_LEN); + dsa_strip_etype_header(skb, YT921X_TAG_LEN); + + return skb; +} + +static const struct dsa_device_ops yt921x_netdev_ops = { + .name = YT921X_TAG_NAME, + .proto = DSA_TAG_PROTO_YT921X, + .xmit = yt921x_tag_xmit, + .rcv = yt921x_tag_rcv, + .needed_headroom = YT921X_TAG_LEN, +}; + +MODULE_DESCRIPTION("DSA tag driver for Motorcomm YT921x switches"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_YT921X, YT921X_TAG_NAME); + +module_dsa_tag_driver(yt921x_netdev_ops); diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 1e493553b9777..629c10916670e 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -9,4 +9,4 @@ ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o mm.o \ module.o cmis_fw_update.o cmis_cdb.o pse-pd.o plca.o \ - phy.o tsconfig.o + phy.o tsconfig.o mse.o diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 55223ebc2a7e6..bd6417dfb362f 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -281,12 +281,35 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_DR8_2 8 #define __LINK_MODE_LANES_T1BRR 1 -#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ +#define __DEFINE_LINK_MODE_PARAMS_PAIRS(_speed, _type, _min_pairs, _pairs, _duplex, _medium) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ .speed = SPEED_ ## _speed, \ .lanes = __LINK_MODE_LANES_ ## _type, \ - .duplex = __DUPLEX_ ## _duplex \ + .min_pairs = _min_pairs, \ + .pairs = _pairs, \ + .duplex = __DUPLEX_ ## _duplex, \ + .mediums = BIT(ETHTOOL_LINK_MEDIUM_BASE ## _medium) \ } + +#define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex, _medium) \ + [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ + .speed = SPEED_ ## _speed, \ + .lanes = __LINK_MODE_LANES_ ## _type, \ + .min_pairs = 0, \ + .pairs = 0, \ + .duplex = __DUPLEX_ ## _duplex, \ + .mediums = BIT(ETHTOOL_LINK_MEDIUM_BASE ## _medium) \ + } +#define __DEFINE_LINK_MODE_PARAMS_MEDIUMS(_speed, _type, _duplex, _mediums) \ + [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ + .speed = SPEED_ ## _speed, \ + .lanes = __LINK_MODE_LANES_ ## _type, \ + .min_pairs = 0, \ + .pairs = 0, \ + .duplex = __DUPLEX_ ## _duplex, \ + .mediums = (_mediums) \ + } +#define __MED(_medium) (BIT(ETHTOOL_LINK_MEDIUM_BASE ## _medium)) #define __DUPLEX_Half DUPLEX_HALF #define __DUPLEX_Full DUPLEX_FULL #define __DEFINE_SPECIAL_MODE_PARAMS(_mode) \ @@ -294,138 +317,165 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); .speed = SPEED_UNKNOWN, \ .lanes = 0, \ .duplex = DUPLEX_UNKNOWN, \ + .mediums = BIT(ETHTOOL_LINK_MEDIUM_NONE), \ } const struct link_mode_info link_mode_params[] = { - __DEFINE_LINK_MODE_PARAMS(10, T, Half), - __DEFINE_LINK_MODE_PARAMS(10, T, Full), - __DEFINE_LINK_MODE_PARAMS(100, T, Half), - __DEFINE_LINK_MODE_PARAMS(100, T, Full), - __DEFINE_LINK_MODE_PARAMS(1000, T, Half), - __DEFINE_LINK_MODE_PARAMS(1000, T, Full), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T, 2, 4, Half, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T, 2, 4, Full, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(100, T, 2, 4, Half, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(100, T, 2, 4, Full, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(1000, T, 4, 4, Half, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(1000, T, 4, 4, Full, T), __DEFINE_SPECIAL_MODE_PARAMS(Autoneg), __DEFINE_SPECIAL_MODE_PARAMS(TP), __DEFINE_SPECIAL_MODE_PARAMS(AUI), __DEFINE_SPECIAL_MODE_PARAMS(MII), __DEFINE_SPECIAL_MODE_PARAMS(FIBRE), __DEFINE_SPECIAL_MODE_PARAMS(BNC), - __DEFINE_LINK_MODE_PARAMS(10000, T, Full), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10000, T, 4, 4, Full, T), __DEFINE_SPECIAL_MODE_PARAMS(Pause), __DEFINE_SPECIAL_MODE_PARAMS(Asym_Pause), - __DEFINE_LINK_MODE_PARAMS(2500, X, Full), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(2500, X, Full, + __MED(C) | __MED(S) | __MED(L)), __DEFINE_SPECIAL_MODE_PARAMS(Backplane), - __DEFINE_LINK_MODE_PARAMS(1000, KX, Full), - __DEFINE_LINK_MODE_PARAMS(10000, KX4, Full), - __DEFINE_LINK_MODE_PARAMS(10000, KR, Full), + __DEFINE_LINK_MODE_PARAMS(1000, KX, Full, K), + __DEFINE_LINK_MODE_PARAMS(10000, KX4, Full, K), + __DEFINE_LINK_MODE_PARAMS(10000, KR, Full, K), [ETHTOOL_LINK_MODE_10000baseR_FEC_BIT] = { .speed = SPEED_10000, .lanes = 1, .duplex = DUPLEX_FULL, }, - __DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full), - __DEFINE_LINK_MODE_PARAMS(20000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(40000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(40000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(40000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(40000, LR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(56000, LR4, Full), - __DEFINE_LINK_MODE_PARAMS(25000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(25000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(25000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(50000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(100000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(100000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(100000, LR4_ER4, Full), - __DEFINE_LINK_MODE_PARAMS(50000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(1000, X, Full), - __DEFINE_LINK_MODE_PARAMS(10000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(10000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(10000, LR, Full), - __DEFINE_LINK_MODE_PARAMS(10000, LRM, Full), - __DEFINE_LINK_MODE_PARAMS(10000, ER, Full), - __DEFINE_LINK_MODE_PARAMS(2500, T, Full), - __DEFINE_LINK_MODE_PARAMS(5000, T, Full), + __DEFINE_LINK_MODE_PARAMS(20000, MLD2, Full, MLD), + __DEFINE_LINK_MODE_PARAMS(20000, KR2, Full, K), + __DEFINE_LINK_MODE_PARAMS(40000, KR4, Full, K), + __DEFINE_LINK_MODE_PARAMS(40000, CR4, Full, C), + __DEFINE_LINK_MODE_PARAMS(40000, SR4, Full, S), + __DEFINE_LINK_MODE_PARAMS(40000, LR4, Full, L), + __DEFINE_LINK_MODE_PARAMS(56000, KR4, Full, K), + __DEFINE_LINK_MODE_PARAMS(56000, CR4, Full, C), + __DEFINE_LINK_MODE_PARAMS(56000, SR4, Full, S), + __DEFINE_LINK_MODE_PARAMS(56000, LR4, Full, L), + __DEFINE_LINK_MODE_PARAMS(25000, CR, Full, C), + __DEFINE_LINK_MODE_PARAMS(25000, KR, Full, K), + __DEFINE_LINK_MODE_PARAMS(25000, SR, Full, S), + __DEFINE_LINK_MODE_PARAMS(50000, CR2, Full, C), + __DEFINE_LINK_MODE_PARAMS(50000, KR2, Full, K), + __DEFINE_LINK_MODE_PARAMS(100000, KR4, Full, K), + __DEFINE_LINK_MODE_PARAMS(100000, SR4, Full, S), + __DEFINE_LINK_MODE_PARAMS(100000, CR4, Full, C), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(100000, LR4_ER4, Full, + __MED(L) | __MED(E)), + __DEFINE_LINK_MODE_PARAMS(50000, SR2, Full, S), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(1000, X, Full, + __MED(C) | __MED(S) | __MED(L)), + __DEFINE_LINK_MODE_PARAMS(10000, CR, Full, C), + __DEFINE_LINK_MODE_PARAMS(10000, SR, Full, S), + __DEFINE_LINK_MODE_PARAMS(10000, LR, Full, L), + __DEFINE_LINK_MODE_PARAMS(10000, LRM, Full, L), + __DEFINE_LINK_MODE_PARAMS(10000, ER, Full, E), + __DEFINE_LINK_MODE_PARAMS_PAIRS(2500, T, 4, 4, Full, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(5000, T, 4, 4, Full, T), __DEFINE_SPECIAL_MODE_PARAMS(FEC_NONE), __DEFINE_SPECIAL_MODE_PARAMS(FEC_RS), __DEFINE_SPECIAL_MODE_PARAMS(FEC_BASER), - __DEFINE_LINK_MODE_PARAMS(50000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, LR_ER_FR, Full), - __DEFINE_LINK_MODE_PARAMS(50000, DR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, LR2_ER2_FR2, Full), - __DEFINE_LINK_MODE_PARAMS(100000, DR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, LR4_ER4_FR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, DR4, Full), - __DEFINE_LINK_MODE_PARAMS(200000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(100, T1, Full), - __DEFINE_LINK_MODE_PARAMS(1000, T1, Full), - __DEFINE_LINK_MODE_PARAMS(400000, KR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, SR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, LR8_ER8_FR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full), - __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full), + __DEFINE_LINK_MODE_PARAMS(50000, KR, Full, K), + __DEFINE_LINK_MODE_PARAMS(50000, SR, Full, S), + __DEFINE_LINK_MODE_PARAMS(50000, CR, Full, C), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(50000, LR_ER_FR, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(50000, DR, Full, D), + __DEFINE_LINK_MODE_PARAMS(100000, KR2, Full, K), + __DEFINE_LINK_MODE_PARAMS(100000, SR2, Full, S), + __DEFINE_LINK_MODE_PARAMS(100000, CR2, Full, C), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(100000, LR2_ER2_FR2, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(100000, DR2, Full, D), + __DEFINE_LINK_MODE_PARAMS(200000, KR4, Full, K), + __DEFINE_LINK_MODE_PARAMS(200000, SR4, Full, S), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(200000, LR4_ER4_FR4, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(200000, DR4, Full, D), + __DEFINE_LINK_MODE_PARAMS(200000, CR4, Full, C), + __DEFINE_LINK_MODE_PARAMS_PAIRS(100, T1, 1, 1, Full, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(1000, T1, 1, 1, Full, T), + __DEFINE_LINK_MODE_PARAMS(400000, KR8, Full, K), + __DEFINE_LINK_MODE_PARAMS(400000, SR8, Full, S), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(400000, LR8_ER8_FR8, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(400000, DR8, Full, D), + __DEFINE_LINK_MODE_PARAMS(400000, CR8, Full, C), __DEFINE_SPECIAL_MODE_PARAMS(FEC_LLRS), - __DEFINE_LINK_MODE_PARAMS(100000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, LR_ER_FR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, DR, Full), - __DEFINE_LINK_MODE_PARAMS(100000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, LR2_ER2_FR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, DR2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, DR4, Full), - __DEFINE_LINK_MODE_PARAMS(400000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(100, FX, Half), - __DEFINE_LINK_MODE_PARAMS(100, FX, Full), - __DEFINE_LINK_MODE_PARAMS(10, T1L, Full), - __DEFINE_LINK_MODE_PARAMS(800000, CR8, Full), - __DEFINE_LINK_MODE_PARAMS(800000, KR8, Full), - __DEFINE_LINK_MODE_PARAMS(800000, DR8, Full), - __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full), - __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full), - __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full), - __DEFINE_LINK_MODE_PARAMS(10, T1S, Full), - __DEFINE_LINK_MODE_PARAMS(10, T1S, Half), - __DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half), - __DEFINE_LINK_MODE_PARAMS(10, T1BRR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, CR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, KR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, DR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, DR_2, Full), - __DEFINE_LINK_MODE_PARAMS(200000, SR, Full), - __DEFINE_LINK_MODE_PARAMS(200000, VR, Full), - __DEFINE_LINK_MODE_PARAMS(400000, CR2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, KR2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, DR2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, DR2_2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, SR2, Full), - __DEFINE_LINK_MODE_PARAMS(400000, VR2, Full), - __DEFINE_LINK_MODE_PARAMS(800000, CR4, Full), - __DEFINE_LINK_MODE_PARAMS(800000, KR4, Full), - __DEFINE_LINK_MODE_PARAMS(800000, DR4, Full), - __DEFINE_LINK_MODE_PARAMS(800000, DR4_2, Full), - __DEFINE_LINK_MODE_PARAMS(800000, SR4, Full), - __DEFINE_LINK_MODE_PARAMS(800000, VR4, Full), + __DEFINE_LINK_MODE_PARAMS(100000, KR, Full, K), + __DEFINE_LINK_MODE_PARAMS(100000, SR, Full, S), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(100000, LR_ER_FR, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(100000, DR, Full, D), + __DEFINE_LINK_MODE_PARAMS(100000, CR, Full, C), + __DEFINE_LINK_MODE_PARAMS(200000, KR2, Full, K), + __DEFINE_LINK_MODE_PARAMS(200000, SR2, Full, S), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(200000, LR2_ER2_FR2, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(200000, DR2, Full, D), + __DEFINE_LINK_MODE_PARAMS(200000, CR2, Full, C), + __DEFINE_LINK_MODE_PARAMS(400000, KR4, Full, K), + __DEFINE_LINK_MODE_PARAMS(400000, SR4, Full, S), + __DEFINE_LINK_MODE_PARAMS_MEDIUMS(400000, LR4_ER4_FR4, Full, + __MED(L) | __MED(E) | __MED(F)), + __DEFINE_LINK_MODE_PARAMS(400000, DR4, Full, D), + __DEFINE_LINK_MODE_PARAMS(400000, CR4, Full, C), + __DEFINE_LINK_MODE_PARAMS(100, FX, Half, F), + __DEFINE_LINK_MODE_PARAMS(100, FX, Full, F), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T1L, 1, 1, Full, T), + __DEFINE_LINK_MODE_PARAMS(800000, CR8, Full, C), + __DEFINE_LINK_MODE_PARAMS(800000, KR8, Full, K), + __DEFINE_LINK_MODE_PARAMS(800000, DR8, Full, D), + __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full, D), + __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full, S), + __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full, V), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T1S, 1, 1, Full, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T1S, 1, 1, Half, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T1S_P2MP, 1, 1, Half, T), + __DEFINE_LINK_MODE_PARAMS_PAIRS(10, T1BRR, 1, 1, Full, T), + __DEFINE_LINK_MODE_PARAMS(200000, CR, Full, C), + __DEFINE_LINK_MODE_PARAMS(200000, KR, Full, K), + __DEFINE_LINK_MODE_PARAMS(200000, DR, Full, D), + __DEFINE_LINK_MODE_PARAMS(200000, DR_2, Full, D), + __DEFINE_LINK_MODE_PARAMS(200000, SR, Full, S), + __DEFINE_LINK_MODE_PARAMS(200000, VR, Full, V), + __DEFINE_LINK_MODE_PARAMS(400000, CR2, Full, C), + __DEFINE_LINK_MODE_PARAMS(400000, KR2, Full, K), + __DEFINE_LINK_MODE_PARAMS(400000, DR2, Full, D), + __DEFINE_LINK_MODE_PARAMS(400000, DR2_2, Full, D), + __DEFINE_LINK_MODE_PARAMS(400000, SR2, Full, S), + __DEFINE_LINK_MODE_PARAMS(400000, VR2, Full, V), + __DEFINE_LINK_MODE_PARAMS(800000, CR4, Full, C), + __DEFINE_LINK_MODE_PARAMS(800000, KR4, Full, K), + __DEFINE_LINK_MODE_PARAMS(800000, DR4, Full, D), + __DEFINE_LINK_MODE_PARAMS(800000, DR4_2, Full, D), + __DEFINE_LINK_MODE_PARAMS(800000, SR4, Full, S), + __DEFINE_LINK_MODE_PARAMS(800000, VR4, Full, V), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); EXPORT_SYMBOL_GPL(link_mode_params); +const char ethtool_link_medium_names[][ETH_GSTRING_LEN] = { + [ETHTOOL_LINK_MEDIUM_BASET] = "BaseT", + [ETHTOOL_LINK_MEDIUM_BASEK] = "BaseK", + [ETHTOOL_LINK_MEDIUM_BASES] = "BaseS", + [ETHTOOL_LINK_MEDIUM_BASEC] = "BaseC", + [ETHTOOL_LINK_MEDIUM_BASEL] = "BaseL", + [ETHTOOL_LINK_MEDIUM_BASED] = "BaseD", + [ETHTOOL_LINK_MEDIUM_BASEE] = "BaseE", + [ETHTOOL_LINK_MEDIUM_BASEF] = "BaseF", + [ETHTOOL_LINK_MEDIUM_BASEV] = "BaseV", + [ETHTOOL_LINK_MEDIUM_BASEMLD] = "BaseMLD", + [ETHTOOL_LINK_MEDIUM_NONE] = "None", +}; +static_assert(ARRAY_SIZE(ethtool_link_medium_names) == __ETHTOOL_LINK_MEDIUM_LAST); +EXPORT_SYMBOL_GPL(ethtool_link_medium_names); + const char netif_msg_class_names[][ETH_GSTRING_LEN] = { [NETIF_MSG_DRV_BIT] = "drv", [NETIF_MSG_PROBE_BIT] = "probe", diff --git a/net/ethtool/mse.c b/net/ethtool/mse.c new file mode 100644 index 0000000000000..6aac004c3ffce --- /dev/null +++ b/net/ethtool/mse.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include + +#include "netlink.h" +#include "common.h" + +/* Channels A-D only; WORST and LINK are exclusive alternatives */ +#define PHY_MSE_CHANNEL_COUNT 4 + +struct mse_req_info { + struct ethnl_req_info base; +}; + +struct mse_snapshot_entry { + struct phy_mse_snapshot snapshot; + int channel; +}; + +struct mse_reply_data { + struct ethnl_reply_data base; + struct phy_mse_capability capability; + struct mse_snapshot_entry *snapshots; + unsigned int num_snapshots; +}; + +static struct mse_reply_data * +mse_repdata(const struct ethnl_reply_data *reply_base) +{ + return container_of(reply_base, struct mse_reply_data, base); +} + +const struct nla_policy ethnl_mse_get_policy[] = { + [ETHTOOL_A_MSE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy_phy), +}; + +static int get_snapshot_if_supported(struct phy_device *phydev, + struct mse_reply_data *data, + unsigned int *idx, u32 cap_bit, + enum phy_mse_channel channel) +{ + int ret; + + if (data->capability.supported_caps & cap_bit) { + ret = phydev->drv->get_mse_snapshot(phydev, channel, + &data->snapshots[*idx].snapshot); + if (ret) + return ret; + data->snapshots[*idx].channel = channel; + (*idx)++; + } + + return 0; +} + +static int mse_get_channels(struct phy_device *phydev, + struct mse_reply_data *data) +{ + unsigned int i = 0; + int ret; + + if (!data->capability.supported_caps) + return 0; + + data->snapshots = kcalloc(PHY_MSE_CHANNEL_COUNT, + sizeof(*data->snapshots), GFP_KERNEL); + if (!data->snapshots) + return -ENOMEM; + + /* Priority 1: Individual channels */ + ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_A, + PHY_MSE_CHANNEL_A); + if (ret) + return ret; + ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_B, + PHY_MSE_CHANNEL_B); + if (ret) + return ret; + ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_C, + PHY_MSE_CHANNEL_C); + if (ret) + return ret; + ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_CHANNEL_D, + PHY_MSE_CHANNEL_D); + if (ret) + return ret; + + /* If any individual channels were found, we are done. */ + if (i > 0) { + data->num_snapshots = i; + return 0; + } + + /* Priority 2: Worst channel, if no individual channels supported. */ + ret = get_snapshot_if_supported(phydev, data, &i, + PHY_MSE_CAP_WORST_CHANNEL, + PHY_MSE_CHANNEL_WORST); + if (ret) + return ret; + + /* If worst channel was found, we are done. */ + if (i > 0) { + data->num_snapshots = i; + return 0; + } + + /* Priority 3: Link-wide, if nothing else is supported. */ + ret = get_snapshot_if_supported(phydev, data, &i, PHY_MSE_CAP_LINK, + PHY_MSE_CHANNEL_LINK); + if (ret) + return ret; + + data->num_snapshots = i; + return 0; +} + +static int mse_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + const struct genl_info *info) +{ + struct mse_reply_data *data = mse_repdata(reply_base); + struct net_device *dev = reply_base->dev; + struct phy_device *phydev; + int ret; + + phydev = ethnl_req_get_phydev(req_base, info->attrs, + ETHTOOL_A_MSE_HEADER, info->extack); + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + if (!phydev) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret) + return ret; + + mutex_lock(&phydev->lock); + + if (!phydev->drv || !phydev->drv->get_mse_capability || + !phydev->drv->get_mse_snapshot) { + ret = -EOPNOTSUPP; + goto out_unlock; + } + if (!phydev->link) { + ret = -ENETDOWN; + goto out_unlock; + } + + ret = phydev->drv->get_mse_capability(phydev, &data->capability); + if (ret) + goto out_unlock; + + ret = mse_get_channels(phydev, data); + +out_unlock: + mutex_unlock(&phydev->lock); + ethnl_ops_complete(dev); + if (ret) + kfree(data->snapshots); + return ret; +} + +static void mse_cleanup_data(struct ethnl_reply_data *reply_base) +{ + struct mse_reply_data *data = mse_repdata(reply_base); + + kfree(data->snapshots); +} + +static int mse_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct mse_reply_data *data = mse_repdata(reply_base); + size_t len = 0; + unsigned int i; + + /* ETHTOOL_A_MSE_CAPABILITIES */ + len += nla_total_size(0); + if (data->capability.supported_caps & PHY_MSE_CAP_AVG) + /* ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE */ + len += nla_total_size(sizeof(u64)); + if (data->capability.supported_caps & (PHY_MSE_CAP_PEAK | + PHY_MSE_CAP_WORST_PEAK)) + /* ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE */ + len += nla_total_size(sizeof(u64)); + /* ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS */ + len += nla_total_size(sizeof(u64)); + /* ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS */ + len += nla_total_size(sizeof(u64)); + + for (i = 0; i < data->num_snapshots; i++) { + size_t snapshot_len = 0; + + /* Per-channel nest (e.g., ETHTOOL_A_MSE_CHANNEL_A / _B / _C / + * _D / _WORST_CHANNEL / _LINK) + */ + snapshot_len += nla_total_size(0); + + if (data->capability.supported_caps & PHY_MSE_CAP_AVG) + snapshot_len += nla_total_size(sizeof(u64)); + if (data->capability.supported_caps & PHY_MSE_CAP_PEAK) + snapshot_len += nla_total_size(sizeof(u64)); + if (data->capability.supported_caps & PHY_MSE_CAP_WORST_PEAK) + snapshot_len += nla_total_size(sizeof(u64)); + + len += snapshot_len; + } + + return len; +} + +static int mse_channel_to_attr(int ch) +{ + switch (ch) { + case PHY_MSE_CHANNEL_A: + return ETHTOOL_A_MSE_CHANNEL_A; + case PHY_MSE_CHANNEL_B: + return ETHTOOL_A_MSE_CHANNEL_B; + case PHY_MSE_CHANNEL_C: + return ETHTOOL_A_MSE_CHANNEL_C; + case PHY_MSE_CHANNEL_D: + return ETHTOOL_A_MSE_CHANNEL_D; + case PHY_MSE_CHANNEL_WORST: + return ETHTOOL_A_MSE_WORST_CHANNEL; + case PHY_MSE_CHANNEL_LINK: + return ETHTOOL_A_MSE_LINK; + default: + return -EINVAL; + } +} + +static int mse_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct mse_reply_data *data = mse_repdata(reply_base); + struct nlattr *nest; + unsigned int i; + int ret; + + nest = nla_nest_start(skb, ETHTOOL_A_MSE_CAPABILITIES); + if (!nest) + return -EMSGSIZE; + + if (data->capability.supported_caps & PHY_MSE_CAP_AVG) { + ret = nla_put_uint(skb, + ETHTOOL_A_MSE_CAPABILITIES_MAX_AVERAGE_MSE, + data->capability.max_average_mse); + if (ret < 0) + goto nla_put_nest_failure; + } + + if (data->capability.supported_caps & (PHY_MSE_CAP_PEAK | + PHY_MSE_CAP_WORST_PEAK)) { + ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_MAX_PEAK_MSE, + data->capability.max_peak_mse); + if (ret < 0) + goto nla_put_nest_failure; + } + + ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_REFRESH_RATE_PS, + data->capability.refresh_rate_ps); + if (ret < 0) + goto nla_put_nest_failure; + + ret = nla_put_uint(skb, ETHTOOL_A_MSE_CAPABILITIES_NUM_SYMBOLS, + data->capability.num_symbols); + if (ret < 0) + goto nla_put_nest_failure; + + nla_nest_end(skb, nest); + + for (i = 0; i < data->num_snapshots; i++) { + const struct mse_snapshot_entry *s = &data->snapshots[i]; + int chan_attr; + + chan_attr = mse_channel_to_attr(s->channel); + if (chan_attr < 0) + return chan_attr; + + nest = nla_nest_start(skb, chan_attr); + if (!nest) + return -EMSGSIZE; + + if (data->capability.supported_caps & PHY_MSE_CAP_AVG) { + ret = nla_put_uint(skb, + ETHTOOL_A_MSE_SNAPSHOT_AVERAGE_MSE, + s->snapshot.average_mse); + if (ret) + goto nla_put_nest_failure; + } + if (data->capability.supported_caps & PHY_MSE_CAP_PEAK) { + ret = nla_put_uint(skb, ETHTOOL_A_MSE_SNAPSHOT_PEAK_MSE, + s->snapshot.peak_mse); + if (ret) + goto nla_put_nest_failure; + } + if (data->capability.supported_caps & PHY_MSE_CAP_WORST_PEAK) { + ret = nla_put_uint(skb, + ETHTOOL_A_MSE_SNAPSHOT_WORST_PEAK_MSE, + s->snapshot.worst_peak_mse); + if (ret) + goto nla_put_nest_failure; + } + + nla_nest_end(skb, nest); + } + + return 0; + +nla_put_nest_failure: + nla_nest_cancel(skb, nest); + return ret; +} + +const struct ethnl_request_ops ethnl_mse_request_ops = { + .request_cmd = ETHTOOL_MSG_MSE_GET, + .reply_cmd = ETHTOOL_MSG_MSE_GET_REPLY, + .hdr_attr = ETHTOOL_A_MSE_HEADER, + .req_info_size = sizeof(struct mse_req_info), + .reply_data_size = sizeof(struct mse_reply_data), + + .prepare_data = mse_prepare_data, + .cleanup_data = mse_cleanup_data, + .reply_size = mse_reply_size, + .fill_reply = mse_fill_reply, +}; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 2f813f25f07e1..6e5f0f4f815a1 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -420,6 +420,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_TSCONFIG_GET] = ðnl_tsconfig_request_ops, [ETHTOOL_MSG_TSCONFIG_SET] = ðnl_tsconfig_request_ops, [ETHTOOL_MSG_PHY_GET] = ðnl_phy_request_ops, + [ETHTOOL_MSG_MSE_GET] = ðnl_mse_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1534,6 +1535,15 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_rss_delete_policy, .maxattr = ARRAY_SIZE(ethnl_rss_delete_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_MSE_GET, + .doit = ethnl_default_doit, + .start = ethnl_perphy_start, + .dumpit = ethnl_perphy_dumpit, + .done = ethnl_perphy_done, + .policy = ethnl_mse_get_policy, + .maxattr = ARRAY_SIZE(ethnl_mse_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 1d4f9ecb3d263..89010eaa67dfc 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -442,6 +442,7 @@ extern const struct ethnl_request_ops ethnl_plca_status_request_ops; extern const struct ethnl_request_ops ethnl_mm_request_ops; extern const struct ethnl_request_ops ethnl_phy_request_ops; extern const struct ethnl_request_ops ethnl_tsconfig_request_ops; +extern const struct ethnl_request_ops ethnl_mse_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -497,6 +498,7 @@ extern const struct nla_policy ethnl_module_fw_flash_act_policy[ETHTOOL_A_MODULE extern const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1]; extern const struct nla_policy ethnl_tsconfig_get_policy[ETHTOOL_A_TSCONFIG_HEADER + 1]; extern const struct nla_policy ethnl_tsconfig_set_policy[ETHTOOL_A_TSCONFIG_MAX + 1]; +extern const struct nla_policy ethnl_mse_get_policy[ETHTOOL_A_MSE_HEADER + 1]; int ethnl_set_features(struct sk_buff *skb, struct genl_info *info); int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info); diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index c96b63adf96ff..db0b0af7a6920 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -166,12 +166,20 @@ static int hsr_fill_info(struct sk_buff *skb, const struct net_device *dev) goto nla_put_failure; } + port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); + if (port) { + if (nla_put_u32(skb, IFLA_HSR_INTERLINK, port->dev->ifindex)) + goto nla_put_failure; + } + if (nla_put(skb, IFLA_HSR_SUPERVISION_ADDR, ETH_ALEN, hsr->sup_multicast_addr) || nla_put_u16(skb, IFLA_HSR_SEQ_NR, hsr->sequence_nr)) goto nla_put_failure; if (hsr->prot_version == PRP_V1) proto = HSR_PROTOCOL_PRP; + else if (nla_put_u8(skb, IFLA_HSR_VERSION, hsr->prot_version)) + goto nla_put_failure; if (nla_put_u8(skb, IFLA_HSR_PROTOCOL, proto)) goto nla_put_failure; diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 18d267921bb53..e542fbe113e7b 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -96,7 +96,7 @@ static int ieee802154_sock_sendmsg(struct socket *sock, struct msghdr *msg, return sk->sk_prot->sendmsg(sk, msg, len); } -static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr, +static int ieee802154_sock_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; @@ -107,7 +107,7 @@ static int ieee802154_sock_bind(struct socket *sock, struct sockaddr *uaddr, return sock_no_bind(sock, uaddr, addr_len); } -static int ieee802154_sock_connect(struct socket *sock, struct sockaddr *uaddr, +static int ieee802154_sock_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; @@ -193,7 +193,7 @@ static void raw_close(struct sock *sk, long timeout) sk_common_release(sk); } -static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) +static int raw_bind(struct sock *sk, struct sockaddr_unsized *_uaddr, int len) { struct ieee802154_addr addr; struct sockaddr_ieee802154 *uaddr = (struct sockaddr_ieee802154 *)_uaddr; @@ -227,7 +227,7 @@ static int raw_bind(struct sock *sk, struct sockaddr *_uaddr, int len) return err; } -static int raw_connect(struct sock *sk, struct sockaddr *uaddr, +static int raw_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { return -ENOTSUPP; @@ -485,7 +485,7 @@ static void dgram_close(struct sock *sk, long timeout) sk_common_release(sk); } -static int dgram_bind(struct sock *sk, struct sockaddr *uaddr, int len) +static int dgram_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int len) { struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; struct ieee802154_addr haddr; @@ -563,7 +563,7 @@ static int dgram_ioctl(struct sock *sk, int cmd, int *karg) } /* FIXME: autobind */ -static int dgram_connect(struct sock *sk, struct sockaddr *uaddr, +static int dgram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int len) { struct sockaddr_ieee802154 *addr = (struct sockaddr_ieee802154 *)uaddr; diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 12850a277251d..b71c22475c515 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -760,9 +760,7 @@ config TCP_AO config TCP_MD5SIG bool "TCP: MD5 Signature Option support (RFC2385)" - select CRYPTO - select CRYPTO_MD5 - select TCP_SIGPOOL + select CRYPTO_LIB_MD5 help RFC2385 specifies a method of giving MD5 protection to TCP sessions. Its main (only?) use is to protect BGP sessions between core routers diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 3109c5ec38f39..a31b94ce8968a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -441,7 +441,7 @@ int inet_release(struct socket *sock) } EXPORT_SYMBOL(inet_release); -int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int inet_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { u32 flags = BIND_WITH_LOCK; int err; @@ -464,13 +464,13 @@ int inet_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) return __inet_bind(sk, uaddr, addr_len, flags); } -int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { return inet_bind_sk(sock->sk, uaddr, addr_len); } EXPORT_SYMBOL(inet_bind); -int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, +int __inet_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; @@ -567,7 +567,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, return err; } -int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr, +int inet_dgram_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; @@ -623,7 +623,7 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias) * Connect to a remote host. There is regrettably still a little * TCP 'magic' in here. */ -int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, +int __inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags, int is_sendmsg) { struct sock *sk = sock->sk; @@ -741,7 +741,7 @@ int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, } EXPORT_SYMBOL(__inet_stream_connect); -int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr, +int inet_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { int err; @@ -755,6 +755,26 @@ EXPORT_SYMBOL(inet_stream_connect); void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *newsk) { + if (mem_cgroup_sockets_enabled) { + gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; + + mem_cgroup_sk_alloc(newsk); + + if (mem_cgroup_from_sk(newsk)) { + int amt; + + /* The socket has not been accepted yet, no need + * to look at newsk->sk_wmem_queued. + */ + amt = sk_mem_pages(newsk->sk_forward_alloc + + atomic_read(&newsk->sk_rmem_alloc)); + if (amt) + mem_cgroup_sk_charge(newsk, amt, gfp); + } + + kmem_cache_charge(newsk, gfp); + } + sock_rps_record_flow(newsk); WARN_ON(!((1 << newsk->sk_state) & (TCPF_ESTABLISHED | TCPF_SYN_RECV | @@ -768,6 +788,7 @@ void __inet_accept(struct socket *sock, struct socket *newsock, struct sock *new newsock->state = SS_CONNECTED; } +EXPORT_SYMBOL_GPL(__inet_accept); /* * Accept a pending connection. The TCP layer now gives BSD semantics. @@ -813,7 +834,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, } sin->sin_port = inet->inet_dport; sin->sin_addr.s_addr = inet->inet_daddr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, + BPF_CGROUP_RUN_SA_PROG(sk, sin, &sin_addr_len, CGROUP_INET4_GETPEERNAME); } else { __be32 addr = inet->inet_rcv_saddr; @@ -821,7 +842,7 @@ int inet_getname(struct socket *sock, struct sockaddr *uaddr, addr = inet->inet_saddr; sin->sin_port = inet->inet_sport; sin->sin_addr.s_addr = addr; - BPF_CGROUP_RUN_SA_PROG(sk, (struct sockaddr *)sin, &sin_addr_len, + BPF_CGROUP_RUN_SA_PROG(sk, sin, &sin_addr_len, CGROUP_INET4_GETSOCKNAME); } release_sock(sk); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 833f2cf97178e..7f3863daaa407 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1189,7 +1189,7 @@ static int arp_req_get(struct net *net, struct arpreq *r) read_lock_bh(&neigh->lock); memcpy(r->arp_ha.sa_data, neigh->ha, - min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); + min(dev->addr_len, sizeof(r->arp_ha.sa_data))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); @@ -1217,10 +1217,10 @@ int arp_invalidate(struct net_device *dev, __be32 ip, bool force) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN, 0); - write_lock_bh(&tbl->lock); + spin_lock_bh(&tbl->lock); neigh_release(neigh); neigh_remove_one(neigh); - write_unlock_bh(&tbl->lock); + spin_unlock_bh(&tbl->lock); } return err; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index c2b2cda1a7e50..1614593b6d727 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -16,7 +16,7 @@ #include #include -int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int __ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *) uaddr; @@ -84,7 +84,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len } EXPORT_SYMBOL(__ip4_datagram_connect); -int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int ip4_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { int res; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 1b7fb5d935edf..4abbec2f47ef5 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -582,6 +582,185 @@ static struct rtable *icmp_route_lookup(struct net *net, struct flowi4 *fl4, return ERR_PTR(err); } +struct icmp_ext_iio_addr4_subobj { + __be16 afi; + __be16 reserved; + __be32 addr4; +}; + +static unsigned int icmp_ext_iio_len(void) +{ + return sizeof(struct icmp_extobj_hdr) + + /* ifIndex */ + sizeof(__be32) + + /* Interface Address Sub-Object */ + sizeof(struct icmp_ext_iio_addr4_subobj) + + /* Interface Name Sub-Object. Length must be a multiple of 4 + * bytes. + */ + ALIGN(sizeof(struct icmp_ext_iio_name_subobj), 4) + + /* MTU */ + sizeof(__be32); +} + +static unsigned int icmp_ext_max_len(u8 ext_objs) +{ + unsigned int ext_max_len; + + ext_max_len = sizeof(struct icmp_ext_hdr); + + if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) + ext_max_len += icmp_ext_iio_len(); + + return ext_max_len; +} + +static __be32 icmp_ext_iio_addr4_find(const struct net_device *dev) +{ + struct in_device *in_dev; + struct in_ifaddr *ifa; + + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) + return 0; + + /* It is unclear from RFC 5837 which IP address should be chosen, but + * it makes sense to choose a global unicast address. + */ + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (READ_ONCE(ifa->ifa_flags) & IFA_F_SECONDARY) + continue; + if (ifa->ifa_scope != RT_SCOPE_UNIVERSE || + ipv4_is_multicast(ifa->ifa_address)) + continue; + return ifa->ifa_address; + } + + return 0; +} + +static void icmp_ext_iio_iif_append(struct net *net, struct sk_buff *skb, + int iif) +{ + struct icmp_ext_iio_name_subobj *name_subobj; + struct icmp_extobj_hdr *objh; + struct net_device *dev; + __be32 data; + + if (!iif) + return; + + /* Add the fields in the order specified by RFC 5837. */ + objh = skb_put(skb, sizeof(*objh)); + objh->class_num = ICMP_EXT_OBJ_CLASS_IIO; + objh->class_type = ICMP_EXT_CTYPE_IIO_ROLE(ICMP_EXT_CTYPE_IIO_ROLE_IIF); + + data = htonl(iif); + skb_put_data(skb, &data, sizeof(__be32)); + objh->class_type |= ICMP_EXT_CTYPE_IIO_IFINDEX; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, iif); + if (!dev) + goto out; + + data = icmp_ext_iio_addr4_find(dev); + if (data) { + struct icmp_ext_iio_addr4_subobj *addr4_subobj; + + addr4_subobj = skb_put_zero(skb, sizeof(*addr4_subobj)); + addr4_subobj->afi = htons(ICMP_AFI_IP); + addr4_subobj->addr4 = data; + objh->class_type |= ICMP_EXT_CTYPE_IIO_IPADDR; + } + + name_subobj = skb_put_zero(skb, ALIGN(sizeof(*name_subobj), 4)); + name_subobj->len = ALIGN(sizeof(*name_subobj), 4); + netdev_copy_name(dev, name_subobj->name); + objh->class_type |= ICMP_EXT_CTYPE_IIO_NAME; + + data = htonl(READ_ONCE(dev->mtu)); + skb_put_data(skb, &data, sizeof(__be32)); + objh->class_type |= ICMP_EXT_CTYPE_IIO_MTU; + +out: + rcu_read_unlock(); + objh->length = htons(skb_tail_pointer(skb) - (unsigned char *)objh); +} + +static void icmp_ext_objs_append(struct net *net, struct sk_buff *skb, + u8 ext_objs, int iif) +{ + if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) + icmp_ext_iio_iif_append(net, skb, iif); +} + +static struct sk_buff * +icmp_ext_append(struct net *net, struct sk_buff *skb_in, struct icmphdr *icmph, + unsigned int room, int iif) +{ + unsigned int payload_len, ext_max_len, ext_len; + struct icmp_ext_hdr *ext_hdr; + struct sk_buff *skb; + u8 ext_objs; + int nhoff; + + switch (icmph->type) { + case ICMP_DEST_UNREACH: + case ICMP_TIME_EXCEEDED: + case ICMP_PARAMETERPROB: + break; + default: + return NULL; + } + + ext_objs = READ_ONCE(net->ipv4.sysctl_icmp_errors_extension_mask); + if (!ext_objs) + return NULL; + + ext_max_len = icmp_ext_max_len(ext_objs); + if (ICMP_EXT_ORIG_DGRAM_MIN_LEN + ext_max_len > room) + return NULL; + + skb = skb_clone(skb_in, GFP_ATOMIC); + if (!skb) + return NULL; + + nhoff = skb_network_offset(skb); + payload_len = min(skb->len - nhoff, ICMP_EXT_ORIG_DGRAM_MIN_LEN); + + if (!pskb_network_may_pull(skb, payload_len)) + goto free_skb; + + if (pskb_trim(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN) || + __skb_put_padto(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN, false)) + goto free_skb; + + if (pskb_expand_head(skb, 0, ext_max_len, GFP_ATOMIC)) + goto free_skb; + + ext_hdr = skb_put_zero(skb, sizeof(*ext_hdr)); + ext_hdr->version = ICMP_EXT_VERSION_2; + + icmp_ext_objs_append(net, skb, ext_objs, iif); + + /* Do not send an empty extension structure. */ + ext_len = skb_tail_pointer(skb) - (unsigned char *)ext_hdr; + if (ext_len == sizeof(*ext_hdr)) + goto free_skb; + + ext_hdr->checksum = ip_compute_csum(ext_hdr, ext_len); + /* The length of the original datagram in 32-bit words (RFC 4884). */ + icmph->un.reserved[1] = ICMP_EXT_ORIG_DGRAM_MIN_LEN / sizeof(u32); + + return skb; + +free_skb: + consume_skb(skb); + return NULL; +} + /* * Send an ICMP message in response to a situation * @@ -601,6 +780,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, struct icmp_bxm icmp_param; struct rtable *rt = skb_rtable(skb_in); bool apply_ratelimit = false; + struct sk_buff *ext_skb; struct ipcm_cookie ipc; struct flowi4 fl4; __be32 saddr; @@ -770,7 +950,12 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, if (room <= (int)sizeof(struct iphdr)) goto ende; - icmp_param.data_len = skb_in->len - icmp_param.offset; + ext_skb = icmp_ext_append(net, skb_in, &icmp_param.data.icmph, room, + parm->iif); + if (ext_skb) + icmp_param.skb = ext_skb; + + icmp_param.data_len = icmp_param.skb->len - icmp_param.offset; if (icmp_param.data_len > room) icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); @@ -785,6 +970,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, trace_icmp_send(skb_in, type, code); icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt); + + if (ext_skb) + consume_skb(ext_skb); ende: ip_rt_put(rt); out_unlock: @@ -1502,6 +1690,7 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratelimit = 1 * HZ; net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; + net->ipv4.sysctl_icmp_errors_extension_mask = 0; net->ipv4.sysctl_icmp_msgs_per_sec = 1000; net->ipv4.sysctl_icmp_msgs_burst = 50; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index cdd1e12aac8c0..ea5fdbf05b055 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -20,6 +20,7 @@ #include #include #include +#include #include #include @@ -712,31 +713,6 @@ struct sock *inet_csk_accept(struct sock *sk, struct proto_accept_arg *arg) release_sock(sk); - if (mem_cgroup_sockets_enabled) { - gfp_t gfp = GFP_KERNEL | __GFP_NOFAIL; - int amt = 0; - - /* atomically get the memory usage, set and charge the - * newsk->sk_memcg. - */ - lock_sock(newsk); - - mem_cgroup_sk_alloc(newsk); - if (mem_cgroup_from_sk(newsk)) { - /* The socket has not been accepted yet, no need - * to look at newsk->sk_wmem_queued. - */ - amt = sk_mem_pages(newsk->sk_forward_alloc + - atomic_read(&newsk->sk_rmem_alloc)); - } - - if (amt) - mem_cgroup_sk_charge(newsk, amt, gfp); - kmem_cache_charge(newsk, gfp); - - release_sock(newsk); - } - if (req) reqsk_put(req); @@ -910,7 +886,6 @@ reqsk_alloc_noprof(const struct request_sock_ops *ops, struct sock *sk_listener, sk_tx_queue_clear(req_to_sk(req)); req->saved_syn = NULL; req->syncookie = 0; - req->timeout = 0; req->num_timeout = 0; req->num_retrans = 0; req->sk = NULL; @@ -938,7 +913,6 @@ struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops, ireq->ireq_state = TCP_NEW_SYN_RECV; write_pnet(&ireq->ireq_net, sock_net(sk_listener)); ireq->ireq_family = sk_listener->sk_family; - req->timeout = TCP_TIMEOUT_INIT; } return req; @@ -1121,16 +1095,21 @@ static void reqsk_timer_handler(struct timer_list *t) young <<= 1; } } + syn_ack_recalc(req, max_syn_ack_retries, READ_ONCE(queue->rskq_defer_accept), &expire, &resend); - req->rsk_ops->syn_ack_timeout(req); + tcp_syn_ack_timeout(req); + if (!expire && (!resend || !tcp_rtx_synack(sk_listener, req) || inet_rsk(req)->acked)) { + if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) + tcp_accecn_fail_mode_set(tcp_sk(sk_listener), + TCP_ACCECN_ACE_FAIL_SEND); if (req->num_timeout++ == 0) atomic_dec(&queue->young); - mod_timer(&req->rsk_timer, jiffies + reqsk_timeout(req, TCP_RTO_MAX)); + mod_timer(&req->rsk_timer, jiffies + tcp_reqsk_timeout(req)); if (!nreq) return; @@ -1167,8 +1146,7 @@ static void reqsk_timer_handler(struct timer_list *t) reqsk_put(oreq); } -static bool reqsk_queue_hash_req(struct request_sock *req, - unsigned long timeout) +static bool reqsk_queue_hash_req(struct request_sock *req) { bool found_dup_sk = false; @@ -1176,8 +1154,9 @@ static bool reqsk_queue_hash_req(struct request_sock *req, return false; /* The timer needs to be setup after a successful insertion. */ + req->timeout = tcp_timeout_init((struct sock *)req); timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED); - mod_timer(&req->rsk_timer, jiffies + timeout); + mod_timer(&req->rsk_timer, jiffies + req->timeout); /* before letting lookups find us, make sure all req fields * are committed to memory and refcnt initialized. @@ -1187,10 +1166,9 @@ static bool reqsk_queue_hash_req(struct request_sock *req, return true; } -bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, - unsigned long timeout) +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req) { - if (!reqsk_queue_hash_req(req, timeout)) + if (!reqsk_queue_hash_req(req)) return false; inet_csk_reqsk_queue_added(sk); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index b7024e3d9ac3d..f5826ec4bcaa8 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -720,8 +720,11 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_nulls_del_node_init_rcu(osk); - } else if (found_dup_sk) { + ret = sk_nulls_replace_node_init_rcu(osk, sk); + goto unlock; + } + + if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -730,6 +733,7 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); +unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c96d61d08854f..d4c781a0667fe 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,12 +88,6 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) -{ - hlist_nulls_add_head_rcu(&tw->tw_node, list); -} - static void inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo) { __inet_twsk_schedule(tw, timeo, false); @@ -113,13 +107,12 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, { const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); - struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead, *bhead2; - /* Step 1: Put TW into bind hash. Original socket stays there too. - Note, that any socket with inet->num != 0 MUST be bound in - binding cache, even if it is closed. + /* Put TW into bind hash. Original socket stays there too. + * Note, that any socket with inet->num != 0 MUST be bound in + * binding cache, even if it is closed. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), inet->inet_num, hashinfo->bhash_size)]; @@ -141,19 +134,6 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, spin_lock(lock); - /* Step 2: Hash TW into tcp ehash chain */ - inet_twsk_add_node_rcu(tw, &ehead->chain); - - /* Step 3: Remove SK from hash chain */ - if (__sk_nulls_del_node_init_rcu(sk)) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - - - /* Ensure above writes are committed into memory before updating the - * refcount. - * Provides ordering vs later refcount_inc(). - */ - smp_wmb(); /* tw_refcnt is set to 3 because we have : * - one reference for bhash chain. * - one reference for ehash chain. @@ -163,6 +143,15 @@ void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw, */ refcount_set(&tw->tw_refcnt, 3); + /* Ensure tw_refcnt has been set before tw is published. + * smp_wmb() provides the necessary memory barrier to enforce this + * ordering. + */ + smp_wmb(); + + hlist_nulls_replace_init_rcu(&sk->sk_nulls_node, &tw->tw_node); + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + inet_twsk_schedule(tw, timeo); spin_unlock(lock); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 273578579a6b0..19d3141dad1f8 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -141,6 +141,8 @@ #include #include #include +#include +#include /* * Process Router Attention IP option (RFC 2113) @@ -317,8 +319,6 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, ip_hdr(hint)->tos == iph->tos; } -int tcp_v4_early_demux(struct sk_buff *skb); -enum skb_drop_reason udp_v4_early_demux(struct sk_buff *skb); static int ip_rcv_finish_core(struct net *net, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 5321c5801c64d..ad56588107cc8 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -286,7 +286,7 @@ void ping_close(struct sock *sk, long timeout) } EXPORT_IPV6_MOD_GPL(ping_close); -static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int ping_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from __ip4_datagram_connect() and @@ -301,7 +301,7 @@ static int ping_pre_connect(struct sock *sk, struct sockaddr *uaddr, /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, - struct sockaddr *uaddr, int addr_len) + struct sockaddr_unsized *uaddr, int addr_len) { struct net *net = sock_net(sk); if (sk->sk_family == AF_INET) { @@ -387,7 +387,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, return 0; } -static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) +static void ping_set_saddr(struct sock *sk, struct sockaddr_unsized *saddr) { if (saddr->sa_family == AF_INET) { struct inet_sock *isk = inet_sk(sk); @@ -407,7 +407,7 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr) * Moreover, we don't allow binding to multi- and broadcast addresses. */ -int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int ping_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct inet_sock *isk = inet_sk(sk); unsigned short snum; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index d54ebb7df966d..5998c4cc6f47b 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -697,7 +697,8 @@ static void raw_destroy(struct sock *sk) } /* This gets rid of all the nasties in af_inet. -DaveM */ -static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int raw_bind(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *addr = (struct sockaddr_in *) uaddr; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 24dbc603cc44d..bde49331dc077 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -47,7 +47,9 @@ static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX; static int tcp_plb_max_rounds = 31; static int tcp_plb_max_cong_thresh = 256; static unsigned int tcp_tw_reuse_delay_max = TCP_PAWS_MSL * MSEC_PER_SEC; -static int tcp_ecn_mode_max = 2; +static int tcp_ecn_mode_max = 5; +static u32 icmp_errors_extension_mask_all = + GENMASK_U8(ICMP_ERR_EXT_COUNT - 1, 0); /* obsolete */ static int sysctl_tcp_low_latency __read_mostly; @@ -674,6 +676,15 @@ static struct ctl_table ipv4_net_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE }, + { + .procname = "icmp_errors_extension_mask", + .data = &init_net.ipv4.sysctl_icmp_errors_extension_mask, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &icmp_errors_extension_mask_all, + }, { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, @@ -738,7 +749,7 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dou8vec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_TWO, + .extra2 = SYSCTL_THREE, }, { .procname = "tcp_ecn_option_beacon", @@ -1440,6 +1451,15 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, + { + .procname = "tcp_comp_sack_rtt_percent", + .data = &init_net.ipv4.sysctl_tcp_comp_sack_rtt_percent, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + .extra2 = SYSCTL_ONE_THOUSAND, + }, { .procname = "tcp_comp_sack_slack_ns", .data = &init_net.ipv4.sysctl_tcp_comp_sack_slack_ns, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a18aeca7ab07..ea28e6a73ec8e 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -243,7 +243,7 @@ #define pr_fmt(fmt) "TCP: " fmt -#include +#include #include #include #include @@ -253,7 +253,6 @@ #include #include #include -#include #include #include #include @@ -425,7 +424,6 @@ void tcp_md5_destruct_sock(struct sock *sk) tcp_clear_md5_list(sk); kfree(rcu_replace_pointer(tp->md5sig_info, NULL, 1)); static_branch_slow_dec_deferred(&tcp_md5_needed); - tcp_md5_release_sigpool(); } } EXPORT_IPV6_MOD_GPL(tcp_md5_destruct_sock); @@ -928,7 +926,8 @@ struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp, } __kfree_skb(skb); } else { - sk->sk_prot->enter_memory_pressure(sk); + if (!sk->sk_bypass_prot_mem) + tcp_enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); } return NULL; @@ -1062,7 +1061,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, } } flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0; - err = __inet_stream_connect(sk->sk_socket, uaddr, + err = __inet_stream_connect(sk->sk_socket, (struct sockaddr_unsized *)uaddr, msg->msg_namelen, flags, 1); /* fastopen_req could already be freed in __inet_stream_connect * if the connection times out or gets rst @@ -1557,8 +1556,10 @@ void __tcp_cleanup_rbuf(struct sock *sk, int copied) time_to_ack = true; } } - if (time_to_ack) + if (time_to_ack) { + tcp_mstamp_refresh(tp); tcp_send_ack(sk); + } } void tcp_cleanup_rbuf(struct sock *sk, int copied) @@ -3419,6 +3420,7 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_accecn_init_counters(tp); tp->prev_ecnfield = 0; tp->accecn_opt_tstamp = 0; + tp->pkts_acked_ewma = 0; if (icsk->icsk_ca_initialized && icsk->icsk_ca_ops->release) icsk->icsk_ca_ops->release(sk); memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); @@ -3583,9 +3585,12 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf, DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled); EXPORT_IPV6_MOD(tcp_tx_delay_enabled); -static void tcp_enable_tx_delay(void) +static void tcp_enable_tx_delay(struct sock *sk, int val) { - if (!static_branch_unlikely(&tcp_tx_delay_enabled)) { + struct tcp_sock *tp = tcp_sk(sk); + s32 delta = (val - tp->tcp_tx_delay) << 3; + + if (val && !static_branch_unlikely(&tcp_tx_delay_enabled)) { static int __tcp_tx_delay_enabled = 0; if (cmpxchg(&__tcp_tx_delay_enabled, 0, 1) == 0) { @@ -3593,6 +3598,22 @@ static void tcp_enable_tx_delay(void) pr_info("TCP_TX_DELAY enabled\n"); } } + /* If we change tcp_tx_delay on a live flow, adjust tp->srtt_us, + * tp->rtt_min, icsk_rto and sk->sk_pacing_rate. + * This is best effort. + */ + if (delta && sk->sk_state == TCP_ESTABLISHED) { + s64 srtt = (s64)tp->srtt_us + delta; + + tp->srtt_us = clamp_t(s64, srtt, 1, ~0U); + + /* Note: does not deal with non zero icsk_backoff */ + tcp_set_rto(sk); + + minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U); + + tcp_update_pacing_rate(sk); + } } /* When set indicates to always queue non-full frames. Later the user clears @@ -4119,8 +4140,12 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, tp->recvmsg_inq = val; break; case TCP_TX_DELAY: - if (val) - tcp_enable_tx_delay(); + /* tp->srtt_us is u32, and is shifted by 3 */ + if (val < 0 || val >= (1U << (31 - 3))) { + err = -EINVAL; + break; + } + tcp_enable_tx_delay(sk, val); WRITE_ONCE(tp->tcp_tx_delay, val); break; default: @@ -4815,52 +4840,45 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, EXPORT_IPV6_MOD(tcp_getsockopt); #ifdef CONFIG_TCP_MD5SIG -int tcp_md5_sigpool_id = -1; -EXPORT_IPV6_MOD_GPL(tcp_md5_sigpool_id); - -int tcp_md5_alloc_sigpool(void) +void tcp_md5_hash_skb_data(struct md5_ctx *ctx, const struct sk_buff *skb, + unsigned int header_len) { - size_t scratch_size; - int ret; + const unsigned int head_data_len = skb_headlen(skb) > header_len ? + skb_headlen(skb) - header_len : 0; + const struct skb_shared_info *shi = skb_shinfo(skb); + struct sk_buff *frag_iter; + unsigned int i; - scratch_size = sizeof(union tcp_md5sum_block) + sizeof(struct tcphdr); - ret = tcp_sigpool_alloc_ahash("md5", scratch_size); - if (ret >= 0) { - /* As long as any md5 sigpool was allocated, the return - * id would stay the same. Re-write the id only for the case - * when previously all MD5 keys were deleted and this call - * allocates the first MD5 key, which may return a different - * sigpool id than was used previously. - */ - WRITE_ONCE(tcp_md5_sigpool_id, ret); /* Avoids the compiler potentially being smart here */ - return 0; - } - return ret; -} + md5_update(ctx, (const u8 *)tcp_hdr(skb) + header_len, head_data_len); -void tcp_md5_release_sigpool(void) -{ - tcp_sigpool_release(READ_ONCE(tcp_md5_sigpool_id)); -} + for (i = 0; i < shi->nr_frags; ++i) { + const skb_frag_t *f = &shi->frags[i]; + u32 p_off, p_len, copied; + const void *vaddr; + struct page *p; -void tcp_md5_add_sigpool(void) -{ - tcp_sigpool_get(READ_ONCE(tcp_md5_sigpool_id)); + skb_frag_foreach_page(f, skb_frag_off(f), skb_frag_size(f), + p, p_off, p_len, copied) { + vaddr = kmap_local_page(p); + md5_update(ctx, vaddr + p_off, p_len); + kunmap_local(vaddr); + } + } + + skb_walk_frags(skb, frag_iter) + tcp_md5_hash_skb_data(ctx, frag_iter, 0); } +EXPORT_IPV6_MOD(tcp_md5_hash_skb_data); -int tcp_md5_hash_key(struct tcp_sigpool *hp, - const struct tcp_md5sig_key *key) +void tcp_md5_hash_key(struct md5_ctx *ctx, + const struct tcp_md5sig_key *key) { u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ - struct scatterlist sg; - - sg_init_one(&sg, key->key, keylen); - ahash_request_set_crypt(hp->req, &sg, NULL, keylen); /* We use data_race() because tcp_md5_do_add() might change * key->key under us */ - return data_race(crypto_ahash_update(hp->req)); + data_race(({ md5_update(ctx, key->key, keylen), 0; })); } EXPORT_IPV6_MOD(tcp_md5_hash_key); @@ -4871,19 +4889,16 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, int family, int l3index, const __u8 *hash_location) { /* This gets called for each TCP segment that has TCP-MD5 option. - * We have 3 drop cases: - * o No MD5 hash and one expected. - * o MD5 hash and we're not expecting one. - * o MD5 hash and its wrong. + * We have 2 drop cases: + * o An MD5 signature is present, but we're not expecting one. + * o The MD5 signature is wrong. */ const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; u8 newhash[16]; - int genhash; key = tcp_md5_do_lookup(sk, l3index, saddr, family); - - if (!key && hash_location) { + if (!key) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); trace_tcp_hash_md5_unexpected(sk, skb); return SKB_DROP_REASON_TCP_MD5UNEXPECTED; @@ -4894,11 +4909,10 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, * IPv4-mapped case. */ if (family == AF_INET) - genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); + tcp_v4_md5_hash_skb(newhash, key, NULL, skb); else - genhash = tp->af_specific->calc_md5_hash(newhash, key, - NULL, skb); - if (genhash || memcmp(hash_location, newhash, 16) != 0) { + tp->af_specific->calc_md5_hash(newhash, key, NULL, skb); + if (memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); trace_tcp_hash_md5_mismatch(sk, skb); return SKB_DROP_REASON_TCP_MD5FAILURE; @@ -5180,6 +5194,7 @@ static void __init tcp_struct_check(void) CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rate_interval_us); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, rcv_rtt_last_tsecr); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_ecn_bytes); + CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, pkts_acked_ewma); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, first_tx_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, delivered_mstamp); CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_rx, bytes_acked); diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index df758adbb445f..e9f6c77e06316 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -16,6 +16,7 @@ #include #include #include +#include #include static DEFINE_SPINLOCK(tcp_cong_list_lock); @@ -227,7 +228,7 @@ void tcp_assign_congestion_control(struct sock *sk) memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); else INET_ECN_dontxmit(sk); } @@ -257,7 +258,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); if (ca->flags & TCP_CONG_NEEDS_ECN) - INET_ECN_xmit(sk); + INET_ECN_xmit_ect_1_negotiation(sk); else INET_ECN_dontxmit(sk); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e4a979b75cc66..87ca6e3515b76 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -488,6 +488,10 @@ static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered, tcp_count_delivered_ce(tp, delivered); } +#define PKTS_ACKED_WEIGHT 6 +#define PKTS_ACKED_PREC 6 +#define ACK_COMP_THRESH 4 + /* Returns the ECN CE delta */ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, u32 delivered_pkts, u32 delivered_bytes, @@ -499,6 +503,7 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, u32 delta, safe_delta, d_ceb; bool opt_deltas_valid; u32 corrected_ace; + u32 ewma; /* Reordered ACK or uncertain due to lack of data to send and ts */ if (!(flag & (FLAG_FORWARD_PROGRESS | FLAG_TS_PROGRESS))) @@ -507,6 +512,18 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, opt_deltas_valid = tcp_accecn_process_option(tp, skb, delivered_bytes, flag); + if (delivered_pkts) { + if (!tp->pkts_acked_ewma) { + ewma = delivered_pkts << PKTS_ACKED_PREC; + } else { + ewma = tp->pkts_acked_ewma; + ewma = (((ewma << PKTS_ACKED_WEIGHT) - ewma) + + (delivered_pkts << PKTS_ACKED_PREC)) >> + PKTS_ACKED_WEIGHT; + } + tp->pkts_acked_ewma = min_t(u32, ewma, 0xFFFFU); + } + if (!(flag & FLAG_SLOWPATH)) { /* AccECN counter might overflow on large ACKs */ if (delivered_pkts <= TCP_ACCECN_CEP_ACE_MASK) @@ -555,7 +572,8 @@ static u32 __tcp_accecn_process(struct sock *sk, const struct sk_buff *skb, if (d_ceb < safe_delta * tp->mss_cache >> TCP_ACCECN_SAFETY_SHIFT) return delta; - } + } else if (tp->pkts_acked_ewma > (ACK_COMP_THRESH << PKTS_ACKED_PREC)) + return delta; return safe_delta; } @@ -937,9 +955,15 @@ void tcp_rcv_space_adjust(struct sock *sk) trace_tcp_rcv_space_adjust(sk); - tcp_mstamp_refresh(tp); + if (unlikely(!tp->rcv_rtt_est.rtt_us)) + return; + + /* We do not refresh tp->tcp_mstamp here. + * Some platforms have expensive ktime_get() implementations. + * Using the last cached value is enough for DRS. + */ time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); - if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) + if (time < (tp->rcv_rtt_est.rtt_us >> 3)) return; /* Number of bytes copied to user in last RTT */ @@ -1102,7 +1126,7 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->srtt_us = max(1U, srtt); } -static void tcp_update_pacing_rate(struct sock *sk) +void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u64 rate; @@ -1139,7 +1163,7 @@ static void tcp_update_pacing_rate(struct sock *sk) /* Calculate rto without backoff. This is the second half of Van Jacobson's * routine referred to above. */ -static void tcp_set_rto(struct sock *sk) +void tcp_set_rto(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); /* Old crap is replaced with new one. 8) @@ -4785,6 +4809,8 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq) static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + /* When the ACK path fails or drops most ACKs, the sender would * timeout and spuriously retransmit the same segment repeatedly. * If it seems our ACKs are not reaching the other side, @@ -4804,6 +4830,14 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb) /* Save last flowlabel after a spurious retrans. */ tcp_save_lrcv_flowlabel(sk, skb); #endif + /* Check DSACK info to detect that the previous ACK carrying the + * AccECN option was lost after the second retransmision, and then + * stop sending AccECN option in all subsequent ACKs. + */ + if (tcp_ecn_mode_accecn(tp) && + TCP_SKB_CB(skb)->seq == tp->duplicate_sack[0].start_seq && + tp->accecn_opt_sent) + tcp_accecn_fail_mode_set(tp, TCP_ACCECN_OPT_FAIL_SEND); } static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) @@ -5887,7 +5921,9 @@ static inline void tcp_data_snd_check(struct sock *sk) static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) { struct tcp_sock *tp = tcp_sk(sk); - unsigned long rtt, delay; + struct net *net = sock_net(sk); + unsigned long rtt; + u64 delay; /* More than one full frame received... */ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && @@ -5906,7 +5942,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) * Defer the ack until tcp_release_cb(). */ if (sock_owned_by_user_nocheck(sk) && - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_backlog_ack_defer)) { + READ_ONCE(net->ipv4.sysctl_tcp_backlog_ack_defer)) { set_bit(TCP_ACK_DEFERRED, &sk->sk_tsq_flags); return; } @@ -5921,7 +5957,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) } if (!tcp_is_sack(tp) || - tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)) + tp->compressed_ack >= READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_nr)) goto send_now; if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { @@ -5936,18 +5972,26 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) if (hrtimer_is_queued(&tp->compressed_ack_timer)) return; - /* compress ack timer : 5 % of rtt, but no more than tcp_comp_sack_delay_ns */ + /* compress ack timer : comp_sack_rtt_percent of rtt, + * but no more than tcp_comp_sack_delay_ns. + */ rtt = tp->rcv_rtt_est.rtt_us; if (tp->srtt_us && tp->srtt_us < rtt) rtt = tp->srtt_us; - delay = min_t(unsigned long, - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns), - rtt * (NSEC_PER_USEC >> 3)/20); + /* delay = (rtt >> 3) * NSEC_PER_USEC * comp_sack_rtt_percent / 100 + * -> + * delay = rtt * 1.25 * comp_sack_rtt_percent + */ + delay = (u64)(rtt + (rtt >> 2)) * + READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_rtt_percent); + + delay = min(delay, READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_delay_ns)); + sock_hold(sk); hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay), - READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns), + READ_ONCE(net->ipv4.sysctl_tcp_comp_sack_slack_ns), HRTIMER_MODE_REL_PINNED_SOFT); } @@ -6196,6 +6240,8 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, if (th->syn) { if (tcp_ecn_mode_accecn(tp)) { accecn_reflector = true; + tp->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & + INET_ECN_MASK; if (tp->rx_opt.accecn && tp->saw_accecn_opt < TCP_ACCECN_OPT_COUNTER_SEEN) { u8 saw_opt = tcp_accecn_option_init(skb, tp->rx_opt.accecn); @@ -6817,7 +6863,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_wl1 = TCP_SKB_CB(skb)->seq; tp->max_window = tp->snd_wnd; - tcp_ecn_rcv_syn(tp, th, skb); + tcp_ecn_rcv_syn(sk, th, skb); tcp_mtup_init(sk); tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -7222,7 +7268,8 @@ static void tcp_ecn_create_request(struct request_sock *req, u32 ecn_ok_dst; if (tcp_accecn_syn_requested(th) && - READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3) { + (READ_ONCE(net->ipv4.sysctl_tcp_ecn) >= 3 || + tcp_ca_needs_accecn(listen_sk))) { inet_rsk(req)->ecn_ok = 1; tcp_rsk(req)->accecn_ok = 1; tcp_rsk(req)->syn_ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & @@ -7525,15 +7572,11 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, sock_put(fastopen_sk); } else { tcp_rsk(req)->tfo_listener = false; - if (!want_cookie) { - req->timeout = tcp_timeout_init((struct sock *)req); - if (unlikely(!inet_csk_reqsk_queue_hash_add(sk, req, - req->timeout))) { - reqsk_free(req); - dst_release(dst); - return 0; - } - + if (!want_cookie && + unlikely(!inet_csk_reqsk_queue_hash_add(sk, req))) { + reqsk_free(req); + dst_release(dst); + return 0; } af_ops->send_synack(sk, dst, &fl, req, &foc, !want_cookie ? TCP_SYNACK_NORMAL : diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b1fcf3e4e1ce0..a7d9fec2950b9 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -53,6 +53,7 @@ #include #include #include +#include #include #include #include @@ -86,14 +87,13 @@ #include #include -#include -#include +#include #include #ifdef CONFIG_TCP_MD5SIG -static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, - __be32 daddr, __be32 saddr, const struct tcphdr *th); +static void tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif struct inet_hashinfo tcp_hashinfo; @@ -205,7 +205,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) } EXPORT_IPV6_MOD_GPL(tcp_twsk_unique); -static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from tcp_v4_connect() and intended to @@ -221,7 +221,7 @@ static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, } /* This will initiate an outgoing connection. */ -int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int tcp_v4_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_timewait_death_row *tcp_death_row; @@ -754,7 +754,6 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, struct tcp_md5sig_key *key = NULL; unsigned char newhash[16]; struct sock *sk1 = NULL; - int genhash; #endif u64 transmit_time = 0; struct sock *ctl_sk; @@ -840,11 +839,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb, if (!key) goto out; - - genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); - if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) + tcp_v4_md5_hash_skb(newhash, key, NULL, skb); + if (memcmp(md5_hash_location, newhash, 16) != 0) goto out; - } if (key) { @@ -1425,13 +1422,13 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { - if (tcp_md5_alloc_sigpool()) - return -ENOMEM; + if (fips_enabled) { + pr_warn_once("TCP-MD5 support is disabled due to FIPS\n"); + return -EOPNOTSUPP; + } - if (tcp_md5sig_info_add(sk, GFP_KERNEL)) { - tcp_md5_release_sigpool(); + if (tcp_md5sig_info_add(sk, GFP_KERNEL)) return -ENOMEM; - } if (!static_branch_inc(&tcp_md5_needed.key)) { struct tcp_md5sig_info *md5sig; @@ -1439,7 +1436,6 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); - tcp_md5_release_sigpool(); return -EUSERS; } } @@ -1456,12 +1452,9 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, struct tcp_sock *tp = tcp_sk(sk); if (!rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk))) { - tcp_md5_add_sigpool(); - if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) { - tcp_md5_release_sigpool(); + if (tcp_md5sig_info_add(sk, sk_gfp_mask(sk, GFP_ATOMIC))) return -ENOMEM; - } if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) { struct tcp_md5sig_info *md5sig; @@ -1470,7 +1463,6 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr, net_warn_ratelimited("Too many TCP-MD5 keys in the system\n"); rcu_assign_pointer(tp->md5sig_info, NULL); kfree_rcu(md5sig, rcu); - tcp_md5_release_sigpool(); return -EUSERS; } } @@ -1578,66 +1570,44 @@ static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, cmd.tcpm_key, cmd.tcpm_keylen); } -static int tcp_v4_md5_hash_headers(struct tcp_sigpool *hp, - __be32 daddr, __be32 saddr, - const struct tcphdr *th, int nbytes) +static void tcp_v4_md5_hash_headers(struct md5_ctx *ctx, + __be32 daddr, __be32 saddr, + const struct tcphdr *th, int nbytes) { - struct tcp4_pseudohdr *bp; - struct scatterlist sg; - struct tcphdr *_th; - - bp = hp->scratch; - bp->saddr = saddr; - bp->daddr = daddr; - bp->pad = 0; - bp->protocol = IPPROTO_TCP; - bp->len = cpu_to_be16(nbytes); - - _th = (struct tcphdr *)(bp + 1); - memcpy(_th, th, sizeof(*th)); - _th->check = 0; + struct { + struct tcp4_pseudohdr ip; + struct tcphdr tcp; + } h; - sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); - ahash_request_set_crypt(hp->req, &sg, NULL, - sizeof(*bp) + sizeof(*th)); - return crypto_ahash_update(hp->req); + h.ip.saddr = saddr; + h.ip.daddr = daddr; + h.ip.pad = 0; + h.ip.protocol = IPPROTO_TCP; + h.ip.len = cpu_to_be16(nbytes); + h.tcp = *th; + h.tcp.check = 0; + md5_update(ctx, (const u8 *)&h, sizeof(h.ip) + sizeof(h.tcp)); } -static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, - __be32 daddr, __be32 saddr, const struct tcphdr *th) +static noinline_for_stack void +tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + __be32 daddr, __be32 saddr, const struct tcphdr *th) { - struct tcp_sigpool hp; + struct md5_ctx ctx; - if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) - goto clear_hash_nostart; - - if (crypto_ahash_init(hp.req)) - goto clear_hash; - if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) - goto clear_hash; - if (tcp_md5_hash_key(&hp, key)) - goto clear_hash; - ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); - if (crypto_ahash_final(hp.req)) - goto clear_hash; - - tcp_sigpool_end(&hp); - return 0; - -clear_hash: - tcp_sigpool_end(&hp); -clear_hash_nostart: - memset(md5_hash, 0, 16); - return 1; + md5_init(&ctx); + tcp_v4_md5_hash_headers(&ctx, daddr, saddr, th, th->doff << 2); + tcp_md5_hash_key(&ctx, key); + md5_final(&ctx, md5_hash); } -int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, - const struct sock *sk, - const struct sk_buff *skb) +noinline_for_stack void +tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); - struct tcp_sigpool hp; __be32 saddr, daddr; + struct md5_ctx ctx; if (sk) { /* valid for establish/request sockets */ saddr = sk->sk_rcv_saddr; @@ -1648,30 +1618,11 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, daddr = iph->daddr; } - if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) - goto clear_hash_nostart; - - if (crypto_ahash_init(hp.req)) - goto clear_hash; - - if (tcp_v4_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) - goto clear_hash; - if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) - goto clear_hash; - if (tcp_md5_hash_key(&hp, key)) - goto clear_hash; - ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); - if (crypto_ahash_final(hp.req)) - goto clear_hash; - - tcp_sigpool_end(&hp); - return 0; - -clear_hash: - tcp_sigpool_end(&hp); -clear_hash_nostart: - memset(md5_hash, 0, 16); - return 1; + md5_init(&ctx); + tcp_v4_md5_hash_headers(&ctx, daddr, saddr, th, skb->len); + tcp_md5_hash_skb_data(&ctx, skb, th->doff << 2); + tcp_md5_hash_key(&ctx, key); + md5_final(&ctx, md5_hash); } EXPORT_IPV6_MOD(tcp_v4_md5_hash_skb); @@ -1709,7 +1660,6 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, - .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { @@ -3645,6 +3595,7 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; net->ipv4.sysctl_tcp_comp_sack_slack_ns = 100 * NSEC_PER_USEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; + net->ipv4.sysctl_tcp_comp_sack_rtt_percent = 33; net->ipv4.sysctl_tcp_backlog_ack_defer = 1; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 0; diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c index 52fe17167460f..976b56644a8a7 100644 --- a/net/ipv4/tcp_lp.c +++ b/net/ipv4/tcp_lp.c @@ -23,9 +23,9 @@ * Original Author: * Aleksandar Kuzmanovic * Available from: - * http://www.ece.rice.edu/~akuzma/Doc/akuzma/TCP-LP.pdf + * https://users.cs.northwestern.edu/~akuzma/doc/TCP-LP-ToN.pdf * Original implementation for 2.4.19: - * http://www-ece.rice.edu/networks/TCP-LP/ + * https://users.cs.northwestern.edu/~akuzma/rice/TCP-LP/linux/tcp-lp-linux.htm * * 2.6.x module Authors: * Wong Hoi Sing, Edison @@ -113,6 +113,8 @@ static void tcp_lp_init(struct sock *sk) /** * tcp_lp_cong_avoid * @sk: socket to avoid congesting + * @ack: current ack sequence number + * @acked: number of ACKed packets * * Implementation of cong_avoid. * Will only call newReno CA when away from inference. @@ -261,6 +263,7 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt) /** * tcp_lp_pkts_acked * @sk: socket requiring congestion avoidance calculations + * @sample: ACK sample containing timing and rate information * * Implementation of pkts_acked. * Deal with active drop under Early Congestion Indication. diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 2ec8c6f1cdccc..e6cbd4317fd52 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -312,7 +312,6 @@ static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw) return; if (!static_key_fast_inc_not_disabled(&tcp_md5_needed.key.key)) goto out_free; - tcp_md5_add_sigpool(); } return; out_free: @@ -406,7 +405,6 @@ void tcp_twsk_destructor(struct sock *sk) if (twsk->tw_md5_key) { kfree(twsk->tw_md5_key); static_branch_slow_dec_deferred(&tcp_md5_needed); - tcp_md5_release_sigpool(); } } #endif @@ -488,9 +486,10 @@ static void tcp_ecn_openreq_child(struct sock *sk, tp->accecn_opt_demand = 1; tcp_ecn_received_counters_payload(sk, skb); } else { - tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ? - TCP_ECN_MODE_RFC3168 : - TCP_ECN_DISABLED); + if (inet_rsk(req)->ecn_ok && !tcp_ca_no_fallback_rfc3168(sk)) + tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168); + else + tcp_ecn_mode_set(tp, TCP_ECN_DISABLED); } } @@ -716,7 +715,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * it can be estimated (approximately) * from another data. */ - tmp_opt.ts_recent_stamp = ktime_get_seconds() - reqsk_timeout(req, TCP_RTO_MAX) / HZ; + tmp_opt.ts_recent_stamp = ktime_get_seconds() - + tcp_reqsk_timeout(req) / HZ; paws_reject = tcp_paws_reject(&tmp_opt, th->rst); } } @@ -750,16 +750,35 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, */ if (!tcp_oow_rate_limited(sock_net(sk), skb, LINUX_MIB_TCPACKSKIPPEDSYNRECV, - &tcp_rsk(req)->last_oow_ack_time) && - - !tcp_rtx_synack(sk, req)) { - unsigned long expires = jiffies; - - expires += reqsk_timeout(req, TCP_RTO_MAX); - if (!fastopen) - mod_timer_pending(&req->rsk_timer, expires); - else - req->rsk_timer.expires = expires; + &tcp_rsk(req)->last_oow_ack_time)) { + if (tcp_rsk(req)->accecn_ok) { + u8 ect_rcv = TCP_SKB_CB(skb)->ip_dsfield & + INET_ECN_MASK; + + tcp_rsk(req)->syn_ect_rcv = ect_rcv; + if (tcp_accecn_ace(tcp_hdr(skb)) == 0x0) { + u8 fail_mode = TCP_ACCECN_ACE_FAIL_RECV; + + tcp_accecn_fail_mode_set(tcp_sk(sk), + fail_mode); + } + } + if (!tcp_rtx_synack(sk, req)) { + u8 fail_mode = TCP_ACCECN_ACE_FAIL_SEND; + unsigned long expires = jiffies; + + if (req->num_retrans > 1 && + tcp_rsk(req)->accecn_ok) + tcp_accecn_fail_mode_set(tcp_sk(sk), + fail_mode); + + expires += tcp_reqsk_timeout(req); + if (!fastopen) + mod_timer_pending(&req->rsk_timer, + expires); + else + req->rsk_timer.expires = expires; + } } return NULL; } diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c index 2cb93da93abc2..9bd710c7bc951 100644 --- a/net/ipv4/tcp_offload.c +++ b/net/ipv4/tcp_offload.c @@ -282,33 +282,6 @@ struct sk_buff *tcp_gro_lookup(struct list_head *head, struct tcphdr *th) return NULL; } -struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb) -{ - unsigned int thlen, hlen, off; - struct tcphdr *th; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*th); - th = skb_gro_header(skb, hlen, off); - if (unlikely(!th)) - return NULL; - - thlen = th->doff * 4; - if (thlen < sizeof(*th)) - return NULL; - - hlen = off + thlen; - if (!skb_gro_may_pull(skb, hlen)) { - th = skb_gro_header_slow(skb, hlen, off); - if (unlikely(!th)) - return NULL; - } - - skb_gro_pull(skb, thlen); - - return th; -} - struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, struct tcphdr *th) { @@ -330,8 +303,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb, goto out_check_final; th2 = tcp_hdr(p); - flush = (__force int)(flags & TCP_FLAG_CWR); - flush |= (__force int)((flags ^ tcp_flag_word(th2)) & + flush = (__force int)((flags ^ tcp_flag_word(th2)) & ~(TCP_FLAG_FIN | TCP_FLAG_PSH)); flush |= (__force int)(th->ack_seq ^ th2->ack_seq); for (i = sizeof(*th); i < thlen; i += 4) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b94efb3050d2f..63c7f448037aa 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include @@ -333,7 +334,8 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb, return; if (tcp_ecn_mode_accecn(tp)) { - if (!tcp_accecn_ace_fail_recv(tp)) + if (!tcp_accecn_ace_fail_recv(tp) && + !tcp_accecn_ace_fail_send(tp)) INET_ECN_xmit(sk); tcp_accecn_set_ace(tp, skb, th); skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ACCECN; @@ -711,9 +713,12 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, if (tp) { tp->accecn_minlen = 0; tp->accecn_opt_tstamp = tp->tcp_mstamp; + tp->accecn_opt_sent = 1; if (tp->accecn_opt_demand) tp->accecn_opt_demand--; } + } else if (tp) { + tp->accecn_opt_sent = 0; } if (unlikely(OPTION_SACK_ADVERTISE & options)) { @@ -802,34 +807,36 @@ static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp, mptcp_options_write(th, ptr, tp, opts); } -static void smc_set_option(const struct tcp_sock *tp, +static void smc_set_option(struct tcp_sock *tp, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) - if (static_branch_unlikely(&tcp_have_smc)) { - if (tp->syn_smc) { - if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { - opts->options |= OPTION_SMC; - *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; - } + if (static_branch_unlikely(&tcp_have_smc) && tp->syn_smc) { + tp->syn_smc = !!smc_call_hsbpf(1, tp, syn_option); + /* re-check syn_smc */ + if (tp->syn_smc && + *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } #endif } static void smc_set_option_cond(const struct tcp_sock *tp, - const struct inet_request_sock *ireq, + struct inet_request_sock *ireq, struct tcp_out_options *opts, unsigned int *remaining) { #if IS_ENABLED(CONFIG_SMC) - if (static_branch_unlikely(&tcp_have_smc)) { - if (tp->syn_smc && ireq->smc_ok) { - if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { - opts->options |= OPTION_SMC; - *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; - } + if (static_branch_unlikely(&tcp_have_smc) && tp->syn_smc && ireq->smc_ok) { + ireq->smc_ok = !!smc_call_hsbpf(1, tp, synack_option, ireq); + /* re-check smc_ok */ + if (ireq->smc_ok && + *remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) { + opts->options |= OPTION_SMC; + *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED; } } #endif @@ -1103,7 +1110,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (treq->accecn_ok && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option) && - req->num_timeout < 1 && remaining >= TCPOLEN_ACCECN_BASE) { + synack_type != TCP_SYNACK_RETRANS && remaining >= TCPOLEN_ACCECN_BASE) { opts->use_synack_ecn_bytes = 1; remaining -= tcp_options_fit_accecn(opts, 0, remaining); } @@ -1183,7 +1190,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb if (tcp_ecn_mode_accecn(tp)) { int ecn_opt = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_option); - if (ecn_opt && tp->saw_accecn_opt && !tcp_accecn_opt_fail_send(tp) && + if (ecn_opt && tp->saw_accecn_opt && + (ecn_opt >= TCP_ACCECN_OPTION_PERSIST || + !tcp_accecn_opt_fail_send(tp)) && (ecn_opt >= TCP_ACCECN_OPTION_FULL || tp->accecn_opt_demand || tcp_accecn_option_beacon_check(sk))) { opts->use_synack_ecn_bytes = 0; @@ -3568,12 +3577,15 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) tcp_retrans_try_collapse(sk, skb, avail_wnd); } - /* RFC3168, section 6.1.1.1. ECN fallback - * As AccECN uses the same SYN flags (+ AE), this check covers both - * cases. - */ - if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == TCPHDR_SYN_ECN) - tcp_ecn_clear_syn(sk, skb); + if (!tcp_ecn_mode_pending(tp) || icsk->icsk_retransmits > 1) { + /* RFC3168, section 6.1.1.1. ECN fallback + * As AccECN uses the same SYN flags (+ AE), this check + * covers both cases. + */ + if ((TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN_ECN) == + TCPHDR_SYN_ECN) + tcp_ecn_clear_syn(sk, skb); + } /* Update global and local TCP statistics. */ segs = tcp_skb_pcount(skb); @@ -3743,12 +3755,17 @@ void sk_forced_mem_schedule(struct sock *sk, int size) delta = size - sk->sk_forward_alloc; if (delta <= 0) return; + amt = sk_mem_pages(delta); sk_forward_alloc_add(sk, amt << PAGE_SHIFT); - sk_memory_allocated_add(sk, amt); if (mem_cgroup_sk_enabled(sk)) mem_cgroup_sk_charge(sk, amt, gfp_memcg_charge() | __GFP_NOFAIL); + + if (sk->sk_bypass_prot_mem) + return; + + sk_memory_allocated_add(sk, amt); } /* Send a FIN. The caller locks the socket for us. @@ -3910,6 +3927,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, switch (synack_type) { case TCP_SYNACK_NORMAL: + case TCP_SYNACK_RETRANS: skb_set_owner_edemux(skb, req_to_sk(req)); break; case TCP_SYNACK_COOKIE: @@ -3992,7 +4010,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, memset(th, 0, sizeof(struct tcphdr)); th->syn = 1; th->ack = 1; - tcp_ecn_make_synack(req, th); + tcp_ecn_make_synack(req, th, synack_type); th->source = htons(ireq->ir_num); th->dest = ireq->ir_rmt_port; skb->mark = ireq->ir_mark; @@ -4595,7 +4613,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); - res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, + res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_RETRANS, NULL); if (!res) { TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 2dd73a4e8e517..58b9d8af43219 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,6 +22,7 @@ #include #include #include +#include #include static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) @@ -458,7 +459,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) struct tcp_sock *tp = tcp_sk(sk); int max_retries; - req->rsk_ops->syn_ack_timeout(req); + tcp_syn_ack_timeout(req); /* Add one more retry for fastopen. * Paired with WRITE_ONCE() in tcp_sock_set_syncnt() @@ -479,6 +480,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) * it's not good to give up too easily. */ tcp_rtx_synack(sk, req); + if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) + tcp_accecn_fail_mode_set(tcp_sk(sk), TCP_ACCECN_ACE_FAIL_SEND); req->num_timeout++; tcp_update_rto_stats(sk); if (!tp->retrans_stamp) @@ -752,7 +755,6 @@ void tcp_syn_ack_timeout(const struct request_sock *req) __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); } -EXPORT_IPV6_MOD(tcp_syn_ack_timeout); void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 30dfbf73729da..ffe074cb58658 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2159,7 +2159,8 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, goto try_again; } -int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int udp_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { /* This check is replicated from __ip4_datagram_connect() and * intended to prevent BPF program called below from accessing bytes @@ -2172,7 +2173,8 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } EXPORT_IPV6_MOD(udp_pre_connect); -static int udp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int udp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { int res; diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c index 54386e06a8136..b1f667c52cb21 100644 --- a/net/ipv4/udp_tunnel_core.c +++ b/net/ipv4/udp_tunnel_core.c @@ -29,7 +29,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->local_ip; udp_addr.sin_port = cfg->local_udp_port; - err = kernel_bind(sock, (struct sockaddr *)&udp_addr, + err = kernel_bind(sock, (struct sockaddr_unsized *)&udp_addr, sizeof(udp_addr)); if (err < 0) goto error; @@ -38,7 +38,7 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, udp_addr.sin_family = AF_INET; udp_addr.sin_addr = cfg->peer_ip; udp_addr.sin_port = cfg->peer_udp_port; - err = kernel_connect(sock, (struct sockaddr *)&udp_addr, + err = kernel_connect(sock, (struct sockaddr_unsized *)&udp_addr, sizeof(udp_addr), 0); if (err < 0) goto error; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 40e9c336f6c55..b66217d1b2f82 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1324,7 +1324,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) __in6_ifa_put(ifp); } - if (ifp->flags & IFA_F_PERMANENT && !(ifp->flags & IFA_F_NOPREFIXROUTE)) + if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) action = check_cleanup_prefix_route(ifp, &expires); list_del_rcu(&ifp->if_list); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 1b0314644e0cc..b705751eb73c6 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -277,7 +277,7 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol, goto out; } -static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, +static int __inet6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len, u32 flags) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; @@ -438,7 +438,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, goto out; } -int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int inet6_bind_sk(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { u32 flags = BIND_WITH_LOCK; const struct proto *prot; @@ -465,7 +465,7 @@ int inet6_bind_sk(struct sock *sk, struct sockaddr *uaddr, int addr_len) } /* bind for INET6 API */ -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int inet6_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { return inet6_bind_sk(sock->sk, uaddr, addr_len); } @@ -960,6 +960,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.icmpv6_echo_ignore_multicast = 0; net->ipv6.sysctl.icmpv6_echo_ignore_anycast = 0; net->ipv6.sysctl.icmpv6_error_anycast_as_unicast = 0; + net->ipv6.sysctl.icmpv6_errors_extension_mask = 0; /* By default, rate limit error messages. * Except for pmtu discovery, it would break it. diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 33ebe93d80e3c..83e03176819ce 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -138,7 +138,7 @@ void ip6_datagram_release_cb(struct sock *sk) } EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); -int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, +int __ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; @@ -194,7 +194,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, sin.sin_port = usin->sin6_port; err = __ip4_datagram_connect(sk, - (struct sockaddr *) &sin, + (struct sockaddr_unsized *)&sin, sizeof(sin)); ipv4_connected: @@ -271,7 +271,7 @@ int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, } EXPORT_SYMBOL_GPL(__ip6_datagram_connect); -int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +int ip6_datagram_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { int res; @@ -282,7 +282,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } EXPORT_SYMBOL_GPL(ip6_datagram_connect); -int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr, +int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, uaddr); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 56c974cf75d15..5d2f90babaa5f 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -444,6 +444,193 @@ static int icmp6_iif(const struct sk_buff *skb) return icmp6_dev(skb)->ifindex; } +struct icmp6_ext_iio_addr6_subobj { + __be16 afi; + __be16 reserved; + struct in6_addr addr6; +}; + +static unsigned int icmp6_ext_iio_len(void) +{ + return sizeof(struct icmp_extobj_hdr) + + /* ifIndex */ + sizeof(__be32) + + /* Interface Address Sub-Object */ + sizeof(struct icmp6_ext_iio_addr6_subobj) + + /* Interface Name Sub-Object. Length must be a multiple of 4 + * bytes. + */ + ALIGN(sizeof(struct icmp_ext_iio_name_subobj), 4) + + /* MTU */ + sizeof(__be32); +} + +static unsigned int icmp6_ext_max_len(u8 ext_objs) +{ + unsigned int ext_max_len; + + ext_max_len = sizeof(struct icmp_ext_hdr); + + if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) + ext_max_len += icmp6_ext_iio_len(); + + return ext_max_len; +} + +static struct in6_addr *icmp6_ext_iio_addr6_find(const struct net_device *dev) +{ + struct inet6_dev *in6_dev; + struct inet6_ifaddr *ifa; + + in6_dev = __in6_dev_get(dev); + if (!in6_dev) + return NULL; + + /* It is unclear from RFC 5837 which IP address should be chosen, but + * it makes sense to choose a global unicast address. + */ + list_for_each_entry_rcu(ifa, &in6_dev->addr_list, if_list) { + if (ifa->flags & (IFA_F_TENTATIVE | IFA_F_DADFAILED)) + continue; + if (ipv6_addr_type(&ifa->addr) != IPV6_ADDR_UNICAST || + ipv6_addr_src_scope(&ifa->addr) != IPV6_ADDR_SCOPE_GLOBAL) + continue; + return &ifa->addr; + } + + return NULL; +} + +static void icmp6_ext_iio_iif_append(struct net *net, struct sk_buff *skb, + int iif) +{ + struct icmp_ext_iio_name_subobj *name_subobj; + struct icmp_extobj_hdr *objh; + struct net_device *dev; + struct in6_addr *addr6; + __be32 data; + + if (!iif) + return; + + /* Add the fields in the order specified by RFC 5837. */ + objh = skb_put(skb, sizeof(*objh)); + objh->class_num = ICMP_EXT_OBJ_CLASS_IIO; + objh->class_type = ICMP_EXT_CTYPE_IIO_ROLE(ICMP_EXT_CTYPE_IIO_ROLE_IIF); + + data = htonl(iif); + skb_put_data(skb, &data, sizeof(__be32)); + objh->class_type |= ICMP_EXT_CTYPE_IIO_IFINDEX; + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, iif); + if (!dev) + goto out; + + addr6 = icmp6_ext_iio_addr6_find(dev); + if (addr6) { + struct icmp6_ext_iio_addr6_subobj *addr6_subobj; + + addr6_subobj = skb_put_zero(skb, sizeof(*addr6_subobj)); + addr6_subobj->afi = htons(ICMP_AFI_IP6); + addr6_subobj->addr6 = *addr6; + objh->class_type |= ICMP_EXT_CTYPE_IIO_IPADDR; + } + + name_subobj = skb_put_zero(skb, ALIGN(sizeof(*name_subobj), 4)); + name_subobj->len = ALIGN(sizeof(*name_subobj), 4); + netdev_copy_name(dev, name_subobj->name); + objh->class_type |= ICMP_EXT_CTYPE_IIO_NAME; + + data = htonl(READ_ONCE(dev->mtu)); + skb_put_data(skb, &data, sizeof(__be32)); + objh->class_type |= ICMP_EXT_CTYPE_IIO_MTU; + +out: + rcu_read_unlock(); + objh->length = htons(skb_tail_pointer(skb) - (unsigned char *)objh); +} + +static void icmp6_ext_objs_append(struct net *net, struct sk_buff *skb, + u8 ext_objs, int iif) +{ + if (ext_objs & BIT(ICMP_ERR_EXT_IIO_IIF)) + icmp6_ext_iio_iif_append(net, skb, iif); +} + +static struct sk_buff * +icmp6_ext_append(struct net *net, struct sk_buff *skb_in, + struct icmp6hdr *icmp6h, unsigned int room, int iif) +{ + unsigned int payload_len, ext_max_len, ext_len; + struct icmp_ext_hdr *ext_hdr; + struct sk_buff *skb; + u8 ext_objs; + int nhoff; + + switch (icmp6h->icmp6_type) { + case ICMPV6_DEST_UNREACH: + case ICMPV6_TIME_EXCEED: + break; + default: + return NULL; + } + + /* Do not overwrite existing extensions. This can happen when we + * receive an ICMPv4 message with extensions from a tunnel and + * translate it to an ICMPv6 message towards an IPv6 host in the + * overlay network. + */ + if (icmp6h->icmp6_datagram_len) + return NULL; + + ext_objs = READ_ONCE(net->ipv6.sysctl.icmpv6_errors_extension_mask); + if (!ext_objs) + return NULL; + + ext_max_len = icmp6_ext_max_len(ext_objs); + if (ICMP_EXT_ORIG_DGRAM_MIN_LEN + ext_max_len > room) + return NULL; + + skb = skb_clone(skb_in, GFP_ATOMIC); + if (!skb) + return NULL; + + nhoff = skb_network_offset(skb); + payload_len = min(skb->len - nhoff, ICMP_EXT_ORIG_DGRAM_MIN_LEN); + + if (!pskb_network_may_pull(skb, payload_len)) + goto free_skb; + + if (pskb_trim(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN) || + __skb_put_padto(skb, nhoff + ICMP_EXT_ORIG_DGRAM_MIN_LEN, false)) + goto free_skb; + + if (pskb_expand_head(skb, 0, ext_max_len, GFP_ATOMIC)) + goto free_skb; + + ext_hdr = skb_put_zero(skb, sizeof(*ext_hdr)); + ext_hdr->version = ICMP_EXT_VERSION_2; + + icmp6_ext_objs_append(net, skb, ext_objs, iif); + + /* Do not send an empty extension structure. */ + ext_len = skb_tail_pointer(skb) - (unsigned char *)ext_hdr; + if (ext_len == sizeof(*ext_hdr)) + goto free_skb; + + ext_hdr->checksum = ip_compute_csum(ext_hdr, ext_len); + /* The length of the original datagram in 64-bit words (RFC 4884). */ + icmp6h->icmp6_datagram_len = ICMP_EXT_ORIG_DGRAM_MIN_LEN / sizeof(u64); + + return skb; + +free_skb: + consume_skb(skb); + return NULL; +} + /* * Send an ICMP message in response to a packet in error */ @@ -458,7 +645,9 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, struct ipv6_pinfo *np; const struct in6_addr *saddr = NULL; bool apply_ratelimit = false; + struct sk_buff *ext_skb; struct dst_entry *dst; + unsigned int room; struct icmp6hdr tmp_hdr; struct flowi6 fl6; struct icmpv6_msg msg; @@ -612,8 +801,13 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, msg.offset = skb_network_offset(skb); msg.type = type; - len = skb->len - msg.offset; - len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr)); + room = IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr); + ext_skb = icmp6_ext_append(net, skb, &tmp_hdr, room, parm->iif); + if (ext_skb) + msg.skb = ext_skb; + + len = msg.skb->len - msg.offset; + len = min_t(unsigned int, len, room); if (len < 0) { net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n", &hdr->saddr, &hdr->daddr); @@ -635,6 +829,8 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info, } out_dst_release: + if (ext_skb) + consume_skb(ext_skb); dst_release(dst); out_unlock: icmpv6_xmit_unlock(sk); @@ -1171,6 +1367,10 @@ int icmpv6_err_convert(u8 type, u8 code, int *err) EXPORT_SYMBOL(icmpv6_err_convert); #ifdef CONFIG_SYSCTL + +static u32 icmpv6_errors_extension_mask_all = + GENMASK_U8(ICMP_ERR_EXT_COUNT - 1, 0); + static struct ctl_table ipv6_icmp_table_template[] = { { .procname = "ratelimit", @@ -1216,6 +1416,15 @@ static struct ctl_table ipv6_icmp_table_template[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "errors_extension_mask", + .data = &init_net.ipv6.sysctl.icmpv6_errors_extension_mask, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &icmpv6_errors_extension_mask_all, + }, }; struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) @@ -1233,6 +1442,7 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net) table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast; table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr; table[5].data = &net->ipv6.sysctl.icmpv6_error_anycast_as_unicast; + table[6].data = &net->ipv6.sysctl.icmpv6_errors_extension_mask; } return table; } diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 02c16909f6182..2111af022d946 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1138,6 +1138,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_set_expires(iter, rt->expires); fib6_add_gc_list(iter); } + if (!(rt->fib6_flags & (RTF_ADDRCONF | RTF_PREFIX_RT))) { + iter->fib6_flags &= ~RTF_ADDRCONF; + iter->fib6_flags &= ~RTF_PREFIX_RT; + } if (rt->fib6_pmtu) fib6_metric_set(iter, RTAX_MTU, diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index a3ff575798dda..60d0be47a9f31 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -66,8 +66,8 @@ EXPORT_SYMBOL(ipv6_flowlabel_exclusive); fl != NULL; \ fl = rcu_dereference(fl->next)) -#define for_each_sk_fl_rcu(np, sfl) \ - for (sfl = rcu_dereference(np->ipv6_fl_list); \ +#define for_each_sk_fl_rcu(sk, sfl) \ + for (sfl = rcu_dereference(inet_sk(sk)->ipv6_fl_list); \ sfl != NULL; \ sfl = rcu_dereference(sfl->next)) @@ -262,12 +262,11 @@ static struct ip6_flowlabel *fl_intern(struct net *net, struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label) { struct ipv6_fl_socklist *sfl; - struct ipv6_pinfo *np = inet6_sk(sk); label &= IPV6_FLOWLABEL_MASK; rcu_read_lock(); - for_each_sk_fl_rcu(np, sfl) { + for_each_sk_fl_rcu(sk, sfl) { struct ip6_flowlabel *fl = sfl->fl; if (fl->label == label && atomic_inc_not_zero(&fl->users)) { @@ -283,16 +282,16 @@ EXPORT_SYMBOL_GPL(__fl6_sock_lookup); void fl6_free_socklist(struct sock *sk) { - struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_sock *inet = inet_sk(sk); struct ipv6_fl_socklist *sfl; - if (!rcu_access_pointer(np->ipv6_fl_list)) + if (!rcu_access_pointer(inet->ipv6_fl_list)) return; spin_lock_bh(&ip6_sk_fl_lock); - while ((sfl = rcu_dereference_protected(np->ipv6_fl_list, + while ((sfl = rcu_dereference_protected(inet->ipv6_fl_list, lockdep_is_held(&ip6_sk_fl_lock))) != NULL) { - np->ipv6_fl_list = sfl->next; + inet->ipv6_fl_list = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); @@ -470,16 +469,15 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, static int mem_check(struct sock *sk) { - struct ipv6_pinfo *np = inet6_sk(sk); - struct ipv6_fl_socklist *sfl; int room = FL_MAX_SIZE - atomic_read(&fl_size); + struct ipv6_fl_socklist *sfl; int count = 0; if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; rcu_read_lock(); - for_each_sk_fl_rcu(np, sfl) + for_each_sk_fl_rcu(sk, sfl) count++; rcu_read_unlock(); @@ -492,13 +490,15 @@ static int mem_check(struct sock *sk) return 0; } -static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, - struct ip6_flowlabel *fl) +static inline void fl_link(struct sock *sk, struct ipv6_fl_socklist *sfl, + struct ip6_flowlabel *fl) { + struct inet_sock *inet = inet_sk(sk); + spin_lock_bh(&ip6_sk_fl_lock); sfl->fl = fl; - sfl->next = np->ipv6_fl_list; - rcu_assign_pointer(np->ipv6_fl_list, sfl); + sfl->next = inet->ipv6_fl_list; + rcu_assign_pointer(inet->ipv6_fl_list, sfl); spin_unlock_bh(&ip6_sk_fl_lock); } @@ -520,7 +520,7 @@ int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, rcu_read_lock(); - for_each_sk_fl_rcu(np, sfl) { + for_each_sk_fl_rcu(sk, sfl) { if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) { spin_lock_bh(&ip6_fl_lock); freq->flr_label = sfl->fl->label; @@ -559,7 +559,7 @@ static int ipv6_flowlabel_put(struct sock *sk, struct in6_flowlabel_req *freq) } spin_lock_bh(&ip6_sk_fl_lock); - for (sflp = &np->ipv6_fl_list; + for (sflp = &inet_sk(sk)->ipv6_fl_list; (sfl = socklist_dereference(*sflp)) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq->flr_label) @@ -579,13 +579,12 @@ static int ipv6_flowlabel_put(struct sock *sk, struct in6_flowlabel_req *freq) static int ipv6_flowlabel_renew(struct sock *sk, struct in6_flowlabel_req *freq) { - struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6_fl_socklist *sfl; int err; rcu_read_lock(); - for_each_sk_fl_rcu(np, sfl) { + for_each_sk_fl_rcu(sk, sfl) { if (sfl->fl->label == freq->flr_label) { err = fl6_renew(sfl->fl, freq->flr_linger, freq->flr_expires); @@ -614,7 +613,6 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, { struct ipv6_fl_socklist *sfl, *sfl1 = NULL; struct ip6_flowlabel *fl, *fl1 = NULL; - struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); int err; @@ -645,7 +643,7 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, if (freq->flr_label) { err = -EEXIST; rcu_read_lock(); - for_each_sk_fl_rcu(np, sfl) { + for_each_sk_fl_rcu(sk, sfl) { if (sfl->fl->label == freq->flr_label) { if (freq->flr_flags & IPV6_FL_F_EXCL) { rcu_read_unlock(); @@ -682,7 +680,7 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) fl1->expires = fl->expires; - fl_link(np, sfl1, fl1); + fl_link(sk, sfl1, fl1); fl_free(fl); return 0; @@ -716,7 +714,7 @@ static int ipv6_flowlabel_get(struct sock *sk, struct in6_flowlabel_req *freq, } } - fl_link(np, sfl1, fl); + fl_link(sk, sfl1, fl); return 0; done: fl_free(fl); diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index 0ff547a4bff71..cef3e02107444 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -40,7 +40,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->local_udp_port; - err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, + err = kernel_bind(sock, (struct sockaddr_unsized *)&udp6_addr, sizeof(udp6_addr)); if (err < 0) goto error; @@ -52,7 +52,7 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->peer_udp_port; err = kernel_connect(sock, - (struct sockaddr *)&udp6_addr, + (struct sockaddr_unsized *)&udp6_addr, sizeof(udp6_addr), 0); } if (err < 0) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index f427e41e9c49b..59d17b6f06bfd 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1449,7 +1449,7 @@ static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb) BASE_REACHABLE_TIME, rtime); NEIGH_VAR_SET(in6_dev->nd_parms, GC_STALETIME, 3 * rtime); - in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime); + neigh_set_reach_time(in6_dev->nd_parms); in6_dev->tstamp = jiffies; send_ifinfo_notify = true; } @@ -1948,9 +1948,9 @@ int ndisc_ifinfo_sysctl_change(const struct ctl_table *ctl, int write, void *buf ret = -1; if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) { - if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)) - idev->nd_parms->reachable_time = - neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME)); + if (ctl->data == NEIGH_VAR_PTR(idev->nd_parms, BASE_REACHABLE_TIME)) + neigh_set_reach_time(idev->nd_parms); + WRITE_ONCE(idev->tstamp, jiffies); inet6_ifinfo_notify(RTM_NEWLINK, idev); in6_dev_put(idev); diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index d7a2cdaa26312..e4afc651731a3 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -45,7 +45,7 @@ static int dummy_ipv6_chk_addr(struct net *net, const struct in6_addr *addr, return 0; } -static int ping_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int ping_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from __ip6_datagram_connect() and diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index e369f54844dd9..b4cd05dba9b6d 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -214,7 +214,8 @@ bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) } /* This cleans up af_inet6 a bit. -DaveM */ -static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int rawv6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 59c4977a811a0..08113f4301249 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -67,8 +67,7 @@ #include #include -#include -#include +#include #include @@ -119,7 +118,7 @@ static u32 tcp_v6_init_ts_off(const struct net *net, const struct sk_buff *skb) ipv6_hdr(skb)->saddr.s6_addr32); } -static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { /* This check is replicated from tcp_v6_connect() and intended to @@ -134,7 +133,7 @@ static int tcp_v6_pre_connect(struct sock *sk, struct sockaddr *uaddr, return BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, &addr_len); } -static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, +static int tcp_v6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; @@ -239,7 +238,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->af_specific = &tcp_sock_ipv6_mapped_specific; #endif - err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin)); + err = tcp_v4_connect(sk, (struct sockaddr_unsized *)&sin, sizeof(sin)); if (err) { icsk->icsk_ext_hdr_len = exthdrlen; @@ -691,69 +690,45 @@ static int tcp_v6_parse_md5_keys(struct sock *sk, int optname, cmd.tcpm_key, cmd.tcpm_keylen); } -static int tcp_v6_md5_hash_headers(struct tcp_sigpool *hp, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - const struct tcphdr *th, int nbytes) +static void tcp_v6_md5_hash_headers(struct md5_ctx *ctx, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + const struct tcphdr *th, int nbytes) { - struct tcp6_pseudohdr *bp; - struct scatterlist sg; - struct tcphdr *_th; - - bp = hp->scratch; - /* 1. TCP pseudo-header (RFC2460) */ - bp->saddr = *saddr; - bp->daddr = *daddr; - bp->protocol = cpu_to_be32(IPPROTO_TCP); - bp->len = cpu_to_be32(nbytes); - - _th = (struct tcphdr *)(bp + 1); - memcpy(_th, th, sizeof(*th)); - _th->check = 0; - - sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); - ahash_request_set_crypt(hp->req, &sg, NULL, - sizeof(*bp) + sizeof(*th)); - return crypto_ahash_update(hp->req); + struct { + struct tcp6_pseudohdr ip; /* TCP pseudo-header (RFC2460) */ + struct tcphdr tcp; + } h; + + h.ip.saddr = *saddr; + h.ip.daddr = *daddr; + h.ip.protocol = cpu_to_be32(IPPROTO_TCP); + h.ip.len = cpu_to_be32(nbytes); + h.tcp = *th; + h.tcp.check = 0; + md5_update(ctx, (const u8 *)&h, sizeof(h.ip) + sizeof(h.tcp)); } -static int tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, - const struct in6_addr *daddr, struct in6_addr *saddr, - const struct tcphdr *th) +static noinline_for_stack void +tcp_v6_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, + const struct in6_addr *daddr, struct in6_addr *saddr, + const struct tcphdr *th) { - struct tcp_sigpool hp; - - if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) - goto clear_hash_nostart; - - if (crypto_ahash_init(hp.req)) - goto clear_hash; - if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, th->doff << 2)) - goto clear_hash; - if (tcp_md5_hash_key(&hp, key)) - goto clear_hash; - ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); - if (crypto_ahash_final(hp.req)) - goto clear_hash; - - tcp_sigpool_end(&hp); - return 0; + struct md5_ctx ctx; -clear_hash: - tcp_sigpool_end(&hp); -clear_hash_nostart: - memset(md5_hash, 0, 16); - return 1; + md5_init(&ctx); + tcp_v6_md5_hash_headers(&ctx, daddr, saddr, th, th->doff << 2); + tcp_md5_hash_key(&ctx, key); + md5_final(&ctx, md5_hash); } -static int tcp_v6_md5_hash_skb(char *md5_hash, - const struct tcp_md5sig_key *key, - const struct sock *sk, - const struct sk_buff *skb) +static noinline_for_stack void +tcp_v6_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, + const struct sock *sk, const struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); const struct in6_addr *saddr, *daddr; - struct tcp_sigpool hp; + struct md5_ctx ctx; if (sk) { /* valid for establish/request sockets */ saddr = &sk->sk_v6_rcv_saddr; @@ -764,30 +739,11 @@ static int tcp_v6_md5_hash_skb(char *md5_hash, daddr = &ip6h->daddr; } - if (tcp_sigpool_start(tcp_md5_sigpool_id, &hp)) - goto clear_hash_nostart; - - if (crypto_ahash_init(hp.req)) - goto clear_hash; - - if (tcp_v6_md5_hash_headers(&hp, daddr, saddr, th, skb->len)) - goto clear_hash; - if (tcp_sigpool_hash_skb_data(&hp, skb, th->doff << 2)) - goto clear_hash; - if (tcp_md5_hash_key(&hp, key)) - goto clear_hash; - ahash_request_set_crypt(hp.req, NULL, md5_hash, 0); - if (crypto_ahash_final(hp.req)) - goto clear_hash; - - tcp_sigpool_end(&hp); - return 0; - -clear_hash: - tcp_sigpool_end(&hp); -clear_hash_nostart: - memset(md5_hash, 0, 16); - return 1; + md5_init(&ctx); + tcp_v6_md5_hash_headers(&ctx, daddr, saddr, th, skb->len); + tcp_md5_hash_skb_data(&ctx, skb, th->doff << 2); + tcp_md5_hash_key(&ctx, key); + md5_final(&ctx, md5_hash); } #endif @@ -840,7 +796,6 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .send_ack = tcp_v6_reqsk_send_ack, .destructor = tcp_v6_reqsk_destructor, .send_reset = tcp_v6_send_reset, - .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { @@ -1032,7 +987,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, int oif = 0; #ifdef CONFIG_TCP_MD5SIG unsigned char newhash[16]; - int genhash; struct sock *sk1 = NULL; #endif @@ -1091,8 +1045,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb, goto out; key.type = TCP_KEY_MD5; - genhash = tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); - if (genhash || memcmp(md5_hash_location, newhash, 16) != 0) + tcp_v6_md5_hash_skb(newhash, key.md5_key, NULL, skb); + if (memcmp(md5_hash_location, newhash, 16) != 0) goto out; } #endif @@ -1386,7 +1340,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (!newsk) return NULL; - inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); + newinet = inet_sk(newsk); + newinet->pinet6 = tcp_inet6_sk(newsk); + newinet->ipv6_fl_list = NULL; newnp = tcp_inet6_sk(newsk); newtp = tcp_sk(newsk); @@ -1405,7 +1361,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; - newnp->ipv6_fl_list = NULL; newnp->pktoptions = NULL; newnp->opt = NULL; newnp->mcast_oif = inet_iif(skb); @@ -1453,10 +1408,12 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * newsk->sk_gso_type = SKB_GSO_TCPV6; inet6_sk_rx_dst_set(newsk, skb); - inet_sk(newsk)->pinet6 = tcp_inet6_sk(newsk); + newinet = inet_sk(newsk); + newinet->pinet6 = tcp_inet6_sk(newsk); + newinet->ipv6_fl_list = NULL; + newinet->inet_opt = NULL; newtp = tcp_sk(newsk); - newinet = inet_sk(newsk); newnp = tcp_inet6_sk(newsk); memcpy(newnp, np, sizeof(struct ipv6_pinfo)); @@ -1469,10 +1426,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * First: no IPv4 options. */ - newinet->inet_opt = NULL; newnp->ipv6_mc_list = NULL; newnp->ipv6_ac_list = NULL; - newnp->ipv6_fl_list = NULL; /* Clone RX bits */ newnp->rxopt.all = np->rxopt.all; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 813a2ba75824d..794c13674e8ab 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1282,7 +1282,7 @@ static void udp_v6_flush_pending_frames(struct sock *sk) } } -static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, +static int udpv6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { if (addr_len < offsetofend(struct sockaddr, sa_family)) @@ -1303,7 +1303,8 @@ static int udpv6_pre_connect(struct sock *sk, struct sockaddr *uaddr, return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len); } -static int udpv6_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int udpv6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { int res; diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 6c717a7ef2928..a4f1df92417d9 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -553,16 +553,17 @@ static void __iucv_auto_name(struct iucv_sock *iucv) { char name[12]; - sprintf(name, "%08x", atomic_inc_return(&iucv_sk_list.autobind_name)); + scnprintf(name, sizeof(name), + "%08x", atomic_inc_return(&iucv_sk_list.autobind_name)); while (__iucv_get_sock_by_name(name)) { - sprintf(name, "%08x", - atomic_inc_return(&iucv_sk_list.autobind_name)); + scnprintf(name, sizeof(name), "%08x", + atomic_inc_return(&iucv_sk_list.autobind_name)); } memcpy(iucv->src_name, name, 8); } /* Bind an unbound socket */ -static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr, +static int iucv_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { DECLARE_SOCKADDR(struct sockaddr_iucv *, sa, addr); @@ -667,7 +668,7 @@ static int iucv_sock_autobind(struct sock *sk) return err; } -static int afiucv_path_connect(struct socket *sock, struct sockaddr *addr) +static int afiucv_path_connect(struct socket *sock, struct sockaddr_unsized *addr) { DECLARE_SOCKADDR(struct sockaddr_iucv *, sa, addr); struct sock *sk = sock->sk; @@ -713,7 +714,7 @@ static int afiucv_path_connect(struct socket *sock, struct sockaddr *addr) } /* Connect an unconnected socket */ -static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr, +static int iucv_sock_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { DECLARE_SOCKADDR(struct sockaddr_iucv *, sa, addr); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 473a7847d80bb..008be0abe3a57 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -95,7 +95,7 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs, if (!dev) goto out_error; va_start(vargs, fmt); - vsnprintf(buf, sizeof(buf), fmt, vargs); + vscnprintf(buf, sizeof(buf), fmt, vargs); rc = dev_set_name(dev, "%s", buf); va_end(vargs); if (rc) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 369a2f2e459cd..c4f4a57cd67c9 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1503,7 +1503,7 @@ static int l2tp_tunnel_sock_create(struct net *net, memcpy(&ip6_addr.l2tp_addr, cfg->local_ip6, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = tunnel_id; - err = kernel_bind(sock, (struct sockaddr *)&ip6_addr, + err = kernel_bind(sock, (struct sockaddr_unsized *)&ip6_addr, sizeof(ip6_addr)); if (err < 0) goto out; @@ -1513,7 +1513,7 @@ static int l2tp_tunnel_sock_create(struct net *net, sizeof(ip6_addr.l2tp_addr)); ip6_addr.l2tp_conn_id = peer_tunnel_id; err = kernel_connect(sock, - (struct sockaddr *)&ip6_addr, + (struct sockaddr_unsized *)&ip6_addr, sizeof(ip6_addr), 0); if (err < 0) goto out; @@ -1530,7 +1530,7 @@ static int l2tp_tunnel_sock_create(struct net *net, ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->local_ip; ip_addr.l2tp_conn_id = tunnel_id; - err = kernel_bind(sock, (struct sockaddr *)&ip_addr, + err = kernel_bind(sock, (struct sockaddr_unsized *)&ip_addr, sizeof(ip_addr)); if (err < 0) goto out; @@ -1538,7 +1538,7 @@ static int l2tp_tunnel_sock_create(struct net *net, ip_addr.l2tp_family = AF_INET; ip_addr.l2tp_addr = cfg->peer_ip; ip_addr.l2tp_conn_id = peer_tunnel_id; - err = kernel_connect(sock, (struct sockaddr *)&ip_addr, + err = kernel_connect(sock, (struct sockaddr_unsized *)&ip_addr, sizeof(ip_addr), 0); if (err < 0) goto out; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 29795d2839e8b..cac1ff59cb83f 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -267,7 +267,8 @@ static void l2tp_ip_destroy_sock(struct sock *sk) } } -static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int l2tp_ip_bind(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct inet_sock *inet = inet_sk(sk); struct sockaddr_l2tpip *addr = (struct sockaddr_l2tpip *)uaddr; @@ -328,7 +329,8 @@ static int l2tp_ip_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) return ret; } -static int l2tp_ip_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int l2tp_ip_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct sockaddr_l2tpip *lsa = (struct sockaddr_l2tpip *)uaddr; struct l2tp_ip_net *pn = l2tp_ip_pernet(sock_net(sk)); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index ea232f338dcb6..05a396ba6a3eb 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -280,7 +280,8 @@ static void l2tp_ip6_destroy_sock(struct sock *sk) } } -static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int l2tp_ip6_bind(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); @@ -383,7 +384,7 @@ static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) return err; } -static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr, +static int l2tp_ip6_connect(struct sock *sk, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5e12e7ce17d8a..ae4543d5597b6 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -684,7 +684,7 @@ static struct l2tp_tunnel *pppol2tp_tunnel_get(struct net *net, /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket */ -static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr, +static int pppol2tp_connect(struct socket *sock, struct sockaddr_unsized *uservaddr, int sockaddr_len, int flags) { struct sock *sk = sock->sk; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 5958a80fe14cf..59d593bb5d186 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -337,7 +337,7 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) * otherwise all hell will break loose. * Returns: 0 upon success, negative otherwise. */ -static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) +static int llc_ui_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addrlen) { struct sockaddr_llc *addr = (struct sockaddr_llc *)uaddr; struct sock *sk = sock->sk; @@ -477,7 +477,7 @@ static int llc_ui_shutdown(struct socket *sock, int how) * This function will autobind if user did not previously call bind. * Returns: 0 upon success, negative otherwise. */ -static int llc_ui_connect(struct socket *sock, struct sockaddr *uaddr, +static int llc_ui_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addrlen, int flags) { struct sock *sk = sock->sk; diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index e38f46ffebfa7..7da909d78c68e 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -9,7 +9,7 @@ * Copyright 2007, Michael Wu * Copyright 2007-2010, Intel Corporation * Copyright(c) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2024 Intel Corporation + * Copyright (C) 2018-2025 Intel Corporation */ /** @@ -206,7 +206,10 @@ u8 ieee80211_retrieve_addba_ext_data(struct sta_info *sta, if (elem_len <= 0) return 0; - elems = ieee802_11_parse_elems(elem_data, elem_len, true, NULL); + elems = ieee802_11_parse_elems(elem_data, elem_len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems || elems->parse_error || !elems->addba_ext_ie) goto free; diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index c52b0456039dd..b51c2c8584ae0 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -63,12 +63,14 @@ static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata, memcpy(sdata->vif.bss_conf.mu_group.position, params->vht_mumimo_groups + WLAN_MEMBERSHIP_LEN, WLAN_USER_POSITION_LEN); - ieee80211_link_info_change_notify(sdata, &sdata->deflink, - BSS_CHANGED_MU_GROUPS); + /* don't care about endianness - just check for 0 */ memcpy(&membership, params->vht_mumimo_groups, WLAN_MEMBERSHIP_LEN); mu_mimo_groups = membership != 0; + + /* Unset following if configured explicitly */ + eth_broadcast_addr(sdata->u.mntr.mu_follow_addr); } if (params->vht_mumimo_follow_addr) { @@ -76,16 +78,26 @@ static void ieee80211_set_mu_mimo_follow(struct ieee80211_sub_if_data *sdata, is_valid_ether_addr(params->vht_mumimo_follow_addr); ether_addr_copy(sdata->u.mntr.mu_follow_addr, params->vht_mumimo_follow_addr); + + /* Unset current membership until a management frame is RXed */ + memset(sdata->vif.bss_conf.mu_group.membership, 0, + WLAN_MEMBERSHIP_LEN); } sdata->vif.bss_conf.mu_mimo_owner = mu_mimo_groups || mu_mimo_follow; + + /* Notify only after setting mu_mimo_owner */ + if (sdata->vif.bss_conf.mu_mimo_owner && + sdata->flags & IEEE80211_SDATA_IN_DRIVER) + ieee80211_link_info_change_notify(sdata, &sdata->deflink, + BSS_CHANGED_MU_GROUPS); } static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, struct vif_params *params) { struct ieee80211_local *local = sdata->local; - struct ieee80211_sub_if_data *monitor_sdata; + struct ieee80211_sub_if_data *monitor_sdata = NULL; /* check flags first */ if (params->flags && ieee80211_sdata_running(sdata)) { @@ -103,23 +115,28 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata, return -EBUSY; } - /* also validate MU-MIMO change */ - if (ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) - monitor_sdata = sdata; - else - monitor_sdata = wiphy_dereference(local->hw.wiphy, - local->monitor_sdata); - - if (!monitor_sdata && + /* validate whether MU-MIMO can be configured */ + if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) && + !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR) && (params->vht_mumimo_groups || params->vht_mumimo_follow_addr)) return -EOPNOTSUPP; + /* Also update dependent monitor_sdata if required */ + if (test_bit(SDATA_STATE_RUNNING, &sdata->state) && + !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) + monitor_sdata = wiphy_dereference(local->hw.wiphy, + local->monitor_sdata); + /* apply all changes now - no failures allowed */ - if (monitor_sdata && - (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) || - ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR))) - ieee80211_set_mu_mimo_follow(monitor_sdata, params); + if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) || + ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) { + /* This is copied in when the VIF is activated */ + ieee80211_set_mu_mimo_follow(sdata, params); + + if (monitor_sdata) + ieee80211_set_mu_mimo_follow(monitor_sdata, params); + } if (params->flags) { if (ieee80211_sdata_running(sdata)) { diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c index 7f8799fd673eb..6aa305839f534 100644 --- a/net/mac80211/chan.c +++ b/net/mac80211/chan.c @@ -12,15 +12,131 @@ #include "driver-ops.h" #include "rate.h" +struct ieee80211_chanctx_user_iter { + struct ieee80211_chan_req *chanreq; + struct ieee80211_sub_if_data *sdata; + struct ieee80211_link_data *link; + enum nl80211_iftype iftype; + bool reserved, radar_required, done; + enum { + CHANCTX_ITER_POS_ASSIGNED, + CHANCTX_ITER_POS_RESERVED, + CHANCTX_ITER_POS_DONE, + } per_link; +}; + +enum ieee80211_chanctx_iter_type { + CHANCTX_ITER_ALL, + CHANCTX_ITER_RESERVED, + CHANCTX_ITER_ASSIGNED, +}; + +static void ieee80211_chanctx_user_iter_next(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_chanctx_user_iter *iter, + enum ieee80211_chanctx_iter_type type, + bool start) +{ + lockdep_assert_wiphy(local->hw.wiphy); + + if (start) { + memset(iter, 0, sizeof(*iter)); + goto next_interface; + } + +next_link: + for (int link_id = iter->link ? iter->link->link_id : 0; + link_id < ARRAY_SIZE(iter->sdata->link); + link_id++) { + struct ieee80211_link_data *link; + + link = sdata_dereference(iter->sdata->link[link_id], + iter->sdata); + if (!link) + continue; + + switch (iter->per_link) { + case CHANCTX_ITER_POS_ASSIGNED: + iter->per_link = CHANCTX_ITER_POS_RESERVED; + if (type != CHANCTX_ITER_RESERVED && + rcu_access_pointer(link->conf->chanctx_conf) == &ctx->conf) { + iter->link = link; + iter->reserved = false; + iter->radar_required = link->radar_required; + iter->chanreq = &link->conf->chanreq; + return; + } + fallthrough; + case CHANCTX_ITER_POS_RESERVED: + iter->per_link = CHANCTX_ITER_POS_DONE; + if (type != CHANCTX_ITER_ASSIGNED && + link->reserved_chanctx == ctx) { + iter->link = link; + iter->reserved = true; + iter->radar_required = + link->reserved_radar_required; + + iter->chanreq = &link->reserved; + return; + } + fallthrough; + case CHANCTX_ITER_POS_DONE: + iter->per_link = CHANCTX_ITER_POS_ASSIGNED; + continue; + } + } + +next_interface: + /* next (or first) interface */ + iter->sdata = list_prepare_entry(iter->sdata, &local->interfaces, list); + list_for_each_entry_continue(iter->sdata, &local->interfaces, list) { + /* AP_VLAN has a chanctx pointer but follows AP */ + if (iter->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) + continue; + + iter->link = NULL; + iter->per_link = CHANCTX_ITER_POS_ASSIGNED; + iter->iftype = iter->sdata->vif.type; + goto next_link; + } + + iter->done = true; +} + +#define for_each_chanctx_user_assigned(local, ctx, iter) \ + for (ieee80211_chanctx_user_iter_next(local, ctx, iter, \ + CHANCTX_ITER_ASSIGNED, \ + true); \ + !((iter)->done); \ + ieee80211_chanctx_user_iter_next(local, ctx, iter, \ + CHANCTX_ITER_ASSIGNED, \ + false)) + +#define for_each_chanctx_user_reserved(local, ctx, iter) \ + for (ieee80211_chanctx_user_iter_next(local, ctx, iter, \ + CHANCTX_ITER_RESERVED, \ + true); \ + !((iter)->done); \ + ieee80211_chanctx_user_iter_next(local, ctx, iter, \ + CHANCTX_ITER_RESERVED, \ + false)) + +#define for_each_chanctx_user_all(local, ctx, iter) \ + for (ieee80211_chanctx_user_iter_next(local, ctx, iter, \ + CHANCTX_ITER_ALL, \ + true); \ + !((iter)->done); \ + ieee80211_chanctx_user_iter_next(local, ctx, iter, \ + CHANCTX_ITER_ALL, \ + false)) + static int ieee80211_chanctx_num_assigned(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; int num = 0; - lockdep_assert_wiphy(local->hw.wiphy); - - list_for_each_entry(link, &ctx->assigned_links, assigned_chanctx_list) + for_each_chanctx_user_assigned(local, ctx, &iter) num++; return num; @@ -29,12 +145,10 @@ static int ieee80211_chanctx_num_assigned(struct ieee80211_local *local, static int ieee80211_chanctx_num_reserved(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; int num = 0; - lockdep_assert_wiphy(local->hw.wiphy); - - list_for_each_entry(link, &ctx->reserved_links, reserved_chanctx_list) + for_each_chanctx_user_reserved(local, ctx, &iter) num++; return num; @@ -43,8 +157,13 @@ static int ieee80211_chanctx_num_reserved(struct ieee80211_local *local, int ieee80211_chanctx_refcount(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { - return ieee80211_chanctx_num_assigned(local, ctx) + - ieee80211_chanctx_num_reserved(local, ctx); + struct ieee80211_chanctx_user_iter iter; + int num = 0; + + for_each_chanctx_user_all(local, ctx, &iter) + num++; + + return num; } static int ieee80211_num_chanctx(struct ieee80211_local *local, int radio_idx) @@ -143,15 +262,15 @@ ieee80211_chanctx_reserved_chanreq(struct ieee80211_local *local, const struct ieee80211_chan_req *req, struct ieee80211_chan_req *tmp) { - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; lockdep_assert_wiphy(local->hw.wiphy); if (WARN_ON(!req)) return NULL; - list_for_each_entry(link, &ctx->reserved_links, reserved_chanctx_list) { - req = ieee80211_chanreq_compatible(&link->reserved, req, tmp); + for_each_chanctx_user_reserved(local, ctx, &iter) { + req = ieee80211_chanreq_compatible(iter.chanreq, req, tmp); if (!req) break; } @@ -165,18 +284,16 @@ ieee80211_chanctx_non_reserved_chandef(struct ieee80211_local *local, const struct ieee80211_chan_req *compat, struct ieee80211_chan_req *tmp) { - struct ieee80211_link_data *link; const struct ieee80211_chan_req *comp_def = compat; + struct ieee80211_chanctx_user_iter iter; lockdep_assert_wiphy(local->hw.wiphy); - list_for_each_entry(link, &ctx->assigned_links, assigned_chanctx_list) { - struct ieee80211_bss_conf *link_conf = link->conf; - - if (link->reserved_chanctx) + for_each_chanctx_user_assigned(local, ctx, &iter) { + if (iter.link->reserved_chanctx) continue; - comp_def = ieee80211_chanreq_compatible(&link_conf->chanreq, + comp_def = ieee80211_chanreq_compatible(iter.chanreq, comp_def, tmp); if (!comp_def) break; @@ -200,7 +317,7 @@ ieee80211_chanctx_can_reserve(struct ieee80211_local *local, if (!ieee80211_chanctx_non_reserved_chandef(local, ctx, req, &tmp)) return false; - if (!list_empty(&ctx->reserved_links) && + if (ieee80211_chanctx_num_reserved(local, ctx) != 0 && ieee80211_chanctx_reserved_chanreq(local, ctx, req, &tmp)) return true; @@ -389,10 +506,10 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local, * channel context. */ static u32 -_ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for, - bool check_reserved) +__ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for, + bool check_reserved) { enum nl80211_chan_width max_bw; struct cfg80211_chan_def min_def; @@ -497,13 +614,14 @@ static void ieee80211_chan_bw_change(struct ieee80211_local *local, * the max of min required widths of all the interfaces bound to this * channel context. */ -void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for, - bool check_reserved) +static void +_ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx, + struct ieee80211_link_data *rsvd_for, + bool check_reserved) { - u32 changed = _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, - check_reserved); + u32 changed = __ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, + check_reserved); if (!changed) return; @@ -517,6 +635,12 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, ieee80211_chan_bw_change(local, ctx, false, false); } +void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, + struct ieee80211_chanctx *ctx) +{ + _ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false); +} + static void _ieee80211_change_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *ctx, struct ieee80211_chanctx *old_ctx, @@ -551,7 +675,7 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local, ieee80211_chan_bw_change(local, old_ctx, false, true); if (ieee80211_chanreq_identical(&ctx_req, chanreq)) { - ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, false); + _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, false); return; } @@ -572,7 +696,8 @@ static void _ieee80211_change_chanctx(struct ieee80211_local *local, ctx->conf.ap = chanreq->ap; /* check if min chanctx also changed */ - changed |= _ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, false); + changed |= __ieee80211_recalc_chanctx_min_def(local, ctx, rsvd_for, + false); ieee80211_add_wbrf(local, &ctx->conf.def); @@ -633,8 +758,6 @@ ieee80211_find_chanctx(struct ieee80211_local *local, * context to actually be removed. */ link->reserved_chanctx = ctx; - list_add(&link->reserved_chanctx_list, - &ctx->reserved_links); ieee80211_change_chanctx(local, ctx, ctx, compat); @@ -675,17 +798,13 @@ static bool ieee80211_chanctx_radar_required(struct ieee80211_local *local, struct ieee80211_chanctx *ctx) { - struct ieee80211_chanctx_conf *conf = &ctx->conf; - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; lockdep_assert_wiphy(local->hw.wiphy); - for_each_sdata_link(local, link) { - if (rcu_access_pointer(link->conf->chanctx_conf) != conf) - continue; - if (!link->radar_required) - continue; - return true; + for_each_chanctx_user_assigned(local, ctx, &iter) { + if (iter.radar_required) + return true; } return false; @@ -705,8 +824,6 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, if (!ctx) return NULL; - INIT_LIST_HEAD(&ctx->assigned_links); - INIT_LIST_HEAD(&ctx->reserved_links); ctx->conf.def = chanreq->oper; ctx->conf.ap = chanreq->ap; ctx->conf.rx_chains_static = 1; @@ -715,7 +832,7 @@ ieee80211_alloc_chanctx(struct ieee80211_local *local, ctx->conf.radar_enabled = false; ctx->conf.radio_idx = radio_idx; ctx->radar_detected = false; - _ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false); + __ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false); return ctx; } @@ -804,27 +921,17 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, { struct ieee80211_chanctx_conf *conf = &ctx->conf; const struct ieee80211_chan_req *compat = NULL; - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; struct ieee80211_chan_req tmp; struct sta_info *sta; lockdep_assert_wiphy(local->hw.wiphy); - for_each_sdata_link(local, link) { - struct ieee80211_bss_conf *link_conf; - - if (link->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) - continue; - - link_conf = link->conf; - - if (rcu_access_pointer(link_conf->chanctx_conf) != conf) - continue; - + for_each_chanctx_user_assigned(local, ctx, &iter) { if (!compat) - compat = &link_conf->chanreq; + compat = iter.chanreq; - compat = ieee80211_chanreq_compatible(&link_conf->chanreq, + compat = ieee80211_chanreq_compatible(iter.chanreq, compat, &tmp); if (WARN_ON_ONCE(!compat)) return; @@ -837,6 +944,7 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local, list_for_each_entry(sta, &local->sta_list, list) { struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_chan_req tdls_chanreq = {}; + struct ieee80211_link_data *link; int tdls_link_id; if (!sta->uploaded || @@ -904,12 +1012,11 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, drv_unassign_vif_chanctx(local, sdata, link->conf, curr_ctx); conf = NULL; - list_del(&link->assigned_chanctx_list); } if (new_ctx) { /* recalc considering the link we'll use it for now */ - ieee80211_recalc_chanctx_min_def(local, new_ctx, link, false); + _ieee80211_recalc_chanctx_min_def(local, new_ctx, link, false); ret = drv_assign_vif_chanctx(local, sdata, link->conf, new_ctx); if (assign_on_failure || !ret) { @@ -919,9 +1026,6 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, /* succeeded, so commit it to the data structures */ conf = &new_ctx->conf; - if (!local->in_reconfig) - list_add(&link->assigned_chanctx_list, - &new_ctx->assigned_links); } } else { ret = 0; @@ -933,12 +1037,12 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, ieee80211_recalc_chanctx_chantype(local, curr_ctx); ieee80211_recalc_smps_chanctx(local, curr_ctx); ieee80211_recalc_radar_chanctx(local, curr_ctx); - ieee80211_recalc_chanctx_min_def(local, curr_ctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, curr_ctx); } if (new_ctx && ieee80211_chanctx_num_assigned(local, new_ctx) > 0) { ieee80211_recalc_txpower(link, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, new_ctx); } if (conf) { @@ -971,21 +1075,21 @@ static int ieee80211_assign_link_chanctx(struct ieee80211_link_data *link, void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx) { + struct ieee80211_chanctx_user_iter iter; struct ieee80211_sub_if_data *sdata; u8 rx_chains_static, rx_chains_dynamic; - struct ieee80211_link_data *link; lockdep_assert_wiphy(local->hw.wiphy); rx_chains_static = 1; rx_chains_dynamic = 1; - for_each_sdata_link(local, link) { + for_each_chanctx_user_assigned(local, chanctx, &iter) { u8 needed_static, needed_dynamic; - switch (link->sdata->vif.type) { + switch (iter.iftype) { case NL80211_IFTYPE_STATION: - if (!link->sdata->u.mgd.associated) + if (!iter.sdata->u.mgd.associated) continue; break; case NL80211_IFTYPE_MONITOR: @@ -1001,26 +1105,23 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, continue; } - if (rcu_access_pointer(link->conf->chanctx_conf) != &chanctx->conf) - continue; - - if (link->sdata->vif.type == NL80211_IFTYPE_MONITOR) { + if (iter.iftype == NL80211_IFTYPE_MONITOR) { rx_chains_dynamic = rx_chains_static = local->rx_chains; break; } - switch (link->smps_mode) { + switch (iter.link->smps_mode) { default: WARN_ONCE(1, "Invalid SMPS mode %d\n", - link->smps_mode); + iter.link->smps_mode); fallthrough; case IEEE80211_SMPS_OFF: - needed_static = link->needed_rx_chains; - needed_dynamic = link->needed_rx_chains; + needed_static = iter.link->needed_rx_chains; + needed_dynamic = iter.link->needed_rx_chains; break; case IEEE80211_SMPS_DYNAMIC: needed_static = 1; - needed_dynamic = link->needed_rx_chains; + needed_dynamic = iter.link->needed_rx_chains; break; case IEEE80211_SMPS_STATIC: needed_static = 1; @@ -1108,7 +1209,6 @@ void ieee80211_link_unreserve_chanctx(struct ieee80211_link_data *link) if (WARN_ON(!ctx)) return; - list_del(&link->reserved_chanctx_list); link->reserved_chanctx = NULL; if (ieee80211_chanctx_refcount(sdata->local, ctx) == 0) { @@ -1142,9 +1242,9 @@ ieee80211_replace_chanctx(struct ieee80211_local *local, struct wiphy *wiphy = local->hw.wiphy; const struct wiphy_radio *radio; - if (!curr_ctx || (curr_ctx->replace_state == - IEEE80211_CHANCTX_WILL_BE_REPLACED) || - !list_empty(&curr_ctx->reserved_links)) { + if (!curr_ctx || + curr_ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED || + ieee80211_chanctx_num_reserved(local, curr_ctx) != 0) { /* * Another link already requested this context for a * reservation. Find another one hoping all links assigned @@ -1167,7 +1267,7 @@ ieee80211_replace_chanctx(struct ieee80211_local *local, IEEE80211_CHANCTX_REPLACE_NONE) continue; - if (!list_empty(&ctx->reserved_links)) + if (ieee80211_chanctx_num_reserved(local, ctx) != 0) continue; if (ctx->conf.radio_idx >= 0) { @@ -1185,9 +1285,9 @@ ieee80211_replace_chanctx(struct ieee80211_local *local, * If that's true then all available contexts already have reservations * and cannot be used. */ - if (!curr_ctx || (curr_ctx->replace_state == - IEEE80211_CHANCTX_WILL_BE_REPLACED) || - !list_empty(&curr_ctx->reserved_links)) + if (!curr_ctx || + curr_ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED || + ieee80211_chanctx_num_reserved(local, curr_ctx) != 0) return ERR_PTR(-EBUSY); new_ctx = ieee80211_alloc_chanctx(local, chanreq, mode, -1); @@ -1267,7 +1367,6 @@ int ieee80211_link_reserve_chanctx(struct ieee80211_link_data *link, return PTR_ERR(new_ctx); } - list_add(&link->reserved_chanctx_list, &new_ctx->reserved_links); link->reserved_chanctx = new_ctx; link->reserved = *chanreq; link->reserved_radar_required = radar_required; @@ -1381,7 +1480,6 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) vif_chsw[0].new_ctx = &new_ctx->conf; vif_chsw[0].link_conf = link->conf; - list_del(&link->reserved_chanctx_list); link->reserved_chanctx = NULL; err = drv_switch_vif_chanctx(local, vif_chsw, 1, @@ -1394,7 +1492,6 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) } link->radar_required = link->reserved_radar_required; - list_move(&link->assigned_chanctx_list, &new_ctx->assigned_links); rcu_assign_pointer(link_conf->chanctx_conf, &new_ctx->conf); if (sdata->vif.type == NL80211_IFTYPE_AP) @@ -1405,7 +1502,7 @@ ieee80211_link_use_reserved_reassign(struct ieee80211_link_data *link) if (ieee80211_chanctx_refcount(local, old_ctx) == 0) ieee80211_free_chanctx(local, old_ctx, false); - ieee80211_recalc_chanctx_min_def(local, new_ctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, new_ctx); ieee80211_recalc_smps_chanctx(local, new_ctx); ieee80211_recalc_radar_chanctx(local, new_ctx); @@ -1451,7 +1548,6 @@ ieee80211_link_use_reserved_assign(struct ieee80211_link_data *link) ieee80211_change_chanctx(local, new_ctx, new_ctx, chanreq); - list_del(&link->reserved_chanctx_list); link->reserved_chanctx = NULL; err = ieee80211_assign_link_chanctx(link, new_ctx, false); @@ -1497,7 +1593,6 @@ static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, int n_vifs) { struct ieee80211_vif_chanctx_switch *vif_chsw; - struct ieee80211_link_data *link; struct ieee80211_chanctx *ctx, *old_ctx; int i, err; @@ -1509,6 +1604,8 @@ static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, i = 0; list_for_each_entry(ctx, &local->chanctx_list, list) { + struct ieee80211_chanctx_user_iter iter; + if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; @@ -1517,16 +1614,15 @@ static int ieee80211_chsw_switch_vifs(struct ieee80211_local *local, goto out; } - list_for_each_entry(link, &ctx->reserved_links, - reserved_chanctx_list) { - if (!ieee80211_link_has_in_place_reservation(link)) + for_each_chanctx_user_reserved(local, ctx, &iter) { + if (!ieee80211_link_has_in_place_reservation(iter.link)) continue; - old_ctx = ieee80211_link_get_chanctx(link); - vif_chsw[i].vif = &link->sdata->vif; + old_ctx = ieee80211_link_get_chanctx(iter.link); + vif_chsw[i].vif = &iter.sdata->vif; vif_chsw[i].old_ctx = &old_ctx->conf; vif_chsw[i].new_ctx = &ctx->conf; - vif_chsw[i].link_conf = link->conf; + vif_chsw[i].link_conf = iter.link->conf; i++; } @@ -1551,7 +1647,7 @@ static int ieee80211_chsw_switch_ctxs(struct ieee80211_local *local) if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; - if (!list_empty(&ctx->replace_ctx->assigned_links)) + if (ieee80211_chanctx_num_assigned(local, ctx) != 0) continue; ieee80211_del_chanctx(local, ctx->replace_ctx, false); @@ -1568,7 +1664,7 @@ static int ieee80211_chsw_switch_ctxs(struct ieee80211_local *local) if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; - if (!list_empty(&ctx->replace_ctx->assigned_links)) + if (ieee80211_chanctx_num_assigned(local, ctx) != 0) continue; ieee80211_del_chanctx(local, ctx, false); @@ -1603,7 +1699,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) */ list_for_each_entry(ctx, &local->chanctx_list, list) { - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; @@ -1619,12 +1715,11 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) n_reserved = 0; n_ready = 0; - list_for_each_entry(link, &ctx->replace_ctx->assigned_links, - assigned_chanctx_list) { + for_each_chanctx_user_assigned(local, ctx, &iter) { n_assigned++; - if (link->reserved_chanctx) { + if (iter.link->reserved_chanctx) { n_reserved++; - if (link->reserved_ready) + if (iter.link->reserved_ready) n_ready++; } } @@ -1641,13 +1736,12 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) } ctx->conf.radar_enabled = false; - list_for_each_entry(link, &ctx->reserved_links, - reserved_chanctx_list) { - if (ieee80211_link_has_in_place_reservation(link) && - !link->reserved_ready) + for_each_chanctx_user_reserved(local, ctx, &iter) { + if (ieee80211_link_has_in_place_reservation(iter.link) && + !iter.link->reserved_ready) return -EAGAIN; - old_ctx = ieee80211_link_get_chanctx(link); + old_ctx = ieee80211_link_get_chanctx(iter.link); if (old_ctx) { if (old_ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED) @@ -1658,7 +1752,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) n_vifs_ctxless++; } - if (link->reserved_radar_required) + if (iter.radar_required) ctx->conf.radar_enabled = true; } } @@ -1673,7 +1767,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) /* update station rate control and min width before switch */ list_for_each_entry(ctx, &local->chanctx_list, list) { - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; @@ -1683,17 +1777,16 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) goto err; } - list_for_each_entry(link, &ctx->reserved_links, - reserved_chanctx_list) { - if (!ieee80211_link_has_in_place_reservation(link)) + for_each_chanctx_user_reserved(local, ctx, &iter) { + if (!ieee80211_link_has_in_place_reservation(iter.link)) continue; ieee80211_chan_bw_change(local, - ieee80211_link_get_chanctx(link), + ieee80211_link_get_chanctx(iter.link), true, true); } - ieee80211_recalc_chanctx_min_def(local, ctx, NULL, true); + _ieee80211_recalc_chanctx_min_def(local, ctx, NULL, true); } /* @@ -1718,7 +1811,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) * context(s). */ list_for_each_entry(ctx, &local->chanctx_list, list) { - struct ieee80211_link_data *link, *link_tmp; + struct ieee80211_chanctx_user_iter iter; if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; @@ -1728,9 +1821,9 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) goto err; } - list_for_each_entry(link, &ctx->reserved_links, - reserved_chanctx_list) { - struct ieee80211_sub_if_data *sdata = link->sdata; + for_each_chanctx_user_reserved(local, ctx, &iter) { + struct ieee80211_link_data *link = iter.link; + struct ieee80211_sub_if_data *sdata = iter.sdata; struct ieee80211_bss_conf *link_conf = link->conf; u64 changed = 0; @@ -1746,9 +1839,9 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_check_fast_xmit_iface(sdata); - link->radar_required = link->reserved_radar_required; + link->radar_required = iter.radar_required; - if (link_conf->chanreq.oper.width != link->reserved.oper.width) + if (link_conf->chanreq.oper.width != iter.chanreq->oper.width) changed = BSS_CHANGED_BANDWIDTH; ieee80211_link_update_chanreq(link, &link->reserved); @@ -1763,19 +1856,15 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) ieee80211_recalc_chanctx_chantype(local, ctx); ieee80211_recalc_smps_chanctx(local, ctx); ieee80211_recalc_radar_chanctx(local, ctx); - ieee80211_recalc_chanctx_min_def(local, ctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, ctx); - list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, - reserved_chanctx_list) { - if (ieee80211_link_get_chanctx(link) != ctx) + for_each_chanctx_user_reserved(local, ctx, &iter) { + if (ieee80211_link_get_chanctx(iter.link) != ctx) continue; - list_del(&link->reserved_chanctx_list); - list_move(&link->assigned_chanctx_list, - &ctx->assigned_links); - link->reserved_chanctx = NULL; + iter.link->reserved_chanctx = NULL; - ieee80211_link_chanctx_reservation_complete(link); + ieee80211_link_chanctx_reservation_complete(iter.link); ieee80211_chan_bw_change(local, ctx, false, false); } @@ -1786,12 +1875,10 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) * reservation for originally requested interface has already * succeeded at this point. */ - list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, - reserved_chanctx_list) { - if (WARN_ON(ieee80211_link_has_in_place_reservation(link))) - continue; + for_each_chanctx_user_reserved(local, ctx, &iter) { + struct ieee80211_link_data *link = iter.link; - if (WARN_ON(link->reserved_chanctx != ctx)) + if (WARN_ON(ieee80211_link_has_in_place_reservation(link))) continue; if (!link->reserved_ready) @@ -1834,15 +1921,14 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local) err: list_for_each_entry(ctx, &local->chanctx_list, list) { - struct ieee80211_link_data *link, *link_tmp; + struct ieee80211_chanctx_user_iter iter; if (ctx->replace_state != IEEE80211_CHANCTX_REPLACES_OTHER) continue; - list_for_each_entry_safe(link, link_tmp, &ctx->reserved_links, - reserved_chanctx_list) { - ieee80211_link_unreserve_chanctx(link); - ieee80211_link_chanctx_reservation_complete(link); + for_each_chanctx_user_reserved(local, ctx, &iter) { + ieee80211_link_unreserve_chanctx(iter.link); + ieee80211_link_chanctx_reservation_complete(iter.link); } } @@ -1949,7 +2035,6 @@ int _ieee80211_link_use_channel(struct ieee80211_link_data *link, /* remove reservation */ WARN_ON(link->reserved_chanctx != ctx); link->reserved_chanctx = NULL; - list_del(&link->reserved_chanctx_list); } if (ret) { @@ -2046,29 +2131,17 @@ ieee80211_chanctx_recheck(struct ieee80211_local *local, struct ieee80211_chan_req *tmp) { const struct ieee80211_chan_req *ret = req; - struct ieee80211_link_data *link; + struct ieee80211_chanctx_user_iter iter; lockdep_assert_wiphy(local->hw.wiphy); - for_each_sdata_link(local, link) { - if (link == skip_link) + for_each_chanctx_user_all(local, ctx, &iter) { + if (iter.link == skip_link) continue; - if (rcu_access_pointer(link->conf->chanctx_conf) == &ctx->conf) { - ret = ieee80211_chanreq_compatible(ret, - &link->conf->chanreq, - tmp); - if (!ret) - return NULL; - } - - if (link->reserved_chanctx == ctx) { - ret = ieee80211_chanreq_compatible(ret, - &link->reserved, - tmp); - if (!ret) - return NULL; - } + ret = ieee80211_chanreq_compatible(ret, iter.chanreq, tmp); + if (!ret) + return NULL; } *tmp = *ret; diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c index ba9fba1659265..49753b73aba26 100644 --- a/net/mac80211/driver-ops.c +++ b/net/mac80211/driver-ops.c @@ -476,8 +476,12 @@ void drv_link_info_changed(struct ieee80211_local *local, if (WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE || sdata->vif.type == NL80211_IFTYPE_NAN || (sdata->vif.type == NL80211_IFTYPE_MONITOR && - !sdata->vif.bss_conf.mu_mimo_owner && - !(changed & BSS_CHANGED_TXPOWER)))) + changed & ~(BSS_CHANGED_TXPOWER | + BSS_CHANGED_MU_GROUPS)))) + return; + + if (WARN_ON_ONCE(changed & BSS_CHANGED_MU_GROUPS && + !sdata->vif.bss_conf.mu_mimo_owner)) return; if (!check_sdata_in_driver(sdata)) diff --git a/net/mac80211/he.c b/net/mac80211/he.c index 5792ef77e986b..f7b05e59374c7 100644 --- a/net/mac80211/he.c +++ b/net/mac80211/he.c @@ -3,7 +3,7 @@ * HE handling * * Copyright(c) 2017 Intel Deutschland GmbH - * Copyright(c) 2019 - 2024 Intel Corporation + * Copyright(c) 2019-2025 Intel Corporation */ #include "ieee80211_i.h" @@ -313,7 +313,7 @@ bool ieee80211_prepare_rx_omi_bw(struct ieee80211_link_sta *pub_link_sta, ieee80211_link_sta_rc_update_omi(link, link_sta); } else { link_sta->rx_omi_bw_rx = bw; - ieee80211_recalc_chanctx_min_def(local, chanctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, chanctx); } link_sta->rx_omi_bw_staging = bw; @@ -359,7 +359,7 @@ void ieee80211_finalize_rx_omi_bw(struct ieee80211_link_sta *pub_link_sta) /* channel context in finalize only when narrowing bandwidth */ WARN_ON(link_sta->rx_omi_bw_rx < link_sta->rx_omi_bw_staging); link_sta->rx_omi_bw_rx = link_sta->rx_omi_bw_staging; - ieee80211_recalc_chanctx_min_def(local, chanctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, chanctx); } trace_api_return_void(local); diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 6e36b09fe97f8..168f84a1353ba 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -9,7 +9,7 @@ * Copyright 2009, Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright(c) 2016 Intel Deutschland GmbH - * Copyright(c) 2018-2024 Intel Corporation + * Copyright(c) 2018-2025 Intel Corporation */ #include @@ -1554,6 +1554,7 @@ void ieee80211_rx_mgmt_probe_beacon(struct ieee80211_sub_if_data *sdata, { size_t baselen; struct ieee802_11_elems *elems; + u16 type; BUILD_BUG_ON(offsetof(typeof(mgmt->u.probe_resp), variable) != offsetof(typeof(mgmt->u.beacon), variable)); @@ -1566,8 +1567,9 @@ void ieee80211_rx_mgmt_probe_beacon(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; + type = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_TYPE; elems = ieee802_11_parse_elems(mgmt->u.probe_resp.variable, - len - baselen, false, NULL); + len - baselen, type, NULL); if (elems) { ieee80211_rx_bss_info(sdata, mgmt, len, rx_status, elems); @@ -1616,9 +1618,11 @@ void ieee80211_ibss_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, if (ies_len < 0) break; - elems = ieee802_11_parse_elems( - mgmt->u.action.u.chan_switch.variable, - ies_len, true, NULL); + elems = ieee802_11_parse_elems(mgmt->u.action.u.chan_switch.variable, + ies_len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (elems && !elems->parse_error) ieee80211_rx_mgmt_spectrum_mgmt(sdata, mgmt, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 878c3b14aeb80..9d9313eee59f8 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -916,9 +916,6 @@ struct ieee80211_chanctx { struct list_head list; struct rcu_head rcu_head; - struct list_head assigned_links; - struct list_head reserved_links; - enum ieee80211_chanctx_replace_state replace_state; struct ieee80211_chanctx *replace_ctx; @@ -1071,9 +1068,6 @@ struct ieee80211_link_data { struct ieee80211_sub_if_data *sdata; unsigned int link_id; - struct list_head assigned_chanctx_list; /* protected by wiphy mutex */ - struct list_head reserved_chanctx_list; /* protected by wiphy mutex */ - /* multicast keys only */ struct ieee80211_key __rcu *gtk[NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS + @@ -1239,9 +1233,12 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) for (struct ieee80211_sub_if_data *___sdata = NULL; \ !___sdata; \ ___sdata = (void *)~0 /* always stop */) \ + for (int ___link_id = ARRAY_SIZE(___sdata->link); \ + ___link_id; ___link_id = 0 /* always stop */) \ list_for_each_entry(___sdata, &(_local)->interfaces, list) \ - if (ieee80211_sdata_running(___sdata)) \ - for (int ___link_id = 0; \ + if (___link_id == ARRAY_SIZE(___sdata->link) && \ + ieee80211_sdata_running(___sdata)) \ + for (___link_id = 0; \ ___link_id < ARRAY_SIZE(___sdata->link); \ ___link_id++) \ if ((_link = wiphy_dereference((_local)->hw.wiphy, \ @@ -1255,9 +1252,12 @@ struct ieee80211_sub_if_data *vif_to_sdata(struct ieee80211_vif *p) for (struct ieee80211_sub_if_data *___sdata = NULL; \ !___sdata; \ ___sdata = (void *)~0 /* always stop */) \ - list_for_each_entry_rcu(___sdata, &(_local)->interfaces, list) \ - if (ieee80211_sdata_running(___sdata)) \ - for (int ___link_id = 0; \ + for (int ___link_id = ARRAY_SIZE(___sdata->link); \ + ___link_id; ___link_id = 0 /* always stop */) \ + list_for_each_entry(___sdata, &(_local)->interfaces, list) \ + if (___link_id == ARRAY_SIZE(___sdata->link) && \ + ieee80211_sdata_running(___sdata)) \ + for (___link_id = 0; \ ___link_id < ARRAY_SIZE((___sdata)->link); \ ___link_id++) \ if ((_link = rcu_dereference((___sdata)->link[___link_id]))) @@ -2107,7 +2107,8 @@ void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata, const int offset); int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up); void ieee80211_sdata_stop(struct ieee80211_sub_if_data *sdata); -int ieee80211_add_virtual_monitor(struct ieee80211_local *local); +int ieee80211_add_virtual_monitor(struct ieee80211_local *local, + struct ieee80211_sub_if_data *creator_sdata); void ieee80211_del_virtual_monitor(struct ieee80211_local *local); bool __ieee80211_recalc_txpower(struct ieee80211_link_data *link); @@ -2422,7 +2423,8 @@ static inline void ieee80211_tx_skb(struct ieee80211_sub_if_data *sdata, * @mode: connection mode for parsing * @start: pointer to the elements * @len: length of the elements - * @action: %true if the elements came from an action frame + * @type: type of the frame the elements came from + * (action, probe response, beacon, etc.) * @filter: bitmap of element IDs to filter out while calculating * the element CRC * @crc: CRC starting value @@ -2440,7 +2442,7 @@ struct ieee80211_elems_parse_params { enum ieee80211_conn_mode mode; const u8 *start; size_t len; - bool action; + u8 type; u64 filter; u32 crc; struct cfg80211_bss *bss; @@ -2452,17 +2454,14 @@ struct ieee802_11_elems * ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params); static inline struct ieee802_11_elems * -ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, - u64 filter, u32 crc, - struct cfg80211_bss *bss) +ieee802_11_parse_elems(const u8 *start, size_t len, u8 type, + struct cfg80211_bss *bss) { struct ieee80211_elems_parse_params params = { .mode = IEEE80211_CONN_MODE_HIGHEST, .start = start, .len = len, - .action = action, - .filter = filter, - .crc = crc, + .type = type, .bss = bss, .link_id = -1, }; @@ -2470,13 +2469,6 @@ ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, return ieee802_11_parse_elems_full(¶ms); } -static inline struct ieee802_11_elems * -ieee802_11_parse_elems(const u8 *start, size_t len, bool action, - struct cfg80211_bss *bss) -{ - return ieee802_11_parse_elems_crc(start, len, action, 0, 0, bss); -} - extern const int ieee802_1d_to_ac[8]; static inline int ieee80211_ac_from_tid(int tid) @@ -2768,9 +2760,7 @@ int ieee80211_chanctx_refcount(struct ieee80211_local *local, void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local, struct ieee80211_chanctx *chanctx); void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local, - struct ieee80211_chanctx *ctx, - struct ieee80211_link_data *rsvd_for, - bool check_reserved); + struct ieee80211_chanctx *ctx); bool ieee80211_is_radar_required(struct ieee80211_local *local, struct cfg80211_scan_request *req); bool ieee80211_is_radio_idx_in_scan_req(struct wiphy *wiphy, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 0ca55b9655a7f..4f04d95c19d49 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -741,8 +741,9 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do ieee80211_configure_filter(local); ieee80211_hw_config(local, -1, hw_reconf_flags); + /* Passing NULL means an interface is picked for configuration */ if (local->virt_monitors == local->open_count) - ieee80211_add_virtual_monitor(local); + ieee80211_add_virtual_monitor(local, NULL); } void ieee80211_stop_mbssid(struct ieee80211_sub_if_data *sdata) @@ -1176,7 +1177,8 @@ static void ieee80211_sdata_init(struct ieee80211_local *local, ieee80211_link_init(sdata, -1, &sdata->deflink, &sdata->vif.bss_conf); } -int ieee80211_add_virtual_monitor(struct ieee80211_local *local) +int ieee80211_add_virtual_monitor(struct ieee80211_local *local, + struct ieee80211_sub_if_data *creator_sdata) { struct ieee80211_sub_if_data *sdata; int ret; @@ -1184,10 +1186,14 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) ASSERT_RTNL(); lockdep_assert_wiphy(local->hw.wiphy); - if (local->monitor_sdata || - ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) + if (ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) return 0; + /* Already have a monitor set up, configure it */ + sdata = wiphy_dereference(local->hw.wiphy, local->monitor_sdata); + if (sdata) + goto configure_monitor; + sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL); if (!sdata) return -ENOMEM; @@ -1240,6 +1246,32 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) skb_queue_head_init(&sdata->status_queue); wiphy_work_init(&sdata->work, ieee80211_iface_work); +configure_monitor: + /* Copy in the MU-MIMO configuration if set */ + if (!creator_sdata) { + struct ieee80211_sub_if_data *other; + + list_for_each_entry(other, &local->mon_list, list) { + if (!other->vif.bss_conf.mu_mimo_owner) + continue; + + creator_sdata = other; + break; + } + } + + if (creator_sdata && creator_sdata->vif.bss_conf.mu_mimo_owner) { + sdata->vif.bss_conf.mu_mimo_owner = true; + memcpy(&sdata->vif.bss_conf.mu_group, + &creator_sdata->vif.bss_conf.mu_group, + sizeof(sdata->vif.bss_conf.mu_group)); + memcpy(&sdata->u.mntr.mu_follow_addr, + creator_sdata->u.mntr.mu_follow_addr, ETH_ALEN); + + ieee80211_link_info_change_notify(sdata, &sdata->deflink, + BSS_CHANGED_MU_GROUPS); + } + return 0; } @@ -1396,11 +1428,13 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up) if (res) goto err_stop; } else { - if (local->virt_monitors == 0 && local->open_count == 0) { - res = ieee80211_add_virtual_monitor(local); + /* add/configure if there is no non-monitor interface */ + if (local->virt_monitors == local->open_count) { + res = ieee80211_add_virtual_monitor(local, sdata); if (res) goto err_stop; } + local->virt_monitors++; /* must be before the call to ieee80211_configure_filter */ diff --git a/net/mac80211/link.c b/net/mac80211/link.c index 4a19b765ccb69..1e05845872afc 100644 --- a/net/mac80211/link.c +++ b/net/mac80211/link.c @@ -23,9 +23,6 @@ static void ieee80211_update_apvlan_links(struct ieee80211_sub_if_data *sdata) list_for_each_entry(vlan, &sdata->u.ap.vlans, u.vlan.list) { int link_id; - if (!vlan) - continue; - /* No support for 4addr with MLO yet */ if (vlan->wdev.use_4addr) return; @@ -119,8 +116,6 @@ void ieee80211_link_init(struct ieee80211_sub_if_data *sdata, ieee80211_color_change_finalize_work); wiphy_delayed_work_init(&link->color_collision_detect_work, ieee80211_color_collision_detection_work); - INIT_LIST_HEAD(&link->assigned_chanctx_list); - INIT_LIST_HEAD(&link->reserved_chanctx_list); wiphy_delayed_work_init(&link->dfs_cac_timer_work, ieee80211_dfs_cac_timer_work); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index eefa6f7e899bd..b05e313c7f176 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -356,8 +356,7 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata, if (WARN_ON_ONCE(sdata->vif.type == NL80211_IFTYPE_P2P_DEVICE || sdata->vif.type == NL80211_IFTYPE_NAN || (sdata->vif.type == NL80211_IFTYPE_MONITOR && - !sdata->vif.bss_conf.mu_mimo_owner && - !(changed & BSS_CHANGED_TXPOWER)))) + changed & ~BSS_CHANGED_TXPOWER))) return; if (!check_sdata_in_driver(sdata)) diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index f37068a533f4e..68901f1def0dd 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2018 - 2024 Intel Corporation + * Copyright (C) 2018 - 2025 Intel Corporation * Authors: Luis Carlos Cobo * Javier Cardona */ @@ -1410,7 +1410,10 @@ ieee80211_mesh_rx_probe_req(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; - elems = ieee802_11_parse_elems(pos, len - baselen, false, NULL); + elems = ieee802_11_parse_elems(pos, len - baselen, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_PROBE_REQ, + NULL); if (!elems) return; @@ -1455,11 +1458,11 @@ ieee80211_mesh_rx_probe_req(struct ieee80211_sub_if_data *sdata, } static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, - u16 stype, struct ieee80211_mgmt *mgmt, size_t len, struct ieee80211_rx_status *rx_status) { + u16 type = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_TYPE; struct ieee80211_local *local = sdata->local; struct ieee80211_if_mesh *ifmsh = &sdata->u.mesh; struct ieee802_11_elems *elems; @@ -1469,7 +1472,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, enum nl80211_band band = rx_status->band; /* ignore ProbeResp to foreign address */ - if (stype == IEEE80211_STYPE_PROBE_RESP && + if (type == (IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP) && !ether_addr_equal(mgmt->da, sdata->vif.addr)) return; @@ -1478,8 +1481,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, return; elems = ieee802_11_parse_elems(mgmt->u.probe_resp.variable, - len - baselen, - false, NULL); + len - baselen, type, NULL); if (!elems) return; @@ -1514,7 +1516,9 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, } if (ifmsh->sync_ops) - ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, len, + ifmsh->sync_ops->rx_bcn_presp(sdata, + type & IEEE80211_FCTL_STYPE, + mgmt, len, elems->mesh_config, rx_status); free: kfree(elems); @@ -1622,7 +1626,10 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, pos = mgmt->u.action.u.chan_switch.variable; baselen = offsetof(struct ieee80211_mgmt, u.action.u.chan_switch.variable); - elems = ieee802_11_parse_elems(pos, len - baselen, true, NULL); + elems = ieee802_11_parse_elems(pos, len - baselen, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems) return; @@ -1699,8 +1706,7 @@ void ieee80211_mesh_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, switch (stype) { case IEEE80211_STYPE_PROBE_RESP: case IEEE80211_STYPE_BEACON: - ieee80211_mesh_rx_bcn_presp(sdata, stype, mgmt, skb->len, - rx_status); + ieee80211_mesh_rx_bcn_presp(sdata, mgmt, skb->len, rx_status); break; case IEEE80211_STYPE_PROBE_REQ: ieee80211_mesh_rx_probe_req(sdata, mgmt, skb->len); diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 9101858525dd8..a41b57bd11ff5 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2019, 2021-2023 Intel Corporation + * Copyright (C) 2019, 2021-2023, 2025 Intel Corporation * Author: Luis Carlos Cobo */ @@ -951,7 +951,10 @@ void mesh_rx_path_sel_frame(struct ieee80211_sub_if_data *sdata, baselen = (u8 *) mgmt->u.action.u.mesh_action.variable - (u8 *) mgmt; elems = ieee802_11_parse_elems(mgmt->u.action.u.mesh_action.variable, - len - baselen, false, NULL); + len - baselen, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems) return; diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c index cb45a5d2009d2..04c931cd20637 100644 --- a/net/mac80211/mesh_plink.c +++ b/net/mac80211/mesh_plink.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, 2009 open80211s Ltd. - * Copyright (C) 2019, 2021-2024 Intel Corporation + * Copyright (C) 2019, 2021-2025 Intel Corporation * Author: Luis Carlos Cobo */ #include @@ -1248,7 +1248,10 @@ void mesh_rx_plink_frame(struct ieee80211_sub_if_data *sdata, if (baselen > len) return; } - elems = ieee802_11_parse_elems(baseaddr, len - baselen, true, NULL); + elems = ieee802_11_parse_elems(baseaddr, len - baselen, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (elems) { mesh_process_plink_frame(sdata, mgmt, elems, rx_status); kfree(elems); diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index f3138d1585353..c705d3f45affe 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -276,11 +276,8 @@ ieee80211_determine_ap_chan(struct ieee80211_sub_if_data *sdata, return IEEE80211_CONN_MODE_VHT; } } else if (!vht_oper || !elems->vht_cap_elem) { - if (sband->band == NL80211_BAND_5GHZ) { - sdata_info(sdata, - "VHT information is missing, disabling VHT\n"); + if (sband->band == NL80211_BAND_5GHZ) return IEEE80211_CONN_MODE_HT; - } no_vht = true; } else if (sband->band == NL80211_BAND_2GHZ) { no_vht = true; @@ -1002,6 +999,9 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata, .from_ap = true, .start = ies->data, .len = ies->len, + .type = ies->from_beacon ? + IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON : + IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP, }; struct ieee802_11_elems *elems; struct ieee80211_supported_band *sband; @@ -2508,6 +2508,16 @@ static void ieee80211_csa_switch_work(struct wiphy *wiphy, link->u.mgd.csa.waiting_bcn = true; + /* + * The next beacon really should always be different, so this should + * have no effect whatsoever. However, some APs (we observed this in + * an Asus AXE11000), the beacon after the CSA might be identical to + * the last beacon on the old channel - in this case we'd ignore it. + * Resetting the CRC will lead us to handle it better (albeit with a + * disconnect, but clearly the AP is broken.) + */ + link->u.mgd.beacon_crc_valid = false; + /* apply new TPE restrictions immediately on the new channel */ if (link->u.mgd.csa.ap_chandef.chan->band == NL80211_BAND_6GHZ && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HE) { @@ -5170,7 +5180,9 @@ static void ieee80211_epcs_teardown(struct ieee80211_sub_if_data *sdata) continue; } - elems = ieee802_11_parse_elems(ies->data, ies->len, false, + elems = ieee802_11_parse_elems(ies->data, ies->len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_BEACON, NULL); if (!elems) { rcu_read_unlock(); @@ -5216,6 +5228,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link, .len = elem_len, .link_id = link_id == assoc_data->assoc_link_id ? -1 : link_id, .from_ap = true, + .type = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_TYPE, }; bool is_5ghz = cbss->channel->band == NL80211_BAND_5GHZ; bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ; @@ -6021,24 +6034,6 @@ ieee80211_determine_our_sta_mode_assoc(struct ieee80211_sub_if_data *sdata, conn->bw_limit, tmp.bw_limit); } -static enum ieee80211_ap_reg_power -ieee80211_ap_power_type(u8 control) -{ - switch (u8_get_bits(control, IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { - case IEEE80211_6GHZ_CTRL_REG_LPI_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: - return IEEE80211_REG_LPI_AP; - case IEEE80211_6GHZ_CTRL_REG_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD: - return IEEE80211_REG_SP_AP; - case IEEE80211_6GHZ_CTRL_REG_VLP_AP: - return IEEE80211_REG_VLP_AP; - default: - return IEEE80211_REG_UNSET_AP; - } -} - static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, struct ieee80211_link_data *link, int link_id, @@ -6081,7 +6076,8 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata, he_6ghz_oper = ieee80211_he_6ghz_oper(elems->he_operation); if (he_6ghz_oper) link->conf->power_type = - ieee80211_ap_power_type(he_6ghz_oper->control); + cfg80211_6ghz_power_type(he_6ghz_oper->control, + cbss->channel->flags); else link_info(link, "HE 6 GHz operation missing (on %d MHz), expect issues\n", @@ -6349,6 +6345,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata, .bss = NULL, .link_id = -1, .from_ap = true, + .type = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_TYPE, }; struct ieee802_11_elems *elems; int ac; @@ -6610,8 +6607,8 @@ static void ieee80211_rx_mgmt_probe_resp(struct ieee80211_link_data *link, * Response frame shall be set to the broadcast address [..]" * So, on 6GHz band we should also accept broadcast responses. */ - channel = ieee80211_get_channel(sdata->local->hw.wiphy, - rx_status->freq); + channel = ieee80211_get_channel_khz(sdata->local->hw.wiphy, + ieee80211_rx_status_to_khz(rx_status)); if (!channel) return; @@ -7257,7 +7254,9 @@ ieee80211_mgd_check_cross_link_csa(struct ieee80211_sub_if_data *sdata, (prof->sta_info_len - 1), len - (prof->sta_info_len - 1), - false, NULL); + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_BEACON, + NULL); /* memory allocation failed - let's hope that's transient */ if (!prof_elems) @@ -7361,6 +7360,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link, .mode = link->u.mgd.conn.mode, .link_id = -1, .from_ap = true, + .type = le16_to_cpu(mgmt->frame_control) & IEEE80211_FCTL_TYPE, }; lockdep_assert_wiphy(local->hw.wiphy); @@ -7963,7 +7963,10 @@ void ieee80211_process_neg_ttlm_req(struct ieee80211_sub_if_data *sdata, ies_len = len - offsetof(struct ieee80211_mgmt, u.action.u.ttlm_req.variable); elems = ieee802_11_parse_elems(mgmt->u.action.u.ttlm_req.variable, - ies_len, true, NULL); + ies_len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems) { ttlm_res = NEG_TTLM_RES_REJECT; goto out; @@ -8169,9 +8172,11 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, break; /* CSA IE cannot be overridden, no need for BSSID */ - elems = ieee802_11_parse_elems( - mgmt->u.action.u.chan_switch.variable, - ies_len, true, NULL); + elems = ieee802_11_parse_elems(mgmt->u.action.u.chan_switch.variable, + ies_len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (elems && !elems->parse_error) { enum ieee80211_csa_source src = @@ -8198,9 +8203,11 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata, * extended CSA IE can't be overridden, no need for * BSSID */ - elems = ieee802_11_parse_elems( - mgmt->u.action.u.ext_chan_switch.variable, - ies_len, true, NULL); + elems = ieee802_11_parse_elems(mgmt->u.action.u.ext_chan_switch.variable, + ies_len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (elems && !elems->parse_error) { enum ieee80211_csa_source src; @@ -10978,7 +10985,10 @@ static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata, pos = scratch + sizeof(control); len -= sizeof(control); - link_elems = ieee802_11_parse_elems(pos, len, false, NULL); + link_elems = ieee802_11_parse_elems(pos, len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!link_elems) continue; @@ -11029,7 +11039,10 @@ void ieee80211_process_epcs_ena_resp(struct ieee80211_sub_if_data *sdata, u.action.u.epcs.variable) - IEEE80211_EPCS_ENA_RESP_BODY_LEN; - elems = ieee802_11_parse_elems(pos, ies_len, true, NULL); + elems = ieee802_11_parse_elems(pos, ies_len, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems) return; diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c index c5e0f7f460048..bfc4ecb7a048e 100644 --- a/net/mac80211/parse.c +++ b/net/mac80211/parse.c @@ -6,7 +6,7 @@ * Copyright 2007 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015-2017 Intel Deutschland GmbH - * Copyright (C) 2018-2024 Intel Corporation + * Copyright (C) 2018-2025 Intel Corporation * * element parsing for mac80211 */ @@ -286,6 +286,24 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, bitmap_zero(seen_elems, 256); + switch (params->type) { + /* we don't need to parse assoc request, luckily (it's value 0) */ + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_REQ: + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_REQ: + default: + WARN(1, "invalid frame type 0x%x for element parsing\n", + params->type); + break; + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ASSOC_RESP: + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_REASSOC_RESP: + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_REQ: + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP: + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON: + case IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_ACTION: + case IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON: + break; + } + for_each_element(elem, params->start, params->len) { const struct element *subelem; u8 elem_parse_failed; @@ -566,7 +584,8 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, if (params->mode < IEEE80211_CONN_MODE_VHT) break; - if (!params->action) { + if (params->type != (IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION)) { elem_parse_failed = IEEE80211_PARSE_ERR_UNEXPECTED_ELEM; break; @@ -582,7 +601,8 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params, case WLAN_EID_CHANNEL_SWITCH_WRAPPER: if (params->mode < IEEE80211_CONN_MODE_VHT) break; - if (params->action) { + if (params->type == (IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION)) { elem_parse_failed = IEEE80211_PARSE_ERR_UNEXPECTED_ELEM; break; @@ -942,7 +962,7 @@ ieee80211_prep_mle_link_parse(struct ieee80211_elems_parse *elems_parse, sub->len = end - sub->start; sub->mode = params->mode; - sub->action = params->action; + sub->type = params->type; sub->from_ap = params->from_ap; sub->link_id = -1; @@ -1041,7 +1061,7 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params) sub.start = elems_parse->scratch_pos; sub.mode = params->mode; sub.len = nontx_len; - sub.action = params->action; + sub.type = params->type; sub.link_id = params->link_id; /* consume the space used for non-transmitted profile */ diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 5b4c3fe9970ad..cc26c279984d7 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -59,7 +59,8 @@ static struct sk_buff *ieee80211_clean_skb(struct sk_buff *skb, status->flag &= ~(RX_FLAG_RADIOTAP_TLV_AT_END | RX_FLAG_RADIOTAP_LSIG | RX_FLAG_RADIOTAP_HE_MU | - RX_FLAG_RADIOTAP_HE); + RX_FLAG_RADIOTAP_HE | + RX_FLAG_RADIOTAP_VHT); hdr = (void *)skb->data; fc = hdr->frame_control; @@ -151,8 +152,10 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, } if (status->encoding == RX_ENC_VHT) { + /* Included even if RX_FLAG_RADIOTAP_VHT is not set */ len = ALIGN(len, 2); len += 12; + BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_vht) != 12); } if (local->hw.radiotap_timestamp.units_pos >= 0) { @@ -195,6 +198,9 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local, * The position to look at depends on the existence (or non- * existence) of other elements, so take that into account... */ + if (status->flag & RX_FLAG_RADIOTAP_VHT) + tlv_offset += + sizeof(struct ieee80211_radiotap_vht); if (status->flag & RX_FLAG_RADIOTAP_HE) tlv_offset += sizeof(struct ieee80211_radiotap_he); @@ -319,10 +325,17 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, u32 tlvs_len = 0; int mpdulen, chain; unsigned long chains = status->chains; + struct ieee80211_radiotap_vht vht = {}; struct ieee80211_radiotap_he he = {}; struct ieee80211_radiotap_he_mu he_mu = {}; struct ieee80211_radiotap_lsig lsig = {}; + if (status->flag & RX_FLAG_RADIOTAP_VHT) { + vht = *(struct ieee80211_radiotap_vht *)skb->data; + skb_pull(skb, sizeof(vht)); + WARN_ON_ONCE(status->encoding != RX_ENC_VHT); + } + if (status->flag & RX_FLAG_RADIOTAP_HE) { he = *(struct ieee80211_radiotap_he *)skb->data; skb_pull(skb, sizeof(he)); @@ -530,45 +543,61 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local, } if (status->encoding == RX_ENC_VHT) { - u16 known = local->hw.radiotap_vht_details; + u16 fill = local->hw.radiotap_vht_details; - rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); - put_unaligned_le16(known, pos); - pos += 2; - /* flags */ - if (status->enc_flags & RX_ENC_FLAG_SHORT_GI) - *pos |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; + /* Leave driver filled fields alone */ + fill &= ~le16_to_cpu(vht.known); + vht.known |= cpu_to_le16(fill); + + if (fill & IEEE80211_RADIOTAP_VHT_KNOWN_GI && + status->enc_flags & RX_ENC_FLAG_SHORT_GI) + vht.flags |= IEEE80211_RADIOTAP_VHT_FLAG_SGI; /* in VHT, STBC is binary */ - if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) - *pos |= IEEE80211_RADIOTAP_VHT_FLAG_STBC; - if (status->enc_flags & RX_ENC_FLAG_BF) + if (fill & IEEE80211_RADIOTAP_VHT_KNOWN_STBC && + status->enc_flags & RX_ENC_FLAG_STBC_MASK) + vht.flags |= IEEE80211_RADIOTAP_VHT_FLAG_STBC; + if (fill & IEEE80211_RADIOTAP_VHT_KNOWN_BEAMFORMED && + status->enc_flags & RX_ENC_FLAG_BF) *pos |= IEEE80211_RADIOTAP_VHT_FLAG_BEAMFORMED; - pos++; - /* bandwidth */ - switch (status->bw) { - case RATE_INFO_BW_80: - *pos++ = 4; - break; - case RATE_INFO_BW_160: - *pos++ = 11; - break; - case RATE_INFO_BW_40: - *pos++ = 1; - break; - default: - *pos++ = 0; + + if (fill & IEEE80211_RADIOTAP_VHT_KNOWN_BANDWIDTH) { + switch (status->bw) { + case RATE_INFO_BW_40: + vht.bandwidth = IEEE80211_RADIOTAP_VHT_BW_40; + break; + case RATE_INFO_BW_80: + vht.bandwidth = IEEE80211_RADIOTAP_VHT_BW_80; + break; + case RATE_INFO_BW_160: + vht.bandwidth = IEEE80211_RADIOTAP_VHT_BW_160; + break; + default: + vht.bandwidth = IEEE80211_RADIOTAP_VHT_BW_20; + break; + } } - /* MCS/NSS */ - *pos = (status->rate_idx << 4) | status->nss; - pos += 4; - /* coding field */ - if (status->enc_flags & RX_ENC_FLAG_LDPC) - *pos |= IEEE80211_RADIOTAP_CODING_LDPC_USER0; - pos++; - /* group ID */ - pos++; - /* partial_aid */ - pos += 2; + + /* + * If the driver filled in mcs_nss[0], then do not touch it. + * + * Otherwise, put some information about MCS/NSS into the + * user 0 field. Note that this is not technically correct for + * an MU frame as we might have decoded a different user. + */ + if (!vht.mcs_nss[0]) { + vht.mcs_nss[0] = (status->rate_idx << 4) | status->nss; + + /* coding field */ + if (status->enc_flags & RX_ENC_FLAG_LDPC) + vht.coding |= IEEE80211_RADIOTAP_CODING_LDPC_USER0; + } + + /* ensure 2 byte alignment */ + while ((pos - (u8 *)rthdr) & 1) + pos++; + rthdr->it_present |= cpu_to_le32(BIT(IEEE80211_RADIOTAP_VHT)); + memcpy(pos, &vht, sizeof(vht)); + pos += sizeof(vht); } if (local->hw.radiotap_timestamp.units_pos >= 0) { @@ -763,6 +792,51 @@ ieee80211_make_monitor_skb(struct ieee80211_local *local, return skb; } +static bool +ieee80211_validate_monitor_radio(struct ieee80211_sub_if_data *sdata, + struct ieee80211_local *local, + struct ieee80211_rx_status *status) +{ + struct wiphy *wiphy = local->hw.wiphy; + int i, freq, bw; + + if (!wiphy->n_radio) + return true; + + switch (status->bw) { + case RATE_INFO_BW_20: + bw = 20000; + break; + case RATE_INFO_BW_40: + bw = 40000; + break; + case RATE_INFO_BW_80: + bw = 80000; + break; + case RATE_INFO_BW_160: + bw = 160000; + break; + case RATE_INFO_BW_320: + bw = 320000; + break; + default: + return false; + } + + freq = MHZ_TO_KHZ(status->freq); + + for (i = 0; i < wiphy->n_radio; i++) { + if (!(sdata->wdev.radio_mask & BIT(i))) + continue; + + if (!ieee80211_radio_freq_range_valid(&wiphy->radio[i], freq, bw)) + continue; + + return true; + } + return false; +} + /* * This function copies a received frame to all monitor interfaces and * returns a cleaned-up SKB that no longer includes the FCS nor the @@ -789,6 +863,9 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, return NULL; } + if (status->flag & RX_FLAG_RADIOTAP_VHT) + rtap_space += sizeof(struct ieee80211_radiotap_vht); + if (status->flag & RX_FLAG_RADIOTAP_HE) rtap_space += sizeof(struct ieee80211_radiotap_he); @@ -855,6 +932,10 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb, chandef->chan->center_freq != status->freq) continue; + if (ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR) && + !ieee80211_validate_monitor_radio(sdata, local, status)) + continue; + if (!prev_sdata) { prev_sdata = sdata; continue; @@ -3521,8 +3602,11 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx) switch (mgmt->u.action.category) { case WLAN_CATEGORY_HT: - /* reject HT action frames from stations not supporting HT */ - if (!rx->link_sta->pub->ht_cap.ht_supported) + /* reject HT action frames from stations not supporting HT + * or not HE Capable + */ + if (!rx->link_sta->pub->ht_cap.ht_supported && + !rx->link_sta->pub->he_cap.has_he) goto invalid; if (sdata->vif.type != NL80211_IFTYPE_STATION && @@ -4903,6 +4987,11 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, /* after this point, don't punt to the slowpath! */ + if (fast_rx->uses_rss) + stats = this_cpu_ptr(rx->link_sta->pcpu_rx_stats); + else + stats = &rx->link_sta->rx_stats; + if (rx->key && !(status->flag & RX_FLAG_MIC_STRIPPED) && pskb_trim(skb, skb->len - fast_rx->icv_len)) goto drop; @@ -4937,6 +5026,8 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, res = ieee80211_rx_mesh_data(rx->sdata, rx->sta, rx->skb); switch (res) { case RX_QUEUED: + stats->last_rx = jiffies; + stats->last_rate = sta_stats_encode_rate(status); return true; case RX_CONTINUE: break; @@ -4950,11 +5041,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx, drop: dev_kfree_skb(skb); - if (fast_rx->uses_rss) - stats = this_cpu_ptr(rx->link_sta->pcpu_rx_stats); - else - stats = &rx->link_sta->rx_stats; - stats->dropped++; return true; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index bb9563f50e7b4..5ef315ed3b0fa 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -76,7 +76,11 @@ void ieee80211_inform_bss(struct wiphy *wiphy, if (!update_data) return; - elems = ieee802_11_parse_elems(ies->data, ies->len, false, NULL); + elems = ieee802_11_parse_elems(ies->data, ies->len, + update_data->beacon ? + IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON : + IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_PROBE_RESP, + NULL); if (!elems) return; diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c index ba5fbacbeeda6..dbbfe2d6842fb 100644 --- a/net/mac80211/tdls.c +++ b/net/mac80211/tdls.c @@ -6,7 +6,7 @@ * Copyright 2014, Intel Corporation * Copyright 2014 Intel Mobile Communications GmbH * Copyright 2015 - 2016 Intel Deutschland GmbH - * Copyright (C) 2019, 2021-2024 Intel Corporation + * Copyright (C) 2019, 2021-2025 Intel Corporation */ #include @@ -1783,7 +1783,10 @@ ieee80211_process_tdls_channel_switch_resp(struct ieee80211_sub_if_data *sdata, } elems = ieee802_11_parse_elems(tf->u.chan_switch_resp.variable, - skb->len - baselen, false, NULL); + skb->len - baselen, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems) { ret = -ENOMEM; goto out; @@ -1902,7 +1905,10 @@ ieee80211_process_tdls_channel_switch_req(struct ieee80211_sub_if_data *sdata, } elems = ieee802_11_parse_elems(tf->u.chan_switch_req.variable, - skb->len - baselen, false, NULL); + skb->len - baselen, + IEEE80211_FTYPE_MGMT | + IEEE80211_STYPE_ACTION, + NULL); if (!elems) return -ENOMEM; diff --git a/net/mac80211/tests/elems.c b/net/mac80211/tests/elems.c index a53c55a879a8e..1039794a01837 100644 --- a/net/mac80211/tests/elems.c +++ b/net/mac80211/tests/elems.c @@ -2,7 +2,7 @@ /* * KUnit tests for element parsing * - * Copyright (C) 2023-2024 Intel Corporation + * Copyright (C) 2023-2025 Intel Corporation */ #include #include "../ieee80211_i.h" @@ -15,6 +15,8 @@ static void mle_defrag(struct kunit *test) .link_id = 12, .from_ap = true, .mode = IEEE80211_CONN_MODE_EHT, + /* type is not really relevant here */ + .type = IEEE80211_FTYPE_MGMT | IEEE80211_STYPE_BEACON, }; struct ieee802_11_elems *parsed; struct sk_buff *skb; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index c9931537f9d2d..0c46009a3d63f 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2206,9 +2206,10 @@ int ieee80211_reconfig(struct ieee80211_local *local) } } + /* Passing NULL means an interface is picked for configuration */ if (local->virt_monitors > 0 && local->virt_monitors == local->open_count) - ieee80211_add_virtual_monitor(local); + ieee80211_add_virtual_monitor(local, NULL); if (!suspended) return 0; @@ -2347,7 +2348,7 @@ void ieee80211_recalc_min_chandef(struct ieee80211_sub_if_data *sdata, chanctx = container_of(chanctx_conf, struct ieee80211_chanctx, conf); - ieee80211_recalc_chanctx_min_def(local, chanctx, NULL, false); + ieee80211_recalc_chanctx_min_def(local, chanctx); } } @@ -4016,23 +4017,23 @@ static u8 ieee80211_chanctx_radar_detect(struct ieee80211_local *local, if (WARN_ON(ctx->replace_state == IEEE80211_CHANCTX_WILL_BE_REPLACED)) return 0; - list_for_each_entry(link, &ctx->reserved_links, reserved_chanctx_list) - if (link->reserved_radar_required) - radar_detect |= BIT(link->reserved.oper.width); - - /* - * An in-place reservation context should not have any assigned vifs - * until it replaces the other context. - */ - WARN_ON(ctx->replace_state == IEEE80211_CHANCTX_REPLACES_OTHER && - !list_empty(&ctx->assigned_links)); + for_each_sdata_link(local, link) { + if (rcu_access_pointer(link->conf->chanctx_conf) == &ctx->conf) { + /* + * An in-place reservation context should not have any + * assigned links until it replaces the other context. + */ + WARN_ON(ctx->replace_state == + IEEE80211_CHANCTX_REPLACES_OTHER); - list_for_each_entry(link, &ctx->assigned_links, assigned_chanctx_list) { - if (!link->radar_required) - continue; + if (link->radar_required) + radar_detect |= + BIT(link->conf->chanreq.oper.width); + } - radar_detect |= - BIT(link->conf->chanreq.oper.width); + if (link->reserved_chanctx == ctx && + link->reserved_radar_required) + radar_detect |= BIT(link->reserved.oper.width); } return radar_detect; diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index b99ba14f39d2b..209a963112e3a 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -49,7 +49,7 @@ static bool mctp_sockaddr_ext_is_ok(const struct sockaddr_mctp_ext *addr) !addr->__smctp_pad0[2]; } -static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen) +static int mctp_bind(struct socket *sock, struct sockaddr_unsized *addr, int addrlen) { struct sock *sk = sock->sk; struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); @@ -128,7 +128,7 @@ static int mctp_bind(struct socket *sock, struct sockaddr *addr, int addrlen) /* Used to set a specific peer prior to bind. Not used for outbound * connections (Tag Owner set) since MCTP is a datagram protocol. */ -static int mctp_connect(struct socket *sock, struct sockaddr *addr, +static int mctp_connect(struct socket *sock, struct sockaddr_unsized *addr, int addrlen, int flags) { struct sock *sk = sock->sk; diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c index 69a3ccfc6310c..be9149ac79dd2 100644 --- a/net/mctp/test/route-test.c +++ b/net/mctp/test/route-test.c @@ -205,7 +205,7 @@ static void __mctp_route_test_init(struct kunit *test, addr.smctp_network = netid; addr.smctp_addr.s_addr = 8; addr.smctp_type = 0; - rc = kernel_bind(sock, (struct sockaddr *)&addr, sizeof(addr)); + rc = kernel_bind(sock, (struct sockaddr_unsized *)&addr, sizeof(addr)); KUNIT_ASSERT_EQ(test, rc, 0); *devp = dev; diff --git a/net/mctp/test/utils.c b/net/mctp/test/utils.c index 953d419027718..35f6be8145674 100644 --- a/net/mctp/test/utils.c +++ b/net/mctp/test/utils.c @@ -279,7 +279,7 @@ void mctp_test_bind_run(struct kunit *test, addr.smctp_addr.s_addr = setup->peer_addr; /* connect() type must match bind() type */ addr.smctp_type = setup->bind_type; - rc = kernel_connect(*sock, (struct sockaddr *)&addr, + rc = kernel_connect(*sock, (struct sockaddr_unsized *)&addr, sizeof(addr), 0); KUNIT_EXPECT_EQ(test, rc, 0); } @@ -292,5 +292,6 @@ void mctp_test_bind_run(struct kunit *test, addr.smctp_type = setup->bind_type; *ret_bind_errno = - kernel_bind(*sock, (struct sockaddr *)&addr, sizeof(addr)); + kernel_bind(*sock, (struct sockaddr_unsized *)&addr, + sizeof(addr)); } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 25c88cba5c48b..580aac112dd21 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -75,16 +75,23 @@ static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt, struct nlmsghdr *nlh, struct net *net, u32 portid, unsigned int nlm_flags); -static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index) +static struct mpls_route *mpls_route_input(struct net *net, unsigned int index) { - struct mpls_route *rt = NULL; + struct mpls_route __rcu **platform_label; - if (index < net->mpls.platform_labels) { - struct mpls_route __rcu **platform_label = - rcu_dereference_rtnl(net->mpls.platform_label); - rt = rcu_dereference_rtnl(platform_label[index]); - } - return rt; + platform_label = mpls_dereference(net, net->mpls.platform_label); + return mpls_dereference(net, platform_label[index]); +} + +static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned int index) +{ + struct mpls_route __rcu **platform_label; + + if (index >= net->mpls.platform_labels) + return NULL; + + platform_label = rcu_dereference(net->mpls.platform_label); + return rcu_dereference(platform_label[index]); } bool mpls_output_possible(const struct net_device *dev) @@ -129,25 +136,26 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) } EXPORT_SYMBOL_GPL(mpls_pkt_too_big); -void mpls_stats_inc_outucastpkts(struct net_device *dev, +void mpls_stats_inc_outucastpkts(struct net *net, + struct net_device *dev, const struct sk_buff *skb) { struct mpls_dev *mdev; if (skb->protocol == htons(ETH_P_MPLS_UC)) { - mdev = mpls_dev_get(dev); + mdev = mpls_dev_rcu(dev); if (mdev) MPLS_INC_STATS_LEN(mdev, skb->len, tx_packets, tx_bytes); } else if (skb->protocol == htons(ETH_P_IP)) { - IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len); + IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len); #if IS_ENABLED(CONFIG_IPV6) } else if (skb->protocol == htons(ETH_P_IPV6)) { - struct inet6_dev *in6dev = __in6_dev_get(dev); + struct inet6_dev *in6dev = in6_dev_rcu(dev); if (in6dev) - IP6_UPD_PO_STATS(dev_net(dev), in6dev, + IP6_UPD_PO_STATS(net, in6dev, IPSTATS_MIB_OUT, skb->len); #endif } @@ -342,7 +350,7 @@ static bool mpls_egress(struct net *net, struct mpls_route *rt, static int mpls_forward(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { - struct net *net = dev_net(dev); + struct net *net = dev_net_rcu(dev); struct mpls_shim_hdr *hdr; const struct mpls_nh *nh; struct mpls_route *rt; @@ -357,7 +365,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, /* Careful this entire function runs inside of an rcu critical section */ - mdev = mpls_dev_get(dev); + mdev = mpls_dev_rcu(dev); if (!mdev) goto drop; @@ -434,7 +442,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, dec.ttl -= 1; if (unlikely(!new_header_size && dec.bos)) { /* Penultimate hop popping */ - if (!mpls_egress(dev_net(out_dev), rt, skb, dec)) + if (!mpls_egress(net, rt, skb, dec)) goto err; } else { bool bos; @@ -451,7 +459,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, } } - mpls_stats_inc_outucastpkts(out_dev, skb); + mpls_stats_inc_outucastpkts(net, out_dev, skb); /* If via wasn't specified then send out using device address */ if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC) @@ -466,7 +474,7 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev, return 0; tx_err: - out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; + out_mdev = out_dev ? mpls_dev_rcu(out_dev) : NULL; if (out_mdev) MPLS_INC_STATS(out_mdev, tx_errors); goto drop; @@ -530,10 +538,23 @@ static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels) return rt; } +static void mpls_rt_free_rcu(struct rcu_head *head) +{ + struct mpls_route *rt; + + rt = container_of(head, struct mpls_route, rt_rcu); + + change_nexthops(rt) { + netdev_put(nh->nh_dev, &nh->nh_dev_tracker); + } endfor_nexthops(rt); + + kfree(rt); +} + static void mpls_rt_free(struct mpls_route *rt) { if (rt) - kfree_rcu(rt, rt_rcu); + call_rcu(&rt->rt_rcu, mpls_rt_free_rcu); } static void mpls_notify_route(struct net *net, unsigned index, @@ -557,10 +578,8 @@ static void mpls_route_update(struct net *net, unsigned index, struct mpls_route __rcu **platform_label; struct mpls_route *rt; - ASSERT_RTNL(); - - platform_label = rtnl_dereference(net->mpls.platform_label); - rt = rtnl_dereference(platform_label[index]); + platform_label = mpls_dereference(net, net->mpls.platform_label); + rt = mpls_dereference(net, platform_label[index]); rcu_assign_pointer(platform_label[index], new); mpls_notify_route(net, index, rt, new, info); @@ -569,24 +588,23 @@ static void mpls_route_update(struct net *net, unsigned index, mpls_rt_free(rt); } -static unsigned find_free_label(struct net *net) +static unsigned int find_free_label(struct net *net) { - struct mpls_route __rcu **platform_label; - size_t platform_labels; - unsigned index; + unsigned int index; - platform_label = rtnl_dereference(net->mpls.platform_label); - platform_labels = net->mpls.platform_labels; - for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels; + for (index = MPLS_LABEL_FIRST_UNRESERVED; + index < net->mpls.platform_labels; index++) { - if (!rtnl_dereference(platform_label[index])) + if (!mpls_route_input(net, index)) return index; } + return LABEL_NOT_SPECIFIED; } #if IS_ENABLED(CONFIG_INET) static struct net_device *inet_fib_lookup_dev(struct net *net, + struct mpls_nh *nh, const void *addr) { struct net_device *dev; @@ -599,14 +617,14 @@ static struct net_device *inet_fib_lookup_dev(struct net *net, return ERR_CAST(rt); dev = rt->dst.dev; - dev_hold(dev); - + netdev_hold(dev, &nh->nh_dev_tracker, GFP_KERNEL); ip_rt_put(rt); return dev; } #else static struct net_device *inet_fib_lookup_dev(struct net *net, + struct mpls_nh *nh, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); @@ -615,6 +633,7 @@ static struct net_device *inet_fib_lookup_dev(struct net *net, #if IS_ENABLED(CONFIG_IPV6) static struct net_device *inet6_fib_lookup_dev(struct net *net, + struct mpls_nh *nh, const void *addr) { struct net_device *dev; @@ -631,13 +650,14 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net, return ERR_CAST(dst); dev = dst->dev; - dev_hold(dev); + netdev_hold(dev, &nh->nh_dev_tracker, GFP_KERNEL); dst_release(dst); return dev; } #else static struct net_device *inet6_fib_lookup_dev(struct net *net, + struct mpls_nh *nh, const void *addr) { return ERR_PTR(-EAFNOSUPPORT); @@ -653,16 +673,17 @@ static struct net_device *find_outdev(struct net *net, if (!oif) { switch (nh->nh_via_table) { case NEIGH_ARP_TABLE: - dev = inet_fib_lookup_dev(net, mpls_nh_via(rt, nh)); + dev = inet_fib_lookup_dev(net, nh, mpls_nh_via(rt, nh)); break; case NEIGH_ND_TABLE: - dev = inet6_fib_lookup_dev(net, mpls_nh_via(rt, nh)); + dev = inet6_fib_lookup_dev(net, nh, mpls_nh_via(rt, nh)); break; case NEIGH_LINK_TABLE: break; } } else { - dev = dev_get_by_index(net, oif); + dev = netdev_get_by_index(net, oif, + &nh->nh_dev_tracker, GFP_KERNEL); } if (!dev) @@ -671,8 +692,7 @@ static struct net_device *find_outdev(struct net *net, if (IS_ERR(dev)) return dev; - /* The caller is holding rtnl anyways, so release the dev reference */ - dev_put(dev); + nh->nh_dev = dev; return dev; } @@ -686,20 +706,17 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, dev = find_outdev(net, rt, nh, oif); if (IS_ERR(dev)) { err = PTR_ERR(dev); - dev = NULL; goto errout; } /* Ensure this is a supported device */ err = -EINVAL; - if (!mpls_dev_get(dev)) - goto errout; + if (!mpls_dev_get(net, dev)) + goto errout_put; if ((nh->nh_via_table == NEIGH_LINK_TABLE) && (dev->addr_len != nh->nh_via_alen)) - goto errout; - - nh->nh_dev = dev; + goto errout_put; if (!(dev->flags & IFF_UP)) { nh->nh_flags |= RTNH_F_DEAD; @@ -713,6 +730,9 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt, return 0; +errout_put: + netdev_put(nh->nh_dev, &nh->nh_dev_tracker); + nh->nh_dev = NULL; errout: return err; } @@ -890,7 +910,8 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, struct nlattr *nla_via, *nla_newdst; int remaining = cfg->rc_mp_len; int err = 0; - u8 nhs = 0; + + rt->rt_nhn = 0; change_nexthops(rt) { int attrlen; @@ -926,11 +947,9 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, rt->rt_nhn_alive--; rtnh = rtnh_next(rtnh, &remaining); - nhs++; + rt->rt_nhn++; } endfor_nexthops(rt); - rt->rt_nhn = nhs; - return 0; errout: @@ -940,30 +959,28 @@ static int mpls_nh_build_multi(struct mpls_route_config *cfg, static bool mpls_label_ok(struct net *net, unsigned int *index, struct netlink_ext_ack *extack) { - bool is_ok = true; - /* Reserved labels may not be set */ if (*index < MPLS_LABEL_FIRST_UNRESERVED) { NL_SET_ERR_MSG(extack, "Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher"); - is_ok = false; + return false; } /* The full 20 bit range may not be supported. */ - if (is_ok && *index >= net->mpls.platform_labels) { + if (*index >= net->mpls.platform_labels) { NL_SET_ERR_MSG(extack, "Label >= configured maximum in platform_labels"); - is_ok = false; + return false; } *index = array_index_nospec(*index, net->mpls.platform_labels); - return is_ok; + + return true; } static int mpls_route_add(struct mpls_route_config *cfg, struct netlink_ext_ack *extack) { - struct mpls_route __rcu **platform_label; struct net *net = cfg->rc_nlinfo.nl_net; struct mpls_route *rt, *old; int err = -EINVAL; @@ -991,8 +1008,7 @@ static int mpls_route_add(struct mpls_route_config *cfg, } err = -EEXIST; - platform_label = rtnl_dereference(net->mpls.platform_label); - old = rtnl_dereference(platform_label[index]); + old = mpls_route_input(net, index); if ((cfg->rc_nlflags & NLM_F_EXCL) && old) goto errout; @@ -1103,7 +1119,7 @@ static int mpls_fill_stats_af(struct sk_buff *skb, struct mpls_dev *mdev; struct nlattr *nla; - mdev = mpls_dev_get(dev); + mdev = mpls_dev_rcu(dev); if (!mdev) return -ENODATA; @@ -1123,7 +1139,7 @@ static size_t mpls_get_stats_af_size(const struct net_device *dev) { struct mpls_dev *mdev; - mdev = mpls_dev_get(dev); + mdev = mpls_dev_rcu(dev); if (!mdev) return 0; @@ -1264,23 +1280,32 @@ static int mpls_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) goto errout; - err = -EINVAL; - if (!tb[NETCONFA_IFINDEX]) + if (!tb[NETCONFA_IFINDEX]) { + err = -EINVAL; goto errout; + } ifindex = nla_get_s32(tb[NETCONFA_IFINDEX]); - dev = __dev_get_by_index(net, ifindex); - if (!dev) - goto errout; - - mdev = mpls_dev_get(dev); - if (!mdev) - goto errout; - err = -ENOBUFS; skb = nlmsg_new(mpls_netconf_msgsize_devconf(NETCONFA_ALL), GFP_KERNEL); - if (!skb) + if (!skb) { + err = -ENOBUFS; goto errout; + } + + rcu_read_lock(); + + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + err = -EINVAL; + goto errout_unlock; + } + + mdev = mpls_dev_rcu(dev); + if (!mdev) { + err = -EINVAL; + goto errout_unlock; + } err = mpls_netconf_fill_devconf(skb, mdev, NETLINK_CB(in_skb).portid, @@ -1289,12 +1314,19 @@ static int mpls_netconf_get_devconf(struct sk_buff *in_skb, if (err < 0) { /* -EMSGSIZE implies BUG in mpls_netconf_msgsize_devconf() */ WARN_ON(err == -EMSGSIZE); - kfree_skb(skb); - goto errout; + goto errout_unlock; } + err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); + + rcu_read_unlock(); errout: return err; + +errout_unlock: + rcu_read_unlock(); + kfree_skb(skb); + goto errout; } static int mpls_netconf_dump_devconf(struct sk_buff *skb, @@ -1326,7 +1358,7 @@ static int mpls_netconf_dump_devconf(struct sk_buff *skb, rcu_read_lock(); for_each_netdev_dump(net, dev, ctx->ifindex) { - mdev = mpls_dev_get(dev); + mdev = mpls_dev_rcu(dev); if (!mdev) continue; err = mpls_netconf_fill_devconf(skb, mdev, @@ -1438,8 +1470,6 @@ static struct mpls_dev *mpls_add_dev(struct net_device *dev) int err = -ENOMEM; int i; - ASSERT_RTNL(); - mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); if (!mdev) return ERR_PTR(err); @@ -1481,16 +1511,15 @@ static void mpls_dev_destroy_rcu(struct rcu_head *head) static int mpls_ifdown(struct net_device *dev, int event) { - struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - unsigned index; + unsigned int index; - platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { - struct mpls_route *rt = rtnl_dereference(platform_label[index]); + struct mpls_route *rt; bool nh_del = false; u8 alive = 0; + rt = mpls_route_input(net, index); if (!rt) continue; @@ -1524,8 +1553,12 @@ static int mpls_ifdown(struct net_device *dev, int event) change_nexthops(rt) { unsigned int nh_flags = nh->nh_flags; - if (nh->nh_dev != dev) + if (nh->nh_dev != dev) { + if (nh_del) + netdev_hold(nh->nh_dev, &nh->nh_dev_tracker, + GFP_KERNEL); goto next; + } switch (event) { case NETDEV_DOWN: @@ -1557,15 +1590,14 @@ static int mpls_ifdown(struct net_device *dev, int event) static void mpls_ifup(struct net_device *dev, unsigned int flags) { - struct mpls_route __rcu **platform_label; struct net *net = dev_net(dev); - unsigned index; + unsigned int index; u8 alive; - platform_label = rtnl_dereference(net->mpls.platform_label); for (index = 0; index < net->mpls.platform_labels; index++) { - struct mpls_route *rt = rtnl_dereference(platform_label[index]); + struct mpls_route *rt; + rt = mpls_route_input(net, index); if (!rt) continue; @@ -1592,28 +1624,33 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); struct mpls_dev *mdev; unsigned int flags; int err; + mutex_lock(&net->mpls.platform_mutex); + if (event == NETDEV_REGISTER) { mdev = mpls_add_dev(dev); - if (IS_ERR(mdev)) - return notifier_from_errno(PTR_ERR(mdev)); + if (IS_ERR(mdev)) { + err = PTR_ERR(mdev); + goto err; + } - return NOTIFY_OK; + goto out; } - mdev = mpls_dev_get(dev); + mdev = mpls_dev_get(net, dev); if (!mdev) - return NOTIFY_OK; + goto out; switch (event) { case NETDEV_DOWN: err = mpls_ifdown(dev, event); if (err) - return notifier_from_errno(err); + goto err; break; case NETDEV_UP: flags = netif_get_flags(dev); @@ -1629,14 +1666,15 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, } else { err = mpls_ifdown(dev, event); if (err) - return notifier_from_errno(err); + goto err; } break; case NETDEV_UNREGISTER: err = mpls_ifdown(dev, event); if (err) - return notifier_from_errno(err); - mdev = mpls_dev_get(dev); + goto err; + + mdev = mpls_dev_get(net, dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); RCU_INIT_POINTER(dev->mpls_ptr, NULL); @@ -1644,16 +1682,23 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event, } break; case NETDEV_CHANGENAME: - mdev = mpls_dev_get(dev); + mdev = mpls_dev_get(net, dev); if (mdev) { mpls_dev_sysctl_unregister(dev, mdev); err = mpls_dev_sysctl_register(dev, mdev); if (err) - return notifier_from_errno(err); + goto err; } break; } + +out: + mutex_unlock(&net->mpls.platform_mutex); return NOTIFY_OK; + +err: + mutex_unlock(&net->mpls.platform_mutex); + return notifier_from_errno(err); } static struct notifier_block mpls_dev_notifier = { @@ -1928,6 +1973,7 @@ static int rtm_to_route_config(struct sk_buff *skb, static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct net *net = sock_net(skb->sk); struct mpls_route_config *cfg; int err; @@ -1939,7 +1985,9 @@ static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto out; + mutex_lock(&net->mpls.platform_mutex); err = mpls_route_del(cfg, extack); + mutex_unlock(&net->mpls.platform_mutex); out: kfree(cfg); @@ -1950,6 +1998,7 @@ static int mpls_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { + struct net *net = sock_net(skb->sk); struct mpls_route_config *cfg; int err; @@ -1961,7 +2010,9 @@ static int mpls_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (err < 0) goto out; + mutex_lock(&net->mpls.platform_mutex); err = mpls_route_add(cfg, extack); + mutex_unlock(&net->mpls.platform_mutex); out: kfree(cfg); @@ -2124,7 +2175,7 @@ static int mpls_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, if (i == RTA_OIF) { ifindex = nla_get_u32(tb[i]); - filter->dev = __dev_get_by_index(net, ifindex); + filter->dev = dev_get_by_index_rcu(net, ifindex); if (!filter->dev) return -ENODEV; filter->filter_set = 1; @@ -2162,20 +2213,19 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) struct net *net = sock_net(skb->sk); struct mpls_route __rcu **platform_label; struct fib_dump_filter filter = { - .rtnl_held = true, + .rtnl_held = false, }; unsigned int flags = NLM_F_MULTI; size_t platform_labels; unsigned int index; + int err; - ASSERT_RTNL(); + rcu_read_lock(); if (cb->strict_check) { - int err; - err = mpls_valid_fib_dump_req(net, nlh, &filter, cb); if (err < 0) - return err; + goto err; /* for MPLS, there is only 1 table with fixed type and flags. * If either are set in the filter then return nothing. @@ -2183,14 +2233,14 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) if ((filter.table_id && filter.table_id != RT_TABLE_MAIN) || (filter.rt_type && filter.rt_type != RTN_UNICAST) || filter.flags) - return skb->len; + goto unlock; } index = cb->args[0]; if (index < MPLS_LABEL_FIRST_UNRESERVED) index = MPLS_LABEL_FIRST_UNRESERVED; - platform_label = rtnl_dereference(net->mpls.platform_label); + platform_label = rcu_dereference(net->mpls.platform_label); platform_labels = net->mpls.platform_labels; if (filter.filter_set) @@ -2199,7 +2249,7 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) for (; index < platform_labels; index++) { struct mpls_route *rt; - rt = rtnl_dereference(platform_label[index]); + rt = rcu_dereference(platform_label[index]); if (!rt) continue; @@ -2214,7 +2264,13 @@ static int mpls_dump_routes(struct sk_buff *skb, struct netlink_callback *cb) } cb->args[0] = index; +unlock: + rcu_read_unlock(); return skb->len; + +err: + rcu_read_unlock(); + return err; } static inline size_t lfib_nlmsg_size(struct mpls_route *rt) @@ -2345,18 +2401,20 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, u32 portid = NETLINK_CB(in_skb).portid; u32 in_label = LABEL_NOT_SPECIFIED; struct nlattr *tb[RTA_MAX + 1]; + struct mpls_route *rt = NULL; u32 labels[MAX_NEW_LABELS]; struct mpls_shim_hdr *hdr; unsigned int hdr_size = 0; const struct mpls_nh *nh; struct net_device *dev; - struct mpls_route *rt; struct rtmsg *rtm, *r; struct nlmsghdr *nlh; struct sk_buff *skb; u8 n_labels; int err; + mutex_lock(&net->mpls.platform_mutex); + err = mpls_valid_getroute_req(in_skb, in_nlh, tb, extack); if (err < 0) goto errout; @@ -2378,7 +2436,8 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, } } - rt = mpls_route_input_rcu(net, in_label); + if (in_label < net->mpls.platform_labels) + rt = mpls_route_input(net, in_label); if (!rt) { err = -ENETUNREACH; goto errout; @@ -2399,7 +2458,8 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, goto errout_free; } - return rtnl_unicast(skb, net, portid); + err = rtnl_unicast(skb, net, portid); + goto errout; } if (tb[RTA_NEWDST]) { @@ -2491,12 +2551,14 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, err = rtnl_unicast(skb, net, portid); errout: + mutex_unlock(&net->mpls.platform_mutex); return err; nla_put_failure: nlmsg_cancel(skb, nlh); err = -EMSGSIZE; errout_free: + mutex_unlock(&net->mpls.platform_mutex); kfree_skb(skb); return err; } @@ -2519,10 +2581,13 @@ static int resize_platform_label_table(struct net *net, size_t limit) /* In case the predefined labels need to be populated */ if (limit > MPLS_LABEL_IPV4NULL) { struct net_device *lo = net->loopback_dev; + rt0 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt0)) goto nort0; + rt0->rt_nh->nh_dev = lo; + netdev_hold(lo, &rt0->rt_nh->nh_dev_tracker, GFP_KERNEL); rt0->rt_protocol = RTPROT_KERNEL; rt0->rt_payload_type = MPT_IPV4; rt0->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; @@ -2533,10 +2598,13 @@ static int resize_platform_label_table(struct net *net, size_t limit) } if (limit > MPLS_LABEL_IPV6NULL) { struct net_device *lo = net->loopback_dev; + rt2 = mpls_rt_alloc(1, lo->addr_len, 0); if (IS_ERR(rt2)) goto nort2; + rt2->rt_nh->nh_dev = lo; + netdev_hold(lo, &rt2->rt_nh->nh_dev_tracker, GFP_KERNEL); rt2->rt_protocol = RTPROT_KERNEL; rt2->rt_payload_type = MPT_IPV6; rt2->rt_ttl_propagate = MPLS_TTL_PROP_DEFAULT; @@ -2546,9 +2614,10 @@ static int resize_platform_label_table(struct net *net, size_t limit) lo->addr_len); } - rtnl_lock(); + mutex_lock(&net->mpls.platform_mutex); + /* Remember the original table */ - old = rtnl_dereference(net->mpls.platform_label); + old = mpls_dereference(net, net->mpls.platform_label); old_limit = net->mpls.platform_labels; /* Free any labels beyond the new table */ @@ -2579,7 +2648,7 @@ static int resize_platform_label_table(struct net *net, size_t limit) net->mpls.platform_labels = limit; rcu_assign_pointer(net->mpls.platform_label, labels); - rtnl_unlock(); + mutex_unlock(&net->mpls.platform_mutex); mpls_rt_free(rt2); mpls_rt_free(rt0); @@ -2652,12 +2721,13 @@ static const struct ctl_table mpls_table[] = { }, }; -static int mpls_net_init(struct net *net) +static __net_init int mpls_net_init(struct net *net) { size_t table_size = ARRAY_SIZE(mpls_table); struct ctl_table *table; int i; + mutex_init(&net->mpls.platform_mutex); net->mpls.platform_labels = 0; net->mpls.platform_label = NULL; net->mpls.ip_ttl_propagate = 1; @@ -2683,7 +2753,7 @@ static int mpls_net_init(struct net *net) return 0; } -static void mpls_net_exit(struct net *net) +static __net_exit void mpls_net_exit(struct net *net) { struct mpls_route __rcu **platform_label; size_t platform_labels; @@ -2703,16 +2773,20 @@ static void mpls_net_exit(struct net *net) * As such no additional rcu synchronization is necessary when * freeing the platform_label table. */ - rtnl_lock(); - platform_label = rtnl_dereference(net->mpls.platform_label); + mutex_lock(&net->mpls.platform_mutex); + + platform_label = mpls_dereference(net, net->mpls.platform_label); platform_labels = net->mpls.platform_labels; + for (index = 0; index < platform_labels; index++) { - struct mpls_route *rt = rtnl_dereference(platform_label[index]); - RCU_INIT_POINTER(platform_label[index], NULL); + struct mpls_route *rt; + + rt = mpls_dereference(net, platform_label[index]); mpls_notify_route(net, index, rt, NULL, NULL); mpls_rt_free(rt); } - rtnl_unlock(); + + mutex_unlock(&net->mpls.platform_mutex); kvfree(platform_label); } @@ -2729,12 +2803,15 @@ static struct rtnl_af_ops mpls_af_ops __read_mostly = { }; static const struct rtnl_msg_handler mpls_rtnl_msg_handlers[] __initdata_or_module = { - {THIS_MODULE, PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, 0}, - {THIS_MODULE, PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, 0}, - {THIS_MODULE, PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, 0}, + {THIS_MODULE, PF_MPLS, RTM_NEWROUTE, mpls_rtm_newroute, NULL, + RTNL_FLAG_DOIT_UNLOCKED}, + {THIS_MODULE, PF_MPLS, RTM_DELROUTE, mpls_rtm_delroute, NULL, + RTNL_FLAG_DOIT_UNLOCKED}, + {THIS_MODULE, PF_MPLS, RTM_GETROUTE, mpls_getroute, mpls_dump_routes, + RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, {THIS_MODULE, PF_MPLS, RTM_GETNETCONF, mpls_netconf_get_devconf, mpls_netconf_dump_devconf, - RTNL_FLAG_DUMP_UNLOCKED}, + RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED}, }; static int __init mpls_init(void) diff --git a/net/mpls/internal.h b/net/mpls/internal.h index 83c629529b575..80cb5bbcd9465 100644 --- a/net/mpls/internal.h +++ b/net/mpls/internal.h @@ -88,6 +88,7 @@ enum mpls_payload_type { struct mpls_nh { /* next hop label forwarding entry */ struct net_device *nh_dev; + netdevice_tracker nh_dev_tracker; /* nh_flags is accessed under RCU in the packet path; it is * modified handling netdev events with rtnl lock held @@ -184,9 +185,20 @@ static inline struct mpls_entry_decoded mpls_entry_decode(struct mpls_shim_hdr * return result; } -static inline struct mpls_dev *mpls_dev_get(const struct net_device *dev) +#define mpls_dereference(net, p) \ + rcu_dereference_protected( \ + (p), \ + lockdep_is_held(&(net)->mpls.platform_mutex)) + +static inline struct mpls_dev *mpls_dev_rcu(const struct net_device *dev) +{ + return rcu_dereference(dev->mpls_ptr); +} + +static inline struct mpls_dev *mpls_dev_get(const struct net *net, + const struct net_device *dev) { - return rcu_dereference_rtnl(dev->mpls_ptr); + return mpls_dereference(net, dev->mpls_ptr); } int nla_put_labels(struct sk_buff *skb, int attrtype, u8 labels, @@ -196,7 +208,8 @@ int nla_get_labels(const struct nlattr *nla, u8 max_labels, u8 *labels, bool mpls_output_possible(const struct net_device *dev); unsigned int mpls_dev_mtu(const struct net_device *dev); bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu); -void mpls_stats_inc_outucastpkts(struct net_device *dev, +void mpls_stats_inc_outucastpkts(struct net *net, + struct net_device *dev, const struct sk_buff *skb); #endif /* MPLS_INTERNAL_H */ diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 6e73da94af7fb..1a1a0eb5b787f 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -53,7 +53,7 @@ static int mpls_xmit(struct sk_buff *skb) /* Find the output device */ out_dev = dst->dev; - net = dev_net(out_dev); + net = dev_net_rcu(out_dev); if (!mpls_output_possible(out_dev) || !dst->lwtstate || skb_warn_if_lro(skb)) @@ -128,7 +128,7 @@ static int mpls_xmit(struct sk_buff *skb) bos = false; } - mpls_stats_inc_outucastpkts(out_dev, skb); + mpls_stats_inc_outucastpkts(net, out_dev, skb); if (rt) { if (rt->rt_gw_family == AF_INET6) @@ -153,7 +153,7 @@ static int mpls_xmit(struct sk_buff *skb) return LWTUNNEL_XMIT_DONE; drop: - out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL; + out_mdev = out_dev ? mpls_dev_rcu(out_dev) : NULL; if (out_mdev) MPLS_INC_STATS(out_mdev, tx_errors); kfree_skb(skb); diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 2ff1b94995683..9604b91902b8b 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -18,6 +18,7 @@ struct mptcp_pm_add_entry { u8 retrans_times; struct timer_list add_timer; struct mptcp_sock *sock; + struct rcu_head rcu; }; static DEFINE_SPINLOCK(mptcp_pm_list_lock); @@ -155,7 +156,7 @@ bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk, entry = mptcp_pm_del_add_timer(msk, addr, false); ret = entry; - kfree(entry); + kfree_rcu(entry, rcu); return ret; } @@ -345,22 +346,27 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, { struct mptcp_pm_add_entry *entry; struct sock *sk = (struct sock *)msk; - struct timer_list *add_timer = NULL; + bool stop_timer = false; + + rcu_read_lock(); spin_lock_bh(&msk->pm.lock); entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (entry && (!check_id || entry->addr.id == addr->id)) { entry->retrans_times = ADD_ADDR_RETRANS_MAX; - add_timer = &entry->add_timer; + stop_timer = true; } if (!check_id && entry) list_del(&entry->list); spin_unlock_bh(&msk->pm.lock); - /* no lock, because sk_stop_timer_sync() is calling timer_delete_sync() */ - if (add_timer) - sk_stop_timer_sync(sk, add_timer); + /* Note: entry might have been removed by another thread. + * We hold rcu_read_lock() to ensure it is not freed under us. + */ + if (stop_timer) + sk_stop_timer_sync(sk, &entry->add_timer); + rcu_read_unlock(); return entry; } @@ -415,7 +421,7 @@ static void mptcp_pm_free_anno_list(struct mptcp_sock *msk) list_for_each_entry_safe(entry, tmp, &free_list, list) { sk_stop_timer_sync(sk, &entry->add_timer); - kfree(entry); + kfree_rcu(entry, rcu); } } diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c index 2ae95476dba35..598f01a573c1b 100644 --- a/net/mptcp/pm_kernel.c +++ b/net/mptcp/pm_kernel.c @@ -22,6 +22,7 @@ struct pm_nl_pernet { u8 endp_signal_max; u8 endp_subflow_max; u8 endp_laminar_max; + u8 endp_fullmesh_max; u8 limit_add_addr_accepted; u8 limit_extra_subflows; u8 next_id; @@ -70,6 +71,14 @@ u8 mptcp_pm_get_endp_laminar_max(const struct mptcp_sock *msk) } EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_laminar_max); +u8 mptcp_pm_get_endp_fullmesh_max(const struct mptcp_sock *msk) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); + + return READ_ONCE(pernet->endp_fullmesh_max); +} +EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_fullmesh_max); + u8 mptcp_pm_get_limit_add_addr_accepted(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); @@ -600,12 +609,11 @@ fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *locals) { bool c_flag_case = remote->id && mptcp_pm_add_addr_c_flag_case(msk); - int i; /* If there is at least one MPTCP endpoint with a fullmesh flag */ - i = fill_local_addresses_vec_fullmesh(msk, remote, locals, c_flag_case); - if (i) - return i; + if (mptcp_pm_get_endp_fullmesh_max(msk)) + return fill_local_addresses_vec_fullmesh(msk, remote, locals, + c_flag_case); /* If there is at least one MPTCP endpoint with a laminar flag */ if (mptcp_pm_get_endp_laminar_max(msk)) @@ -790,6 +798,10 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, addr_max = pernet->endp_laminar_max; WRITE_ONCE(pernet->endp_laminar_max, addr_max + 1); } + if (entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { + addr_max = pernet->endp_fullmesh_max; + WRITE_ONCE(pernet->endp_fullmesh_max, addr_max + 1); + } pernet->endpoints++; if (!entry->addr.port) @@ -855,10 +867,10 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, addrlen = sizeof(struct sockaddr_in6); #endif if (ssk->sk_family == AF_INET) - err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen); + err = inet_bind_sk(ssk, (struct sockaddr_unsized *)&addr, addrlen); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (ssk->sk_family == AF_INET6) - err = inet6_bind_sk(ssk, (struct sockaddr *)&addr, addrlen); + err = inet6_bind_sk(ssk, (struct sockaddr_unsized *)&addr, addrlen); #endif if (err) return err; @@ -1187,6 +1199,10 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) addr_max = pernet->endp_laminar_max; WRITE_ONCE(pernet->endp_laminar_max, addr_max - 1); } + if (entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { + addr_max = pernet->endp_fullmesh_max; + WRITE_ONCE(pernet->endp_fullmesh_max, addr_max - 1); + } pernet->endpoints--; list_del_rcu(&entry->list); @@ -1502,6 +1518,18 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local, changed = (local->flags ^ entry->flags) & mask; entry->flags = (entry->flags & ~mask) | (local->flags & mask); *local = *entry; + + if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) { + u8 addr_max = pernet->endp_fullmesh_max; + + if (entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) + addr_max++; + else + addr_max--; + + WRITE_ONCE(pernet->endp_fullmesh_max, addr_max); + } + spin_unlock_bh(&pernet->lock); mptcp_pm_nl_set_flags_all(net, local, changed); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 90b4aeca2596a..26bb74095c300 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -937,14 +937,19 @@ static void mptcp_reset_rtx_timer(struct sock *sk) bool mptcp_schedule_work(struct sock *sk) { - if (inet_sk_state_load(sk) != TCP_CLOSE && - schedule_work(&mptcp_sk(sk)->work)) { - /* each subflow already holds a reference to the sk, and the - * workqueue is invoked by a subflow, so sk can't go away here. - */ - sock_hold(sk); + if (inet_sk_state_load(sk) == TCP_CLOSE) + return false; + + /* Get a reference on this socket, mptcp_worker() will release it. + * As mptcp_worker() might complete before us, we can not avoid + * a sock_hold()/sock_put() if schedule_work() returns false. + */ + sock_hold(sk); + + if (schedule_work(&mptcp_sk(sk)->work)) return true; - } + + sock_put(sk); return false; } @@ -1076,11 +1081,12 @@ static void mptcp_enter_memory_pressure(struct sock *sk) mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - if (first) + if (first && !ssk->sk_bypass_prot_mem) { tcp_enter_memory_pressure(ssk); - sk_stream_moderate_sndbuf(ssk); + first = false; + } - first = false; + sk_stream_moderate_sndbuf(ssk); } __mptcp_sync_sndbuf(sk); } @@ -3747,7 +3753,8 @@ static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) return 0; } -static int mptcp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) +static int mptcp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk = mptcp_sk(sk); @@ -3857,7 +3864,7 @@ static struct proto mptcp_prot = { .no_autobind = true, }; -static int mptcp_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int mptcp_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct sock *ssk, *sk = sock->sk; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 379a88e14e8d2..9a34291757585 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1183,6 +1183,7 @@ void __mptcp_pm_kernel_worker(struct mptcp_sock *msk); u8 mptcp_pm_get_endp_signal_max(const struct mptcp_sock *msk); u8 mptcp_pm_get_endp_subflow_max(const struct mptcp_sock *msk); u8 mptcp_pm_get_endp_laminar_max(const struct mptcp_sock *msk); +u8 mptcp_pm_get_endp_fullmesh_max(const struct mptcp_sock *msk); u8 mptcp_pm_get_limit_add_addr_accepted(const struct mptcp_sock *msk); u8 mptcp_pm_get_limit_extra_subflows(const struct mptcp_sock *msk); diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index a28a483858852..de90a2897d2d8 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -982,6 +982,8 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) mptcp_pm_get_endp_subflow_max(msk); info->mptcpi_endp_laminar_max = mptcp_pm_get_endp_laminar_max(msk); + info->mptcpi_endp_fullmesh_max = + mptcp_pm_get_endp_fullmesh_max(msk); } if (__mptcp_check_fallback(msk)) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index af707ce0f6244..ddd0fc6fcf453 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1660,7 +1660,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local, addrlen = sizeof(struct sockaddr_in6); #endif ssk->sk_bound_dev_if = local->ifindex; - err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen); + err = kernel_bind(sf, (struct sockaddr_unsized *)&addr, addrlen); if (err) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXBINDERR); pr_debug("msk=%p local=%d remote=%d bind error: %d\n", @@ -1680,7 +1680,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local, sock_hold(ssk); list_add_tail(&subflow->node, &msk->conn_list); - err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK); + err = kernel_connect(sf, (struct sockaddr_unsized *)&addr, addrlen, O_NONBLOCK); if (err && err != -EINPROGRESS) { MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNTXCONNECTERR); pr_debug("msk=%p local=%d remote=%d connect error: %d\n", diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3402675bf5215..5a0c6f42bd8f2 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1435,7 +1435,7 @@ static int bind_mcastif_addr(struct socket *sock, struct net_device *dev) sin.sin_addr.s_addr = addr; sin.sin_port = 0; - return kernel_bind(sock, (struct sockaddr *)&sin, sizeof(sin)); + return kernel_bind(sock, (struct sockaddr_unsized *)&sin, sizeof(sin)); } static void get_mcast_sockaddr(union ipvs_sockaddr *sa, int *salen, @@ -1501,7 +1501,7 @@ static int make_send_sock(struct netns_ipvs *ipvs, int id, } get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->mcfg, id); - result = kernel_connect(sock, (struct sockaddr *)&mcast_addr, + result = kernel_connect(sock, (struct sockaddr_unsized *)&mcast_addr, salen, 0); if (result < 0) { pr_err("Error connecting to the multicast addr\n"); @@ -1542,7 +1542,7 @@ static int make_receive_sock(struct netns_ipvs *ipvs, int id, get_mcast_sockaddr(&mcast_addr, &salen, &ipvs->bcfg, id); sock->sk->sk_bound_dev_if = dev->ifindex; - result = kernel_bind(sock, (struct sockaddr *)&mcast_addr, salen); + result = kernel_bind(sock, (struct sockaddr_unsized *)&mcast_addr, salen); if (result < 0) { pr_err("Error binding to the multicast addr\n"); goto error; diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 344f88295976d..0b95f226f2111 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1668,7 +1668,7 @@ __nf_conntrack_alloc(struct net *net, /* We don't want any race condition at early drop stage */ ct_count = atomic_inc_return(&cnet->count); - if (nf_conntrack_max && unlikely(ct_count > nf_conntrack_max)) { + if (unlikely(ct_count > nf_conntrack_max)) { if (!early_drop(net, hash)) { if (!conntrack_gc_work.early_drop) conntrack_gc_work.early_drop = true; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 708b79380f047..207b240b14e5d 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -648,7 +648,7 @@ static struct ctl_table nf_ct_sysctl_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, [NF_SYSCTL_CT_COUNT] = { @@ -929,7 +929,7 @@ static struct ctl_table nf_ct_netfilter_table[] = { .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = SYSCTL_ZERO, + .extra1 = SYSCTL_ONE, .extra2 = SYSCTL_INT_MAX, }, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index eed434e0a9702..f3de2f9bbebf1 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5770,7 +5770,11 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, struct nft_set_binding *binding) { struct nft_set_binding *i; - struct nft_set_iter iter; + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, + .fn = nf_tables_bind_check_setelem, + }; if (!list_empty(&set->bindings) && nft_set_is_anonymous(set)) return -EBUSY; @@ -5785,13 +5789,6 @@ int nf_tables_bind_set(const struct nft_ctx *ctx, struct nft_set *set, goto bind; } - iter.genmask = nft_genmask_next(ctx->net); - iter.type = NFT_ITER_UPDATE; - iter.skip = 0; - iter.count = 0; - iter.err = 0; - iter.fn = nf_tables_bind_check_setelem; - set->ops->walk(ctx, set, &iter); if (!iter.err) iter.err = nft_set_catchall_bind_check(ctx, set); @@ -6195,7 +6192,17 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) struct nftables_pernet *nft_net; struct nft_table *table; struct nft_set *set; - struct nft_set_dump_args args; + struct nft_set_dump_args args = { + .cb = cb, + .skb = skb, + .reset = dump_ctx->reset, + .iter = { + .genmask = nft_genmask_cur(net), + .type = NFT_ITER_READ, + .skip = cb->args[0], + .fn = nf_tables_dump_setelem, + }, + }; bool set_found = false; struct nlmsghdr *nlh; struct nlattr *nest; @@ -6246,15 +6253,6 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb) if (nest == NULL) goto nla_put_failure; - args.cb = cb; - args.skb = skb; - args.reset = dump_ctx->reset; - args.iter.genmask = nft_genmask_cur(net); - args.iter.type = NFT_ITER_READ; - args.iter.skip = cb->args[0]; - args.iter.count = 0; - args.iter.err = 0; - args.iter.fn = nf_tables_dump_setelem; set->ops->walk(&dump_ctx->ctx, set, &args.iter); if (!args.iter.err && args.iter.count == cb->args[0]) diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 58c5b14889c47..fc2d7c5d83c8e 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -246,19 +246,16 @@ static int nft_lookup_validate(const struct nft_ctx *ctx, const struct nft_expr *expr) { const struct nft_lookup *priv = nft_expr_priv(expr); - struct nft_set_iter iter; + struct nft_set_iter iter = { + .genmask = nft_genmask_next(ctx->net), + .type = NFT_ITER_UPDATE, + .fn = nft_setelem_validate, + }; if (!(priv->set->flags & NFT_SET_MAP) || priv->set->dtype != NFT_DATA_VERDICT) return 0; - iter.genmask = nft_genmask_next(ctx->net); - iter.type = NFT_ITER_UPDATE; - iter.skip = 0; - iter.count = 0; - iter.err = 0; - iter.fn = nft_setelem_validate; - priv->set->ops->walk(ctx, priv->set, &iter); if (!iter.err) iter.err = nft_set_catchall_validate(ctx, priv->set); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 2b46c0cd752a3..8e5151f0c6e46 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -596,10 +596,8 @@ static void netlink_remove(struct sock *sk) table = &nl_table[sk->sk_protocol]; if (!rhashtable_remove_fast(&table->hash, &nlk_sk(sk)->node, - netlink_rhashtable_params)) { - WARN_ON(refcount_read(&sk->sk_refcnt) == 1); + netlink_rhashtable_params)) __sock_put(sk); - } netlink_table_grab(); if (nlk_sk(sk)->subscriptions) { @@ -968,7 +966,7 @@ static void netlink_undo_bind(int group, long unsigned int groups, nlk->netlink_unbind(sock_net(sk), undo + 1); } -static int netlink_bind(struct socket *sock, struct sockaddr *addr, +static int netlink_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sock *sk = sock->sk; @@ -1056,7 +1054,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } -static int netlink_connect(struct socket *sock, struct sockaddr *addr, +static int netlink_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { int err = 0; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 3331669d8e33a..5ed1a71ceec1e 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -561,7 +561,7 @@ static int nr_release(struct socket *sock) return 0; } -static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int nr_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); @@ -632,8 +632,8 @@ static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return 0; } -static int nr_connect(struct socket *sock, struct sockaddr *uaddr, - int addr_len, int flags) +static int nr_connect(struct socket *sock, struct sockaddr_unsized *uaddr, + int addr_len, int flags) { struct sock *sk = sock->sk; struct nr_sock *nr = nr_sk(sk); diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index 57a2f97004e17..f1be1e84f6653 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -56,7 +56,7 @@ static struct proto llcp_sock_proto = { .obj_size = sizeof(struct nfc_llcp_sock), }; -static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) +static int llcp_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int alen) { struct sock *sk = sock->sk; struct nfc_llcp_sock *llcp_sock = nfc_llcp_sock(sk); @@ -146,7 +146,7 @@ static int llcp_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) return ret; } -static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr *addr, +static int llcp_raw_sock_bind(struct socket *sock, struct sockaddr_unsized *addr, int alen) { struct sock *sk = sock->sk; @@ -648,7 +648,7 @@ static int llcp_sock_release(struct socket *sock) return err; } -static int llcp_sock_connect(struct socket *sock, struct sockaddr *_addr, +static int llcp_sock_connect(struct socket *sock, struct sockaddr_unsized *_addr, int len, int flags) { struct sock *sk = sock->sk; diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index 5125392bb68eb..b049022399aea 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -73,7 +73,7 @@ static int rawsock_release(struct socket *sock) return 0; } -static int rawsock_connect(struct socket *sock, struct sockaddr *_addr, +static int rawsock_connect(struct socket *sock, struct sockaddr_unsized *_addr, int len, int flags) { struct sock *sk = sock->sk; diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 2832e07941971..792ca44a461da 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -572,69 +572,6 @@ static int set_ipv6(struct sk_buff *skb, struct sw_flow_key *flow_key, return 0; } -static int set_nsh(struct sk_buff *skb, struct sw_flow_key *flow_key, - const struct nlattr *a) -{ - struct nshhdr *nh; - size_t length; - int err; - u8 flags; - u8 ttl; - int i; - - struct ovs_key_nsh key; - struct ovs_key_nsh mask; - - err = nsh_key_from_nlattr(a, &key, &mask); - if (err) - return err; - - /* Make sure the NSH base header is there */ - if (!pskb_may_pull(skb, skb_network_offset(skb) + NSH_BASE_HDR_LEN)) - return -ENOMEM; - - nh = nsh_hdr(skb); - length = nsh_hdr_len(nh); - - /* Make sure the whole NSH header is there */ - err = skb_ensure_writable(skb, skb_network_offset(skb) + - length); - if (unlikely(err)) - return err; - - nh = nsh_hdr(skb); - skb_postpull_rcsum(skb, nh, length); - flags = nsh_get_flags(nh); - flags = OVS_MASKED(flags, key.base.flags, mask.base.flags); - flow_key->nsh.base.flags = flags; - ttl = nsh_get_ttl(nh); - ttl = OVS_MASKED(ttl, key.base.ttl, mask.base.ttl); - flow_key->nsh.base.ttl = ttl; - nsh_set_flags_and_ttl(nh, flags, ttl); - nh->path_hdr = OVS_MASKED(nh->path_hdr, key.base.path_hdr, - mask.base.path_hdr); - flow_key->nsh.base.path_hdr = nh->path_hdr; - switch (nh->mdtype) { - case NSH_M_TYPE1: - for (i = 0; i < NSH_MD1_CONTEXT_SIZE; i++) { - nh->md1.context[i] = - OVS_MASKED(nh->md1.context[i], key.context[i], - mask.context[i]); - } - memcpy(flow_key->nsh.context, nh->md1.context, - sizeof(nh->md1.context)); - break; - case NSH_M_TYPE2: - memset(flow_key->nsh.context, 0, - sizeof(flow_key->nsh.context)); - break; - default: - return -EINVAL; - } - skb_postpush_rcsum(skb, nh, length); - return 0; -} - /* Must follow skb_ensure_writable() since that can move the skb data. */ static void set_tp_port(struct sk_buff *skb, __be16 *port, __be16 new_port, __sum16 *check) @@ -1130,10 +1067,6 @@ static int execute_masked_set_action(struct sk_buff *skb, get_mask(a, struct ovs_key_ethernet *)); break; - case OVS_KEY_ATTR_NSH: - err = set_nsh(skb, flow_key, a); - break; - case OVS_KEY_ATTR_IPV4: err = set_ipv4(skb, flow_key, nla_data(a), get_mask(a, struct ovs_key_ipv4 *)); @@ -1170,6 +1103,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4: case OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6: + case OVS_KEY_ATTR_NSH: err = -EINVAL; break; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ad64bb9ab5e25..1cb4f97335d87 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1305,6 +1305,11 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, return 0; } +/* + * Constructs NSH header 'nh' from attributes of OVS_ACTION_ATTR_PUSH_NSH, + * where 'nh' points to a memory block of 'size' bytes. It's assumed that + * attributes were previously validated with validate_push_nsh(). + */ int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size) { @@ -1314,8 +1319,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, u8 ttl = 0; int mdlen = 0; - /* validate_nsh has check this, so we needn't do duplicate check here - */ if (size < NSH_BASE_HDR_LEN) return -ENOBUFS; @@ -1359,46 +1362,6 @@ int nsh_hdr_from_nlattr(const struct nlattr *attr, return 0; } -int nsh_key_from_nlattr(const struct nlattr *attr, - struct ovs_key_nsh *nsh, struct ovs_key_nsh *nsh_mask) -{ - struct nlattr *a; - int rem; - - /* validate_nsh has check this, so we needn't do duplicate check here - */ - nla_for_each_nested(a, attr, rem) { - int type = nla_type(a); - - switch (type) { - case OVS_NSH_KEY_ATTR_BASE: { - const struct ovs_nsh_key_base *base = nla_data(a); - const struct ovs_nsh_key_base *base_mask = base + 1; - - nsh->base = *base; - nsh_mask->base = *base_mask; - break; - } - case OVS_NSH_KEY_ATTR_MD1: { - const struct ovs_nsh_key_md1 *md1 = nla_data(a); - const struct ovs_nsh_key_md1 *md1_mask = md1 + 1; - - memcpy(nsh->context, md1->context, sizeof(*md1)); - memcpy(nsh_mask->context, md1_mask->context, - sizeof(*md1_mask)); - break; - } - case OVS_NSH_KEY_ATTR_MD2: - /* Not supported yet */ - return -ENOTSUPP; - default: - return -EINVAL; - } - } - - return 0; -} - static int nsh_key_put_from_nlattr(const struct nlattr *attr, struct sw_flow_match *match, bool is_mask, bool is_push_nsh, bool log) @@ -2839,17 +2802,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, return err; } -static bool validate_nsh(const struct nlattr *attr, bool is_mask, - bool is_push_nsh, bool log) +static bool validate_push_nsh(const struct nlattr *attr, bool log) { struct sw_flow_match match; struct sw_flow_key key; - int ret = 0; ovs_match_init(&match, &key, true, NULL); - ret = nsh_key_put_from_nlattr(attr, &match, is_mask, - is_push_nsh, log); - return !ret; + return !nsh_key_put_from_nlattr(attr, &match, false, true, log); } /* Return false if there are any non-masked bits set. @@ -2997,13 +2956,6 @@ static int validate_set(const struct nlattr *a, break; - case OVS_KEY_ATTR_NSH: - if (eth_type != htons(ETH_P_NSH)) - return -EINVAL; - if (!validate_nsh(nla_data(a), masked, false, log)) - return -EINVAL; - break; - default: return -EINVAL; } @@ -3437,7 +3389,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, return -EINVAL; } mac_proto = MAC_PROTO_NONE; - if (!validate_nsh(nla_data(a), false, true, true)) + if (!validate_push_nsh(nla_data(a), log)) return -EINVAL; break; diff --git a/net/openvswitch/flow_netlink.h b/net/openvswitch/flow_netlink.h index fe7f77fc5f189..ff8cdecbe3465 100644 --- a/net/openvswitch/flow_netlink.h +++ b/net/openvswitch/flow_netlink.h @@ -65,8 +65,6 @@ int ovs_nla_put_actions(const struct nlattr *attr, void ovs_nla_free_flow_actions(struct sw_flow_actions *); void ovs_nla_free_flow_actions_rcu(struct sw_flow_actions *); -int nsh_key_from_nlattr(const struct nlattr *attr, struct ovs_key_nsh *nsh, - struct ovs_key_nsh *nsh_mask); int nsh_hdr_from_nlattr(const struct nlattr *attr, struct nshhdr *nh, size_t size); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 173e6edda08f8..494d628d10a51 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -3279,11 +3279,12 @@ static int packet_do_bind(struct sock *sk, const char *name, int ifindex, * Bind a packet socket to a device */ -static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, +static int packet_bind_spkt(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data_min) + 1]; + struct sockaddr *sa = (struct sockaddr *)uaddr; + char name[sizeof(sa->sa_data) + 1]; /* * Check legality @@ -3294,13 +3295,13 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); - name[sizeof(uaddr->sa_data_min)] = 0; + memcpy(name, sa->sa_data, sizeof(sa->sa_data)); + name[sizeof(sa->sa_data)] = 0; return packet_do_bind(sk, name, 0, 0); } -static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int packet_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_ll *sll = (struct sockaddr_ll *)uaddr; struct sock *sk = sock->sk; @@ -3580,11 +3581,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); rcu_read_unlock(); return sizeof(*uaddr); diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 4db564d9d522b..120e711ea78cb 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -882,7 +882,8 @@ static struct sock *pep_sock_accept(struct sock *sk, return newsk; } -static int pep_sock_connect(struct sock *sk, struct sockaddr *addr, int len) +static int pep_sock_connect(struct sock *sk, struct sockaddr_unsized *addr, + int len) { struct pep_sock *pn = pep_sk(sk); int err; diff --git a/net/phonet/socket.c b/net/phonet/socket.c index db2d552e9b32e..4423d483c630a 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -153,7 +153,7 @@ EXPORT_SYMBOL(pn_sock_unhash); static DEFINE_MUTEX(port_mutex); -static int pn_socket_bind(struct socket *sock, struct sockaddr *addr, int len) +static int pn_socket_bind(struct socket *sock, struct sockaddr_unsized *addr, int len) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); @@ -206,16 +206,16 @@ static int pn_socket_autobind(struct socket *sock) memset(&sa, 0, sizeof(sa)); sa.spn_family = AF_PHONET; - err = pn_socket_bind(sock, (struct sockaddr *)&sa, - sizeof(struct sockaddr_pn)); + err = pn_socket_bind(sock, (struct sockaddr_unsized *)&sa, + sizeof(struct sockaddr_pn)); if (err != -EINVAL) return err; BUG_ON(!pn_port(pn_sk(sock->sk)->sobject)); return 0; /* socket was already bound */ } -static int pn_socket_connect(struct socket *sock, struct sockaddr *addr, - int len, int flags) +static int pn_socket_connect(struct socket *sock, struct sockaddr_unsized *addr, + int len, int flags) { struct sock *sk = sock->sk; struct pn_sock *pn = pn_sk(sk); diff --git a/net/psp/psp-nl-gen.c b/net/psp/psp-nl-gen.c index 9fdd6f831803e..73f8b06d66f0f 100644 --- a/net/psp/psp-nl-gen.c +++ b/net/psp/psp-nl-gen.c @@ -47,6 +47,11 @@ static const struct nla_policy psp_tx_assoc_nl_policy[PSP_A_ASSOC_SOCK_FD + 1] = [PSP_A_ASSOC_SOCK_FD] = { .type = NLA_U32, }, }; +/* PSP_CMD_GET_STATS - do */ +static const struct nla_policy psp_get_stats_nl_policy[PSP_A_STATS_DEV_ID + 1] = { + [PSP_A_STATS_DEV_ID] = NLA_POLICY_MIN(NLA_U32, 1), +}; + /* Ops table for psp */ static const struct genl_split_ops psp_nl_ops[] = { { @@ -99,6 +104,20 @@ static const struct genl_split_ops psp_nl_ops[] = { .maxattr = PSP_A_ASSOC_SOCK_FD, .flags = GENL_CMD_CAP_DO, }, + { + .cmd = PSP_CMD_GET_STATS, + .pre_doit = psp_device_get_locked, + .doit = psp_nl_get_stats_doit, + .post_doit = psp_device_unlock, + .policy = psp_get_stats_nl_policy, + .maxattr = PSP_A_STATS_DEV_ID, + .flags = GENL_CMD_CAP_DO, + }, + { + .cmd = PSP_CMD_GET_STATS, + .dumpit = psp_nl_get_stats_dumpit, + .flags = GENL_CMD_CAP_DUMP, + }, }; static const struct genl_multicast_group psp_nl_mcgrps[] = { diff --git a/net/psp/psp-nl-gen.h b/net/psp/psp-nl-gen.h index 25268ed11fb56..5bc3b5d5a53e2 100644 --- a/net/psp/psp-nl-gen.h +++ b/net/psp/psp-nl-gen.h @@ -28,6 +28,8 @@ int psp_nl_dev_set_doit(struct sk_buff *skb, struct genl_info *info); int psp_nl_key_rotate_doit(struct sk_buff *skb, struct genl_info *info); int psp_nl_rx_assoc_doit(struct sk_buff *skb, struct genl_info *info); int psp_nl_tx_assoc_doit(struct sk_buff *skb, struct genl_info *info); +int psp_nl_get_stats_doit(struct sk_buff *skb, struct genl_info *info); +int psp_nl_get_stats_dumpit(struct sk_buff *skb, struct netlink_callback *cb); enum { PSP_NLGRP_MGMT, diff --git a/net/psp/psp_main.c b/net/psp/psp_main.c index 481aaf0fc9fcf..a8534124f6266 100644 --- a/net/psp/psp_main.c +++ b/net/psp/psp_main.c @@ -60,7 +60,8 @@ psp_dev_create(struct net_device *netdev, !psd_ops->key_rotate || !psd_ops->rx_spi_alloc || !psd_ops->tx_key_add || - !psd_ops->tx_key_del)) + !psd_ops->tx_key_del || + !psd_ops->get_stats)) return ERR_PTR(-EINVAL); psd = kzalloc(sizeof(*psd), GFP_KERNEL); diff --git a/net/psp/psp_nl.c b/net/psp/psp_nl.c index 8aaca62744c3c..6afd7707ec12e 100644 --- a/net/psp/psp_nl.c +++ b/net/psp/psp_nl.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0-only +#include #include #include #include @@ -262,6 +263,7 @@ int psp_nl_key_rotate_doit(struct sk_buff *skb, struct genl_info *info) psd->generation & ~PSP_GEN_VALID_MASK); psp_assocs_key_rotated(psd); + psd->stats.rotations++; nlmsg_end(ntf, (struct nlmsghdr *)ntf->data); genlmsg_multicast_netns(&psp_nl_family, dev_net(psd->main_netdev), ntf, @@ -503,3 +505,94 @@ int psp_nl_tx_assoc_doit(struct sk_buff *skb, struct genl_info *info) nlmsg_free(rsp); return err; } + +static int +psp_nl_stats_fill(struct psp_dev *psd, struct sk_buff *rsp, + const struct genl_info *info) +{ + unsigned int required_cnt = sizeof(struct psp_dev_stats) / sizeof(u64); + struct psp_dev_stats stats; + void *hdr; + int i; + + memset(&stats, 0xff, sizeof(stats)); + psd->ops->get_stats(psd, &stats); + + for (i = 0; i < required_cnt; i++) + if (WARN_ON_ONCE(stats.required[i] == ETHTOOL_STAT_NOT_SET)) + return -EOPNOTSUPP; + + hdr = genlmsg_iput(rsp, info); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_u32(rsp, PSP_A_STATS_DEV_ID, psd->id) || + nla_put_uint(rsp, PSP_A_STATS_KEY_ROTATIONS, + psd->stats.rotations) || + nla_put_uint(rsp, PSP_A_STATS_STALE_EVENTS, psd->stats.stales) || + nla_put_uint(rsp, PSP_A_STATS_RX_PACKETS, stats.rx_packets) || + nla_put_uint(rsp, PSP_A_STATS_RX_BYTES, stats.rx_bytes) || + nla_put_uint(rsp, PSP_A_STATS_RX_AUTH_FAIL, stats.rx_auth_fail) || + nla_put_uint(rsp, PSP_A_STATS_RX_ERROR, stats.rx_error) || + nla_put_uint(rsp, PSP_A_STATS_RX_BAD, stats.rx_bad) || + nla_put_uint(rsp, PSP_A_STATS_TX_PACKETS, stats.tx_packets) || + nla_put_uint(rsp, PSP_A_STATS_TX_BYTES, stats.tx_bytes) || + nla_put_uint(rsp, PSP_A_STATS_TX_ERROR, stats.tx_error)) + goto err_cancel_msg; + + genlmsg_end(rsp, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(rsp, hdr); + return -EMSGSIZE; +} + +int psp_nl_get_stats_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct psp_dev *psd = info->user_ptr[0]; + struct sk_buff *rsp; + int err; + + rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!rsp) + return -ENOMEM; + + err = psp_nl_stats_fill(psd, rsp, info); + if (err) + goto err_free_msg; + + return genlmsg_reply(rsp, info); + +err_free_msg: + nlmsg_free(rsp); + return err; +} + +static int +psp_nl_stats_get_dumpit_one(struct sk_buff *rsp, struct netlink_callback *cb, + struct psp_dev *psd) +{ + if (psp_dev_check_access(psd, sock_net(rsp->sk))) + return 0; + + return psp_nl_stats_fill(psd, rsp, genl_info_dump(cb)); +} + +int psp_nl_get_stats_dumpit(struct sk_buff *rsp, struct netlink_callback *cb) +{ + struct psp_dev *psd; + int err = 0; + + mutex_lock(&psp_devs_lock); + xa_for_each_start(&psp_devs, cb->args[0], psd, cb->args[0]) { + mutex_lock(&psd->lock); + err = psp_nl_stats_get_dumpit_one(rsp, cb, psd); + mutex_unlock(&psd->lock); + if (err) + break; + } + mutex_unlock(&psp_devs_lock); + + return err; +} diff --git a/net/psp/psp_sock.c b/net/psp/psp_sock.c index a931d825d1cc4..f785672b7df66 100644 --- a/net/psp/psp_sock.c +++ b/net/psp/psp_sock.c @@ -253,8 +253,10 @@ void psp_assocs_key_rotated(struct psp_dev *psd) /* Mark the stale associations as invalid, they will no longer * be able to Rx any traffic. */ - list_for_each_entry_safe(pas, next, &psd->prev_assocs, assocs_list) + list_for_each_entry_safe(pas, next, &psd->prev_assocs, assocs_list) { pas->generation |= ~PSP_GEN_VALID_MASK; + psd->stats.stales++; + } list_splice_init(&psd->prev_assocs, &psd->stale_assocs); list_splice_init(&psd->active_assocs, &psd->prev_assocs); diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 00c51cf693f3d..dab839f61ee93 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -824,7 +824,7 @@ static int qrtr_autobind(struct socket *sock) } /* Bind socket to specified sockaddr. */ -static int qrtr_bind(struct socket *sock, struct sockaddr *saddr, int len) +static int qrtr_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, saddr); struct qrtr_sock *ipc = qrtr_sk(sock->sk); @@ -1084,7 +1084,7 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, return rc; } -static int qrtr_connect(struct socket *sock, struct sockaddr *saddr, +static int qrtr_connect(struct socket *sock, struct sockaddr_unsized *saddr, int len, int flags) { DECLARE_SOCKADDR(struct sockaddr_qrtr *, addr, saddr); diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c index 3de9350cbf307..bfcc1a453f238 100644 --- a/net/qrtr/ns.c +++ b/net/qrtr/ns.c @@ -714,7 +714,7 @@ int qrtr_ns_init(void) sq.sq_port = QRTR_PORT_CTRL; qrtr_ns.local_node = sq.sq_node; - ret = kernel_bind(qrtr_ns.sock, (struct sockaddr *)&sq, sizeof(sq)); + ret = kernel_bind(qrtr_ns.sock, (struct sockaddr_unsized *)&sq, sizeof(sq)); if (ret < 0) { pr_err("failed to bind to socket\n"); goto err_wq; diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 4a7217fbeab6f..b396c673dfaf6 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -533,7 +533,7 @@ static int rds_getsockopt(struct socket *sock, int level, int optname, } -static int rds_connect(struct socket *sock, struct sockaddr *uaddr, +static int rds_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; diff --git a/net/rds/bind.c b/net/rds/bind.c index 97a29172a8eec..f800d920d9690 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -160,7 +160,7 @@ void rds_remove_bound(struct rds_sock *rs) rs->rs_bound_addr = in6addr_any; } -int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +int rds_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; struct rds_sock *rs = rds_sk_to_rs(sk); diff --git a/net/rds/rds.h b/net/rds/rds.h index 5b1c072e2e7ff..a029e5fcdea72 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -735,7 +735,7 @@ extern wait_queue_head_t rds_poll_waitq; /* bind.c */ -int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); +int rds_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len); void rds_remove_bound(struct rds_sock *rs); struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port, __u32 scope_id); diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c index a0046e99d6df7..92891b0d224d3 100644 --- a/net/rds/tcp_connect.c +++ b/net/rds/tcp_connect.c @@ -145,7 +145,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) addrlen = sizeof(sin); } - ret = kernel_bind(sock, addr, addrlen); + ret = kernel_bind(sock, (struct sockaddr_unsized *)addr, addrlen); if (ret) { rdsdebug("bind failed with %d at address %pI6c\n", ret, &conn->c_laddr); @@ -173,7 +173,7 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp) * own the socket */ rds_tcp_set_callbacks(sock, cp); - ret = kernel_connect(sock, addr, addrlen, O_NONBLOCK); + ret = kernel_connect(sock, (struct sockaddr_unsized *)addr, addrlen, O_NONBLOCK); rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret); if (ret == -EINPROGRESS) diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index 91e34af3fe5d5..820d3e20de195 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -290,7 +290,7 @@ struct socket *rds_tcp_listen_init(struct net *net, bool isv6) addr_len = sizeof(*sin); } - ret = kernel_bind(sock, (struct sockaddr *)&ss, addr_len); + ret = kernel_bind(sock, (struct sockaddr_unsized *)&ss, addr_len); if (ret < 0) { rdsdebug("could not bind %s listener socket: %d\n", isv6 ? "IPv6" : "IPv4", ret); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 543f9e8ebb693..fd67494f2815e 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -693,7 +693,7 @@ static int rose_release(struct socket *sock) return 0; } -static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int rose_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); @@ -765,7 +765,8 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) return err; } -static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_len, int flags) +static int rose_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, + int flags) { struct sock *sk = sock->sk; struct rose_sock *rose = rose_sk(sk); diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 36df0274d7b74..0c2c68c4b07e4 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -127,7 +127,7 @@ static int rxrpc_validate_address(struct rxrpc_sock *rx, /* * bind a local address to an RxRPC socket */ -static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) +static int rxrpc_bind(struct socket *sock, struct sockaddr_unsized *saddr, int len) { struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)saddr; struct rxrpc_local *local; @@ -481,7 +481,7 @@ EXPORT_SYMBOL(rxrpc_kernel_set_notifications); * - this just targets it at a specific destination; no actual connection * negotiation takes place */ -static int rxrpc_connect(struct socket *sock, struct sockaddr *addr, +static int rxrpc_connect(struct socket *sock, struct sockaddr_unsized *addr, int addr_len, int flags) { struct sockaddr_rxrpc *srx = (struct sockaddr_rxrpc *)addr; diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c index 2ea71e3831f75..98ea76fae70f3 100644 --- a/net/rxrpc/rxperf.c +++ b/net/rxrpc/rxperf.c @@ -211,7 +211,7 @@ static int rxperf_open_socket(void) ret = rxrpc_sock_set_security_keyring(socket->sk, rxperf_sec_keyring); - ret = kernel_bind(socket, (struct sockaddr *)&srx, sizeof(srx)); + ret = kernel_bind(socket, (struct sockaddr_unsized *)&srx, sizeof(srx)); if (ret < 0) goto error_2; diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 7c6975632fc2e..1dfdda6c2d4c5 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -649,9 +649,9 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind, memset(&opt, 0, sizeof(opt)); - opt.index = ife->tcf_index, - opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref, - opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind, + opt.index = ife->tcf_index; + opt.refcnt = refcount_read(&ife->tcf_refcnt) - ref; + opt.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind; spin_lock_bh(&ife->tcf_lock); opt.action = ife->tcf_action; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 5f01f567c934d..f27b583def78e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -29,31 +29,6 @@ static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); -#define MIRRED_NEST_LIMIT 4 - -#ifndef CONFIG_PREEMPT_RT -static u8 tcf_mirred_nest_level_inc_return(void) -{ - return __this_cpu_inc_return(softnet_data.xmit.sched_mirred_nest); -} - -static void tcf_mirred_nest_level_dec(void) -{ - __this_cpu_dec(softnet_data.xmit.sched_mirred_nest); -} - -#else -static u8 tcf_mirred_nest_level_inc_return(void) -{ - return current->net_xmit.sched_mirred_nest++; -} - -static void tcf_mirred_nest_level_dec(void) -{ - current->net_xmit.sched_mirred_nest--; -} -#endif - static bool tcf_mirred_is_act_redirect(int action) { return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR; @@ -439,44 +414,53 @@ TC_INDIRECT_SCOPE int tcf_mirred_act(struct sk_buff *skb, { struct tcf_mirred *m = to_mirred(a); int retval = READ_ONCE(m->tcf_action); - unsigned int nest_level; + struct netdev_xmit *xmit; bool m_mac_header_xmit; struct net_device *dev; - int m_eaction; + int i, m_eaction; u32 blockid; - nest_level = tcf_mirred_nest_level_inc_return(); - if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { +#ifdef CONFIG_PREEMPT_RT + xmit = ¤t->net_xmit; +#else + xmit = this_cpu_ptr(&softnet_data.xmit); +#endif + if (unlikely(xmit->sched_mirred_nest >= MIRRED_NEST_LIMIT)) { net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", netdev_name(skb->dev)); - retval = TC_ACT_SHOT; - goto dec_nest_level; + return TC_ACT_SHOT; } tcf_lastuse_update(&m->tcf_tm); tcf_action_update_bstats(&m->common, skb); blockid = READ_ONCE(m->tcfm_blockid); - if (blockid) { - retval = tcf_blockcast(skb, m, blockid, res, retval); - goto dec_nest_level; - } + if (blockid) + return tcf_blockcast(skb, m, blockid, res, retval); dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); tcf_action_inc_overlimit_qstats(&m->common); - goto dec_nest_level; + return retval; } + for (i = 0; i < xmit->sched_mirred_nest; i++) { + if (xmit->sched_mirred_dev[i] != dev) + continue; + pr_notice_once("tc mirred: loop on device %s\n", + netdev_name(dev)); + tcf_action_inc_overlimit_qstats(&m->common); + return retval; + } + + xmit->sched_mirred_dev[xmit->sched_mirred_nest++] = dev; m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); retval = tcf_mirred_to_dev(skb, m, dev, m_mac_header_xmit, m_eaction, retval); - -dec_nest_level: - tcf_mirred_nest_level_dec(); + xmit->sched_mirred_nest--; return retval; } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ecec0a1e1c1a0..f751cd5eeac8d 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1866,7 +1866,7 @@ int tcf_classify(struct sk_buff *skb, struct tc_skb_cb *cb = tc_skb_cb(skb); ext = tc_skb_ext_alloc(skb); - if (WARN_ON_ONCE(!ext)) { + if (!ext) { tcf_set_drop_reason(skb, SKB_DROP_REASON_NOMEM); return TC_ACT_SHOT; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 7dee9748a56be..852e603c17551 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -669,7 +669,6 @@ struct Qdisc noop_qdisc = { .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, - .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, .prev = (struct sk_buff *)&noop_qdisc.gso_skb, @@ -682,7 +681,6 @@ struct Qdisc noop_qdisc = { .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), }, - .owner = -1, }; EXPORT_SYMBOL(noop_qdisc); @@ -974,10 +972,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, } } - spin_lock_init(&sch->busylock); - lockdep_set_class(&sch->busylock, - dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); - /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); lockdep_set_class(&sch->seqlock, @@ -988,7 +982,6 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; - sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 568ff8797c393..069b7e45d8bda 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -777,54 +777,6 @@ static enum sctp_scope sctp_v6_scope(union sctp_addr *addr) return retval; } -/* Create and initialize a new sk for the socket to be returned by accept(). */ -static struct sock *sctp_v6_create_accept_sk(struct sock *sk, - struct sctp_association *asoc, - bool kern) -{ - struct sock *newsk; - struct ipv6_pinfo *newnp, *np = inet6_sk(sk); - struct sctp6_sock *newsctp6sk; - - newsk = sk_alloc(sock_net(sk), PF_INET6, GFP_KERNEL, sk->sk_prot, kern); - if (!newsk) - goto out; - - sock_init_data(NULL, newsk); - - sctp_copy_sock(newsk, sk, asoc); - sock_reset_flag(sk, SOCK_ZAPPED); - - newsctp6sk = (struct sctp6_sock *)newsk; - inet_sk(newsk)->pinet6 = &newsctp6sk->inet6; - - sctp_sk(newsk)->v4mapped = sctp_sk(sk)->v4mapped; - - newnp = inet6_sk(newsk); - - memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - newnp->ipv6_mc_list = NULL; - newnp->ipv6_ac_list = NULL; - newnp->ipv6_fl_list = NULL; - - sctp_v6_copy_ip_options(sk, newsk); - - /* Initialize sk's sport, dport, rcv_saddr and daddr for getsockname() - * and getpeername(). - */ - sctp_v6_to_sk_daddr(&asoc->peer.primary_addr, newsk); - - newsk->sk_v6_rcv_saddr = sk->sk_v6_rcv_saddr; - - if (newsk->sk_prot->init(newsk)) { - sk_common_release(newsk); - newsk = NULL; - } - -out: - return newsk; -} - /* Format a sockaddr for return to user space. This makes sure the return is * AF_INET or AF_INET6 depending on the SCTP_I_WANT_MAPPED_V4_ADDR option. */ @@ -1171,7 +1123,6 @@ static struct sctp_pf sctp_pf_inet6 = { .bind_verify = sctp_inet6_bind_verify, .send_verify = sctp_inet6_send_verify, .supported_addrs = sctp_inet6_supported_addrs, - .create_accept_sk = sctp_v6_create_accept_sk, .addr_to_user = sctp_v6_addr_to_user, .to_sk_saddr = sctp_v6_to_sk_saddr, .to_sk_daddr = sctp_v6_to_sk_daddr, diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 9dbc24af749b5..2c3398f75d766 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -580,38 +580,6 @@ static int sctp_v4_is_ce(const struct sk_buff *skb) return INET_ECN_is_ce(ip_hdr(skb)->tos); } -/* Create and initialize a new sk for the socket returned by accept(). */ -static struct sock *sctp_v4_create_accept_sk(struct sock *sk, - struct sctp_association *asoc, - bool kern) -{ - struct sock *newsk = sk_alloc(sock_net(sk), PF_INET, GFP_KERNEL, - sk->sk_prot, kern); - struct inet_sock *newinet; - - if (!newsk) - goto out; - - sock_init_data(NULL, newsk); - - sctp_copy_sock(newsk, sk, asoc); - sock_reset_flag(newsk, SOCK_ZAPPED); - - sctp_v4_copy_ip_options(sk, newsk); - - newinet = inet_sk(newsk); - - newinet->inet_daddr = asoc->peer.primary_addr.v4.sin_addr.s_addr; - - if (newsk->sk_prot->init(newsk)) { - sk_common_release(newsk); - newsk = NULL; - } - -out: - return newsk; -} - static int sctp_v4_addr_to_user(struct sctp_sock *sp, union sctp_addr *addr) { /* No address mapping for V4 sockets */ @@ -1119,7 +1087,6 @@ static struct sctp_pf sctp_pf_inet = { .bind_verify = sctp_inet_bind_verify, .send_verify = sctp_inet_send_verify, .supported_addrs = sctp_inet_supported_addrs, - .create_accept_sk = sctp_v4_create_accept_sk, .addr_to_user = sctp_v4_addr_to_user, .to_sk_saddr = sctp_v4_to_sk_saddr, .to_sk_daddr = sctp_v4_to_sk_daddr, diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ed8293a342402..d808096f5ab17 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -306,7 +306,8 @@ static struct sctp_transport *sctp_addr_id2transport(struct sock *sk, * sockaddr_in6 [RFC 2553]), * addr_len - the size of the address structure. */ -static int sctp_bind(struct sock *sk, struct sockaddr *addr, int addr_len) +static int sctp_bind(struct sock *sk, struct sockaddr_unsized *addr, + int addr_len) { int retval = 0; @@ -1053,13 +1054,13 @@ static int sctp_setsockopt_bindx(struct sock *sk, struct sockaddr *addrs, } } -static int sctp_bind_add(struct sock *sk, struct sockaddr *addrs, - int addrlen) +static int sctp_bind_add(struct sock *sk, struct sockaddr_unsized *addrs, + int addrlen) { int err; lock_sock(sk); - err = sctp_setsockopt_bindx(sk, addrs, addrlen, SCTP_BINDX_ADD_ADDR); + err = sctp_setsockopt_bindx(sk, (struct sockaddr *)addrs, addrlen, SCTP_BINDX_ADD_ADDR); release_sock(sk); return err; } @@ -1553,8 +1554,6 @@ static void sctp_close(struct sock *sk, long timeout) spin_unlock_bh(&net->sctp.addr_wq_lock); sock_put(sk); - - SCTP_DBG_OBJCNT_DEC(sock); } /* Handle EPIPE error. */ @@ -4822,7 +4821,7 @@ static int sctp_connect(struct sock *sk, struct sockaddr *addr, return err; } -int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, +int sctp_inet_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { if (addr_len < sizeof(uaddr->sa_family)) @@ -4831,7 +4830,7 @@ int sctp_inet_connect(struct socket *sock, struct sockaddr *uaddr, if (uaddr->sa_family == AF_UNSPEC) return -EOPNOTSUPP; - return sctp_connect(sock->sk, uaddr, addr_len, flags); + return sctp_connect(sock->sk, (struct sockaddr *)uaddr, addr_len, flags); } /* Only called when shutdown a listening SCTP socket. */ @@ -4844,6 +4843,75 @@ static int sctp_disconnect(struct sock *sk, int flags) return 0; } +static struct sock *sctp_clone_sock(struct sock *sk, + struct sctp_association *asoc, + enum sctp_socket_type type) +{ + struct sock *newsk = sk_clone(sk, GFP_KERNEL, false); + struct inet_sock *newinet; + struct sctp_sock *newsp; + int err = -ENOMEM; + + if (!newsk) + return ERR_PTR(err); + + /* sk_clone() sets refcnt to 2 */ + sock_put(newsk); + + newinet = inet_sk(newsk); + newsp = sctp_sk(newsk); + + newsp->pf->to_sk_daddr(&asoc->peer.primary_addr, newsk); + newinet->inet_dport = htons(asoc->peer.port); + + newsp->pf->copy_ip_options(sk, newsk); + atomic_set(&newinet->inet_id, get_random_u16()); + + inet_set_bit(MC_LOOP, newsk); + newinet->mc_ttl = 1; + newinet->mc_index = 0; + newinet->mc_list = NULL; + +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) { + struct ipv6_pinfo *newnp = inet6_sk(newsk); + + newinet->pinet6 = &((struct sctp6_sock *)newsk)->inet6; + newinet->ipv6_fl_list = NULL; + + memcpy(newnp, inet6_sk(sk), sizeof(struct ipv6_pinfo)); + newnp->ipv6_mc_list = NULL; + newnp->ipv6_ac_list = NULL; + } +#endif + + newsp->do_auto_asconf = 0; + skb_queue_head_init(&newsp->pd_lobby); + + newsp->ep = sctp_endpoint_new(newsk, GFP_KERNEL); + if (!newsp->ep) + goto out_release; + + SCTP_DBG_OBJCNT_INC(sock); + sk_sockets_allocated_inc(newsk); + sock_prot_inuse_add(sock_net(sk), newsk->sk_prot, 1); + + err = sctp_sock_migrate(sk, newsk, asoc, type); + if (err) + goto out_release; + + /* Set newsk security attributes from original sk and connection + * security attribute from asoc. + */ + security_sctp_sk_clone(asoc, sk, newsk); + + return newsk; + +out_release: + sk_common_release(newsk); + return ERR_PTR(err); +} + /* 4.1.4 accept() - TCP Style Syntax * * Applications use accept() call to remove an established SCTP @@ -4853,18 +4921,13 @@ static int sctp_disconnect(struct sock *sk, int flags) */ static struct sock *sctp_accept(struct sock *sk, struct proto_accept_arg *arg) { - struct sctp_sock *sp; - struct sctp_endpoint *ep; - struct sock *newsk = NULL; struct sctp_association *asoc; - long timeo; + struct sock *newsk = NULL; int error = 0; + long timeo; lock_sock(sk); - sp = sctp_sk(sk); - ep = sp->ep; - if (!sctp_style(sk, TCP)) { error = -EOPNOTSUPP; goto out; @@ -4885,20 +4948,12 @@ static struct sock *sctp_accept(struct sock *sk, struct proto_accept_arg *arg) /* We treat the list of associations on the endpoint as the accept * queue and pick the first association on the list. */ - asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); + asoc = list_entry(sctp_sk(sk)->ep->asocs.next, + struct sctp_association, asocs); - newsk = sp->pf->create_accept_sk(sk, asoc, arg->kern); - if (!newsk) { - error = -ENOMEM; - goto out; - } - - /* Populate the fields of the newsk from the oldsk and migrate the - * asoc to the newsk. - */ - error = sctp_sock_migrate(sk, newsk, asoc, SCTP_SOCKET_TCP); - if (error) { - sk_common_release(newsk); + newsk = sctp_clone_sock(sk, asoc, SCTP_SOCKET_TCP); + if (IS_ERR(newsk)) { + error = PTR_ERR(newsk); newsk = NULL; } @@ -5109,9 +5164,12 @@ static void sctp_destroy_sock(struct sock *sk) sp->do_auto_asconf = 0; list_del(&sp->auto_asconf_list); } + sctp_endpoint_free(sp->ep); + sk_sockets_allocated_dec(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + SCTP_DBG_OBJCNT_DEC(sock); } static void sctp_destruct_sock(struct sock *sk) @@ -5615,11 +5673,11 @@ static int sctp_getsockopt_autoclose(struct sock *sk, int len, char __user *optv /* Helper routine to branch off an association to a new socket. */ static int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, - struct socket **sockp) + struct socket **sockp) { struct sctp_association *asoc = sctp_id2assoc(sk, id); - struct sctp_sock *sp = sctp_sk(sk); struct socket *sock; + struct sock *newsk; int err = 0; /* Do not peel off from one netns to another one. */ @@ -5635,30 +5693,24 @@ static int sctp_do_peeloff(struct sock *sk, sctp_assoc_t id, if (!sctp_style(sk, UDP)) return -EINVAL; - /* Create a new socket. */ - err = sock_create(sk->sk_family, SOCK_SEQPACKET, IPPROTO_SCTP, &sock); - if (err < 0) + err = sock_create_lite(sk->sk_family, SOCK_SEQPACKET, IPPROTO_SCTP, &sock); + if (err) return err; - sctp_copy_sock(sock->sk, sk, asoc); - - /* Make peeled-off sockets more like 1-1 accepted sockets. - * Set the daddr and initialize id to something more random and also - * copy over any ip options. - */ - sp->pf->to_sk_daddr(&asoc->peer.primary_addr, sock->sk); - sp->pf->copy_ip_options(sk, sock->sk); - - /* Populate the fields of the newsk from the oldsk and migrate the - * asoc to the newsk. - */ - err = sctp_sock_migrate(sk, sock->sk, asoc, - SCTP_SOCKET_UDP_HIGH_BANDWIDTH); - if (err) { + newsk = sctp_clone_sock(sk, asoc, SCTP_SOCKET_UDP_HIGH_BANDWIDTH); + if (IS_ERR(newsk)) { sock_release(sock); - sock = NULL; + *sockp = NULL; + return PTR_ERR(newsk); } + lock_sock_nested(newsk, SINGLE_DEPTH_NESTING); + __inet_accept(sk->sk_socket, sock, newsk); + release_sock(newsk); + + sock->ops = sk->sk_socket->ops; + __module_get(sock->ops->owner); + *sockp = sock; return err; @@ -9441,71 +9493,6 @@ static void sctp_skb_set_owner_r_frag(struct sk_buff *skb, struct sock *sk) sctp_skb_set_owner_r(skb, sk); } -void sctp_copy_sock(struct sock *newsk, struct sock *sk, - struct sctp_association *asoc) -{ - struct inet_sock *inet = inet_sk(sk); - struct inet_sock *newinet; - struct sctp_sock *sp = sctp_sk(sk); - - newsk->sk_type = sk->sk_type; - newsk->sk_bound_dev_if = sk->sk_bound_dev_if; - newsk->sk_flags = sk->sk_flags; - newsk->sk_tsflags = sk->sk_tsflags; - newsk->sk_no_check_tx = sk->sk_no_check_tx; - newsk->sk_no_check_rx = sk->sk_no_check_rx; - newsk->sk_reuse = sk->sk_reuse; - sctp_sk(newsk)->reuse = sp->reuse; - - newsk->sk_shutdown = sk->sk_shutdown; - newsk->sk_destruct = sk->sk_destruct; - newsk->sk_family = sk->sk_family; - newsk->sk_protocol = IPPROTO_SCTP; - newsk->sk_backlog_rcv = sk->sk_prot->backlog_rcv; - newsk->sk_sndbuf = sk->sk_sndbuf; - newsk->sk_rcvbuf = sk->sk_rcvbuf; - newsk->sk_lingertime = sk->sk_lingertime; - newsk->sk_rcvtimeo = READ_ONCE(sk->sk_rcvtimeo); - newsk->sk_sndtimeo = READ_ONCE(sk->sk_sndtimeo); - newsk->sk_rxhash = sk->sk_rxhash; - - newinet = inet_sk(newsk); - - /* Initialize sk's sport, dport, rcv_saddr and daddr for - * getsockname() and getpeername() - */ - newinet->inet_sport = inet->inet_sport; - newinet->inet_saddr = inet->inet_saddr; - newinet->inet_rcv_saddr = inet->inet_rcv_saddr; - newinet->inet_dport = htons(asoc->peer.port); - newinet->pmtudisc = inet->pmtudisc; - atomic_set(&newinet->inet_id, get_random_u16()); - - newinet->uc_ttl = inet->uc_ttl; - inet_set_bit(MC_LOOP, newsk); - newinet->mc_ttl = 1; - newinet->mc_index = 0; - newinet->mc_list = NULL; - - if (newsk->sk_flags & SK_FLAGS_TIMESTAMP) - net_enable_timestamp(); - - /* Set newsk security attributes from original sk and connection - * security attribute from asoc. - */ - security_sctp_sk_clone(asoc, sk, newsk); -} - -static inline void sctp_copy_descendant(struct sock *sk_to, - const struct sock *sk_from) -{ - size_t ancestor_size = sizeof(struct inet_sock); - - ancestor_size += sk_from->sk_prot->obj_size; - ancestor_size -= offsetof(struct sctp_sock, pd_lobby); - __inet_sk_copy_descendant(sk_to, sk_from, ancestor_size); -} - /* Populate the fields of the newsk from the oldsk and migrate the assoc * and its messages to the newsk. */ @@ -9522,14 +9509,6 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sctp_bind_hashbucket *head; int err; - /* Migrate socket buffer sizes and all the socket level options to the - * new socket. - */ - newsk->sk_sndbuf = oldsk->sk_sndbuf; - newsk->sk_rcvbuf = oldsk->sk_rcvbuf; - /* Brute force copy old sctp opt. */ - sctp_copy_descendant(newsk, oldsk); - /* Restore the ep value that was overwritten with the above structure * copy. */ diff --git a/net/sctp/stream.c b/net/sctp/stream.c index f205556c5b248..0615e4426341c 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -54,7 +54,7 @@ static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) static void sctp_stream_free_ext(struct sctp_stream *stream, __u16 sid) { - struct sctp_sched_ops *sched; + const struct sctp_sched_ops *sched; if (!SCTP_SO(stream, sid)->ext) return; @@ -130,7 +130,7 @@ static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt, int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, gfp_t gfp) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i, ret = 0; gfp |= __GFP_NOWARN; @@ -182,7 +182,7 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) void sctp_stream_free(struct sctp_stream *stream) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); int i; sched->unsched_all(stream); @@ -207,7 +207,7 @@ void sctp_stream_clear(struct sctp_stream *stream) void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); sched->unsched_all(stream); sctp_stream_outq_migrate(stream, new, new->outcnt); diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 54afbe4fb0872..50f8b5240359e 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -91,7 +91,7 @@ static void sctp_sched_fcfs_unsched_all(struct sctp_stream *stream) { } -static struct sctp_sched_ops sctp_sched_fcfs = { +static const struct sctp_sched_ops sctp_sched_fcfs = { .set = sctp_sched_fcfs_set, .get = sctp_sched_fcfs_get, .init = sctp_sched_fcfs_init, @@ -111,10 +111,10 @@ static void sctp_sched_ops_fcfs_init(void) /* API to other parts of the stack */ -static struct sctp_sched_ops *sctp_sched_ops[SCTP_SS_MAX + 1]; +static const struct sctp_sched_ops *sctp_sched_ops[SCTP_SS_MAX + 1]; void sctp_sched_ops_register(enum sctp_sched_type sched, - struct sctp_sched_ops *sched_ops) + const struct sctp_sched_ops *sched_ops) { sctp_sched_ops[sched] = sched_ops; } @@ -130,7 +130,7 @@ void sctp_sched_ops_init(void) static void sctp_sched_free_sched(struct sctp_stream *stream) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); struct sctp_stream_out_ext *soute; int i; @@ -148,9 +148,9 @@ static void sctp_sched_free_sched(struct sctp_stream *stream) int sctp_sched_set_sched(struct sctp_association *asoc, enum sctp_sched_type sched) { - struct sctp_sched_ops *old = asoc->outqueue.sched; + const struct sctp_sched_ops *old = asoc->outqueue.sched; struct sctp_datamsg *msg = NULL; - struct sctp_sched_ops *n; + const struct sctp_sched_ops *n; struct sctp_chunk *ch; int i, ret = 0; @@ -263,14 +263,14 @@ void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch) int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp) { - struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); + const struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream); struct sctp_stream_out_ext *ext = SCTP_SO(stream, sid)->ext; INIT_LIST_HEAD(&ext->outq); return sched->init_sid(stream, sid, gfp); } -struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) +const struct sctp_sched_ops *sctp_sched_ops_from_stream(struct sctp_stream *stream) { struct sctp_association *asoc; diff --git a/net/sctp/stream_sched_fc.c b/net/sctp/stream_sched_fc.c index 4bd18a497a6dc..776c6de46c224 100644 --- a/net/sctp/stream_sched_fc.c +++ b/net/sctp/stream_sched_fc.c @@ -188,7 +188,7 @@ static void sctp_sched_fc_unsched_all(struct sctp_stream *stream) list_del_init(&soute->fc_list); } -static struct sctp_sched_ops sctp_sched_fc = { +static const struct sctp_sched_ops sctp_sched_fc = { .set = sctp_sched_fc_set, .get = sctp_sched_fc_get, .init = sctp_sched_fc_init, @@ -206,7 +206,7 @@ void sctp_sched_ops_fc_init(void) sctp_sched_ops_register(SCTP_SS_FC, &sctp_sched_fc); } -static struct sctp_sched_ops sctp_sched_wfq = { +static const struct sctp_sched_ops sctp_sched_wfq = { .set = sctp_sched_wfq_set, .get = sctp_sched_wfq_get, .init = sctp_sched_fc_init, diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 4d4d9da331f4c..fb6c55e5615df 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -300,7 +300,7 @@ static void sctp_sched_prio_unsched_all(struct sctp_stream *stream) sctp_sched_prio_unsched(soute); } -static struct sctp_sched_ops sctp_sched_prio = { +static const struct sctp_sched_ops sctp_sched_prio = { .set = sctp_sched_prio_set, .get = sctp_sched_prio_get, .init = sctp_sched_prio_init, diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c index 1f235e7f643a7..9157b653f1961 100644 --- a/net/sctp/stream_sched_rr.c +++ b/net/sctp/stream_sched_rr.c @@ -171,7 +171,7 @@ static void sctp_sched_rr_unsched_all(struct sctp_stream *stream) sctp_sched_rr_unsched(stream, soute); } -static struct sctp_sched_ops sctp_sched_rr = { +static const struct sctp_sched_ops sctp_sched_rr = { .set = sctp_sched_rr_set, .get = sctp_sched_rr_get, .init = sctp_sched_rr_init, diff --git a/net/smc/Kconfig b/net/smc/Kconfig index 99ecd59d1f4b8..325addf83cc69 100644 --- a/net/smc/Kconfig +++ b/net/smc/Kconfig @@ -19,3 +19,13 @@ config SMC_DIAG smcss. if unsure, say Y. + +config SMC_HS_CTRL_BPF + bool "Generic eBPF hook for SMC handshake flow" + depends on SMC && BPF_SYSCALL + default y + help + SMC_HS_CTRL_BPF enables support to register generic eBPF hook for SMC + handshake flow, which offer much greater flexibility in modifying the behavior + of the SMC protocol stack compared to a complete kernel-based approach. Select + this option if you want filtring the handshake process via eBPF programs. \ No newline at end of file diff --git a/net/smc/Makefile b/net/smc/Makefile index 0e754cbc38f9c..5368634c5dd6d 100644 --- a/net/smc/Makefile +++ b/net/smc/Makefile @@ -6,3 +6,4 @@ smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o smc_stats.o smc-y += smc_tracepoint.o smc_inet.o smc-$(CONFIG_SYSCTL) += smc_sysctl.o +smc-$(CONFIG_SMC_HS_CTRL_BPF) += smc_hs_bpf.o diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 77b99e8ef35a4..e388de8dca097 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -58,6 +58,7 @@ #include "smc_tracepoint.h" #include "smc_sysctl.h" #include "smc_inet.h" +#include "smc_hs_bpf.h" static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group * creation on server @@ -421,7 +422,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, return sk; } -int smc_bind(struct socket *sock, struct sockaddr *uaddr, +int smc_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_in *addr = (struct sockaddr_in *)uaddr; @@ -1642,7 +1643,7 @@ static void smc_connect_work(struct work_struct *work) release_sock(&smc->sk); } -int smc_connect(struct socket *sock, struct sockaddr *addr, +int smc_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { struct sock *sk = sock->sk; @@ -1694,7 +1695,7 @@ int smc_connect(struct socket *sock, struct sockaddr *addr, rc = -EALREADY; goto out; } - rc = kernel_connect(smc->clcsock, addr, alen, flags); + rc = kernel_connect(smc->clcsock, (struct sockaddr_unsized *)addr, alen, flags); if (rc && rc != -EINPROGRESS) goto out; @@ -2140,7 +2141,7 @@ static void smc_check_ism_v2_match(struct smc_init_info *ini, } } -static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini) +static void smc_init_info_store_rc(u32 rc, struct smc_init_info *ini) { if (!ini->rc) ini->rc = rc; @@ -2203,7 +2204,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, mutex_unlock(&smcd_dev_list.mutex); if (!ini->ism_dev[0]) { - smc_find_ism_store_rc(SMC_CLC_DECL_NOSMCD2DEV, ini); + smc_init_info_store_rc(SMC_CLC_DECL_NOSMCD2DEV, ini); goto not_found; } @@ -2220,7 +2221,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, ini->ism_selected = i; rc = smc_listen_ism_init(new_smc, ini); if (rc) { - smc_find_ism_store_rc(rc, ini); + smc_init_info_store_rc(rc, ini); /* try next active ISM device */ continue; } @@ -2260,7 +2261,7 @@ static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc, return; /* V1 ISM device found */ not_found: - smc_find_ism_store_rc(rc, ini); + smc_init_info_store_rc(rc, ini); ini->smcd_version &= ~SMC_V1; ini->ism_dev[0] = NULL; ini->is_smcd = false; @@ -2311,7 +2312,7 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, ini->smcrv2.daddr = smc_ib_gid_to_ipv4(smc_v2_ext->roce); rc = smc_find_rdma_device(new_smc, ini); if (rc) { - smc_find_ism_store_rc(rc, ini); + smc_init_info_store_rc(rc, ini); goto not_found; } if (!ini->smcrv2.uses_gateway) @@ -2328,7 +2329,7 @@ static void smc_find_rdma_v2_device_serv(struct smc_sock *new_smc, if (!rc) return; ini->smcr_version = smcr_version; - smc_find_ism_store_rc(rc, ini); + smc_init_info_store_rc(rc, ini); not_found: ini->smcr_version &= ~SMC_V2; @@ -2375,7 +2376,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc, /* check for matching IP prefix and subnet length (V1) */ prfx_rc = smc_listen_prfx_check(new_smc, pclc); if (prfx_rc) - smc_find_ism_store_rc(prfx_rc, ini); + smc_init_info_store_rc(prfx_rc, ini); /* get vlan id from IP device */ if (smc_vlan_by_tcpsk(new_smc->clcsock, ini)) @@ -2402,7 +2403,7 @@ static int smc_listen_find_device(struct smc_sock *new_smc, int rc; rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini); - smc_find_ism_store_rc(rc, ini); + smc_init_info_store_rc(rc, ini); return (!rc) ? 0 : ini->rc; } return prfx_rc; @@ -3600,8 +3601,16 @@ static int __init smc_init(void) pr_err("%s: smc_inet_init fails with %d\n", __func__, rc); goto out_ulp; } + rc = bpf_smc_hs_ctrl_init(); + if (rc) { + pr_err("%s: bpf_smc_hs_ctrl_init fails with %d\n", __func__, + rc); + goto out_inet; + } static_branch_enable(&tcp_have_smc); return 0; +out_inet: + smc_inet_exit(); out_ulp: tcp_unregister_ulp(&smc_ulp_ops); out_ib: diff --git a/net/smc/smc.h b/net/smc/smc.h index 2c90849637398..9e6af72784baa 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -42,9 +42,9 @@ void smc_unhash_sk(struct sock *sk); void smc_release_cb(struct sock *sk); int smc_release(struct socket *sock); -int smc_bind(struct socket *sock, struct sockaddr *uaddr, +int smc_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len); -int smc_connect(struct socket *sock, struct sockaddr *addr, +int smc_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags); int smc_accept(struct socket *sock, struct socket *new_sock, struct proto_accept_arg *arg); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index be0c2da83d2bf..e4eabc83719e1 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -810,6 +810,8 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, lnk->clearing = 0; lnk->path_mtu = lnk->smcibdev->pattr[lnk->ibport - 1].active_mtu; lnk->link_id = smcr_next_link_id(lgr); + lnk->max_send_wr = lgr->max_send_wr; + lnk->max_recv_wr = lgr->max_recv_wr; lnk->lgr = lgr; smc_lgr_hold(lgr); /* lgr_put in smcr_link_clear() */ lnk->link_idx = link_idx; @@ -836,27 +838,39 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk, rc = smc_llc_link_init(lnk); if (rc) goto out; - rc = smc_wr_alloc_link_mem(lnk); - if (rc) - goto clear_llc_lnk; rc = smc_ib_create_protection_domain(lnk); if (rc) - goto free_link_mem; - rc = smc_ib_create_queue_pair(lnk); - if (rc) - goto dealloc_pd; + goto clear_llc_lnk; + do { + rc = smc_ib_create_queue_pair(lnk); + if (rc) + goto dealloc_pd; + rc = smc_wr_alloc_link_mem(lnk); + if (!rc) + break; + else if (rc != -ENOMEM) /* give up */ + goto destroy_qp; + /* retry with smaller ... */ + lnk->max_send_wr /= 2; + lnk->max_recv_wr /= 2; + /* ... unless droping below old SMC_WR_BUF_SIZE */ + if (lnk->max_send_wr < 16 || lnk->max_recv_wr < 48) + goto destroy_qp; + smc_ib_destroy_queue_pair(lnk); + } while (1); + rc = smc_wr_create_link(lnk); if (rc) - goto destroy_qp; + goto free_link_mem; lnk->state = SMC_LNK_ACTIVATING; return 0; +free_link_mem: + smc_wr_free_link_mem(lnk); destroy_qp: smc_ib_destroy_queue_pair(lnk); dealloc_pd: smc_ib_dealloc_protection_domain(lnk); -free_link_mem: - smc_wr_free_link_mem(lnk); clear_llc_lnk: smc_llc_link_clear(lnk, false); out: diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index a5a78cbff3411..5c18f08a4c8a5 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -34,6 +34,8 @@ * distributions may modify it to a value between * 16-255 as needed. */ +#define SMCR_MAX_SEND_WR_DEF 16 /* Default number of work requests per send queue */ +#define SMCR_MAX_RECV_WR_DEF 48 /* Default number of work requests per recv queue */ struct smc_lgr_list { /* list of link group definition */ struct list_head list; @@ -173,6 +175,8 @@ struct smc_link { struct completion llc_testlink_resp; /* wait for rx of testlink */ int llc_testlink_time; /* testlink interval */ atomic_t conn_cnt; /* connections on this link */ + u16 max_send_wr; + u16 max_recv_wr; }; /* For now we just allow one parallel link per link group. The SMC protocol @@ -366,6 +370,10 @@ struct smc_link_group { /* max conn can be assigned to lgr */ u8 max_links; /* max links can be added in lgr */ + u16 max_send_wr; + /* number of WR buffers on send */ + u16 max_recv_wr; + /* number of WR buffers on recv */ }; struct { /* SMC-D */ struct smcd_gid peer_gid; diff --git a/net/smc/smc_hs_bpf.c b/net/smc/smc_hs_bpf.c new file mode 100644 index 0000000000000..063d23d858508 --- /dev/null +++ b/net/smc/smc_hs_bpf.c @@ -0,0 +1,140 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Generic hook for SMC handshake flow. + * + * Copyright IBM Corp. 2016 + * Copyright (c) 2025, Alibaba Inc. + * + * Author: D. Wythe + */ + +#include +#include +#include +#include + +#include "smc_hs_bpf.h" + +static DEFINE_SPINLOCK(smc_hs_ctrl_list_lock); +static LIST_HEAD(smc_hs_ctrl_list); + +static int smc_hs_ctrl_reg(struct smc_hs_ctrl *ctrl) +{ + int ret = 0; + + spin_lock(&smc_hs_ctrl_list_lock); + /* already exist or duplicate name */ + if (smc_hs_ctrl_find_by_name(ctrl->name)) + ret = -EEXIST; + else + list_add_tail_rcu(&ctrl->list, &smc_hs_ctrl_list); + spin_unlock(&smc_hs_ctrl_list_lock); + return ret; +} + +static void smc_hs_ctrl_unreg(struct smc_hs_ctrl *ctrl) +{ + spin_lock(&smc_hs_ctrl_list_lock); + list_del_rcu(&ctrl->list); + spin_unlock(&smc_hs_ctrl_list_lock); + + /* Ensure that all readers to complete */ + synchronize_rcu(); +} + +struct smc_hs_ctrl *smc_hs_ctrl_find_by_name(const char *name) +{ + struct smc_hs_ctrl *ctrl; + + list_for_each_entry_rcu(ctrl, &smc_hs_ctrl_list, list) { + if (strcmp(ctrl->name, name) == 0) + return ctrl; + } + return NULL; +} + +static int __smc_bpf_stub_set_tcp_option(struct tcp_sock *tp) { return 1; } +static int __smc_bpf_stub_set_tcp_option_cond(const struct tcp_sock *tp, + struct inet_request_sock *ireq) +{ + return 1; +} + +static struct smc_hs_ctrl __smc_bpf_hs_ctrl = { + .syn_option = __smc_bpf_stub_set_tcp_option, + .synack_option = __smc_bpf_stub_set_tcp_option_cond, +}; + +static int smc_bpf_hs_ctrl_init(struct btf *btf) { return 0; } + +static int smc_bpf_hs_ctrl_reg(void *kdata, struct bpf_link *link) +{ + if (link) + return -EOPNOTSUPP; + + return smc_hs_ctrl_reg(kdata); +} + +static void smc_bpf_hs_ctrl_unreg(void *kdata, struct bpf_link *link) +{ + smc_hs_ctrl_unreg(kdata); +} + +static int smc_bpf_hs_ctrl_init_member(const struct btf_type *t, + const struct btf_member *member, + void *kdata, const void *udata) +{ + const struct smc_hs_ctrl *u_ctrl; + struct smc_hs_ctrl *k_ctrl; + u32 moff; + + u_ctrl = (const struct smc_hs_ctrl *)udata; + k_ctrl = (struct smc_hs_ctrl *)kdata; + + moff = __btf_member_bit_offset(t, member) / 8; + switch (moff) { + case offsetof(struct smc_hs_ctrl, name): + if (bpf_obj_name_cpy(k_ctrl->name, u_ctrl->name, + sizeof(u_ctrl->name)) <= 0) + return -EINVAL; + return 1; + case offsetof(struct smc_hs_ctrl, flags): + if (u_ctrl->flags & ~SMC_HS_CTRL_ALL_FLAGS) + return -EINVAL; + k_ctrl->flags = u_ctrl->flags; + return 1; + default: + break; + } + + return 0; +} + +static const struct bpf_func_proto * +bpf_smc_hs_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + return bpf_base_func_proto(func_id, prog); +} + +static const struct bpf_verifier_ops smc_bpf_verifier_ops = { + .get_func_proto = bpf_smc_hs_func_proto, + .is_valid_access = bpf_tracing_btf_ctx_access, +}; + +static struct bpf_struct_ops bpf_smc_hs_ctrl_ops = { + .name = "smc_hs_ctrl", + .init = smc_bpf_hs_ctrl_init, + .reg = smc_bpf_hs_ctrl_reg, + .unreg = smc_bpf_hs_ctrl_unreg, + .cfi_stubs = &__smc_bpf_hs_ctrl, + .verifier_ops = &smc_bpf_verifier_ops, + .init_member = smc_bpf_hs_ctrl_init_member, + .owner = THIS_MODULE, +}; + +int bpf_smc_hs_ctrl_init(void) +{ + return register_bpf_struct_ops(&bpf_smc_hs_ctrl_ops, smc_hs_ctrl); +} diff --git a/net/smc/smc_hs_bpf.h b/net/smc/smc_hs_bpf.h new file mode 100644 index 0000000000000..f5f1807c079e8 --- /dev/null +++ b/net/smc/smc_hs_bpf.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Shared Memory Communications over RDMA (SMC-R) and RoCE + * + * Generic hook for SMC handshake flow. + * + * Copyright IBM Corp. 2016 + * Copyright (c) 2025, Alibaba Inc. + * + * Author: D. Wythe + */ + +#ifndef __SMC_HS_CTRL +#define __SMC_HS_CTRL + +#include + +/* Find hs_ctrl by the target name, which required to be a c-string. + * Return NULL if no such ctrl was found,otherwise, return a valid ctrl. + * + * Note: Caller MUST ensure it's was invoked under rcu_read_lock. + */ +struct smc_hs_ctrl *smc_hs_ctrl_find_by_name(const char *name); + +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) +int bpf_smc_hs_ctrl_init(void); +#else +static inline int bpf_smc_hs_ctrl_init(void) { return 0; } +#endif /* CONFIG_SMC_HS_CTRL_BPF */ + +#endif /* __SMC_HS_CTRL */ diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 0052f02756ebb..1154907c5c050 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -669,11 +669,6 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) .recv_cq = lnk->smcibdev->roce_cq_recv, .srq = NULL, .cap = { - /* include unsolicited rdma_writes as well, - * there are max. 2 RDMA_WRITE per 1 WR_SEND - */ - .max_send_wr = SMC_WR_BUF_CNT * 3, - .max_recv_wr = SMC_WR_BUF_CNT * 3, .max_send_sge = SMC_IB_MAX_SEND_SGE, .max_recv_sge = lnk->wr_rx_sge_cnt, .max_inline_data = 0, @@ -683,6 +678,11 @@ int smc_ib_create_queue_pair(struct smc_link *lnk) }; int rc; + /* include unsolicited rdma_writes as well, + * there are max. 2 RDMA_WRITE per 1 WR_SEND + */ + qp_attr.cap.max_send_wr = 3 * lnk->lgr->max_send_wr; + qp_attr.cap.max_recv_wr = lnk->lgr->max_recv_wr; lnk->roce_qp = ib_create_qp(lnk->roce_pd, &qp_attr); rc = PTR_ERR_OR_ZERO(lnk->roce_qp); if (IS_ERR(lnk->roce_qp)) diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index f865c58c3aa77..f5d5eb6175267 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -2157,6 +2157,8 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) init_waitqueue_head(&lgr->llc_msg_waiter); init_rwsem(&lgr->llc_conf_mutex); lgr->llc_testlink_time = READ_ONCE(net->smc.sysctl_smcr_testlink_time); + lgr->max_send_wr = (u16)(READ_ONCE(net->smc.sysctl_smcr_max_send_wr)); + lgr->max_recv_wr = (u16)(READ_ONCE(net->smc.sysctl_smcr_max_recv_wr)); } /* called after lgr was removed from lgr_list */ diff --git a/net/smc/smc_sysctl.c b/net/smc/smc_sysctl.c index 2fab6456f7654..b1efed5462435 100644 --- a/net/smc/smc_sysctl.c +++ b/net/smc/smc_sysctl.c @@ -12,12 +12,14 @@ #include #include +#include #include #include "smc.h" #include "smc_core.h" #include "smc_llc.h" #include "smc_sysctl.h" +#include "smc_hs_bpf.h" static int min_sndbuf = SMC_BUF_MIN_SIZE; static int min_rcvbuf = SMC_BUF_MIN_SIZE; @@ -29,6 +31,71 @@ static int links_per_lgr_min = SMC_LINKS_ADD_LNK_MIN; static int links_per_lgr_max = SMC_LINKS_ADD_LNK_MAX; static int conns_per_lgr_min = SMC_CONN_PER_LGR_MIN; static int conns_per_lgr_max = SMC_CONN_PER_LGR_MAX; +static unsigned int smcr_max_wr_min = 2; +static unsigned int smcr_max_wr_max = 2048; + +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) +static int smc_net_replace_smc_hs_ctrl(struct net *net, const char *name) +{ + struct smc_hs_ctrl *ctrl = NULL; + + rcu_read_lock(); + /* null or empty name ask to clear current ctrl */ + if (name && name[0]) { + ctrl = smc_hs_ctrl_find_by_name(name); + if (!ctrl) { + rcu_read_unlock(); + return -EINVAL; + } + /* no change, just return */ + if (ctrl == rcu_dereference(net->smc.hs_ctrl)) { + rcu_read_unlock(); + return 0; + } + if (!bpf_try_module_get(ctrl, ctrl->owner)) { + rcu_read_unlock(); + return -EBUSY; + } + } + /* xhcg old ctrl with the new one atomically */ + ctrl = unrcu_pointer(xchg(&net->smc.hs_ctrl, RCU_INITIALIZER(ctrl))); + /* release old ctrl */ + if (ctrl) + bpf_module_put(ctrl, ctrl->owner); + + rcu_read_unlock(); + return 0; +} + +static int proc_smc_hs_ctrl(const struct ctl_table *ctl, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + struct net *net = container_of(ctl->data, struct net, smc.hs_ctrl); + char val[SMC_HS_CTRL_NAME_MAX]; + const struct ctl_table tbl = { + .data = val, + .maxlen = SMC_HS_CTRL_NAME_MAX, + }; + struct smc_hs_ctrl *ctrl; + int ret; + + rcu_read_lock(); + ctrl = rcu_dereference(net->smc.hs_ctrl); + if (ctrl) + memcpy(val, ctrl->name, sizeof(ctrl->name)); + else + val[0] = '\0'; + rcu_read_unlock(); + + ret = proc_dostring(&tbl, write, buffer, lenp, ppos); + if (ret) + return ret; + + if (write) + ret = smc_net_replace_smc_hs_ctrl(net, val); + return ret; +} +#endif /* CONFIG_SMC_HS_CTRL_BPF */ static struct ctl_table smc_table[] = { { @@ -99,6 +166,33 @@ static struct ctl_table smc_table[] = { .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, + { + .procname = "smcr_max_send_wr", + .data = &init_net.smc.sysctl_smcr_max_send_wr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &smcr_max_wr_min, + .extra2 = &smcr_max_wr_max, + }, + { + .procname = "smcr_max_recv_wr", + .data = &init_net.smc.sysctl_smcr_max_recv_wr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &smcr_max_wr_min, + .extra2 = &smcr_max_wr_max, + }, +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) + { + .procname = "hs_ctrl", + .data = &init_net.smc.hs_ctrl, + .mode = 0644, + .maxlen = SMC_HS_CTRL_NAME_MAX, + .proc_handler = proc_smc_hs_ctrl, + }, +#endif /* CONFIG_SMC_HS_CTRL_BPF */ }; int __net_init smc_sysctl_net_init(struct net *net) @@ -109,6 +203,16 @@ int __net_init smc_sysctl_net_init(struct net *net) table = smc_table; if (!net_eq(net, &init_net)) { int i; +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) + struct smc_hs_ctrl *ctrl; + + rcu_read_lock(); + ctrl = rcu_dereference(init_net.smc.hs_ctrl); + if (ctrl && ctrl->flags & SMC_HS_CTRL_FLAG_INHERITABLE && + bpf_try_module_get(ctrl, ctrl->owner)) + rcu_assign_pointer(net->smc.hs_ctrl, ctrl); + rcu_read_unlock(); +#endif /* CONFIG_SMC_HS_CTRL_BPF */ table = kmemdup(table, sizeof(smc_table), GFP_KERNEL); if (!table) @@ -130,6 +234,8 @@ int __net_init smc_sysctl_net_init(struct net *net) WRITE_ONCE(net->smc.sysctl_rmem, net_smc_rmem_init); net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER; net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER; + net->smc.sysctl_smcr_max_send_wr = SMCR_MAX_SEND_WR_DEF; + net->smc.sysctl_smcr_max_recv_wr = SMCR_MAX_RECV_WR_DEF; /* disable handshake limitation by default */ net->smc.limit_smc_hs = 0; @@ -139,6 +245,9 @@ int __net_init smc_sysctl_net_init(struct net *net) if (!net_eq(net, &init_net)) kfree(table); err_alloc: +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) + smc_net_replace_smc_hs_ctrl(net, NULL); +#endif /* CONFIG_SMC_HS_CTRL_BPF */ return -ENOMEM; } @@ -148,6 +257,10 @@ void __net_exit smc_sysctl_net_exit(struct net *net) table = net->smc.smc_hdr->ctl_table_arg; unregister_net_sysctl_table(net->smc.smc_hdr); +#if IS_ENABLED(CONFIG_SMC_HS_CTRL_BPF) + smc_net_replace_smc_hs_ctrl(net, NULL); +#endif /* CONFIG_SMC_HS_CTRL_BPF */ + if (!net_eq(net, &init_net)) kfree(table); } diff --git a/net/smc/smc_sysctl.h b/net/smc/smc_sysctl.h index eb2465ae1e15e..8538915af7afe 100644 --- a/net/smc/smc_sysctl.h +++ b/net/smc/smc_sysctl.h @@ -25,6 +25,8 @@ static inline int smc_sysctl_net_init(struct net *net) net->smc.sysctl_autocorking_size = SMC_AUTOCORKING_DEFAULT_SIZE; net->smc.sysctl_max_links_per_lgr = SMC_LINKS_PER_LGR_MAX_PREFER; net->smc.sysctl_max_conns_per_lgr = SMC_CONN_PER_LGR_PREFER; + net->smc.sysctl_smcr_max_send_wr = SMCR_MAX_SEND_WR_DEF; + net->smc.sysctl_smcr_max_recv_wr = SMCR_MAX_RECV_WR_DEF; return 0; } diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index b04a21b8c5111..5feafa98ab1a1 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -547,9 +547,9 @@ void smc_wr_remember_qp_attr(struct smc_link *lnk) IB_QP_DEST_QPN, &init_attr); - lnk->wr_tx_cnt = min_t(size_t, SMC_WR_BUF_CNT, + lnk->wr_tx_cnt = min_t(size_t, lnk->max_send_wr, lnk->qp_attr.cap.max_send_wr); - lnk->wr_rx_cnt = min_t(size_t, SMC_WR_BUF_CNT * 3, + lnk->wr_rx_cnt = min_t(size_t, lnk->max_recv_wr, lnk->qp_attr.cap.max_recv_wr); } @@ -741,50 +741,51 @@ int smc_wr_alloc_lgr_mem(struct smc_link_group *lgr) int smc_wr_alloc_link_mem(struct smc_link *link) { /* allocate link related memory */ - link->wr_tx_bufs = kcalloc(SMC_WR_BUF_CNT, SMC_WR_BUF_SIZE, GFP_KERNEL); + link->wr_tx_bufs = kcalloc(link->max_send_wr, + SMC_WR_BUF_SIZE, GFP_KERNEL); if (!link->wr_tx_bufs) goto no_mem; - link->wr_rx_bufs = kcalloc(SMC_WR_BUF_CNT * 3, link->wr_rx_buflen, + link->wr_rx_bufs = kcalloc(link->max_recv_wr, link->wr_rx_buflen, GFP_KERNEL); if (!link->wr_rx_bufs) goto no_mem_wr_tx_bufs; - link->wr_tx_ibs = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_ibs[0]), - GFP_KERNEL); + link->wr_tx_ibs = kcalloc(link->max_send_wr, + sizeof(link->wr_tx_ibs[0]), GFP_KERNEL); if (!link->wr_tx_ibs) goto no_mem_wr_rx_bufs; - link->wr_rx_ibs = kcalloc(SMC_WR_BUF_CNT * 3, + link->wr_rx_ibs = kcalloc(link->max_recv_wr, sizeof(link->wr_rx_ibs[0]), GFP_KERNEL); if (!link->wr_rx_ibs) goto no_mem_wr_tx_ibs; - link->wr_tx_rdmas = kcalloc(SMC_WR_BUF_CNT, + link->wr_tx_rdmas = kcalloc(link->max_send_wr, sizeof(link->wr_tx_rdmas[0]), GFP_KERNEL); if (!link->wr_tx_rdmas) goto no_mem_wr_rx_ibs; - link->wr_tx_rdma_sges = kcalloc(SMC_WR_BUF_CNT, + link->wr_tx_rdma_sges = kcalloc(link->max_send_wr, sizeof(link->wr_tx_rdma_sges[0]), GFP_KERNEL); if (!link->wr_tx_rdma_sges) goto no_mem_wr_tx_rdmas; - link->wr_tx_sges = kcalloc(SMC_WR_BUF_CNT, sizeof(link->wr_tx_sges[0]), + link->wr_tx_sges = kcalloc(link->max_send_wr, sizeof(link->wr_tx_sges[0]), GFP_KERNEL); if (!link->wr_tx_sges) goto no_mem_wr_tx_rdma_sges; - link->wr_rx_sges = kcalloc(SMC_WR_BUF_CNT * 3, + link->wr_rx_sges = kcalloc(link->max_recv_wr, sizeof(link->wr_rx_sges[0]) * link->wr_rx_sge_cnt, GFP_KERNEL); if (!link->wr_rx_sges) goto no_mem_wr_tx_sges; - link->wr_tx_mask = bitmap_zalloc(SMC_WR_BUF_CNT, GFP_KERNEL); + link->wr_tx_mask = bitmap_zalloc(link->max_send_wr, GFP_KERNEL); if (!link->wr_tx_mask) goto no_mem_wr_rx_sges; - link->wr_tx_pends = kcalloc(SMC_WR_BUF_CNT, + link->wr_tx_pends = kcalloc(link->max_send_wr, sizeof(link->wr_tx_pends[0]), GFP_KERNEL); if (!link->wr_tx_pends) goto no_mem_wr_tx_mask; - link->wr_tx_compl = kcalloc(SMC_WR_BUF_CNT, + link->wr_tx_compl = kcalloc(link->max_send_wr, sizeof(link->wr_tx_compl[0]), GFP_KERNEL); if (!link->wr_tx_compl) @@ -905,7 +906,7 @@ int smc_wr_create_link(struct smc_link *lnk) goto dma_unmap; } smc_wr_init_sge(lnk); - bitmap_zero(lnk->wr_tx_mask, SMC_WR_BUF_CNT); + bitmap_zero(lnk->wr_tx_mask, lnk->max_send_wr); init_waitqueue_head(&lnk->wr_tx_wait); rc = percpu_ref_init(&lnk->wr_tx_refs, smcr_wr_tx_refs_free, 0, GFP_KERNEL); if (rc) diff --git a/net/smc/smc_wr.h b/net/smc/smc_wr.h index f3008dda222a6..aa4533af9122d 100644 --- a/net/smc/smc_wr.h +++ b/net/smc/smc_wr.h @@ -19,8 +19,6 @@ #include "smc.h" #include "smc_core.h" -#define SMC_WR_BUF_CNT 16 /* # of ctrl buffers per link */ - #define SMC_WR_TX_WAIT_FREE_SLOT_TIME (10 * HZ) #define SMC_WR_TX_SIZE 44 /* actual size of wr_send data (<=SMC_WR_BUF_SIZE) */ diff --git a/net/socket.c b/net/socket.c index e8892b2187087..101a7ed574e75 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1872,7 +1872,7 @@ int __sys_bind_socket(struct socket *sock, struct sockaddr_storage *address, addrlen); if (!err) err = READ_ONCE(sock->ops)->bind(sock, - (struct sockaddr *)address, + (struct sockaddr_unsized *)address, addrlen); return err; } @@ -2099,8 +2099,8 @@ int __sys_connect_file(struct file *file, struct sockaddr_storage *address, if (err) goto out; - err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)address, - addrlen, sock->file->f_flags | file_flags); + err = READ_ONCE(sock->ops)->connect(sock, (struct sockaddr_unsized *)address, + addrlen, sock->file->f_flags | file_flags); out: return err; } @@ -3583,13 +3583,13 @@ static long compat_sock_ioctl(struct file *file, unsigned int cmd, * Returns 0 or an error. */ -int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) +int kernel_bind(struct socket *sock, struct sockaddr_unsized *addr, int addrlen) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); - return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr *)&address, + return READ_ONCE(sock->ops)->bind(sock, (struct sockaddr_unsized *)&address, addrlen); } EXPORT_SYMBOL(kernel_bind); @@ -3662,14 +3662,14 @@ EXPORT_SYMBOL(kernel_accept); * Returns 0 or an error code. */ -int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, +int kernel_connect(struct socket *sock, struct sockaddr_unsized *addr, int addrlen, int flags) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); - return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr *)&address, + return READ_ONCE(sock->ops)->connect(sock, (struct sockaddr_unsized *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index e659fea2da70f..fe0e76fdd1f1c 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -127,7 +127,7 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, } if (!strp->skb_nextp) { - /* We are going to append to the frags_list of head. + /* We are going to append to the frag_list of head. * Need to unshare the frag_list. */ err = skb_unclone(head, GFP_ATOMIC); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8ca354ecfd02a..58442ae1c2da2 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1457,12 +1457,12 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, switch (sap->sa_family) { case AF_INET: err = kernel_bind(sock, - (struct sockaddr *)&rpc_inaddr_loopback, + (struct sockaddr_unsized *)&rpc_inaddr_loopback, sizeof(rpc_inaddr_loopback)); break; case AF_INET6: err = kernel_bind(sock, - (struct sockaddr *)&rpc_in6addr_loopback, + (struct sockaddr_unsized *)&rpc_in6addr_loopback, sizeof(rpc_in6addr_loopback)); break; default: @@ -1474,7 +1474,7 @@ static int rpc_sockname(struct net *net, struct sockaddr *sap, size_t salen, goto out_release; } - err = kernel_connect(sock, sap, salen, 0); + err = kernel_connect(sock, (struct sockaddr_unsized *)sap, salen, 0); if (err < 0) { dprintk("RPC: can't connect UDP socket (%d)\n", err); goto out_release; diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 7b90abc5cf0ee..16ff6c100821a 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -1557,7 +1557,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv, ip6_sock_set_v6only(sock->sk); if (type == SOCK_STREAM) sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */ - error = kernel_bind(sock, sin, len); + error = kernel_bind(sock, (struct sockaddr_unsized *)sin, len); if (error < 0) goto bummer; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 3aa987e7f0724..2e1fe60133615 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1845,8 +1845,8 @@ static int xs_bind(struct sock_xprt *transport, struct socket *sock) memcpy(&myaddr, &transport->srcaddr, transport->xprt.addrlen); do { rpc_set_port((struct sockaddr *)&myaddr, port); - err = kernel_bind(sock, (struct sockaddr *)&myaddr, - transport->xprt.addrlen); + err = kernel_bind(sock, (struct sockaddr_unsized *)&myaddr, + transport->xprt.addrlen); if (err == 0) { if (transport->xprt.reuseport) transport->srcport = port; @@ -2005,7 +2005,7 @@ static int xs_local_finish_connecting(struct rpc_xprt *xprt, xs_stream_start_connect(transport); - return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, 0); + return kernel_connect(sock, (struct sockaddr_unsized *)xs_addr(xprt), xprt->addrlen, 0); } /** @@ -2405,7 +2405,8 @@ static int xs_tcp_finish_connecting(struct rpc_xprt *xprt, struct socket *sock) /* Tell the socket layer to start connecting... */ set_bit(XPRT_SOCK_CONNECTING, &transport->sock_state); - return kernel_connect(sock, xs_addr(xprt), xprt->addrlen, O_NONBLOCK); + return kernel_connect(sock, (struct sockaddr_unsized *)xs_addr(xprt), + xprt->addrlen, O_NONBLOCK); } /** diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1574a83384f88..817b07d95a914 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -710,7 +710,7 @@ int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen) return res; } -static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen) +static int tipc_bind(struct socket *sock, struct sockaddr_unsized *skaddr, int alen) { struct tipc_uaddr *ua = (struct tipc_uaddr *)skaddr; u32 atype = ua->addrtype; @@ -726,7 +726,7 @@ static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen) return -EACCES; } } - return tipc_sk_bind(sock, skaddr, alen); + return tipc_sk_bind(sock, (struct sockaddr *)skaddr, alen); } /** @@ -2565,7 +2565,7 @@ static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr) * * Return: 0 on success, errno otherwise */ -static int tipc_connect(struct socket *sock, struct sockaddr *dest, +static int tipc_connect(struct socket *sock, struct sockaddr_unsized *dest, int destlen, int flags) { struct sock *sk = sock->sk; @@ -3031,10 +3031,8 @@ static void tipc_sk_remove(struct tipc_sock *tsk) struct sock *sk = &tsk->sk; struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id); - if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) { - WARN_ON(refcount_read(&sk->sk_refcnt) == 1); + if (!rhashtable_remove_fast(&tn->sk_rht, &tsk->node, tsk_rht_params)) __sock_put(sk); - } } static const struct rhashtable_params tsk_rht_params = { diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 71734411ff4c3..82ea407e520a0 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -373,7 +373,8 @@ static int tls_do_allocation(struct sock *sk, if (!offload_ctx->open_record) { if (unlikely(!skb_page_frag_refill(prepend_size, pfrag, sk->sk_allocation))) { - READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk); + if (!sk->sk_bypass_prot_mem) + READ_ONCE(sk->sk_prot)->enter_memory_pressure(sk); sk_stream_moderate_sndbuf(sk); return -ENOMEM; } @@ -461,7 +462,7 @@ static int tls_push_data(struct sock *sk, /* TLS_HEADER_SIZE is not counted as part of the TLS record, and * we need to leave room for an authentication tag. */ - max_open_record_len = TLS_MAX_PAYLOAD_SIZE + + max_open_record_len = tls_ctx->tx_max_payload_len + prot->prepend_size; do { rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 39a2ab47fe720..56ce0bc8317b1 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -541,6 +541,28 @@ static int do_tls_getsockopt_no_pad(struct sock *sk, char __user *optval, return 0; } +static int do_tls_getsockopt_tx_payload_len(struct sock *sk, char __user *optval, + int __user *optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + u16 payload_len = ctx->tx_max_payload_len; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + if (len < sizeof(payload_len)) + return -EINVAL; + + if (put_user(sizeof(payload_len), optlen)) + return -EFAULT; + + if (copy_to_user(optval, &payload_len, sizeof(payload_len))) + return -EFAULT; + + return 0; +} + static int do_tls_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { @@ -560,6 +582,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, case TLS_RX_EXPECT_NO_PAD: rc = do_tls_getsockopt_no_pad(sk, optval, optlen); break; + case TLS_TX_MAX_PAYLOAD_LEN: + rc = do_tls_getsockopt_tx_payload_len(sk, optval, optlen); + break; default: rc = -ENOPROTOOPT; break; @@ -809,6 +834,32 @@ static int do_tls_setsockopt_no_pad(struct sock *sk, sockptr_t optval, return rc; } +static int do_tls_setsockopt_tx_payload_len(struct sock *sk, sockptr_t optval, + unsigned int optlen) +{ + struct tls_context *ctx = tls_get_ctx(sk); + struct tls_sw_context_tx *sw_ctx = tls_sw_ctx_tx(ctx); + u16 value; + bool tls_13 = ctx->prot_info.version == TLS_1_3_VERSION; + + if (sw_ctx && sw_ctx->open_rec) + return -EBUSY; + + if (sockptr_is_null(optval) || optlen != sizeof(value)) + return -EINVAL; + + if (copy_from_sockptr(&value, optval, sizeof(value))) + return -EFAULT; + + if (value < TLS_MIN_RECORD_SIZE_LIM - (tls_13 ? 1 : 0) || + value > TLS_MAX_PAYLOAD_SIZE) + return -EINVAL; + + ctx->tx_max_payload_len = value; + + return 0; +} + static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, unsigned int optlen) { @@ -830,6 +881,11 @@ static int do_tls_setsockopt(struct sock *sk, int optname, sockptr_t optval, case TLS_RX_EXPECT_NO_PAD: rc = do_tls_setsockopt_no_pad(sk, optval, optlen); break; + case TLS_TX_MAX_PAYLOAD_LEN: + lock_sock(sk); + rc = do_tls_setsockopt_tx_payload_len(sk, optval, optlen); + release_sock(sk); + break; default: rc = -ENOPROTOOPT; break; @@ -1019,6 +1075,7 @@ static int tls_init(struct sock *sk) ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; + ctx->tx_max_payload_len = TLS_MAX_PAYLOAD_SIZE; update_sk_prot(sk, ctx); out: write_unlock_bh(&sk->sk_callback_lock); @@ -1108,6 +1165,12 @@ static int tls_get_info(struct sock *sk, struct sk_buff *skb, bool net_admin) goto nla_failure; } + err = nla_put_u16(skb, TLS_INFO_TX_MAX_PAYLOAD_LEN, + ctx->tx_max_payload_len); + + if (err) + goto nla_failure; + rcu_read_unlock(); nla_nest_end(skb, start); return 0; @@ -1129,6 +1192,7 @@ static size_t tls_get_info_size(const struct sock *sk, bool net_admin) nla_total_size(sizeof(u16)) + /* TLS_INFO_TXCONF */ nla_total_size(0) + /* TLS_INFO_ZC_RO_TX */ nla_total_size(0) + /* TLS_INFO_RX_NO_PAD */ + nla_total_size(sizeof(u16)) + /* TLS_INFO_TX_MAX_PAYLOAD_LEN */ 0; return size; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d171353699800..9937d4c810f2b 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1079,7 +1079,7 @@ static int tls_sw_sendmsg_locked(struct sock *sk, struct msghdr *msg, orig_size = msg_pl->sg.size; full_record = false; try_to_copy = msg_data_left(msg); - record_room = TLS_MAX_PAYLOAD_SIZE - msg_pl->sg.size; + record_room = tls_ctx->tx_max_payload_len - msg_pl->sg.size; if (try_to_copy >= record_room) { try_to_copy = record_room; full_record = true; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 768098dec2310..e518116f81719 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -733,19 +733,7 @@ static void unix_release_sock(struct sock *sk, int embrion) /* ---- Socket is dead now and most probably destroyed ---- */ - /* - * Fixme: BSD difference: In BSD all sockets connected to us get - * ECONNRESET and we die on the spot. In Linux we behave - * like files and pipes do and wait for the last - * dereference. - * - * Can't we simply set sock->err? - * - * What the above comment does talk about? --ANK(980817) - */ - - if (READ_ONCE(unix_tot_inflight)) - unix_gc(); /* Garbage collect fds */ + unix_schedule_gc(NULL); } struct unix_peercred { @@ -854,8 +842,8 @@ static int unix_listen(struct socket *sock, int backlog) } static int unix_release(struct socket *); -static int unix_bind(struct socket *, struct sockaddr *, int); -static int unix_stream_connect(struct socket *, struct sockaddr *, +static int unix_bind(struct socket *, struct sockaddr_unsized *, int); +static int unix_stream_connect(struct socket *, struct sockaddr_unsized *, int addr_len, int flags); static int unix_socketpair(struct socket *, struct socket *); static int unix_accept(struct socket *, struct socket *, struct proto_accept_arg *arg); @@ -877,7 +865,7 @@ static int unix_dgram_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_dgram_recvmsg(struct socket *, struct msghdr *, size_t, int); static int unix_read_skb(struct sock *sk, skb_read_actor_t recv_actor); static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor); -static int unix_dgram_connect(struct socket *, struct sockaddr *, +static int unix_dgram_connect(struct socket *, struct sockaddr_unsized *, int, int); static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, @@ -1477,7 +1465,7 @@ static int unix_bind_abstract(struct sock *sk, struct sockaddr_un *sunaddr, return err; } -static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int unix_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; struct sock *sk = sock->sk; @@ -1523,7 +1511,7 @@ static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) unix_state_unlock(sk2); } -static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, +static int unix_dgram_connect(struct socket *sock, struct sockaddr_unsized *addr, int alen, int flags) { struct sockaddr_un *sunaddr = (struct sockaddr_un *)addr; @@ -1642,7 +1630,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) return timeo; } -static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, +static int unix_stream_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sockaddr_un *sunaddr = (struct sockaddr_un *)uaddr; @@ -2110,8 +2098,6 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) return err; - wait_for_unix_gc(scm.fp); - if (msg->msg_flags & MSG_OOB) { err = -EOPNOTSUPP; goto out; @@ -2405,8 +2391,6 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg, if (err < 0) return err; - wait_for_unix_gc(scm.fp); - if (msg->msg_flags & MSG_OOB) { err = -EOPNOTSUPP; #if IS_ENABLED(CONFIG_AF_UNIX_OOB) diff --git a/net/unix/af_unix.h b/net/unix/af_unix.h index 59db179df9bb5..c4f1b2da363de 100644 --- a/net/unix/af_unix.h +++ b/net/unix/af_unix.h @@ -24,14 +24,12 @@ struct unix_skb_parms { #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) /* GC for SCM_RIGHTS */ -extern unsigned int unix_tot_inflight; void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver); void unix_del_edges(struct scm_fp_list *fpl); void unix_update_edges(struct unix_sock *receiver); int unix_prepare_fpl(struct scm_fp_list *fpl); void unix_destroy_fpl(struct scm_fp_list *fpl); -void unix_gc(void); -void wait_for_unix_gc(struct scm_fp_list *fpl); +void unix_schedule_gc(struct user_struct *user); /* SOCK_DIAG */ long unix_inq_len(struct sock *sk); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 65396a4e1b07e..78323d43e63ed 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -121,8 +121,13 @@ static struct unix_vertex *unix_edge_successor(struct unix_edge *edge) return edge->successor->vertex; } -static bool unix_graph_maybe_cyclic; -static bool unix_graph_grouped; +enum { + UNIX_GRAPH_NOT_CYCLIC, + UNIX_GRAPH_MAYBE_CYCLIC, + UNIX_GRAPH_CYCLIC, +}; + +static unsigned char unix_graph_state; static void unix_update_graph(struct unix_vertex *vertex) { @@ -132,8 +137,7 @@ static void unix_update_graph(struct unix_vertex *vertex) if (!vertex) return; - unix_graph_maybe_cyclic = true; - unix_graph_grouped = false; + WRITE_ONCE(unix_graph_state, UNIX_GRAPH_MAYBE_CYCLIC); } static LIST_HEAD(unix_unvisited_vertices); @@ -196,7 +200,6 @@ static void unix_free_vertices(struct scm_fp_list *fpl) } static DEFINE_SPINLOCK(unix_gc_lock); -unsigned int unix_tot_inflight; void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) { @@ -222,7 +225,6 @@ void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver) } while (i < fpl->count_unix); receiver->scm_stat.nr_unix_fds += fpl->count_unix; - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight + fpl->count); @@ -253,7 +255,6 @@ void unix_del_edges(struct scm_fp_list *fpl) receiver = fpl->edges[0].successor; receiver->scm_stat.nr_unix_fds -= fpl->count_unix; } - WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - fpl->count_unix); out: WRITE_ONCE(fpl->user->unix_inflight, fpl->user->unix_inflight - fpl->count); @@ -299,6 +300,8 @@ int unix_prepare_fpl(struct scm_fp_list *fpl) if (!fpl->edges) goto err; + unix_schedule_gc(fpl->user); + return 0; err: @@ -404,9 +407,11 @@ static bool unix_scc_cyclic(struct list_head *scc) static LIST_HEAD(unix_visited_vertices); static unsigned long unix_vertex_grouped_index = UNIX_VERTEX_INDEX_MARK2; -static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_index, - struct sk_buff_head *hitlist) +static unsigned long __unix_walk_scc(struct unix_vertex *vertex, + unsigned long *last_index, + struct sk_buff_head *hitlist) { + unsigned long cyclic_sccs = 0; LIST_HEAD(vertex_stack); struct unix_edge *edge; LIST_HEAD(edge_stack); @@ -497,8 +502,8 @@ static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_inde if (unix_vertex_max_scc_index < vertex->scc_index) unix_vertex_max_scc_index = vertex->scc_index; - if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + if (unix_scc_cyclic(&scc)) + cyclic_sccs++; } list_del(&scc); @@ -507,13 +512,17 @@ static void __unix_walk_scc(struct unix_vertex *vertex, unsigned long *last_inde /* Need backtracking ? */ if (!list_empty(&edge_stack)) goto prev_vertex; + + return cyclic_sccs; } +static unsigned long unix_graph_cyclic_sccs; + static void unix_walk_scc(struct sk_buff_head *hitlist) { unsigned long last_index = UNIX_VERTEX_INDEX_START; + unsigned long cyclic_sccs = 0; - unix_graph_maybe_cyclic = false; unix_vertex_max_scc_index = UNIX_VERTEX_INDEX_START; /* Visit every vertex exactly once. @@ -523,18 +532,20 @@ static void unix_walk_scc(struct sk_buff_head *hitlist) struct unix_vertex *vertex; vertex = list_first_entry(&unix_unvisited_vertices, typeof(*vertex), entry); - __unix_walk_scc(vertex, &last_index, hitlist); + cyclic_sccs += __unix_walk_scc(vertex, &last_index, hitlist); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); swap(unix_vertex_unvisited_index, unix_vertex_grouped_index); - unix_graph_grouped = true; + WRITE_ONCE(unix_graph_cyclic_sccs, cyclic_sccs); + WRITE_ONCE(unix_graph_state, + cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC); } static void unix_walk_scc_fast(struct sk_buff_head *hitlist) { - unix_graph_maybe_cyclic = false; + unsigned long cyclic_sccs = unix_graph_cyclic_sccs; while (!list_empty(&unix_unvisited_vertices)) { struct unix_vertex *vertex; @@ -551,34 +562,38 @@ static void unix_walk_scc_fast(struct sk_buff_head *hitlist) scc_dead = unix_vertex_dead(vertex); } - if (scc_dead) + if (scc_dead) { + cyclic_sccs--; unix_collect_skb(&scc, hitlist); - else if (!unix_graph_maybe_cyclic) - unix_graph_maybe_cyclic = unix_scc_cyclic(&scc); + } list_del(&scc); } list_replace_init(&unix_visited_vertices, &unix_unvisited_vertices); + + WRITE_ONCE(unix_graph_cyclic_sccs, cyclic_sccs); + WRITE_ONCE(unix_graph_state, + cyclic_sccs ? UNIX_GRAPH_CYCLIC : UNIX_GRAPH_NOT_CYCLIC); } static bool gc_in_progress; -static void __unix_gc(struct work_struct *work) +static void unix_gc(struct work_struct *work) { struct sk_buff_head hitlist; struct sk_buff *skb; spin_lock(&unix_gc_lock); - if (!unix_graph_maybe_cyclic) { + if (unix_graph_state == UNIX_GRAPH_NOT_CYCLIC) { spin_unlock(&unix_gc_lock); goto skip_gc; } __skb_queue_head_init(&hitlist); - if (unix_graph_grouped) + if (unix_graph_state == UNIX_GRAPH_CYCLIC) unix_walk_scc_fast(&hitlist); else unix_walk_scc(&hitlist); @@ -595,36 +610,27 @@ static void __unix_gc(struct work_struct *work) WRITE_ONCE(gc_in_progress, false); } -static DECLARE_WORK(unix_gc_work, __unix_gc); +static DECLARE_WORK(unix_gc_work, unix_gc); -void unix_gc(void) -{ - WRITE_ONCE(gc_in_progress, true); - queue_work(system_dfl_wq, &unix_gc_work); -} +#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) -#define UNIX_INFLIGHT_TRIGGER_GC 16000 -#define UNIX_INFLIGHT_SANE_USER (SCM_MAX_FD * 8) - -void wait_for_unix_gc(struct scm_fp_list *fpl) +void unix_schedule_gc(struct user_struct *user) { - /* If number of inflight sockets is insane, - * force a garbage collect right now. - * - * Paired with the WRITE_ONCE() in unix_inflight(), - * unix_notinflight(), and __unix_gc(). - */ - if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && - !READ_ONCE(gc_in_progress)) - unix_gc(); + if (READ_ONCE(unix_graph_state) == UNIX_GRAPH_NOT_CYCLIC) + return; /* Penalise users who want to send AF_UNIX sockets * but whose sockets have not been received yet. */ - if (!fpl || !fpl->count_unix || - READ_ONCE(fpl->user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) + if (user && + READ_ONCE(user->unix_inflight) < UNIX_INFLIGHT_SANE_USER) return; - if (READ_ONCE(gc_in_progress)) + if (!READ_ONCE(gc_in_progress)) { + WRITE_ONCE(gc_in_progress, true); + queue_work(system_dfl_wq, &unix_gc_work); + } + + if (user && READ_ONCE(unix_graph_cyclic_sccs)) flush_work(&unix_gc_work); } diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 76763247a377a..72bb6b7ed386b 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -987,7 +987,7 @@ static int vsock_release(struct socket *sock) } static int -vsock_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +vsock_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { int err; struct sock *sk; @@ -1328,7 +1328,7 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg, } static int vsock_dgram_connect(struct socket *sock, - struct sockaddr *addr, int addr_len, int flags) + struct sockaddr_unsized *addr, int addr_len, int flags) { int err; struct sock *sk; @@ -1528,7 +1528,7 @@ static void vsock_connect_timeout(struct work_struct *work) sock_put(sk); } -static int vsock_connect(struct socket *sock, struct sockaddr *addr, +static int vsock_connect(struct socket *sock, struct sockaddr_unsized *addr, int addr_len, int flags) { int err; diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c index 223b9660a759f..a986aa6fff9bb 100644 --- a/net/vmw_vsock/vsock_addr.c +++ b/net/vmw_vsock/vsock_addr.c @@ -57,7 +57,7 @@ bool vsock_addr_equals_addr(const struct sockaddr_vm *addr, } EXPORT_SYMBOL_GPL(vsock_addr_equals_addr); -int vsock_addr_cast(const struct sockaddr *addr, +int vsock_addr_cast(const struct sockaddr_unsized *addr, size_t len, struct sockaddr_vm **out_addr) { if (len < sizeof(**out_addr)) diff --git a/net/wireless/core.c b/net/wireless/core.c index 54a34d8d356e0..aa78dbaaf093b 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -34,6 +34,9 @@ /* name for sysfs, %d is appended */ #define PHY_NAME "phy" +/* maximum length of radio debugfs directory name */ +#define RADIO_DEBUGFSDIR_MAX_LEN 8 + MODULE_AUTHOR("Johannes Berg"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("wireless configuration support"); @@ -1042,6 +1045,18 @@ int wiphy_register(struct wiphy *wiphy) /* add to debugfs */ rdev->wiphy.debugfsdir = debugfs_create_dir(wiphy_name(&rdev->wiphy), ieee80211_debugfs_dir); + if (wiphy->n_radio > 0) { + int idx; + char radio_name[RADIO_DEBUGFSDIR_MAX_LEN]; + + for (idx = 0; idx < wiphy->n_radio; idx++) { + scnprintf(radio_name, sizeof(radio_name), "radio%d", + idx); + wiphy->radio_cfg[idx].radio_debugfsdir = + debugfs_create_dir(radio_name, + rdev->wiphy.debugfsdir); + } + } cfg80211_debugfs_rdev_add(rdev); nl80211_notify_wiphy(rdev, NL80211_CMD_NEW_WIPHY); @@ -1051,12 +1066,12 @@ int wiphy_register(struct wiphy *wiphy) wiphy_regulatory_register(wiphy); if (wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) { - struct regulatory_request request; - - request.wiphy_idx = get_wiphy_idx(wiphy); - request.initiator = NL80211_REGDOM_SET_BY_DRIVER; - request.alpha2[0] = '9'; - request.alpha2[1] = '9'; + struct regulatory_request request = { + .wiphy_idx = get_wiphy_idx(wiphy), + .initiator = NL80211_REGDOM_SET_BY_DRIVER, + .alpha2[0] = '9', + .alpha2[1] = '9', + }; nl80211_send_reg_change_event(&request); } diff --git a/net/wireless/core.h b/net/wireless/core.h index b6bd7f4d6385a..82f343663e8fa 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -550,7 +550,8 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, bool signal_valid, unsigned long ts); enum ieee80211_ap_reg_power -cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len); +cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len, + u32 client_flags); #ifdef CONFIG_CFG80211_DEVELOPER_WARNINGS #define CFG80211_DEV_WARN_ON(cond) WARN_ON(cond) diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c index 40e49074e2eeb..f9e7fff1ef257 100644 --- a/net/wireless/debugfs.c +++ b/net/wireless/debugfs.c @@ -29,6 +29,24 @@ static const struct file_operations name## _ops = { \ .llseek = generic_file_llseek, \ } +#define DEBUGFS_RADIO_READONLY_FILE(name, buflen, fmt, value...) \ +static ssize_t name## _read(struct file *file, char __user *userbuf, \ + size_t count, loff_t *ppos) \ +{ \ + struct wiphy_radio_cfg *radio_cfg = file->private_data; \ + char buf[buflen]; \ + int res; \ + \ + res = scnprintf(buf, buflen, fmt "\n", ##value); \ + return simple_read_from_buffer(userbuf, count, ppos, buf, res); \ +} \ + \ +static const struct file_operations name## _ops = { \ + .read = name## _read, \ + .open = simple_open, \ + .llseek = generic_file_llseek, \ +} + DEBUGFS_READONLY_FILE(rts_threshold, 20, "%d", wiphy->rts_threshold); DEBUGFS_READONLY_FILE(fragmentation_threshold, 20, "%d", @@ -38,6 +56,9 @@ DEBUGFS_READONLY_FILE(short_retry_limit, 20, "%d", DEBUGFS_READONLY_FILE(long_retry_limit, 20, "%d", wiphy->retry_long); +DEBUGFS_RADIO_READONLY_FILE(radio_rts_threshold, 20, "%d", + radio_cfg->rts_threshold); + static int ht_print_chan(struct ieee80211_channel *chan, char *buf, int buf_size, int offset) { @@ -100,15 +121,27 @@ static const struct file_operations ht40allow_map_ops = { #define DEBUGFS_ADD(name) \ debugfs_create_file(#name, 0444, phyd, &rdev->wiphy, &name## _ops) +#define DEBUGFS_RADIO_ADD(name, radio_idx) \ + debugfs_create_file(#name, 0444, radiod, \ + &rdev->wiphy.radio_cfg[radio_idx], \ + &name## _ops) + void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev) { struct dentry *phyd = rdev->wiphy.debugfsdir; + struct dentry *radiod; + u8 i; DEBUGFS_ADD(rts_threshold); DEBUGFS_ADD(fragmentation_threshold); DEBUGFS_ADD(short_retry_limit); DEBUGFS_ADD(long_retry_limit); DEBUGFS_ADD(ht40allow_map); + + for (i = 0; i < rdev->wiphy.n_radio; i++) { + radiod = rdev->wiphy.radio_cfg[i].radio_debugfsdir; + DEBUGFS_RADIO_ADD(radio_rts_threshold, i); + } } struct debugfs_read_work { diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 03d07b54359a4..29c92bc8291bd 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3544,6 +3544,9 @@ static int _nl80211_parse_chandef(struct cfg80211_registered_device *rdev, return -EINVAL; } + if (cfg80211_chandef_is_s1g(chandef)) + chandef->width = NL80211_CHAN_WIDTH_1; + if (attrs[NL80211_ATTR_WIPHY_CHANNEL_TYPE]) { enum nl80211_channel_type chantype; @@ -6745,7 +6748,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) beacon_check.relax = true; beacon_check.reg_power = cfg80211_get_6ghz_power_type(params->beacon.tail, - params->beacon.tail_len); + params->beacon.tail_len, 0); if (!cfg80211_reg_check_beaconing(&rdev->wiphy, ¶ms->chandef, &beacon_check)) { err = -EINVAL; @@ -6924,7 +6927,7 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) beacon_check.relax = true; beacon_check.reg_power = cfg80211_get_6ghz_power_type(params->beacon.tail, - params->beacon.tail_len); + params->beacon.tail_len, 0); if (!cfg80211_reg_check_beaconing(&rdev->wiphy, &wdev->links[link_id].ap.chandef, &beacon_check)) { diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 90a9187a6b135..7546647752fd8 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -2212,7 +2212,8 @@ struct cfg80211_inform_single_bss_data { }; enum ieee80211_ap_reg_power -cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len) +cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len, + u32 client_flags) { const struct ieee80211_he_6ghz_oper *he_6ghz_oper; struct ieee80211_he_operation *he_oper; @@ -2230,26 +2231,13 @@ cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len) if (!he_6ghz_oper) return IEEE80211_REG_UNSET_AP; - switch (u8_get_bits(he_6ghz_oper->control, - IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO)) { - case IEEE80211_6GHZ_CTRL_REG_LPI_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP: - return IEEE80211_REG_LPI_AP; - case IEEE80211_6GHZ_CTRL_REG_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP: - case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD: - return IEEE80211_REG_SP_AP; - case IEEE80211_6GHZ_CTRL_REG_VLP_AP: - return IEEE80211_REG_VLP_AP; - default: - return IEEE80211_REG_UNSET_AP; - } + return cfg80211_6ghz_power_type(he_6ghz_oper->control, client_flags); } static bool cfg80211_6ghz_power_type_valid(const u8 *elems, size_t elems_len, const u32 flags) { - switch (cfg80211_get_6ghz_power_type(elems, elems_len)) { + switch (cfg80211_get_6ghz_power_type(elems, elems_len, flags)) { case IEEE80211_REG_LPI_AP: return true; case IEEE80211_REG_SP_AP: diff --git a/net/wireless/util.c b/net/wireless/util.c index 56724b33af045..97f40c6d1e9d1 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -2942,9 +2942,8 @@ cfg80211_get_iftype_ext_capa(struct wiphy *wiphy, enum nl80211_iftype type) } EXPORT_SYMBOL(cfg80211_get_iftype_ext_capa); -static bool -ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, - u32 freq, u32 width) +bool ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, + u32 freq, u32 width) { const struct wiphy_radio_freq_range *r; int i; @@ -2958,6 +2957,7 @@ ieee80211_radio_freq_range_valid(const struct wiphy_radio *radio, return false; } +EXPORT_SYMBOL(ieee80211_radio_freq_range_valid); bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio, const struct cfg80211_chan_def *chandef) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 655d1e0ae25f7..af8762b24039d 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -670,7 +670,7 @@ static int x25_release(struct socket *sock) return 0; } -static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int x25_bind(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len) { struct sock *sk = sock->sk; struct sockaddr_x25 *addr = (struct sockaddr_x25 *)uaddr; @@ -743,7 +743,7 @@ static int x25_wait_for_connection_establishment(struct sock *sk) return rc; } -static int x25_connect(struct socket *sock, struct sockaddr *uaddr, +static int x25_connect(struct socket *sock, struct sockaddr_unsized *uaddr, int addr_len, int flags) { struct sock *sk = sock->sk; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 7b0c68a70888c..bcfd400e9cf8b 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -548,12 +548,11 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags) static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool) { - unsigned long flags; int ret; - spin_lock_irqsave(&pool->cq_lock, flags); + spin_lock(&pool->cq_cached_prod_lock); ret = xskq_prod_reserve(pool->cq); - spin_unlock_irqrestore(&pool->cq_lock, flags); + spin_unlock(&pool->cq_cached_prod_lock); return ret; } @@ -566,7 +565,7 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, unsigned long flags; u32 idx; - spin_lock_irqsave(&pool->cq_lock, flags); + spin_lock_irqsave(&pool->cq_prod_lock, flags); idx = xskq_get_prod(pool->cq); xskq_prod_write_addr(pool->cq, idx, @@ -583,16 +582,14 @@ static void xsk_cq_submit_addr_locked(struct xsk_buff_pool *pool, } } xskq_prod_submit_n(pool->cq, descs_processed); - spin_unlock_irqrestore(&pool->cq_lock, flags); + spin_unlock_irqrestore(&pool->cq_prod_lock, flags); } static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n) { - unsigned long flags; - - spin_lock_irqsave(&pool->cq_lock, flags); + spin_lock(&pool->cq_cached_prod_lock); xskq_prod_cancel_n(pool->cq, n); - spin_unlock_irqrestore(&pool->cq_lock, flags); + spin_unlock(&pool->cq_cached_prod_lock); } static void xsk_inc_num_desc(struct sk_buff *skb) @@ -605,7 +602,8 @@ static u32 xsk_get_num_desc(struct sk_buff *skb) return XSKCB(skb)->num_descs; } -static void xsk_destruct_skb(struct sk_buff *skb) +INDIRECT_CALLABLE_SCOPE +void xsk_destruct_skb(struct sk_buff *skb) { struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta; @@ -1241,7 +1239,7 @@ static bool xsk_validate_queues(struct xdp_sock *xs) return xs->fq_tmp && xs->cq_tmp; } -static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +static int xsk_bind(struct socket *sock, struct sockaddr_unsized *addr, int addr_len) { struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; struct sock *sk = sock->sk; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index aa9788f20d0db..51526034c42ac 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -12,26 +12,22 @@ void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { - unsigned long flags; - if (!xs->tx) return; - spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + spin_lock(&pool->xsk_tx_list_lock); list_add_rcu(&xs->tx_list, &pool->xsk_tx_list); - spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); + spin_unlock(&pool->xsk_tx_list_lock); } void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs) { - unsigned long flags; - if (!xs->tx) return; - spin_lock_irqsave(&pool->xsk_tx_list_lock, flags); + spin_lock(&pool->xsk_tx_list_lock); list_del_rcu(&xs->tx_list); - spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags); + spin_unlock(&pool->xsk_tx_list_lock); } void xp_destroy(struct xsk_buff_pool *pool) @@ -94,7 +90,8 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs, INIT_LIST_HEAD(&pool->xskb_list); INIT_LIST_HEAD(&pool->xsk_tx_list); spin_lock_init(&pool->xsk_tx_list_lock); - spin_lock_init(&pool->cq_lock); + spin_lock_init(&pool->cq_prod_lock); + spin_lock_init(&pool->cq_cached_prod_lock); refcount_set(&pool->users, 1); pool->fq = xs->fq_tmp; @@ -158,10 +155,6 @@ static void xp_disable_drv_zc(struct xsk_buff_pool *pool) } } -#define NETDEV_XDP_ACT_ZC (NETDEV_XDP_ACT_BASIC | \ - NETDEV_XDP_ACT_REDIRECT | \ - NETDEV_XDP_ACT_XSK_ZEROCOPY) - int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *netdev, u16 queue_id, u16 flags) { @@ -203,7 +196,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool, /* For copy-mode, we are done. */ return 0; - if ((netdev->xdp_features & NETDEV_XDP_ACT_ZC) != NETDEV_XDP_ACT_ZC) { + if ((netdev->xdp_features & NETDEV_XDP_ACT_XSK) != NETDEV_XDP_ACT_XSK) { err = -EOPNOTSUPP; goto err_unreg_pool; } diff --git a/samples/qmi/qmi_sample_client.c b/samples/qmi/qmi_sample_client.c index b27d861f354f5..d1814582319bc 100644 --- a/samples/qmi/qmi_sample_client.c +++ b/samples/qmi/qmi_sample_client.c @@ -468,7 +468,7 @@ static int qmi_sample_probe(struct platform_device *pdev) return ret; sq = dev_get_platdata(&pdev->dev); - ret = kernel_connect(sample->qmi.sock, (struct sockaddr *)sq, + ret = kernel_connect(sample->qmi.sock, (struct sockaddr_unsized *)sq, sizeof(*sq), 0); if (ret < 0) { pr_err("failed to connect to remote service port\n"); diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig index 160c07699a8b7..5c93033677e80 100644 --- a/sound/soc/codecs/Kconfig +++ b/sound/soc/codecs/Kconfig @@ -787,7 +787,6 @@ config SND_SOC_CS_AMP_LIB config SND_SOC_CS_AMP_LIB_TEST tristate "KUnit test for Cirrus Logic cs-amp-lib" if !KUNIT_ALL_TESTS depends on SND_SOC_CS_AMP_LIB && KUNIT - default KUNIT_ALL_TESTS help This builds KUnit tests for the Cirrus Logic common amplifier library. diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f5713f59ac10a..be7d8e060e104 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -7205,6 +7205,7 @@ enum { TCP_BPF_SYN_MAC = 1007, /* Copy the MAC, IP[46], and TCP header */ TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */ SK_BPF_CB_FLAGS = 1009, /* Get or set sock ops flags in socket */ + SK_BPF_BYPASS_PROT_MEM = 1010, /* Get or Set sk->sk_bypass_prot_mem */ }; enum { diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 48eb49aa03d41..048c8de1a130d 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -80,6 +80,7 @@ enum netdev_qstats_scope { enum netdev_napi_threaded { NETDEV_NAPI_THREADED_DISABLED, NETDEV_NAPI_THREADED_ENABLED, + NETDEV_NAPI_THREADED_BUSY_POLL, }; enum { diff --git a/tools/net/ynl/Makefile b/tools/net/ynl/Makefile index 211df5a93ad93..a40591e513b73 100644 --- a/tools/net/ynl/Makefile +++ b/tools/net/ynl/Makefile @@ -12,10 +12,11 @@ endif libdir ?= $(prefix)/$(libdir_relative) includedir ?= $(prefix)/include -SUBDIRS = lib generated samples +SUBDIRS = lib generated samples ynltool tests all: $(SUBDIRS) libynl.a +ynltool: | lib generated libynl.a samples: | lib generated libynl.a: | lib generated @echo -e "\tAR $@" @@ -48,5 +49,9 @@ install: libynl.a lib/*.h @echo -e "\tINSTALL pyynl" @pip install --prefix=$(DESTDIR)$(prefix) . @make -C generated install + @make -C tests install -.PHONY: all clean distclean install $(SUBDIRS) +run_tests: + @$(MAKE) -C tests run_tests + +.PHONY: all clean distclean install run_tests $(SUBDIRS) diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py index 62383c70ebb95..36d36eb7e3b80 100644 --- a/tools/net/ynl/pyynl/lib/ynl.py +++ b/tools/net/ynl/pyynl/lib/ynl.py @@ -100,12 +100,21 @@ class Netlink: 'bitfield32', 'sint', 'uint']) class NlError(Exception): - def __init__(self, nl_msg): - self.nl_msg = nl_msg - self.error = -nl_msg.error - - def __str__(self): - return f"Netlink error: {os.strerror(self.error)}\n{self.nl_msg}" + def __init__(self, nl_msg): + self.nl_msg = nl_msg + self.error = -nl_msg.error + + def __str__(self): + msg = "Netlink error: " + + extack = self.nl_msg.extack.copy() if self.nl_msg.extack else {} + if 'msg' in extack: + msg += extack['msg'] + ': ' + del extack['msg'] + msg += os.strerror(self.error) + if extack: + msg += ' ' + str(extack) + return msg class ConfigError(Exception): @@ -976,6 +985,15 @@ def _from_string(self, string, attr_spec): raw = bytes.fromhex(string) else: raw = int(string, 16) + elif attr_spec.display_hint == 'mac': + # Parse MAC address in format "00:11:22:33:44:55" or "001122334455" + if ':' in string: + mac_bytes = [int(x, 16) for x in string.split(':')] + else: + if len(string) % 2 != 0: + raise Exception(f"Invalid MAC address format: {string}") + mac_bytes = [int(string[i:i+2], 16) for i in range(0, len(string), 2)] + raw = bytes(mac_bytes) else: raise Exception(f"Display hint '{attr_spec.display_hint}' not implemented" f" when parsing '{attr_spec['name']}'") @@ -1039,15 +1057,15 @@ def poll_ntf(self, duration=None): self.check_ntf() def operation_do_attributes(self, name): - """ - For a given operation name, find and return a supported - set of attributes (as a dict). - """ - op = self.find_operation(name) - if not op: - return None - - return op['do']['request']['attributes'].copy() + """ + For a given operation name, find and return a supported + set of attributes (as a dict). + """ + op = self.find_operation(name) + if not op: + return None + + return op['do']['request']['attributes'].copy() def _encode_message(self, op, vals, flags, req_seq): nl_flags = Netlink.NLM_F_REQUEST | Netlink.NLM_F_ACK diff --git a/tools/net/ynl/samples/page-pool.c b/tools/net/ynl/samples/page-pool.c deleted file mode 100644 index e5d521320fbf3..0000000000000 --- a/tools/net/ynl/samples/page-pool.c +++ /dev/null @@ -1,149 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define _GNU_SOURCE - -#include -#include - -#include - -#include - -#include "netdev-user.h" - -struct stat { - unsigned int ifc; - - struct { - unsigned int cnt; - size_t refs, bytes; - } live[2]; - - size_t alloc_slow, alloc_fast, recycle_ring, recycle_cache; -}; - -struct stats_array { - unsigned int i, max; - struct stat *s; -}; - -static struct stat *find_ifc(struct stats_array *a, unsigned int ifindex) -{ - unsigned int i; - - for (i = 0; i < a->i; i++) { - if (a->s[i].ifc == ifindex) - return &a->s[i]; - } - - a->i++; - if (a->i == a->max) { - a->max *= 2; - a->s = reallocarray(a->s, a->max, sizeof(*a->s)); - } - a->s[i].ifc = ifindex; - return &a->s[i]; -} - -static void count(struct stat *s, unsigned int l, - struct netdev_page_pool_get_rsp *pp) -{ - s->live[l].cnt++; - if (pp->_present.inflight) - s->live[l].refs += pp->inflight; - if (pp->_present.inflight_mem) - s->live[l].bytes += pp->inflight_mem; -} - -int main(int argc, char **argv) -{ - struct netdev_page_pool_stats_get_list *pp_stats; - struct netdev_page_pool_get_list *pools; - struct stats_array a = {}; - struct ynl_error yerr; - struct ynl_sock *ys; - - ys = ynl_sock_create(&ynl_netdev_family, &yerr); - if (!ys) { - fprintf(stderr, "YNL: %s\n", yerr.msg); - return 1; - } - - a.max = 128; - a.s = calloc(a.max, sizeof(*a.s)); - if (!a.s) - goto err_close; - - pools = netdev_page_pool_get_dump(ys); - if (!pools) - goto err_free; - - ynl_dump_foreach(pools, pp) { - struct stat *s = find_ifc(&a, pp->ifindex); - - count(s, 1, pp); - if (pp->_present.detach_time) - count(s, 0, pp); - } - netdev_page_pool_get_list_free(pools); - - pp_stats = netdev_page_pool_stats_get_dump(ys); - if (!pp_stats) - goto err_free; - - ynl_dump_foreach(pp_stats, pp) { - struct stat *s = find_ifc(&a, pp->info.ifindex); - - if (pp->_present.alloc_fast) - s->alloc_fast += pp->alloc_fast; - if (pp->_present.alloc_refill) - s->alloc_fast += pp->alloc_refill; - if (pp->_present.alloc_slow) - s->alloc_slow += pp->alloc_slow; - if (pp->_present.recycle_ring) - s->recycle_ring += pp->recycle_ring; - if (pp->_present.recycle_cached) - s->recycle_cache += pp->recycle_cached; - } - netdev_page_pool_stats_get_list_free(pp_stats); - - for (unsigned int i = 0; i < a.i; i++) { - char ifname[IF_NAMESIZE]; - struct stat *s = &a.s[i]; - const char *name; - double recycle; - - if (!s->ifc) { - name = "\t"; - } else { - name = if_indextoname(s->ifc, ifname); - if (name) - printf("%8s", name); - printf("[%u]\t", s->ifc); - } - - printf("page pools: %u (zombies: %u)\n", - s->live[1].cnt, s->live[0].cnt); - printf("\t\trefs: %zu bytes: %zu (refs: %zu bytes: %zu)\n", - s->live[1].refs, s->live[1].bytes, - s->live[0].refs, s->live[0].bytes); - - /* We don't know how many pages are sitting in cache and ring - * so we will under-count the recycling rate a bit. - */ - recycle = (double)(s->recycle_ring + s->recycle_cache) / - (s->alloc_fast + s->alloc_slow) * 100; - printf("\t\trecycling: %.1lf%% (alloc: %zu:%zu recycle: %zu:%zu)\n", - recycle, s->alloc_slow, s->alloc_fast, - s->recycle_ring, s->recycle_cache); - } - - ynl_sock_destroy(ys); - return 0; - -err_free: - free(a.s); -err_close: - fprintf(stderr, "YNL: %s\n", ys->err.msg); - ynl_sock_destroy(ys); - return 2; -} diff --git a/tools/net/ynl/tests/Makefile b/tools/net/ynl/tests/Makefile new file mode 100644 index 0000000000000..38161217e249a --- /dev/null +++ b/tools/net/ynl/tests/Makefile @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for YNL tests + +TESTS := \ + test_ynl_cli.sh \ + test_ynl_ethtool.sh \ +# end of TESTS + +all: $(TESTS) + +run_tests: + @for test in $(TESTS); do \ + ./$$test; \ + done + +install: $(TESTS) + @mkdir -p $(DESTDIR)/usr/bin + @mkdir -p $(DESTDIR)/usr/share/kselftest + @cp ../../../testing/selftests/kselftest/ktap_helpers.sh $(DESTDIR)/usr/share/kselftest/ + @for test in $(TESTS); do \ + name=$$(basename $$test .sh); \ + sed -e 's|^ynl=.*|ynl="ynl"|' \ + -e 's|^ynl_ethtool=.*|ynl_ethtool="ynl-ethtool"|' \ + -e 's|KSELFTEST_KTAP_HELPERS=.*|KSELFTEST_KTAP_HELPERS="/usr/share/kselftest/ktap_helpers.sh"|' \ + $$test > $(DESTDIR)/usr/bin/$$name; \ + chmod +x $(DESTDIR)/usr/bin/$$name; \ + done + +clean: + @# Nothing to clean + +.PHONY: all install clean run_tests diff --git a/tools/net/ynl/tests/config b/tools/net/ynl/tests/config new file mode 100644 index 0000000000000..339f1309c03f3 --- /dev/null +++ b/tools/net/ynl/tests/config @@ -0,0 +1,6 @@ +CONFIG_DUMMY=m +CONFIG_INET_DIAG=y +CONFIG_IPV6=y +CONFIG_NET_NS=y +CONFIG_NETDEVSIM=m +CONFIG_VETH=m diff --git a/tools/net/ynl/tests/test_ynl_cli.sh b/tools/net/ynl/tests/test_ynl_cli.sh new file mode 100755 index 0000000000000..f40eecbb9701d --- /dev/null +++ b/tools/net/ynl/tests/test_ynl_cli.sh @@ -0,0 +1,309 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Test YNL CLI functionality + +# Load KTAP test helpers +KSELFTEST_KTAP_HELPERS="$(dirname "$(realpath "$0")")/../../../testing/selftests/kselftest/ktap_helpers.sh" +# shellcheck disable=SC1090 +source "$KSELFTEST_KTAP_HELPERS" + +# Default ynl path for direct execution, can be overridden by make install +ynl="../pyynl/cli.py" + +readonly NSIM_ID="1338" +readonly NSIM_DEV_NAME="nsim${NSIM_ID}" +readonly VETH_A="veth_a" +readonly VETH_B="veth_b" + +testns="ynl-$(mktemp -u XXXXXX)" + +# Test listing available families +cli_list_families() { + if $ynl --list-families &>/dev/null; then + ktap_test_pass "YNL CLI list families" + else + ktap_test_fail "YNL CLI list families" + fi +} + +# Test netdev family operations (dev-get, queue-get) +cli_netdev_ops() { + local dev_output + local ifindex + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + dev_output=$(ip netns exec "$testns" $ynl --family netdev \ + --do dev-get --json "{\"ifindex\": $ifindex}" 2>/dev/null) + + if ! echo "$dev_output" | grep -q "ifindex"; then + ktap_test_fail "YNL CLI netdev operations (netdev dev-get output missing ifindex)" + return + fi + + if ! ip netns exec "$testns" $ynl --family netdev \ + --dump queue-get --json "{\"ifindex\": $ifindex}" &>/dev/null; then + ktap_test_fail "YNL CLI netdev operations (failed to get netdev queue info)" + return + fi + + ktap_test_pass "YNL CLI netdev operations" +} + +# Test ethtool family operations (rings-get, linkinfo-get) +cli_ethtool_ops() { + local rings_output + local linkinfo_output + + rings_output=$(ip netns exec "$testns" $ynl --family ethtool \ + --do rings-get --json "{\"header\": {\"dev-name\": \"$NSIM_DEV_NAME\"}}" 2>/dev/null) + + if ! echo "$rings_output" | grep -q "header"; then + ktap_test_fail "YNL CLI ethtool operations (ethtool rings-get output missing header)" + return + fi + + linkinfo_output=$(ip netns exec "$testns" $ynl --family ethtool \ + --do linkinfo-get --json "{\"header\": {\"dev-name\": \"$VETH_A\"}}" 2>/dev/null) + + if ! echo "$linkinfo_output" | grep -q "header"; then + ktap_test_fail "YNL CLI ethtool operations (ethtool linkinfo-get output missing header)" + return + fi + + ktap_test_pass "YNL CLI ethtool operations" +} + +# Test rt-route family operations +cli_rt_route_ops() { + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-route"; then + ktap_test_skip "YNL CLI rt-route operations (rt-route family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + # Add route: 192.0.2.0/24 dev $dev scope link + if ! ip netns exec "$testns" $ynl --family rt-route --do newroute --create \ + --json "{\"dst\": \"192.0.2.0\", \"oif\": $ifindex, \"rtm-dst-len\": 24, \"rtm-family\": 2, \"rtm-scope\": 253, \"rtm-type\": 1, \"rtm-protocol\": 3, \"rtm-table\": 254}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-route operations (failed to add route)" + return + fi + + local route_output + route_output=$(ip netns exec "$testns" $ynl --family rt-route --dump getroute 2>/dev/null) + if echo "$route_output" | grep -q "192.0.2.0"; then + ktap_test_pass "YNL CLI rt-route operations" + else + ktap_test_fail "YNL CLI rt-route operations (failed to verify route)" + fi + + ip netns exec "$testns" $ynl --family rt-route --do delroute \ + --json "{\"dst\": \"192.0.2.0\", \"oif\": $ifindex, \"rtm-dst-len\": 24, \"rtm-family\": 2, \"rtm-scope\": 253, \"rtm-type\": 1, \"rtm-protocol\": 3, \"rtm-table\": 254}" &>/dev/null +} + +# Test rt-addr family operations +cli_rt_addr_ops() { + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-addr"; then + ktap_test_skip "YNL CLI rt-addr operations (rt-addr family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + if ! ip netns exec "$testns" $ynl --family rt-addr --do newaddr \ + --json "{\"ifa-index\": $ifindex, \"local\": \"192.0.2.100\", \"ifa-prefixlen\": 24, \"ifa-family\": 2}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-addr operations (failed to add address)" + return + fi + + local addr_output + addr_output=$(ip netns exec "$testns" $ynl --family rt-addr --dump getaddr 2>/dev/null) + if echo "$addr_output" | grep -q "192.0.2.100"; then + ktap_test_pass "YNL CLI rt-addr operations" + else + ktap_test_fail "YNL CLI rt-addr operations (failed to verify address)" + fi + + ip netns exec "$testns" $ynl --family rt-addr --do deladdr \ + --json "{\"ifa-index\": $ifindex, \"local\": \"192.0.2.100\", \"ifa-prefixlen\": 24, \"ifa-family\": 2}" &>/dev/null +} + +# Test rt-link family operations +cli_rt_link_ops() { + if ! $ynl --list-families 2>/dev/null | grep -q "rt-link"; then + ktap_test_skip "YNL CLI rt-link operations (rt-link family not available)" + return + fi + + if ! ip netns exec "$testns" $ynl --family rt-link --do newlink --create \ + --json "{\"ifname\": \"dummy0\", \"linkinfo\": {\"kind\": \"dummy\"}}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-link operations (failed to add link)" + return + fi + + local link_output + link_output=$(ip netns exec "$testns" $ynl --family rt-link --dump getlink 2>/dev/null) + if echo "$link_output" | grep -q "$NSIM_DEV_NAME" && echo "$link_output" | grep -q "dummy0"; then + ktap_test_pass "YNL CLI rt-link operations" + else + ktap_test_fail "YNL CLI rt-link operations (failed to verify link)" + fi + + ip netns exec "$testns" $ynl --family rt-link --do dellink \ + --json "{\"ifname\": \"dummy0\"}" &>/dev/null +} + +# Test rt-neigh family operations +cli_rt_neigh_ops() { + local ifindex + + if ! $ynl --list-families 2>/dev/null | grep -q "rt-neigh"; then + ktap_test_skip "YNL CLI rt-neigh operations (rt-neigh family not available)" + return + fi + + ifindex=$(ip netns exec "$testns" cat /sys/class/net/"$NSIM_DEV_NAME"/ifindex 2>/dev/null) + + # Add neighbor: 192.0.2.1 dev nsim1338 lladdr 11:22:33:44:55:66 PERMANENT + if ! ip netns exec "$testns" $ynl --family rt-neigh --do newneigh --create \ + --json "{\"ndm-ifindex\": $ifindex, \"dst\": \"192.0.2.1\", \"lladdr\": \"11:22:33:44:55:66\", \"ndm-family\": 2, \"ndm-state\": 128}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-neigh operations (failed to add neighbor)" + fi + + local neigh_output + neigh_output=$(ip netns exec "$testns" $ynl --family rt-neigh --dump getneigh 2>/dev/null) + if echo "$neigh_output" | grep -q "192.0.2.1"; then + ktap_test_pass "YNL CLI rt-neigh operations" + else + ktap_test_fail "YNL CLI rt-neigh operations (failed to verify neighbor)" + fi + + ip netns exec "$testns" $ynl --family rt-neigh --do delneigh \ + --json "{\"ndm-ifindex\": $ifindex, \"dst\": \"192.0.2.1\", \"lladdr\": \"11:22:33:44:55:66\", \"ndm-family\": 2}" &>/dev/null +} + +# Test rt-rule family operations +cli_rt_rule_ops() { + if ! $ynl --list-families 2>/dev/null | grep -q "rt-rule"; then + ktap_test_skip "YNL CLI rt-rule operations (rt-rule family not available)" + return + fi + + # Add rule: from 192.0.2.0/24 lookup 100 none + if ! ip netns exec "$testns" $ynl --family rt-rule --do newrule \ + --json "{\"family\": 2, \"src-len\": 24, \"src\": \"192.0.2.0\", \"table\": 100}" &>/dev/null; then + ktap_test_fail "YNL CLI rt-rule operations (failed to add rule)" + return + fi + + local rule_output + rule_output=$(ip netns exec "$testns" $ynl --family rt-rule --dump getrule 2>/dev/null) + if echo "$rule_output" | grep -q "192.0.2.0"; then + ktap_test_pass "YNL CLI rt-rule operations" + else + ktap_test_fail "YNL CLI rt-rule operations (failed to verify rule)" + fi + + ip netns exec "$testns" $ynl --family rt-rule --do delrule \ + --json "{\"family\": 2, \"src-len\": 24, \"src\": \"192.0.2.0\", \"table\": 100}" &>/dev/null +} + +# Test nlctrl family operations +cli_nlctrl_ops() { + local family_output + + if ! family_output=$($ynl --family nlctrl \ + --do getfamily --json "{\"family-name\": \"netdev\"}" 2>/dev/null); then + ktap_test_fail "YNL CLI nlctrl getfamily (failed to get nlctrl family info)" + return + fi + + if ! echo "$family_output" | grep -q "family-name"; then + ktap_test_fail "YNL CLI nlctrl getfamily (nlctrl getfamily output missing family-name)" + return + fi + + if ! echo "$family_output" | grep -q "family-id"; then + ktap_test_fail "YNL CLI nlctrl getfamily (nlctrl getfamily output missing family-id)" + return + fi + + ktap_test_pass "YNL CLI nlctrl getfamily" +} + +setup() { + modprobe netdevsim &> /dev/null + if ! [ -f /sys/bus/netdevsim/new_device ]; then + ktap_skip_all "netdevsim module not available" + exit "$KSFT_SKIP" + fi + + if ! ip netns add "$testns" 2>/dev/null; then + ktap_skip_all "failed to create test namespace" + exit "$KSFT_SKIP" + fi + + echo "$NSIM_ID 1" | ip netns exec "$testns" tee /sys/bus/netdevsim/new_device >/dev/null 2>&1 || { + ktap_skip_all "failed to create netdevsim device" + exit "$KSFT_SKIP" + } + + local dev + dev=$(ip netns exec "$testns" ls /sys/bus/netdevsim/devices/netdevsim$NSIM_ID/net 2>/dev/null | head -1) + if [[ -z "$dev" ]]; then + ktap_skip_all "failed to find netdevsim device" + exit "$KSFT_SKIP" + fi + + ip -netns "$testns" link set dev "$dev" name "$NSIM_DEV_NAME" 2>/dev/null || { + ktap_skip_all "failed to rename netdevsim device" + exit "$KSFT_SKIP" + } + + ip -netns "$testns" link set dev "$NSIM_DEV_NAME" up 2>/dev/null + + if ! ip -n "$testns" link add "$VETH_A" type veth peer name "$VETH_B" 2>/dev/null; then + ktap_skip_all "failed to create veth pair" + exit "$KSFT_SKIP" + fi + + ip -n "$testns" link set "$VETH_A" up 2>/dev/null + ip -n "$testns" link set "$VETH_B" up 2>/dev/null +} + +cleanup() { + if [[ -n "$testns" ]]; then + ip netns exec "$testns" bash -c "echo $NSIM_ID > /sys/bus/netdevsim/del_device" 2>/dev/null || true + ip netns del "$testns" 2>/dev/null || true + fi +} + +# Check if ynl command is available +if ! command -v $ynl &>/dev/null && [[ ! -x $ynl ]]; then + ktap_skip_all "ynl command not found: $ynl" + exit "$KSFT_SKIP" +fi + +trap cleanup EXIT + +ktap_print_header +ktap_set_plan 9 +setup + +# Run all tests +cli_list_families +cli_netdev_ops +cli_ethtool_ops +cli_rt_route_ops +cli_rt_addr_ops +cli_rt_link_ops +cli_rt_neigh_ops +cli_rt_rule_ops +cli_nlctrl_ops + +ktap_finished diff --git a/tools/net/ynl/tests/test_ynl_ethtool.sh b/tools/net/ynl/tests/test_ynl_ethtool.sh new file mode 100755 index 0000000000000..01cb9d87f7fae --- /dev/null +++ b/tools/net/ynl/tests/test_ynl_ethtool.sh @@ -0,0 +1,206 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Test YNL ethtool functionality + +# Load KTAP test helpers +KSELFTEST_KTAP_HELPERS="$(dirname "$(realpath "$0")")/../../../testing/selftests/kselftest/ktap_helpers.sh" +# shellcheck disable=SC1090 +source "$KSELFTEST_KTAP_HELPERS" + +# Default ynl-ethtool path for direct execution, can be overridden by make install +ynl_ethtool="../pyynl/ethtool.py" + +readonly NSIM_ID="1337" +readonly NSIM_DEV_NAME="nsim${NSIM_ID}" +readonly VETH_A="veth_a" +readonly VETH_B="veth_b" + +testns="ynl-ethtool-$(mktemp -u XXXXXX)" + +# Uses veth device as netdevsim doesn't support basic ethtool device info +ethtool_device_info() { + local info_output + + info_output=$(ip netns exec "$testns" $ynl_ethtool "$VETH_A" 2>/dev/null) + + if ! echo "$info_output" | grep -q "Settings for"; then + ktap_test_fail "YNL ethtool device info (device info output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool device info" +} + +ethtool_statistics() { + local stats_output + + stats_output=$(ip netns exec "$testns" $ynl_ethtool --statistics "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$stats_output" | grep -q -E "(NIC statistics|packets|bytes)"; then + ktap_test_fail "YNL ethtool statistics (statistics output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool statistics" +} + +ethtool_ring_params() { + local ring_output + + ring_output=$(ip netns exec "$testns" $ynl_ethtool --show-ring "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$ring_output" | grep -q -E "(Ring parameters|RX|TX)"; then + ktap_test_fail "YNL ethtool ring parameters (ring parameters output missing expected content)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-ring "$NSIM_DEV_NAME" rx 64 2>/dev/null; then + ktap_test_fail "YNL ethtool ring parameters (set-ring command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool ring parameters (show/set)" +} + +ethtool_coalesce_params() { + if ! ip netns exec "$testns" $ynl_ethtool --show-coalesce "$NSIM_DEV_NAME" &>/dev/null; then + ktap_test_fail "YNL ethtool coalesce parameters (failed to get coalesce parameters)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-coalesce "$NSIM_DEV_NAME" rx-usecs 50 2>/dev/null; then + ktap_test_fail "YNL ethtool coalesce parameters (set-coalesce command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool coalesce parameters (show/set)" +} + +ethtool_pause_params() { + if ! ip netns exec "$testns" $ynl_ethtool --show-pause "$NSIM_DEV_NAME" &>/dev/null; then + ktap_test_fail "YNL ethtool pause parameters (failed to get pause parameters)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-pause "$NSIM_DEV_NAME" tx 1 rx 1 2>/dev/null; then + ktap_test_fail "YNL ethtool pause parameters (set-pause command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool pause parameters (show/set)" +} + +ethtool_features_info() { + local features_output + + features_output=$(ip netns exec "$testns" $ynl_ethtool --show-features "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$features_output" | grep -q -E "(Features|offload)"; then + ktap_test_fail "YNL ethtool features info (features output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool features info (show/set)" +} + +ethtool_channels_info() { + local channels_output + + channels_output=$(ip netns exec "$testns" $ynl_ethtool --show-channels "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$channels_output" | grep -q -E "(Channel|Combined|RX|TX)"; then + ktap_test_fail "YNL ethtool channels info (channels output missing expected content)" + return + fi + + if ! ip netns exec "$testns" $ynl_ethtool --set-channels "$NSIM_DEV_NAME" combined-count 1 2>/dev/null; then + ktap_test_fail "YNL ethtool channels info (set-channels command failed unexpectedly)" + return + fi + + ktap_test_pass "YNL ethtool channels info (show/set)" +} + +ethtool_time_stamping() { + local ts_output + + ts_output=$(ip netns exec "$testns" $ynl_ethtool --show-time-stamping "$NSIM_DEV_NAME" 2>/dev/null) + + if ! echo "$ts_output" | grep -q -E "(Time stamping|timestamping|SOF_TIMESTAMPING)"; then + ktap_test_fail "YNL ethtool time stamping (time stamping output missing expected content)" + return + fi + + ktap_test_pass "YNL ethtool time stamping" +} + +setup() { + modprobe netdevsim &> /dev/null + if ! [ -f /sys/bus/netdevsim/new_device ]; then + ktap_skip_all "netdevsim module not available" + exit "$KSFT_SKIP" + fi + + if ! ip netns add "$testns" 2>/dev/null; then + ktap_skip_all "failed to create test namespace" + exit "$KSFT_SKIP" + fi + + echo "$NSIM_ID 1" | ip netns exec "$testns" tee /sys/bus/netdevsim/new_device >/dev/null 2>&1 || { + ktap_skip_all "failed to create netdevsim device" + exit "$KSFT_SKIP" + } + + local dev + dev=$(ip netns exec "$testns" ls /sys/bus/netdevsim/devices/netdevsim$NSIM_ID/net 2>/dev/null | head -1) + if [[ -z "$dev" ]]; then + ktap_skip_all "failed to find netdevsim device" + exit "$KSFT_SKIP" + fi + + ip -netns "$testns" link set dev "$dev" name "$NSIM_DEV_NAME" 2>/dev/null || { + ktap_skip_all "failed to rename netdevsim device" + exit "$KSFT_SKIP" + } + + ip -netns "$testns" link set dev "$NSIM_DEV_NAME" up 2>/dev/null + + if ! ip -n "$testns" link add "$VETH_A" type veth peer name "$VETH_B" 2>/dev/null; then + ktap_skip_all "failed to create veth pair" + exit "$KSFT_SKIP" + fi + + ip -n "$testns" link set "$VETH_A" up 2>/dev/null + ip -n "$testns" link set "$VETH_B" up 2>/dev/null +} + +cleanup() { + if [[ -n "$testns" ]]; then + ip netns exec "$testns" bash -c "echo $NSIM_ID > /sys/bus/netdevsim/del_device" 2>/dev/null || true + ip netns del "$testns" 2>/dev/null || true + fi +} + +# Check if ynl-ethtool command is available +if ! command -v $ynl_ethtool &>/dev/null && [[ ! -x $ynl_ethtool ]]; then + ktap_skip_all "ynl-ethtool command not found: $ynl_ethtool" + exit "$KSFT_SKIP" +fi + +trap cleanup EXIT + +ktap_print_header +ktap_set_plan 8 +setup + +# Run all tests +ethtool_device_info +ethtool_statistics +ethtool_ring_params +ethtool_coalesce_params +ethtool_pause_params +ethtool_features_info +ethtool_channels_info +ethtool_time_stamping + +ktap_finished diff --git a/tools/net/ynl/ynltool/.gitignore b/tools/net/ynl/ynltool/.gitignore new file mode 100644 index 0000000000000..f38848dbb0d30 --- /dev/null +++ b/tools/net/ynl/ynltool/.gitignore @@ -0,0 +1 @@ +ynltool diff --git a/tools/net/ynl/ynltool/Makefile b/tools/net/ynl/ynltool/Makefile new file mode 100644 index 0000000000000..5edaa0f932374 --- /dev/null +++ b/tools/net/ynl/ynltool/Makefile @@ -0,0 +1,55 @@ +# SPDX-License-Identifier: GPL-2.0-only + +include ../Makefile.deps + +INSTALL ?= install +prefix ?= /usr + +CC := gcc +CFLAGS := -Wall -Wextra -Werror -O2 +ifeq ("$(DEBUG)","1") + CFLAGS += -g -fsanitize=address -fsanitize=leak -static-libasan +endif +CFLAGS += -I../lib -I../generated -I../../../include/uapi/ + +SRC_VERSION := \ + $(shell make --no-print-directory -sC ../../../.. kernelversion || \ + echo "unknown") + +CFLAGS += -DSRC_VERSION='"$(SRC_VERSION)"' + +SRCS := $(wildcard *.c) +OBJS := $(patsubst %.c,$(OUTPUT)%.o,$(SRCS)) + +YNLTOOL := $(OUTPUT)ynltool + +include $(wildcard *.d) + +all: $(YNLTOOL) + +Q = @ + +$(YNLTOOL): ../libynl.a $(OBJS) + $(Q)echo -e "\tLINK $@" + $(Q)$(CC) $(CFLAGS) -o $@ $(OBJS) ../libynl.a -lmnl -lm + +%.o: %.c ../libynl.a + $(Q)echo -e "\tCC $@" + $(Q)$(COMPILE.c) -MMD -c -o $@ $< + +../libynl.a: + $(Q)$(MAKE) -C ../ + +clean: + rm -f *.o *.d *~ + +distclean: clean + rm -f $(YNLTOOL) + +bindir ?= /usr/bin + +install: $(YNLTOOL) + $(INSTALL) -m 0755 $(YNLTOOL) $(DESTDIR)$(bindir)/$(YNLTOOL) + +.PHONY: all clean distclean +.DEFAULT_GOAL=all diff --git a/tools/net/ynl/ynltool/json_writer.c b/tools/net/ynl/ynltool/json_writer.c new file mode 100644 index 0000000000000..c8685e592cd37 --- /dev/null +++ b/tools/net/ynl/ynltool/json_writer.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-Clause) +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger + */ + +#include +#include +#include +#include +#include +#include +#include + +#include "json_writer.h" + +struct json_writer { + FILE *out; + unsigned depth; + bool pretty; + char sep; +}; + +static void jsonw_indent(json_writer_t *self) +{ + unsigned i; + for (i = 0; i < self->depth; ++i) + fputs(" ", self->out); +} + +static void jsonw_eol(json_writer_t *self) +{ + if (!self->pretty) + return; + + putc('\n', self->out); + jsonw_indent(self); +} + +static void jsonw_eor(json_writer_t *self) +{ + if (self->sep != '\0') + putc(self->sep, self->out); + self->sep = ','; +} + +static void jsonw_puts(json_writer_t *self, const char *str) +{ + putc('"', self->out); + for (; *str; ++str) + switch (*str) { + case '\t': + fputs("\\t", self->out); + break; + case '\n': + fputs("\\n", self->out); + break; + case '\r': + fputs("\\r", self->out); + break; + case '\f': + fputs("\\f", self->out); + break; + case '\b': + fputs("\\b", self->out); + break; + case '\\': + fputs("\\\\", self->out); + break; + case '"': + fputs("\\\"", self->out); + break; + default: + putc(*str, self->out); + } + putc('"', self->out); +} + +json_writer_t *jsonw_new(FILE *f) +{ + json_writer_t *self = malloc(sizeof(*self)); + if (self) { + self->out = f; + self->depth = 0; + self->pretty = false; + self->sep = '\0'; + } + return self; +} + +void jsonw_destroy(json_writer_t **self_p) +{ + json_writer_t *self = *self_p; + + assert(self->depth == 0); + fputs("\n", self->out); + fflush(self->out); + free(self); + *self_p = NULL; +} + +void jsonw_pretty(json_writer_t *self, bool on) +{ + self->pretty = on; +} + +void jsonw_reset(json_writer_t *self) +{ + assert(self->depth == 0); + self->sep = '\0'; +} + +static void jsonw_begin(json_writer_t *self, int c) +{ + jsonw_eor(self); + putc(c, self->out); + ++self->depth; + self->sep = '\0'; +} + +static void jsonw_end(json_writer_t *self, int c) +{ + assert(self->depth > 0); + + --self->depth; + if (self->sep != '\0') + jsonw_eol(self); + putc(c, self->out); + self->sep = ','; +} + +void jsonw_name(json_writer_t *self, const char *name) +{ + jsonw_eor(self); + jsonw_eol(self); + self->sep = '\0'; + jsonw_puts(self, name); + putc(':', self->out); + if (self->pretty) + putc(' ', self->out); +} + +void jsonw_vprintf_enquote(json_writer_t *self, const char *fmt, va_list ap) +{ + jsonw_eor(self); + putc('"', self->out); + vfprintf(self->out, fmt, ap); + putc('"', self->out); +} + +void jsonw_printf(json_writer_t *self, const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + jsonw_eor(self); + vfprintf(self->out, fmt, ap); + va_end(ap); +} + +void jsonw_start_object(json_writer_t *self) +{ + jsonw_begin(self, '{'); +} + +void jsonw_end_object(json_writer_t *self) +{ + jsonw_end(self, '}'); +} + +void jsonw_start_array(json_writer_t *self) +{ + jsonw_begin(self, '['); +} + +void jsonw_end_array(json_writer_t *self) +{ + jsonw_end(self, ']'); +} + +void jsonw_string(json_writer_t *self, const char *value) +{ + jsonw_eor(self); + jsonw_puts(self, value); +} + +void jsonw_bool(json_writer_t *self, bool val) +{ + jsonw_printf(self, "%s", val ? "true" : "false"); +} + +void jsonw_null(json_writer_t *self) +{ + jsonw_printf(self, "null"); +} + +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num) +{ + jsonw_printf(self, fmt, num); +} + +void jsonw_float(json_writer_t *self, double num) +{ + jsonw_printf(self, "%g", num); +} + +void jsonw_hu(json_writer_t *self, unsigned short num) +{ + jsonw_printf(self, "%hu", num); +} + +void jsonw_uint(json_writer_t *self, uint64_t num) +{ + jsonw_printf(self, "%"PRIu64, num); +} + +void jsonw_lluint(json_writer_t *self, unsigned long long int num) +{ + jsonw_printf(self, "%llu", num); +} + +void jsonw_int(json_writer_t *self, int64_t num) +{ + jsonw_printf(self, "%"PRId64, num); +} + +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val) +{ + jsonw_name(self, prop); + jsonw_string(self, val); +} + +void jsonw_bool_field(json_writer_t *self, const char *prop, bool val) +{ + jsonw_name(self, prop); + jsonw_bool(self, val); +} + +void jsonw_float_field(json_writer_t *self, const char *prop, double val) +{ + jsonw_name(self, prop); + jsonw_float(self, val); +} + +void jsonw_float_field_fmt(json_writer_t *self, + const char *prop, + const char *fmt, + double val) +{ + jsonw_name(self, prop); + jsonw_float_fmt(self, fmt, val); +} + +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num) +{ + jsonw_name(self, prop); + jsonw_uint(self, num); +} + +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num) +{ + jsonw_name(self, prop); + jsonw_hu(self, num); +} + +void jsonw_lluint_field(json_writer_t *self, + const char *prop, + unsigned long long int num) +{ + jsonw_name(self, prop); + jsonw_lluint(self, num); +} + +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num) +{ + jsonw_name(self, prop); + jsonw_int(self, num); +} + +void jsonw_null_field(json_writer_t *self, const char *prop) +{ + jsonw_name(self, prop); + jsonw_null(self); +} diff --git a/tools/net/ynl/ynltool/json_writer.h b/tools/net/ynl/ynltool/json_writer.h new file mode 100644 index 0000000000000..0f1e63c88f6ac --- /dev/null +++ b/tools/net/ynl/ynltool/json_writer.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* + * Simple streaming JSON writer + * + * This takes care of the annoying bits of JSON syntax like the commas + * after elements + * + * Authors: Stephen Hemminger + */ + +#ifndef _JSON_WRITER_H_ +#define _JSON_WRITER_H_ + +#include +#include +#include +#include + +/* Opaque class structure */ +typedef struct json_writer json_writer_t; + +/* Create a new JSON stream */ +json_writer_t *jsonw_new(FILE *f); +/* End output to JSON stream */ +void jsonw_destroy(json_writer_t **self_p); + +/* Cause output to have pretty whitespace */ +void jsonw_pretty(json_writer_t *self, bool on); + +/* Reset separator to create new JSON */ +void jsonw_reset(json_writer_t *self); + +/* Add property name */ +void jsonw_name(json_writer_t *self, const char *name); + +/* Add value */ +void __attribute__((format(printf, 2, 0))) jsonw_vprintf_enquote(json_writer_t *self, + const char *fmt, + va_list ap); +void __attribute__((format(printf, 2, 3))) jsonw_printf(json_writer_t *self, + const char *fmt, ...); +void jsonw_string(json_writer_t *self, const char *value); +void jsonw_bool(json_writer_t *self, bool value); +void jsonw_float(json_writer_t *self, double number); +void jsonw_float_fmt(json_writer_t *self, const char *fmt, double num); +void jsonw_uint(json_writer_t *self, uint64_t number); +void jsonw_hu(json_writer_t *self, unsigned short number); +void jsonw_int(json_writer_t *self, int64_t number); +void jsonw_null(json_writer_t *self); +void jsonw_lluint(json_writer_t *self, unsigned long long int num); + +/* Useful Combinations of name and value */ +void jsonw_string_field(json_writer_t *self, const char *prop, const char *val); +void jsonw_bool_field(json_writer_t *self, const char *prop, bool value); +void jsonw_float_field(json_writer_t *self, const char *prop, double num); +void jsonw_uint_field(json_writer_t *self, const char *prop, uint64_t num); +void jsonw_hu_field(json_writer_t *self, const char *prop, unsigned short num); +void jsonw_int_field(json_writer_t *self, const char *prop, int64_t num); +void jsonw_null_field(json_writer_t *self, const char *prop); +void jsonw_lluint_field(json_writer_t *self, const char *prop, + unsigned long long int num); +void jsonw_float_field_fmt(json_writer_t *self, const char *prop, + const char *fmt, double val); + +/* Collections */ +void jsonw_start_object(json_writer_t *self); +void jsonw_end_object(json_writer_t *self); + +void jsonw_start_array(json_writer_t *self); +void jsonw_end_array(json_writer_t *self); + +/* Override default exception handling */ +typedef void (jsonw_err_handler_fn)(const char *); + +#endif /* _JSON_WRITER_H_ */ diff --git a/tools/net/ynl/ynltool/main.c b/tools/net/ynl/ynltool/main.c new file mode 100644 index 0000000000000..5d0f428eed0a7 --- /dev/null +++ b/tools/net/ynl/ynltool/main.c @@ -0,0 +1,242 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +/* Copyright Meta Platforms, Inc. and affiliates */ + +#include +#include +#include +#include +#include +#include +#include + +#include "main.h" + +const char *bin_name; +static int last_argc; +static char **last_argv; +static int (*last_do_help)(int argc, char **argv); +json_writer_t *json_wtr; +bool pretty_output; +bool json_output; + +static void __attribute__((noreturn)) clean_and_exit(int i) +{ + if (json_output) + jsonw_destroy(&json_wtr); + + exit(i); +} + +void usage(void) +{ + last_do_help(last_argc - 1, last_argv + 1); + + clean_and_exit(-1); +} + +static int do_help(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s [OPTIONS] OBJECT { COMMAND | help }\n" + " %s version\n" + "\n" + " OBJECT := { page-pool | qstats }\n" + " " HELP_SPEC_OPTIONS "\n" + "", + bin_name, bin_name); + + return 0; +} + +static int do_version(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "version"); + jsonw_printf(json_wtr, SRC_VERSION); + jsonw_end_object(json_wtr); + } else { + printf("%s " SRC_VERSION "\n", bin_name); + } + return 0; +} + +static const struct cmd commands[] = { + { "help", do_help }, + { "page-pool", do_page_pool }, + { "qstats", do_qstats }, + { "version", do_version }, + { 0 } +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)) +{ + unsigned int i; + + last_argc = argc; + last_argv = argv; + last_do_help = help; + + if (argc < 1 && cmds[0].func) + return cmds[0].func(argc, argv); + + for (i = 0; cmds[i].cmd; i++) { + if (is_prefix(*argv, cmds[i].cmd)) { + if (!cmds[i].func) { + p_err("command '%s' is not available", cmds[i].cmd); + return -1; + } + return cmds[i].func(argc - 1, argv + 1); + } + } + + help(argc - 1, argv + 1); + + return -1; +} + +bool is_prefix(const char *pfx, const char *str) +{ + if (!pfx) + return false; + if (strlen(str) < strlen(pfx)) + return false; + + return !memcmp(str, pfx, strlen(pfx)); +} + +/* Last argument MUST be NULL pointer */ +int detect_common_prefix(const char *arg, ...) +{ + unsigned int count = 0; + const char *ref; + char msg[256]; + va_list ap; + + snprintf(msg, sizeof(msg), "ambiguous prefix: '%s' could be '", arg); + va_start(ap, arg); + while ((ref = va_arg(ap, const char *))) { + if (!is_prefix(arg, ref)) + continue; + count++; + if (count > 1) + strncat(msg, "' or '", sizeof(msg) - strlen(msg) - 1); + strncat(msg, ref, sizeof(msg) - strlen(msg) - 1); + } + va_end(ap); + strncat(msg, "'", sizeof(msg) - strlen(msg) - 1); + + if (count >= 2) { + p_err("%s", msg); + return -1; + } + + return 0; +} + +void p_err(const char *fmt, ...) +{ + va_list ap; + + va_start(ap, fmt); + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "error"); + jsonw_vprintf_enquote(json_wtr, fmt, ap); + jsonw_end_object(json_wtr); + } else { + fprintf(stderr, "Error: "); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + } + va_end(ap); +} + +void p_info(const char *fmt, ...) +{ + va_list ap; + + if (json_output) + return; + + va_start(ap, fmt); + vfprintf(stderr, fmt, ap); + fprintf(stderr, "\n"); + va_end(ap); +} + +int main(int argc, char **argv) +{ + static const struct option options[] = { + { "json", no_argument, NULL, 'j' }, + { "help", no_argument, NULL, 'h' }, + { "pretty", no_argument, NULL, 'p' }, + { "version", no_argument, NULL, 'V' }, + { 0 } + }; + bool version_requested = false; + int opt, ret; + + setlinebuf(stdout); + + last_do_help = do_help; + pretty_output = false; + json_output = false; + bin_name = "ynltool"; + + opterr = 0; + while ((opt = getopt_long(argc, argv, "Vhjp", + options, NULL)) >= 0) { + switch (opt) { + case 'V': + version_requested = true; + break; + case 'h': + return do_help(argc, argv); + case 'p': + pretty_output = true; + /* fall through */ + case 'j': + if (!json_output) { + json_wtr = jsonw_new(stdout); + if (!json_wtr) { + p_err("failed to create JSON writer"); + return -1; + } + json_output = true; + } + jsonw_pretty(json_wtr, pretty_output); + break; + default: + p_err("unrecognized option '%s'", argv[optind - 1]); + if (json_output) + clean_and_exit(-1); + else + usage(); + } + } + + argc -= optind; + argv += optind; + if (argc < 0) + usage(); + + if (version_requested) + ret = do_version(argc, argv); + else + ret = cmd_select(commands, argc, argv, do_help); + + if (json_output) + jsonw_destroy(&json_wtr); + + return ret; +} diff --git a/tools/net/ynl/ynltool/main.h b/tools/net/ynl/ynltool/main.h new file mode 100644 index 0000000000000..c7039f9ac55a6 --- /dev/null +++ b/tools/net/ynl/ynltool/main.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */ +/* Copyright (C) 2017-2018 Netronome Systems, Inc. */ +/* Copyright Meta Platforms, Inc. and affiliates */ + +#ifndef __YNLTOOL_H +#define __YNLTOOL_H + +#ifndef _GNU_SOURCE +#define _GNU_SOURCE +#endif +#include +#include +#include +#include +#include + +#include "json_writer.h" + +#define NEXT_ARG() ({ argc--; argv++; if (argc < 0) usage(); }) +#define NEXT_ARGP() ({ (*argc)--; (*argv)++; if (*argc < 0) usage(); }) +#define BAD_ARG() ({ p_err("what is '%s'?", *argv); -1; }) +#define GET_ARG() ({ argc--; *argv++; }) +#define REQ_ARGS(cnt) \ + ({ \ + int _cnt = (cnt); \ + bool _res; \ + \ + if (argc < _cnt) { \ + p_err("'%s' needs at least %d arguments, %d found", \ + argv[-1], _cnt, argc); \ + _res = false; \ + } else { \ + _res = true; \ + } \ + _res; \ + }) + +#define HELP_SPEC_OPTIONS \ + "OPTIONS := { {-j|--json} [{-p|--pretty}] }" + +extern const char *bin_name; + +extern json_writer_t *json_wtr; +extern bool json_output; +extern bool pretty_output; + +void __attribute__((format(printf, 1, 2))) p_err(const char *fmt, ...); +void __attribute__((format(printf, 1, 2))) p_info(const char *fmt, ...); + +bool is_prefix(const char *pfx, const char *str); +int detect_common_prefix(const char *arg, ...); +void usage(void) __attribute__((noreturn)); + +struct cmd { + const char *cmd; + int (*func)(int argc, char **argv); +}; + +int cmd_select(const struct cmd *cmds, int argc, char **argv, + int (*help)(int argc, char **argv)); + +/* subcommands */ +int do_page_pool(int argc, char **argv); +int do_qstats(int argc, char **argv); + +#endif /* __YNLTOOL_H */ diff --git a/tools/net/ynl/ynltool/page-pool.c b/tools/net/ynl/ynltool/page-pool.c new file mode 100644 index 0000000000000..4b24492abab78 --- /dev/null +++ b/tools/net/ynl/ynltool/page-pool.c @@ -0,0 +1,461 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +#include +#include +#include +#include +#include + +#include +#include "netdev-user.h" + +#include "main.h" + +struct pp_stat { + unsigned int ifc; + + struct { + unsigned int cnt; + size_t refs, bytes; + } live[2]; + + size_t alloc_slow, alloc_fast, recycle_ring, recycle_cache; +}; + +struct pp_stats_array { + unsigned int i, max; + struct pp_stat *s; +}; + +static struct pp_stat *find_ifc(struct pp_stats_array *a, unsigned int ifindex) +{ + unsigned int i; + + for (i = 0; i < a->i; i++) { + if (a->s[i].ifc == ifindex) + return &a->s[i]; + } + + a->i++; + if (a->i == a->max) { + a->max *= 2; + a->s = reallocarray(a->s, a->max, sizeof(*a->s)); + } + a->s[i].ifc = ifindex; + return &a->s[i]; +} + +static void count_pool(struct pp_stat *s, unsigned int l, + struct netdev_page_pool_get_rsp *pp) +{ + s->live[l].cnt++; + if (pp->_present.inflight) + s->live[l].refs += pp->inflight; + if (pp->_present.inflight_mem) + s->live[l].bytes += pp->inflight_mem; +} + +/* We don't know how many pages are sitting in cache and ring + * so we will under-count the recycling rate a bit. + */ +static void print_json_recycling_stats(struct pp_stat *s) +{ + double recycle; + + if (s->alloc_fast + s->alloc_slow) { + recycle = (double)(s->recycle_ring + s->recycle_cache) / + (s->alloc_fast + s->alloc_slow) * 100; + jsonw_float_field(json_wtr, "recycling_pct", recycle); + } + + jsonw_name(json_wtr, "alloc"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "slow", s->alloc_slow); + jsonw_uint_field(json_wtr, "fast", s->alloc_fast); + jsonw_end_object(json_wtr); + + jsonw_name(json_wtr, "recycle"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "ring", s->recycle_ring); + jsonw_uint_field(json_wtr, "cache", s->recycle_cache); + jsonw_end_object(json_wtr); +} + +static void print_plain_recycling_stats(struct pp_stat *s) +{ + double recycle; + + if (s->alloc_fast + s->alloc_slow) { + recycle = (double)(s->recycle_ring + s->recycle_cache) / + (s->alloc_fast + s->alloc_slow) * 100; + printf("recycling: %.1lf%% (alloc: %zu:%zu recycle: %zu:%zu)", + recycle, s->alloc_slow, s->alloc_fast, + s->recycle_ring, s->recycle_cache); + } +} + +static void print_json_stats(struct pp_stats_array *a) +{ + jsonw_start_array(json_wtr); + + for (unsigned int i = 0; i < a->i; i++) { + char ifname[IF_NAMESIZE]; + struct pp_stat *s = &a->s[i]; + const char *name; + + jsonw_start_object(json_wtr); + + if (!s->ifc) { + jsonw_string_field(json_wtr, "ifname", ""); + jsonw_uint_field(json_wtr, "ifindex", 0); + } else { + name = if_indextoname(s->ifc, ifname); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", s->ifc); + } + + jsonw_uint_field(json_wtr, "page_pools", s->live[1].cnt); + jsonw_uint_field(json_wtr, "zombies", s->live[0].cnt); + + jsonw_name(json_wtr, "live"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "refs", s->live[1].refs); + jsonw_uint_field(json_wtr, "bytes", s->live[1].bytes); + jsonw_end_object(json_wtr); + + jsonw_name(json_wtr, "zombie"); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "refs", s->live[0].refs); + jsonw_uint_field(json_wtr, "bytes", s->live[0].bytes); + jsonw_end_object(json_wtr); + + if (s->alloc_fast || s->alloc_slow) + print_json_recycling_stats(s); + + jsonw_end_object(json_wtr); + } + + jsonw_end_array(json_wtr); +} + +static void print_plain_stats(struct pp_stats_array *a) +{ + for (unsigned int i = 0; i < a->i; i++) { + char ifname[IF_NAMESIZE]; + struct pp_stat *s = &a->s[i]; + const char *name; + + if (!s->ifc) { + printf("\t"); + } else { + name = if_indextoname(s->ifc, ifname); + if (name) + printf("%8s", name); + printf("[%u]\t", s->ifc); + } + + printf("page pools: %u (zombies: %u)\n", + s->live[1].cnt, s->live[0].cnt); + printf("\t\trefs: %zu bytes: %zu (refs: %zu bytes: %zu)\n", + s->live[1].refs, s->live[1].bytes, + s->live[0].refs, s->live[0].bytes); + + if (s->alloc_fast || s->alloc_slow) { + printf("\t\t"); + print_plain_recycling_stats(s); + printf("\n"); + } + } +} + +static bool +find_pool_stat_in_list(struct netdev_page_pool_stats_get_list *pp_stats, + __u64 pool_id, struct pp_stat *pstat) +{ + ynl_dump_foreach(pp_stats, pp) { + if (!pp->_present.info || !pp->info._present.id) + continue; + if (pp->info.id != pool_id) + continue; + + memset(pstat, 0, sizeof(*pstat)); + if (pp->_present.alloc_fast) + pstat->alloc_fast = pp->alloc_fast; + if (pp->_present.alloc_refill) + pstat->alloc_fast += pp->alloc_refill; + if (pp->_present.alloc_slow) + pstat->alloc_slow = pp->alloc_slow; + if (pp->_present.recycle_ring) + pstat->recycle_ring = pp->recycle_ring; + if (pp->_present.recycle_cached) + pstat->recycle_cache = pp->recycle_cached; + return true; + } + return false; +} + +static void +print_json_pool_list(struct netdev_page_pool_get_list *pools, + struct netdev_page_pool_stats_get_list *pp_stats, + bool zombies_only) +{ + jsonw_start_array(json_wtr); + + ynl_dump_foreach(pools, pp) { + char ifname[IF_NAMESIZE]; + struct pp_stat pstat; + const char *name; + + if (zombies_only && !pp->_present.detach_time) + continue; + + jsonw_start_object(json_wtr); + + jsonw_uint_field(json_wtr, "id", pp->id); + + if (pp->_present.ifindex) { + name = if_indextoname(pp->ifindex, ifname); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", pp->ifindex); + } + + if (pp->_present.napi_id) + jsonw_uint_field(json_wtr, "napi_id", pp->napi_id); + + if (pp->_present.inflight) + jsonw_uint_field(json_wtr, "refs", pp->inflight); + + if (pp->_present.inflight_mem) + jsonw_uint_field(json_wtr, "bytes", pp->inflight_mem); + + if (pp->_present.detach_time) + jsonw_uint_field(json_wtr, "detach_time", pp->detach_time); + + if (pp->_present.dmabuf) + jsonw_uint_field(json_wtr, "dmabuf", pp->dmabuf); + + if (find_pool_stat_in_list(pp_stats, pp->id, &pstat) && + (pstat.alloc_fast || pstat.alloc_slow)) + print_json_recycling_stats(&pstat); + + jsonw_end_object(json_wtr); + } + + jsonw_end_array(json_wtr); +} + +static void +print_plain_pool_list(struct netdev_page_pool_get_list *pools, + struct netdev_page_pool_stats_get_list *pp_stats, + bool zombies_only) +{ + ynl_dump_foreach(pools, pp) { + char ifname[IF_NAMESIZE]; + struct pp_stat pstat; + const char *name; + + if (zombies_only && !pp->_present.detach_time) + continue; + + printf("pool id: %llu", pp->id); + + if (pp->_present.ifindex) { + name = if_indextoname(pp->ifindex, ifname); + if (name) + printf(" dev: %s", name); + printf("[%u]", pp->ifindex); + } + + if (pp->_present.napi_id) + printf(" napi: %llu", pp->napi_id); + + printf("\n"); + + if (pp->_present.inflight || pp->_present.inflight_mem) { + printf(" inflight:"); + if (pp->_present.inflight) + printf(" %llu pages", pp->inflight); + if (pp->_present.inflight_mem) + printf(" %llu bytes", pp->inflight_mem); + printf("\n"); + } + + if (pp->_present.detach_time) + printf(" detached: %llu\n", pp->detach_time); + + if (pp->_present.dmabuf) + printf(" dmabuf: %u\n", pp->dmabuf); + + if (find_pool_stat_in_list(pp_stats, pp->id, &pstat) && + (pstat.alloc_fast || pstat.alloc_slow)) { + printf(" "); + print_plain_recycling_stats(&pstat); + printf("\n"); + } + } +} + +static void aggregate_device_stats(struct pp_stats_array *a, + struct netdev_page_pool_get_list *pools, + struct netdev_page_pool_stats_get_list *pp_stats) +{ + ynl_dump_foreach(pools, pp) { + struct pp_stat *s = find_ifc(a, pp->ifindex); + + count_pool(s, 1, pp); + if (pp->_present.detach_time) + count_pool(s, 0, pp); + } + + ynl_dump_foreach(pp_stats, pp) { + struct pp_stat *s = find_ifc(a, pp->info.ifindex); + + if (pp->_present.alloc_fast) + s->alloc_fast += pp->alloc_fast; + if (pp->_present.alloc_refill) + s->alloc_fast += pp->alloc_refill; + if (pp->_present.alloc_slow) + s->alloc_slow += pp->alloc_slow; + if (pp->_present.recycle_ring) + s->recycle_ring += pp->recycle_ring; + if (pp->_present.recycle_cached) + s->recycle_cache += pp->recycle_cached; + } +} + +static int do_stats(int argc, char **argv) +{ + struct netdev_page_pool_stats_get_list *pp_stats; + struct netdev_page_pool_get_list *pools; + enum { + GROUP_BY_DEVICE, + GROUP_BY_POOL, + } group_by = GROUP_BY_DEVICE; + bool zombies_only = false; + struct pp_stats_array a = {}; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret = 0; + + /* Parse options */ + while (argc > 0) { + if (is_prefix(*argv, "group-by")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + return -1; + + if (is_prefix(*argv, "device")) { + group_by = GROUP_BY_DEVICE; + } else if (is_prefix(*argv, "pp") || + is_prefix(*argv, "page-pool") || + is_prefix(*argv, "none")) { + group_by = GROUP_BY_POOL; + } else { + p_err("invalid group-by value '%s'", *argv); + return -1; + } + NEXT_ARG(); + } else if (is_prefix(*argv, "zombies")) { + zombies_only = true; + group_by = GROUP_BY_POOL; + NEXT_ARG(); + } else { + p_err("unknown option '%s'", *argv); + return -1; + } + } + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + p_err("YNL: %s", yerr.msg); + return -1; + } + + pools = netdev_page_pool_get_dump(ys); + if (!pools) { + p_err("failed to get page pools: %s", ys->err.msg); + ret = -1; + goto exit_close; + } + + pp_stats = netdev_page_pool_stats_get_dump(ys); + if (!pp_stats) { + p_err("failed to get page pool stats: %s", ys->err.msg); + ret = -1; + goto exit_free_pp_list; + } + + /* If grouping by pool, print individual pools */ + if (group_by == GROUP_BY_POOL) { + if (json_output) + print_json_pool_list(pools, pp_stats, zombies_only); + else + print_plain_pool_list(pools, pp_stats, zombies_only); + } else { + /* Aggregated stats mode (group-by device) */ + a.max = 64; + a.s = calloc(a.max, sizeof(*a.s)); + if (!a.s) { + p_err("failed to allocate stats array"); + ret = -1; + goto exit_free_stats_list; + } + + aggregate_device_stats(&a, pools, pp_stats); + + if (json_output) + print_json_stats(&a); + else + print_plain_stats(&a); + + free(a.s); + } + +exit_free_stats_list: + netdev_page_pool_stats_get_list_free(pp_stats); +exit_free_pp_list: + netdev_page_pool_get_list_free(pools); +exit_close: + ynl_sock_destroy(ys); + return ret; +} + +static int do_help(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s page-pool { COMMAND | help }\n" + " %s page-pool stats [ OPTIONS ]\n" + "\n" + " OPTIONS := { group-by { device | page-pool | none } | zombies }\n" + "\n" + " stats - Display page pool statistics\n" + " stats group-by device - Group statistics by network device (default)\n" + " stats group-by page-pool | pp | none\n" + " - Show individual page pool details (no grouping)\n" + " stats zombies - Show only zombie page pools (detached but with\n" + " pages in flight). Implies group-by page-pool.\n" + "", + bin_name, bin_name); + + return 0; +} + +static const struct cmd page_pool_cmds[] = { + { "help", do_help }, + { "stats", do_stats }, + { 0 } +}; + +int do_page_pool(int argc, char **argv) +{ + return cmd_select(page_pool_cmds, argc, argv, do_help); +} diff --git a/tools/net/ynl/ynltool/qstats.c b/tools/net/ynl/ynltool/qstats.c new file mode 100644 index 0000000000000..31fb45709ffab --- /dev/null +++ b/tools/net/ynl/ynltool/qstats.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) + +#include +#include +#include +#include +#include +#include + +#include +#include "netdev-user.h" + +#include "main.h" + +static enum netdev_qstats_scope scope; /* default - device */ + +struct queue_balance { + unsigned int ifindex; + enum netdev_queue_type type; + unsigned int queue_count; + __u64 *rx_packets; + __u64 *rx_bytes; + __u64 *tx_packets; + __u64 *tx_bytes; +}; + +static void print_json_qstats(struct netdev_qstats_get_list *qstats) +{ + jsonw_start_array(json_wtr); + + ynl_dump_foreach(qstats, qs) { + char ifname[IF_NAMESIZE]; + const char *name; + + jsonw_start_object(json_wtr); + + name = if_indextoname(qs->ifindex, ifname); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", qs->ifindex); + + if (qs->_present.queue_type) + jsonw_string_field(json_wtr, "queue-type", + netdev_queue_type_str(qs->queue_type)); + if (qs->_present.queue_id) + jsonw_uint_field(json_wtr, "queue-id", qs->queue_id); + + if (qs->_present.rx_packets || qs->_present.rx_bytes || + qs->_present.rx_alloc_fail || qs->_present.rx_hw_drops || + qs->_present.rx_csum_complete || qs->_present.rx_hw_gro_packets) { + jsonw_name(json_wtr, "rx"); + jsonw_start_object(json_wtr); + if (qs->_present.rx_packets) + jsonw_uint_field(json_wtr, "packets", qs->rx_packets); + if (qs->_present.rx_bytes) + jsonw_uint_field(json_wtr, "bytes", qs->rx_bytes); + if (qs->_present.rx_alloc_fail) + jsonw_uint_field(json_wtr, "alloc-fail", qs->rx_alloc_fail); + if (qs->_present.rx_hw_drops) + jsonw_uint_field(json_wtr, "hw-drops", qs->rx_hw_drops); + if (qs->_present.rx_hw_drop_overruns) + jsonw_uint_field(json_wtr, "hw-drop-overruns", qs->rx_hw_drop_overruns); + if (qs->_present.rx_hw_drop_ratelimits) + jsonw_uint_field(json_wtr, "hw-drop-ratelimits", qs->rx_hw_drop_ratelimits); + if (qs->_present.rx_csum_complete) + jsonw_uint_field(json_wtr, "csum-complete", qs->rx_csum_complete); + if (qs->_present.rx_csum_unnecessary) + jsonw_uint_field(json_wtr, "csum-unnecessary", qs->rx_csum_unnecessary); + if (qs->_present.rx_csum_none) + jsonw_uint_field(json_wtr, "csum-none", qs->rx_csum_none); + if (qs->_present.rx_csum_bad) + jsonw_uint_field(json_wtr, "csum-bad", qs->rx_csum_bad); + if (qs->_present.rx_hw_gro_packets) + jsonw_uint_field(json_wtr, "hw-gro-packets", qs->rx_hw_gro_packets); + if (qs->_present.rx_hw_gro_bytes) + jsonw_uint_field(json_wtr, "hw-gro-bytes", qs->rx_hw_gro_bytes); + if (qs->_present.rx_hw_gro_wire_packets) + jsonw_uint_field(json_wtr, "hw-gro-wire-packets", qs->rx_hw_gro_wire_packets); + if (qs->_present.rx_hw_gro_wire_bytes) + jsonw_uint_field(json_wtr, "hw-gro-wire-bytes", qs->rx_hw_gro_wire_bytes); + jsonw_end_object(json_wtr); + } + + if (qs->_present.tx_packets || qs->_present.tx_bytes || + qs->_present.tx_hw_drops || qs->_present.tx_csum_none || + qs->_present.tx_hw_gso_packets) { + jsonw_name(json_wtr, "tx"); + jsonw_start_object(json_wtr); + if (qs->_present.tx_packets) + jsonw_uint_field(json_wtr, "packets", qs->tx_packets); + if (qs->_present.tx_bytes) + jsonw_uint_field(json_wtr, "bytes", qs->tx_bytes); + if (qs->_present.tx_hw_drops) + jsonw_uint_field(json_wtr, "hw-drops", qs->tx_hw_drops); + if (qs->_present.tx_hw_drop_errors) + jsonw_uint_field(json_wtr, "hw-drop-errors", qs->tx_hw_drop_errors); + if (qs->_present.tx_hw_drop_ratelimits) + jsonw_uint_field(json_wtr, "hw-drop-ratelimits", qs->tx_hw_drop_ratelimits); + if (qs->_present.tx_csum_none) + jsonw_uint_field(json_wtr, "csum-none", qs->tx_csum_none); + if (qs->_present.tx_needs_csum) + jsonw_uint_field(json_wtr, "needs-csum", qs->tx_needs_csum); + if (qs->_present.tx_hw_gso_packets) + jsonw_uint_field(json_wtr, "hw-gso-packets", qs->tx_hw_gso_packets); + if (qs->_present.tx_hw_gso_bytes) + jsonw_uint_field(json_wtr, "hw-gso-bytes", qs->tx_hw_gso_bytes); + if (qs->_present.tx_hw_gso_wire_packets) + jsonw_uint_field(json_wtr, "hw-gso-wire-packets", qs->tx_hw_gso_wire_packets); + if (qs->_present.tx_hw_gso_wire_bytes) + jsonw_uint_field(json_wtr, "hw-gso-wire-bytes", qs->tx_hw_gso_wire_bytes); + if (qs->_present.tx_stop) + jsonw_uint_field(json_wtr, "stop", qs->tx_stop); + if (qs->_present.tx_wake) + jsonw_uint_field(json_wtr, "wake", qs->tx_wake); + jsonw_end_object(json_wtr); + } + + jsonw_end_object(json_wtr); + } + + jsonw_end_array(json_wtr); +} + +static void print_one(bool present, const char *name, unsigned long long val, + int *line) +{ + if (!present) + return; + + if (!*line) { + printf(" "); + ++(*line); + } + + /* Don't waste space on tx- and rx- prefix, its implied by queue type */ + if (scope == NETDEV_QSTATS_SCOPE_QUEUE && + (name[0] == 'r' || name[0] == 't') && + name[1] == 'x' && name[2] == '-') + name += 3; + + printf(" %15s: %15llu", name, val); + + if (++(*line) == 3) { + printf("\n"); + *line = 0; + } +} + +static void print_plain_qstats(struct netdev_qstats_get_list *qstats) +{ + ynl_dump_foreach(qstats, qs) { + char ifname[IF_NAMESIZE]; + const char *name; + int n; + + name = if_indextoname(qs->ifindex, ifname); + if (name) + printf("%s", name); + else + printf("ifindex:%u", qs->ifindex); + + if (qs->_present.queue_type && qs->_present.queue_id) + printf("\t%s-%-3u", + netdev_queue_type_str(qs->queue_type), + qs->queue_id); + else + printf("\t "); + + n = 1; + + /* Basic counters */ + print_one(qs->_present.rx_packets, "rx-packets", qs->rx_packets, &n); + print_one(qs->_present.rx_bytes, "rx-bytes", qs->rx_bytes, &n); + print_one(qs->_present.tx_packets, "tx-packets", qs->tx_packets, &n); + print_one(qs->_present.tx_bytes, "tx-bytes", qs->tx_bytes, &n); + + /* RX error/drop counters */ + print_one(qs->_present.rx_alloc_fail, "rx-alloc-fail", + qs->rx_alloc_fail, &n); + print_one(qs->_present.rx_hw_drops, "rx-hw-drops", + qs->rx_hw_drops, &n); + print_one(qs->_present.rx_hw_drop_overruns, "rx-hw-drop-overruns", + qs->rx_hw_drop_overruns, &n); + print_one(qs->_present.rx_hw_drop_ratelimits, "rx-hw-drop-ratelimits", + qs->rx_hw_drop_ratelimits, &n); + + /* RX checksum counters */ + print_one(qs->_present.rx_csum_complete, "rx-csum-complete", + qs->rx_csum_complete, &n); + print_one(qs->_present.rx_csum_unnecessary, "rx-csum-unnecessary", + qs->rx_csum_unnecessary, &n); + print_one(qs->_present.rx_csum_none, "rx-csum-none", + qs->rx_csum_none, &n); + print_one(qs->_present.rx_csum_bad, "rx-csum-bad", + qs->rx_csum_bad, &n); + + /* RX GRO counters */ + print_one(qs->_present.rx_hw_gro_packets, "rx-hw-gro-packets", + qs->rx_hw_gro_packets, &n); + print_one(qs->_present.rx_hw_gro_bytes, "rx-hw-gro-bytes", + qs->rx_hw_gro_bytes, &n); + print_one(qs->_present.rx_hw_gro_wire_packets, "rx-hw-gro-wire-packets", + qs->rx_hw_gro_wire_packets, &n); + print_one(qs->_present.rx_hw_gro_wire_bytes, "rx-hw-gro-wire-bytes", + qs->rx_hw_gro_wire_bytes, &n); + + /* TX error/drop counters */ + print_one(qs->_present.tx_hw_drops, "tx-hw-drops", + qs->tx_hw_drops, &n); + print_one(qs->_present.tx_hw_drop_errors, "tx-hw-drop-errors", + qs->tx_hw_drop_errors, &n); + print_one(qs->_present.tx_hw_drop_ratelimits, "tx-hw-drop-ratelimits", + qs->tx_hw_drop_ratelimits, &n); + + /* TX checksum counters */ + print_one(qs->_present.tx_csum_none, "tx-csum-none", + qs->tx_csum_none, &n); + print_one(qs->_present.tx_needs_csum, "tx-needs-csum", + qs->tx_needs_csum, &n); + + /* TX GSO counters */ + print_one(qs->_present.tx_hw_gso_packets, "tx-hw-gso-packets", + qs->tx_hw_gso_packets, &n); + print_one(qs->_present.tx_hw_gso_bytes, "tx-hw-gso-bytes", + qs->tx_hw_gso_bytes, &n); + print_one(qs->_present.tx_hw_gso_wire_packets, "tx-hw-gso-wire-packets", + qs->tx_hw_gso_wire_packets, &n); + print_one(qs->_present.tx_hw_gso_wire_bytes, "tx-hw-gso-wire-bytes", + qs->tx_hw_gso_wire_bytes, &n); + + /* TX queue control */ + print_one(qs->_present.tx_stop, "tx-stop", qs->tx_stop, &n); + print_one(qs->_present.tx_wake, "tx-wake", qs->tx_wake, &n); + + if (n) + printf("\n"); + } +} + +static int do_show(int argc, char **argv) +{ + struct netdev_qstats_get_list *qstats; + struct netdev_qstats_get_req *req; + struct ynl_error yerr; + struct ynl_sock *ys; + int ret = 0; + + /* Parse options */ + while (argc > 0) { + if (is_prefix(*argv, "scope") || is_prefix(*argv, "group-by")) { + NEXT_ARG(); + + if (!REQ_ARGS(1)) + return -1; + + if (is_prefix(*argv, "queue")) { + scope = NETDEV_QSTATS_SCOPE_QUEUE; + } else if (is_prefix(*argv, "device")) { + scope = 0; + } else { + p_err("invalid scope value '%s'", *argv); + return -1; + } + NEXT_ARG(); + } else { + p_err("unknown option '%s'", *argv); + return -1; + } + } + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + p_err("YNL: %s", yerr.msg); + return -1; + } + + req = netdev_qstats_get_req_alloc(); + if (!req) { + p_err("failed to allocate qstats request"); + ret = -1; + goto exit_close; + } + + if (scope) + netdev_qstats_get_req_set_scope(req, scope); + + qstats = netdev_qstats_get_dump(ys, req); + netdev_qstats_get_req_free(req); + if (!qstats) { + p_err("failed to get queue stats: %s", ys->err.msg); + ret = -1; + goto exit_close; + } + + /* Print the stats as returned by the kernel */ + if (json_output) + print_json_qstats(qstats); + else + print_plain_qstats(qstats); + + netdev_qstats_get_list_free(qstats); +exit_close: + ynl_sock_destroy(ys); + return ret; +} + +static void compute_stats(__u64 *values, unsigned int count, + double *mean, double *stddev, __u64 *min, __u64 *max) +{ + double sum = 0.0, variance = 0.0; + unsigned int i; + + *min = ~0ULL; + *max = 0; + + if (count == 0) { + *mean = 0; + *stddev = 0; + *min = 0; + return; + } + + for (i = 0; i < count; i++) { + sum += values[i]; + if (values[i] < *min) + *min = values[i]; + if (values[i] > *max) + *max = values[i]; + } + + *mean = sum / count; + + if (count > 1) { + for (i = 0; i < count; i++) { + double diff = values[i] - *mean; + + variance += diff * diff; + } + *stddev = sqrt(variance / (count - 1)); + } else { + *stddev = 0; + } +} + +static void print_balance_stats(const char *name, enum netdev_queue_type type, + __u64 *values, unsigned int count) +{ + double mean, stddev, cv, ns; + __u64 min, max; + + if ((name[0] == 'r' && type != NETDEV_QUEUE_TYPE_RX) || + (name[0] == 't' && type != NETDEV_QUEUE_TYPE_TX)) + return; + + compute_stats(values, count, &mean, &stddev, &min, &max); + + cv = mean > 0 ? (stddev / mean) * 100.0 : 0.0; + ns = min + max > 0 ? (double)2 * (max - min) / (max + min) * 100 : 0.0; + + printf(" %-12s: cv=%.1f%% ns=%.1f%% stddev=%.0f\n", + name, cv, ns, stddev); + printf(" %-12s min=%llu max=%llu mean=%.0f\n", + "", min, max, mean); +} + +static void +print_balance_stats_json(const char *name, enum netdev_queue_type type, + __u64 *values, unsigned int count) +{ + double mean, stddev, cv, ns; + __u64 min, max; + + if ((name[0] == 'r' && type != NETDEV_QUEUE_TYPE_RX) || + (name[0] == 't' && type != NETDEV_QUEUE_TYPE_TX)) + return; + + compute_stats(values, count, &mean, &stddev, &min, &max); + + cv = mean > 0 ? (stddev / mean) * 100.0 : 0.0; + ns = min + max > 0 ? (double)2 * (max - min) / (max + min) * 100 : 0.0; + + jsonw_name(json_wtr, name); + jsonw_start_object(json_wtr); + jsonw_uint_field(json_wtr, "queue-count", count); + jsonw_uint_field(json_wtr, "min", min); + jsonw_uint_field(json_wtr, "max", max); + jsonw_float_field(json_wtr, "mean", mean); + jsonw_float_field(json_wtr, "stddev", stddev); + jsonw_float_field(json_wtr, "coefficient-of-variation", cv); + jsonw_float_field(json_wtr, "normalized-spread", ns); + jsonw_end_object(json_wtr); +} + +static int cmp_ifindex_type(const void *a, const void *b) +{ + const struct netdev_qstats_get_rsp *qa = a; + const struct netdev_qstats_get_rsp *qb = b; + + if (qa->ifindex != qb->ifindex) + return qa->ifindex - qb->ifindex; + if (qa->queue_type != qb->queue_type) + return qa->queue_type - qb->queue_type; + return qa->queue_id - qb->queue_id; +} + +static int do_balance(int argc, char **argv __attribute__((unused))) +{ + struct netdev_qstats_get_list *qstats; + struct netdev_qstats_get_req *req; + struct netdev_qstats_get_rsp **sorted; + struct ynl_error yerr; + struct ynl_sock *ys; + unsigned int count = 0; + unsigned int i, j; + int ret = 0; + + if (argc > 0) { + p_err("balance command takes no arguments"); + return -1; + } + + ys = ynl_sock_create(&ynl_netdev_family, &yerr); + if (!ys) { + p_err("YNL: %s", yerr.msg); + return -1; + } + + req = netdev_qstats_get_req_alloc(); + if (!req) { + p_err("failed to allocate qstats request"); + ret = -1; + goto exit_close; + } + + /* Always use queue scope for balance analysis */ + netdev_qstats_get_req_set_scope(req, NETDEV_QSTATS_SCOPE_QUEUE); + + qstats = netdev_qstats_get_dump(ys, req); + netdev_qstats_get_req_free(req); + if (!qstats) { + p_err("failed to get queue stats: %s", ys->err.msg); + ret = -1; + goto exit_close; + } + + /* Count and sort queues */ + ynl_dump_foreach(qstats, qs) + count++; + + if (count == 0) { + if (json_output) + jsonw_start_array(json_wtr); + else + printf("No queue statistics available\n"); + goto exit_free_qstats; + } + + sorted = calloc(count, sizeof(*sorted)); + if (!sorted) { + p_err("failed to allocate sorted array"); + ret = -1; + goto exit_free_qstats; + } + + i = 0; + ynl_dump_foreach(qstats, qs) + sorted[i++] = qs; + + qsort(sorted, count, sizeof(*sorted), cmp_ifindex_type); + + if (json_output) + jsonw_start_array(json_wtr); + + /* Process each device/queue-type combination */ + i = 0; + while (i < count) { + __u64 *rx_packets, *rx_bytes, *tx_packets, *tx_bytes; + enum netdev_queue_type type = sorted[i]->queue_type; + unsigned int ifindex = sorted[i]->ifindex; + unsigned int queue_count = 0; + char ifname[IF_NAMESIZE]; + const char *name; + + /* Count queues for this device/type */ + for (j = i; j < count && sorted[j]->ifindex == ifindex && + sorted[j]->queue_type == type; j++) + queue_count++; + + /* Skip if no packets/bytes (inactive queues) */ + if (!sorted[i]->_present.rx_packets && + !sorted[i]->_present.rx_bytes && + !sorted[i]->_present.tx_packets && + !sorted[i]->_present.tx_bytes) + goto next_ifc; + + /* Allocate arrays for statistics */ + rx_packets = calloc(queue_count, sizeof(*rx_packets)); + rx_bytes = calloc(queue_count, sizeof(*rx_bytes)); + tx_packets = calloc(queue_count, sizeof(*tx_packets)); + tx_bytes = calloc(queue_count, sizeof(*tx_bytes)); + + if (!rx_packets || !rx_bytes || !tx_packets || !tx_bytes) { + p_err("failed to allocate statistics arrays"); + free(rx_packets); + free(rx_bytes); + free(tx_packets); + free(tx_bytes); + ret = -1; + goto exit_free_sorted; + } + + /* Collect statistics */ + for (j = 0; j < queue_count; j++) { + rx_packets[j] = sorted[i + j]->_present.rx_packets ? + sorted[i + j]->rx_packets : 0; + rx_bytes[j] = sorted[i + j]->_present.rx_bytes ? + sorted[i + j]->rx_bytes : 0; + tx_packets[j] = sorted[i + j]->_present.tx_packets ? + sorted[i + j]->tx_packets : 0; + tx_bytes[j] = sorted[i + j]->_present.tx_bytes ? + sorted[i + j]->tx_bytes : 0; + } + + name = if_indextoname(ifindex, ifname); + + if (json_output) { + jsonw_start_object(json_wtr); + if (name) + jsonw_string_field(json_wtr, "ifname", name); + jsonw_uint_field(json_wtr, "ifindex", ifindex); + jsonw_string_field(json_wtr, "queue-type", + netdev_queue_type_str(type)); + + print_balance_stats_json("rx-packets", type, + rx_packets, queue_count); + print_balance_stats_json("rx-bytes", type, + rx_bytes, queue_count); + print_balance_stats_json("tx-packets", type, + tx_packets, queue_count); + print_balance_stats_json("tx-bytes", type, + tx_bytes, queue_count); + + jsonw_end_object(json_wtr); + } else { + if (name) + printf("%s", name); + else + printf("ifindex:%u", ifindex); + printf(" %s %d queues:\n", + netdev_queue_type_str(type), queue_count); + + print_balance_stats("rx-packets", type, + rx_packets, queue_count); + print_balance_stats("rx-bytes", type, + rx_bytes, queue_count); + print_balance_stats("tx-packets", type, + tx_packets, queue_count); + print_balance_stats("tx-bytes", type, + tx_bytes, queue_count); + printf("\n"); + } + + free(rx_packets); + free(rx_bytes); + free(tx_packets); + free(tx_bytes); + +next_ifc: + i += queue_count; + } + + if (json_output) + jsonw_end_array(json_wtr); + +exit_free_sorted: + free(sorted); +exit_free_qstats: + netdev_qstats_get_list_free(qstats); +exit_close: + ynl_sock_destroy(ys); + return ret; +} + +static int do_help(int argc __attribute__((unused)), + char **argv __attribute__((unused))) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s qstats { COMMAND | help }\n" + " %s qstats [ show ] [ OPTIONS ]\n" + " %s qstats balance\n" + "\n" + " OPTIONS := { scope queue | group-by { device | queue } }\n" + "\n" + " show - Display queue statistics (default)\n" + " Statistics are aggregated for the entire device.\n" + " show scope queue - Display per-queue statistics\n" + " show group-by device - Display device-aggregated statistics (default)\n" + " show group-by queue - Display per-queue statistics\n" + " balance - Analyze traffic distribution balance.\n" + "", + bin_name, bin_name, bin_name); + + return 0; +} + +static const struct cmd qstats_cmds[] = { + { "show", do_show }, + { "balance", do_balance }, + { "help", do_help }, + { 0 } +}; + +int do_qstats(int argc, char **argv) +{ + return cmd_select(qstats_cmds, argc, argv, do_help); +} diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 3b262487ec060..77d7c59f5d8b1 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -34,10 +34,7 @@ typedef __kernel_sa_family_t sa_family_t; struct sockaddr { sa_family_t sa_family; /* address family, AF_xxx */ - union { - char sa_data_min[14]; /* Minimum 14 bytes of protocol address */ - DECLARE_FLEX_ARRAY(char, sa_data); - }; + char sa_data[14]; /* 14 bytes of protocol address */ }; struct linger { diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config index 422e186cf3cf1..2f093048d985c 100644 --- a/tools/testing/kunit/configs/all_tests.config +++ b/tools/testing/kunit/configs/all_tests.config @@ -36,22 +36,6 @@ CONFIG_MAC80211=y CONFIG_WLAN_VENDOR_INTEL=y CONFIG_IWLWIFI=y -CONFIG_DAMON=y -CONFIG_DAMON_VADDR=y -CONFIG_DAMON_PADDR=y - CONFIG_REGMAP_BUILD=y -CONFIG_AUDIT=y - CONFIG_PRIME_NUMBERS=y - -CONFIG_SECURITY=y -CONFIG_SECURITY_APPARMOR=y -CONFIG_SECURITY_LANDLOCK=y - -CONFIG_SOUND=y -CONFIG_SND=y -CONFIG_SND_SOC=y -CONFIG_SND_SOC_TOPOLOGY_BUILD=y -CONFIG_SND_SOC_CS35L56_I2C=y diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f2a2fd236ca83..558839e3c185e 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -126,3 +126,8 @@ CONFIG_XDP_SOCKETS=y CONFIG_XFRM_INTERFACE=y CONFIG_TCP_CONG_DCTCP=y CONFIG_TCP_CONG_BBR=y +CONFIG_INFINIBAND=y +CONFIG_SMC=y +CONFIG_SMC_HS_CTRL_BPF=y +CONFIG_DIBS=y +CONFIG_DIBS_LO=y \ No newline at end of file diff --git a/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c new file mode 100644 index 0000000000000..e4940583924b1 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/sk_bypass_prot_mem.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include +#include "sk_bypass_prot_mem.skel.h" +#include "network_helpers.h" + +#define NR_PAGES 32 +#define NR_SOCKETS 2 +#define BUF_TOTAL (NR_PAGES * 4096 / NR_SOCKETS) +#define BUF_SINGLE 1024 +#define NR_SEND (BUF_TOTAL / BUF_SINGLE) + +struct test_case { + char name[8]; + int family; + int type; + int (*create_sockets)(struct test_case *test_case, int sk[], int len); + long (*get_memory_allocated)(struct test_case *test_case, struct sk_bypass_prot_mem *skel); +}; + +static int tcp_create_sockets(struct test_case *test_case, int sk[], int len) +{ + int server, i, err = 0; + + server = start_server(test_case->family, test_case->type, NULL, 0, 0); + if (!ASSERT_GE(server, 0, "start_server_str")) + return server; + + /* Keep for-loop so we can change NR_SOCKETS easily. */ + for (i = 0; i < len; i += 2) { + sk[i] = connect_to_fd(server, 0); + if (sk[i] < 0) { + ASSERT_GE(sk[i], 0, "connect_to_fd"); + err = sk[i]; + break; + } + + sk[i + 1] = accept(server, NULL, NULL); + if (sk[i + 1] < 0) { + ASSERT_GE(sk[i + 1], 0, "accept"); + err = sk[i + 1]; + break; + } + } + + close(server); + + return err; +} + +static int udp_create_sockets(struct test_case *test_case, int sk[], int len) +{ + int i, j, err, rcvbuf = BUF_TOTAL; + + /* Keep for-loop so we can change NR_SOCKETS easily. */ + for (i = 0; i < len; i += 2) { + sk[i] = start_server(test_case->family, test_case->type, NULL, 0, 0); + if (sk[i] < 0) { + ASSERT_GE(sk[i], 0, "start_server"); + return sk[i]; + } + + sk[i + 1] = connect_to_fd(sk[i], 0); + if (sk[i + 1] < 0) { + ASSERT_GE(sk[i + 1], 0, "connect_to_fd"); + return sk[i + 1]; + } + + err = connect_fd_to_fd(sk[i], sk[i + 1], 0); + if (err) { + ASSERT_EQ(err, 0, "connect_fd_to_fd"); + return err; + } + + for (j = 0; j < 2; j++) { + err = setsockopt(sk[i + j], SOL_SOCKET, SO_RCVBUF, &rcvbuf, sizeof(int)); + if (err) { + ASSERT_EQ(err, 0, "setsockopt(SO_RCVBUF)"); + return err; + } + } + } + + return 0; +} + +static long get_memory_allocated(struct test_case *test_case, + bool *activated, long *memory_allocated) +{ + int sk; + + *activated = true; + + /* AF_INET and AF_INET6 share the same memory_allocated. + * tcp_init_sock() is called by AF_INET and AF_INET6, + * but udp_lib_init_sock() is inline. + */ + sk = socket(AF_INET, test_case->type, 0); + if (!ASSERT_GE(sk, 0, "get_memory_allocated")) + return -1; + + close(sk); + + return *memory_allocated; +} + +static long tcp_get_memory_allocated(struct test_case *test_case, struct sk_bypass_prot_mem *skel) +{ + return get_memory_allocated(test_case, + &skel->bss->tcp_activated, + &skel->bss->tcp_memory_allocated); +} + +static long udp_get_memory_allocated(struct test_case *test_case, struct sk_bypass_prot_mem *skel) +{ + return get_memory_allocated(test_case, + &skel->bss->udp_activated, + &skel->bss->udp_memory_allocated); +} + +static int check_bypass(struct test_case *test_case, + struct sk_bypass_prot_mem *skel, bool bypass) +{ + char buf[BUF_SINGLE] = {}; + long memory_allocated[2]; + int sk[NR_SOCKETS]; + int err, i, j; + + for (i = 0; i < ARRAY_SIZE(sk); i++) + sk[i] = -1; + + err = test_case->create_sockets(test_case, sk, ARRAY_SIZE(sk)); + if (err) + goto close; + + memory_allocated[0] = test_case->get_memory_allocated(test_case, skel); + + /* allocate pages >= NR_PAGES */ + for (i = 0; i < ARRAY_SIZE(sk); i++) { + for (j = 0; j < NR_SEND; j++) { + int bytes = send(sk[i], buf, sizeof(buf), 0); + + /* Avoid too noisy logs when something failed. */ + if (bytes != sizeof(buf)) { + ASSERT_EQ(bytes, sizeof(buf), "send"); + if (bytes < 0) { + err = bytes; + goto drain; + } + } + } + } + + memory_allocated[1] = test_case->get_memory_allocated(test_case, skel); + + if (bypass) + ASSERT_LE(memory_allocated[1], memory_allocated[0] + 10, "bypass"); + else + ASSERT_GT(memory_allocated[1], memory_allocated[0] + NR_PAGES, "no bypass"); + +drain: + if (test_case->type == SOCK_DGRAM) { + /* UDP starts purging sk->sk_receive_queue after one RCU + * grace period, then udp_memory_allocated goes down, + * so drain the queue before close(). + */ + for (i = 0; i < ARRAY_SIZE(sk); i++) { + for (j = 0; j < NR_SEND; j++) { + int bytes = recv(sk[i], buf, 1, MSG_DONTWAIT | MSG_TRUNC); + + if (bytes == sizeof(buf)) + continue; + if (bytes != -1 || errno != EAGAIN) + PRINT_FAIL("bytes: %d, errno: %s\n", bytes, strerror(errno)); + break; + } + } + } + +close: + for (i = 0; i < ARRAY_SIZE(sk); i++) { + if (sk[i] < 0) + break; + + close(sk[i]); + } + + return err; +} + +static void run_test(struct test_case *test_case) +{ + struct sk_bypass_prot_mem *skel; + struct nstoken *nstoken; + int cgroup, err; + + skel = sk_bypass_prot_mem__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + return; + + skel->bss->nr_cpus = libbpf_num_possible_cpus(); + + err = sk_bypass_prot_mem__attach(skel); + if (!ASSERT_OK(err, "attach")) + goto destroy_skel; + + cgroup = test__join_cgroup("/sk_bypass_prot_mem"); + if (!ASSERT_GE(cgroup, 0, "join_cgroup")) + goto destroy_skel; + + err = make_netns("sk_bypass_prot_mem"); + if (!ASSERT_EQ(err, 0, "make_netns")) + goto close_cgroup; + + nstoken = open_netns("sk_bypass_prot_mem"); + if (!ASSERT_OK_PTR(nstoken, "open_netns")) + goto remove_netns; + + err = check_bypass(test_case, skel, false); + if (!ASSERT_EQ(err, 0, "test_bypass(false)")) + goto close_netns; + + err = write_sysctl("/proc/sys/net/core/bypass_prot_mem", "1"); + if (!ASSERT_EQ(err, 0, "write_sysctl(1)")) + goto close_netns; + + err = check_bypass(test_case, skel, true); + if (!ASSERT_EQ(err, 0, "test_bypass(true by sysctl)")) + goto close_netns; + + err = write_sysctl("/proc/sys/net/core/bypass_prot_mem", "0"); + if (!ASSERT_EQ(err, 0, "write_sysctl(0)")) + goto close_netns; + + skel->links.sock_create = bpf_program__attach_cgroup(skel->progs.sock_create, cgroup); + if (!ASSERT_OK_PTR(skel->links.sock_create, "attach_cgroup(sock_create)")) + goto close_netns; + + err = check_bypass(test_case, skel, true); + ASSERT_EQ(err, 0, "test_bypass(true by bpf)"); + +close_netns: + close_netns(nstoken); +remove_netns: + remove_netns("sk_bypass_prot_mem"); +close_cgroup: + close(cgroup); +destroy_skel: + sk_bypass_prot_mem__destroy(skel); +} + +static struct test_case test_cases[] = { + { + .name = "TCP ", + .family = AF_INET, + .type = SOCK_STREAM, + .create_sockets = tcp_create_sockets, + .get_memory_allocated = tcp_get_memory_allocated, + }, + { + .name = "UDP ", + .family = AF_INET, + .type = SOCK_DGRAM, + .create_sockets = udp_create_sockets, + .get_memory_allocated = udp_get_memory_allocated, + }, + { + .name = "TCPv6", + .family = AF_INET6, + .type = SOCK_STREAM, + .create_sockets = tcp_create_sockets, + .get_memory_allocated = tcp_get_memory_allocated, + }, + { + .name = "UDPv6", + .family = AF_INET6, + .type = SOCK_DGRAM, + .create_sockets = udp_create_sockets, + .get_memory_allocated = udp_get_memory_allocated, + }, +}; + +void serial_test_sk_bypass_prot_mem(void) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(test_cases); i++) { + if (test__start_subtest(test_cases[i].name)) + run_test(&test_cases[i]); + } +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c b/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c new file mode 100644 index 0000000000000..de22734abc4d2 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bpf_smc.c @@ -0,0 +1,390 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include "network_helpers.h" +#include "bpf_smc.skel.h" + +#ifndef IPPROTO_SMC +#define IPPROTO_SMC 256 +#endif + +#define CLIENT_IP "127.0.0.1" +#define SERVER_IP "127.0.1.0" +#define SERVER_IP_VIA_RISK_PATH "127.0.2.0" + +#define SERVICE_1 80 +#define SERVICE_2 443 +#define SERVICE_3 8443 + +#define TEST_NS "bpf_smc_netns" + +static struct netns_obj *test_netns; + +struct smc_policy_ip_key { + __u32 sip; + __u32 dip; +}; + +struct smc_policy_ip_value { + __u8 mode; +}; + +#if defined(__s390x__) +/* s390x has default seid */ +static bool setup_ueid(void) { return true; } +static void cleanup_ueid(void) {} +#else +enum { + SMC_NETLINK_ADD_UEID = 10, + SMC_NETLINK_REMOVE_UEID +}; + +enum { + SMC_NLA_EID_TABLE_UNSPEC, + SMC_NLA_EID_TABLE_ENTRY, /* string */ +}; + +struct msgtemplate { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[1024]; +}; + +#define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) +#define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) +#define NLA_DATA(na) ((void *)((char *)(na) + NLA_HDRLEN)) +#define NLA_PAYLOAD(len) ((len) - NLA_HDRLEN) + +#define SMC_GENL_FAMILY_NAME "SMC_GEN_NETLINK" +#define SMC_BPFTEST_UEID "SMC-BPFTEST-UEID" + +static uint16_t smc_nl_family_id = -1; + +static int send_cmd(int fd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u16 nlmsg_flags, __u8 genl_cmd, __u16 nla_type, + void *nla_data, int nla_len) +{ + struct nlattr *na; + struct sockaddr_nl nladdr; + int r, buflen; + char *buf; + + struct msgtemplate msg = {0}; + + msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + msg.n.nlmsg_type = nlmsg_type; + msg.n.nlmsg_flags = nlmsg_flags; + msg.n.nlmsg_seq = 0; + msg.n.nlmsg_pid = nlmsg_pid; + msg.g.cmd = genl_cmd; + msg.g.version = 1; + na = (struct nlattr *)GENLMSG_DATA(&msg); + na->nla_type = nla_type; + na->nla_len = nla_len + 1 + NLA_HDRLEN; + memcpy(NLA_DATA(na), nla_data, nla_len); + msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len); + + buf = (char *)&msg; + buflen = msg.n.nlmsg_len; + memset(&nladdr, 0, sizeof(nladdr)); + nladdr.nl_family = AF_NETLINK; + + while ((r = sendto(fd, buf, buflen, 0, (struct sockaddr *)&nladdr, + sizeof(nladdr))) < buflen) { + if (r > 0) { + buf += r; + buflen -= r; + } else if (errno != EAGAIN) { + return -1; + } + } + return 0; +} + +static bool get_smc_nl_family_id(void) +{ + struct sockaddr_nl nl_src; + struct msgtemplate msg; + struct nlattr *nl; + int fd, ret; + pid_t pid; + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + if (!ASSERT_OK_FD(fd, "nl_family socket")) + return false; + + pid = getpid(); + + memset(&nl_src, 0, sizeof(nl_src)); + nl_src.nl_family = AF_NETLINK; + nl_src.nl_pid = pid; + + ret = bind(fd, (struct sockaddr *)&nl_src, sizeof(nl_src)); + if (!ASSERT_OK(ret, "nl_family bind")) + goto fail; + + ret = send_cmd(fd, GENL_ID_CTRL, pid, + NLM_F_REQUEST, CTRL_CMD_GETFAMILY, + CTRL_ATTR_FAMILY_NAME, (void *)SMC_GENL_FAMILY_NAME, + strlen(SMC_GENL_FAMILY_NAME)); + if (!ASSERT_OK(ret, "nl_family query")) + goto fail; + + ret = recv(fd, &msg, sizeof(msg), 0); + if (!ASSERT_FALSE(msg.n.nlmsg_type == NLMSG_ERROR || ret < 0 || + !NLMSG_OK(&msg.n, ret), "nl_family response")) + goto fail; + + nl = (struct nlattr *)GENLMSG_DATA(&msg); + nl = (struct nlattr *)((char *)nl + NLA_ALIGN(nl->nla_len)); + if (!ASSERT_EQ(nl->nla_type, CTRL_ATTR_FAMILY_ID, "nl_family nla type")) + goto fail; + + smc_nl_family_id = *(uint16_t *)NLA_DATA(nl); + close(fd); + return true; +fail: + close(fd); + return false; +} + +static bool smc_ueid(int op) +{ + struct sockaddr_nl nl_src; + struct msgtemplate msg; + struct nlmsgerr *err; + char test_ueid[32]; + int fd, ret; + pid_t pid; + + /* UEID required */ + memset(test_ueid, '\x20', sizeof(test_ueid)); + memcpy(test_ueid, SMC_BPFTEST_UEID, strlen(SMC_BPFTEST_UEID)); + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_GENERIC); + if (!ASSERT_OK_FD(fd, "ueid socket")) + return false; + + pid = getpid(); + memset(&nl_src, 0, sizeof(nl_src)); + nl_src.nl_family = AF_NETLINK; + nl_src.nl_pid = pid; + + ret = bind(fd, (struct sockaddr *)&nl_src, sizeof(nl_src)); + if (!ASSERT_OK(ret, "ueid bind")) + goto fail; + + ret = send_cmd(fd, smc_nl_family_id, pid, + NLM_F_REQUEST | NLM_F_ACK, op, SMC_NLA_EID_TABLE_ENTRY, + (void *)test_ueid, sizeof(test_ueid)); + if (!ASSERT_OK(ret, "ueid cmd")) + goto fail; + + ret = recv(fd, &msg, sizeof(msg), 0); + if (!ASSERT_FALSE(ret < 0 || + !NLMSG_OK(&msg.n, ret), "ueid response")) + goto fail; + + if (msg.n.nlmsg_type == NLMSG_ERROR) { + err = NLMSG_DATA(&msg); + switch (op) { + case SMC_NETLINK_REMOVE_UEID: + if (!ASSERT_FALSE((err->error && err->error != -ENOENT), + "ueid remove")) + goto fail; + break; + case SMC_NETLINK_ADD_UEID: + if (!ASSERT_OK(err->error, "ueid add")) + goto fail; + break; + default: + break; + } + } + close(fd); + return true; +fail: + close(fd); + return false; +} + +static bool setup_ueid(void) +{ + /* get smc nl id */ + if (!get_smc_nl_family_id()) + return false; + /* clear old ueid for bpftest */ + smc_ueid(SMC_NETLINK_REMOVE_UEID); + /* smc-loopback required ueid */ + return smc_ueid(SMC_NETLINK_ADD_UEID); +} + +static void cleanup_ueid(void) +{ + smc_ueid(SMC_NETLINK_REMOVE_UEID); +} +#endif /* __s390x__ */ + +static bool setup_netns(void) +{ + test_netns = netns_new(TEST_NS, true); + if (!ASSERT_OK_PTR(test_netns, "open net namespace")) + goto fail_netns; + + SYS(fail_ip, "ip addr add 127.0.1.0/8 dev lo"); + SYS(fail_ip, "ip addr add 127.0.2.0/8 dev lo"); + + return true; +fail_ip: + netns_free(test_netns); +fail_netns: + return false; +} + +static void cleanup_netns(void) +{ + netns_free(test_netns); +} + +static bool setup_smc(void) +{ + if (!setup_ueid()) + return false; + + if (!setup_netns()) + goto fail_netns; + + return true; +fail_netns: + cleanup_ueid(); + return false; +} + +static int set_client_addr_cb(int fd, void *opts) +{ + const char *src = (const char *)opts; + struct sockaddr_in localaddr; + + localaddr.sin_family = AF_INET; + localaddr.sin_port = htons(0); + localaddr.sin_addr.s_addr = inet_addr(src); + return !ASSERT_OK(bind(fd, &localaddr, sizeof(localaddr)), "client bind"); +} + +static void run_link(const char *src, const char *dst, int port) +{ + struct network_helper_opts opts = {0}; + int server, client; + + server = start_server_str(AF_INET, SOCK_STREAM, dst, port, NULL); + if (!ASSERT_OK_FD(server, "start service_1")) + return; + + opts.proto = IPPROTO_TCP; + opts.post_socket_cb = set_client_addr_cb; + opts.cb_opts = (void *)src; + + client = connect_to_fd_opts(server, &opts); + if (!ASSERT_OK_FD(client, "start connect")) + goto fail_client; + + close(client); +fail_client: + close(server); +} + +static void block_link(int map_fd, const char *src, const char *dst) +{ + struct smc_policy_ip_value val = { .mode = /* block */ 0 }; + struct smc_policy_ip_key key = { + .sip = inet_addr(src), + .dip = inet_addr(dst), + }; + + bpf_map_update_elem(map_fd, &key, &val, BPF_ANY); +} + +/* + * This test describes a real-life service topology as follows: + * + * +-------------> service_1 + * link 1 | | + * +--------------------> server | link 2 + * | | V + * | +-------------> service_2 + * | link 3 + * client -------------------> server_via_unsafe_path -> service_3 + * + * Among them, + * 1. link-1 is very suitable for using SMC. + * 2. link-2 is not suitable for using SMC, because the mode of this link is + * kind of short-link services. + * 3. link-3 is also not suitable for using SMC, because the RDMA link is + * unavailable and needs to go through a long timeout before it can fallback + * to TCP. + * To achieve this goal, we use a customized SMC ip strategy via smc_hs_ctrl. + */ +static void test_topo(void) +{ + struct bpf_smc *skel; + int rc, map_fd; + + skel = bpf_smc__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_smc__open_and_load")) + return; + + rc = bpf_smc__attach(skel); + if (!ASSERT_OK(rc, "bpf_smc__attach")) + goto fail; + + map_fd = bpf_map__fd(skel->maps.smc_policy_ip); + if (!ASSERT_OK_FD(map_fd, "bpf_map__fd")) + goto fail; + + /* Mock the process of transparent replacement, since we will modify + * protocol to ipproto_smc accropding to it via + * fmod_ret/update_socket_protocol. + */ + write_sysctl("/proc/sys/net/smc/hs_ctrl", "linkcheck"); + + /* Configure ip strat */ + block_link(map_fd, CLIENT_IP, SERVER_IP_VIA_RISK_PATH); + block_link(map_fd, SERVER_IP, SERVER_IP); + + /* should go with smc */ + run_link(CLIENT_IP, SERVER_IP, SERVICE_1); + /* should go with smc fallback */ + run_link(SERVER_IP, SERVER_IP, SERVICE_2); + + ASSERT_EQ(skel->bss->smc_cnt, 2, "smc count"); + ASSERT_EQ(skel->bss->fallback_cnt, 1, "fallback count"); + + /* should go with smc */ + run_link(CLIENT_IP, SERVER_IP, SERVICE_2); + + ASSERT_EQ(skel->bss->smc_cnt, 3, "smc count"); + ASSERT_EQ(skel->bss->fallback_cnt, 1, "fallback count"); + + /* should go with smc fallback */ + run_link(CLIENT_IP, SERVER_IP_VIA_RISK_PATH, SERVICE_3); + + ASSERT_EQ(skel->bss->smc_cnt, 4, "smc count"); + ASSERT_EQ(skel->bss->fallback_cnt, 2, "fallback count"); + +fail: + bpf_smc__destroy(skel); +} + +void test_bpf_smc(void) +{ + if (!setup_smc()) { + printf("setup for smc test failed, test SKIP:\n"); + test__skip(); + return; + } + + if (test__start_subtest("topo")) + test_topo(); + + cleanup_ueid(); + cleanup_netns(); +} diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c index 178292d1251a1..ee94c281888ae 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c @@ -124,10 +124,10 @@ static int send_test_packet(int ifindex) int n, sock = -1; __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; - /* The ethernet header is not relevant for this test and doesn't need to - * be meaningful. - */ - struct ethhdr eth = { 0 }; + /* We use the Ethernet header only to identify the test packet */ + struct ethhdr eth = { + .h_source = { 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF }, + }; memcpy(packet, ð, sizeof(eth)); memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN); @@ -160,8 +160,16 @@ static int write_test_packet(int tap_fd) __u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN]; int n; - /* The ethernet header doesn't need to be valid for this test */ - memset(packet, 0, sizeof(struct ethhdr)); + /* The Ethernet header is mostly not relevant. We use it to identify the + * test packet and some BPF helpers we exercise expect to operate on + * Ethernet frames carrying IP packets. Pretend that's the case. + */ + struct ethhdr eth = { + .h_source = { 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF }, + .h_proto = htons(ETH_P_IP), + }; + + memcpy(packet, ð, sizeof(eth)); memcpy(packet + sizeof(struct ethhdr), test_payload, TEST_PAYLOAD_LEN); n = write(tap_fd, packet, sizeof(packet)); @@ -171,31 +179,19 @@ static int write_test_packet(int tap_fd) return 0; } -static void assert_test_result(const struct bpf_map *result_map) -{ - int err; - __u32 map_key = 0; - __u8 map_value[TEST_PAYLOAD_LEN]; - - err = bpf_map__lookup_elem(result_map, &map_key, sizeof(map_key), - &map_value, TEST_PAYLOAD_LEN, BPF_ANY); - if (!ASSERT_OK(err, "lookup test_result")) - return; - - ASSERT_MEMEQ(&map_value, &test_payload, TEST_PAYLOAD_LEN, - "test_result map contains test payload"); -} - -static bool clear_test_result(struct bpf_map *result_map) +static void dump_err_stream(const struct bpf_program *prog) { - const __u8 v[sizeof(test_payload)] = {}; - const __u32 k = 0; - int err; - - err = bpf_map__update_elem(result_map, &k, sizeof(k), v, sizeof(v), BPF_ANY); - ASSERT_OK(err, "update test_result"); + char buf[512]; + int ret; - return err == 0; + ret = 0; + do { + ret = bpf_prog_stream_read(bpf_program__fd(prog), + BPF_STREAM_STDERR, buf, sizeof(buf), + NULL); + if (ret > 0) + fwrite(buf, sizeof(buf[0]), ret, stderr); + } while (ret > 0); } void test_xdp_context_veth(void) @@ -270,11 +266,14 @@ void test_xdp_context_veth(void) if (!ASSERT_GE(tx_ifindex, 0, "if_nametoindex tx")) goto close; + skel->bss->test_pass = false; + ret = send_test_packet(tx_ifindex); if (!ASSERT_OK(ret, "send_test_packet")) goto close; - assert_test_result(skel->maps.test_result); + if (!ASSERT_TRUE(skel->bss->test_pass, "test_pass")) + dump_err_stream(tc_prog); close: close_netns(nstoken); @@ -286,7 +285,7 @@ void test_xdp_context_veth(void) static void test_tuntap(struct bpf_program *xdp_prog, struct bpf_program *tc_prio_1_prog, struct bpf_program *tc_prio_2_prog, - struct bpf_map *result_map) + bool *test_pass) { LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS); LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1); @@ -295,8 +294,7 @@ static void test_tuntap(struct bpf_program *xdp_prog, int tap_ifindex; int ret; - if (!clear_test_result(result_map)) - return; + *test_pass = false; ns = netns_new(TAP_NETNS, true); if (!ASSERT_OK_PTR(ns, "create and open ns")) @@ -340,7 +338,8 @@ static void test_tuntap(struct bpf_program *xdp_prog, if (!ASSERT_OK(ret, "write_test_packet")) goto close; - assert_test_result(result_map); + if (!ASSERT_TRUE(*test_pass, "test_pass")) + dump_err_stream(tc_prio_2_prog ? : tc_prio_1_prog); close: if (tap_fd >= 0) @@ -411,7 +410,8 @@ static void test_tuntap_mirred(struct bpf_program *xdp_prog, if (!ASSERT_OK(ret, "write_test_packet")) goto close; - ASSERT_TRUE(*test_pass, "test_pass"); + if (!ASSERT_TRUE(*test_pass, "test_pass")) + dump_err_stream(tc_prog); close: if (tap_fd >= 0) @@ -431,61 +431,82 @@ void test_xdp_context_tuntap(void) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls, NULL, /* tc prio 2 */ - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_read")) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls_dynptr_read, NULL, /* tc prio 2 */ - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_slice")) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls_dynptr_slice, NULL, /* tc prio 2 */ - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_write")) test_tuntap(skel->progs.ing_xdp_zalloc_meta, skel->progs.ing_cls_dynptr_write, skel->progs.ing_cls_dynptr_read, - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_slice_rdwr")) test_tuntap(skel->progs.ing_xdp_zalloc_meta, skel->progs.ing_cls_dynptr_slice_rdwr, skel->progs.ing_cls_dynptr_slice, - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_offset")) test_tuntap(skel->progs.ing_xdp_zalloc_meta, skel->progs.ing_cls_dynptr_offset_wr, skel->progs.ing_cls_dynptr_offset_rd, - skel->maps.test_result); + &skel->bss->test_pass); if (test__start_subtest("dynptr_offset_oob")) test_tuntap(skel->progs.ing_xdp, skel->progs.ing_cls_dynptr_offset_oob, skel->progs.ing_cls, - skel->maps.test_result); - if (test__start_subtest("clone_data_meta_empty_on_data_write")) + &skel->bss->test_pass); + if (test__start_subtest("clone_data_meta_survives_data_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_data_meta_empty_on_data_write, + skel->progs.clone_data_meta_survives_data_write, &skel->bss->test_pass); - if (test__start_subtest("clone_data_meta_empty_on_meta_write")) + if (test__start_subtest("clone_data_meta_survives_meta_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_data_meta_empty_on_meta_write, + skel->progs.clone_data_meta_survives_meta_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_empty_on_data_slice_write")) + if (test__start_subtest("clone_meta_dynptr_survives_data_slice_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_empty_on_data_slice_write, + skel->progs.clone_meta_dynptr_survives_data_slice_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_empty_on_meta_slice_write")) + if (test__start_subtest("clone_meta_dynptr_survives_meta_slice_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_empty_on_meta_slice_write, + skel->progs.clone_meta_dynptr_survives_meta_slice_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_rdonly_before_data_dynptr_write")) + if (test__start_subtest("clone_meta_dynptr_rw_before_data_dynptr_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_rdonly_before_data_dynptr_write, + skel->progs.clone_meta_dynptr_rw_before_data_dynptr_write, &skel->bss->test_pass); - if (test__start_subtest("clone_dynptr_rdonly_before_meta_dynptr_write")) + if (test__start_subtest("clone_meta_dynptr_rw_before_meta_dynptr_write")) test_tuntap_mirred(skel->progs.ing_xdp, - skel->progs.clone_dynptr_rdonly_before_meta_dynptr_write, + skel->progs.clone_meta_dynptr_rw_before_meta_dynptr_write, &skel->bss->test_pass); + /* Tests for BPF helpers which touch headroom */ + if (test__start_subtest("helper_skb_vlan_push_pop")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_vlan_push_pop, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); + if (test__start_subtest("helper_skb_adjust_room")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_adjust_room, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); + if (test__start_subtest("helper_skb_change_head_tail")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_change_head_tail, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); + if (test__start_subtest("helper_skb_change_proto")) + test_tuntap(skel->progs.ing_xdp, + skel->progs.helper_skb_change_proto, + NULL, /* tc prio 2 */ + &skel->bss->test_pass); test_xdp_meta__destroy(skel); } diff --git a/tools/testing/selftests/bpf/progs/bpf_smc.c b/tools/testing/selftests/bpf/progs/bpf_smc.c new file mode 100644 index 0000000000000..70d8b08f59140 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bpf_smc.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include "vmlinux.h" + +#include +#include +#include "bpf_tracing_net.h" + +char _license[] SEC("license") = "GPL"; + +enum { + BPF_SMC_LISTEN = 10, +}; + +struct smc_sock___local { + struct sock sk; + struct smc_sock *listen_smc; + bool use_fallback; +} __attribute__((preserve_access_index)); + +int smc_cnt = 0; +int fallback_cnt = 0; + +SEC("fentry/smc_release") +int BPF_PROG(bpf_smc_release, struct socket *sock) +{ + /* only count from one side (client) */ + if (sock->sk->__sk_common.skc_state == BPF_SMC_LISTEN) + return 0; + smc_cnt++; + return 0; +} + +SEC("fentry/smc_switch_to_fallback") +int BPF_PROG(bpf_smc_switch_to_fallback, struct smc_sock___local *smc) +{ + /* only count from one side (client) */ + if (smc && !smc->listen_smc) + fallback_cnt++; + return 0; +} + +/* go with default value if no strat was found */ +bool default_ip_strat_value = true; + +struct smc_policy_ip_key { + __u32 sip; + __u32 dip; +}; + +struct smc_policy_ip_value { + __u8 mode; +}; + +struct { + __uint(type, BPF_MAP_TYPE_HASH); + __uint(key_size, sizeof(struct smc_policy_ip_key)); + __uint(value_size, sizeof(struct smc_policy_ip_value)); + __uint(max_entries, 128); + __uint(map_flags, BPF_F_NO_PREALLOC); +} smc_policy_ip SEC(".maps"); + +static bool smc_check(__u32 src, __u32 dst) +{ + struct smc_policy_ip_value *value; + struct smc_policy_ip_key key = { + .sip = src, + .dip = dst, + }; + + value = bpf_map_lookup_elem(&smc_policy_ip, &key); + return value ? value->mode : default_ip_strat_value; +} + +SEC("fmod_ret/update_socket_protocol") +int BPF_PROG(smc_run, int family, int type, int protocol) +{ + struct task_struct *task; + + if (family != AF_INET && family != AF_INET6) + return protocol; + + if ((type & 0xf) != SOCK_STREAM) + return protocol; + + if (protocol != 0 && protocol != IPPROTO_TCP) + return protocol; + + task = bpf_get_current_task_btf(); + /* Prevent from affecting other tests */ + if (!task || !task->nsproxy->net_ns->smc.hs_ctrl) + return protocol; + + return IPPROTO_SMC; +} + +SEC("struct_ops") +int BPF_PROG(bpf_smc_set_tcp_option_cond, const struct tcp_sock *tp, + struct inet_request_sock *ireq) +{ + return smc_check(ireq->req.__req_common.skc_daddr, + ireq->req.__req_common.skc_rcv_saddr); +} + +SEC("struct_ops") +int BPF_PROG(bpf_smc_set_tcp_option, struct tcp_sock *tp) +{ + return smc_check(tp->inet_conn.icsk_inet.sk.__sk_common.skc_rcv_saddr, + tp->inet_conn.icsk_inet.sk.__sk_common.skc_daddr); +} + +SEC(".struct_ops") +struct smc_hs_ctrl linkcheck = { + .name = "linkcheck", + .syn_option = (void *)bpf_smc_set_tcp_option, + .synack_option = (void *)bpf_smc_set_tcp_option_cond, +}; diff --git a/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c b/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c new file mode 100644 index 0000000000000..09a00d11ffcc4 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sk_bypass_prot_mem.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright 2025 Google LLC */ + +#include "bpf_tracing_net.h" +#include +#include +#include + +extern int tcp_memory_per_cpu_fw_alloc __ksym; +extern int udp_memory_per_cpu_fw_alloc __ksym; + +int nr_cpus; +bool tcp_activated, udp_activated; +long tcp_memory_allocated, udp_memory_allocated; + +struct sk_prot { + long *memory_allocated; + int *memory_per_cpu_fw_alloc; +}; + +static int drain_memory_per_cpu_fw_alloc(__u32 i, struct sk_prot *sk_prot_ctx) +{ + int *memory_per_cpu_fw_alloc; + + memory_per_cpu_fw_alloc = bpf_per_cpu_ptr(sk_prot_ctx->memory_per_cpu_fw_alloc, i); + if (memory_per_cpu_fw_alloc) + *sk_prot_ctx->memory_allocated += *memory_per_cpu_fw_alloc; + + return 0; +} + +static long get_memory_allocated(struct sock *_sk, int *memory_per_cpu_fw_alloc) +{ + struct sock *sk = bpf_core_cast(_sk, struct sock); + struct sk_prot sk_prot_ctx; + long memory_allocated; + + /* net_aligned_data.{tcp,udp}_memory_allocated was not available. */ + memory_allocated = sk->__sk_common.skc_prot->memory_allocated->counter; + + sk_prot_ctx.memory_allocated = &memory_allocated; + sk_prot_ctx.memory_per_cpu_fw_alloc = memory_per_cpu_fw_alloc; + + bpf_loop(nr_cpus, drain_memory_per_cpu_fw_alloc, &sk_prot_ctx, 0); + + return memory_allocated; +} + +static void fentry_init_sock(struct sock *sk, bool *activated, + long *memory_allocated, int *memory_per_cpu_fw_alloc) +{ + if (!*activated) + return; + + *memory_allocated = get_memory_allocated(sk, memory_per_cpu_fw_alloc); + *activated = false; +} + +SEC("fentry/tcp_init_sock") +int BPF_PROG(fentry_tcp_init_sock, struct sock *sk) +{ + fentry_init_sock(sk, &tcp_activated, + &tcp_memory_allocated, &tcp_memory_per_cpu_fw_alloc); + return 0; +} + +SEC("fentry/udp_init_sock") +int BPF_PROG(fentry_udp_init_sock, struct sock *sk) +{ + fentry_init_sock(sk, &udp_activated, + &udp_memory_allocated, &udp_memory_per_cpu_fw_alloc); + return 0; +} + +SEC("cgroup/sock_create") +int sock_create(struct bpf_sock *ctx) +{ + int err, val = 1; + + err = bpf_setsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM, + &val, sizeof(val)); + if (err) + goto err; + + val = 0; + + err = bpf_getsockopt(ctx, SOL_SOCKET, SK_BPF_BYPASS_PROT_MEM, + &val, sizeof(val)); + if (err) + goto err; + + if (val != 1) { + err = -EINVAL; + goto err; + } + + return 1; + +err: + bpf_set_retval(err); + return 0; +} + +char LICENSE[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c index d79cb74b571e7..0a0f371a2decc 100644 --- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c +++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c @@ -4,6 +4,7 @@ #include #include +#include #include #include "bpf_kfuncs.h" @@ -11,37 +12,72 @@ #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem -/* Demonstrates how metadata can be passed from an XDP program to a TC program - * using bpf_xdp_adjust_meta. - * For the sake of testing the metadata support in drivers, the XDP program uses - * a fixed-size payload after the Ethernet header as metadata. The TC program - * copies the metadata it receives into a map so it can be checked from - * userspace. +/* Demonstrate passing metadata from XDP to TC using bpf_xdp_adjust_meta. + * + * The XDP program extracts a fixed-size payload following the Ethernet header + * and stores it as packet metadata to test the driver's metadata support. The + * TC program then verifies if the passed metadata is correct. */ -struct { - __uint(type, BPF_MAP_TYPE_ARRAY); - __uint(max_entries, 1); - __type(key, __u32); - __uint(value_size, META_SIZE); -} test_result SEC(".maps"); - bool test_pass; +static const __u8 smac_want[ETH_ALEN] = { + 0x12, 0x34, 0xDE, 0xAD, 0xBE, 0xEF, +}; + +static const __u8 meta_want[META_SIZE] = { + 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, + 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, + 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, + 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, +}; + +static bool check_smac(const struct ethhdr *eth) +{ + return !__builtin_memcmp(eth->h_source, smac_want, ETH_ALEN); +} + +static bool check_metadata(const char *file, int line, __u8 *meta_have) +{ + if (!__builtin_memcmp(meta_have, meta_want, META_SIZE)) + return true; + + bpf_stream_printk(BPF_STREAM_STDERR, + "FAIL:%s:%d: metadata mismatch\n" + " have:\n %pI6\n %pI6\n" + " want:\n %pI6\n %pI6\n", + file, line, + &meta_have[0x00], &meta_have[0x10], + &meta_want[0x00], &meta_want[0x10]); + return false; +} + +#define check_metadata(meta_have) check_metadata(__FILE__, __LINE__, meta_have) + +static bool check_skb_metadata(const char *file, int line, struct __sk_buff *skb) +{ + __u8 *data_meta = ctx_ptr(skb, data_meta); + __u8 *data = ctx_ptr(skb, data); + + return data_meta + META_SIZE <= data && (check_metadata)(file, line, data_meta); +} + +#define check_skb_metadata(skb) check_skb_metadata(__FILE__, __LINE__, skb) + SEC("tc") int ing_cls(struct __sk_buff *ctx) { - __u8 *data, *data_meta; - __u32 key = 0; - - data_meta = ctx_ptr(ctx, data_meta); - data = ctx_ptr(ctx, data); + __u8 *meta_have = ctx_ptr(ctx, data_meta); + __u8 *data = ctx_ptr(ctx, data); - if (data_meta + META_SIZE > data) - return TC_ACT_SHOT; + if (meta_have + META_SIZE > data) + goto out; - bpf_map_update_elem(&test_result, &key, data_meta, BPF_ANY); + if (!check_metadata(meta_have)) + goto out; + test_pass = true; +out: return TC_ACT_SHOT; } @@ -49,17 +85,17 @@ int ing_cls(struct __sk_buff *ctx) SEC("tc") int ing_cls_dynptr_read(struct __sk_buff *ctx) { + __u8 meta_have[META_SIZE]; struct bpf_dynptr meta; - const __u32 zero = 0; - __u8 *dst; - - dst = bpf_map_lookup_elem(&test_result, &zero); - if (!dst) - return TC_ACT_SHOT; bpf_dynptr_from_skb_meta(ctx, 0, &meta); - bpf_dynptr_read(dst, META_SIZE, &meta, 0, 0); + bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (!check_metadata(meta_have)) + goto out; + + test_pass = true; +out: return TC_ACT_SHOT; } @@ -86,20 +122,18 @@ SEC("tc") int ing_cls_dynptr_slice(struct __sk_buff *ctx) { struct bpf_dynptr meta; - const __u32 zero = 0; - __u8 *dst, *src; - - dst = bpf_map_lookup_elem(&test_result, &zero); - if (!dst) - return TC_ACT_SHOT; + __u8 *meta_have; bpf_dynptr_from_skb_meta(ctx, 0, &meta); - src = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE); - if (!src) - return TC_ACT_SHOT; + meta_have = bpf_dynptr_slice(&meta, 0, NULL, META_SIZE); + if (!meta_have) + goto out; - __builtin_memcpy(dst, src, META_SIZE); + if (!check_metadata(meta_have)) + goto out; + test_pass = true; +out: return TC_ACT_SHOT; } @@ -129,14 +163,12 @@ int ing_cls_dynptr_slice_rdwr(struct __sk_buff *ctx) SEC("tc") int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx) { - struct bpf_dynptr meta; const __u32 chunk_len = META_SIZE / 4; - const __u32 zero = 0; + __u8 meta_have[META_SIZE]; + struct bpf_dynptr meta; __u8 *dst, *src; - dst = bpf_map_lookup_elem(&test_result, &zero); - if (!dst) - return TC_ACT_SHOT; + dst = meta_have; /* 1. Regular read */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); @@ -155,9 +187,14 @@ int ing_cls_dynptr_offset_rd(struct __sk_buff *ctx) /* 4. Read from a slice starting at an offset */ src = bpf_dynptr_slice(&meta, 2 * chunk_len, NULL, chunk_len); if (!src) - return TC_ACT_SHOT; + goto out; __builtin_memcpy(dst, src, chunk_len); + if (!check_metadata(meta_have)) + goto out; + + test_pass = true; +out: return TC_ACT_SHOT; } @@ -254,7 +291,7 @@ int ing_xdp_zalloc_meta(struct xdp_md *ctx) /* Drop any non-test packets */ if (eth + 1 > ctx_ptr(ctx, data_end)) return XDP_DROP; - if (eth->h_proto != 0) + if (!check_smac(eth)) return XDP_DROP; ret = bpf_xdp_adjust_meta(ctx, -META_SIZE); @@ -294,9 +331,9 @@ int ing_xdp(struct xdp_md *ctx) /* The Linux networking stack may send other packets on the test * interface that interfere with the test. Just drop them. - * The test packets can be recognized by their ethertype of zero. + * The test packets can be recognized by their source MAC address. */ - if (eth->h_proto != 0) + if (!check_smac(eth)) return XDP_DROP; __builtin_memcpy(data_meta, payload, META_SIZE); @@ -304,22 +341,25 @@ int ing_xdp(struct xdp_md *ctx) } /* - * Check that skb->data_meta..skb->data is empty if prog writes to packet - * _payload_ using packet pointers. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb->data_meta..skb->data is + * kept intact if prog writes to packet _payload_ using packet pointers. */ SEC("tc") -int clone_data_meta_empty_on_data_write(struct __sk_buff *ctx) +int clone_data_meta_survives_data_write(struct __sk_buff *ctx) { + __u8 *meta_have = ctx_ptr(ctx, data_meta); struct ethhdr *eth = ctx_ptr(ctx, data); if (eth + 1 > ctx_ptr(ctx, data_end)) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) + goto out; + + if (meta_have + META_SIZE > eth) goto out; - /* Expect no metadata */ - if (ctx->data_meta != ctx->data) + if (!check_metadata(meta_have)) goto out; /* Packet write to trigger unclone in prologue */ @@ -331,40 +371,44 @@ int clone_data_meta_empty_on_data_write(struct __sk_buff *ctx) } /* - * Check that skb->data_meta..skb->data is empty if prog writes to packet - * _metadata_ using packet pointers. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb->data_meta..skb->data is + * kept intact if prog writes to packet _metadata_ using packet pointers. */ SEC("tc") -int clone_data_meta_empty_on_meta_write(struct __sk_buff *ctx) +int clone_data_meta_survives_meta_write(struct __sk_buff *ctx) { + __u8 *meta_have = ctx_ptr(ctx, data_meta); struct ethhdr *eth = ctx_ptr(ctx, data); - __u8 *md = ctx_ptr(ctx, data_meta); if (eth + 1 > ctx_ptr(ctx, data_end)) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - if (md + 1 > ctx_ptr(ctx, data)) { - /* Expect no metadata */ - test_pass = true; - } else { - /* Metadata write to trigger unclone in prologue */ - *md = 42; - } + if (meta_have + META_SIZE > eth) + goto out; + + if (!check_metadata(meta_have)) + goto out; + + /* Metadata write to trigger unclone in prologue */ + *meta_have = 42; + + test_pass = true; out: return TC_ACT_SHOT; } /* - * Check that skb_meta dynptr is writable but empty if prog writes to packet - * _payload_ using a dynptr slice. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, metadata remains intact if + * prog creates a r/w slice to packet _payload_. */ SEC("tc") -int clone_dynptr_empty_on_data_slice_write(struct __sk_buff *ctx) +int clone_meta_dynptr_survives_data_slice_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; + __u8 meta_have[META_SIZE]; struct ethhdr *eth; bpf_dynptr_from_skb(ctx, 0, &data); @@ -372,51 +416,45 @@ int clone_dynptr_empty_on_data_slice_write(struct __sk_buff *ctx) if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect no metadata */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0) + bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (!check_metadata(meta_have)) goto out; - /* Packet write to trigger unclone in prologue */ - eth->h_proto = 42; - test_pass = true; out: return TC_ACT_SHOT; } /* - * Check that skb_meta dynptr is writable but empty if prog writes to packet - * _metadata_ using a dynptr slice. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, metadata remains intact if + * prog creates an r/w slice to packet _metadata_. */ SEC("tc") -int clone_dynptr_empty_on_meta_slice_write(struct __sk_buff *ctx) +int clone_meta_dynptr_survives_meta_slice_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; const struct ethhdr *eth; - __u8 *md; + __u8 *meta_have; bpf_dynptr_from_skb(ctx, 0, &data); eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect no metadata */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) > 0) + meta_have = bpf_dynptr_slice_rdwr(&meta, 0, NULL, META_SIZE); + if (!meta_have) goto out; - /* Metadata write to trigger unclone in prologue */ - bpf_dynptr_from_skb_meta(ctx, 0, &meta); - md = bpf_dynptr_slice_rdwr(&meta, 0, NULL, sizeof(*md)); - if (md) - *md = 42; + if (!check_metadata(meta_have)) + goto out; test_pass = true; out: @@ -424,34 +462,40 @@ int clone_dynptr_empty_on_meta_slice_write(struct __sk_buff *ctx) } /* - * Check that skb_meta dynptr is read-only before prog writes to packet payload - * using dynptr_write helper. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb_meta dynptr is read-write + * before prog writes to packet _payload_ using dynptr_write helper and metadata + * remains intact before and after the write. */ SEC("tc") -int clone_dynptr_rdonly_before_data_dynptr_write(struct __sk_buff *ctx) +int clone_meta_dynptr_rw_before_data_dynptr_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; + __u8 meta_have[META_SIZE]; const struct ethhdr *eth; + int err; bpf_dynptr_from_skb(ctx, 0, &data); eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect read-only metadata before unclone */ + /* Expect read-write metadata before unclone */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE) + if (bpf_dynptr_is_rdonly(&meta)) + goto out; + + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) goto out; /* Helper write to payload will unclone the packet */ bpf_dynptr_write(&data, offsetof(struct ethhdr, h_proto), "x", 1, 0); - /* Expect no metadata after unclone */ - bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != 0) + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) goto out; test_pass = true; @@ -460,31 +504,165 @@ int clone_dynptr_rdonly_before_data_dynptr_write(struct __sk_buff *ctx) } /* - * Check that skb_meta dynptr is read-only if prog writes to packet - * metadata using dynptr_write helper. Applies only to cloned skbs. + * Check that, when operating on a cloned packet, skb_meta dynptr is read-write + * before prog writes to packet _metadata_ using dynptr_write helper and + * metadata remains intact before and after the write. */ SEC("tc") -int clone_dynptr_rdonly_before_meta_dynptr_write(struct __sk_buff *ctx) +int clone_meta_dynptr_rw_before_meta_dynptr_write(struct __sk_buff *ctx) { struct bpf_dynptr data, meta; + __u8 meta_have[META_SIZE]; const struct ethhdr *eth; + int err; bpf_dynptr_from_skb(ctx, 0, &data); eth = bpf_dynptr_slice(&data, 0, NULL, sizeof(*eth)); if (!eth) goto out; /* Ignore non-test packets */ - if (eth->h_proto != 0) + if (!check_smac(eth)) goto out; - /* Expect read-only metadata */ + /* Expect read-write metadata before unclone */ bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (!bpf_dynptr_is_rdonly(&meta) || bpf_dynptr_size(&meta) != META_SIZE) + if (bpf_dynptr_is_rdonly(&meta)) goto out; - /* Metadata write. Expect failure. */ - bpf_dynptr_from_skb_meta(ctx, 0, &meta); - if (bpf_dynptr_write(&meta, 0, "x", 1, 0) != -EINVAL) + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) + goto out; + + /* Helper write to metadata will unclone the packet */ + bpf_dynptr_write(&meta, 0, &meta_have[0], 1, 0); + + err = bpf_dynptr_read(meta_have, META_SIZE, &meta, 0, 0); + if (err || !check_metadata(meta_have)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_vlan_push_pop(struct __sk_buff *ctx) +{ + int err; + + /* bpf_skb_vlan_push assumes HW offload for primary VLAN tag. Only + * secondary tag push triggers an actual MAC header modification. + */ + err = bpf_skb_vlan_push(ctx, 0, 42); + if (err) + goto out; + err = bpf_skb_vlan_push(ctx, 0, 207); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + err = bpf_skb_vlan_pop(ctx); + if (err) + goto out; + err = bpf_skb_vlan_pop(ctx); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_adjust_room(struct __sk_buff *ctx) +{ + int err; + + /* Grow a 1 byte hole after the MAC header */ + err = bpf_skb_adjust_room(ctx, 1, BPF_ADJ_ROOM_MAC, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Shrink a 1 byte hole after the MAC header */ + err = bpf_skb_adjust_room(ctx, -1, BPF_ADJ_ROOM_MAC, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Grow a 256 byte hole to trigger head reallocation */ + err = bpf_skb_adjust_room(ctx, 256, BPF_ADJ_ROOM_MAC, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_change_head_tail(struct __sk_buff *ctx) +{ + int err; + + /* Reserve 1 extra in the front for packet data */ + err = bpf_skb_change_head(ctx, 1, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Reserve 256 extra bytes in the front to trigger head reallocation */ + err = bpf_skb_change_head(ctx, 256, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + /* Reserve 4k extra bytes in the back to trigger head reallocation */ + err = bpf_skb_change_tail(ctx, ctx->len + 4096, 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + test_pass = true; +out: + return TC_ACT_SHOT; +} + +SEC("tc") +int helper_skb_change_proto(struct __sk_buff *ctx) +{ + int err; + + err = bpf_skb_change_proto(ctx, bpf_htons(ETH_P_IPV6), 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) + goto out; + + err = bpf_skb_change_proto(ctx, bpf_htons(ETH_P_IP), 0); + if (err) + goto out; + + if (!check_skb_metadata(ctx)) goto out; test_pass = true; diff --git a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c index ed0a4721d8fd5..1669a7eeda260 100644 --- a/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c +++ b/tools/testing/selftests/bpf/test_kmods/bpf_testmod.c @@ -926,7 +926,7 @@ __bpf_kfunc int bpf_kfunc_call_kernel_connect(struct addr_args *args) goto out; } - err = kernel_connect(sock, (struct sockaddr *)&args->addr, + err = kernel_connect(sock, (struct sockaddr_unsized *)&args->addr, args->addrlen, 0); out: mutex_unlock(&sock_lock); @@ -949,7 +949,7 @@ __bpf_kfunc int bpf_kfunc_call_kernel_bind(struct addr_args *args) goto out; } - err = kernel_bind(sock, (struct sockaddr *)&args->addr, args->addrlen); + err = kernel_bind(sock, (struct sockaddr_unsized *)&args->addr, args->addrlen); out: mutex_unlock(&sock_lock); diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile index 71ee69e524d77..33f4816216ecd 100644 --- a/tools/testing/selftests/drivers/net/Makefile +++ b/tools/testing/selftests/drivers/net/Makefile @@ -23,6 +23,7 @@ TEST_PROGS := \ ping.py \ psp.py \ queues.py \ + ring_reconfig.py \ shaper.py \ stats.py \ xdp.py \ diff --git a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh index c4711272fe45d..f89f8f9eb34d2 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_macvlan_ipvlan.sh @@ -30,9 +30,49 @@ check_connection() local message=${3} RET=0 + ip netns exec ${ns} nstat >/dev/null + ip netns exec ${xvlan2_ns} nstat >/dev/null ip netns exec ${ns} ping ${target} -c 4 -i 0.1 &>/dev/null - check_err $? "ping failed" + R=$? + N=$( ip netns exec ${ns} nstat) + N2=$(ip netns exec ${xvlan2_ns} nstat) + check_err $R "ping failed" log_test "${bond_mode}/${xvlan_type}_${xvlan_mode}: ${message}" + + if [ $R -ne 0 ]; then + echo "===" + echo $O + echo + echo $N + echo + echo $N2 + echo + echo 'local' + ip link + echo + ip addr + echo + ip neigh + echo + ip route + echo 'ns' + ip -s -s -netns ${ns} link + echo + ip -netns ${ns} addr + echo + ip -netns ${ns} neigh + echo + ip -netns ${ns} route + echo 'X ns 2' + ip -s -s -netns ${xvlan2_ns} link + echo + ip -netns ${xvlan2_ns} addr + echo + ip -netns ${xvlan2_ns} neigh + echo + ip -netns ${xvlan2_ns} route + echo "=<=" + fi } xvlan_over_bond() @@ -57,7 +97,7 @@ xvlan_over_bond() ip -n ${xvlan2_ns} addr add ${xvlan2_ip4}/24 dev ${xvlan_type}0 ip -n ${xvlan2_ns} addr add ${xvlan2_ip6}/24 dev ${xvlan_type}0 - sleep 2 + sleep 3 check_connection "${c_ns}" "${s_ip4}" "IPv4: client->server" check_connection "${c_ns}" "${s_ip6}" "IPv6: client->server" diff --git a/tools/testing/selftests/drivers/net/netdevsim/Makefile b/tools/testing/selftests/drivers/net/netdevsim/Makefile index df10c72435119..1a228c5430f58 100644 --- a/tools/testing/selftests/drivers/net/netdevsim/Makefile +++ b/tools/testing/selftests/drivers/net/netdevsim/Makefile @@ -8,7 +8,6 @@ TEST_PROGS := \ ethtool-features.sh \ ethtool-fec.sh \ ethtool-pause.sh \ - ethtool-ring.sh \ fib.sh \ fib_notifications.sh \ hw_stats_l3.sh \ diff --git a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh b/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh deleted file mode 100755 index c969559ffa7a1..0000000000000 --- a/tools/testing/selftests/drivers/net/netdevsim/ethtool-ring.sh +++ /dev/null @@ -1,85 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0-only - -source ethtool-common.sh - -function get_value { - local query="${SETTINGS_MAP[$1]}" - - echo $(ethtool -g $NSIM_NETDEV | \ - tail -n +$CURR_SETT_LINE | \ - awk -F':' -v pattern="$query:" '$0 ~ pattern {gsub(/[\t ]/, "", $2); print $2}') -} - -function update_current_settings { - for key in ${!SETTINGS_MAP[@]}; do - CURRENT_SETTINGS[$key]=$(get_value $key) - done - echo ${CURRENT_SETTINGS[@]} -} - -if ! ethtool -h | grep -q set-ring >/dev/null; then - echo "SKIP: No --set-ring support in ethtool" - exit 4 -fi - -NSIM_NETDEV=$(make_netdev) - -set -o pipefail - -declare -A SETTINGS_MAP=( - ["rx"]="RX" - ["rx-mini"]="RX Mini" - ["rx-jumbo"]="RX Jumbo" - ["tx"]="TX" -) - -declare -A EXPECTED_SETTINGS=( - ["rx"]="" - ["rx-mini"]="" - ["rx-jumbo"]="" - ["tx"]="" -) - -declare -A CURRENT_SETTINGS=( - ["rx"]="" - ["rx-mini"]="" - ["rx-jumbo"]="" - ["tx"]="" -) - -MAX_VALUE=$((RANDOM % $((2**32-1)))) -RING_MAX_LIST=$(ls $NSIM_DEV_DFS/ethtool/ring/) - -for ring_max_entry in $RING_MAX_LIST; do - echo $MAX_VALUE > $NSIM_DEV_DFS/ethtool/ring/$ring_max_entry -done - -CURR_SETT_LINE=$(ethtool -g $NSIM_NETDEV | grep -i -m1 -n 'Current hardware settings' | cut -f1 -d:) - -# populate the expected settings map -for key in ${!SETTINGS_MAP[@]}; do - EXPECTED_SETTINGS[$key]=$(get_value $key) -done - -# test -for key in ${!SETTINGS_MAP[@]}; do - value=$((RANDOM % $MAX_VALUE)) - - ethtool -G $NSIM_NETDEV "$key" "$value" - - EXPECTED_SETTINGS[$key]="$value" - expected=${EXPECTED_SETTINGS[@]} - current=$(update_current_settings) - - check $? "$current" "$expected" - set +x -done - -if [ $num_errors -eq 0 ]; then - echo "PASSED all $((num_passes)) checks" - exit 0 -else - echo "FAILED $num_errors/$((num_errors+num_passes)) checks" - exit 1 -fi diff --git a/tools/testing/selftests/drivers/net/psp.py b/tools/testing/selftests/drivers/net/psp.py index 4ae7a785ff10a..06559ef49b9a5 100755 --- a/tools/testing/selftests/drivers/net/psp.py +++ b/tools/testing/selftests/drivers/net/psp.py @@ -109,6 +109,10 @@ def _check_data_outq(s, exp_len, force_wait=False): time.sleep(0.01) ksft_eq(outq, exp_len) + +def _get_stat(cfg, key): + return cfg.pspnl.get_stats({'dev-id': cfg.psp_dev_id})[key] + # # Test case boiler plate # @@ -171,11 +175,16 @@ def dev_rotate(cfg): """ Test key rotation """ _init_psp_dev(cfg) + prev_rotations = _get_stat(cfg, 'key-rotations') + rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) ksft_eq(rot['id'], cfg.psp_dev_id) rot = cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) ksft_eq(rot['id'], cfg.psp_dev_id) + cur_rotations = _get_stat(cfg, 'key-rotations') + ksft_eq(cur_rotations, prev_rotations + 2) + def dev_rotate_spi(cfg): """ Test key rotation and SPI check """ @@ -475,6 +484,7 @@ def data_stale_key(cfg): """ Test send on a double-rotated key """ _init_psp_dev(cfg) + prev_stale = _get_stat(cfg, 'stale-events') s = _make_psp_conn(cfg) try: rx_assoc = cfg.pspnl.rx_assoc({"version": 0, @@ -495,6 +505,9 @@ def data_stale_key(cfg): cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) cfg.pspnl.key_rotate({"id": cfg.psp_dev_id}) + cur_stale = _get_stat(cfg, 'stale-events') + ksft_gt(cur_stale, prev_stale) + s.send(b'0123456789' * 200) _check_data_outq(s, 2000, force_wait=True) finally: diff --git a/tools/testing/selftests/drivers/net/ring_reconfig.py b/tools/testing/selftests/drivers/net/ring_reconfig.py new file mode 100755 index 0000000000000..f9530a8b08567 --- /dev/null +++ b/tools/testing/selftests/drivers/net/ring_reconfig.py @@ -0,0 +1,167 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Test channel and ring size configuration via ethtool (-L / -G). +""" + +from lib.py import ksft_run, ksft_exit, ksft_pr +from lib.py import ksft_eq +from lib.py import NetDrvEpEnv, EthtoolFamily, GenerateTraffic +from lib.py import defer, NlError + + +def channels(cfg) -> None: + """ + Twiddle channel counts in various combinations of parameters. + We're only looking for driver adhering to the requested config + if the config is accepted and crashes. + """ + ehdr = {'header':{'dev-index': cfg.ifindex}} + chans = cfg.eth.channels_get(ehdr) + + all_keys = ["rx", "tx", "combined"] + mixes = [{"combined"}, {"rx", "tx"}, {"rx", "combined"}, {"tx", "combined"}, + {"rx", "tx", "combined"},] + + # Get the set of keys that device actually supports + restore = {} + supported = set() + for key in all_keys: + if key + "-max" in chans: + supported.add(key) + restore |= {key + "-count": chans[key + "-count"]} + + defer(cfg.eth.channels_set, ehdr | restore) + + def test_config(config): + try: + cfg.eth.channels_set(ehdr | config) + get = cfg.eth.channels_get(ehdr) + for k, v in config.items(): + ksft_eq(get.get(k, 0), v) + except NlError as e: + failed.append(mix) + ksft_pr("Can't set", config, e) + else: + ksft_pr("Okay", config) + + failed = [] + for mix in mixes: + if not mix.issubset(supported): + continue + + # Set all the values in the mix to 1, other supported to 0 + config = {} + for key in all_keys: + config[key + "-count"] = 1 if key in mix else 0 + test_config(config) + + for mix in mixes: + if not mix.issubset(supported): + continue + if mix in failed: + continue + + # Set all the values in the mix to max, other supported to 0 + config = {} + for key in all_keys: + config[key + "-count"] = chans[key + '-max'] if key in mix else 0 + test_config(config) + + +def _configure_min_ring_cnt(cfg) -> None: + """ Try to configure a single Rx/Tx ring. """ + ehdr = {'header':{'dev-index': cfg.ifindex}} + chans = cfg.eth.channels_get(ehdr) + + all_keys = ["rx-count", "tx-count", "combined-count"] + restore = {} + config = {} + for key in all_keys: + if key in chans: + restore[key] = chans[key] + config[key] = 0 + + if chans.get('combined-count', 0) > 1: + config['combined-count'] = 1 + elif chans.get('rx-count', 0) > 1 and chans.get('tx-count', 0) > 1: + config['tx-count'] = 1 + config['rx-count'] = 1 + else: + # looks like we're already on 1 channel + return + + cfg.eth.channels_set(ehdr | config) + defer(cfg.eth.channels_set, ehdr | restore) + + +def ringparam(cfg) -> None: + """ + Tweak the ringparam configuration. Try to run some traffic over min + ring size to make sure it actually functions. + """ + ehdr = {'header':{'dev-index': cfg.ifindex}} + rings = cfg.eth.rings_get(ehdr) + + restore = {} + maxes = {} + params = set() + for key in rings.keys(): + if 'max' in key: + param = key[:-4] + maxes[param] = rings[key] + params.add(param) + restore[param] = rings[param] + + defer(cfg.eth.rings_set, ehdr | restore) + + # Speed up the reconfig by configuring just one ring + _configure_min_ring_cnt(cfg) + + # Try to reach min on all settings + for param in params: + val = rings[param] + while True: + try: + cfg.eth.rings_set({'header':{'dev-index': cfg.ifindex}, + param: val // 2}) + if val == 0: + break + val //= 2 + except NlError: + break + + get = cfg.eth.rings_get(ehdr) + ksft_eq(get[param], val) + + ksft_pr(f"Reached min for '{param}' at {val} (max {rings[param]})") + + GenerateTraffic(cfg).wait_pkts_and_stop(10000) + + # Try max across all params, if the driver supports large rings + # this may OOM so we ignore errors + try: + ksft_pr("Applying max settings") + config = {p: maxes[p] for p in params} + cfg.eth.rings_set(ehdr | config) + except NlError as e: + ksft_pr("Can't set max params", config, e) + else: + GenerateTraffic(cfg).wait_pkts_and_stop(10000) + + +def main() -> None: + """ Ksft boiler plate main """ + + with NetDrvEpEnv(__file__) as cfg: + cfg.eth = EthtoolFamily() + + ksft_run([channels, + ringparam], + args=(cfg, )) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/settings b/tools/testing/selftests/drivers/net/settings new file mode 100644 index 0000000000000..a953c96aa16e1 --- /dev/null +++ b/tools/testing/selftests/drivers/net/settings @@ -0,0 +1 @@ +timeout=180 diff --git a/tools/testing/selftests/drivers/net/stats.py b/tools/testing/selftests/drivers/net/stats.py index 04d0a2a13e736..b08e4d48b15ce 100755 --- a/tools/testing/selftests/drivers/net/stats.py +++ b/tools/testing/selftests/drivers/net/stats.py @@ -263,14 +263,15 @@ def procfs_downup_hammer(cfg) -> None: Reading stats via procfs only holds the RCU lock, drivers often try to sleep when reading the stats, or don't protect against races. """ - # Max out the queues, we'll flip between max and 1 + # Set a large number of queues, + # we'll flip between min(max_queues, 64) and 1 channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}}) if channels['combined-count'] == 0: rx_type = 'rx' else: rx_type = 'combined' cur_queue_cnt = channels[f'{rx_type}-count'] - max_queue_cnt = channels[f'{rx_type}-max'] + max_queue_cnt = min(channels[f'{rx_type}-max'], 64) cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}") defer(cmd, f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}") diff --git a/tools/testing/selftests/drivers/net/xdp.py b/tools/testing/selftests/drivers/net/xdp.py index a148004e1c36a..834a37ae7d0d4 100755 --- a/tools/testing/selftests/drivers/net/xdp.py +++ b/tools/testing/selftests/drivers/net/xdp.py @@ -687,9 +687,12 @@ def _test_xdp_native_ifc_stats(cfg, act): "/dev/null" # Listener runs on "remote" in case of XDP_TX rx_host = cfg.remote if act == XDPAction.TX else None - # We want to spew 2000 packets quickly, bash seems to do a good enough job - tx_udp = f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ - "for i in `seq 2000`; do echo a >&5; done; exec 5>&-" + # We want to spew 1000 packets quickly, bash seems to do a good enough job + # Each reopening of the socket gives us a differenot local port (for RSS) + tx_udp = "for _ in `seq 20`; do " \ + f"exec 5<>/dev/udp/{cfg.addr}/{port}; " \ + "for i in `seq 50`; do echo a >&5; done; " \ + "exec 5>&-; done" cfg.wait_hw_stats_settle() # Qstats have more clearly defined semantics than rtnetlink. @@ -704,11 +707,11 @@ def _test_xdp_native_ifc_stats(cfg, act): cfg.wait_hw_stats_settle() after = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0] - ksft_ge(after['rx-packets'] - before['rx-packets'], 2000) + expected_pkts = 1000 + ksft_ge(after['rx-packets'] - before['rx-packets'], expected_pkts) if act == XDPAction.TX: - ksft_ge(after['tx-packets'] - before['tx-packets'], 2000) + ksft_ge(after['tx-packets'] - before['tx-packets'], expected_pkts) - expected_pkts = 2000 stats = _get_stats(prog_info["maps"]["map_xdp_stats"]) ksft_eq(stats[XDPStats.RX.value], expected_pkts, "XDP RX stats mismatch") if act == XDPAction.TX: diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl index 12a7f4ca2684d..b8e4d697e3b3a 100755 --- a/tools/testing/selftests/kselftest/prefix.pl +++ b/tools/testing/selftests/kselftest/prefix.pl @@ -4,12 +4,15 @@ # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd". use strict; use IO::Handle; +use Time::HiRes qw( time ); binmode STDIN; binmode STDOUT; STDOUT->autoflush(1); +my $start_time = time(); +my $prev_time = $start_time; my $needed = 1; while (1) { my $char; @@ -17,6 +20,11 @@ exit 0 if ($bytes == 0); if ($needed) { print "# "; + if ($ENV{kselftest_profile}) { + my $now = time(); + printf("%.2f [+%.2f] ", $now - $start_time, $now - $prev_time); + $prev_time = $now; + } $needed = 0; } print $char; diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh index 2c3c58e65a419..e65bffb9981f8 100644 --- a/tools/testing/selftests/kselftest/runner.sh +++ b/tools/testing/selftests/kselftest/runner.sh @@ -89,7 +89,7 @@ run_one() fi field=$(echo "$line" | cut -d= -f1) value=$(echo "$line" | cut -d= -f2-) - eval "kselftest_$field"="$value" + eval "export kselftest_$field"="$value" done < "$settings" fi diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index 439101b518eee..e89a60581a135 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -65,3 +65,4 @@ udpgso udpgso_bench_rx udpgso_bench_tx unix_connect +unix_connreset diff --git a/tools/testing/selftests/net/af_unix/Makefile b/tools/testing/selftests/net/af_unix/Makefile index de805cbbdf693..5826a83724518 100644 --- a/tools/testing/selftests/net/af_unix/Makefile +++ b/tools/testing/selftests/net/af_unix/Makefile @@ -7,6 +7,7 @@ TEST_GEN_PROGS := \ scm_pidfd \ scm_rights \ unix_connect \ + unix_connreset \ # end of TEST_GEN_PROGS include ../../lib.mk diff --git a/tools/testing/selftests/net/af_unix/unix_connreset.c b/tools/testing/selftests/net/af_unix/unix_connreset.c new file mode 100644 index 0000000000000..bffef2b54bfd1 --- /dev/null +++ b/tools/testing/selftests/net/af_unix/unix_connreset.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Selftest for AF_UNIX socket close and ECONNRESET behaviour. + * + * This test verifies: + * 1. SOCK_STREAM returns EOF when the peer closes normally. + * 2. SOCK_STREAM returns ECONNRESET if peer closes with unread data. + * 3. SOCK_SEQPACKET returns EOF when the peer closes normally. + * 4. SOCK_SEQPACKET returns ECONNRESET if the peer closes with unread data. + * 5. SOCK_DGRAM does not return ECONNRESET when the peer closes. + * + * These tests document the intended Linux behaviour. + * + */ + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include "../../kselftest_harness.h" + +#define SOCK_PATH "/tmp/af_unix_connreset.sock" + +static void remove_socket_file(void) +{ + unlink(SOCK_PATH); +} + +FIXTURE(unix_sock) +{ + int server; + int client; + int child; +}; + +FIXTURE_VARIANT(unix_sock) +{ + int socket_type; + const char *name; +}; + +FIXTURE_VARIANT_ADD(unix_sock, stream) { + .socket_type = SOCK_STREAM, + .name = "SOCK_STREAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, dgram) { + .socket_type = SOCK_DGRAM, + .name = "SOCK_DGRAM", +}; + +FIXTURE_VARIANT_ADD(unix_sock, seqpacket) { + .socket_type = SOCK_SEQPACKET, + .name = "SOCK_SEQPACKET", +}; + +FIXTURE_SETUP(unix_sock) +{ + struct sockaddr_un addr = {}; + int err; + + addr.sun_family = AF_UNIX; + strcpy(addr.sun_path, SOCK_PATH); + remove_socket_file(); + + self->server = socket(AF_UNIX, variant->socket_type, 0); + ASSERT_LT(-1, self->server); + + err = bind(self->server, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + err = listen(self->server, 1); + ASSERT_EQ(0, err); + } + + self->client = socket(AF_UNIX, variant->socket_type | SOCK_NONBLOCK, 0); + ASSERT_LT(-1, self->client); + + err = connect(self->client, (struct sockaddr *)&addr, sizeof(addr)); + ASSERT_EQ(0, err); +} + +FIXTURE_TEARDOWN(unix_sock) +{ + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) + close(self->child); + + close(self->client); + close(self->server); + remove_socket_file(); +} + +/* Test 1: peer closes normally */ +TEST_F(unix_sock, eof) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + close(self->child); + } else { + close(self->server); + } + + n = recv(self->client, buf, sizeof(buf), 0); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(0, n); + } else { + ASSERT_EQ(-1, n); + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 2: peer closes with unread data */ +TEST_F(unix_sock, reset_unread_behavior) +{ + char buf[16] = {}; + ssize_t n; + + /* Send data that will remain unread */ + send(self->client, "hello", 5, 0); + + if (variant->socket_type == SOCK_DGRAM) { + /* No real connection, just close the server */ + close(self->server); + } else { + self->child = accept(self->server, NULL, NULL); + ASSERT_LT(-1, self->child); + + /* Peer closes before client reads */ + close(self->child); + } + + n = recv(self->client, buf, sizeof(buf), 0); + ASSERT_EQ(-1, n); + + if (variant->socket_type == SOCK_STREAM || + variant->socket_type == SOCK_SEQPACKET) { + ASSERT_EQ(ECONNRESET, errno); + } else { + ASSERT_EQ(EAGAIN, errno); + } +} + +/* Test 3: closing unaccepted (embryo) server socket should reset client. */ +TEST_F(unix_sock, reset_closed_embryo) +{ + char buf[16] = {}; + ssize_t n; + + if (variant->socket_type == SOCK_DGRAM) + SKIP(return, "This test only applies to SOCK_STREAM and SOCK_SEQPACKET"); + + /* Close server without accept()ing */ + close(self->server); + + n = recv(self->client, buf, sizeof(buf), 0); + + ASSERT_EQ(-1, n); + ASSERT_EQ(ECONNRESET, errno); +} + +TEST_HARNESS_MAIN + diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh index 7d2d40812074f..5ec1c85c1623e 100755 --- a/tools/testing/selftests/net/busy_poll_test.sh +++ b/tools/testing/selftests/net/busy_poll_test.sh @@ -27,6 +27,8 @@ NAPI_DEFER_HARD_IRQS=100 GRO_FLUSH_TIMEOUT=50000 SUSPEND_TIMEOUT=20000000 +NAPI_THREADED_MODE_BUSY_POLL=2 + setup_ns() { set -e @@ -62,6 +64,9 @@ cleanup_ns() test_busypoll() { suspend_value=${1:-0} + napi_threaded_value=${2:-0} + prefer_busy_poll_value=${3:-$PREFER_BUSY_POLL} + tmp_file=$(mktemp) out_file=$(mktemp) @@ -73,10 +78,11 @@ test_busypoll() -b${SERVER_IP} \ -m${MAX_EVENTS} \ -u${BUSY_POLL_USECS} \ - -P${PREFER_BUSY_POLL} \ + -P${prefer_busy_poll_value} \ -g${BUSY_POLL_BUDGET} \ -i${NSIM_SV_IFIDX} \ -s${suspend_value} \ + -t${napi_threaded_value} \ -o${out_file}& wait_local_port_listen nssv ${SERVER_PORT} tcp @@ -109,6 +115,15 @@ test_busypoll_with_suspend() return $? } +test_busypoll_with_napi_threaded() +{ + # Only enable napi threaded poll. Set suspend timeout and prefer busy + # poll to 0. + test_busypoll 0 ${NAPI_THREADED_MODE_BUSY_POLL} 0 + + return $? +} + ### ### Code start ### @@ -154,6 +169,13 @@ if [ $? -ne 0 ]; then exit 1 fi +test_busypoll_with_napi_threaded +if [ $? -ne 0 ]; then + echo "test_busypoll_with_napi_threaded failed" + cleanup_ns + exit 1 +fi + echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c index 04c7ff577bb89..3a81f9c947950 100644 --- a/tools/testing/selftests/net/busy_poller.c +++ b/tools/testing/selftests/net/busy_poller.c @@ -65,15 +65,16 @@ static uint32_t cfg_busy_poll_usecs; static uint16_t cfg_busy_poll_budget; static uint8_t cfg_prefer_busy_poll; -/* IRQ params */ +/* NAPI params */ static uint32_t cfg_defer_hard_irqs; static uint64_t cfg_gro_flush_timeout; static uint64_t cfg_irq_suspend_timeout; +static enum netdev_napi_threaded cfg_napi_threaded_poll = NETDEV_NAPI_THREADED_DISABLED; static void usage(const char *filepath) { error(1, 0, - "Usage: %s -p -b -m -u -P -g -o -d -r -s -i", + "Usage: %s -p -b -m -u -P -g -o -d -r -s -t -i", filepath); } @@ -86,7 +87,7 @@ static void parse_opts(int argc, char **argv) if (argc <= 1) usage(argv[0]); - while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) { + while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:t:")) != -1) { /* most options take integer values, except o and b, so reduce * code duplication a bit for the common case by calling * strtoull here and leave bounds checking and casting per @@ -168,6 +169,12 @@ static void parse_opts(int argc, char **argv) cfg_ifindex = (int)tmp; break; + case 't': + if (tmp > 2) + error(1, ERANGE, "napi threaded poll value must be 0-2"); + + cfg_napi_threaded_poll = (enum netdev_napi_threaded)tmp; + break; } } @@ -247,6 +254,9 @@ static void setup_queue(void) netdev_napi_set_req_set_irq_suspend_timeout(set_req, cfg_irq_suspend_timeout); + if (cfg_napi_threaded_poll) + netdev_napi_set_req_set_threaded(set_req, cfg_napi_threaded_poll); + if (netdev_napi_set(ys, set_req)) error(1, 0, "can't set NAPI params: %s\n", yerr.msg); diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index a94b73a53f72e..a88f797c549a7 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -11,7 +11,8 @@ TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify \ ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics \ ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr \ ipv6_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh fib6_gc_test \ - ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance" + ipv4_mpath_list ipv6_mpath_list ipv4_mpath_balance ipv6_mpath_balance \ + fib6_ra_to_static" VERBOSE=0 PAUSE_ON_FAIL=no @@ -1476,6 +1477,68 @@ ipv6_route_metrics_test() route_cleanup } +fib6_ra_to_static() +{ + setup + + echo + echo "Fib6 route promotion from RA-learned to static test" + set -e + + # ra6 is required for the test. (ipv6toolkit) + if [ ! -x "$(command -v ra6)" ]; then + echo "SKIP: ra6 not found." + set +e + cleanup &> /dev/null + return + fi + + # Create a pair of veth devices to send a RA message from one + # device to another. + $IP link add veth1 type veth peer name veth2 + $IP link set dev veth1 up + $IP link set dev veth2 up + $IP -6 address add 2001:10::1/64 dev veth1 nodad + $IP -6 address add 2001:10::2/64 dev veth2 nodad + + # Make veth1 ready to receive RA messages. + $NS_EXEC sysctl -wq net.ipv6.conf.veth1.accept_ra=2 + + # Send a RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + + # Wait for the RA message. + sleep 1 + + # systemd may mess up the test. Make sure that + # systemd-networkd.service and systemd-networkd.socket are stopped. + check_rt_num_clean 2 $($IP -6 route list|grep expires|wc -l) || return + + # Configure static address on the same prefix + $IP -6 address add 2001:12::dead/64 dev veth1 nodad + + # On-link route won't expire anymore, default route still owned by RA + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + # Send a second RA message with a prefix from veth2. + $NS_EXEC ra6 -i veth2 -d 2001:10::1 -P 2001:12::/64\#LA\#120\#60 + sleep 1 + + # Expire is not back, on-link route is still static + check_rt_num 1 $($IP -6 route list |grep expires|wc -l) + + $IP -6 address del 2001:12::dead/64 dev veth1 nodad + + # Expire is back, on-link route is now owned by RA again + check_rt_num 2 $($IP -6 route list |grep expires|wc -l) + + log_test $ret 0 "ipv6 promote RA route to static" + + set +e + + cleanup &> /dev/null +} + # add route for a prefix, flushing any existing routes first # expected to be the first step of a test add_route() @@ -2798,6 +2861,7 @@ do ipv6_mpath_list) ipv6_mpath_list_test;; ipv4_mpath_balance) ipv4_mpath_balance_test;; ipv6_mpath_balance) ipv6_mpath_balance_test;; + fib6_ra_to_static) fib6_ra_to_static;; help) echo "Test names: $TESTS"; exit 0;; esac diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh index 8c1597ebc2d38..e86d779465853 100755 --- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh +++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh @@ -28,6 +28,7 @@ ALL_TESTS=" cfg_test fwd_test ctrl_test + disable_test " NUM_NETIFS=4 @@ -64,7 +65,10 @@ h2_destroy() switch_create() { - ip link add name br0 type bridge vlan_filtering 1 vlan_default_pvid 0 \ + local vlan_filtering=$1; shift + + ip link add name br0 type bridge \ + vlan_filtering "$vlan_filtering" vlan_default_pvid 0 \ mcast_snooping 1 mcast_igmp_version 3 mcast_mld_version 2 bridge vlan add vid 10 dev br0 self bridge vlan add vid 20 dev br0 self @@ -118,7 +122,7 @@ setup_prepare() h1_create h2_create - switch_create + switch_create 1 } cleanup() @@ -1357,6 +1361,98 @@ ctrl_test() ctrl_mldv2_is_in_test } +check_group() +{ + local group=$1; shift + local vid=$1; shift + local should_fail=$1; shift + local when=$1; shift + local -a vidkws + + if ((vid)); then + vidkws=(vid "$vid") + fi + + bridge mdb get dev br0 grp "$group" "${vidkws[@]}" 2>/dev/null | + grep -q "port $swp1" + check_err_fail "$should_fail" $? "$group seen $when snooping disable:" +} + +__disable_test() +{ + local vid=$1; shift + local what=$1; shift + local -a vidkws + + if ((vid)); then + vidkws=(vid "$vid") + fi + + RET=0 + + bridge mdb add dev br0 port "$swp1" grp ff0e::1 permanent \ + "${vidkws[@]}" filter_mode include source_list 2001:db8:1::1 + bridge mdb add dev br0 port "$swp1" grp ff0e::2 permanent \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp ff0e::3 \ + "${vidkws[@]}" filter_mode include source_list 2001:db8:1::2 + bridge mdb add dev br0 port "$swp1" grp ff0e::4 \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp 239.1.1.1 permanent \ + "${vidkws[@]}" filter_mode include source_list 192.0.2.1 + bridge mdb add dev br0 port "$swp1" grp 239.1.1.2 permanent \ + "${vidkws[@]}" filter_mode exclude + + bridge mdb add dev br0 port "$swp1" grp 239.1.1.3 \ + "${vidkws[@]}" filter_mode include source_list 192.0.2.2 + bridge mdb add dev br0 port "$swp1" grp 239.1.1.4 \ + "${vidkws[@]}" filter_mode exclude + + check_group ff0e::1 "$vid" 0 "before" + check_group ff0e::2 "$vid" 0 "before" + check_group ff0e::3 "$vid" 0 "before" + check_group ff0e::4 "$vid" 0 "before" + + check_group 239.1.1.1 "$vid" 0 "before" + check_group 239.1.1.2 "$vid" 0 "before" + check_group 239.1.1.3 "$vid" 0 "before" + check_group 239.1.1.4 "$vid" 0 "before" + + ip link set dev br0 type bridge mcast_snooping 0 + + check_group ff0e::1 "$vid" 0 "after" + check_group ff0e::2 "$vid" 0 "after" + check_group ff0e::3 "$vid" 1 "after" + check_group ff0e::4 "$vid" 1 "after" + + check_group 239.1.1.1 "$vid" 0 "after" + check_group 239.1.1.2 "$vid" 0 "after" + check_group 239.1.1.3 "$vid" 1 "after" + check_group 239.1.1.4 "$vid" 1 "after" + + log_test "$what: Flush after disable" + + ip link set dev br0 type bridge mcast_snooping 1 + sleep 10 +} + +disable_test() +{ + __disable_test 10 802.1q + + switch_destroy + switch_create 0 + setup_wait + + __disable_test 0 802.1d + + switch_destroy + switch_create 1 + setup_wait +} + if ! bridge mdb help 2>&1 | grep -q "flush"; then echo "SKIP: iproute2 too old, missing bridge mdb flush support" exit $ksft_skip diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings index e7b9417537fbc..ff3de4936a009 100644 --- a/tools/testing/selftests/net/forwarding/settings +++ b/tools/testing/selftests/net/forwarding/settings @@ -1 +1,2 @@ -timeout=0 +timeout=10800 +profile=1 diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index ea89e558672db..5823d94b19e9b 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -223,19 +223,32 @@ mirred_egress_to_ingress_tcp_test() ip_proto icmp \ action drop - ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & - local rpid=$! - ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 - wait -n $rpid - cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 - check_err $? "server output check failed" + echo P2 $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ -t icmp "ping,id=42,seq=5" -q + echo P2.1 tc_check_packets "dev $h1 egress" 101 10 check_err $? "didn't mirred redirect ICMP" + echo P2.2 tc_check_packets "dev $h1 ingress" 102 10 check_err $? "didn't drop mirred ICMP" + echo P2.3 + + echo P1 + + ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 & + local rpid=$! + sleep 0.2 + echo P1.1 + ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1 + echo P1.2 + sleep 0.2 + wait -n $rpid + cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2 + check_err $? "server output check failed" + + echo P3 tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower @@ -359,4 +372,5 @@ else tests_run fi +dmesg exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c index cfc39f70635df..50bf1b96ea9d2 100644 --- a/tools/testing/selftests/net/gro.c +++ b/tools/testing/selftests/net/gro.c @@ -11,8 +11,8 @@ * 2.ack * Pure ACK does not coalesce. * 3.flags - * Specific test cases: no packets with PSH, SYN, URG, RST set will - * be coalesced. + * Specific test cases: no packets with PSH, SYN, URG, RST, CWR set + * will be coalesced. * 4.tcp * Packets with incorrect checksum, non-consecutive seqno and * different TCP header options shouldn't coalesce. Nit: given that @@ -332,32 +332,57 @@ static void create_packet(void *buf, int seq_offset, int ack_offset, fill_datalinklayer(buf); } -/* send one extra flag, not first and not last pkt */ -static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, - int rst, int urg) +#ifndef TH_CWR +#define TH_CWR 0x80 +#endif +static void set_flags(struct tcphdr *tcph, int payload_len, int psh, int syn, + int rst, int urg, int cwr) { - static char flag_buf[MAX_HDR_LEN + PAYLOAD_LEN]; - static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; - int payload_len, pkt_size, flag, i; - struct tcphdr *tcph; - - payload_len = PAYLOAD_LEN * psh; - pkt_size = total_hdr_len + payload_len; - flag = NUM_PACKETS / 2; - - create_packet(flag_buf, flag * payload_len, 0, payload_len, 0); - - tcph = (struct tcphdr *)(flag_buf + tcp_offset); tcph->psh = psh; tcph->syn = syn; tcph->rst = rst; tcph->urg = urg; + if (cwr) + tcph->th_flags |= TH_CWR; + else + tcph->th_flags &= ~TH_CWR; tcph->check = 0; tcph->check = tcp_checksum(tcph, payload_len); +} + +/* send extra flags of the (NUM_PACKETS / 2) and (NUM_PACKETS / 2 - 1) + * pkts, not first and not last pkt + */ +static void send_flags(int fd, struct sockaddr_ll *daddr, int psh, int syn, + int rst, int urg, int cwr) +{ + static char flag_buf[2][MAX_HDR_LEN + PAYLOAD_LEN]; + static char buf[MAX_HDR_LEN + PAYLOAD_LEN]; + int payload_len, pkt_size, i; + struct tcphdr *tcph; + int flag[2]; + + payload_len = PAYLOAD_LEN * (psh || cwr); + pkt_size = total_hdr_len + payload_len; + flag[0] = NUM_PACKETS / 2; + flag[1] = NUM_PACKETS / 2 - 1; + + // Create and configure packets with flags + for (i = 0; i < 2; i++) { + if (flag[i] > 0) { + create_packet(flag_buf[i], flag[i] * payload_len, 0, + payload_len, 0); + tcph = (struct tcphdr *)(flag_buf[i] + tcp_offset); + set_flags(tcph, payload_len, psh, syn, rst, urg, cwr); + } + } for (i = 0; i < NUM_PACKETS + 1; i++) { - if (i == flag) { - write_packet(fd, flag_buf, pkt_size, daddr); + if (i == flag[0]) { + write_packet(fd, flag_buf[0], pkt_size, daddr); + continue; + } else if (i == flag[1] && cwr) { + write_packet(fd, flag_buf[1], pkt_size, daddr); continue; } create_packet(buf, i * PAYLOAD_LEN, 0, PAYLOAD_LEN, 0); @@ -1020,16 +1045,19 @@ static void gro_sender(void) send_ack(txfd, &daddr); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "flags") == 0) { - send_flags(txfd, &daddr, 1, 0, 0, 0); + send_flags(txfd, &daddr, 1, 0, 0, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - send_flags(txfd, &daddr, 0, 1, 0, 0); + send_flags(txfd, &daddr, 0, 1, 0, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - send_flags(txfd, &daddr, 0, 0, 1, 0); + send_flags(txfd, &daddr, 0, 0, 1, 0, 0); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); - send_flags(txfd, &daddr, 0, 0, 0, 1); + send_flags(txfd, &daddr, 0, 0, 0, 1, 0); + write_packet(txfd, fin_pkt, total_hdr_len, &daddr); + + send_flags(txfd, &daddr, 0, 0, 0, 0, 1); write_packet(txfd, fin_pkt, total_hdr_len, &daddr); } else if (strcmp(testname, "tcp") == 0) { send_changed_checksum(txfd, &daddr); @@ -1163,6 +1191,12 @@ static void gro_receiver(void) printf("urg flag ends coalescing: "); check_recv_pkts(rxfd, correct_payload, 3); + + correct_payload[0] = PAYLOAD_LEN; + correct_payload[1] = PAYLOAD_LEN * 2; + correct_payload[2] = PAYLOAD_LEN * 2; + printf("cwr flag ends coalescing: "); + check_recv_pkts(rxfd, correct_payload, 3); } else if (strcmp(testname, "tcp") == 0) { correct_payload[0] = PAYLOAD_LEN; correct_payload[1] = PAYLOAD_LEN; diff --git a/tools/testing/selftests/net/io_uring_zerocopy_tx.c b/tools/testing/selftests/net/io_uring_zerocopy_tx.c index 76e604e4810e1..7bfeeb1337054 100644 --- a/tools/testing/selftests/net/io_uring_zerocopy_tx.c +++ b/tools/testing/selftests/net/io_uring_zerocopy_tx.c @@ -106,14 +106,14 @@ static void do_tx(int domain, int type, int protocol) ret = io_uring_queue_init(512, &ring, 0); if (ret) - error(1, ret, "io_uring: queue init"); + error(1, -ret, "io_uring: queue init"); iov.iov_base = payload; iov.iov_len = cfg_payload_len; ret = io_uring_register_buffers(&ring, &iov, 1); if (ret) - error(1, ret, "io_uring: buffer registration"); + error(1, -ret, "io_uring: buffer registration"); tstop = gettimeofday_ms() + cfg_runtime_ms; do { @@ -149,24 +149,24 @@ static void do_tx(int domain, int type, int protocol) ret = io_uring_submit(&ring); if (ret != cfg_nr_reqs) - error(1, ret, "submit"); + error(1, -ret, "submit"); if (cfg_cork) do_setsockopt(fd, IPPROTO_UDP, UDP_CORK, 0); for (i = 0; i < cfg_nr_reqs; i++) { ret = io_uring_wait_cqe(&ring, &cqe); if (ret) - error(1, ret, "wait cqe"); + error(1, -ret, "wait cqe"); if (cqe->user_data != NONZC_TAG && cqe->user_data != ZC_TAG) - error(1, -EINVAL, "invalid cqe->user_data"); + error(1, EINVAL, "invalid cqe->user_data"); if (cqe->flags & IORING_CQE_F_NOTIF) { if (cqe->flags & IORING_CQE_F_MORE) - error(1, -EINVAL, "invalid notif flags"); + error(1, EINVAL, "invalid notif flags"); if (compl_cqes <= 0) - error(1, -EINVAL, "notification mismatch"); + error(1, EINVAL, "notification mismatch"); compl_cqes--; i--; io_uring_cqe_seen(&ring); @@ -174,14 +174,14 @@ static void do_tx(int domain, int type, int protocol) } if (cqe->flags & IORING_CQE_F_MORE) { if (cqe->user_data != ZC_TAG) - error(1, cqe->res, "unexpected F_MORE"); + error(1, -cqe->res, "unexpected F_MORE"); compl_cqes++; } if (cqe->res >= 0) { packets++; bytes += cqe->res; } else if (cqe->res != -EAGAIN) { - error(1, cqe->res, "send failed"); + error(1, -cqe->res, "send failed"); } io_uring_cqe_seen(&ring); } @@ -190,11 +190,11 @@ static void do_tx(int domain, int type, int protocol) while (compl_cqes) { ret = io_uring_wait_cqe(&ring, &cqe); if (ret) - error(1, ret, "wait cqe"); + error(1, -ret, "wait cqe"); if (cqe->flags & IORING_CQE_F_MORE) - error(1, -EINVAL, "invalid notif flags"); + error(1, EINVAL, "invalid notif flags"); if (!(cqe->flags & IORING_CQE_F_NOTIF)) - error(1, -EINVAL, "missing notif flag"); + error(1, EINVAL, "missing notif flag"); io_uring_cqe_seen(&ring); compl_cqes--; diff --git a/tools/testing/selftests/net/lib/xdp_native.bpf.c b/tools/testing/selftests/net/lib/xdp_native.bpf.c index c368fc045f4b4..64f05229ab243 100644 --- a/tools/testing/selftests/net/lib/xdp_native.bpf.c +++ b/tools/testing/selftests/net/lib/xdp_native.bpf.c @@ -332,7 +332,7 @@ static __u16 csum_fold_helper(__u32 csum) } static int xdp_adjst_tail_shrnk_data(struct xdp_md *ctx, __u16 offset, - __u32 hdr_len) + unsigned long hdr_len) { char tmp_buff[MAX_ADJST_OFFSET]; __u32 buff_pos, udp_csum = 0; @@ -422,8 +422,9 @@ static int xdp_adjst_tail(struct xdp_md *ctx, __u16 port) { struct udphdr *udph = NULL; __s32 *adjust_offset, *val; - __u32 key, hdr_len; + unsigned long hdr_len; void *offset_ptr; + __u32 key; __u8 tag; int ret; diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index fc7e22b503d3b..404a77bf366a8 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1072,6 +1072,8 @@ static void check_getpeername_connect(int fd) socklen_t salen = sizeof(ss); char a[INET6_ADDRSTRLEN]; char b[INET6_ADDRSTRLEN]; + const char *iface; + size_t len; if (getpeername(fd, (struct sockaddr *)&ss, &salen) < 0) { perror("getpeername"); @@ -1081,7 +1083,13 @@ static void check_getpeername_connect(int fd) xgetnameinfo((struct sockaddr *)&ss, salen, a, sizeof(a), b, sizeof(b)); - if (strcmp(cfg_host, a) || strcmp(cfg_port, b)) + iface = strchr(cfg_host, '%'); + if (iface) + len = iface - cfg_host; + else + len = strlen(cfg_host) + 1; + + if (strncmp(cfg_host, a, len) || strcmp(cfg_port, b)) fprintf(stderr, "%s: %s vs %s, %s vs %s\n", __func__, cfg_host, a, cfg_port, b); } diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.sh b/tools/testing/selftests/net/mptcp/mptcp_connect.sh index 9b7b93f8eb0c3..a6447f7a31fe5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.sh @@ -375,81 +375,75 @@ do_transfer() local capfile="${rndh}-${connector_ns:0:3}-${listener_ns:0:3}-${cl_proto}-${srv_proto}-${connect_addr}-${port}" local capopt="-i any -s 65535 -B 32768 ${capuser}" - ip netns exec ${listener_ns} tcpdump ${capopt} -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & + ip netns exec ${listener_ns} tcpdump ${capopt} \ + -w "${capfile}-listener.pcap" >> "${capout}" 2>&1 & local cappid_listener=$! - ip netns exec ${connector_ns} tcpdump ${capopt} -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & - local cappid_connector=$! + if [ ${listener_ns} != ${connector_ns} ]; then + ip netns exec ${connector_ns} tcpdump ${capopt} \ + -w "${capfile}-connector.pcap" >> "${capout}" 2>&1 & + local cappid_connector=$! + fi sleep 1 fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - fi - - local stat_synrx_last_l - local stat_ackrx_last_l - local stat_cookietx_last - local stat_cookierx_last - local stat_csum_err_s - local stat_csum_err_c - local stat_tcpfb_last_l - stat_synrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_last=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") - stat_csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - stat_tcpfb_last_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_args $local_addr < "$sin" > "$sout" & + mptcp_lib_nstat_init "${connector_ns}" + fi + + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ + $extra_args $local_addr < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" local start start=$(date +%s%3N) - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_args $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + local stop stop=$(date +%s%3N) if $capture; then sleep 1 kill ${cappid_listener} - kill ${cappid_connector} + if [ ${listener_ns} != ${connector_ns} ]; then + kill ${cappid_connector} + fi fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out + mptcp_lib_nstat_get "${listener_ns}" if [ ${listener_ns} != ${connector_ns} ]; then - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${connector_ns}" fi local duration duration=$((stop-start)) printf "(duration %05sms) " "${duration}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" echo cat "$capout" @@ -463,38 +457,38 @@ do_transfer() rets=$? local extra="" - local stat_synrx_now_l - local stat_ackrx_now_l - local stat_cookietx_now - local stat_cookierx_now - local stat_ooo_now - local stat_tcpfb_now_l - stat_synrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") - stat_ackrx_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") - stat_cookietx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") - stat_cookierx_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") - stat_ooo_now=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") - stat_tcpfb_now_l=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") - - expect_synrx=$((stat_synrx_last_l)) - expect_ackrx=$((stat_ackrx_last_l)) + local stat_synrx + local stat_ackrx + local stat_cookietx + local stat_cookierx + local stat_ooo + local stat_tcpfb + stat_synrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableSYNRX") + stat_ackrx=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableACKRX") + stat_cookietx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesSent") + stat_cookierx=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtSyncookiesRecv") + stat_ooo=$(mptcp_lib_get_counter "${listener_ns}" "TcpExtTCPOFOQueue") + stat_tcpfb=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtMPCapableFallbackACK") + + expect_synrx=0 + expect_ackrx=0 cookies=$(ip netns exec ${listener_ns} sysctl net.ipv4.tcp_syncookies) cookies=${cookies##*=} if [ ${cl_proto} = "MPTCP" ] && [ ${srv_proto} = "MPTCP" ]; then - expect_synrx=$((stat_synrx_last_l+connect_per_transfer)) - expect_ackrx=$((stat_ackrx_last_l+connect_per_transfer)) + expect_synrx=${connect_per_transfer} + expect_ackrx=${connect_per_transfer} fi - if [ ${stat_synrx_now_l} -lt ${expect_synrx} ]; then - mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx_now_l})" \ + if [ ${stat_synrx} -lt ${expect_synrx} ]; then + mptcp_lib_pr_fail "lower MPC SYN rx (${stat_synrx})" \ "than expected (${expect_synrx})" retc=1 fi - if [ ${stat_ackrx_now_l} -lt ${expect_ackrx} ]; then - if [ ${stat_ooo_now} -eq 0 ]; then - mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx_now_l})" \ + if [ ${stat_ackrx} -lt ${expect_ackrx} ]; then + if [ ${stat_ooo} -eq 0 ]; then + mptcp_lib_pr_fail "lower MPC ACK rx (${stat_ackrx})" \ "than expected (${expect_ackrx})" rets=1 else @@ -508,47 +502,45 @@ do_transfer() csum_err_s=$(mptcp_lib_get_counter "${listener_ns}" "MPTcpExtDataCsumErr") csum_err_c=$(mptcp_lib_get_counter "${connector_ns}" "MPTcpExtDataCsumErr") - local csum_err_s_nr=$((csum_err_s - stat_csum_err_s)) - if [ $csum_err_s_nr -gt 0 ]; then - mptcp_lib_pr_fail "server got ${csum_err_s_nr} data checksum error[s]" + if [ $csum_err_s -gt 0 ]; then + mptcp_lib_pr_fail "server got ${csum_err_s} data checksum error[s]" rets=1 fi - local csum_err_c_nr=$((csum_err_c - stat_csum_err_c)) - if [ $csum_err_c_nr -gt 0 ]; then - mptcp_lib_pr_fail "client got ${csum_err_c_nr} data checksum error[s]" + if [ $csum_err_c -gt 0 ]; then + mptcp_lib_pr_fail "client got ${csum_err_c} data checksum error[s]" retc=1 fi fi - if [ ${stat_ooo_now} -eq 0 ] && [ ${stat_tcpfb_last_l} -ne ${stat_tcpfb_now_l} ]; then + if [ ${stat_ooo} -eq 0 ] && [ ${stat_tcpfb} -gt 0 ]; then mptcp_lib_pr_fail "unexpected fallback to TCP" rets=1 fi if [ $cookies -eq 2 ];then - if [ $stat_cookietx_last -ge $stat_cookietx_now ] ;then + if [ $stat_cookietx -eq 0 ] ;then extra+=" WARN: CookieSent: did not advance" fi - if [ $stat_cookierx_last -ge $stat_cookierx_now ] ;then + if [ $stat_cookierx -eq 0 ] ;then extra+=" WARN: CookieRecv: did not advance" fi else - if [ $stat_cookietx_last -ne $stat_cookietx_now ] ;then + if [ $stat_cookietx -gt 0 ] ;then extra+=" WARN: CookieSent: changed" fi - if [ $stat_cookierx_last -ne $stat_cookierx_now ] ;then + if [ $stat_cookierx -gt 0 ] ;then extra+=" WARN: CookieRecv: changed" fi fi - if [ ${stat_synrx_now_l} -gt ${expect_synrx} ]; then + if [ ${stat_synrx} -gt ${expect_synrx} ]; then extra+=" WARN: SYNRX: expect ${expect_synrx}," - extra+=" got ${stat_synrx_now_l} (probably retransmissions)" + extra+=" got ${stat_synrx} (probably retransmissions)" fi - if [ ${stat_ackrx_now_l} -gt ${expect_ackrx} ]; then + if [ ${stat_ackrx} -gt ${expect_ackrx} ]; then extra+=" WARN: ACKRX: expect ${expect_ackrx}," - extra+=" got ${stat_ackrx_now_l} (probably retransmissions)" + extra+=" got ${stat_ackrx} (probably retransmissions)" fi if [ $retc -eq 0 ] && [ $rets -eq 0 ]; then diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 41503c241989d..be61612f68fe5 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -62,6 +62,7 @@ unset sflags unset fastclose unset fullmesh unset speed +unset bind_addr unset join_syn_rej unset join_csum_ns1 unset join_csum_ns2 @@ -645,6 +646,27 @@ wait_mpj() done } +wait_ll_ready() +{ + local ns="${1}" + + local i + for i in $(seq 50); do + ip -n "${ns}" -6 addr show scope link | grep "inet6 fe80" | + grep -qw "tentative" || break + sleep 0.1 + done +} + +get_ll_addr() +{ + local ns="${1}" + local iface="${2}" + + ip -n "${ns}" -6 addr show dev "${iface}" scope link | + grep "inet6 fe80" | sed 's#.*\(fe80::.*\)/.*#\1#' +} + kill_events_pids() { mptcp_lib_kill_wait $evts_ns1_pid @@ -951,6 +973,9 @@ do_transfer() local FAILING_LINKS=${FAILING_LINKS:-""} local fastclose=${fastclose:-""} local speed=${speed:-"fast"} + local bind_addr=${bind_addr:-"::"} + local listener_in="${sin}" + local connector_in="${cin}" port=$(get_port) :> "$cout" @@ -958,10 +983,8 @@ do_transfer() cond_start_capture ${listener_ns} - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" local extra_args if [ $speed = "fast" ]; then @@ -999,42 +1022,40 @@ do_transfer() extra_srv_args="$extra_args $extra_srv_args" if [ "$test_linkfail" -gt 1 ];then - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sinfail" > "$sout" & - else - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - ./mptcp_connect -t ${timeout_poll} -l -p $port -s ${srv_proto} \ - $extra_srv_args "::" < "$sin" > "$sout" & + listener_in="${sinfail}" fi + ip netns exec ${listener_ns} \ + ./mptcp_connect -t ${timeout_poll} -l -p ${port} -s ${srv_proto} \ + ${extra_srv_args} "${bind_addr}" < "${listener_in}" > "${sout}" & local spid=$! mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" extra_cl_args="$extra_args $extra_cl_args" if [ "$test_linkfail" -eq 0 ];then - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr < "$cin" > "$cout" & elif [ "$test_linkfail" -eq 1 ] || [ "$test_linkfail" -eq 2 ];then + connector_in="${cinsent}" ( cat "$cinfail" ; sleep 2; link_failure $listener_ns ; cat "$cinfail" ) | \ tee "$cinsent" | \ - timeout ${timeout_test} \ ip netns exec ${connector_ns} \ ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ $extra_cl_args $connect_addr > "$cout" & else + connector_in="${cinsent}" tee "$cinsent" < "$cinfail" | \ - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ - $extra_cl_args $connect_addr > "$cout" & + ip netns exec ${connector_ns} \ + ./mptcp_connect -t ${timeout_poll} -p $port -s ${cl_proto} \ + $extra_cl_args $connect_addr > "$cout" & fi local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + pm_nl_set_endpoint $listener_ns $connector_ns $connect_addr check_cestab $listener_ns $connector_ns @@ -1043,31 +1064,26 @@ do_transfer() wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + cond_stop_capture - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then fail_test "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" return 1 fi - if [ "$test_linkfail" -gt 1 ];then - check_transfer $sinfail $cout "file received by client" $trunc_size - else - check_transfer $sin $cout "file received by client" $trunc_size - fi + check_transfer $listener_in $cout "file received by client" $trunc_size retc=$? - if [ "$test_linkfail" -eq 0 ];then - check_transfer $cin $sout "file received by server" $trunc_size - else - check_transfer $cinsent $sout "file received by server" $trunc_size - fi + check_transfer $connector_in $sout "file received by server" $trunc_size rets=$? [ $retc -eq 0 ] && [ $rets -eq 0 ] @@ -1136,12 +1152,20 @@ run_tests() do_transfer ${listener_ns} ${connector_ns} MPTCP MPTCP ${connect_addr} } +_dump_stats() +{ + local ns="${1}" + local side="${2}" + + mptcp_lib_print_err "${side} ns stats (${ns2})" + mptcp_lib_pr_nstat "${ns}" + echo +} + dump_stats() { - echo Server ns stats - ip netns exec $ns1 nstat -as | grep Tcp - echo Client ns stats - ip netns exec $ns2 nstat -as | grep Tcp + _dump_stats "${ns1}" "Server" + _dump_stats "${ns2}" "Client" } chk_csum_nr() @@ -2952,7 +2976,11 @@ mixed_tests() pm_nl_add_endpoint $ns1 10.0.1.1 flags signal speed=slow \ run_tests $ns1 $ns2 dead:beef:2::1 - chk_join_nr 1 1 1 + if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_fullmesh_max$"; then + chk_join_nr 0 0 0 + else + chk_join_nr 1 1 1 + fi fi # fullmesh still tries to create all the possibly subflows with @@ -3233,6 +3261,133 @@ add_addr_ports_tests() fi } +bind_tests() +{ + # bind to one address should not allow extra subflows to other addresses + if reset "bind main address v4, no join v4"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + bind_addr="10.0.1.1" \ + run_tests $ns1 $ns2 10.0.1.1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # bind to one address should not allow extra subflows to other addresses + if reset "bind main address v6, no join v6"; then + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + bind_addr="dead:beef:1::1" \ + run_tests $ns1 $ns2 dead:beef:1::1 + join_syn_tx=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + fi + + # multiple binds to allow extra subflows to other addresses + if reset "multiple bind to allow joins v4"; then + local extra_bind + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + + # Launching another app listening on a different address + # Note: it could be a totally different app, e.g. nc, socat, ... + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP 10.0.2.1 & + extra_bind=$! + + bind_addr="10.0.1.1" \ + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to other addresses + if reset "multiple bind to allow joins v6"; then + local extra_bind + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 dead:beef:2::1 flags signal + + # Launching another app listening on a different address + # Note: it could be a totally different app, e.g. nc, socat, ... + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP dead:beef:2::1 & + extra_bind=$! + + bind_addr="dead:beef:1::1" \ + run_tests $ns1 $ns2 dead:beef:1::1 + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to other addresses: v6 LL case + if reset "multiple bind to allow joins v6 link-local routing"; then + local extra_bind ns1ll1 ns1ll2 + + ns1ll1="$(get_ll_addr $ns1 ns1eth1)" + ns1ll2="$(get_ll_addr $ns1 ns1eth2)" + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 "${ns1ll2}" flags signal + + wait_ll_ready $ns1 # to be able to bind + wait_ll_ready $ns2 # also needed to bind on the client side + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP "${ns1ll2}%ns1eth2" & + extra_bind=$! + + bind_addr="${ns1ll1}%ns1eth1" \ + run_tests $ns1 $ns2 "${ns1ll1}%ns2eth1" + # it is not possible to connect to the announced LL addr without + # specifying the outgoing interface. + join_connect_err=1 \ + chk_join_nr 0 0 0 + chk_add_nr 1 1 + + kill ${extra_bind} + fi + + # multiple binds to allow extra subflows to v6 LL addresses: laminar + if reset "multiple bind to allow joins v6 link-local laminar" && + continue_if mptcp_lib_kallsyms_has "mptcp_pm_get_endp_laminar_max$"; then + local extra_bind ns1ll1 ns1ll2 ns2ll2 + + ns1ll1="$(get_ll_addr $ns1 ns1eth1)" + ns1ll2="$(get_ll_addr $ns1 ns1eth2)" + ns2ll2="$(get_ll_addr $ns2 ns2eth2)" + + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 2 2 + pm_nl_add_endpoint $ns1 "${ns1ll2}" flags signal + pm_nl_add_endpoint $ns2 "${ns2ll2}" flags laminar dev ns2eth2 + + wait_ll_ready $ns1 # to be able to bind + wait_ll_ready $ns2 # also needed to bind on the client side + ip netns exec ${ns1} ./mptcp_connect -l -t -1 -p "$(get_port)" \ + -s MPTCP "${ns1ll2}%ns1eth2" & + extra_bind=$! + + bind_addr="${ns1ll1}%ns1eth1" \ + run_tests $ns1 $ns2 "${ns1ll1}%ns2eth1" + chk_join_nr 1 1 1 + chk_add_nr 1 1 + + kill ${extra_bind} + fi +} + syncookies_tests() { # single subflow, syncookies @@ -4187,6 +4342,7 @@ all_tests_sorted=( M@mixed_tests b@backup_tests p@add_addr_ports_tests + B@bind_tests k@syncookies_tests S@checksum_tests d@deny_join_id0_tests diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh index f4388900016ab..5fea7e7df628c 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh @@ -106,23 +106,32 @@ mptcp_lib_pr_info() { mptcp_lib_print_info "INFO: ${*}" } -# $1-2: listener/connector ns ; $3 port ; $4-5 listener/connector stat file +mptcp_lib_pr_nstat() { + local ns="${1}" + local hist="/tmp/${ns}.out" + + if [ -f "${hist}" ]; then + awk '$2 != 0 { print " "$0 }' "${hist}" + else + ip netns exec "${ns}" nstat -as | grep Tcp + fi +} + +# $1-2: listener/connector ns ; $3 port mptcp_lib_pr_err_stats() { local lns="${1}" local cns="${2}" local port="${3}" - local lstat="${4}" - local cstat="${5}" echo -en "${MPTCP_LIB_COLOR_RED}" { printf "\nnetns %s (listener) socket stat for %d:\n" "${lns}" "${port}" ip netns exec "${lns}" ss -Menitam -o "sport = :${port}" - cat "${lstat}" + mptcp_lib_pr_nstat "${lns}" printf "\nnetns %s (connector) socket stat for %d:\n" "${cns}" "${port}" ip netns exec "${cns}" ss -Menitam -o "dport = :${port}" - [ "${lstat}" != "${cstat}" ] && cat "${cstat}" + [ "${lns}" != "${cns}" ] && mptcp_lib_pr_nstat "${cns}" } 1>&2 echo -en "${MPTCP_LIB_COLOR_RESET}" } @@ -341,6 +350,19 @@ mptcp_lib_evts_get_info() { mptcp_lib_get_info_value "${1}" "^type:${3:-1}," } +mptcp_lib_wait_timeout() { + local timeout_test="${1}" + local listener_ns="${2}" + local connector_ns="${3}" + local port="${4}" + shift 4 # rest are PIDs + + sleep "${timeout_test}" + mptcp_lib_print_err "timeout" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" + kill "${@}" 2>/dev/null +} + # $1: PID mptcp_lib_kill_wait() { [ "${1}" -eq 0 ] && return 0 @@ -376,14 +398,36 @@ mptcp_lib_is_v6() { [ -z "${1##*:*}" ] } +mptcp_lib_nstat_init() { + local ns="${1}" + + rm -f "/tmp/${ns}."{nstat,out} + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -n +} + +mptcp_lib_nstat_get() { + local ns="${1}" + + # filter out non-*TCP stats, and the rate (last column) + NSTAT_HISTORY="/tmp/${ns}.nstat" ip netns exec "${ns}" nstat -sz | + grep -o ".*Tcp\S\+\s\+[0-9]\+" > "/tmp/${ns}.out" +} + # $1: ns, $2: MIB counter +# Get the counter from the history (mptcp_lib_nstat_{init,get}()) if available. +# If not, get the counter from nstat ignoring any history. mptcp_lib_get_counter() { local ns="${1}" local counter="${2}" + local hist="/tmp/${ns}.out" local count - count=$(ip netns exec "${ns}" nstat -asz "${counter}" | - awk 'NR==1 {next} {print $2}') + if [[ -s "${hist}" && "${counter}" == *"Tcp"* ]]; then + count=$(awk "/^${counter} / {print \$2; exit}" "${hist}") + else + count=$(ip netns exec "${ns}" nstat -asz "${counter}" | + awk 'NR==1 {next} {print $2}') + fi if [ -z "${count}" ]; then mptcp_lib_fail_if_expected_feature "${counter} counter" return 1 diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh index f01989be6e9b3..ab8bce06b2626 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.sh @@ -169,41 +169,44 @@ do_transfer() cmsg+=",TCPINQ" fi - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat -n - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${listener_ns} \ - $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ - ${local_addr} < "$sin" > "$sout" & + mptcp_lib_nstat_init "${listener_ns}" + mptcp_lib_nstat_init "${connector_ns}" + + ip netns exec ${listener_ns} \ + $mptcp_connect -t ${timeout_poll} -l -M 1 -p $port -s ${srv_proto} -c "${cmsg}" \ + ${local_addr} < "$sin" > "$sout" & local spid=$! - sleep 1 + mptcp_lib_wait_local_port_listen "${listener_ns}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${connector_ns} \ - $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ - $connect_addr < "$cin" > "$cout" & + ip netns exec ${connector_ns} \ + $mptcp_connect -t ${timeout_poll} -M 2 -p $port -s ${cl_proto} -c "${cmsg}" \ + $connect_addr < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${listener_ns}" \ + "${connector_ns}" "${port}" "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? - NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \ - nstat | grep Tcp > /tmp/${listener_ns}.out - NSTAT_HISTORY=/tmp/${connector_ns}.nstat ip netns exec ${connector_ns} \ - nstat | grep Tcp > /tmp/${connector_ns}.out + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + + mptcp_lib_nstat_get "${listener_ns}" + mptcp_lib_nstat_get "${connector_ns}" print_title "Transfer ${ip:2}" - if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ]; then + if [ ${rets} -ne 0 ] || [ ${retc} -ne 0 ] || [ ${timeout_pid} -ne 0 ]; then mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" \ - "/tmp/${listener_ns}.out" "/tmp/${connector_ns}.out" + mptcp_lib_pr_err_stats "${listener_ns}" "${connector_ns}" "${port}" mptcp_lib_result_fail "transfer ${ip}" diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 1903e8e84a315..806aaa7d2d61d 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -155,48 +155,53 @@ do_transfer() sleep 1 fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat -n - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat -n - - timeout ${timeout_test} \ - ip netns exec ${ns3} \ - ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ - 0.0.0.0 < "$sin" > "$sout" & + mptcp_lib_nstat_init "${ns3}" + mptcp_lib_nstat_init "${ns1}" + + ip netns exec ${ns3} \ + ./mptcp_connect -jt ${timeout_poll} -l -p $port -T $max_time \ + 0.0.0.0 < "$sin" > "$sout" & local spid=$! mptcp_lib_wait_local_port_listen "${ns3}" "${port}" - timeout ${timeout_test} \ - ip netns exec ${ns1} \ - ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ - 10.0.3.3 < "$cin" > "$cout" & + ip netns exec ${ns1} \ + ./mptcp_connect -jt ${timeout_poll} -p $port -T $max_time \ + 10.0.3.3 < "$cin" > "$cout" & local cpid=$! + mptcp_lib_wait_timeout "${timeout_test}" "${ns3}" "${ns1}" "${port}" \ + "${cpid}" "${spid}" & + local timeout_pid=$! + wait $cpid local retc=$? wait $spid local rets=$? + if kill -0 $timeout_pid; then + # Finished before the timeout: kill the background job + mptcp_lib_kill_group_wait $timeout_pid + timeout_pid=0 + fi + if $capture; then sleep 1 kill ${cappid_listener} kill ${cappid_connector} fi - NSTAT_HISTORY=/tmp/${ns3}.nstat ip netns exec ${ns3} \ - nstat | grep Tcp > /tmp/${ns3}.out - NSTAT_HISTORY=/tmp/${ns1}.nstat ip netns exec ${ns1} \ - nstat | grep Tcp > /tmp/${ns1}.out + mptcp_lib_nstat_get "${ns3}" + mptcp_lib_nstat_get "${ns1}" cmp $sin $cout > /dev/null 2>&1 local cmps=$? cmp $cin $sout > /dev/null 2>&1 local cmpc=$? - if [ $retc -eq 0 ] && [ $rets -eq 0 ] && \ - [ $cmpc -eq 0 ] && [ $cmps -eq 0 ]; then + if [ $retc -eq 0 ] && [ $rets -eq 0 ] && + [ $cmpc -eq 0 ] && [ $cmps -eq 0 ] && + [ $timeout_pid -eq 0 ]; then printf "%-16s" " max $max_time " mptcp_lib_pr_ok cat "$capout" @@ -204,8 +209,7 @@ do_transfer() fi mptcp_lib_pr_fail "client exit code $retc, server $rets" - mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" \ - "/tmp/${ns3}.out" "/tmp/${ns1}.out" + mptcp_lib_pr_err_stats "${ns3}" "${ns1}" "${port}" ls -l $sin $cout ls -l $cin $sout diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 87323942cb8a0..e9ae1806ab071 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -211,7 +211,8 @@ make_connection() ip netns exec "$ns1" \ ./mptcp_connect -s MPTCP -w 300 -p $app_port -l $listen_addr > /dev/null 2>&1 & local server_pid=$! - sleep 0.5 + + mptcp_lib_wait_local_port_listen "${ns1}" "${port}" # Run the client, transfer $file and stay connected to the server # to conduct tests diff --git a/tools/testing/selftests/net/netfilter/sctp_collision.c b/tools/testing/selftests/net/netfilter/sctp_collision.c index 21bb1cfd8a856..b282d1785c9b0 100644 --- a/tools/testing/selftests/net/netfilter/sctp_collision.c +++ b/tools/testing/selftests/net/netfilter/sctp_collision.c @@ -9,9 +9,10 @@ int main(int argc, char *argv[]) { struct sockaddr_in saddr = {}, daddr = {}; - int sd, ret, len = sizeof(daddr); + socklen_t len = sizeof(daddr); struct timeval tv = {25, 0}; char buf[] = "hello"; + int sd, ret; if (argc != 6 || (strcmp(argv[1], "server") && strcmp(argv[1], "client"))) { printf("%s \n", diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c index 7618ebe528a4c..679b6c77ace7c 100644 --- a/tools/testing/selftests/net/netlink-dumps.c +++ b/tools/testing/selftests/net/netlink-dumps.c @@ -143,6 +143,7 @@ TEST(dump_extack) EXPECT_EQ(n, -1); EXPECT_EQ(errno, ENOBUFS); + ret = NO_CTRL; for (i = 0; i < cnt; i++) { struct ext_ack ea = {}; diff --git a/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt b/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt new file mode 100644 index 0000000000000..47550df124cec --- /dev/null +++ b/tools/testing/selftests/net/packetdrill/tcp_rto_synack_rto_max.pkt @@ -0,0 +1,54 @@ +// SPDX-License-Identifier: GPL-2.0 +// +// Test SYN+ACK RTX with 1s RTO. +// +`./defaults.sh + ./set_sysctls.py /proc/sys/net/ipv4/tcp_rto_max_ms=1000` + +// +// Test 1: TFO SYN+ACK +// + 0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + +0 setsockopt(3, SOL_TCP, TCP_FASTOPEN, [1], 4) = 0 + + +0 < S 0:10(10) win 1000 + +0 > S. 0:0(0) ack 11 + +// RTO must be capped to 1s + +1 > S. 0:0(0) ack 11 + +1 > S. 0:0(0) ack 11 + +1 > S. 0:0(0) ack 11 + + +0 < . 11:11(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) != 0, tcpi_options }% + + +0 close(4) = 0 + +0 close(3) = 0 + + +// +// Test 2: non-TFO SYN+ACK +// + +0 socket(..., SOCK_STREAM|SOCK_NONBLOCK, IPPROTO_TCP) = 3 + +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 + +0 bind(3, ..., ...) = 0 + +0 listen(3, 1) = 0 + + +0 < S 0:0(0) win 1000 + +0 > S. 0:0(0) ack 1 + +// RTO must be capped to 1s + +1 > S. 0:0(0) ack 1 + +1 > S. 0:0(0) ack 1 + +1 > S. 0:0(0) ack 1 + + +0 < . 1:1(0) ack 1 win 1000 + +0 accept(3, ..., ...) = 4 + +0 %{ assert (tcpi_options & TCPI_OPT_SYN_DATA) == 0, tcpi_options }% + + +0 close(4) = 0 + +0 close(3) = 0 diff --git a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt index 183051ba0cae3..6882b8240a8a9 100644 --- a/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt +++ b/tools/testing/selftests/net/packetdrill/tcp_user_timeout_user-timeout-probe.pkt @@ -23,14 +23,16 @@ // install a qdisc dropping all packets +0 `tc qdisc delete dev tun0 root 2>/dev/null ; tc qdisc add dev tun0 root pfifo limit 0` + +0 write(4, ..., 24) = 24 // When qdisc is congested we retry every 500ms // (TCP_RESOURCE_PROBE_INTERVAL) and therefore // we retry 6 times before hitting 3s timeout. // First verify that the connection is alive: -+3.250 write(4, ..., 24) = 24 ++3 write(4, ..., 24) = 24 + // Now verify that shortly after that the socket is dead: - +.100 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) ++1 write(4, ..., 24) = -1 ETIMEDOUT (Connection timed out) +0 %{ assert tcpi_probes == 6, tcpi_probes; \ assert tcpi_backoff == 0, tcpi_backoff }% diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index 163a084d525d5..248c2b91fe42b 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -8,6 +8,7 @@ ALL_TESTS=" kci_test_polrouting kci_test_route_get kci_test_addrlft + kci_test_addrlft_route_cleanup kci_test_promote_secondaries kci_test_tc kci_test_gre @@ -323,6 +324,25 @@ kci_test_addrlft() end_test "PASS: preferred_lft addresses have expired" } +kci_test_addrlft_route_cleanup() +{ + local ret=0 + local test_addr="2001:db8:99::1/64" + local test_prefix="2001:db8:99::/64" + + run_cmd ip -6 addr add $test_addr dev "$devdummy" valid_lft 300 preferred_lft 300 + run_cmd_grep "$test_prefix proto kernel" ip -6 route show dev "$devdummy" + run_cmd ip -6 addr del $test_addr dev "$devdummy" + run_cmd_grep_fail "$test_prefix" ip -6 route show dev "$devdummy" + + if [ $ret -ne 0 ]; then + end_test "FAIL: route not cleaned up when address with valid_lft deleted" + return 1 + fi + + end_test "PASS: route cleaned up when address with valid_lft deleted" +} + kci_test_promote_secondaries() { run_cmd ifconfig "$devdummy" diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings index ed8418e8217a0..a38764182822e 100644 --- a/tools/testing/selftests/net/settings +++ b/tools/testing/selftests/net/settings @@ -1 +1,2 @@ timeout=3600 +profile=1 diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 5c6d8215021c9..da1b50b307194 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -2856,6 +2856,147 @@ TEST_F(tls_err, oob_pressure) EXPECT_EQ(send(self->fd2, buf, 5, MSG_OOB), 5); } +/* + * Parse a stream of TLS records and ensure that each record respects + * the specified @max_payload_len. + */ +static size_t parse_tls_records(struct __test_metadata *_metadata, + const __u8 *rx_buf, int rx_len, int overhead, + __u16 max_payload_len) +{ + const __u8 *rec = rx_buf; + size_t total_plaintext_rx = 0; + const __u8 rec_header_len = 5; + + while (rec < rx_buf + rx_len) { + __u16 record_payload_len; + __u16 plaintext_len; + + /* Sanity check that it's a TLS header for application data */ + ASSERT_EQ(rec[0], 23); + ASSERT_EQ(rec[1], 0x3); + ASSERT_EQ(rec[2], 0x3); + + memcpy(&record_payload_len, rec + 3, 2); + record_payload_len = ntohs(record_payload_len); + ASSERT_GE(record_payload_len, overhead); + + plaintext_len = record_payload_len - overhead; + total_plaintext_rx += plaintext_len; + + /* Plaintext must not exceed the specified limit */ + ASSERT_LE(plaintext_len, max_payload_len); + rec += rec_header_len + record_payload_len; + } + + return total_plaintext_rx; +} + +TEST(tls_12_tx_max_payload_len) +{ + struct tls_crypto_info_keys tls12; + int cfd, ret, fd, overhead; + size_t total_plaintext_rx = 0; + __u8 tx[1024], rx[2000]; + __u16 limit = 128; + __u16 opt = 0; + unsigned int optlen = sizeof(opt); + bool notls; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); + + if (notls) + exit(KSFT_SKIP); + + /* Don't install keys on fd, we'll parse raw records */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &limit, + sizeof(limit)); + ASSERT_EQ(ret, 0); + + ret = getsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &opt, &optlen); + EXPECT_EQ(ret, 0); + EXPECT_EQ(limit, opt); + EXPECT_EQ(optlen, sizeof(limit)); + + memset(tx, 0, sizeof(tx)); + ASSERT_EQ(send(cfd, tx, sizeof(tx), 0), sizeof(tx)); + close(cfd); + + ret = recv(fd, rx, sizeof(rx), 0); + + /* + * 16B tag + 8B IV -- record header (5B) is not counted but we'll + * need it to walk the record stream + */ + overhead = 16 + 8; + total_plaintext_rx = parse_tls_records(_metadata, rx, ret, overhead, + limit); + + ASSERT_EQ(total_plaintext_rx, sizeof(tx)); + close(fd); +} + +TEST(tls_12_tx_max_payload_len_open_rec) +{ + struct tls_crypto_info_keys tls12; + int cfd, ret, fd, overhead; + size_t total_plaintext_rx = 0; + __u8 tx[1024], rx[2000]; + __u16 tx_partial = 256; + __u16 og_limit = 512, limit = 128; + bool notls; + + tls_crypto_info_init(TLS_1_2_VERSION, TLS_CIPHER_AES_CCM_128, + &tls12, 0); + + ulp_sock_pair(_metadata, &fd, &cfd, ¬ls); + + if (notls) + exit(KSFT_SKIP); + + /* Don't install keys on fd, we'll parse raw records */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX, &tls12, tls12.len); + ASSERT_EQ(ret, 0); + + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &og_limit, + sizeof(og_limit)); + ASSERT_EQ(ret, 0); + + memset(tx, 0, sizeof(tx)); + ASSERT_EQ(send(cfd, tx, tx_partial, MSG_MORE), tx_partial); + + /* + * Changing the payload limit with a pending open record should + * not be allowed. + */ + ret = setsockopt(cfd, SOL_TLS, TLS_TX_MAX_PAYLOAD_LEN, &limit, + sizeof(limit)); + ASSERT_EQ(ret, -1); + ASSERT_EQ(errno, EBUSY); + + ASSERT_EQ(send(cfd, tx + tx_partial, sizeof(tx) - tx_partial, MSG_EOR), + sizeof(tx) - tx_partial); + close(cfd); + + ret = recv(fd, rx, sizeof(rx), 0); + + /* + * 16B tag + 8B IV -- record header (5B) is not counted but we'll + * need it to walk the record stream + */ + overhead = 16 + 8; + total_plaintext_rx = parse_tls_records(_metadata, rx, ret, overhead, + og_limit); + ASSERT_EQ(total_plaintext_rx, sizeof(tx)); + close(fd); +} + TEST(non_established) { struct tls12_crypto_info_aes_gcm_256 tls12; struct sockaddr_in addr; diff --git a/tools/testing/selftests/net/traceroute.sh b/tools/testing/selftests/net/traceroute.sh index dbb34c7e09ce5..a7c6ab8a03475 100755 --- a/tools/testing/selftests/net/traceroute.sh +++ b/tools/testing/selftests/net/traceroute.sh @@ -36,6 +36,35 @@ run_cmd() return $rc } +__check_traceroute_version() +{ + local cmd=$1; shift + local req_ver=$1; shift + local ver + + req_ver=$(echo "$req_ver" | sed 's/\.//g') + ver=$($cmd -V 2>&1 | grep -Eo '[0-9]+.[0-9]+.[0-9]+' | sed 's/\.//g') + if [[ $ver -lt $req_ver ]]; then + return 1 + else + return 0 + fi +} + +check_traceroute6_version() +{ + local req_ver=$1; shift + + __check_traceroute_version traceroute6 "$req_ver" +} + +check_traceroute_version() +{ + local req_ver=$1; shift + + __check_traceroute_version traceroute "$req_ver" +} + ################################################################################ # create namespaces and interconnects @@ -59,6 +88,8 @@ create_ns() ip netns exec ${ns} ip -6 ro add unreachable default metric 8192 ip netns exec ${ns} sysctl -qw net.ipv4.ip_forward=1 + ip netns exec ${ns} sysctl -qw net.ipv4.icmp_ratelimit=0 + ip netns exec ${ns} sysctl -qw net.ipv6.icmp.ratelimit=0 ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.keep_addr_on_down=1 ip netns exec ${ns} sysctl -qw net.ipv6.conf.all.forwarding=1 ip netns exec ${ns} sysctl -qw net.ipv6.conf.default.forwarding=1 @@ -297,6 +328,144 @@ run_traceroute6_vrf() cleanup_traceroute6_vrf } +################################################################################ +# traceroute6 with ICMP extensions test +# +# Verify that in this scenario +# +# ---- ---- ---- +# |H1|--------------------------|R1|--------------------------|H2| +# ---- N1 ---- N2 ---- +# +# ICMP extensions are correctly reported. The loopback interfaces on all the +# nodes are assigned global addresses and the interfaces connecting the nodes +# are assigned IPv6 link-local addresses. + +cleanup_traceroute6_ext() +{ + cleanup_all_ns +} + +setup_traceroute6_ext() +{ + # Start clean + cleanup_traceroute6_ext + + setup_ns h1 r1 h2 + create_ns "$h1" + create_ns "$r1" + create_ns "$h2" + + # Setup N1 + connect_ns "$h1" eth1 - fe80::1/64 "$r1" eth1 - fe80::2/64 + # Setup N2 + connect_ns "$r1" eth2 - fe80::3/64 "$h2" eth2 - fe80::4/64 + + # Setup H1 + ip -n "$h1" address add 2001:db8:1::1/128 dev lo + ip -n "$h1" route add ::/0 nexthop via fe80::2 dev eth1 + + # Setup R1 + ip -n "$r1" address add 2001:db8:1::2/128 dev lo + ip -n "$r1" route add 2001:db8:1::1/128 nexthop via fe80::1 dev eth1 + ip -n "$r1" route add 2001:db8:1::3/128 nexthop via fe80::4 dev eth2 + + # Setup H2 + ip -n "$h2" address add 2001:db8:1::3/128 dev lo + ip -n "$h2" route add ::/0 nexthop via fe80::3 dev eth2 + + # Prime the network + ip netns exec "$h1" ping6 -c5 2001:db8:1::3 >/dev/null 2>&1 +} + +traceroute6_ext_iio_iif_test() +{ + local r1_ifindex h2_ifindex + local pkt_len=$1; shift + + # Test that incoming interface info is not appended by default. + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended by default when should not" + + # Test that the extension is appended when enabled. + run_cmd "$r1" "bash -c \"echo 0x01 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_err $? "Failed to enable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_err $? "Incoming interface info not appended after enable" + + # Test that the extension is not appended when disabled. + run_cmd "$r1" "bash -c \"echo 0x00 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_err $? "Failed to disable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended after disable" + + # Test that the extension is sent correctly from both R1 and H2. + run_cmd "$r1" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x01" + r1_ifindex=$(ip -n "$r1" -j link show dev eth1 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from R1" + + run_cmd "$h2" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x01" + h2_ifindex=$(ip -n "$h2" -j link show dev eth2 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from H2" + + # Add a global address on the incoming interface of R1 and check that + # it is reported. + run_cmd "$r1" "ip address add 2001:db8:100::1/64 dev eth1 nodad" + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from R1 after address addition" + run_cmd "$r1" "ip address del 2001:db8:100::1/64 dev eth1" + + # Change name and MTU and make sure the result is still correct. + run_cmd "$r1" "ip link set dev eth1 name eth1tag mtu 1501" + run_cmd "$h1" "traceroute6 -e 2001:db8:1::3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from R1 after name and MTU change" + run_cmd "$r1" "ip link set dev eth1tag name eth1 mtu 1500" + + run_cmd "$r1" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x00" + run_cmd "$h2" "sysctl -w net.ipv6.icmp.errors_extension_mask=0x00" +} + +run_traceroute6_ext() +{ + # Need at least version 2.1.5 for RFC 5837 support. + if ! check_traceroute6_version 2.1.5; then + log_test_skip "traceroute6 too old, missing ICMP extensions support" + return + fi + + setup_traceroute6_ext + + RET=0 + + ## General ICMP extensions tests + + # Test that ICMP extensions are disabled by default. + run_cmd "$h1" "sysctl net.ipv6.icmp.errors_extension_mask | grep \"= 0$\"" + check_err $? "ICMP extensions are not disabled by default" + + # Test that unsupported values are rejected. Do not use "sysctl" as + # older versions do not return an error code upon failure. + run_cmd "$h1" "bash -c \"echo 0x80 > /proc/sys/net/ipv6/icmp/errors_extension_mask\"" + check_fail $? "Unsupported sysctl value was not rejected" + + ## Extension-specific tests + + # Incoming interface info test. Test with various packet sizes, + # including the default one. + traceroute6_ext_iio_iif_test + traceroute6_ext_iio_iif_test 127 + traceroute6_ext_iio_iif_test 128 + traceroute6_ext_iio_iif_test 129 + + log_test "IPv6 traceroute with ICMP extensions" + + cleanup_traceroute6_ext +} + ################################################################################ # traceroute test # @@ -437,6 +606,147 @@ run_traceroute_vrf() cleanup_traceroute_vrf } +################################################################################ +# traceroute with ICMP extensions test +# +# Verify that in this scenario +# +# ---- ---- ---- +# |H1|--------------------------|R1|--------------------------|H2| +# ---- N1 ---- N2 ---- +# +# ICMP extensions are correctly reported. The loopback interfaces on all the +# nodes are assigned global addresses and the interfaces connecting the nodes +# are assigned IPv6 link-local addresses. + +cleanup_traceroute_ext() +{ + cleanup_all_ns +} + +setup_traceroute_ext() +{ + # Start clean + cleanup_traceroute_ext + + setup_ns h1 r1 h2 + create_ns "$h1" + create_ns "$r1" + create_ns "$h2" + + # Setup N1 + connect_ns "$h1" eth1 - fe80::1/64 "$r1" eth1 - fe80::2/64 + # Setup N2 + connect_ns "$r1" eth2 - fe80::3/64 "$h2" eth2 - fe80::4/64 + + # Setup H1 + ip -n "$h1" address add 192.0.2.1/32 dev lo + ip -n "$h1" route add 0.0.0.0/0 nexthop via inet6 fe80::2 dev eth1 + + # Setup R1 + ip -n "$r1" address add 192.0.2.2/32 dev lo + ip -n "$r1" route add 192.0.2.1/32 nexthop via inet6 fe80::1 dev eth1 + ip -n "$r1" route add 192.0.2.3/32 nexthop via inet6 fe80::4 dev eth2 + + # Setup H2 + ip -n "$h2" address add 192.0.2.3/32 dev lo + ip -n "$h2" route add 0.0.0.0/0 nexthop via inet6 fe80::3 dev eth2 + + # Prime the network + ip netns exec "$h1" ping -c5 192.0.2.3 >/dev/null 2>&1 +} + +traceroute_ext_iio_iif_test() +{ + local r1_ifindex h2_ifindex + local pkt_len=$1; shift + + # Test that incoming interface info is not appended by default. + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended by default when should not" + + # Test that the extension is appended when enabled. + run_cmd "$r1" "bash -c \"echo 0x01 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_err $? "Failed to enable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_err $? "Incoming interface info not appended after enable" + + # Test that the extension is not appended when disabled. + run_cmd "$r1" "bash -c \"echo 0x00 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_err $? "Failed to disable incoming interface info extension on R1" + + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep INC" + check_fail $? "Incoming interface info appended after disable" + + # Test that the extension is sent correctly from both R1 and H2. + run_cmd "$r1" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x01" + r1_ifindex=$(ip -n "$r1" -j link show dev eth1 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from R1" + + run_cmd "$h2" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x01" + h2_ifindex=$(ip -n "$h2" -j link show dev eth2 | jq '.[]["ifindex"]') + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from H2" + + # Add a global address on the incoming interface of R1 and check that + # it is reported. + run_cmd "$r1" "ip address add 198.51.100.1/24 dev eth1" + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from R1 after address addition" + run_cmd "$r1" "ip address del 198.51.100.1/24 dev eth1" + + # Change name and MTU and make sure the result is still correct. + # Re-add the route towards H1 since it was deleted when we removed the + # last IPv4 address from eth1 on R1. + run_cmd "$r1" "ip route add 192.0.2.1/32 nexthop via inet6 fe80::1 dev eth1" + run_cmd "$r1" "ip link set dev eth1 name eth1tag mtu 1501" + run_cmd "$h1" "traceroute -e 192.0.2.3 $pkt_len | grep ''" + check_err $? "Wrong incoming interface info reported from R1 after name and MTU change" + run_cmd "$r1" "ip link set dev eth1tag name eth1 mtu 1500" + + run_cmd "$r1" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x00" + run_cmd "$h2" "sysctl -w net.ipv4.icmp_errors_extension_mask=0x00" +} + +run_traceroute_ext() +{ + # Need at least version 2.1.5 for RFC 5837 support. + if ! check_traceroute_version 2.1.5; then + log_test_skip "traceroute too old, missing ICMP extensions support" + return + fi + + setup_traceroute_ext + + RET=0 + + ## General ICMP extensions tests + + # Test that ICMP extensions are disabled by default. + run_cmd "$h1" "sysctl net.ipv4.icmp_errors_extension_mask | grep \"= 0$\"" + check_err $? "ICMP extensions are not disabled by default" + + # Test that unsupported values are rejected. Do not use "sysctl" as + # older versions do not return an error code upon failure. + run_cmd "$h1" "bash -c \"echo 0x80 > /proc/sys/net/ipv4/icmp_errors_extension_mask\"" + check_fail $? "Unsupported sysctl value was not rejected" + + ## Extension-specific tests + + # Incoming interface info test. Test with various packet sizes, + # including the default one. + traceroute_ext_iio_iif_test + traceroute_ext_iio_iif_test 127 + traceroute_ext_iio_iif_test 128 + traceroute_ext_iio_iif_test 129 + + log_test "IPv4 traceroute with ICMP extensions" + + cleanup_traceroute_ext +} + ################################################################################ # Run tests @@ -444,8 +754,10 @@ run_tests() { run_traceroute6 run_traceroute6_vrf + run_traceroute6_ext run_traceroute run_traceroute_vrf + run_traceroute_ext } ################################################################################ @@ -462,6 +774,7 @@ done require_command traceroute6 require_command traceroute +require_command jq run_tests diff --git a/tools/testing/selftests/net/txtimestamp.c b/tools/testing/selftests/net/txtimestamp.c index dae91eb97d699..2a8d6a463397a 100644 --- a/tools/testing/selftests/net/txtimestamp.c +++ b/tools/testing/selftests/net/txtimestamp.c @@ -62,6 +62,7 @@ static int do_ipv4 = 1; static int do_ipv6 = 1; static int cfg_payload_len = 10; static int cfg_poll_timeout = 100; +static bool cfg_wake_every_msec = true; static int cfg_delay_snd; static int cfg_delay_ack; static int cfg_delay_tolerance_usec = 500; @@ -286,6 +287,16 @@ static void print_pktinfo(int family, int ifindex, void *saddr, void *daddr) daddr ? inet_ntop(family, daddr, da, sizeof(da)) : "unknown"); } +static int64_t get_time_now_us64(void) +{ + static struct timespec ts; + + if (clock_gettime(CLOCK_REALTIME, &ts)) + error(1, errno, "clock_gettime"); + + return timespec_to_us64(&ts); +} + static void __epoll(int epfd) { struct epoll_event events; @@ -300,11 +311,19 @@ static void __epoll(int epfd) static void __poll(int fd) { struct pollfd pollfd; + int64_t end_of_wait; + int timeout; int ret; - memset(&pollfd, 0, sizeof(pollfd)); - pollfd.fd = fd; - ret = poll(&pollfd, 1, cfg_poll_timeout); + timeout = cfg_wake_every_msec ? 1 : cfg_poll_timeout; + end_of_wait = get_time_now_us64() + cfg_poll_timeout * 1000; + + do { + memset(&pollfd, 0, sizeof(pollfd)); + pollfd.fd = fd; + ret = poll(&pollfd, 1, timeout); + } while (!ret && get_time_now_us64() < end_of_wait); + if (ret != 1) error(1, errno, "poll"); } @@ -707,6 +726,7 @@ static void __attribute__((noreturn)) usage(const char *filepath) " -P: use PF_PACKET\n" " -r: use raw\n" " -R: use raw (IP_HDRINCL)\n" + " -s: single sleep until timeout (from -S), by default wake every 1msec\n" " -S N: usec to sleep before reading error queue\n" " -t N: tolerance (usec) for timestamp validation\n" " -u: use udp\n" @@ -723,7 +743,7 @@ static void parse_opt(int argc, char **argv) int c; while ((c = getopt(argc, argv, - "46bc:CeEFhIl:LnNo:p:PrRS:t:uv:V:x")) != -1) { + "46bc:CeEFhIl:LnNo:p:PrRsS:t:uv:V:x")) != -1) { switch (c) { case '4': do_ipv6 = 0; @@ -787,6 +807,9 @@ static void parse_opt(int argc, char **argv) cfg_proto = SOCK_RAW; cfg_ipproto = IPPROTO_RAW; break; + case 's': /* sleep 'till timeout */ + cfg_wake_every_msec = false; + break; case 'S': cfg_sleep_usec = strtoul(optarg, NULL, 10); break; @@ -825,6 +848,8 @@ static void parse_opt(int argc, char **argv) error(1, 0, "cannot ask for pktinfo over pf_packet"); if (cfg_busy_poll && cfg_use_epoll) error(1, 0, "pass epoll or busy_poll, not both"); + if (cfg_wake_every_msec && cfg_use_epoll) + error(1, 0, "periodic wake not implemented for epoll, use -s"); if (cfg_proto == SOCK_STREAM && cfg_use_cmsg_opt_id) error(1, 0, "TCP sockets don't support SCM_TS_OPT_ID"); diff --git a/tools/testing/selftests/vsock/vmtest.sh b/tools/testing/selftests/vsock/vmtest.sh index 8ceeb8a7894f5..c7b270dd77a92 100755 --- a/tools/testing/selftests/vsock/vmtest.sh +++ b/tools/testing/selftests/vsock/vmtest.sh @@ -7,6 +7,8 @@ # * virtme-ng # * busybox-static (used by virtme-ng) # * qemu (used by virtme-ng) +# +# shellcheck disable=SC2317,SC2119 readonly SCRIPT_DIR="$(cd -P -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd -P)" readonly KERNEL_CHECKOUT=$(realpath "${SCRIPT_DIR}"/../../../../) @@ -22,8 +24,9 @@ readonly SSH_HOST_PORT=2222 readonly VSOCK_CID=1234 readonly WAIT_PERIOD=3 readonly WAIT_PERIOD_MAX=60 -readonly WAIT_TOTAL=$(( WAIT_PERIOD * WAIT_PERIOD_MAX )) -readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) +readonly WAIT_QEMU=5 +readonly PIDFILE_TEMPLATE=/tmp/vsock_vmtest_XXXX.pid +declare -A PIDFILES # virtme-ng offers a netdev for ssh when using "--ssh", but we also need a # control port forwarded for vsock_test. Because virtme-ng doesn't support @@ -33,12 +36,6 @@ readonly QEMU_PIDFILE=$(mktemp /tmp/qemu_vsock_vmtest_XXXX.pid) # add the kernel cmdline options that virtme-init uses to setup the interface. readonly QEMU_TEST_PORT_FWD="hostfwd=tcp::${TEST_HOST_PORT}-:${TEST_GUEST_PORT}" readonly QEMU_SSH_PORT_FWD="hostfwd=tcp::${SSH_HOST_PORT}-:${SSH_GUEST_PORT}" -readonly QEMU_OPTS="\ - -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ - -device virtio-net-pci,netdev=n0 \ - -device vhost-vsock-pci,guest-cid=${VSOCK_CID} \ - --pidfile ${QEMU_PIDFILE} \ -" readonly KERNEL_CMDLINE="\ virtme.dhcp net.ifnames=0 biosdevname=0 \ virtme.ssh virtme_ssh_channel=tcp virtme_ssh_user=$USER \ @@ -51,6 +48,8 @@ readonly TEST_DESCS=( "Run vsock_test using the loopback transport in the VM." ) +readonly USE_SHARED_VM=(vm_server_host_client vm_client_host_server vm_loopback) + VERBOSE=0 usage() { @@ -84,21 +83,33 @@ die() { exit "${KSFT_FAIL}" } +check_result() { + local rc arg + + rc=$1 + arg=$2 + + cnt_total=$(( cnt_total + 1 )) + + if [[ ${rc} -eq ${KSFT_PASS} ]]; then + cnt_pass=$(( cnt_pass + 1 )) + echo "ok ${cnt_total} ${arg}" + elif [[ ${rc} -eq ${KSFT_SKIP} ]]; then + cnt_skip=$(( cnt_skip + 1 )) + echo "ok ${cnt_total} ${arg} # SKIP" + elif [[ ${rc} -eq ${KSFT_FAIL} ]]; then + cnt_fail=$(( cnt_fail + 1 )) + echo "not ok ${cnt_total} ${arg} # exit=${rc}" + fi +} + vm_ssh() { ssh -q -o UserKnownHostsFile=/dev/null -p ${SSH_HOST_PORT} localhost "$@" return $? } cleanup() { - if [[ -s "${QEMU_PIDFILE}" ]]; then - pkill -SIGTERM -F "${QEMU_PIDFILE}" > /dev/null 2>&1 - fi - - # If failure occurred during or before qemu start up, then we need - # to clean this up ourselves. - if [[ -e "${QEMU_PIDFILE}" ]]; then - rm "${QEMU_PIDFILE}" - fi + terminate_pidfiles "${!PIDFILES[@]}" } check_args() { @@ -147,7 +158,7 @@ check_vng() { local version local ok - tested_versions=("1.33" "1.36") + tested_versions=("1.33" "1.36" "1.37") version="$(vng --version)" ok=0 @@ -188,10 +199,37 @@ handle_build() { popd &>/dev/null } +create_pidfile() { + local pidfile + + pidfile=$(mktemp "${PIDFILE_TEMPLATE}") + PIDFILES["${pidfile}"]=1 + + echo "${pidfile}" +} + +terminate_pidfiles() { + local pidfile + + for pidfile in "$@"; do + if [[ -s "${pidfile}" ]]; then + pkill -SIGTERM -F "${pidfile}" > /dev/null 2>&1 + fi + + if [[ -e "${pidfile}" ]]; then + rm -f "${pidfile}" + fi + + unset "PIDFILES[${pidfile}]" + done +} + vm_start() { + local pidfile=$1 local logfile=/dev/null local verbose_opt="" local kernel_opt="" + local qemu_opts="" local qemu qemu=$(command -v "${QEMU}") @@ -201,6 +239,13 @@ vm_start() { logfile=/dev/stdout fi + qemu_opts="\ + -netdev user,id=n0,${QEMU_TEST_PORT_FWD},${QEMU_SSH_PORT_FWD} \ + -device virtio-net-pci,netdev=n0 \ + -device vhost-vsock-pci,guest-cid=${VSOCK_CID} \ + --pidfile ${pidfile} + " + if [[ "${BUILD}" -eq 1 ]]; then kernel_opt="${KERNEL_CHECKOUT}" fi @@ -209,16 +254,14 @@ vm_start() { --run \ ${kernel_opt} \ ${verbose_opt} \ - --qemu-opts="${QEMU_OPTS}" \ + --qemu-opts="${qemu_opts}" \ --qemu="${qemu}" \ --user root \ --append "${KERNEL_CMDLINE}" \ --rw &> ${logfile} & - if ! timeout ${WAIT_TOTAL} \ - bash -c 'while [[ ! -s '"${QEMU_PIDFILE}"' ]]; do sleep 1; done; exit 0'; then - die "failed to boot VM" - fi + timeout "${WAIT_QEMU}" \ + bash -c 'while [[ ! -s '"${pidfile}"' ]]; do sleep 1; done; exit 0' } vm_wait_for_ssh() { @@ -251,9 +294,11 @@ wait_for_listener() # for tcp protocol additionally check the socket state [ "${protocol}" = "tcp" ] && pattern="${pattern}0A" + for i in $(seq "${max_intervals}"); do - if awk '{print $2" "$4}' /proc/net/"${protocol}"* | \ - grep -q "${pattern}"; then + if awk -v pattern="${pattern}" \ + 'BEGIN {rc=1} $2" "$4 ~ pattern {rc=0} END {exit rc}' \ + /proc/net/"${protocol}"*; then break fi sleep "${interval}" @@ -270,113 +315,196 @@ EOF } host_wait_for_listener() { - wait_for_listener "${TEST_HOST_PORT_LISTENER}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" + local port=$1 + + wait_for_listener "${port}" "${WAIT_PERIOD}" "${WAIT_PERIOD_MAX}" } -__log_stdin() { - cat | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +vm_vsock_test() { + local host=$1 + local cid=$2 + local port=$3 + local rc + + # log output and use pipefail to respect vsock_test errors + set -o pipefail + if [[ "${host}" != server ]]; then + vm_ssh -- "${VSOCK_TEST}" \ + --mode=client \ + --control-host="${host}" \ + --peer-cid="${cid}" \ + --control-port="${port}" \ + 2>&1 | log_guest + rc=$? + else + vm_ssh -- "${VSOCK_TEST}" \ + --mode=server \ + --peer-cid="${cid}" \ + --control-port="${port}" \ + 2>&1 | log_guest & + rc=$? + + if [[ $rc -ne 0 ]]; then + set +o pipefail + return $rc + fi + + vm_wait_for_listener "${port}" + rc=$? + fi + set +o pipefail + + return $rc } -__log_args() { - echo "$*" | awk '{ printf "%s:\t%s\n","'"${prefix}"'", $0 }' +host_vsock_test() { + local host=$1 + local cid=$2 + local port=$3 + local rc + + # log output and use pipefail to respect vsock_test errors + set -o pipefail + if [[ "${host}" != server ]]; then + ${VSOCK_TEST} \ + --mode=client \ + --peer-cid="${cid}" \ + --control-host="${host}" \ + --control-port="${port}" 2>&1 | log_host + rc=$? + else + ${VSOCK_TEST} \ + --mode=server \ + --peer-cid="${cid}" \ + --control-port="${port}" 2>&1 | log_host & + rc=$? + + if [[ $rc -ne 0 ]]; then + set +o pipefail + return $rc + fi + + host_wait_for_listener "${port}" + rc=$? + fi + set +o pipefail + + return $rc } log() { - local prefix="$1" + local redirect + local prefix - shift - local redirect= if [[ ${VERBOSE} -eq 0 ]]; then redirect=/dev/null else redirect=/dev/stdout fi + prefix="${LOG_PREFIX:-}" + if [[ "$#" -eq 0 ]]; then - __log_stdin | tee -a "${LOG}" > ${redirect} + if [[ -n "${prefix}" ]]; then + awk -v prefix="${prefix}" '{printf "%s: %s\n", prefix, $0}' + else + cat + fi else - __log_args "$@" | tee -a "${LOG}" > ${redirect} - fi -} - -log_setup() { - log "setup" "$@" + if [[ -n "${prefix}" ]]; then + echo "${prefix}: " "$@" + else + echo "$@" + fi + fi | tee -a "${LOG}" > "${redirect}" } log_host() { - local testname=$1 - - shift - log "test:${testname}:host" "$@" + LOG_PREFIX=host log "$@" } log_guest() { - local testname=$1 - - shift - log "test:${testname}:guest" "$@" + LOG_PREFIX=guest log "$@" } test_vm_server_host_client() { - local testname="${FUNCNAME[0]#test_}" + if ! vm_vsock_test "server" 2 "${TEST_GUEST_PORT}"; then + return "${KSFT_FAIL}" + fi - vm_ssh -- "${VSOCK_TEST}" \ - --mode=server \ - --control-port="${TEST_GUEST_PORT}" \ - --peer-cid=2 \ - 2>&1 | log_guest "${testname}" & + if ! host_vsock_test "127.0.0.1" "${VSOCK_CID}" "${TEST_HOST_PORT}"; then + return "${KSFT_FAIL}" + fi - vm_wait_for_listener "${TEST_GUEST_PORT}" + return "${KSFT_PASS}" +} - ${VSOCK_TEST} \ - --mode=client \ - --control-host=127.0.0.1 \ - --peer-cid="${VSOCK_CID}" \ - --control-port="${TEST_HOST_PORT}" 2>&1 | log_host "${testname}" +test_vm_client_host_server() { + if ! host_vsock_test "server" "${VSOCK_CID}" "${TEST_HOST_PORT_LISTENER}"; then + return "${KSFT_FAIL}" + fi - return $? + if ! vm_vsock_test "10.0.2.2" 2 "${TEST_HOST_PORT_LISTENER}"; then + return "${KSFT_FAIL}" + fi + + return "${KSFT_PASS}" } -test_vm_client_host_server() { - local testname="${FUNCNAME[0]#test_}" +test_vm_loopback() { + local port=60000 # non-forwarded local port - ${VSOCK_TEST} \ - --mode "server" \ - --control-port "${TEST_HOST_PORT_LISTENER}" \ - --peer-cid "${VSOCK_CID}" 2>&1 | log_host "${testname}" & + vm_ssh -- modprobe vsock_loopback &> /dev/null || : - host_wait_for_listener + if ! vm_vsock_test "server" 1 "${port}"; then + return "${KSFT_FAIL}" + fi - vm_ssh -- "${VSOCK_TEST}" \ - --mode=client \ - --control-host=10.0.2.2 \ - --peer-cid=2 \ - --control-port="${TEST_HOST_PORT_LISTENER}" 2>&1 | log_guest "${testname}" + if ! vm_vsock_test "127.0.0.1" 1 "${port}"; then + return "${KSFT_FAIL}" + fi - return $? + return "${KSFT_PASS}" } -test_vm_loopback() { - local testname="${FUNCNAME[0]#test_}" - local port=60000 # non-forwarded local port +shared_vm_test() { + local tname + + tname="${1}" + + for testname in "${USE_SHARED_VM[@]}"; do + if [[ "${tname}" == "${testname}" ]]; then + return 0 + fi + done - vm_ssh -- "${VSOCK_TEST}" \ - --mode=server \ - --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest "${testname}" & + return 1 +} - vm_wait_for_listener "${port}" +shared_vm_tests_requested() { + for arg in "$@"; do + if shared_vm_test "${arg}"; then + return 0 + fi + done - vm_ssh -- "${VSOCK_TEST}" \ - --mode=client \ - --control-host="127.0.0.1" \ - --control-port="${port}" \ - --peer-cid=1 2>&1 | log_guest "${testname}" + return 1 +} - return $? +run_shared_vm_tests() { + local arg + + for arg in "$@"; do + if ! shared_vm_test "${arg}"; then + continue + fi + + run_shared_vm_test "${arg}" + check_result "$?" "${arg}" + done } -run_test() { +run_shared_vm_test() { local host_oops_cnt_before local host_warn_cnt_before local vm_oops_cnt_before @@ -399,31 +527,32 @@ run_test() { host_oops_cnt_after=$(dmesg | grep -i 'Oops' | wc -l) if [[ ${host_oops_cnt_after} -gt ${host_oops_cnt_before} ]]; then - echo "FAIL: kernel oops detected on host" | log_host "${name}" + echo "FAIL: kernel oops detected on host" | log_host rc=$KSFT_FAIL fi host_warn_cnt_after=$(dmesg --level=warn | grep -c -i 'vsock') if [[ ${host_warn_cnt_after} -gt ${host_warn_cnt_before} ]]; then - echo "FAIL: kernel warning detected on host" | log_host "${name}" + echo "FAIL: kernel warning detected on host" | log_host rc=$KSFT_FAIL fi vm_oops_cnt_after=$(vm_ssh -- dmesg | grep -i 'Oops' | wc -l) if [[ ${vm_oops_cnt_after} -gt ${vm_oops_cnt_before} ]]; then - echo "FAIL: kernel oops detected on vm" | log_host "${name}" + echo "FAIL: kernel oops detected on vm" | log_host rc=$KSFT_FAIL fi vm_warn_cnt_after=$(vm_ssh -- dmesg --level=warn | grep -c -i 'vsock') if [[ ${vm_warn_cnt_after} -gt ${vm_warn_cnt_before} ]]; then - echo "FAIL: kernel warning detected on vm" | log_host "${name}" + echo "FAIL: kernel warning detected on vm" | log_host rc=$KSFT_FAIL fi return "${rc}" } +BUILD=0 QEMU="qemu-system-$(uname -m)" while getopts :hvsq:b o @@ -452,30 +581,21 @@ handle_build echo "1..${#ARGS[@]}" -log_setup "Booting up VM" -vm_start -vm_wait_for_ssh -log_setup "VM booted up" - cnt_pass=0 cnt_fail=0 cnt_skip=0 cnt_total=0 -for arg in "${ARGS[@]}"; do - run_test "${arg}" - rc=$? - if [[ ${rc} -eq $KSFT_PASS ]]; then - cnt_pass=$(( cnt_pass + 1 )) - echo "ok ${cnt_total} ${arg}" - elif [[ ${rc} -eq $KSFT_SKIP ]]; then - cnt_skip=$(( cnt_skip + 1 )) - echo "ok ${cnt_total} ${arg} # SKIP" - elif [[ ${rc} -eq $KSFT_FAIL ]]; then - cnt_fail=$(( cnt_fail + 1 )) - echo "not ok ${cnt_total} ${arg} # exit=$rc" - fi - cnt_total=$(( cnt_total + 1 )) -done + +if shared_vm_tests_requested "${ARGS[@]}"; then + log_host "Booting up VM" + pidfile="$(create_pidfile)" + vm_start "${pidfile}" + vm_wait_for_ssh + log_host "VM booted up" + + run_shared_vm_tests "${ARGS[@]}" + terminate_pidfiles "${pidfile}" +fi echo "SUMMARY: PASS=${cnt_pass} SKIP=${cnt_skip} FAIL=${cnt_fail}" echo "Log: ${LOG}"